Extracting Information from Construction Safety Requirements Using Large Language Model Si Tran Chung Ang University, Korea, Republic of Nasrullah Khan Chung Ang University, Korea, Republic of Emmanuel Charles Kimito Chung Ang University, Korea, Republic of Akeem Pedro Chung Ang University, Korea, Republic of Mehrtash Soltani Chung Ang University, Korea, Republic of Rahat Hussain Chung Ang University, Korea, Republic of Taehan Yoo Chung Ang University, Korea, Republic of Chansik Park Chung Ang University, Korea, Republic of This is a section of CONVR 2023 - Proceedings of the 23rd International Conference on Construction Applications of Virtual Reality (DOI: 10.36253/979-12-215-0289-3) by Pietro Capone, Vito Getuli, Farzad Pour Rahimian, Nashwan Dawood, Alessandro Bruttini, Tommaso Sorbi Firenze University Press Florence 2023 https://doi.org/10.36253/10.36253/979-12-215-0289-3.76

Available for academic research purposes

Open Access

Copyright Author(s)

Content licence CC BY-NC 4.0

Metadata licence CC0 1.0

This is original content, published for academic research purposes

 Digital edition XML powered by Booksflow

The construction industry has long been recognized for its complex safety regulations, which are essential to ensure the well-being of on-site employees. However, navigating these regulations and ensuring compliance can be challenging due to the volume and complexity of the documents involved. This study proposes a novel approach to extracting information from construction safety documents utilizing Large Language Models (LLM), called CSQA, to provide real-time, precise answers to queries related to safety regulations. The approach comprises three modules: (1) the construction safety investigation module (CSI) collects safety regulations for building the information needed. By leveraging a collection of safety regulation PDFs, the system follows a process of text extraction, preprocessing, and global indexing for efficient search. (2) The safety condition identification module (SCI) retrieves the CSI database; after that, the LLM, with its extensive training, processes user queries, searches the indexed regulations, and retrieves pertinent information. (3) the safety information delivery (SID) would provide the answer to the user and incorporate a feedback mechanism to further refine system accuracy based on user responses. Preliminary evaluations reveal the system's superior performance over traditional search engines, owing to its ability to grasp query context and nuances. The CSQA presents a promising method for accessing safety regulations, with potential benefits including reduced non-compliance incidents, enhanced worker safety, and streamlined regulatory consultations in construction

 Construction safety document extraction LLM

It is available online at https://doi.org/10.36253/10.36253/979-12-215-0289-3.76

References Baker, H., Hallowell, M. R., & Tixier, A. J. P. (2020). Automatically learning construction injury precursors from text. Automation in Construction, 118, 103145. 10.1016/J.AUTCON.2020.103145 Bao, L., Tran, S. V. T., Nguyen, T. L., Pham, H. C., Lee, D., & Park, C. (2022). Cross-platform virtual reality for real-time construction safety training using immersive web and industry foundation classes. Automation in Construction, 143, 104565. 10.1016/J.AUTCON.2022.104565 Construction Work | Statistics Korea. (n.d.). Retrieved October 6, 2022, from http://kostat.go.kr/portal/eng/pressReleases/4/5/index.board Feng, D., & Chen, H. (2021). A small samples training framework for deep Learning-based automatic information extraction: Case study of construction accident news reports analysis. Advanced Engineering Informatics, 47, 101256. 10.1016/J.AEI.2021.101256 Jeong, H., Shin, & Wonsang. (2023). An Analysis on the Safety Management Level of Domestic Medium Construction Companies and Its Improvement Measures. Korean Journal of Construction Engineering and Management, 24(3), 20–30. 10.6106/KJCEM.2023.24.3.020 Kang, Jeong, H., Chae, J., & Kang, Y. (2023). Distribution of Occupational Safety and Health Management Costs (OSHMC) by Project Size and Activity Type with the Consideration of Accident Rates. Korean Journal of Construction Engineering and Management, 24(4), 44–51. 10.6106/KJCEM.2023.24.4.044 OSHA fatality report. (n.d.). Retrieved October 6, 2022, from https://www.osha.gov/stop-falls Rupasinghe, N. K. A. H., & Panuwatwanich, K. (2021). UNDERSTANDING CONSTRUCTION SITE SAFETY HAZARDS THROUGH OPEN DATA: TEXT MINING APPROACH. ASEAN Engineering Journal, 11(4), 160–178. 10.11113/AEJ.V11.17871 Tran, S. V.-T., Lee, D., Bao, Q. L., Yoo, T., Khan, M., Jo, J., & Park, C. (2023). A Human Detection Approach for Intrusion in Hazardous Areas Using 4D-BIM-Based Spatial-Temporal Analysis and Computer Vision. Buildings 2023, Vol. 13, Page 2313, 13(9), 2313. 10.3390/BUILDINGS13092313 Tran, S. V., Bao, L. Q., Nguyen, L. T., & Pedro, A. (2022). Development of Computer Vision and BIM-cloud based Automated Status Updating for Construction Safety Monitoring. Nov 2022. cloud_based_Automated_Status_Updating_for_Construction_Safety_Monitoring Tran, S. V. T., Khan, N., Lee, D., & Park, C. (2021). A Hazard Identification Approach of Integrating 4D BIM and Accident Case Analysis of Spatial–Temporal Exposure. Sustainability 2021, Vol. 13, Page 2211, 13(4), 2211. 10.3390/SU13042211 Tran, S. V. T., Nguyen, T. L., Chi, H. L., Lee, D., & Park, C. (2022). Generative planning for construction safety surveillance camera installation in 4D BIM environment. Automation in Construction, 134, 104103. 10.1016/J.AUTCON.2021.104103 Wu, C., Li, X., Guo, Y., Wang, J., Ren, Z., Wang, M., & Yang, Z. (2022). Natural language processing for smart construction: Current status and future directions. Automation in Construction, 134, 104059. 10.1016/J.AUTCON.2021.104059 Zhong, B., He, W., Huang, Z., Love, P. E. D., Tang, J., & Luo, H. (2020). A building regulation question answering system: A deep learning methodology. Advanced Engineering Informatics, 46, 101195. 10.1016/J.AEI.2020.101195