Harnessing Digital Technologies for Rural Industrial Integration: A Pathway to Sustainable Growth

Abstract

Data have become a virtual factor of production, and when integrated with the traditional factors of labor, capital, and land form digital labor, digital capital, and digital land, thereby generating a multiplier effect that contributes to the comprehensive revitalization of rural areas. This paper utilizes panel data from 30 provinces (autonomous regions and municipalities) in China from 2013 to 2023 and employs a double machine learning model to empirically test the impact mechanism of rural digitalization on the integration of rural industries. The results indicate that digital villages significantly promote the integrated development of rural industries through three direct pathways—digital industry development, digital information infrastructure, and digital service levels—with this conclusion remaining valid after a series of robustness tests. A mechanism analysis shows that digital villages facilitate the integration of rural industries through three indirect pathways—alleviating urban–rural factor mismatches, adjusting the agricultural–industrial structure, and promoting agricultural technological advancement—with this conclusion still valid after various robustness tests. The heterogeneity results show that there is significant variability in how digital villages promote the development of integrated rural industries, with the effects being more pronounced in major grain-producing and eastern regions compared to non-major grain-producing and central-western regions. Based on this, this paper proposes policy recommendations focused on accelerating digital village construction, formulating differentiated strategies, and alleviating factor mismatches, aiming to provide references for achieving rural revitalization. We mainly propose countermeasures and suggestions from three aspects: digital dividend, differentiation strategy, and element mismatch. Our main purpose in writing this article is to make up for the shortcomings of existing theories, enrich the theoretical system of digital rural construction, contribute Chinese solutions for digital rural construction around the world, and improve the word’s level of digital rural construction.

1. Introduction

Rural development programs frequently promote the expansion of food processing industries to enhance economic growth, create employment opportunities, and improve rural livelihoods. The agri-food chain, encompassing farming, processing, handling, and selling, is a significant component of the economy, particularly in rural areas [1]. The relationship between rural development and the agricultural food chain is close, and they are interdependent and mutually reinforcing The extension of the agricultural industry chain is an important component of rural development. The value chain of agricultural products includes multiple stages from seed cultivation, actual planting, and product processing to final product integration. Rural development can increase the added value of agricultural products, increase farmers’ income, and promote diversified development of the rural economy by extending the agricultural industry chain. The development of agricultural product processing industry has provided a large number of employment opportunities for rural areas, which is conducive to the local employment of rural labor, reducing the outflow of rural populations, and promoting rural stability and economic development. Furthermore, rural development initiatives often leverage tourism’s potential to diversify economies and stimulate economic growth by attracting visitors to rural areas, generating employment opportunities, and invigorating local economies [2]. Chinese scholars have provided ample evidence to demonstrate the integration of the agricultural food sector with tourism activities to promote demand for locally produced goods and services [3,4,5,6]. This integration can be achieved by showcasing distinctive regional food specialties and highlighting unique rural landscapes [7]. Through the integration of agriculture, culture, and tourism, with rural tourism as the main focus, we aim to promote the deep integration of tourism with agricultural resources, cultural resources, ecological resources, and other resources; improve the efficiency of resource utilization; and achieve organic integration and optimized allocation of resources. This will help guide traditional agriculture and agricultural product processing enterprises to extend their value chain, form a modern industrial system, and achieve structural adjustment and transformation upgrading of the agricultural, cultural, and tourism industries. The integrated development of the agricultural and cultural tourism industries can persuade a large number of villagers to return to their hometowns for employment and entrepreneurship, creating more employment opportunities and sources of income. For example, developing leisure agriculture can drive the development of related industries, such as catering, accommodation, and educational research, providing more employment opportunities for farmers and increasing their household income levels. The integrated development of agriculture and the cultural tourism industry helps to promote improvements in the rural environment. In the process of developing leisure tourism and rural tourism, improving and beautifying the rural environment, promoting the transformation of traditional villages, and improving the appearance of villages can help to improve the living environment and living conditions in rural areas.

Rural development has identified localized agri-food systems’ potential contribution and increased political relevancy. This context presents digital technologies as drivers for transforming agri-food systems [8]. Moreover, current studies have focused on the interrelationship between agri-food, tourism, and digitalization, stressing digital technologies as new tools for boosting local agri-food within local tourism and rural territories. On the other hand, according to various studies, digital technologies promote collaboration among actors in agri-food and food tourism enterprises [9]. Nonetheless, a model based on cooperation among partners has yet to be implemented that emphasizes the use of available information technology tools. This study seeks to fill this gap using this premise by defining a model for developing rural territories based on the agri-food chain and food tourism, with collaborative aspects among all stakeholders, enabled by digital technologies. The current study will add value to the literature by providing an in-depth understanding of how digital rural advancement can lead to rural industrial integration, thus enriching the theoretical system of digital village construction and providing Chinese solutions for use across the world [10].

This study has three main objectives. The first aim is to examine how digital technologies facilitate collaboration among players in the agri-food chain and the food and tourism industries. Thus, it analyzes the various ways that electronic tools and platforms can help streamline the flow of information, coordination, and joint value making [11]. This study seeks to determine how improved rural infrastructure, governance, and applications can improve the integration and quality of development in various rural industries. Through this clarification, this research enriches the theoretical foundations of digital rural construction and provide practice-based insights that policymakers can rely on when implementing their rural digital revitalization strategies in the future and within China’s current borders. It aimed to develop a conceptual model of cooperation based on digital technologies for comprehensive territorial development of the countryside [12]. The study explores how digital technologies can enhance cooperation among people and organizations in agri-food and food tourism. It aims to stimulate economic development and social progress in rural areas. The plan suggests leveraging digital tools to facilitate collaboration between the agri-food industry, tourism, and rural enterprises. The analysis indicates that rural enterprises must have digital infrastructures to integrate into the modern economy [13]. Furthermore, it discusses how innovation can address global challenges, including insights for using digital means to revive China’s hinterlands and in other parts of the world. In fact, these three goals are integrated and are sustainable paths for digital technology to promote rural industrial integration. Through big data, the Internet, e-commerce platforms, etc., digital technology can achieve a zero distance connection between consumers and producers of agricultural products; accelerate the production of agricultural products via market demand and local advantages; comprehensively open up the production end, circulation end, and consumer end of the agricultural industry chain; effectively extend the agricultural industry chain; and improve farmers’ share of income throughout the whole industry chain. Digital technology utilizes technologies such as digital perception, digital analysis, and digital control to embed into the agricultural industry chain, supply chain, and value chain, targeting people’s aspirations for a better life, vigorously developing the agricultural product processing industry, promoting the digitalization process of the industry, promoting the vertical extension of the agricultural industry, and providing technical support and risk avoidance for the deep integration of the primary, secondary, and tertiary industries. Digital technology utilizes agricultural big data and information platforms to fully tap into the cultural, ecological, and leisure values of agriculture in various regions; expand the boundaries of agricultural operations; promote the integration and development of agriculture with tourism, culture, education, and other industries; advance the deep expansion of functional agriculture, the sustained growth of creative agriculture, and the optimization and upgrading of leisure agriculture. The entire agricultural industry chain connects farmland and dining tables, serving as an intermediate between producers and consumers, as well as a comprehensive carrier for multiple links, such as production, processing, circulation, and consumption. Carrying out value tapping, optimizing benefit distribution, and achieving value enhancement throughout the entire industry chain have become direct demands for the green development of the entire agricultural industry chain.

Digital technology empowers the integration of the tertiary industry through the construction of digital infrastructure, industrial digitization, and digital industrialization [14]. The construction of digital infrastructure has liberated the temporal and spatial boundaries of traditional industries, improved the efficiency of production factor utilization, and enhanced the division of labor and specialization among rural industries [15]. New infrastructure in various fields, such as network communication, big data, cloud computing, blockchain, 5G, and the Internet of Things, has promoted the generation of knowledge spillover effects within industrial structures, thereby promoting the integration of the entire industry chain. The entry of new-generation digital technology into rural areas has given rise to new industries, formats, and business models, such as smart logistics, smart energy, smart e-commerce, and gig economy [16]. It has changed the production, distribution, exchange, and consumption relationships in rural areas, achieved by internal industrial upgrading, and accelerated the integration of tertiary industries. By integrating machine learning, deep learning, and other technologies, a recognition model can be constructed to achieve real-time monitoring and early warning of pests and diseases [17]. This application improves agricultural production efficiency and reduces labor costs and environmental impacts. Machine learning technology can provide intelligent agricultural machinery control solutions for agricultural enterprises, achieve automated operation and remote monitoring of agricultural machinery, and further enhance automation and intelligence in agricultural production [18]. By analyzing market demand data and consumption trends, machine learning models can predict the market demand for agricultural products, helping farmers and businesses adjust their production plans. Decision trees, random forests, and neural networks have significant effects on demand forecasting. China is accelerating the digital and intelligent transformation of infrastructure, including water conservancy, highways, electricity, cold chain logistics, and agricultural production and processing in rural areas, and promoting the construction of smart water conservancy, smart transportation, smart grid, smart agriculture, and smart logistics [19]. China plans to promote the deep integration of digital economy and agricultural rural economy through the development of smart agriculture [20]. This includes strengthening planning and layout, accelerating the construction of a new generation of rural information infrastructure, unleashing digital dividends, and cultivating and strengthening new driving forces for agricultural and rural development. China is generating big data on agricultural natural resources and utilizing data on rural land contract and management rights registration, permanent basic farmland delineation, etc., to establish a database of basic information on cultivated land, producing big data on basic land ownership, area, spatial distribution, quality, and planting types [21]. Overall, the main purpose of this article is to study the mechanism and path of the impact of digital rural construction on rural industrial integration. Research has found that digital villages significantly promote the integrated development of rural industries through the following three direct channels: digital industry development, digital information infrastructure, and digital service level. Digital villages promote rural industrial integration through the following three mechanisms: alleviating urban–rural factor mismatch, adjusting agricultural industry structure, and promoting agricultural technology progress.

