Next Article in Journal
Wi-Fi Sensing and Passenger Counting: A Statistical Analysis of Local Factors and Error Patterns
Previous Article in Journal
A Transductive Zero-Shot Learning Framework for Ransomware Detection Using Malware Knowledge Graphs
Previous Article in Special Issue
The Application of Machine Learning in Diagnosing the Financial Health and Performance of Companies in the Construction Industry
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Information
Volume 16
Issue 6
10.3390/info16060457
information-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Review

Integrating Natural Language Processing with 4D BIM: A Review and Thematic Synthesis

by
Mohamed ElSaadany
1,*,
Ibrahim Motawa
1 and
Asser El Sheikh
1,2
1
Structural Department, Faculty of Engineering, Mansoura University, Mansoura 35516, Egypt
2
Department of Construction Technology and Structural Materials, Peoples’ Friendship University of Russia (RUDN University), Moscow 117198, Russia
*
Author to whom correspondence should be addressed.
Information 2025, 16(6), 457; https://doi.org/10.3390/info16060457
Submission received: 29 April 2025 / Revised: 21 May 2025 / Accepted: 24 May 2025 / Published: 29 May 2025
(This article belongs to the Special Issue AI Applications in Construction and Infrastructure)
Browse Figures
Versions Notes

Abstract

:
This paper explores the integration of Natural Language Processing (NLP) and 4D Building Information Modeling (BIM). The integration of knowledge disciplines facilitates the emergence of new trends. One form of this integration is the use of artificial intelligence (AI). Recently, the BIM literature has expanded with the application of AI technology. However, AI and BIM are broad domains, and each of them encompasses multiple sub-domains. NLP, a well-established sub-domain of AI, enables computers to understand and communicate using human language. Conversely, 4D BIM is a specific area within BIM that facilitates the integration of BIM models with construction schedules. While existing literature explores the integration of each sub-domain with other major fields—such as the interplay between NLP and BIM and the connection between 4D BIM and AI—a significant gap remains in integrating the two sub-domains of NLP and 4D BIM. To provide state-of-the-art research for this integration, this paper presents a review to investigate the building blocks of both chains. This review aims to evaluate the literature, synthesize information, and identify potential research gaps. It uses a qualitative research methodology to facilitate a thorough examination of data from 122 articles. This supports the identification of 72 topics, eight 4D BIM themes, and five NLP themes.

1. Introduction

Building information modeling (BIM) relies on creating a digital model that simulates building processes across their lifecycle stages, including planning, design, construction, and operation. This model acts as a digital representation of the building, enriched with information assigned to its components, resulting in a smart, intelligent framework [1]. While 4D BIM technologies have been known for several years, their application is still limited. This is because the adoption of 4D BIM encounters barriers such as the pressure from the tight timeframe and the cost of its implementation [2]. Developing the 4D BIM requires scheduling and BIM experts to work for a long duration to develop the 4D BIM model. Therefore, the manual development of the 4D BIM model is considered a time-consuming and error-prone process. Accordingly, the utilization of automated techniques based on artificial intelligence (AI) will help accelerate the process and improve project planning and control.
Although the literature indicates several attempts to explore the integration of AI techniques and BIM [3,4,5,6], this area is rich due to the multiple sub-domains within both BIM and AI. BIM sub-domains include Industry Foundation Classes (IFC), interoperability, nD (4D BIM, 5D BIM, 6D BIM, etc.), augmented reality, and point cloud [7]. In contrast, AI encompasses a large number of sub-domains, such as expert systems, case-based reasoning (CBR), natural language processing (NLP), genetic algorithms, neural networks, convolutional neural networks, fuzzy logic, fuzzy sets, and machine learning [8,9,10].
Among the BIM sub-domains, 4D BIM represents the relationship between the project schedule and the building model [11]. On the other hand, Natural Language Processing (NLP) is an AI sub-domain that is defined as the ability of a computer program to realize the human language [12]. Therefore, using NLP empowers computer programs to understand the textual elements (such as the time schedule) that contribute to 4D BIM. The integration of these two sub-domains (i.e., 4D BIM and NLP) represents a research gap that needs further exploration and investigation.

Research Aim

Based on the research gap defined in the previous section, this review aims to analyze and synthesize the literature on both NLP and 4D BIM so that potential integrations can be revealed and addressed. Therefore, the research question is how NLP techniques can be integrated with 4D BIM to enhance the automation of construction project planning and scheduling. The rationale behind this research question stems from the investigation of an underexplored area that may reveal the potential synergies between NLP and 4D BIM, uncovering innovative ways to automate construction project planning and scheduling. This would help provide benefits such as improved efficiency, reduced time, and improved decision making.

2. Research Methodology

While most review studies primarily adopt quantitative or automated approaches, this SLR employs a qualitative methodology to conduct a deep, manual investigation of articles. Due to the novelty of this research topic, the adoption of qualitative analysis methodologies is valuable in gaining a deeper understanding of unexplored areas in which little knowledge currently exists [13]. To ensure transparency and limit preconceptions, the Grounded Theory Method (GTM) was utilized to help develop substantive theories, following multiple steps. These steps included data collection, open coding, axial coding, selective coding, and category development [14]. Additionally, the research method was designed to align with PRISMA guidelines.

2.1. Data Collection Process

Research studies on related topics were collected and analyzed to provide a comprehensive analysis and appropriate representation. According to the research aim, the main topics in this research were 4D BIM and NLP. AI is the parent domain of NLP. Likewise, BIM is the parent domain of 4D BIM but with a different perspective, where 4D BIM results from the integration of BIM and scheduling. Therefore, the inclusion criterion was the consideration of BIM, scheduling, 4D modeling, AI, and NLP. The collected research studies were classified according to the terms of the inclusion criteria. This classification was tabulated to support the sorting and synthesis process. Studies that were not related to either of these categories were excluded.
The research studies were collected from different bibliographic databases, including Scopus and Web of Science. Additionally, other open-access platforms, like Google Scholar and ResearchGate, were consulted. The search strategies mainly depended on using relevant keywords, like “BIM”, “NLP in Construction”, and “4D BIM”. Moreover, the publication dates were set to identify articles published in the past fifteen years and to limit the results to peer-reviewed articles.
To decide whether a study met the inclusion criteria, initially, title assessment was the first step to exclude irrelevant articles from the identified ones before moving to the screening stage. Qualitative evaluation of each abstract was the second step in the screening and continued until reaching the group of studies included in the review. Likewise, qualitative evaluation was utilized in data collection when assessing the article content. The domains of data collection outcomes were mainly BIM, scheduling, 4D BIM, and NLP in construction, and all the results were compatible with these domains.

2.2. Coding and Category Development Methodology

During the open coding process, all previously collected data were revisited to assign codes for the collected data segments. A total of 54 codes were initially identified during the open coding phase. Subsequently, axial coding was implemented to connect the identified codes, yielding 13 categories; 5 categories were for NLP and 8 categories were for 4D BIM. During the coding, these steps were repeated for continuous grounding to collect more data, define more codes, re-sort the codes under the defined categories, merge similar codes under one integrated code, and remove repeated codes. This process eventually resulted in 72 codes with the same 13 categories, as illustrated later in the Results section.

3. Data Collection Results

3.1. Building Information Modeling

This section discusses the BIM topics related to the research aims, including BIM functions, automation in BIM, and Industry Foundation Classes (IFCs). The BIM topics related to 4D modeling and AI are discussed in later sections.

3.1.1. BIM Functions and Benefits

BIM offers users several functions, such as automated generation of drawings, visualization, rapid generation of design alternatives, and electronic object-based communication [15]. The adoption of BIM provides benefits such as minimizing clashes, ensuring constructability, improving cost estimation, measuring energy efficiency, monitoring project performance, and obtaining as-built models for asset management. However, there are barriers to BIM implementation, including organizational change resistance, high initial cost, lengthy model creation, a shortage of skilled users, and a lack of recognition of the importance of BIM [16]. Khanzadi et al. identified nine benefits: project coordination, scheduling, clash detection, integration of subcontractor and supplier data, safety, cost estimation, site layout planning, prefabrication, and construction monitoring [17].

3.1.2. BIM Domains and Applications

Research confirms the utilization of BIM in various fields, such as progress measurement [18], cost estimation [19], sustainability [20,21,22,23,24], facility management [25], automated safety checking for construction activities [26], and construction processes [27]. Li et al. [7] identified nine eras for the evolution of the BIM literature, which include automatic and parametric design, IFC, nD modeling, rapid and automatic 3D modeling, implementation and adoption, knowledge and strategy-based management, green buildings, quality inspection, and interoperability. Wu et al. [28] indicated that the most frequently co-occurring keywords include IFC, collaboration, facility management, GIS, information technology, virtual reality, augmented reality, cloud computing, lean construction, interoperability, safety, simulation, sustainability, and visual programming language.

