Search Results (980)

The purpose of few-shot relation extraction (RE) is to recognize the relationship between specific entity pairs in text when there are a limited number of labeled samples. A few-shot RE method based on a prototype network, which constructs relation prototypes by relying on the support set to assign labels to query samples, inherently leverages the symmetry between support and query processing. Although these methods have achieved remarkable results, they still face challenges such as the misjudging of noisy samples or outliers, as well as distinguishing semantic similarity relations. To address the aforementioned challenges, we propose a novel semantic enhanced prototype network, which can integrate the semantic information of relations more effectively to promote more expressive representations of instances and relation prototypes, so as to improve the performance of the few-shot RE. Firstly, we design a prompt encoder to uniformly process different prompt templates for instance and relation information, and then utilize the powerful semantic understanding and generation capabilities of large language models (LLMs) to obtain precise semantic representations of instances, their prototypes, and conceptual prototypes. Secondly, graph attention learning techniques are introduced to effectively extract specific-relation features between conceptual prototypes and isomorphic instances while maintaining structural symmetry. Meanwhile, a prototype-level contrastive learning strategy with bidirectional feature symmetry is proposed to predict query instances by integrating the interpretable features of conceptual prototypes and the intra-class shared features captured by instance prototypes. In addition, a clustering loss function was designed to guide the model to learn a discriminative metric space with improved relational symmetry, effectively improving the accuracy of the model’s relationship recognition. Finally, the experimental results on the FewRel1.0 and FewRel2.0 datasets show that the proposed approach delivers improved performance compared to existing advanced models in the task of few-shot RE. Full article

Relation extraction in the equipment domain often exhibits asymmetric patterns, where entities participate in multiple overlapping relations that break the expected structural symmetry of semantic associations. Such asymmetry increases task complexity and reduces extraction accuracy in conventional approaches. To address this issue, we propose a symmetry- and asymmetry-aware dual-path retrieval and in-context learning-based large language model. Specifically, the BGE-M3 embedding model is fine-tuned for domain-specific adaptation, and a multi-level retrieval database is constructed to capture both global semantic symmetry at the sentence level and local asymmetric interactions at the relation level. A dual-path retrieval strategy, combined with Reciprocal Rank Fusion, integrates these complementary perspectives, while task-specific prompt templates further enhance extraction accuracy. Experimental results demonstrate that our method not only mitigates the challenges posed by overlapping and asymmetric relations but also leverages the latent symmetry of semantic structures to improve performance. Experimental results show that our approach effectively mitigates challenges from overlapping and asymmetric relations while exploiting latent semantic symmetry, achieving an F1-score of 88.53%, a 1.86% improvement over the strongest baseline (GPT-RE). Full article

To address the fragmentation and weak correlation of knowledge in the design method domain, this paper proposes a framework for constructing a knowledge graph driven by multi-source heterogeneous data. The process involves collecting multi-source heterogeneous data and subsequently utilizing text mining and natural language processing techniques to extract design themes and method elements. A “theme–stage–attribute” three-dimensional mapping model is established to achieve semantic coupling of knowledge. The BERT-BiLSTM-CRF (Bidirectional Encoder Representations from Transformers-Bidirectional Long Short-Term Memory-Conditional Random Field) model is employed for entity recognition and relation extraction, while the Sentence-BERT (Sentence Bidirectional Encoder Representations from Transformers) model is used to perform multi-source knowledge fusion. The Neo4j graph database facilitates knowledge storage, visualization, and querying, forming the basis for developing a prototype of a design method recommendation system. The framework’s effectiveness was validated through experiments on extraction performance and knowledge graph quality. The results demonstrate that the framework achieves an F1 score of 91.2% for knowledge extraction, and an 8.44% improvement over the baseline. The resulting graph’s node and relation coverage reached 94.1% and 91.2%, respectively. In complex semantic query tasks, the framework shows a significant advantage over traditional classification systems, achieving a maximum F1 score of 0.97. It can effectively integrate dispersed knowledge in the field of design methods and support method matching throughout the entire design process. This research is of significant value for advancing knowledge management and application in innovative product design. Full article