2. Mechanisms of Digital Village Development: A Theoretical Overview

2.1. Basic Concept Definition and Scope

(1) Integrated development of rural industries. The integrated development of rural industries refers to the organic combination of agriculture, processing, sales, catering, leisure, and other service industries through the cross-border integration of capital, technology, and resources based on agriculture, breaking the isolation of agricultural production, processing, sales, and other links. This integration can extend the agricultural industry chain, expand industrial functions, form new industrial forms, increase employment opportunities for farmers, and increase income. Ultimately, a good industrial pattern will form with smooth links and harmonious coexistence among all parties involved. Specifically, the integrated development of rural industries includes the following aspects: extending the industrial chain, cross-border development toward upstream and downstream industries, enhancing the value chain, deep processing and refined management, and increasing added value. By sharing the benefit chain, farmers can share the value-added benefits of the industrial chain and achieve increased income for farmers; introduce modern new concepts, such as “Internet plus” into production and operation activities; and innovate production, operational, and resource utilization methods. Based on agriculture, with new agricultural management entities as the links and through the integration, penetration, and cross-restructuring of industries as the paths, we aim to extend the industrial chain, expand the scope of industries, and transform industrial functions; expand the multifunctionality of agriculture; cultivate new growth points in rural areas; and achieve the modernization of agriculture. Promoting the integrated development of the primary, secondary, and tertiary industries in rural areas is an important component of China’s urban–rural integration development, an important means to increase farmers’ income, and an objective requirement for achieving sustainable rural development.

(2) Digital countryside. Digital countryside refers to the endogenous modernization and transformation process of agriculture and rural areas, which is accompanied by the application of networking, informatization, and digitization in the economic and social development of agriculture and rural areas, as well as improvement in farmers’ modern information skills. It is not only a strategic direction for rural revitalization but also an important part of building a digital China. The connotations of digital village include the following aspects: the construction and application of information infrastructure, such as the Internet, Internet of Things, and information terminal equipment in rural areas, and promotes the comprehensive and deep integration of information technology and rural production and life. Digital countryside is a process of modernization and transformation in agriculture and rural areas. It promotes informatization construction in various fields such as rural economy, politics, culture, society, ecological civilization, and party building by improving farmers’ modern information skills. Digital countryside is an important means to achieve rural revitalization. By exploring the enormous potential of informatization in rural revitalization, it promotes the comprehensive upgrading of agriculture, progress in rural areas, and development of farmers. Digital countryside is an important component of building a digital China, and it involves various aspects such as rural information infrastructure construction, rural digital economy, technological innovation supply, smart green countryside, rural governance, online poverty alleviation, and urban–rural information integration. The digital countryside also emphasizes the integrated development of urban and rural informatization, guiding the flow of urban network, information, technology, and talent resources to rural areas and promoting the rational allocation of urban and rural factors. Digital rural areas empower rural areas through information technology; promotion of systematic processes in departmental coordination, organizational integration, and rural spatial reconstruction; and enhances rural governance efficiency and farmers’ quality of life. The construction of the digital countryside is an ecological system that involves multi-party participation, complementary advantages, and integrated development, involving multiple entities, such as government, enterprises, and social organizations, to jointly promote rural construction.

(3) Data governance technology. Data governance technology refers to the collection of management activities throughout the entire lifecycle of data within a certain organizational scope, relying on institutional regulations, standard specifications, application practices, and supporting technologies. These activities include data ownership, quality management, security control, privacy protection, open sharing, transaction circulation, and analytical processing. Its core goal is to improve the availability, security, and circulation of data; activate the value of data resources; and unleash the economic and social benefits of data resources. Data governance technology involves a set of management practices for data collection, processing, and application aimed at improving data quality, achieving widespread data sharing, and, ultimately, maximizing data value. With the popularization of information technology, data governance technology needs to address the challenge of the exponential growth in human generated data and utilize new methods to manage massive amounts of data. Data governance technology also includes specific analyses of data specifications, data cleaning, data exchange, and data integration, and it involves the maturity of data governance and the design of data governance frameworks. It not only focuses on the technical aspects of data but also includes decision making, supervision, and coordination at the organizational level via data quality, data consistency, data security, data privacy, and data compliance.

2.2. Harnessing Digital Power: How Digital Villages Drive Industrial Integration

Digital villages result from the modernization and transformation of agriculture and rural areas in line with the advent of networks, informatization, and digitalization, as well as contemporary villagers’ increase in digital skills and literacy [22]. The building of digital villages can stimulate and enable the immense potential of the multiplier effects of digital economies to drive rural rejuvenation. These transform the countryside into modernized agricultural centers through modern information networks and digital technology that have data integrated into the classical factors of production for optimizing resource allocation, enhancing productivity, and revitalizing rural industries [23]. This research examines how development in a digital village affects integration among rural industries from the following three essential aspects: range in scale of a rural area’s digital economy, its digital information infrastructure, and the level of its digital public services together with applications [24]. This study explains these mechanisms, enriching the theoretical basis for the construction of a new digital countryside while providing valuable suggestions for implementing Chinese practices in digitizing rural revivalism.

The reasons for choosing digital industries, digital infrastructure, and digital services are presented below.

The deep integration of the digitization and modernization of agricultural technology is an important driver of rural industrial revitalization. Digitization runs through the seed source, variety innovation, and industrial integration of the seed industry, providing new impetus for the digitization of rural industries. Through a seed industry big data platform, we can achieve the comprehensive modernization and self-reliance of seed industry technology, including variety selection and promotion of high-quality seeds, and consolidate the foundation of food security. Digital cultural tourism leads to the integration of industries with data elements, improving the single-industry structure of rural areas dominated by agriculture, utilizing technology to digitally integrate, develop, and present IP resources, such as characteristic culture, folk skills, historical relics, and pastoral scenery, in rural areas, making digitization a new carrier for the presentation and output of rural culture. This promotes the digital and intelligent transformation of infrastructure, such as for water conservancy, highways, electricity, cold chain logistics, and agricultural production and processing in rural areas, and advance the construction of smart water conservancy, smart transportation, smart grid, smart agriculture, and smart logistics. It consolidates the foundation of digital agriculture, improving the “one map” of a natural resource remote sensing monitoring and supervision platform, as well as the implementation of dynamic monitoring of permanent basic farmland. It promotes the construction of agricultural and rural big data centers and development of big data on important agricultural products for the entire industrial chain, as well as the integration and sharing of basic data in agricultural and rural areas. The integration of digital technologies, such as the Internet and e-commerce platforms, with traditional industries can improve industrial efficiency in production, operations, and sales, realizing the structural upgrading of traditional industries and improving the level of industrial digitalization. The digital economy has demonstrated diverse models for promoting the integration of primary, secondary, and tertiary industries in rural areas. Rural e-commerce is booming, resulting in fast-track pathways for agricultural products to move from the field to the dining table. This not only expands sales for agricultural product processing industries but also attracts tourists to experience rural life, driving rural tourism. The digital economy optimizes the allocation of rural industrial factors through Internet platforms. In terms of funding, online financial platforms have broken the limitations of time and space, allowing funds to flow quickly and accurately to rural industries. In terms of talent, online recruitment and training platforms have attracted talent inflows and effectively improved their digital skills. Land is being efficiently transferred through digital platforms.

2.2.1. Digital Industries: Pioneering the Future of Rural Economies

Deepening supply-side structural reform, promoting rural–industrial integration, and developing digital industries are the only options, and will contribute significantly to the building of digital villages in China [25]. To accelerate the digitization and intelligent production processes in rural sectors and the creation of new digital industries and business models at large, data, as a novel factor in production, are usually multiplied in their degree of utilization with their merging with labor, capital, and land [26]. More specifically, the use of the Internet can be popularized among individuals engaged in agriculture so that, in general, their social networks expand, but also so they can use it for specific economic purposes. Accurately matching market demand and supply through the integration of traditional rural sectors and digital technology makes the flow between urban and rural areas easier, which will encourage younger generations of farmers to adopt digital agricultural business strategies and create e-commerce and other businesses for farmers [27]. By applying digital technology to the supply or sale of agricultural products, who supplies what, as well as customer needs, will become more visible. It plays a role in uniting upstream/downstream participants, including producers, customers, and sales organizations from various related industries, thereby increasing revenue for farmers and promoting innovation/entrepreneurship among both enterprises involved in agriculture and households engaged in related activities, creating conditions under which better interconnections among other value chains can take place [28].

2.2.2. Building the Backbone: The Role of Digital Infrastructure

A central IT infrastructure can be likened to a highway, serving as the lifeblood of economic growth, enabling the swift and efficient movement of information and resources from one location to another. The development of new forms of digital infrastructure, such as 5G base stations and fiber optic networks, has positive externalities that help address gaps in essential public services between urban and rural areas [29]. Rural information facilities have broken down barriers to accessing information for farmers, thus bridging the first-level of the digital divide and increasing the possibilities of introducing digital technology to sectors and empowering farmers [30,31,32]. Conversely, if new-generation digital techniques are incorporated into traditional rural infrastructure that link up with farming and breeding activities, this will boost farmers’ inclinations to use digital technologies. This improves precision and mass production, moving factors across industries, reducing cross-industry transaction costs, and driving the integrated production, processing, and sales industry chains. Upgrading digital information infrastructure facilitates increased productions of scale in agriculture, which results in reliable supply sources for raw materials. Agricultural processing enterprises usually decide to build their factories near farms because it is more cost-effective than transporting goods from remote locations, minimizing logistics expenses and crop losses to encourage the integration of primary and secondary sector activities, thereby giving rise to new industrial integration business models pioneered by agro-processing industries [33,34,35].