3.1.3. Automation in BIM

The BIM literature encompasses the automated development of models, including creating the BIM models from 2D CAD drawings [29], images of floor plans [30], and developing as-built BIM models based on surveying using laser scanning [31]. In addition, the literature suggests using automation to extract operational information from the model, such as quantity, dimensions, and materials [32]. Sigalov et al. introduced BIM contracts by integrating the BIM model with Smart Contracts (SCs) based on a blockchain to automate the contractor’s payments [33].
Another perspective is the automation of construction activities through integration with robots that perform construction activities [34] or the utilization of sensors to collect data using the IoT, which are transferred to the BIM model to automate building systems and support energy management [35].

3.1.4. IFC Querying and Parsing

Industry Foundation Classes (IFCs) enable interoperability by exchanging BIM model information [36]. They define 26 base entities, such as material, geometry, property, and quantity [37]. The limitation of querying the BIM data to be extracted and processed out of the BIM tools has resulted in various efforts to introduce intermediate solutions. These include the BIM Query Language (BIMQL) [38]; the BIMRL schema, which provides a simple form of BIM data using a relational database structure that can be queried more straightforwardly with SQL [39]; and the extraction of some of the IFC information using predefined parameters [40].
Another challenge is the parsing of the IFC files to enable BIM model data processing and integration with other applications. Wang and Tang argued that the current C++ tools are not suitable usable for web applications, and therefore, they utilized Java language and MySQL to parse the IFC [41]. Another IFC parsing tool is IfcOpenShell, an open-source software tool that supports IFC file parsing using C++ and Python [42].

3.2. Scheduling of Construction Projects

The project schedule demonstrates the planned work in the form of linked activities showing duration and planned dates [43]. This section discusses the scheduling topics related to the research aims, including the work breakdown structure (WBS) and BIM-related scheduling practices.

3.2.1. Work Breakdown Structure

The WBS represents a hierarchical decomposition of project scope [43]. Despite the scarcity of articles related to WBS development [44,45], some standards have been issued by the Construction Specifications Institute (CSI), including MasterFormatTM, UniFormatTM, and OmniClassTM, which can be employed for organizing and classification. UniFormat is based on the way elements are used (e.g., substructure, shell, interiors, and services) [46], while the MasterFormat is based on work results (e.g., concrete, masonry, metals, and finishes) [47]. OmniClass consists of 15 independent tables, each of which classifies a certain type of information, such as construction entities, spaces, elements, products, and phases [48].

3.2.2. BIM and Scheduling

Efforts were made to integrate the scheduling process with a 3D CAD model to infer the sequence, estimate the duration, and automatically create the schedule [49]. However, utilizing the BIM model helped avoid inefficiencies due to misinterpreting CAD drawings [50] or insufficient information [51]. Although 4D modeling is a form of integration between scheduling and BIM, it will be discussed in a separate section.
One integration method is automated schedule creation using the information in the BIM model, such as transferring the components into activities [52], mapping the BIM quantity takeoffs to the scheduled activities [53], optimizing the scheduling process through the generation of schedule alternatives using multi-objective genetic algorithms [54], and generating schedule sequencing [55,56,57]. Recent dependency-related studies have claimed that the spatial relationships between the building components were overlooked, and therefore, they have concentrated on analyzing these relationships to achieve a proper sequence in steel structure systems [58] and MEP systems [59].
Two other integration methods are the creation of a WBS-based BIM database structure using the Entity Relationship Diagram (ERD), which supports keeping construction records and documents [60], and the Visual Project Planner (VPP), which enables the stakeholders to contribute to the project schedule [61].

3.3. 4D BIM

3.3.1. Introduction to 4D BIM

4D BIM has many applications, such as visualization and animation, time–space conflict analysis, automated generation of activities, sequence optimization, progress tracking, procurement tracking, and site logistics management [62], in addition to facilitation of plan understanding and early identification of potential risks [63]. Although visualization is one of the benefits of 4D BIM, it has been classified as passive use [64], while the movement to co-creation using virtual reality (VR) enables all the stakeholders to participate in the development of the schedule. Moreover, 4D BIM helps represent the construction methodology and evaluate the different scheduling scenarios [2]. In addition, it facilitates time and space relationships for engineering, procurement, and construction (EPC) projects [65]. On the other hand, several barriers hinder the adoption of 4D BIM, including significant implementation costs, change resistance due to human factors, insufficient proof of performance improvement, and usability issues due to a lack of training [2].
Some enablers also support the adoption of 4D BIM, such as the platform to visualize the construction process and track the progress, the ability to model the layout to help with the planning of material handling and site logistics, the ability to model equipment, and the detection of time–space clashes [66]. The literature includes several research studies that investigated the integration of 4D BIM with other disciplines like delay analysis [67], time–cost tradeoff [68], risk management [69], waste management [70], geospatial information systems [71], health and safety [72], workspace management [73], and logistics management [74]. However, this section concentrates on the topics related to the research aims.

3.3.2. Common Tools of 4D BIM

4D BIM tools are either independent, stand-alone tools such as Autodesk Navisworks, in which 4D functions are already integrated; freeware tools like SketchUp, in which some functions can be added through plugins; or open-source tools such as FreeCad [75]. 4D BIM stand-alone tools include the Vico Schedule Planner by Trimble, Visual 4D Simulation by Innovaya, Synchro Pro by Bentley Systems (formerly Synchro), and Powerproject BIM by Elecosoft. Although these tools support both schedule creation and schedule import functions (except for Vico Schedule Planner, which does not support schedule creation), only Synchro features dependency analysis [76].

3.3.3. 4D BIM and Progress Measurement

The 4D BIM literature implies several project control applications that use the as-built model derived from point clouds to update the schedule [77] or compare it with the as-planned 4D model to assess progress [78,79,80]. However, evaluating progress solely based on point clouds is error-prone due to occlusions and noise in the captured point clouds [81], in addition to limited visibility, lighting and shadow conditions, and indoor construction work [82].
Furthermore, the utilization of unmanned aerial vehicles (UAVs) such as drones would support overcoming the occlusion problems [83], especially by directing the UAVs to target specific construction elements, such as behind-schedule elements [84]. However, recognizing the progress of interior construction can be conducted through image analysis [85] or AI techniques to compensate for occluded elements [6].
In addition, appending electronic tags to construction elements and using radio frequency identification (RFID) enables a reader to track these items and acquire their location information [86], especially for Prefabricated Housing Production (PHP) during manufacturing, logistics, and site assembly [87].
Moreover, employing chronographic modeling methods to represent site spatial management enhances the communication of schedule information classified by locations or trades [88]. The chronographic method addresses five phases, including space creation, systems, division of spaces, finishing trades, and space closure [89].

3.3.4. 4D BIM and Lean Scheduling

The Last Planner System (LPS) is a lean management tool [90] that emphasizes postponing detailed planning until the time of action and developing plans in coordination with those who will execute the tasks [91]. To integrate the LPS with 4D BIM, Heigermoser et al. developed a tool that represents two simulation modes: the learning mode (which simulates the construction up to the current status to realize lessons learned) and the short-term plan mode (which simulates a four-week look ahead to reflect its readiness) [92]. Based on a literature analysis on integrating LPS and BIM, Schimanski et al. addressed two categories: production planning and control supported by BIM and the theory of BIM–LPS integration [93].

3.3.5. Alignment of Activities and Objects

Cheng et al. proposed an automation process to align the 3D model elements to the scheduled tasks using two approaches. The first is a code-based approach that depends on the similarity of the task ID and the 3D object, while the second is a linguistic-based approach that depends on the similarity of the task name and the 3D object [94]. However, the accuracy of the second approach was impacted in complex projects. Furthermore, Cheng et al. emphasized the many-to-many context, in which multiple tasks can be aligned to the same 3D object, while one task can be aligned to multiple objects [94].

3.4. NLP Within the Review Context

This section represents a review of the AI and NLP literature in relation to the research aim. It includes an introduction to NLP as a part of AI. In addition, it represents an overview of the applications of both AI and NLP in the AEC industry. Furthermore, it addresses the integration of NLP and BIM.

3.4.1. AI Applications in the AEC Industry

While advancements in AI and BIM enhance construction technologies [95], the most commonly used AI techniques in the AEC industry are expert systems, genetic algorithms, neural networks, fuzzy logic, fuzzy sets, and machine learning [9,10]. On the other hand, the AEC clusters that have been addressed using AI techniques include optimum design, reusability, large steel structures, bridges, and project management [9], while the promising areas are strategy, transportation, warehouses, and quality control [96]. Considering the project management guide developed by the Project Management Institute, three knowledge areas (cost, schedule, and risk management) and three processes (creating the WBS, monitoring and controlling project work, and planning procurement) are the areas that are expected to be impacted by AI applications [97]. In addition, AI can be used to forecast project duration based on learning the relation between the performance and the real project duration [98]. Furthermore, AI can also be used in the planning process of repetitive construction [99].

