Automated Building Information Modeling Compliance Check through a Large Language Model Combined with Deep Learning and Ontology

被引:3
作者
Chen, Nanjiang [1 ]
Lin, Xuhui [2 ]
Jiang, Hai [1 ]
An, Yi [3 ]
机构
[1] Tsinghua Univ, Dept Ind Engn, Beijing 100084, Peoples R China
[2] UCL, Barlett Sch Sustainable Construct, London WC1E 6BT, England
[3] Cardiff Univ, Dept Engn, Cardiff CF24 3AA, Wales
关键词
automated compliance check; large language models (LLMs); deep learning; ontology knowledge models; BIM; design regulations;
D O I
10.3390/buildings14071983
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Ensuring compliance with complex industry standards and regulations during the design and implementation phases of construction projects is a significant challenge in the building information modeling (BIM) domain. Traditional manual compliance checking methods are inefficient and error-prone, failing to meet modern engineering demands. Natural language processing (NLP) and deep learning methods have improved efficiency and accuracy in rule interpretation and compliance checking. However, these methods still require extensive manual feature engineering, large, annotated datasets, and significant computational resources. Large language models (LLMs) provide robust language understanding with minimal labeled data due to their pre-training and few-shot learning capabilities. However, their application in the AEC field is still limited by the need for fine-tuning for specific tasks, handling complex texts with nested clauses and conditional statements. This study introduces an innovative automated compliance checking framework that integrates LLM, deep learning models, and ontology knowledge models. The use of LLM is motivated by its few-shot learning capability, which significantly reduces the need for large, annotated datasets required by previous methods. Deep learning is employed to preliminarily classify regulatory texts, which further enhances the accuracy of structured information extraction by the LLM compared to directly feeding raw data into the LLM. This novel combination of deep learning and LLM significantly enhances the efficiency and accuracy of compliance checks by automating the processing of regulatory texts and reducing manual intervention. This approach is crucial for architects, engineers, project managers, and regulators, providing a scalable and adaptable solution for automated compliance in the construction industry with broad application prospects.
引用
收藏
页数:28
相关论文
共 32 条
  • [1] Achiam OJ, 2023, Arxiv, DOI [arXiv:2303.08774, 10.48550/arXiv.2303.08774, DOI 10.48550/ARXIV.2303.08774]
  • [2] Effective 20 Newsgroups Dataset Cleaning
    Albishre, Khaled
    Albathan, Mubarak
    Li, Yuefeng
    [J]. 2015 IEEE/WIC/ACM INTERNATIONAL CONFERENCE ON WEB INTELLIGENCE AND INTELLIGENT AGENT TECHNOLOGY (WI-IAT), VOL 3, 2015, : 98 - 101
  • [3] [Anonymous], 2011, Residential Design Specification
  • [4] Borrmann A., 2018, Build. Inf. Model., P1, DOI [10.1007/978-3-319-92862-3_1, DOI 10.1007/978-3-319-92862-3_1]
  • [5] Brown TB, 2020, ADV NEUR IN, V33
  • [6] Chowdhery A., 2022, arXiv preprint arXiv:2204.02311, V24, P1
  • [7] Devlin J, 2019, Arxiv, DOI [arXiv:1810.04805, DOI 10.48550/ARXIV.1810.04805]
  • [8] Automatic rule-based checking of building designs
    Eastman, C.
    Lee, Jae-min
    Jeong, Yeon-suk
    Lee, Jin-kook
    [J]. AUTOMATION IN CONSTRUCTION, 2009, 18 (08) : 1011 - 1033
  • [9] Domain Ontology for Processes in Infrastructure and Construction
    El-Gohary, Nora M.
    El-Diraby, Tamer E.
    [J]. JOURNAL OF CONSTRUCTION ENGINEERING AND MANAGEMENT, 2010, 136 (07) : 730 - 744
  • [10] Fuchs S., 2021, P C CIB W78, DOI DOI 10.13140/RG.2.2.29107.55845