2.2.3. Digital Services: Accelerating Sectoral Integration

The speed at which digital services are developed acts as a critical accelerator of rural industrial mergers, and its advancement can hasten the integration of primary, secondary, and tertiary sectors in rural areas. On another level, the use of digital foundation software by farmers may enhance technology and data information sharing, leading to the full utilization of technological empowerment and knowledge spillover effects in the digital economy. This will also assist in building up farmers’ digital literacy and ability to extract more helpful information for use in transforming aging into a demographic dividend, addressing the “second-level” digital divide. Conversely, embedding digital services within agriculture can promote an alternative way of rendering traditional service models for agri-businesses, including farming, forestry, animal husbandry, and fishery. On the production side, through intelligent agriculture, digital agriculture, and other means, precise control over farming and breeding growth data can be achieved, providing intelligent services at every stage [36]. On the sales side, the perfection of agricultural product e-commerce transaction platforms and logistics distribution systems helps to improve the online sale and distribution of farm products, gradually extending the industrial chain and forming digital-core-based agricultural product storage, packaging, cold chain distribution, and other sales service systems. Moreover, various types of information on rural characteristics, such as culture and natural landscapes, can be transmitted to urban residents through integrated media, live broadcasting platforms, online audio–visual programs, and other channels, encouraging urban residents to visit the countryside to engage in consumption, thereby driving the development of the agricultural, cultural, and tourism industries [37].

The relationship between the food chain and rural industrial integration is multifaceted. According to research, a food-chain research system on “soil crop livestock family environment” was constructed, and it was found that the flow of nutrients from “soil crop livestock” to “family” is pyramid shaped, which determines the productivity, nutrient efficiency, and environmental effects of the system. This indicates that rural industrial integration needs to consider nutrient flow and resource management throughout the entire food chain to improve resource utilization efficiency and reduce environmental pollution. The study of the food chain emphasizes the importance of green development in agriculture, which means ensuring food security while achieving efficient use of resources and environmental friendliness. The integration of rural industries requires the integration of this concept into various aspects of agricultural production, processing, and circulation in order to promote the transformation of agriculture in a green and sustainable direction. Expanding food sources and enriching supply categories, extending the agricultural industry chain, and enhancing the value chain are keys to enhancing agricultural competitiveness. Through various means, such as technology, management, and marketing, we aim to enhance the added value of products, increase brand awareness, and establish partnerships to promote the integrated development of the primary, secondary, and tertiary industries, as well as promote the construction of the entire industry chain, enhance the value chain of food development, including improving the level of food processing and the circulation industry, promoting the agglomeration development of the food industry, fully developing various functions of agriculture, extending the food industry chain, improving the value chain, and building the supply chain.

Based on the above analysis, this paper proposes the following hypothesis:

Hypothesis 1:

Digital technology’s development directly enhances rural industries’ integrated growth.

2.3. Optimizing Resources: Digital Villages and Efficient Resource Allocation

Classic endogenous growth theory suggests that industrial development benefits from improved labor productivity and investment in factors like land and capital. Given that these factors are limited or that their input levels can impact production efficiency, the efficient and rational allocation of limited resources is crucial for industrial development [38,39]. Digital village building can enable remote sensing imagery, photography, and large rural databases to access and manage rural natural resources, attaining remote understanding and monitoring. To facilitate momentum in the endogenous development of villages, the protection of bare farmland serves to aid governmental departments in rural land planning and construction and in addressing unclear land property rights and fragmentation issues, such as planning for modern agricultural–industrial park land use or transportation infrastructure, thereby enhancing momentum in the endogenous development of villages [40].

From a capital perspective, constructing a digital countryside can promote the flow of urban–rural elements, breaking through temporal and spatial constraints and connecting investors with rural projects via the same digital information platforms. This is possible using information on matches in the market supply and demand, which in turn helps to enhance investment precision and marginal advantages and enables rural industries to access finance and expand in scale, which are essential for promoting their transformation, upgrading, and integration [41,42]. Modern technologies like artificial intelligence have resulted in notable decreases in job positions in labor-intensive sectors and, thus, surplus labor between urban areas and the countryside if we consider it from the perspective of labor [43]. By constructing digital villages, cities can facilitate the free flow of network information among them, thereby enriching employment channels and information, thus widening both the breadth and depth of employment choices, resulting in greater matching precision, and absorbing a more significant amount of the rural labor force that has been affected by the transition in addition to the urban labor surplus. By optimizing land resource allocation through digital village construction, this study posits that the integrated development of rural industries can be achieved effectively to contribute to the high-quality development of the rural economy [44]. Based on the above analysis, this paper proposes the hypothesis:

Hypothesis 2:

The development of digital villages facilitates the integration of rural industries by addressing the mismatch between urban and rural elements.

Digital village construction is the digital transformation that has closed the gap between urban and rural areas and traditional market boundaries. This has also accelerated urban–rural linkages, promoted industrial cooperation, and facilitated resource sharing. Moreover, digital village construction complements or substitutes industries, strengthening the “clustering effect”, which helps rationalize an agricultural industrial structure. Additionally, building digital villages attracts high-end digital technology industries to settle and cluster in rural areas, thus speeding up the coordinated development of digital industrialization and industrialization in general. It achieves this by facilitating the conversion of traditional farming enterprises and accelerating the modernization of agriculture’s industrial structure [45]. Industrial structural adjustments initiate the clustering of businesses within rural areas, establishing a conducive environment that enhances collaboration among different sectors, and the sharing of resource innovation through digital village development lays the foundation for an integrated and sustainable rural economy. The networking among related trades creates synergies, thereby aiding in the creation of new value through joint operations. Because of this clustering effect, additional industries and skilled labor may be attracted to such areas, further enhancing their economic potential [46]. Based on the analysis above, this paper proposes the following hypothesis:

Hypothesis 3:

The construction of digital rural areas indirectly fosters the integration and growth of rural industries by facilitating adjustments in the industrial structure.

Technological progress and institutional changes are the drivers of rural industrial integration; thus, agricultural technological progress is critical for promoting rural industrial integration. The digital countryside construction is a particular form and the result of a digital economy based on the empowerment of rural areas, agriculture, and farmers. On the one hand, rural industrialization can be accelerated by constructing digital villages, because they provide suitable environments for agricultural science research, increasing technological growth in agriculture, blurring industry boundaries, and promoting rural industrial integration [47,48]. Conversely, digital village construction introduces more advanced forms of digital technology applications into China’s rural industries, enhancing productivity and altering production relationships in rural industries [49]. This may combine crop farming with animal husbandry to form an integrated development model that raises the added value of agricultural products while speeding up the establishment of farm-stay agritourism and agricultural processing bases. Digital village construction plays a central role in this process by improving the environments in which these industries operate and changing their productive structures using these technologies, thereby facilitating high-quality development and integration in modern China’s agrarian sector. Based on the analysis above, this paper proposes the following hypothesis:

Hypothesis 4:

The development of digital villages enhances the integration of rural industries by advancing agricultural technology.

Figure 1 depicts the “Theoretical Model of the Impact Mechanism of Digital Technique on Rural Industrial Integration”, which shows how digital technology affects rural industrial integration. The model highlights various direct and mechanistic impacts. This connects the scope of the digital industry with the integration of rural industries through positive influence as it expands. However, low digital service levels hurt such integration, implying that a lack of a good internet connection in the country can impede convergence among these places. Mechanistic effects are also suggested by this model, where changes in the industrial structure are influenced by the digital infrastructure, and, therefore, improvements in this type of infrastructure cause the adjustment of rural industrial structures. Subsequently, adjustments along this vein positively affect the interconnectedness among the rural trades, increasing their degree of interrelation. Again, digital infrastructure closes the urban–rural divide and reduces discrepancies between two types of regions to achieve a better institutional fit. Additionally, this mismatch reduction fosters further amalgamation processes within rural sectors.

3. Methodological Approach: Examining the Impact of Digital Villages

3.1. Advanced Econometrics: Double Machine Learning Model

3.1.1. Double Machine Learning Model

Previous research has mainly employed conventional causal inference models to examine these issues. However, these models are faced with challenges such as the “curse of dimensionality” and multicollinearity problems when controlling for high-dimensional covariates, leading to low estimate accuracy [50]. The relationship between digital village construction and industrial development may not always be linear, involving complex non-linear relationships. In order to overcome these methodological limitations, a double machine learning model will be used in this study, since it can automatically filter high-dimensional control variables so that a more accurate set of influential controls can be obtained and also because it has strengths in dealing with non-linearity issues [51]. It is anticipated that this advanced econometric technique will provide more compelling and nuanced results in examining the effects of digital village construction on rural industrial integration than those obtained by some existing studies. The aim is also to employ double machine learning’s advantages in explicating the specific causal mechanisms through which rural areas’ digitization enhances the quality-based integration and growth paths within diverse rural industries [52].

The setup for the double machine learning model in partial linear regression is as follows:

$$IC{L_i}_t={\alpha }_{1}DR{L}_{it}+{\alpha }_{2}Control{s}_{it}+{\lambda }_t+{\mu }_i+{\epsilon }_{it}$$

(1)

$$E\left(IC{L_i}_j|DR{L}_{it},Control{s}_{it}\right)=0$$

(2)

In the model, $“IC{L}_{it}$” represents the level of rural industrial integration in region $\mathrm{“}i$” in year $“t\mathrm{”}$, and $\mathrm{“}DR{L}_{it}\mathrm{”}$ represents the level of digital village development in region $“i\mathrm{”}$ in year $“t\mathrm{”}$, with “α₁” being the treatment coefficient of primary focus. $“Control{s}_{it}”$ denotes the collection of high-dimensional control variables, with the addition of the year-specific fixed effects, $“{\lambda }_t\mathrm{”},$ and the province-specific fixed effects, $“{\mu }_i\mathrm{”}$, with $“{\epsilon }_{it}\mathrm{”}$ as the random error term, under the condition that the expectation is constrained to 0. Further, following the methodology, models (1) and (2) are estimated to obtain the treatment coefficient estimates; based on these estimates, the estimation bias is further examined to obtain unbiased treatment coefficient estimates.