3.4.2. Introduction to NLP

Studies that began in the late 1980s and early 1990s have advanced natural language cognition through computers. These studies include semantic nets [100], textual correlations of semantic similarities [101], and WordNet [102]. WordNet is an extensive lexical database of English in which nouns, verbs, adverbs, and adjectives are organized by semantic relations such as synonymy, similar, hyponymy, autonomy, domain, and cause [103]. These initial efforts supported the evolution of NLP. According to Tucci et al., NLP represents the ability of a computer program to realize the human language using tokenization (breaking down the text into smaller parts), lemmatization/stemming (reducing the word to its root), and algorithm development [12].
A common use of NLP is document recognition, which is important for interoperability purposes between enterprises [104] and for the analysis of unstructured data [105,106]. However, extracting topic-related content is a challenge that can be tackled through probability distributions over words to rank sentence relevancies [107]. Another challenge is removing noise from big data and eliminating irrelevant data [108]. In addition to document recognition, NLP tasks include machine translation (MT), machine reading comprehension (MRC), chatbots, and generative pre-training (GPT) [109].

3.4.3. NLP Technologies and Software Tools

Ding et al. summarized common NLP tools in Table 1, which shows that these tools have various functions, such as syntactic parsing (SP), part-of-speech (POS), topic modeling (TopMo), text analysis (TA), data mining (DM), and machine learning (ML). Some of these tools are stand-alone software, while others are packages of a programming language such as NLTK, which is utilized to process AI models such as BERT and GPT [110]. BERT (Bidirectional Encoder Representations From Transformers) is a language representation model that was designed by Google AI researchers [111], while GPT (Generative Pre-Trained Transformer) is a transformer-based architecture learning model that was developed by OpenAI [112]. However, NLTK (Natural Language Toolkit) is a Python package [113]. Other Python packages mentioned by Wu et al. include SpaCy, Sklearn, and Gensim, in addition to NLTK [114].

3.4.4. NLP Applications in AEC and BIM

Several studies discussed the utilization of NLP in the AEC industry, including building information modeling [115,116,117,118], smart cities [119], project risk management [120,121,122], project information systems [123], and construction safety [124,125]. According to Locatelli et al., efforts to integrate BIM and NLP have mainly been related to automated compliance checking and semantic BIM enrichment [126]. Lin et al. proposed an approach to integrate NLP and BIM by receiving a user’s request, understanding it using the NLP Stanford Parser, and mapping it to the entities of the BIM model [115]. The utilized NLP steps include tokenization (separating the sentence into words), tagging (labeling the word as a noun, verb, etc.), parsing (analysis of the syntactic structure and the relationships between the sentence words), classification (whether the word can be mapped to an entity or an attribute), and mapping (mapping of keywords to an IFC entity or its attributes) [115].
A similar concept to parse user requests was introduced by Wang et al., who proposed a scheme using BIM, NLP, and the International Framework for Dictionaries (IFD) (also known as the buildingSMART International Data Dictionary) [127]. Likewise, Yin et al. introduced a parser that automatically maps user queries with the BIM model, taking into account both attribute constraints (retrieving objects on the basis of their type, property, quantity, and material) and relational constraints (containment and composition) [128]. Furthermore, Nabavi et al. used latent semantic analysis (LSA) as an NLP method to understand user questions semantically by analyzing significant keywords [129]. Finally, Wang et al. utilized BIM and NLP to continuously capture project information throughout the project lifecycle [130].

4. Results, Coding, and Category Development

4.1. Statistics of Reviewed Articles

The previous sections illustrated a review of 116 peer-reviewed journal articles. Figure 1 shows the number of articles in each publication. It shows that almost 23% of the articles were cited in Automation in Construction. Note that Journal of Management Engineering, Applied Sciences, Advanced Engineering Informatics, and Journal of Information Technology in Construction combined represent almost 20% of the articles.

4.2. Results of the Coding Process

Based on the collected data, all the data illustrated in the previous section were revisited to set codes for the collected data segments. A total of 54 codes were initially identified during the free coding phase. Then, the axial coding was conducted to develop more abstract and integrated categories, resulting in 13 categories (5 categories for NLP and 8 categories for 4D BIM).
These steps were repeated for continuous grounding and selective coding to collect more data, define more codes, re-sort the codes under the defined categories, merge similar codes under one integrated code, and remove repeated codes. Prior assumptions were set aside to enable novel findings to emerge. Moreover, deep immersion in the collected data, codes, and categories was required to comprehensively understand the content, context, and potential theoretical connections. Eventually, this process yielded 72 codes under the previously defined 13 categories, as shown in Table 1.
The left side of Figure 2 shows the five NLP categories: NLP Techniques, NLP Enablers, NLP Functions, NLP–BIM Applications, and Integration of BIM with other AI Tools. Both NLP techniques and NLP enablers contribute to NLP applications, whether General Applications or NLP–BIM Applications. However, Integration of BIM with other AI Tools represents another category that is NLP-irrelevant. The right side of the figure shows the eight categories of 4D BIM, including Tracking, BIM-based Scheduling, Point Cloud, Data Processing, Time–Space Management, Visual Simulation, Mapping, and Collaboration.

4.3. NLP-Related Categories

This section includes an explanation and discussion of the emerging NLP-related categories after sorting the codes under each category. It includes five categories with 27 identified codes, as shown in Figure 3.
The first category, NLP Techniques, refers to the implied techniques of how NLP works, such as tokenization of sentence words, finding the roots of the words, and understanding the whole sentence. The second category, NLP Enablers, includes tools or techniques with which the NLP tools integrate. It includes Semantic Network, WordNet, and the International Framework for Dictionaries.
The third category, NLP Functions, represents the uses of NLP that were addressed in the previously illustrated review. It includes document recognition, extraction of topic-related content, machine translation, machine reading, chatbots, and syntactic parsing. Although these elements can be categorized as NLP applications, they have been classified as functions to consider the context of this research, which aims to investigate the integration of NLP and 4D BIM. This drives the analysis from the broad perspective of NLP applications to the detailed perspective of NLP applications in the field of 4D BIM.
The fourth category, NLP–BIM Applications, refers to applications that previous research studies have previously introduced. This category indicates that the literature shows few BIM–NLP integration practices, and they are limited to 3D BIM, with no integration introduced in the 4D BIM field. This category includes receiving user queries, understanding them, and mapping them to the BIM components. It also includes the specific types of querying based on the attributes of the model element or its relations to other elements in the model. This category also includes automated compliance checking and the continuous capturing of project information. The fifth category, Integration with other AI tools, refers to AI tools other than NLP that NLP integrates with.

4.4. 4D BIM-Related Categories

This section includes an explanation and discussion of the emerging BIM-related categories after sorting the codes under each category. It includes eight categories with 45 identified codes, as shown in Figure 4.
The first category is Tracking, which represents the 4D BIM topics related to monitoring construction work, gathering information, and communicating this information for further processing. The gathering and communication techniques include sensors, unmanned aerial vehicles, robots, RFID, and IOT, while the domains of applications include progress measurement and procurement tracking.
The second category is BIM-Based Scheduling, which represents the development of the schedule using the BIM model. It includes creating the scheduled WBS/activities based on the model components, transferring the quantities from the BIM model to the scheduled activities, estimating the activity durations based on the model quantities, evaluating multiple construction scenarios, and utilizing the model to develop LPS schedules.
The third category, Point Cloud, represents using the point clouds acquired through laser-scanning the as-built work. This includes comparing the taken point cloud to the as-planned model for delay analysis, measuring progress, and updating the project schedule. It also includes the point-cloud challenges (e.g., occlusions, noise, and interior work) and how to overcome them using AI (for the first two challenges) and image analysis (for the third challenge).
The fourth category, Data Processing, pertains to the data structure and its integration with the 4D model. It includes the parsing of the IFC files, interoperability problems, ERD structures for the 4D model database, utilizing the relational database, utilizing the WBS to build the database, querying the 4D model database, and BIM query language.
The fifth category, Time–Space Management, represents the topics related to managing the site space at different points during the project lifecycle based on the as-planned models at each point in time. Identifying the vacant space enables the planning of the construction activities that require this space, such as temporary formwork and equipment movement. This category includes site layout planning, managing the construction processes, ensuring constructability, equipment modeling, planning of material handling, safety problems, and logistics management.
The sixth category, Visual Simulation, represents the topics that require the visualization of the construction at different points in time. It includes understanding the planned construction methodology, assisting in the early identification of potential risks, visualizing the work for presentation purposes, simulating the work for analysis purposes, and generating animations for the planned progress.
The seventh category, Mapping, refers to topics related to mapping the scheduled activities to the BIM model components. It includes mapping to link the BIM model with the schedule to create the 4D BIM model. In addition, it includes automated mapping, which can be based on the scheduled activity codes and their similarity to the BIM model components or the linguistics, such as phrasing if the activity name matches the name of the BIM components. Furthermore, it includes the many-to-many context, which indicates that various scheduled activities might be aligned to only one component of the model (e.g., the different stages of painting for the same wall), while many components of the model might be aligned to only one schedule activity (e.g., the walls of a specific floor). Moreover, an additional topic was considered to be classified under this category: the WBS standard. Although this might seem to be a scheduling topic, the automated creation of the 4D BIM model—achieved by mapping schedule activities to the BIM components—depends on the schedule’s WBS, whether it is code-based or linguistic. Consequently, the standardization of the WBS facilitates the automated alignment process.
The eighth category, “Collaboration”, represents the group efforts done through the 4D BIM model. It includes utilizing the 4D BIM tool as an electronic platform for collaboration between users. In addition, it involves facilitating the schedule creation through virtual reality, which enables the co-creation of the schedule and empowers different stakeholders to contribute and provide feedback.