Mineral prospecting from vast geological text corpora is impeded by challenges in domain-specific semantic interpretation and knowledge synthesis. General-purpose Large Language Models (LLMs) struggle to parse the complex lexicon and relational semantics of geological texts, limiting their utility for constructing precise knowledge graphs (KGs). Our novel framework addresses this gap by integrating a domain-specific LLM, GeoGPT, with a lightweight retrieval-augmented generation architecture, LightRAG. Within this framework, GeoGPT automates the construction of a high-quality mineral-prospecting KG by performing ontology definition, entity recognition, and relation extraction. The LightRAG component then leverages this KG to power a specialized geological question-answering (Q&A) system featuring a dual-layer retrieval mechanism for enhanced precision and an incremental update capability for dynamic knowledge incorporation. The results indicate that the proposed method achieves a mean F1-score of 0.835 for entity extraction, representing a 17% to 25% performance improvement over general-purpose large models using generic prompts. Furthermore, the geological Q&A model, built upon the LightRAG framework with GeoGPT as its core, demonstrates a superior win rate against the DeepSeek-V3 and Qwen2.5-72B general-purpose large models by 8–29% in the geochemistry domain and 53–78% in the remote sensing geology domain. This study establishes an effective and scalable methodology for intelligent geological text analysis, enabling lightweight, high-performance Q&A systems that accelerate knowledge discovery in mineral exploration. Full article

Sales competition and recycling rivalry are critical factors affecting the operation of closed-loop supply (CLSC). The existing research on competitive CLSCs primarily analyzes the impact of competition between two sales entities and/or two recycling entities on management decisions. To make the study more realistic, this study constructs a Stackelberg game model with the manufacturer as a leader, and analyzes the impacts of competition among $n$ retailers ($\mathrm{w}\mathrm{h}\mathrm{e}\mathrm{r}\mathrm{e} n\ge 2$) and rivalry among $m$ third-party recyclers $(\mathrm{w}\mathrm{h}\mathrm{e}\mathrm{r}\mathrm{e} m\ge 2)$ on the decision-making and profits of both node enterprises and the supply chain system, and proposes a linear transfer-payment contract to coordinate the CLSC from an economic perspective. Numerical analyses are conducted to visualize the effects of competition on the decisions and profits. The key findings are as follows: (1) In the centralized system, inter-retailer competition reduces optimal order quantities but does not affect optimal retail prices. In the decentralized system, however, it decreases both optimal order quantities and retail prices. (2) Rivalry among recyclers reduces their optimal recycling volumes but does not affect their optimal recycling prices in the centralized system. In the decentralized system, however, such rivalry not only decreases recycling volumes but also increases optimal recycling prices. (3) The manufacturer’s product wholesale price and used product recycling price remain independent of competitive interactions among retailers and recyclers in the decentralized system. (4) Competition among retailers and recyclers positively affects the profits of the CLSC and the manufacturer, but negatively impacts those of retailers and recyclers. (5) When the reward–penalty factors for product order and used product recycling fall within a specific range, the linear transfer-payment contract can coordinate the CLSC in the presence of competition in both retail and recycling. (6) All enterprises’ profits are sensitive to the penalty–reward factor, but this sensitivities also gradually decrease as the number of retailers and (or) recyclers increases. Full article

Integrating human–robot collaboration (HRC) into construction sites has significantly enhanced efficiency and quality. However, it also introduces new or intensifies existing risks as it brings in new entities, relationships, and construction activities. Safety remains the top priority and a persistent concern in HRC systems. However, the current literature on human–robot collaboration safety (HRCS) is vast yet fragmented, and a systematic exploration of its status and research trends in the construction context is still lacking. This paper explores advances in HRCS over the past two decades through a mixed quantitative and qualitative analysis method. Initially, 287 related articles were identified by keyword-searching in Scopus, followed by bibliometric analysis using CiteSpace to uncover the knowledge structure and track emerging research trends. Subsequently, a qualitative discussion highlights achievements in HRCS across five dimensions: (1) optimization of remote intelligent machinery; (2) hazard analysis and risk assessment in HRCS; (3) digital twin for safety monitoring; (4) cognitive and psychological impacts; (5) organizational management perspective. This study quantitatively maps the scientific landscape of HRCS at a macro level and qualitatively identifies key research areas. It provides a comprehensive foundation for understanding the evolution of HRCS and exploring future research directions and applications. Full article

Recent advances in Large Language Models (LLMs) have reignited discussions concerning the similarities and differences between human and machine intelligence. This article approaches such questions from the viewpoint of the overarching explanation for biological and technological information systems provided by Emergent Information Theory. Particular attention is given to the role of language in the construction of high-level emergent informational processes and entities and to its use in conscious reporting. This leads to the conclusion that language may also provide a window into the inner workings of these systems that can provide evidence relevant to these discussions. Full article

A significant contradiction exists between the demand for standardized processes and the need for precise process parameter design in the rapid design of superplastic forming (SPF). To address this, an SPF process parameter design method integrating a knowledge graph and artificial intelligence is proposed. Firstly, based on process data analysis, the entity labels, relationship categories, and attributes are determined. On this basis, the knowledge graph for the SPF process is constructed, comprising the pattern layer and the data layer, which provides structured knowledge support for process generation. Secondly, the process parameter prediction model based on small samples and an improved back propagation (BP) neural network is constructed, with model convergence ensured through an adaptive maximum iteration strategy. Experimental results show that the improved BP model significantly outperforms support vector regression (SVR), random forest (RF), extreme gradient boosting (XGBoost), and standard BP models in prediction accuracy. Compared to the standard BP model, the improved model reduces the mean squared error (MSE), mean absolute error (MAE), and root mean squared error (RMSE) by 82.1% (to 0.0005), 46% (to 0.0188), and 57.1% (to 0.0229), respectively. Finally, the effectiveness, feasibility, and superiority of the method in the SPF process parameter design are verified by taking typical hemispherical parts as an example. Full article

Artificial intelligence (AI) adoption in strategic sectors such as energy is often framed in optimistic narratives, yet its actual economic contribution remains under-quantified. This study proposes a novel, multi-stage methodology at the intersection of machine learning, statistics, and big data analytics to bridge this gap. First, we construct a media-derived AI Adoption Score using natural language processing (NLP) techniques, including dictionary-based keyword extraction, sentiment analysis, and zero-shot classification, applied to a large corpus of firm-related news and scientific publications. To enhance reliability, we introduce a Misinformation Bias Score (MBS)—developed via zero-shot classification and named entity recognition—to penalise speculative or biased reporting, yielding a credibility-adjusted adoption metric. Using these scores, we classify firms and apply a Fixed Effects Difference-in-Differences (FE DiD) econometric model to estimate the causal effect of AI adoption on turnover. Finally, we scale firm-level results to the macroeconomic level via a Leontief Input–Output model, quantifying direct, indirect, and induced contributions to GDP and employment. Results show that AI adoption in Romania’s energy sector accounts for up to 42.8% of adopter turnover, contributing 3.54% to national GDP in 2023 and yielding a net employment gain of over 65,000 jobs, despite direct labour displacement. By integrating machine learning-based text analytics, statistical causal inference, and big data-driven macroeconomic modelling, this study delivers a replicable framework for measuring credible AI adoption and its economy-wide impacts, offering valuable insights for policymakers and researchers in digital transformation, energy economics, and sustainable development. Full article

The sustainable transformation of areas associated with mining is an essential contemporary challenge. In the course of such transformations, economic benefits are confronted with community criticism of heavy industry. In this context, the study examines spatial solutions implemented in the revitalisation of areas adjacent to active industrial sites. The article aims to characterise solutions applied in locations that elude a straightforward division into industrial and post-industrial. The motivations of the entities involved in the construction and the effects of implementing such projects are investigated. To achieve this aim, compositional and visual linkages in four locations (in Germany and Poland) were analysed, along with the intentions of designers and investors and the opinions of users. The study revealed the influence of political decisions on spatial solutions, an aspect not previously analysed, which has led to a limited understanding of the role they play in the transformation. It was indicated that drawing users’ attention to the aesthetic values of active industrial areas coincides with diverting attention from their nuisances. The discreet cooperation between local authorities, designers, and industry (as expressed in architectural solutions) was emphasised. The research opens a field for discussion on managing community perceptions through spatial solutions. Full article