Specific information about bidirectional machine learning is provided as follows:

(1) The setup of a bidirectional machine learning model involves multiple steps, mainly including data preparation, model architecture design, training configuration, and model evaluation. For the data preparation, firstly, you need to collect data that are suitable for your task. For time series prediction and natural language processing tasks, data typically appear in the form of sequences. Secondly, it is necessary to remove noise and irrelevant information, such as stop words in text and outliers in time series. Scaling the data to the same scale accelerates the training speed and improves the model’s performance. For text data, the words or characters are converted into numerical representations, such as word embeddings. The data is divided into sequences, each containing data points within a certain time window. For the model architecture design, the appropriate bidirectional model is chosen for different tasks. In natural language processing, bidirectional recurrent neural networks are commonly used, which combine long short-term memory networks or gated recurrent units. The input layer is defined based on the number of features in the data. The RNN layer is wrapped with a bidirectional wrapper to create a bidirectional model, and how to merge information from two directions is defined, commonly using concatenation and summation. Additionally, fully connected or dense layers are added as needed. According to the task definition, output layers are used, such as the softmax layer for classification tasks and the linear layer for regression tasks. For the training configuration, the appropriate loss function and optimizer are chosen. Setting the batch size and iteration times can affect the training efficiency and effectiveness of the model. The use of callback functions, such as early stop and model checkpoint, prevent overfitting and save the best model. For the model’s evaluation, the dataset is divided into a training set, validation set, and testing set to evaluate the model’s generalization ability. The appropriate evaluation metrics are selected based on the task, such as accuracy, recall, F1 score, AUC, etc. Cross-validation is used to evaluate the stability and reliability of the model. For the model’s optimization, the hyperparameters are adjusted, such as the learning rate, number of layers, and number of cells, through grid search or random search methods. Based on the performance of the model on the validation set, it may be necessary to return and adjust the feature engineering steps to improve the model’s performance.

(2) The basic principle of bidirectional machine learning models is the use of the contextual information in the data to improve the predictive or comprehension ability of the model. This model is particularly suitable for processing sequential data, such as time series and natural language text, for which the order and position of the elements are important. The following are several core principles of bidirectional machine learning models: firstly, the core of bidirectional machine learning models is to simultaneously consider the forward and backward (past) information in the data. In natural language processing, this means that the model considers not only the words before a word but also the words after it. In time series analysis, the model considers both past and future data points simultaneously. Secondly, in deep learning, recurrent neural networks are the foundation for achieving bidirectional information processing. An RNN memorizes previous information by updating the hidden state at each time step. In a bidirectional RNN, there are two RNN layers, as follows: one handles forward sequences and the other handles reverse sequences. Thirdly, with information merging, in a BiRNN, the information from both directions needs to be merged for the final prediction. The merging method can be simple summation, concatenation, or other more complex fusion methods. This merging allows the model to utilize both forward and backward contextual information when making decisions. Fourthly, in order to solve the problems of gradient vanishing and exploding in traditional RNNs, an LSTM or GRU is usually used as the basic unit of a BiRNN. These structures control the flow of information through gating mechanisms to better handle long sequence data. Fifth, in some applications such as machine translation or text summarization, bidirectional machine learning models can adopt a sequence-to-sequence architecture. In this architecture, one BiRNN encoder processes the input sequence, while another RNN decoder generates the output sequence. This model can generate output by utilizing the complete contextual information of the input sequence.

(3) Although bidirectional machine learning models perform well in many aspects, they also have some limitations and challenges. Firstly, because of the need to run two RNN branches simultaneously (forward and reverse), the computational complexity and memory consumption of bidirectional machine learning models are about twice that of unidirectional models. This is particularly challenging for large-scale datasets and long sequence data, as they require more computing resources and time. Secondly, the application of bidirectional models is limited for data that require real-time or streaming processing, as future data are often unavailable in practical applications. This means that when predicting the next time point, the model cannot utilize future information, which may lead to a decrease in the accuracy of the model in practical applications. Because of the large number of parameters in bidirectional models, especially when dealing with small datasets, overfitting is prone to occur, and regularization techniques need to be adopted to avoid it. Thirdly, machine learning algorithms typically make predictions based on correlations among the data, but they may not be able to uncover potential causal relationships among the data. In scenarios in which causal relationships need to be determined, this may limit the predictive ability of the model. Fourthly, machine learning models, especially complex ones, are often considered “black boxes” because they do not provide transparency in how decisions are made. This may be a problem in scenarios that require model interpretability, such as medical diagnosis or financial risk assessment.

3.1.2. Ranking the Factors: Entropy-Weighted TOPSIS Model

The entropy-weighted TOPSIS model combines traditional TOPSIS and information entropy. To avoid subjective factors affecting the determination of the index weight in the analysis, the entropy weight method is adopted in the TOPSIS model [53]. This is accomplished through the use of enhanced objectivity in the evaluation results. However, it must be acknowledged that this is not the sole benefit; these methods also offer more scientifically objective approaches to ranking. The entropy-weighted TOPSIS model approximates the ideal solution and does not impose strict sample data requirements. It mainly applies to multi-criteria and multi-alternative decision-making systems, where multiple decisions must be made [54]. By building and calculating Euclidean distances between positive and negative ideal solutions, this model allows for rating units’ superiorities or inferiorities (better or worse than SFA or DEA). This helps provide a complete systematic framework for evaluating complex choices while ensuring only the best possible solution is identified. The main calculation steps in the TOPSIS model with entropy weight are as follows:

Construction of a decision matrix: The evaluation involves m participating units, and there are evaluation indicators for each unit. The structural decision matrix is as follows:

$$X=\left({x_i}_j{)}_{m\times n}\right(i=\mathrm{1,2},...,m;j=\mathrm{1,2},...,n)$$

(3)

Construction of a dimensionless decision matrix: The indicators are normalized, with the positive and negative indicators treated differently. The normalization formulas are as follows:

$${x_i}_j={\displaystyle \frac{{x_i}_j-\mathit{min}(x_j)}{max(x_j)-\mathit{min}(x_j)}}(+)$$

$${x_i}_j={\displaystyle \frac{max(x_j)-{x_i}_j}{max(x_j)-\mathit{min}(x_j)}}(-)$$

(4)

Calculation of the information entropy of the indicator, as follows:

$$e_j=-{\displaystyle \frac{1}{\mathit{ln}(m)}}{\sum }_{i=1}^m{p}_{ij}\mathit{ln}(p_{ij});p_{ij}={\displaystyle \frac{{x_i}_j}{{\sum }_{i=1}^m{x_i}_j}}$$

(5)

Calculation of the index entropy weight, as follows:

$$w_j=-{\displaystyle \frac{1-e_j}{{\sum }_{j=1}^n(1-e_j)}};w_j\in \left[\mathrm{0,1}\right],{\sum }_{j=1}^n{w}_j=1$$

(6)

Calculation of the weight matrix, as follows:

$$R=(r_{ij}{)}_{m\times n},r_{ij}=w_j{x}_{ij}$$

(7)

Calculation of the optimal solution and the worst solution, as follows:

$$S_j^{+}=\mathit{max}(r_{1j},r_{2j},\cdots ,r_{nj}),S_j^{-}=\mathit{min}(r_{1j},r_{2j},\cdots ,r_{nj})$$

(8)

Calculation of the distance between each unit and the positive and negative ideal solutions using Euclidean distance, as follows:

$$S{d}_i^{+}=\sqrt{{\sum }_{j=1}^n(S_j^{+}-r_{ij}{)}^2};S{d}_i^{-}=\sqrt{{\sum }_{j=1}^n(S_j^{-}-r_{ij}{)}^2}$$

(9)

Calculation of the relative progress of each unit, as follows:

$$C_i={\displaystyle \frac{S{d}_i^{+}}{S{d}_i^{+}+S{d}_i^{-}}},C_i\in \left[\mathrm{0,1}\right]$$

(10)

3.2. Key Indicators: Measuring Rural Industrial Integration

3.2.1. Measuring Rural Industrial Integration: Core Metrics

The variable explained in this study is rural industrial integration. The development of rural industrial fusion is characterized by dynamism and complexity, and, at present, no unified measurement index system has been developed by the academic community [55]. Therefore, based on discussions of rural industrial integration in the No.1 Central Document from 2015 to 2023 and existing research, the article constructs a comprehensive index system from the connotation of rural industrial fusion development. From the perspective of integration between agriculture and industrial chains, it mainly relies on advanced technology empowerment to increase the added value of agricultural products, with the agricultural processing industry as a typical representative [56]. Considering that currently China is vigorously developing modern facility agriculture, it is included as one of the measurement indicators, along with the proportion of the primary industry, to jointly measure the degree of industrial chain extension. In addition, the proportion of employment in the secondary industry is incorporated into the index system [57].

From the perspective of integration between the agriculture and service sectors, when the service sector empowers agriculture, it provides services for the entire agricultural industry chain, mainly represented by the agriculture, forestry, animal husbandry, and fishery service industries. When agriculture empowers the service industry by leveraging its ecological and cultural functions integrated with the service industry, it cultivates new business forms represented by leisure agriculture, thereby increasing the proportion of non-agricultural employment. From the perspective of integration between agriculture and emerging industries, rural industrial integration originates from technological progress and impacts the agricultural sector. Therefore, this article measures it using the degree of farm mechanization and agricultural labor productivity [58]. The study provides a multidimensional and holistic approach to measuring rural industrial integration by constructing a comprehensive index system from these three aspects. The index system comprises the principal points of interaction between agriculture and other sectors and technical progress in promoting industrial linkage. The entropy method is employed to objectively compute the weights of each indicator to make a precise and dependable assessment of rural industrial integration [59].

Table 1. Rural industrial integration index system.