5. Conclusions

The BIM literature highlights various efforts to integrate AI techniques; however, both AI and BIM are very broad domains. NLP (a sub-domain of AI) enables computers to understand human language, while 4D BIM (a sub-domain of BIM) facilitates the integration of the BIM model with construction schedules. By combining NLP and 4D BIM, this paper offers a state-of-the-art review of both topics, which culminates in a framework for potential integrations.
The primary contribution of this paper includes addressing 72 topics, of which 45 are related to 4D BIM and 27 to NLP, in addition to classifying these topics into 13 categories. Eight of these categories are related to the 4D BIM (Tracking, BIM-based Scheduling, Point Cloud, Data Processing, Time–Space Management, Visual Simulation, Mapping, and Collaboration) while five categories are related to the NLP (NLP Techniques, NLP Enablers, NLP Functions, NLP–BIM Applications, and Integration of BIM with other AI Tools). These findings provide a significant foundation for exploring each identified category and the integration between the topics. The investigation of these integrations helps identify synergies, develop new tools and methodologies, and automate project management practices.
Another significant contribution is the results of exploring the utilization of NLP in each of the eight categories identified for 4D BIM. For the first category, Tracking, NLP can be used to compile the user requests directed to the 4D BIM tools such as querying progress, requesting a 4D scenario, or reporting the analyzed progress. For the second category, Point Cloud Comparisons, NLP can be used to conclude the findings of comparing the as-built point cloud against the 4D model at a certain point in time. This comparison needs to be analyzed and reported on different levels according to the reporting requirements. NLP can help solve these issues by introducing the results and summarizing the required conclusions. For the third category, BIM-Based Scheduling, the NLP helps transfer user commands phrased in natural language to the tools to support preparing the time schedule based on the model. This includes requesting that tools recommend scheduling strategies, suggest activity durations based on the quantities in the model, or ask for more what-if scenarios in the model structure that impact the time schedule. For the fourth category, Visual Simulation, NLP supports compiling the simulated videos into a written conclusion and identifying risks based on visual simulation.
For the fifth category, Time–Space Management, NLP enables the tools to respond to user queries regarding constructability notes related to time–space issues. It also enables analysis of the issues, the reporting of solutions in natural language, and the revision of solutions based on user comments. For the sixth category, Activity-Elements Mapping, NLP helps elucidate the meaning of the schedule activity, written in natural language, and maps it to the appropriate BIM element to support the preparation of the 4D BIM model. For the seventh category, Data Processing, NLP helps compile the requests of non-technical experts who want to query the model information without BIM tools. Keeping the information in the 4D BIM models requires experts to access and extract this information. However, empowering non-technical users to query the information of the 4D model using natural language facilitates data analysis and accelerates the decision-making process. For the last category, Work Collaboration, NLP helps leverage the utilization of the modeling tools as a collaboration environment. Enabling the use of natural language helps users write their queries to the tool, while the tool understands these queries and communicates them to the appropriate audience based on this understanding.
A key challenge is the quantitative validation of results. Although it was important to utilize a qualitative methodology in this research, as previously explained, quantitative validation of results would provide added value. Another challenge is the utilization of the NLP keyword to search databases, overlooking terms like BERT, RoBERTa, and GPT, which are specific pre-trained models. This oversight may have limited the scope of the identified articles. Future reviews should explicitly include such terms.
This review identifies critical avenues for advancing NLP in 4D BIM: (1) Tracking—future work must explore the utilization of NLP to automate the analysis of the periodic reports and update 4D BIM automatically; (2) Activity-Elements Mapping—exploring the automated mapping of schedule activities to the elements of the BIM model using NLP could accelerate the development of the 4D BIM model; (3) Work Collaboration—future studies should explore the utilization of NLP to understand user requests in order to enable stakeholders to propose different scheduling strategies and visualize them on the 4D BIM model.

Author Contributions

Conceptualization, M.E. and I.M.; methodology, M.E. and I.M.; investigation, M.E.; writing—original draft preparation, M.E.; writing—review and editing, I.M. and A.E.S.; visualization, M.E.; supervision, I.M. and A.E.S. All authors have read and agreed to the published version of the manuscript.

Funding

The authors declare that no funds, grants, or other financial support were received during the preparation of this manuscript.

Conflicts of Interest

The authors confirm that there are no conflicts of interest that could have biased this review. Due to copyright restrictions on the extracted data, only aggregated results are presented.