Providing age-friendly metro service substantially enhances the elderly’s mobility and well-being. Despite recent progress in user profiling and mobility prediction, the prediction of the elderly’s metro travel patterns remains limited. To fill this gap, this study proposes a framework integrating user profiling and knowledge graph embedding to predict the elderly’s activity types at metro trip destinations, utilizing 180,143 smart card records and 885,072 points of interest (POI) records from Chongqing, China in 2019. First, an elderly metro travel profile (EMTP) tag system is developed to capture the elderly’s spatiotemporal metro travel behaviors and preferences. Subsequently, an elderly metro travel knowledge graph (EMTKG) is constructed to support semantic reasoning, transforming the activity types prediction problem into a knowledge graph completion problem. To solve the completion problem, the Temporal and Non-Temporal ComplEx (TNTComplEx) model is introduced to embed entities and relations into a complex vector space and distinguish between time-sensitive and time-insensitive behavioral patterns. Fact plausibility within the graph is evaluated by a scoring function. Numerical experiments validate that the proposed model outperforms the best-performing baselines by 13.37% higher Accuracy@1 and 52.40% faster training time per epoch, and ablation studies further confirm component effectiveness. This study provides an enlightening and scalable approach for enhancing age-friendly metro system service. Full article

Cyberattacks, especially Advanced Persistent Threats (APTs), have become more complex. These evolving threats challenge traditional defense systems, which struggle to counter long-lasting and covert attacks. Cybersecurity Knowledge Graphs (CKGs), enabled through the integration of multi-source CTI, introduce novel approaches for proactive defense. However, building CKGs faces challenges such as unclear terminology, overlapping entity relationships in attack chains, and differences in CTI across sources. To tackle these challenges, we propose the CyberKG framework, which improves entity recognition and relation extraction using a SecureBERT_Plus-BiLSTM-Attention-CRF joint architecture. Semantic features are captured using a domain-adapted SecureBERT_Plus model, while temporal dependencies are modeled through BiLSTM. Attention mechanisms highlight key cross-sentence relationships, while CRF incorporates ATT&CK rule constraints. Hierarchical clustering (HAC), based on contextual embeddings, facilitates dynamic entity disambiguation and semantic fusion. Experimental evaluations on the DNRTI and MalwareDB datasets demonstrate strong performance in extraction accuracy, entity normalization, and the resolution of overlapping relations. The constructed knowledge graph supports APT tracking, attack-chain provenance, proactive defense prediction. Full article

As unique geographical entities, island cities boast abundant ecological resources and profound cultural values, serving as critical hubs for maintaining ecosystem services in coastal transition zones. Ensuring the stability of ecosystem services is strategically significant for sustainable urban development, while the construction of Ecosystem Service Networks (ESNs) has emerged as a core strategy to enhance ecological functionality and mitigate systemic risks. Based on current research gaps, this study focuses on three key questions: (1) How to construct a Composite Ecosystem Service Index (CESI) for island cities? (2) How to identify the Ecosystem Service Networks (ESNs) of island-type cities? (3) How to optimize the ecosystem service networks of island cities? This study selects Pingtan Island as a representative case, innovatively integrating the InVEST and MaxEnt models to conduct a comprehensive assessment of ecological and cultural services. By employing Principal Component Analysis (PCA), a Composite Ecosystem Service Index (CESI) was established. The research follows a systematic technical approach to construct and optimize the ESN: landscape connectivity indices were applied to identify ecological source areas based on CESI outcomes; multidimensional resistance factors were integrated into the Minimum Cumulative Resistance (MCR) model to develop the foundational ecological network; gradient buffer zone analysis and circuit theory were sequentially employed to refine the network structure and evaluate ecological efficacy. Key findings reveal: (1) Landscape connectivity analysis scientifically delineated 20 ecologically valuable source areas; (2) The coupled MCR model and circuit theory established a hierarchical ESN comprising 45 corridors (12 Level-1, 14 Level-2, and 19 Level-3), identifying 5.75 km² of ecological pinch points, 7.17 km² of ecological barriers, and 84 critical nodes—primarily concentrated in cultivated areas; (3) Buffer zone gradient analysis confirmed 30 m as the optimal corridor width for multi-scale planning; (4) Circuit theory optimization significantly enhanced network current density (1.653→8.224), demonstrating a leapfrog improvement in ecological service efficiency. The proposed “assessment–construction–optimization” integrated methodology establishes an innovative paradigm for deep integration of ecosystem services with urban spatial planning. These findings provide practical spatial guidance for island city planning, supporting corridor design, conservation prioritization, and targeted restoration, thereby enhancing ecosystem service efficiency, biodiversity protection, and resilience against coastal ecosystem fragmentation. Full article