Primary Indicator	Secondary Indicator	Measurement Formula
Integration between Agriculture and Industrial Chains	Proportion of Primary Industry in Total Output	Value added by the Primary Industry/Regional GDP
	Per Capita Output Value of Agro-Processing Industry	Total Output Value of Agro-Processing Industry above Designated Size/Rural Population
	Proportion of Non-Agricultural Employment in Villages	Number of People Employed in the Secondary Industry in Villages/Total Number of People Employed in Villages
Integration between Agriculture and the Service Industry	Per Capita Output Value of Agriculture, Forestry, Animal Husbandry, and Fishery Services	Output Value of Agriculture, Forestry, Animal Husbandry, and Fishery Services/Rural Population
	Development of Leisure Agriculture	Annual Revenue from Leisure Agriculture/Total Output Value of the Primary Industry
Integration between Agriculture and Emerging Industries	Proportion of Facility Agriculture Area	Total Area of Facility Agriculture/Total Arable Land Area
	Degree of Agricultural Mechanization	Total Power of Agricultural Machinery/Total Arable Land Area
	Agricultural Labor Productivity	Total Output Value of the Primary

presents the Rural Industrial Integration Index system, which judges the amalgamation of the agricultural sector with the industrial, service, and emergent industries. It measures the degree to which agriculture is being integrated into industrial chains by examining how much value primary industry contributes to the regional GDP in the total output measured. It also looks at per capita output values for agro-processing industries above a particular size divided by the total population. The ratio of non-agricultural employment in villages to secondary employment within villages is expressed as the number of those working in the secondary sector over those employed in villages. Regarding integration between the agricultural and service sectors, it analyses per capita output from agricultural-related services, such as forestry, animal husbandry, and fisheries and leisure agricultural development, measured by annual revenue from leisure agriculture over the primary industry’s total output. Also, for emerging industries’ integration, it examines facility agriculture’s share of acreage of total arable land; level of agricultural mechanization measured using power utilization density, that is, the agricultural machinery capacity of land under cultivation; and, lastly, agricultural labor productivity, although the complete formula for this metric is missing on the table. These indicators collectively provide a comprehensive framework to analyze how well-integrated agriculture is with other sectors to promote rural industrial development.

3.2.2. Digital Village Development: Key Indicators and Measures

The explanatory variable of this study is digital village construction. Based on the “Digital Village Construction Guide 2.0” and other relevant policy documents, as well as existing literature, this paper constructs a comprehensive set of indicators to measure digital village construction from an input–output perspective [60]. These indicators concern the following three dimensions of focus: development of digital industries, digital information infrastructure, and digital service level. In rural areas, where land resources are relatively fixed and unchangeable, this paper primarily takes into account the following three inputs to construct a digital village: infrastructure (hardware and software), capital, and labor. The output indicator is the developmental status of digital industries that show how much the traditional rural industries have transformed through integration with digital technologies.

Table 2. Digital village development evaluation indicators.

Primary Indicator	Secondary Indicator	Measurement Formula
Digital Industry Development	Digital Bases	Proportion of Taobao villages among all Administrative Villages
	Digital Transaction Level	E-Commerce Sales and Purchase Volumes
	Online Payment Level	Rural Inclusive Finance Digital Index
Digital Information Infrastructure	Smartphone Penetration Rate	Number of Mobile Phones per Million Households at Year End in Rural Areas
	Internet Penetration Rate	Number of Rural Internet Broadband Access Users
	Agricultural Meteorological Stations	Rural Meteorological Observation Services
Digital Service Level	Scope of Services Using IoT and Other Information Technologies	Rural Delivery Routes
	Digital Talent Service Teams	Agricultural Technical Personnel
	Level of Digital Service Consumption	Per Capita Transportation and Communication Expenditure of Rural Households

introduces the digital village development evaluation indicators, which measure the development progress of a digital village through the following three key indicators: digital industry development, digital information infrastructure, and digital service level. For Taobao villages, among all administrative villages with respect to their proportion, this is one of the ways that digital bases can be measured, thus reflecting the presence of electronic business. On the other hand, e-commerce sales and purchase volumes determine the digital transaction level, while the rural inclusive finance digital index indicates online payment. Smartphone penetration represents the number of mobile phones per million households in rural areas, and internet penetration refers to the number of users accessing rural broadband internet. The rural meteorological observation services are assessed by examining the availability of agricultural meteorological stations. Rural delivery routes show how much IoT and other information technologies have been used in providing services, while the presence of agricultural meteorological stations is indicated by rural meteorological observation services. Conversely, digital talent service teams can be evaluated through the existence of agrarian technical personnel. Lastly, digital service consumption is measured using per capita transportation and communication expenditures of rural households. All these indicators are put together to create an evaluative framework for a comprehensive evaluation of the actualization and integration process in terms of implementing IT technologies into country life.

3.2.3. Exploring Pathways: Mechanisms Linking Digital Villages and Integration

The primary purpose of this study is to analyze the impact of digital village construction on rural industrial integration through the following three relevant pathways: bridging urban–rural gaps, adjusting agricultural industrial structure, and promoting agro-technological innovation. Urban–rural element mismatch is represented by a logarithmic transformation λ (λin agriculture and λin non-agriculture) for its level attainment. This study calculates the urban–rural element mismatch coefficients (λ) for 2013–2023, assuming that non-agricultural activities are concentrated in urban areas while rural areas are mainly engaged in agricultural production. An overallocation of labor relative to capital is denoted by a value of λ greater than 1. If λ equals one, this indicates an even distribution that is reasonable within elements. A value of λ less than one implies an under-allocation of labor about capital. The adjustment of the agricultural industry structure is measured by combining the rationalization of agricultural structure with the advancement of agricultural structure to form a comprehensive indicator of agricultural structure adjustment. The growth rate in agriculture reflects changes in productivity resulting from technological advancement; thus, measuring how much total factor productivity has changed because of technological innovation is essential. Accordingly, we aim to unveil these pathways for an enhanced understanding of how digital villages can integrate rural industries and facilitate their high-quality development. This empirical study will reveal specific mechanisms through which digital change can improve resource allocation, restructure agriculture-based sectors, and trigger technological renewal, ultimately leading to holistic development across different rural settings.

3.2.4. Control Variables

To avoid the influence of other factors on rural industrial integration, this research considers some important control variables. The average level of education in rural areas is a measure of rural human capital, as higher human capital can encourage digital technology absorption and integration of rural industries. The ratio of the disaster-affected regions to total planted areas indicates a plantation structure because natural disasters can disrupt farming activities and prevent industrial cohesion. The logarithm of the total power of agricultural machinery refers to the total power (in logarithm form) used in the agricultural sector, since mechanization boosts productivity in agriculture, making it possible to amalgamate the primary, secondary, and tertiary economic sectors [61].

Table 3. Variable definitions and descriptive statistics.

Variable Name	Variable Definition	Mean	Standard Deviation	Minimum	Maximum
Rural Industrial Integration	/	0.175	0.214	0.063	0.642
Digital Village Level	/	0.262	0.187	0.024	0.764
Mismatch Level	/	0.571	0.126	0.401	0.724
Agricultural Structure Adjustment	/	0.157	0.284	0.147	0.976
Agricultural Technological Progress	Green Total Factor Productivity in Agriculture	1.293	0.341	0.377	2.812
Rural Human Capital	Average years of education in rural areas	7.721	0.712	6.927	10.261
Planting Structure	Ratio of crop planting area to total planting area	0.945	0.271	0.668	0.899
Total Power of Agricultural Machinery	Logarithm of the total power of agricultural machinery	8.786	1.412	5.845	10.428

demonstrates the influence of digital village construction on rural industrial integration after controlling for various factors. Model (1) shows that digital village construction significantly affects rural industrial integration and indicates that as a digital village program goes forward, there is a corresponding improvement in the industrial integration in the countryside at a 1% level. This, thus, reveals the importance of digital infrastructure in promoting economic growth within rural regions. Furthermore, model (2) confirms how these findings remain robust even after including second-order terms on control variables while maintaining a positive relationship between digital village construction and rural industrial integration. In addition, these models (3)–(5) explore the following additional dimensions of digital village construction: digital industrial development, information infrastructure in the digital area, and degree of digital services, each separately showing positive impacts on rural industrial integration. To ensure the reliability of the results, the models involved year and province-specific fixed effects, as well as control variables. Descriptive statistics in Table 3 help add context by showing the variation and distribution of other essential variables such as rural industrial integration, DV levels, and agriculture-related issues, further solidifying our regression findings. These results indicate that multidimensional frameworks for any programs or policies that promote intersectoral links are necessary for promoting employment opportunities with sustainable income levels.

3.3. Comprehensive Data Analysis: Sources and Methods

This study used 30 provinces (municipalities and autonomous regions) in mainland China as the sample, not including Hong Kong, Macao, Taiwan, and Tibet Autonomous Region, in 2013–2023. The data were collected from many sources, like provincial statistical yearbooks, the China Statistical Yearbook, the China Rural Statistical Yearbook published by Peking University, “Digital Inclusive Finance Development Index Report”, “China E-commerce Yearbook”, and EPS database. If there was any value gap, the linear interpolation method filled in such gaps, ensuring a complete set of reliable data for empirical purposes. This broad-based data collection from multiple authoritative sources encompassed national and provincial information, forming a solid foundation for this study to examine the effects of digital village construction on rural industrial integration across China over the last decade.

The reason for selecting 30 provinces and the time range from 2013 to 2023 for research is that China has a total of 34 provincial-level administrative regions, including 31 provinces, autonomous regions, and municipalities directly under the central government, excluding Hong Kong, Macao, and Taiwan. Selecting 30 provinces for research, covering almost all provincial-level administrative regions in mainland China, this sample size can better represent the overall situation in China, ensuring the comprehensiveness and representativeness of the research results. The ten-year period from 2013 to 2023 covered 765 critical periods in the development of China’s digital economy. Since 2013, China’s digital economy has started to develop rapidly, especially with the popularization of 4G networks and the rise of 5G technology. The application of digital technology in rural areas has become increasingly widespread, and its impact on rural industrial integration has become increasingly significant. Choosing this time period allowed for a comprehensive observation and analysis of the role and effectiveness of digital technology in the integration of rural industries in China. The data from 2013 to 2023 were relatively easy to obtain and have good continuity, which is conducive to long-term trend analysis and comparative research. Meanwhile, the data during this period can effectively reflect the latest trends in digital technology development and the actual progress of rural industrial integration.