References

  1. AGC. The Contractors’ Guide to BIM; AGC Publication: Arlington, VA, USA; Associated General Contractors of America: Arlington, VA, USA, 2006; Available online: https://books.google.com.sa/books?id=LDk7HQAACAAJ (accessed on 20 March 2024).
  2. Aredah, A.S.; Baraka, M.A.; ElKhafif, M. Project Scheduling Techniques Within a Building Information Modeling (BIM) Environment: A Survey Study. IEEE Eng. Manag. Rev. 2019, 47, 133–143. [Google Scholar] [CrossRef]
  3. Kim, K.; Cho, Y.K. Construction-specific spatial information reasoning in Building Information Models. Adv. Eng. Inform. 2015, 29, 1013–1027. [Google Scholar] [CrossRef]
  4. Li, X.; Chi, H.; Wu, P.; Shen, G.Q. Smart work packaging-enabled constraint-free path re-planning for tower crane in prefabricated products assembly process. Adv. Eng. Inform. 2020, 43, 101008. [Google Scholar] [CrossRef]
  5. Sacks, R.; Girolami, M.; Brilakis, I. Building Information Modelling, Artificial Intelligence and Construction Tech. Dev. Built Environ. 2020, 4, 100011. [Google Scholar] [CrossRef]
  6. Park, J.; Kim, J.; Lee, D.; Jeong, K.; Lee, J.; Kim, H.; Hong, T. Deep Learning–Based Automation of Scan-to-BIM with Modeling Objects from Occluded Point Clouds. J. Manag. Eng. 2022, 38, 04022025. [Google Scholar] [CrossRef]
  7. Li, X.; Wu, P.; Shen, G.Q.; Wang, X.; Teng, Y. Mapping the knowledge domains of Building Information Modeling (BIM): A bibliometric approach. Autom. Constr. 2017, 84, 195–206. [Google Scholar] [CrossRef]
  8. Hosseini, M.R.; Martek, I.; Zavadskas, E.K.; Aibinu, A.A.; Arashpour, M.; Chileshe, N. Critical evaluation of off-site construction research: A Scientometric analysis. Autom. Constr. 2018, 87, 235–247. [Google Scholar] [CrossRef]
  9. Darko, A.; Chan, A.P.C.; Adabre, M.A.; Edwards, D.J.; Hosseini, M.R.; Ameyaw, E.E. Artificial intelligence in the AEC industry: Scientometric analysis and visualization of research activities. Autom. Constr. 2020, 112, 103081. [Google Scholar] [CrossRef]
  10. Pan, Y.; Zhang, L. Roles of artificial intelligence in construction engineering and management: A critical review and future trends. Autom. Constr. 2021, 122, 103517. [Google Scholar] [CrossRef]
  11. McKinney, K.; Fischer, M. Generating, evaluating and visualizing construction schedules with CAD tools. Autom. Constr. 1998, 7, 433–447. [Google Scholar] [CrossRef]
  12. Tucci, L.; Gillis, A.S.; Lutkevich, B.; Burns, E. A Guide to Artificial Intelligence in the Enterprise. TechTarget. 2024. Available online: https://www.techtarget.com/searchenterpriseai/Ultimate-guide-to-artificial-intelligence-in-the-enterprise (accessed on 10 April 2024).
  13. Creswell, J.W.; Poth, C.N. Qualitative Inquiry and Research Design; SAGE Publications: Thousand Oaks, CA, USA, 2016. [Google Scholar]
  14. Glaser, B.G.; Strauss, A.L. The Discovery of Grounded Theory: Strategies for Qualitative Research, 1st ed.; Routledge: New York, NY, USA, 2017. [Google Scholar] [CrossRef]
  15. Sacks, R.; Koskela, L.; Dave, B.A.; Owen, R. Interaction of Lean and Building Information Modeling in Construction. J. Constr. Eng. Manag. 2010, 136, 968–980. [Google Scholar] [CrossRef]
  16. Stojanovska-Georgievska, L.; Sandeva, I.; Krleski, A.; Spasevska, H.; Ginovska, M.; Panchevski, I.; Ivanov, R.; Perez Arnal, I.; Cerovsek, T.; Funtik, T. BIM in the Center of Digital Transformation of the Construction Sector—The Status of BIM Adoption in North Macedonia. Buildings 2022, 12, 218. [Google Scholar] [CrossRef]
  17. Khanzadi, M.; Sheikhkhoshkar, M.; Banihashemi, S. BIM applications toward key performance indicators of construction projects in Iran. Int. J. Constr. Manag. 2020, 20, 305–320. [Google Scholar] [CrossRef]
  18. Kim, Y.-W.; Ballard, G. Management Thinking in the Earned Value Method System and the Last Planner System. J. Manag. Eng. 2010, 26, 223–228. [Google Scholar] [CrossRef]
  19. Lee, S.-K.; Kim, K.-R.; Yu, J.-H. BIM and ontology-based approach for building cost estimation. Autom. Constr. 2014, 41, 96–105. [Google Scholar] [CrossRef]
  20. Akbarnezhad, A.; Ong, K.C.G.; Chandra, L.R. Economic and environmental assessment of deconstruction strategies using building information modeling. Autom. Constr. 2014, 37, 131–144. [Google Scholar] [CrossRef]
  21. Amiri, R.; Sardroud, J.M.; Soto, B.G.D. BIM-based Applications of Metaheuristic Algorithms to Support the Decision-making Process: Uses in the Planning of Construction Site Layout. Procedia Eng. 2017, 196, 558–564. [Google Scholar] [CrossRef]
  22. Cheng, J.C.P.; Ma, L.Y.H. A BIM-based system for demolition and renovation waste estimation and planning. Waste Manag. 2013, 33, 1539–1551. [Google Scholar] [CrossRef]
  23. Saieg, P.; Sotelino, E.D.; Nascimento, D.; Caiado, R.G.G. Interactions of Building Information Modeling, Lean and Sustainability on the Architectural, Engineering and Construction industry: A systematic review. J. Clean. Prod. 2018, 174, 788–806. [Google Scholar] [CrossRef]
  24. Santiago, P. BIM to BEM as Teaching Methodology to Support Sustainable Construction Decisions. Period. Polytech. Archit. 2016, 47, 94–98. [Google Scholar] [CrossRef]
  25. Lin, Y.C.; Hsu, Y.T.; Hu, H.T. BIM Model Management for BIM-Based Facility Management in Buildings. Adv. Civ. Eng. 2022, 2022, 1901201. [Google Scholar] [CrossRef]
  26. Zhang, S.; Teizer, J.; Lee, J.-K.; Eastman, C.M.; Venugopal, M. Building Information Modeling (BIM) and Safety: Automatic Safety Checking of Construction Models and Schedules. Autom. Constr. 2013, 29, 183–195. [Google Scholar] [CrossRef]
  27. Wang, K.; Zhang, C.; Guo, F.; Guo, S. Toward an Efficient Construction Process: What Drives BIM Professionals to Collaborate in BIM-Enabled Projects. J. Manag. Eng. 2022, 38, 04022033. [Google Scholar] [CrossRef]
  28. Wu, Z.; Chen, C.; Cai, Y.; Lu, C.; Wang, H.; Yu, T. BIM-Based Visualization Research in the Construction Industry: A Network Analysis. Int. J. Environ. Res. Public Health 2019, 16, 3473. [Google Scholar] [CrossRef]
  29. Alwisy, A.; Hamdan, S.B.; Barkokebas, B.; Bouferguene, A.; Al-Hussein, M. A BIM-based automation of design and drafting for manufacturing of wood panels for modular residential buildings. Int. J. Constr. Manag. 2019, 19, 187–205. [Google Scholar] [CrossRef]
  30. Wu, Y.; Shang, J.; Chen, P.; Zlatanova, S.; Hu, X.; Zhou, Z. Indoor mapping and modeling by parsing floor plan images. Int. J. Geogr. Inf. Sci. 2021, 35, 1205–1231. [Google Scholar] [CrossRef]
  31. Banfi, F.; Fai, S.; Brumana, R. BIM automation: Advanced modeling generative process for complex structures. In ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences; Copernicus GmbH: Göttingen, Germany, 2017; pp. 9–16. [Google Scholar] [CrossRef]
  32. Chong, O.W.; Zhang, J. Logic representation and reasoning for automated BIM analysis to support automation in offsite construction. Autom. Constr. 2021, 129, 103756. [Google Scholar] [CrossRef]
  33. Sigalov, K.; Ye, X.; König, M.; Hagedorn, P.; Blum, F.; Severin, B.; Hettmer, M.; Hückinghaus, P.; Wölkerling, J.; Groß, D. Automated Payment and Contract Management in the Construction Industry by Integrating Building Information Modeling and Blockchain-Based Smart Contracts. Appl. Sci. 2021, 11, 7653. [Google Scholar] [CrossRef]
  34. Zhang, J.; Luo, H.; Xu, J. Towards fully BIM-enabled building automation and robotics: A perspective of lifecycle information flow. Comput. Ind. 2022, 135, 103570. [Google Scholar] [CrossRef]
  35. Quinn, C.; Shabestari, A.Z.; Misic, T.; Gilani, S.; Litoiu, M.; McArthur, J.J. Building automation system—BIM integration using a linked data structure. Autom. Constr. 2020, 118, 103257. [Google Scholar] [CrossRef]
  36. Froese, T.; Grobler, F.; Ritzenthaler, J.; Yu, K.; Akinci, B.; Akbas, R.; Koo, B.; Barron, A.; Kunz, J.C. Industry Foundation Classes for Project Management—A Trial Implementation. J. Inf. Technol. Constr. 1999, 4, 17–36. [Google Scholar]
  37. Eastman, C.; Teicholz, P.; Sacks, R.; Liston, K. BIM Handbook: A Guide to Building Information Modeling for Owners, Managers, Designers, Engineers, and Contractors, 1st ed.; Wiley: Hoboken, NJ, USA, 2008. [Google Scholar] [CrossRef]