Macau’s Ching Chau Hill, as a composite entity of modern industrial heritage and natural cultural landscape, faces the dual challenges of conservation and regeneration. This study takes Ching Chau Hill as a case study, integrating structural equation modeling (SEM) with Geographic Information System (GIS) technology and combining the theory of the creative class, to construct an evaluation model of “industrial heritage-creative perception-cultural innovation.” Through questionnaire surveys, data from the creative class were collected, and SEM was employed for path analysis and hypothesis testing, while GIS was used for spatial analysis and visualization. This study systematically explores the creative perception pathways of industrial heritage value from the perspective of the creative class and its driving mechanisms for cultural inheritance and innovation. This study found that the retention rate of industrial structures (73%) and the “sacred-industrial” axis formed by the integrity of the spatial sequence (β = 0.58) together constitute the core of the material attachment path, and there is a significant threshold for the site identity effect: when the material authenticity score exceeds the 3.5 critical point, the identity value jumps by 37.8%, which provides a quantitative basis for the precise protection of “ruin aesthetics”. In the process of transforming cultural inheritance into innovative practice, the participation in creative activities showed a mediating effect of 72.1%, and the driving efficiency of co-creation activities was ten times higher than that of ceremonial guided tours, confirming the core position of “learning by doing” in heritage revitalization. The results show the following: (1) the creative class’s perception of the aesthetic uniqueness and historical memory of Ching Chau Hill’s industrial heritage significantly and positively influences their recognition of its creative value; (2) spatial accessibility and environmental atmosphere are key geographical factors affecting creative perception; (3) recognition of creative value effectively drives the innovative transformation of cultural heritage by stimulating participation willingness and innovative ideas. This study provides a strategy basis with both theoretical depth and practical guidance value for the revitalization and utilization of industrial heritage in post-industrial urban renewal. Full article

The integration of renewable energy into the grid has led to problems such as low utilization rate of energy storage resources (“underutilization after construction”) and insufficient system stability. This paper studied the co-evolution mechanism of power market entities empowered by shared energy storage. Based on the interaction among power generation enterprises, power grid operators, and government regulatory agencies, this paper constructed a three-party evolutionary game model. The model introduced a dynamic reward and punishment mechanism as well as a random interference mechanism, which makes it more in line with the actual situation. The stability conditions of the game players were analyzed by using stochastic differential equations, and the influences of key parameters and incentive mechanisms on the stability of the game players were investigated through numerical simulation. The main research results showed the following: (1) The benefits of shared energy storage and opportunistic gains had a significant impact on the strategic choices of power generation companies and grid operators. (2) The regulatory efficiency had significantly promoted the long-term stable maintenance of the system. (3) Dynamic incentives were superior to static incentives in promoting cooperation, while the deterrent effect of static penalties is stronger than that of dynamic penalties. (4) The increase in the intensity of random disturbances led to strategy oscillation. This study suggested that the government implement gradient-based dynamic incentives, maintain strict static penalties to curb opportunism, and enhance regulatory robustness against uncertainty. This research provided theoretical and practical inspirations for optimizing energy storage incentive policies and promoting multi-subject coordination in the power market. Full article