The data collection process for this article mainly included the following steps.

The first step was to determine the requirements. Statistical agencies at all levels must comprehensively consider and evaluate user needs based on the importance of user needs, difficulty of investigation, satisfaction of existing statistical resources, and guarantee of human, financial, and technological conditions, and provide feedback on the processing results to users within the prescribed time.

The second step is the statistical design. Based on the statistical survey’s objectives and plans, the statistical survey unit, survey indicators, survey time, survey frequency, survey methods, data collection and processing methods, data evaluation methods, data usage and release, and organizational methods must be determined and a statistical survey system developed.

Step three involves approval and filing. Statistical agencies at all levels must approve or file the proposed statistical survey projects and their supporting statistical survey systems and plans and promptly announce approved statistical survey projects.

Step four is task deployment. According to the approved statistical survey system or survey plan, document notices must be issued and statistical survey work formally arrange. Supportive resources, such as investigators, funds, and equipment, must be implemented. Software development and testing must be completed, statistical survey forms customized, historical data loaded, a data collection and reporting platform opened, and permissions managed and allocated.

Step five involves data collection. Statistical agencies collected raw data through household surveys, on-site price collection, telephone surveys, online surveys, electronic bookkeeping, online reporting, unmanned aerial vehicle remote sensing measurements, and other methods in accordance with the survey system or survey plan, including time, content, and methods. Administrative records from relevant functional departments, commercial record data from enterprises and institutions, relevant data from industry associations, and network big data are collected.

Step six is data processing. In this step, the survey data were reviewed, queried, revised, and confirmed. Data from multiple sources were organized, cleaned, and transformed, and the priority order of the data processing was determined, and the data correlated. The intermediate data were analyzed, grouped, and aggregated during the data processing, with problematic data verified and corrected.

Step seven is the data evaluation. Statistical agencies at all levels must develop a scientifically feasible system for evaluating statistical survey projects based on the principles and standards of statistical quality evaluation. On-site research, questionnaire surveys, and other methods were conducted to assess the completion status of each stage of work. The project was analyzed and comprehensively evaluated, and the evaluation information was collected, classified, organized, and summarized, with and the experience summarized and shortcomings identified.

Step eight is organization and archiving. Paper and electronic documents, such as notifications, survey plans, statistical data, and metadata, were archived for statistical survey projects, classified, backed up, or cleaned according to standardized processes and requirements. Statistical databases were established in a timely manner and improved, with query and retrieval mechanisms established.

4. Empirical Insights: Effects of Digital Village Construction

4.1. Key Findings: Digital Villages Enhance Rural Industrial Integration

This study employed a double machine learning model to determine the effect of digital village projects on rural industrial integration. The random forest method was used to solve primary regression and auxiliary regressions in a sample split ratio of 1:4. This modern econometric technique effectively handles the problem of high dimensional control variables and potential non-linearities in the relationship among critical variables. It is important to note that before conducting an empirical analysis, this study conducted a comprehensive multicollinearity test among variables included in the model. Based on these results, all VIF (variance inflation factor) values were below 6.5, with an average value of 3.54, thus indicating the absence of severe multicollinearity problems. This implies that independent variables employed in the model were sufficiently different from each other, as they did not have any strong correlations that may have affected the reliability of the regression estimates otherwise [62].

Table 4. Baseline regression results.

Variable Name	(1)	(2)	(3)	(4)	(5)
Digital Village Construction	0.311 ***	0.219 ***
	(0.031)	(0.017)
Digital Industry Development			0.373 ***
			(0.009)
Digital Information Infrastructure				0.342 ***
				(0.011)
Digital Service Level					0.242 ***
					(0.041)

Note: The robust standard error is indicated in parentheses, and *** represents the 1% significance level; Due to space limitations, the results of controlling variables were not listed; Same below.

shows that the four traits of constructing a digital village all at once contributed to rural industrial integration, which is statistically significant. For example, if one unit is added to digital village construction, the rural industrial integration index will increase by 0.219 units, as shown in model (2). The most significant impact was caused by the development of the digital industry, with a one-unit rise corresponding to a 0.373 unit increase in the integration index, as seen from the model (3). An improvement in the digital information infrastructure and e-service level also positively affected integration; these change by 0.342 and 0.242 units, respectively, as seen from models (4) and (5). These results are statistically significant, denoted by three asterisks (***) with a year-fixed effect plus a province-fixed effect, among other control variables, across 300 observations for all models presented. Thus, Hypothesis H1 verifies that digital dimensions progress toward enhancing rural industrialization, among others, indicating that advancements in these aspects could be essential in underpinning it.

4.2. Verifying Results: Robustness and Sensitivity Analyses

Several robustness tests were used in this study to ensure the accuracy of the baseline regression results, including trimming, adjusting the sample, changing the sample split ratio, and altering the algorithm. Firstly, this involves conducting a baseline regression after trimming the regression variables by 1% and 5% highest and lowest values so that outliers will have minimum influence on the final results obtained from regression analysis. This eliminates unusual results that could be caused by extreme numbers, which may unduly affect regression coefficients. Secondly, given that direct-controlled municipalities differ significantly from other regions regarding government financial input, investment attraction, and primary conditions, the research re-conducts the baseline regression after removing samples of four direct-controlled municipalities. Thus, these findings cannot be biased because of the single features of such localities; instead, they should represent more people living there. Thirdly, to avoid biasing conclusions concerning sample split ratio, the study changes the sample split ratio from 1:4 in the original manuscript to both 1:2 and 1:6. Consequently, it helps them prove that their findings do not depend on specific sample split ratio, as well as are applicable for all different sizes of subgroups, among which the samples were distributed randomly among members according to their respective population numbers.

Table 5. Robustness test.

Variable Name	(1)		(2)	(3)
	Trimming Sample		Adjusting Sample Study	Changing Sample Split Ratio
	Trimming1%	Trimming5%	Excluding Direct-Controlled Municipalities	1:2	1:6
Digital Village Construction	0.322 ***	0.365 ***	0.265 ***	0.246 ***	0.326 ***
	(0.031)	(0.026)	(0.083)	(0.012)	(0.032)
Control Variables	Controlled	Controlled	Controlled	Controlled	Controlled
Year-Specific Fixed Effects	Controlled	Controlled	Controlled	Controlled	Controlled
Province-Specific Fixed Effects	Controlled	Controlled	Controlled	Controlled	Controlled
Observations	294	270	260	300	300

presents the robustness test results for the impact of digital village construction on rural industrial integration. The table shows that regardless of the method used—whether trimming the sample by 1% or 5%, adjusting the sample by excluding direct-controlled municipalities, or changing the sample split ratio to 1:2 or 1:6—the positive and significant effect of digital village construction remains consistent. Different models have statistically significant coefficients ranging from 0.246 to 0.365, indicated by *** (p < 0.001). This means that the regression results are robust and do not change regardless of the sample used or any other methodological manipulations (consistent). To avoid alternative factors that could cause this, each model had fixed effects for two controls—year and province—as well as other observational variables. Nevertheless, although the number of observations changed slightly across models because of the sample size adjustment, the fact is the same, as follows: digital village construction greatly facilitates rural industrial integration development (findings).

5. Interpreting the Impact: Mechanisms and Policy Implications

5.1. Unpacking the Pathways: Mechanistic Insights

Benchmark regression results have firmly established that establishing digital villages can enhance rural industrial integration. Expanding on these findings, this study explores further mechanisms by which the construction of a digital town affects rural industrial integration development while also addressing potential endogeneity bias in testing for mediating effects. The primary examination focuses on bridging urban–rural gaps, shifting agricultural industrial structure, and promoting agricultural technological development in rural areas. By critically evaluating these processes, this research demonstrates how digitalization may help unlock integrated rural industry development and provides salient points for policymakers and implementers about rural growth [63].

5.1.1. Correcting Imbalances: Digital Villages as Equalizers

In order to evaluate whether digital village construction can solve the problem of urban–rural factor mismatch and its impact on rural industrial integration, this study draws on the approach of Zhang et al. [64] to apply logarithms to measure the level of urban–rural factor mismatch between rural and urban areas. Also, the study compares the heterogeneity in indirect effects between alleviating rural element mismatch and urban element mismatch while testing for urban–rural element mismatch mechanism. Consequently, the results show that rural resource elements with high gaps and mismatches for city-level resources are related to a significant coefficient of −0.441 at 1% level by developing digital villages. These two analyses indicate that since they also confirm hypothesis H2 that digital village construction can promote rural industrial integration by addressing these imbalances, it confirms that constructing digital villages can effectively alleviate urban and rural resource element mismatches. However, the impact of lowering rural element mismatch levels surpasses that of reducing those of urban compared to coefficient estimates, implying that their main focus is primarily on correcting issues of misalignment associated with factors’ appropriation in the countryside. This improvement in rural element mismatch levels enhances the efficiency of capital, labor, and land factor allocation, which is vital in fostering the integration of agriculture and industry, explicitly improving capital factor allocation, thus integrating virtual capital and agricultural real economy, hence promoting quality agricultural production and creating new enterprises. It also promotes labor factor allocation efficiency, leading to the diversified development of human resources suitable for the ever-changing requirements of integrating industries into the countryside. Therefore, this means that it is necessary to improve the efficiency of land element allocation, so that various types of agriculture, including all non-agricultural enterprises, can use a given piece of land. This is consistent with the findings of Mei et al. [65]. They also believe that modernization has brought about a shift from low productivity farms to high productivity farms. In contrast, some other areas, such as transforming certain parts of rural areas to concentrate service or processing industries, will lead to their integrated transformation and increase the possibility of further industrial and agricultural integration in these settlements. By reducing the urban–rural element misalignment, the construction of digital villages creates a conducive environment for effective rural industrial integration, optimizing resources and unlocking their potential to remain rural and sustainable [66].