  38. Mazairac, W.; Beetz, J. BIMQL—An open query language for building information models. Adv. Eng. Inform. 2013, 27, 444–456. [Google Scholar] [CrossRef]
  39. Solihin, W.; Eastman, C.; Lee, Y.-C.; Yang, D.-H. A simplified relational database schema for transformation of BIM data into a query-efficient and spatially enabled database. Autom. Constr. 2017, 84, 367–383. [Google Scholar] [CrossRef]
  40. Deng, X.; Lai, H.; Xu, J.; Zhao, Y. Generic Language for Partial Model Extraction from an IFC Model Based on Selection Set. Appl. Sci. 2020, 10, 1968. [Google Scholar] [CrossRef]
  41. Wang, R.; Tang, Y. Research on Parsing and Storage of BIM Information Based on IFC Standard. IOP Conf. Ser. Earth Environ. Sci. 2021, 643, 012172. [Google Scholar] [CrossRef]
  42. OSArch. IfcOpenShell. 16 February 2024. Available online: https://wiki.osarch.org/index.php?title=IfcOpenShell (accessed on 1 March 2024).
  43. PMI. A Guide to the Project Management Body of Knowledge (PMBOK® Guide); Project Management Institute, Inc.: Newtown Square, PA, USA, 2017. [Google Scholar]
  44. Kenley, R.; Harfield, T. Reviewing the IJPM for WBS: The Search for Planning and Control. Procedia—Soc. Behav. Sci. 2014, 119, 887–893. [Google Scholar] [CrossRef]
  45. Siami-Irdemoosa, E.; Dindarloo, S.R.; Sharifzadeh, M. Work breakdown structure (WBS) development for underground construction. Autom. Constr. 2015, 58, 85–94. [Google Scholar] [CrossRef]
  46. CSI. UniFormat®: A Uniform Classification of Construction Systems and Assemblies; Construction Specifications Institute (CSI): Alexandria, VA, USA, 2010. [Google Scholar]
  47. CSI. MasterFormat® Numbers & Titles; Construction Specifications Institute (CSI): Alexandria, VA, USA, 2016. [Google Scholar]
  48. CSI. OmniClass; Construction Specifications Institute (CSI): Alexandria, VA, USA, 2019. [Google Scholar]
  49. De Vries, B.; Harink, J.M.J. Generation of a construction planning from a 3D CAD model. Autom. Constr. 2007, 16, 13–18. [Google Scholar] [CrossRef]
  50. Nawaz, A.; Su, X.; Nasir, I.M. BIM Adoption and Its Impact on Planning and Scheduling Influencing Mega Plan Projects- (CPEC-) Quantitative Approach. Complexity 2021, 2021, 8818296. [Google Scholar] [CrossRef]
  51. Mikulakova, E.; König, M.; Tauscher, E.; Beucke, K. Knowledge-based schedule generation and evaluation. Adv. Eng. Inform. 2010, 24, 389–403. [Google Scholar] [CrossRef]
  52. Kim, H.; Anderson, K.; Lee, S.; Hildreth, J. Generating construction schedules through automatic data extraction using open BIM (building information modeling) technology. Autom. Constr. 2013, 35, 285–295. [Google Scholar] [CrossRef]
  53. Chen, S.-M.; (Bud) Griffis, F.H.; Chen, P.-H.; Chang, L.-M. A framework for an automated and integrated project scheduling and management system. Autom. Constr. 2013, 35, 89–110. [Google Scholar] [CrossRef]
  54. Nusen, P.; Boonyung, W.; Nusen, S.; Panuwatwanich, K.; Champrasert, P.; Kaewmoracharoen, M. Construction Planning and Scheduling of a Renovation Project Using BIM-Based Multi-Objective Genetic Algorithm. Appl. Sci. 2021, 11, 4716. [Google Scholar] [CrossRef]
  55. Faghihi, V.; Reinschmidt, K.F.; Kang, J.H. Construction scheduling using Genetic Algorithm based on Building Information Model. Expert Syst. Appl. 2014, 41, 7565–7578. [Google Scholar] [CrossRef]
  56. Hartmann, V.; Beucke, K.E.; Shapir, K.; König, M. Model-based Scheduling for Construction Planning. In Proceedings of the 14th International Conference on Computing in Civil and Building Engineering, Moscow, Russia, 27–29 June 2012; Available online: https://api.semanticscholar.org/CorpusID:17071843 (accessed on 10 April 2024).
  57. Liu, H.; Al-Hussein, M.; Lu, M. BIM-based integrated approach for detailed construction scheduling under resource constraints. Autom. Constr. 2015, 53, 29–43. [Google Scholar] [CrossRef]
  58. Kim, K.; Park, J.; Cho, C. Framework for Automated Generation of Constructible Steel Erection Sequences Using Structural Information of Static Indeterminacy Variation in BIM. KSCE J. Civ. Eng. 2020, 24, 3169–3178. [Google Scholar] [CrossRef]
  59. Isaac, S.; Shimanovich, M. Automated scheduling and control of mechanical and electrical works with BIM. Autom. Constr. 2021, 124, 103600. [Google Scholar] [CrossRef]
  60. Park, J.; Cai, H. WBS-based dynamic multi-dimensional BIM database for total construction as-built documentation. Autom. Constr. 2017, 77, 15–23. [Google Scholar] [CrossRef]
  61. Tallgren, M.V.; Roupé, M.; Johansson, M.; Bosch-Sijtsema, P. BIM tool development enhancing collaborative scheduling for pre-construction. J. Inf. Technol. Constr. 2020, 25, 374–397. [Google Scholar] [CrossRef]
  62. Sbiti, M.; Beddiar, K.; Beladjine, D.; Perrault, R.; Mazari, B. Toward BIM and LPS Data Integration for Lean Site Project Management: A State-of-the-Art Review and Recommendations. Buildings 2021, 11, 196. [Google Scholar] [CrossRef]
  63. Crowther, J.; Ajayi, S.O. Impacts of 4D BIM on construction project performance. Int. J. Constr. Manag. 2021, 21, 724–737. [Google Scholar] [CrossRef]
  64. Tallgren, M.V.; Roupé, M.; Johansson, M. 4D modelling using virtual collaborative planning and scheduling. J. Inf. Technol. Constr. 2021, 26, 763–782. [Google Scholar] [CrossRef]
  65. Gong, P.; Zeng, N.; Ye, K.; König, M. An Empirical Study on the Acceptance of 4D BIM in EPC Projects in China. Sustainability 2019, 11, 1316. [Google Scholar] [CrossRef]
  66. Jupp, J. 4D BIM for Environmental Planning and Management. Procedia Eng. 2017, 180, 190–201. [Google Scholar] [CrossRef]
  67. Chou, H.-Y.; Yang, J.-B. Preliminary Evaluation of BIM-based Approaches for Schedule Delay Analysis. IOP Conf. Ser. Mater. Sci. Eng. 2017, 245, 062048. [Google Scholar] [CrossRef]
  68. Ma, G.; Zhang, L. Exact Overlap Rate Analysis and the Combination with 4D BIM of Time-Cost Tradeoff Problem in Project Scheduling. Adv. Civ. Eng. 2019, 2019, 9120795. [Google Scholar] [CrossRef]
  69. Sloot, R.N.F.; Heutink, A.; Voordijk, J.T. Assessing usefulness of 4D BIM tools in risk mitigation strategies. Autom. Constr. 2019, 106, 102881. [Google Scholar] [CrossRef]
  70. Guerra, B.C.; Leite, F.; Faust, K.M. 4D-BIM to enhance construction waste reuse and recycle planning: Case studies on concrete and drywall waste streams. Waste Manag. 2020, 116, 79–90. [Google Scholar] [CrossRef]
  71. Liu, A.H.; Ellul, C.; Swiderska, M. Decision Making in the 4th Dimension—Exploring Use Cases and Technical Options for the Integration of 4D BIM and GIS during Construction. ISPRS Int. J. Geo-Inf. 2021, 10, 203. [Google Scholar] [CrossRef]
  72. Tran, S.V.-T.; Khan, N.; Lee, D.; Park, C. A Hazard Identification Approach of Integrating 4D BIM and Accident Case Analysis of Spatial–Temporal Exposure. Sustainability 2021, 13, 2211. [Google Scholar] [CrossRef]
  73. Cheng, M.-Y.; Chang, N.-W. Dynamic construction material layout planning optimization model by integrating 4D BIM. Eng. Comput. 2019, 35, 703–720. [Google Scholar] [CrossRef]
  74. Kolarić, S.; Vukomanović, M.; Ramljak, A. Analyzing the Level of Detail of Construction Schedule for Enabling Site Logistics Planning (SLP) in the Building Information Modeling (BIM) Environment. Sustainability 2022, 14, 6701. [Google Scholar] [CrossRef]
  75. Di Donato, D.; Abita, M. Low-cost 4d bim modelling: A comparison between freecad and commercial software. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. 2019, 42, 107–114. [Google Scholar] [CrossRef]
  76. Nechyporchuk, Y.; Bašková, R. The conformity of the tools of selected software programs for 4D building modeling. IOP Conf. Ser. Mater. Sci. Eng. 2020, 867, 012034. [Google Scholar] [CrossRef]
  77. Son, H.; Kim, C.; Cho, Y.K. Automated Schedule Updates Using As-Built Data and a 4D Building Information Model. J. Manag. Eng. 2017, 33, 04017012. [Google Scholar] [CrossRef]
  78. Han, K.K.; Cline, D.; Golparvar-Fard, M. Formalized knowledge of construction sequencing for visual monitoring of work-in-progress via incomplete point clouds and low-LoD 4D BIMs. Adv. Eng. Inform. 2015, 29, 889–901. [Google Scholar] [CrossRef]
  79. Maalek, R.; Lichti, D.D.; Ruwanpura, J.Y. Automatic Recognition of Common Structural Elements from Point Clouds for Automated Progress Monitoring and Dimensional Quality Control in Reinforced Concrete Construction. Remote Sens. 2019, 11, 1102. [Google Scholar] [CrossRef]
  80. Tuttas, S.; Braun, A.; Borrmann, A.; Stilla, U. Acquisition and Consecutive Registration of Photogrammetric Point Clouds for Construction Progress Monitoring Using a 4D BIM. PFG—J. Photogramm. Remote Sens. Geoinform. Sci. 2017, 85, 3–15. [Google Scholar] [CrossRef]
  81. Bassier, M.; Vincke, S.; Mattheuwsen, L.; De Lima Hernandez, R.; Derdaele, J.; Vergauwen, M. Percentage of completion of in-situ cast concrete walls using point cloud data and bim. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. 2019, 42, 21–28. [Google Scholar] [CrossRef]
  82. Xue, J.; Hou, X.; Zeng, Y. Review of Image-Based 3D Reconstruction of Building for Automated Construction Progress Monitoring. Appl. Sci. 2021, 11, 7840. [Google Scholar] [CrossRef]
  83. Kim, S.; Kim, S.; Lee, D.-E. 3D Point Cloud and BIM-Based Reconstruction for Evaluation of Project by As-Planned and As-Built. Remote Sens. 2020, 12, 1457. [Google Scholar] [CrossRef]
  84. Hamledari, H.; Sajedi, S.; McCabe, B.; Fischer, M. Automation of Inspection Mission Planning Using 4D BIMs and in Support of Unmanned Aerial Vehicle–Based Data Collection. J. Constr. Eng. Manag. 2021, 147, 04020179. [Google Scholar] [CrossRef]
  85. Kropp, C.; Koch, C.; König, M. Interior construction state recognition with 4D BIM registered image sequences. Autom. Constr. 2018, 86, 11–32. [Google Scholar] [CrossRef]
  86. Ngai, E.W.T.; Moon, K.K.L.; Riggins, F.J.; Yi, C.Y. RFID research: An academic literature review (1995–2005) and future research directions. Int. J. Prod. Econ. 2008, 112, 510–520. [Google Scholar] [CrossRef]
  87. Li, X.; Shen, G.Q.; Wu, P.; Fan, H.; Wu, H.; Teng, Y. RBL-PHP: Simulation of Lean Construction and Information Technologies for Prefabrication Housing Production. J. Manag. Eng. 2018, 34, 04017053. [Google Scholar] [CrossRef]
  88. Mazars, T.; Francis, A. Chronographical spatiotemporal dynamic 4D planning. Autom. Constr. 2020, 112, 103076. [Google Scholar] [CrossRef]
  89. Francis, A.; Morin-Pepin, S. The Concept of Float Calculation Based on the Site Occupation using the Chronographical Logic. Procedia Eng. 2017, 196, 690–697. [Google Scholar] [CrossRef]
  90. Ballard, H.G. The Last Planner System of Production Control; University of Birmingham: Birmingham, UK, 2000; Available online: https://etheses.bham.ac.uk/id/eprint/4789/1/Ballard00PhD.pdf (accessed on 15 April 2024).
  91. Ballard, G.; Tommelein, I. Lean management methods for complex projects. Eng. Proj. Organ. J. 2012, 2, 85–96. [Google Scholar] [CrossRef]
  92. Heigermoser, D.; De Soto, B.G.; Abbott, E.L.S.; Chua, D.K.H. BIM-based Last Planner System tool for improving construction project management. Autom. Constr. 2019, 104, 246–254. [Google Scholar] [CrossRef]
  93. Schimanski, C.P.; Marcher, C.; Pasetti Monizza, G.; Matt, D.T. The Last Planner® System and Building Information Modeling in Construction Execution: From an Integrative Review to a Conceptual Model for Integration. Appl. Sci. 2020, 10, 821. [Google Scholar] [CrossRef]
  94. Cheng, J.C.P.; Tan, Y.; Song, Y.; Liu, X.; Wang, X. A semi-automated approach to generate 4D/5D BIM models for evaluating different offshore oil and gas platform decommissioning options. Vis. Eng. 2017, 5, 12. [Google Scholar] [CrossRef]
  95. Bassir, D.; Lodge, H.; Chang, H.; Majak, J.; Chen, G. Application of artificial intelligence and machine learning for BIM: Review. Int. J. Simul. Multidiscip. Des. Optim. 2023, 14, 5. [Google Scholar] [CrossRef]
  96. Nikolaeva, D.R.; Nikolenko, T.A. Methodological basis for using artificial intelligence technologies in a construction company. IOP Conf. Ser. Earth Environ. Sci. 2021, 751, 012106. [Google Scholar] [CrossRef]
  97. Fridgeirsson, T.V.; Ingason, H.T.; Jonasson, H.I.; Jonsdottir, H. An Authoritative Study on the Near Future Effect of Artificial Intelligence on Project Management Knowledge Areas. Sustainability 2021, 13, 2345. [Google Scholar] [CrossRef]
  98. Wauters, M.; Vanhoucke, M. A comparative study of Artificial Intelligence methods for project duration forecasting. Expert Syst. Appl. 2016, 46, 249–261. [Google Scholar] [CrossRef]
  99. Hajdasz, M. Flexible management of repetitive construction processes by an intelligent support system. Expert Syst. Appl. 2014, 41, 962–973. [Google Scholar] [CrossRef]
  100. Rada, R.; Mili, H.; Bicknell, E.; Blettner, M. Development and application of a metric on semantic nets. IEEE Trans. Syst. Man Cybern. 1989, 19, 17–30. [Google Scholar] [CrossRef]
  101. Miller, G.A.; Charles, W.G. Contextual correlates of semantic similarity. Lang. Cogn. Process. 1991, 6, 1–28. [Google Scholar] [CrossRef]
  102. Miller, G.A.; Beckwith, R.; Fellbaum, C.; Gross, D.; Miller, K.J. Introduction to WordNet: An On-line Lexical Database *. Int. J. Lexicogr. 1990, 3, 235–244. [Google Scholar] [CrossRef]
  103. Meng, L.; Huang, R.; Gu, J. A Review of Semantic Similarity Measures in WordNet. Int. J. Hybrid Inf. Technol. 2013, 6, 1–12. [Google Scholar]
  104. Wajid, U.; Namoun, A.; Marín, C.A.; Mehandjiev, N. Designing and evaluating a system of document recognition to support interoperability among collaborative enterprises. Comput. Ind. 2013, 64, 598–608. [Google Scholar] [CrossRef]
  105. Ittoo, A.; Nguyen, L.M.; Van Den Bosch, A. Text analytics in industry: Challenges, desiderata and trends. Comput. Ind. 2016, 78, 96–107. [Google Scholar] [CrossRef]
  106. Khan, Z.; Vorley, T. Big data text analytics: An enabler of knowledge management. J. Knowl. Manag. 2017, 21, 18–34. [Google Scholar] [CrossRef]
  107. Liang, Y.; Liu, Y.; Chen, C.; Jiang, Z. Extracting topic-sensitive content from textual documents—A hybrid topic model approach. Eng. Appl. Artif. Intell. 2018, 70, 81–91. [Google Scholar] [CrossRef]
  108. Al-Maitah, M. Text analytics for big data using rough–fuzzy soft computing techniques. Expert Syst. 2019, 36, e12463. [Google Scholar] [CrossRef]
  109. Zhou, M.; Duan, N.; Liu, S.; Shum, H.-Y. Progress in Neural NLP: Modeling, Learning, and Reasoning. Engineering 2020, 6, 275–290. [Google Scholar] [CrossRef]
  110. Ding, Y.; Ma, J.; Luo, X. Applications of natural language processing in construction. Autom. Constr. 2022, 136, 104169. [Google Scholar] [CrossRef]
  111. Devlin, J.; Chang, M.-W.; Lee, K.; Toutanova, K. BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding. arXiv 2018, arXiv:1810.04805. [Google Scholar]
  112. Brown, T.; Mann, B.; Ryder, N.; Subbiah, M.; Kaplan, J.D.; Dhariwal, P.; Neelakantan, A.; Shyam, P.; Sastry, G.; Askell, A.; et al. Language Models are Few-Shot Learners. Adv. Neural Inf. Process. Syst. 2020, 33, 1877–1901. [Google Scholar] [CrossRef]
  113. Wagner, W. Steven Bird, Ewan Klein and Edward Loper: Natural Language Processing with Python, Analyzing Text with the Natural Language Toolkit. Lang. Resour. Eval. 2010, 44, 421–424. [Google Scholar] [CrossRef]
  114. Wu, C.; Li, X.; Guo, Y.; Wang, J.; Ren, Z.; Wang, M.; Yang, Z. Natural language processing for smart construction: Current status and future directions. Autom. Constr. 2022, 134, 104059. [Google Scholar] [CrossRef]
  115. Lin, J.; Hu, Z.; Zhang, J.; Yu, F. A Natural-Language-Based Approach to Intelligent Data Retrieval and Representation for Cloud BIM. Comput.-Aided Civ. Infrastruct. Eng. 2016, 31, 18–33. [Google Scholar] [CrossRef]
  116. Xie, Q.; Zhou, X.; Wang, J.; Gao, X.; Chen, X.; Chun, L. Matching Real-World Facilities to Building Information Modeling Data Using Natural Language Processing. IEEE Access 2019, 7, 119465–119475. [Google Scholar] [CrossRef]
  117. Zhang, J.; El-Gohary, N.M. Extending Building Information Models Semiautomatically Using Semantic Natural Language Processing Techniques. J. Comput. Civ. Eng. 2016, 30, C4016004. [Google Scholar] [CrossRef]
  118. Zhou, S.; Ng, S.T.; Lee, S.H.; Xu, F.J.; Yang, Y. A domain knowledge incorporated text mining approach for capturing user needs on BIM applications. Eng. Constr. Archit. Manag. 2019, 27, 458–482. [Google Scholar] [CrossRef]
  119. Tyagi, N.; Bhushan, B. Demystifying the Role of Natural Language Processing (NLP) in Smart City Applications: Background, Motivation, Recent Advances, and Future Research Directions. Wirel. Pers. Commun. 2023, 130, 857–908. [Google Scholar] [CrossRef]