5.1.2. Reshaping Rural Economies: Adjusting Agricultural Structures

This study applies a comprehensive calculation of agricultural structure optimization and advancement to measure the degree of agricultural structure adjustment to test the mechanism by which digital village construction can lead to agricultural restructuring, thus influencing rural industrial integration. With a coefficient of 0.242, the results show that digital village construction significantly impacted agricultural structure adjustment. This means that rural industrial integration is greatly influenced by changes in the agrarian landscape through digital village construction, thereby supporting our hypothesis H3. The effective adjustment of the agricultural system, as stated by Zheng Li et al. [67], will optimize the industrial layout from traditional production methods to multiple business models, including agricultural product processing, integration of agriculture and tourism, and agricultural technology innovation (ATI), in order to improve the efficiency and competitiveness of rural industrial integration.

5.1.3. Advancing Technology: Digital Villages and Agricultural Innovation

This study measures the degree of agricultural technological progress through the contribution rate of agricultural scientific and technological advancement in order to test the mechanism by which the construction of digital villages can enhance agricultural technological progress and thereby affect rural industrial fusion. The results indicate a significantly positive estimated coefficient of 0.314 for digital village construction, implying that with every unit increase in digital village construction, agricultural technological progress increases by 0.314 units. This shows that villages play an essential role in advancing agriculture through technology once digitized. Hypothesis H4 was validated as it simply showed that constructing digital villages could considerably improve agriculture productivity and broaden its scope across rural regions. The development of high-quality crops, increased level of processing and value addition into farm products, merging primary and secondary sectors, and ecological and environmental protection, including green agriculture and water-saving irrigation technologies, are among these practices. Consequently, it provides a suitable environment basis for rural industrial integration while at the same time unlocking new opportunities such as diversified high-quality rural industrialization like agritourism, innovative agricultural products and services, and sustainable use of natural resources.

Table 6. Mechanism analysis results.

Variable Name	Rural Industrial Integration	Element Mismatch Level	Agricultural Structure Adjustment	Agricultural Technological Progress
Digital Village Construction	0.342 ***	−0.441 ***	0.245 ***	0.314 **
	(0.051)	(0.223)	(0.032)	(0.016)
Control Variables	Controlled	Controlled	Controlled	Controlled
Year-Specific Fixed Effects	Controlled	Controlled	Controlled	Controlled
Province-Specific Fixed Effects	Controlled	Controlled	Controlled	Controlled
Observations	300	300	300	300

explores how digital village building can affect rural industrial integration. The following significant coefficients are presented: digital village construction effects on the Rural Industrial Integration were positive (0.342 ***), showing its contribution to connecting rural industries. Subsequently, it reduces the Element Mismatch Level (−0.441 ***), effectively making urban and rural elements compatible. Additionally, digital village construction supports Agricultural Structure Adjustment (0.245 ***), which indicates some changes in the workings of agricultural sectors for better performance. Nonetheless, it moderately affects Agricultural Technological Progress (0.314 **). This means there is little influence on technological development in agriculture, yet this effect is still relevant concerning promoting such developments on a small scale within farms or fields. In order to ensure reliability across these observations, we have controlled for variables like year and province fixed effects.

5.2. Regional Variations: Differential Impacts Across China

The level of agricultural planting and economic development are key factors affecting the integration of rural industries. This study draws on academic achievements [68] to divide the sample into the following two factors: the first category is grain-producing areas and non-grain-producing areas, and the second category is the eastern and central western regions, exploring the role and differences of digital rural construction in promoting the integrated development of rural industries under different conditions.

Table 7. Heterogeneity test.

Variable Name	Grain-Producing vs. Non-Grain-Producing Areas		Two Major Regions
	Grain-Producing Areas	Non-Grain-Producing Areas	Eastern Region	Central-Western Region
Digital Village	0.296 ***	0.123 ***	0.224 ***	0.107 ***
	(0.049)	(0.032)	(0.043)	(0.032)
Control Variables	Controlled	Controlled	Controlled	Controlled
Year-Specific Fixed Effects	Controlled	Controlled	Controlled	Controlled
Province-Specific Fixed Effects	130	170	120	180

illustrates how the heterogeneity test results differ in how digital village construction has impacted different areas in China. These coefficients show significant differences, meaning that for principal grain-producing arrears, digital village construction substantially positively affects rural industrial integration (0.296 ***). Therefore, it significantly influences economic integration in this agricultural area. On the other hand, however, this impact could be more pronounced in non-grain-producing areas (0.123 ***), indicating regional variations concerning the effectiveness of digitized methods. Correspondingly, a significant favorable influence (0.224 ***) is seen from digital village construction in the Eastern part, where the economy is more developed but less so than that found within significant grain-producing regions. Conversely, digitalization had less impact (0.107 ***) in the Central-Western region, which is less economically developed, implying that targeted strategies are required to take full advantage of it. In other words, these results can be trusted because they account for variations across periods and further stress that successful implementation of such programs should consider diverse local settings within China’s rural sector.

5.2.1. Relieve the Mismatch of Urban and Rural Factors to Achieve Industrial Integration

How to promote industrial integration through alleviating the mismatch of urban and rural factors in digital rural construction. The government formulates strategies to tilt development factor resources toward rural areas through macroeconomic regulation, guiding urban production factors to tilt toward rural areas and stimulating internal production vitality in rural areas. By utilizing ecological advantages such as agricultural modernization and ecotourism, we can attract factors to spontaneously flow from cities to rural areas, achieve free two-way flow of urban–rural factors, and promote integrated urban–rural development. The government should fully leverage fiscal funds, gradually relax policies for the financial services industry to enter the market, lower the threshold for the financial industry to enter the market, and guide social capital to invest in rural agriculture. Improve the financial service system, enhance the efficiency of capital allocation in rural financial institutions, reduce financing costs for rural residents, and alleviate the degree of distortion in urban and rural capital allocation. It should strengthen the integrated design, synchronous implementation, collaborative progress, and integrated innovation to promote the digital, networked, and intelligent development of urban and rural production, living, and ecological spaces. We encourage qualified small towns to plan first, develop “Internet-plus” features industries in line with local conditions, create an “Internet-plus” industrial ecosystem, and drive rural entrepreneurship and innovation. We will guide different types of villages to deepen the application of network information technology, foster new rural businesses, develop the digital economy, explore unique resources, and build Internet featured villages. The deep integration of digitization and industry is an important lever for the revitalization of rural industries, which runs through seed sources, variety innovation, and industrial integration, providing new impetus for the digitization of rural industries. Reshaping farmers’ subjective consciousness through digital cultural tourism, effectively connecting rural areas, farmers, and tourists, and improving the single-industry structure of rural areas that is mainly based on agriculture.

5.2.2. Adjusting the Agricultural Industry Structure to Achieve Industrial Integration

How to promote industrial integration through adjusting the agricultural industry structure in the construction of digital rural areas. Digital technology precisely regulates, operates, and manages the entire process of agricultural production through data, models, and computing power, effectively reducing uncontrollable risks in agricultural production and improving management level and agricultural production efficiency. For example, through intelligent agricultural machinery such as unmanned tractors and drones, farming can be more standardized and standardized, increasing crop planting density and yield, reducing energy consumption and usage costs. Digital technology is driving the gradual maturity of online cooperation models, effectively connecting diverse entities such as industrial producers and operators, agricultural enterprises, regulatory agencies, and consumer groups before and after the agricultural industry chain, which helps to ensure industrial and food safety. At the same time, the digital upgrading of the entire agricultural industry chain will promote the integrated development of the primary, secondary, and tertiary industries, integrating agriculture with fields such as technology, culture, and tourism. Digital technology promotes intelligent and precise management of agricultural production, and comprehensively improves agricultural productivity. Digital technology can facilitate various aspects of agricultural production, processing, circulation, and sales, achieving diversified and personalized production and services. Digital technology promotes the deep integration of the primary, secondary, and tertiary industries in rural areas, horizontally expands the width of the industrial chain, vertically extends the length of the industrial chain, and promotes the continuous emergence of new industrial formats and models. According to the research results of [69], we found that by using data as a new production factor, the production, processing, and sales of agricultural products can be more informationized, efficient, and transparent. It supports counties (cities and districts) with the conditions to build modern agricultural industrial parks; promote the concentration of market entities, such as scientific research and development, processing logistics, and marketing services in the park; and gathers factors such as capital, technology, and talent in the park.

5.2.3. Promoting Agricultural Technological Progress to Achieve Industrial Integration

How to achieve industrial integration through promoting agricultural technological progress in digital rural construction? The application of digital technology runs through key areas such as seed source, variety innovation, and industrial integration, providing new impetus for the digitization of rural industries. Through the seed industry big data platform, we aim to achieve comprehensive modernization and autonomy in variety selection, promotion of high-quality seeds, and seed industry technology, laying a solid foundation for food security. Digitization can enhance technological innovation capabilities, achieve agricultural industrialization, and strengthen the foundation support of modern agriculture. The key lies in technological progress, innovating important agricultural product varieties through technology, increasing the added value of agricultural products, and achieving high-level self-sufficiency and self-reliance in the agricultural field [70]. Digitization promotes the deep integration of agricultural production and processing; agricultural product market services; small farmers and rural industries; large, medium, and small enterprises; and characteristic economies, providing a platform for rural industrial integration, agricultural technology achievement transformation, and business model innovation, and promoting the coordinated development of rural primary, secondary, and tertiary industries. It also promotes the digital and intelligent transformation of infrastructure such as water conservancy, highways, electricity, cold chain logistics, and agricultural production and processing in rural areas and advances the construction of smart water conservancy, smart transportation, smart grid, smart agriculture, and smart logistics. It improves the “one map” of natural resource remote sensing monitoring and comprehensive supervision platform, and implements dynamic monitoring of permanent basic farmland. It builds space-based facilities such as agricultural and rural remote sensing satellites and vigorously promotes the application of Beidou satellite navigation system and a high-resolution earth observation system for agricultural production. It accelerates the application of cloud computing, big data, Internet of Things, and artificial intelligence in agricultural production and management, and it promotes the comprehensive and deep integration of new-generation information technology with planting, seed, animal husbandry, fisheries, and agricultural product processing industries, and it creates technology-based agriculture, smart agriculture, and brand agriculture. It builds a number of new technology for farmers’ entrepreneurship and innovation centers to promote cooperation between industry, academia, research, and application. It establishes a network service system for the transformation of agricultural scientific and technological achievements and supports the construction of an online trading market for agricultural technology.

6. Conclusions

This study provides a comprehensive examination of the impact of digital village construction on the development of rural industrial integration in China. The research uncovered the fundamental mechanisms through which digital transformation can drive the high-quality integration of various rural industries by employing a double machine learning model. First, it is essential to recognize that digital rural construction has a general impact on integrating rural industries, with an impact factor = 0.311, which means digitization can enhance the fusion and progress of rural industries. It has been established that industry digitization, digital information infrastructure, and the level of service in a digital format are factors that significantly contribute to the merging of rural industries, whereby the most significant effect was made by an evolution of industry toward digital (0.373), then digital infrastructure (0.342), and, finally, a digital service level (0.242). From a mechanism analysis viewpoint, constructing e-villages helps in solving urban/rural factor misallocation (−0.441), adjusting the agricultural and industrial structure (0.245), and promoting agricultural technological change (0.314), hence fostering integrated development among different industrial aspects within rural areas. This study emphasizes how important it is for digitization to play a significant role in resource optimization, an adjustment in industry structure, and technology innovation, among others, as would apply in any rural area.

The driving effect of digital rural construction on the integrated development of rural industries varies significantly among regions. In major grain-producing areas, the coefficient was 0.296 as opposed to in non-major grain-producing areas’ with 0.123. Furthermore, this stands at 0.107 and 0.224, respectively, in eastern and central-western regions. The results obtained show that for major grain-producing areas and eastern regions, the coefficient of influence for digital rural construction on rural industrial integration was high. In contrast, it is low for central-western regions.

This research examined how the construction of digital villages in China contributes to rural industrial integration by increasing productivity and innovation. The study used a double machine learning model to demonstrate that digital economic development, infrastructure, and services foster high-quality industry integration. It outlines how the growth in digitization has bridged urban–rural imbalances through technological innovation, thus enhancing system efficiency and effectiveness. Furthermore, the study identifies regional disparities reinforcing the need for place-based approaches to economic development and resource-optimizing measures for sustainable expansion in agrarian zones.

The construction of digital rural areas is an important lever to accelerate the integration of rural industries and achieve rural revitalization. Based on the research conclusions of this article, policy recommendations are proposed from three aspects.

Firstly, firmly grasping the dividend effect of digital economy development in rural revitalization, we must first recognize the key role of the digital economy in promoting rural revitalization [71]. On the one hand, there is the strengthening of top-level design, promotion of digital rural construction through policies, and acceleration of the penetration of digital technology into rural industries. This includes accelerating the construction of digital projects, such as 5G base stations and rural power grid renovation, improving the level of rural digital industrialization and industrial digitization, and enhancing the “hematopoietic” function of rural industries. For example, through the application of 5G technology, the automation and intelligence level of agriculture can be improved, precision agriculture can be achieved, and agricultural production efficiency and product quality can be enhanced. On the other hand, local governments should accelerate the construction of digital rural infrastructure and create a favorable environment for digital empowerment industries. This involves improving the supply of information terminals and services, encouraging the development of information terminals, technical products and mobile internet application (APP) software that adapt to the characteristics of “agriculture, rural areas and farmers”, and promoting the research, development, and application of audio and video technologies in ethnic languages. At the same time, we will comprehensively implement the introduction of technology into villages and households, build a comprehensive agricultural service platform, and accelerate the digital transformation of rural infrastructure. The complementary role of digital infrastructure in rural infrastructure services is reflected in multiple aspects, for example, by promoting the construction of smart water conservancy, smart transportation, smart power grid, smart agriculture, and smart logistics, the production and quality of life in rural areas can be improved. In addition, consolidating the foundation of digital agriculture, improving the “one map” of natural resource remote sensing monitoring and comprehensive supervision platform, implementing dynamic monitoring of permanent basic farmland, constructing space-based facilities such as agricultural and rural remote sensing satellites, and promoting the application of Beidou satellite navigation system and high-resolution earth observation systems in agricultural production are all important measures to enhance the level of rural digital industrialization and industrial digitization. To further strengthen the supply of infrastructure in rural areas, it is necessary to coordinate the development of digital villages and smart cities, promote the digital, networked, and intelligent development of urban and rural production, life, and ecological spaces, and accelerate the formation of a digital urban–rural integrated development pattern that is cobuilt, shared, interconnected, distinctive, and mutually beneficial [72]. This can not only improve the infrastructure level in rural areas, but also promote the transformation and upgrading of rural industries through the application of digital technology, achieve industrial integration, and inject new impetus into rural revitalization. Through these measures, digital rural construction can effectively promote agricultural technological progress, achieve industrial integration, and promote the modernization of agriculture and rural areas

Secondly, developing differentiated strategies is crucial for the construction of digital villages. Based on the conclusion of heterogeneity analysis, each region should focus on its own development advantages and explore development strategies that are suitable for the local conditions. For major grain-producing areas, it is necessary to leverage the advantages of abundant local agricultural resources, focus on agriculture, use digital technology to accelerate the extension of the agricultural industry chain, and promote the integrated development of rural industries. This can be achieved by strengthening resource integration, policy integration, improving material equipment and technological conditions, creating agricultural modernization demonstration zones, and exploring differentiated and distinctive agricultural modernization development models. At the same time, the application of digital technology in production and operation, especially in grain production, including the widespread use of intelligent large-scale agricultural machinery, can be utilized. Taking the production process of crops from the field to the dining table as an example, the application of digital technology is ubiquitous in the front-end monitoring of soil moisture and seedling conditions, growth during production, pest and disease monitoring, and post production particle storage. Non grain producing areas need to firmly grasp the dividends of the digital age, use digital technology to empower the secondary and tertiary industries, and then feed back into agriculture, accelerate the entry of the secondary and tertiary industries into the agricultural sector, and promote the integration of rural industries. This can be achieved through the establishment of national modern agricultural industrial parks, the cultivation of strong agricultural industry towns, national “one village, one product” demonstration villages and towns, and advantageous characteristic industrial clusters with an output value exceeding 10 billion yuan, as well as the construction of science and technology demonstration parks, modern forestry industry demonstration zones, and other measures. The eastern region should fully leverage its economic and digital technology advantages, enrich agricultural application scenarios, tilt high-quality resources toward rural areas, and empower the integrated development of rural industries. This includes strengthening the construction of digital infrastructure in rural areas, vigorously improving the quality of rural communication networks, creating a favorable environment for the development of the digital economy, and providing basic conditions for farmers to invest digital technology in actual agricultural production and operation. The central and western regions need to accelerate the continuous integration of agricultural engineering with big data, information technology, biotechnology, artificial intelligence, etc., promote high-quality agricultural development, and provide good support for the entry of the secondary and tertiary industries into the agricultural sector.

Thirdly, alleviating factor mismatch is a key step in promoting rural revitalization, which involves optimizing the allocation of key factors such as capital, labor, and land. Firstly, optimizing the allocation of capital factors is an important way to alleviate factor mismatches. The local government can tilt resources toward rural areas through tax reductions, financial support, and policy incentives to enhance farmers’ production enthusiasm [73]. For example, by providing financial services and offering certain interest rate discounts, it can promote the integration and upgrading of the industrial chain, and enhance the “hematopoietic” function of rural industries. This can not only provide necessary financial support for agriculture, but also promote the digital transformation of rural industries through financial means, improve agricultural production efficiency and product quality. Secondly, optimizing the allocation of labor factors is equally crucial. By optimizing the management system for agricultural technology personnel and allocating them to various fields based on their professional expertise, we can strengthen the mechanism for matching labor supply and demand, and promote the flow of labor factors between urban and rural areas. The digital development of rural areas has increased the supply of rural labor and increased the duration of non-agricultural employment for workers, improved job flexibility, and promoted the diversified employment status of rural labor. This helps to unleash the potential surplus labor factor dividends in rural areas and increase the supply of rural labor. Once again, the rational planning and use of land elements are also important aspects in mitigating element mismatches. Local governments should reasonably plan land use and improve land use efficiency while ensuring that the cultivated land area remains unchanged and implementing the system of balanced protection of cultivated land proportion. This can be achieved by promoting the digital and intelligent transformation of infrastructure, such as for water conservancy, highways, electricity, cold chain logistics, and agricultural production and processing in rural areas, thereby increasing the production potential and economic benefits of land.

This study indicates several possible research areas to be explored in the future. One way of doing this is by investigating whether the proposed mechanisms can apply to other countries with different institutional and socio-economic backgrounds, enabling comparisons among countries and a more extensive comprehension of digital transformation’s part in rural industrialization. Such data-gathering processes as surveys or case studies may illuminate the processes behind such changes at the grassroots levels and the impacts of technology application in rural areas. The authors suggest exploring them from a geographic perspective by examining how digital development has influenced rural industries. By focusing on these issues, future studies will develop a better understanding of both the theoretical and practical aspects regarding how digital technologies foster sustainable and inclusive development of rural economies.