  120. Lee, J.; Ham, Y.; Yi, J.-S.; Son, J. Effective Risk Positioning through Automated Identification of Missing Contract Conditions from the Contractor’s Perspective Based on FIDIC Contract Cases. J. Manag. Eng. 2020, 36, 05020003. [Google Scholar] [CrossRef]
  121. Lee, J.; Yi, J.-S.; Son, J. Development of Automatic-Extraction Model of Poisonous Clauses in International Construction Contracts Using Rule-Based NLP. J. Comput. Civ. Eng. 2019, 33, 04019003. [Google Scholar] [CrossRef]
  122. Lee, J.; Yi, J.-S. Predicting Project’s Uncertainty Risk in the Bidding Process by Integrating Unstructured Text Data and Structured Numerical Data Using Text Mining. Appl. Sci. 2017, 7, 1141. [Google Scholar] [CrossRef]
  123. Fan, H.; Xue, F.; Li, H. Project-Based As-Needed Information Retrieval from Unstructured AEC Documents. J. Manag. Eng. 2015, 31, A4014012. [Google Scholar] [CrossRef]
  124. Cheng, M.-Y.; Kusoemo, D.; Gosno, R.A. Text mining-based construction site accident classification using hybrid supervised machine learning. Autom. Constr. 2020, 118, 103265. [Google Scholar] [CrossRef]
  125. Tixier, A.J.-P.; Hallowell, M.R.; Rajagopalan, B.; Bowman, D. Construction Safety Clash Detection: Identifying Safety Incompatibilities among Fundamental Attributes using Data Mining. Autom. Constr. 2017, 74, 39–54. [Google Scholar] [CrossRef]
  126. Locatelli, M.; Seghezzi, E.; Pellegrini, L.; Tagliabue, L.C.; Di Giuda, G.M. Exploring Natural Language Processing in Construction and Integration with Building Information Modeling: A Scientometric Analysis. Buildings 2021, 11, 583. [Google Scholar] [CrossRef]
  127. Wang, J.; Gao, X.; Zhou, X.; Xie, Q. Multi-scale Information Retrieval for BIM using Hierarchical Structure Modelling and Natural Language Processing. J. Inf. Technol. Constr. 2021, 26, 409–426. [Google Scholar] [CrossRef]
  128. Yin, M.; Tang, L.; Webster, C.; Xu, S.; Li, X.; Ying, H. An ontology-aided, natural language-based approach for multi-constraint BIM model querying. J. Build. Eng. 2023, 76, 107066. [Google Scholar] [CrossRef]
  129. Nabavi, A.; Ramaji, I.; Sadeghi, N.; Anderson, A. Leveraging Natural Language Processing for Automated Information Inquiry from Building Information Models. J. Inf. Technol. Constr. 2023, 28, 266–285. [Google Scholar] [CrossRef]
  130. Wang, H.; Meng, X.; Zhu, X. Improving knowledge capture and retrieval in the BIM environment: Combining case-based reasoning and natural language processing. Autom. Constr. 2022, 139, 104317. [Google Scholar] [CrossRef]
Information 16 00457 g001
Figure 1. Number of reviewed articles in selected publications.
Figure 1. Number of reviewed articles in selected publications.
Information 16 00457 g001
Information 16 00457 g002
Figure 2. The framework of NLP–4D BIM integration, showing identified categories.
Figure 2. The framework of NLP–4D BIM integration, showing identified categories.
Information 16 00457 g002
Information 16 00457 g003
Figure 3. Overview of the obtained NLP codes and categories.
Figure 3. Overview of the obtained NLP codes and categories.
Information 16 00457 g003
Information 16 00457 g004
Figure 4. Overview of the identified 4D BIM codes and categories.
Figure 4. Overview of the identified 4D BIM codes and categories.
Information 16 00457 g004
Table 1. Codes and categories.
Table 1. Codes and categories.
SectionCodeCategorySectionCodeCategory
BIMVisualizing for presentationVisual Simulation4D BIMPoint cloud challenges: Occlusions and noisePoint Cloud
BIMProgress MeasurementTracking4D BIMGathering progress data through unmanned Aerial VehiclesTracking
BIMSafety Management based on as-planned simulationTime-space management4D BIMInterior progress measurement through image analysisPoint Cloud
BIMConstruction ProcessesTime-space management4D BIMAI techniques to compensate occluded elementsPoint Cloud
BIMIFC Parsing Data Processing4D BIMGathering progress data through RFIDTracking
BIMconstructibilityTime-space management4D BIMLast planner system (LPS) using the modelBIM-based Scheduling
BIMcollaboration through the 4D BIM systemCollaboration4D BIMCode-based mapping using Similarity of Task IDMapping
BIMSite layout planningTime-space management4D BIMLinguistic-based mapping of components to activitiesMapping
BIMInteroperabilityData Processing4D BIMMany-to-many context for both model and scheduleMapping
BIMSimulation for AnalysisVisual SimulationAI/NLPExpert systemsIntegration with other AI Tools
BIMInformation extractionData ProcessingAI/NLPGenetic algorithmsIntegration with other AI Tools
BIMGathering and communicating site data through RobotsTrackingAI/NLPNural networkIntegration with other AI Tools
BIMGathering progress data through sensorsTrackingAI/NLPFuzzy logic & Fuzzy setsIntegration with other AI Tools
BIMCommunicating site data to the model through IOTTrackingAI/NLPMachine LearningIntegration with other AI Tools
BIMBIM Query LanguagesData ProcessingAI/NLPSemantic NetNLP Enablers
BIMRepresenting BIM Data using relational DatabaseData ProcessingAI/NLPWord NetNLP Enablers
SchedulingWBS Creation Based on the modelBIM-based SchedulingAI/NLPTokenizationNLP Techniques
SchedulingDuration estimate based on the modelBIM-based SchedulingAI/NLPLemmatizationNLP Techniques
SchedulingTransfer model components into activitiesBIM-based SchedulingAI/NLPStemmingNLP Techniques
SchedulingQuantities of schedule activities based on the modelBIM-based SchedulingAI/NLPDocument RecognitionNLP Functions
SchedulingWBS StandardsMappingAI/NLPExtraction of Topic-related ContentNLP Functions
SchedulingWBS-based data base structureData ProcessingAI/NLPMachine Translation NLP Functions
SchedulingData Entity Relationship DiagramData ProcessingAI/NLPMachine ReadingNLP Functions
SchedulingContribution of stakeholder to the scheduleCollaborationAI/NLPChatbotNLP Functions
SchedulingMap BIM components to schedule activitiesMappingAI/NLPgenerative Pre-training (GPT)Integration with other AI Tools
4D BIMAnimationVisual SimulationAI/NLPSyntactic Parsing (SP)NLP Functions
4D BIMProcurement trackingTrackingAI/NLPPart-of-speechNLP Techniques
4D BIMEarly identification of potential risksVisual SimulationAI/NLPTopic modelingNLP Techniques
4D BIMSchedule co-creation using VRCollaborationAI/NLPUnderstanding Users’ RequestNLP-BIM Application
4D BIMRepresenting and understanding construction methodologyVisual SimulationAI/NLPMapping User Request to BIM ComponentsNLP-BIM Application
4D BIMEvaluating different scheduling scenariosBIM-based SchedulingAI/NLPBIM Querying—Attribute Constraints NLP-BIM Application
4D BIMPlanning of material handlingTime-space managementAI/NLPTagging NLP Techniques
4D BIMEquipment modelingTime-space managementAI/NLPInternational framework for dictionariesNLP Enablers
4D BIMCompare point cloud to as-planned for delay analysisPoint CloudAI/NLPBIM Querying—Relational Constraints NLP-BIM Application
4D BIMLogistics managementTime-space managementAI/NLPAutomated BIM Compliance CheckingNLP-BIM Application
4D BIMProgress measurement using point cloud to update the schedulePoint CloudAI/NLPContinuous Capturing of Project InformationNLP-BIM Application
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

ElSaadany, M.; Motawa, I.; El Sheikh, A. Integrating Natural Language Processing with 4D BIM: A Review and Thematic Synthesis. Information 2025, 16, 457. https://doi.org/10.3390/info16060457

AMA Style

ElSaadany M, Motawa I, El Sheikh A. Integrating Natural Language Processing with 4D BIM: A Review and Thematic Synthesis. Information. 2025; 16(6):457. https://doi.org/10.3390/info16060457

Chicago/Turabian Style

ElSaadany, Mohamed, Ibrahim Motawa, and Asser El Sheikh. 2025. "Integrating Natural Language Processing with 4D BIM: A Review and Thematic Synthesis" Information 16, no. 6: 457. https://doi.org/10.3390/info16060457

APA Style

ElSaadany, M., Motawa, I., & El Sheikh, A. (2025). Integrating Natural Language Processing with 4D BIM: A Review and Thematic Synthesis. Information, 16(6), 457. https://doi.org/10.3390/info16060457

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop