Information Integration of Regulation Texts and Tables for Automated Construction Safety Knowledge Mapping
Publication: Journal of Construction Engineering and Management
Volume 150, Issue 5
Abstract
The explicit safety knowledge contained in regulations in the form of texts and tables is crucial for construction safety management. However, the presence of rich semantic content within texts and the intricate layout of complex tables makes domain information extraction challenging. Therefore, this research proposed a hybrid approach to map safety knowledge graphs by automatically extracting information from both texts and tables in a scenario-oriented manner, combining rules and deep learning methods to achieve a balance between scene applicability and method flexibility. Furthermore, metrics from social network analysis (SNA) were applied to evaluate and verify the quality of the constructed knowledge graph. For extracting semantic information from text, the proposed approach supplemented the semantics information of the sentence and balanced the granularity of knowledge by combining the BERT-BiLSTM-CRF-based named entity recognition (NER) model and semantic role labeling (SRL)-based information extraction model. For irregular tables, a unified automatic extraction method was developed to process nested tables without preprocessing. The experiment constructed a comprehensive and scenario-oriented knowledge graph with 907 nodes, and showed high precision and recall for texts (89.37%, 85.42%) and tables (97.11%, 85.22%) on the test data. SNA results showed the proposed method ensured information richness and structural complexity.
Practical Applications
The construction safety knowledge graph constructed in this research offers three significant practical advantages. First, the proposed framework provides a solution for automatically integrating regulations into a knowledge graph with rich semantics and comprehensive information. Considering both sentence semantics and entity granularity enhances the application of Chinese regulatory clauses to specific construction scenarios. Second, the knowledge graph incorporated both textual semantics and tabular data, which assists managers in querying more accurate and comprehensive safety requirements. The comprehensive knowledge graph allows managers to quickly locate the necessary construction requirements on a larger scale and make more comprehensive and accurate construction decisions, effectively improving work efficiency and decision-making quality. Third, metrics from SNA suggested that the proposed method maintained the amount and diversity of regulatory information, while strengthening the compactness of the community structure and providing specific and clear requirements for the construction situation, operation procedures, and threshold definition. As a result, it is easier for managers to understand and process the safety information, perform construction operations in accordance with regulatory requirements, ensure the compliance of the operation, and further improve construction safety.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
The authors acknowledge the support provided by China Railway First Group Corp., Ltd., the National Natural Science Foundation of China (Nos. 51978302, 72101093, and U2021A20151), the Natural Science Research Program of Shaanxi Province (No. 2023-JC-YB-620), and the Social Science Foundation of Xi’an City (23GL66). We also thank the insightful comments on methodology from Associate Professor Kaiqi Zhang of Chang’an University on the revision of this manuscript.
References
Akanbi, T., and J. Zhang. 2020. “Automated design information extraction from construction specifications to support wood construction cost estimation.” In Construction research congress (CRC) on construction research and innovation to transform society, 658–666. Tempe, AZ: Arizona State Univ.
Baidu. 2022. “Table text recognition.” Accessed April 12, 2022. https://ai.baidu.com/tech/ocr_others/table?_=1693020707575.
Burt, R. S., M. Kilduff, and S. Tasselli. 2013. “Social network analysis: Foundations and frontiers on advantage.” Annu. Rev. Psychol. 64 (1): 527–547. https://doi.org/10.1146/annurev-psych-113011-143828.
Chen, H., Y. Zhu, and X. Luo. 2022. “TableGraph: An image segmentation-based table knowledge interpretation model for civil and construction inspection documentation.” J. Constr. Eng. Manage. 148 (10): 04022103. https://doi.org/10.1061/(ASCE)CO.1943-7862.0002346.
Chinese Standard. 2016. Code for construction and quality acceptance of immersed tunnel. GB 51201-2016. Beijing: China Planning Press.
Chinese Standard. 2017. Code for construction and acceptance of shield tunnelling method. GB 50446-2017. Beijing: China Architecture & Building Press.
Fang, W., L. Ma, P. E. D. Love, H. Luo, L. Ding, and A. Zhou. 2020. “Knowledge graph for identifying hazards on construction sites: Integrating computer vision with ontology.” Autom. Constr. 119: 103310. https://doi.org/10.1016/j.autcon.2020.103310.
Fang, W., B. Zhong, N. Zhao, P. E. Love, H. Luo, J. Xue, and S. Xu. 2019. “A deep learning-based approach for mitigating falls from height with computer vision: Convolutional neural network.” Adv. Eng. Inform. 39 (Jan): 170–177. https://doi.org/10.1016/j.aei.2018.12.005.
Fang, W. L., P. E. D. Love, H. B. Luo, and S. J. Xu. 2022. “A deep learning fusion approach to retrieve images of People’s unsafe behavior from construction sites.” Dev. Built Environ. 12 (Dec): 100085. https://doi.org/10.1016/j.dibe.2022.100085.
Feng, D., and H. S. Chen. 2021. “A small samples training framework for deep learning-based automatic information extraction: Case study of construction accident news reports analysis of paper.” Adv. Eng. Inform. 39 (Jan): 170–177. https://doi.org/10.1016/j.aei.2021.101256.
Ferrada, X., and A. Serpell. 2014. “Selection of construction methods for construction projects: A knowledge problem.” J. Constr. Eng. Manage. 140 (4): B4014002. https://doi.org/10.1061/(ASCE)CO.1943-7862.0000715.
Hao, J., L. Zhao, J. Milisavljevic-Syed, and Z. Ming. 2021. “Integrating and navigating engineering design decision-related knowledge using decision knowledge graph.” Adv. Eng. Inform. 50 (Oct): 101366. https://doi.org/10.1016/j.aei.2021.101366.
Hu, H. M. 2014. A thesis submitted in partial fulfillment of the requirements for the degree of master of engineering. Hongshan, China: Huazhong Univ. of Science and Technology.
Jiang, Y., X. Gao, W. Su, and J. Li. 2021. “Systematic knowledge management of construction safety standards based on knowledge graphs: a case study in China.” Int. J. Environ. Res. Public Health 18 (20): 10692. https://doi.org/10.3390/ijerph182010692.
Kasar, T., P. Barlas, S. Adam, C. Chatelain, and T. Paquet. 2013. “Learning to detect tables in scanned document images using line information.” In Proc., 12th Int. Conf. on Document Analysis and Recognition (ICDAR), 1185–1189. New York: IEEE.
Lee, J.-K., K. Cho, H. Choi, S. Choi, S. Kim, and S. H. Cha. 2023. “High-level implementable methods for automated building code compliance checking.” Dev. Built Environ. 15 (Dec): 100174. https://doi.org/10.1016/j.dibe.2023.100174.
Li, F., Y. Song, and Y. Shan. 2020. “Joint extraction of multiple relations and entities from building code clauses.” Appl. Sci. 10 (20): 7103. https://doi.org/10.3390/app10207103.
Li, J., A. X. Sun, J. L. Han, and C. L. Li. 2022. “A survey on deep learning for named entity recognition.” IEEE Trans. Knowl. Data Eng. 34 (1): 50–70. https://doi.org/10.1109/TKDE.2020.2981314.
Li, R., T. Mo, J. Yang, D. Li, S. Jiang, and D. Wang. 2021. “Bridge inspection named entity recognition via BERT and lexicon augmented machine reading comprehension neural model.” Adv. Eng. Inform. 50 (Mar): 101416. https://doi.org/10.1016/j.aei.2021.101416.
Li, Z., V. Raskin, and K. Ramani. 2008. “Developing engineering ontology for information retrieval.” J. Comput. Inf. Sci. Eng., 8 (May): 011003. https://doi.org/10.1115/1.2830851.
Liu, J., H. Luo, W. Fang, and P. E. Love. 2023a. “Contrastive learning framework for safety information extraction in construction of paper.” Adv. Eng. Inform. 58 (Oct): 102194. https://doi.org/10.1016/j.aei.2023.102194.
Liu, J., H. Luo, and H. Liu. 2022. “Deep learning-based data analytics for safety in construction.” Autom. Constr. 140 (May): 104302. https://doi.org/10.1016/j.autcon.2022.104302.
Liu, X., X. Jing, Q. Zhu, W. Du, and X. S. Wang. 2023b. “Automatic construction hazard identification integrating on-site scene graphs with information extraction in outfield test of paper.” Buildings 13 (2): 377. https://doi.org/10.3390/buildings13020377.
Mandal, S., S. P. Chowdhury, A. K. Das, and B. Chanda. 2006. Detection and segmentation of tables and math-zones from document images, 841–846. New York: Association for Computing Machinery.
Meng, F. Q., S. S. Yang, J. D. Wang, L. Xia, and H. Liu. 2022. “Creating knowledge graph of electric power equipment faults based on BERT-BiLSTM-CRF model.” J. Electr. Eng. Technol. 17 (May): 2507–2516. https://doi.org/10.1007/s42835-022-01032-3.
Moon, S., S. Chi, and S.-B. Im. 2022. “Automated detection of contractual risk clauses from construction specifications using bidirectional encoder representations from transformers (BERT).” Autom. Constr. 142 (May): 104465. https://doi.org/10.1016/j.autcon.2022.104465.
Moon, S., G. Lee, S. Chi, and H. Oh. 2021. “Automated construction specification review with named entity recognition using natural language processing.” J. Constr. Eng. Manage. 147 (1): 101495. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001953.
Pegu, B., M. Singh, A. Agarwal, A. Mitra, and K. Singh. 2021. “Table structure recognition using CoDec encoder-decoder.” In Vol. 12917 of Proc., 16th IAPR Int. Conf. on Document Analysis and Recognition (ICDAR), edited by E. H. Barney Smith and U. Pal, 66–80. Cham, Switzerland: Springer. https://doi.org/10.1007/978-3-030-86159-9_5.
Ren, R., and J. Zhang. 2021. “Semantic rule-based construction procedural information extraction to guide jobsite sensing and monitoring.” J. Comput. Civ. Eng. 35 (6): 04021026. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000971.
Riad, A., C. Sporer, S. S. Bukhari, and A. Dengel. 2017. “Classification and information extraction for complex and nested tabular structures in images.” In Proc., 14th IAPR Int. Conf. on Document Analysis & Recognition (ICDAR), 1156–1161. New York: IEEE.
Ristoski, P., A. L. Gentile, A. Alba, D. Gruhl, and S. Welch. 2020. “Large-scale relation extraction from web documents and knowledge graphs with human-in-the-loop.” J. Web Semant. 60 (Jan): 100546. https://doi.org/10.1016/j.websem.2019.100546.
Song, J., J.-K. Lee, J. Choi, and I. Kim. 2020. “Deep learning-based extraction of predicate-argument structure (PAS) in building design rule sentences.” J. Comput. Des. Eng. 7 (5): 563–576. https://doi.org/10.1093/jcde/qwaa046.
Taylan, O., A. O. Bafail, R. M. S. Abdulaal, and M. R. Kabli. 2014. “Construction projects selection and risk assessment by fuzzy AHP and fuzzy TOPSIS methodologies.” Appl. Soft. Comput. 17 (May): 105–116. https://doi.org/10.1016/j.asoc.2014.01.003.
Wang, X., and N. El-Gohary. 2023a. “Deep learning-based relation extraction and knowledge graph-based representation of construction safety requirements.” Autom. Constr. 147 (Jun): 104696. https://doi.org/10.1016/j.autcon.2022.104696.
Wang, X., and N. S. El-Gohary. 2023b. “Deep learning-based named entity recognition and resolution of referential ambiguities for enhanced information extraction from construction safety regulations.” J. Comput. Civ. Eng. 37 (5): 04023023. https://doi.org/10.1061/(ASCE)CP.1943-5487.0001064.
Wang, X., J. Li, Z. Zheng, Y. Chang, and M. Zhu. 2022. “Entity and relation extraction with rule-guided dictionary as domain knowledge.” Front. Eng. Manage. 9 (May): 610–622. https://doi.org/10.1007/s42524-022-0226-0.
Wu, C., P. Wu, J. Wang, R. Jiang, M. Chen, and X. Wang. 2021. “Developing a hybrid approach to extract constraints related information for constraint management.” Autom. Constr. 124 (Apr): 103563. https://doi.org/10.1016/j.autcon.2021.103563.
Xiao, Z., and C. Zhang. 2021. “Construction of meteorological simulation knowledge graph based on deep learning method.” Sustainability 13 (3): 1311. https://doi.org/10.3390/su13031311.
Xu, X., and H. Cai. 2021. “Ontology and rule-based natural language processing approach for interpreting textual regulations on underground utility infrastructure.” Adv. Eng. Inform. 48 (May): 101288. https://doi.org/10.1016/j.aei.2021.101288.
Xu, Y., Y. Zhou, P. Sekula, and L. Ding. 2021. “Machine learning in construction: From shallow to deep learning.” Dev. Built Environ. 6 (Mar): 100045. https://doi.org/10.1016/j.dibe.2021.100045.
Xue, X., J. Wu, and J. Zhang. 2022. “Semiautomated generation of logic rules for tabular information in building codes to support automated code compliance checking.” J. Comput. Civ. Eng. 36 (1): 04021033. https://doi.org/10.1061/(ASCE)CP.1943-5487.0001000.
Xue, X., and J. Zhang. 2022. “Regulatory information transformation ruleset expansion to support automated building code compliance checking.” Autom. Constr. 138 (Jun): 104230. https://doi.org/10.1016/j.autcon.2022.104230.
Yang, C. L., L. Sheng, Z. C. Wei, and W. Wang. 2022. “Chinese named entity recognition of epidemiological investigation of information on COVID-19 based on BERT.” IEEE Access 10 (May): 104156–104168. https://doi.org/10.1109/ACCESS.2022.3210119.
Zhang, J., and N. M. El-Gohary. 2015. “Automated information transformation for automated regulatory compliance checking in construction.” J. Comput. Civ. Eng. 29 (4): B4015001. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000427.
Zhang, J., and N. M. El-Gohary. 2016. “Semantic NLP-based information extraction from construction regulatory documents for automated compliance checking.” J. Comput. Civ. Eng. 30 (2): 04015014. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000346.
Zhang, R., and N. El-Gohary. 2021. “A deep neural network-based method for deep information extraction using transfer learning strategies to support automated compliance checking.” Autom. Constr. 132 (Dec): 103834. https://doi.org/10.1016/j.autcon.2021.103834.
Zhang, R., and N. El-Gohary. 2022. “Hierarchical representation and deep learning-based method for automatically transforming textual building codes into semantic computable requirements.” J. Comput. Civ. Eng. 36 (5): 04022022. https://doi.org/10.1061/(ASCE)CP.1943-5487.0001014.
Zhang, S., F. Boukamp, and J. Teizer. 2015. “Ontology-based semantic modeling of construction safety knowledge: Towards automated safety planning for job hazard analysis (JHA).” Autom. Constr. 52 (Apr): 29–41. https://doi.org/10.1016/j.autcon.2015.02.005.
Zhao, H., Y. Pan, and F. Yang. 2020. “Research on information extraction of technical documents and construction of domain knowledge graph.” IEEE Access 8 (Sep): 168087–168098. https://doi.org/10.1109/ACCESS.2020.3024070.
Zhong, B., X. Pan, P. Love, J. Sun, and C. Tao. 2020a. “Hazard analysis: A deep learning and text mining framework for accident prevention.” Adv. Eng. Inform. 46 (Apr): 101152. https://doi.org/10.1016/j.aei.2020.101152.
Zhong, B., H. Wu, R. Xiang, and J. Guo. 2022. “Automatic information extraction from construction quality inspection regulations: A knowledge pattern–Based ontological method.” J. Constr. Eng. Manage. 148 (3): 04021207. https://doi.org/10.1061/(ASCE)CO.1943-7862.0002240.
Zhong, B., X. Xing, H. Luo, Q. Zhou, H. Li, T. Rose, and W. Fang. 2020b. “Deep learning-based extraction of construction procedural constraints from construction regulations.” Adv. Eng. Inform. 43 (Jan): 101003. https://doi.org/10.1016/j.aei.2019.101003.
Zhong, B. T., L. Y. Ding, H. B. Luo, Y. Zhou, Y. Z. Hu, and H. M. Hu. 2012. “Ontology-based semantic modeling of regulation constraint for automated construction quality compliance checking.” Autom. Constr. 28 (Dec): 58–70. https://doi.org/10.1016/j.autcon.2012.06.006.
Zhou, B., B. Hua, X. Gu, Y. Lu, T. Peng, Y. Zheng, X. Shen, and J. Bao. 2021a. “An end-to-end tabular information-oriented causality event evolutionary knowledge graph for manufacturing documents.” Adv. Eng. Inform. 50 (Oct): 101441. https://doi.org/10.1016/j.aei.2021.101441.
Zhou, Y., J. Lin, and Z. She. 2021b. “Automatic construction of building code graph for regulation intelligence.” In Proc., Int. Conf. on Construction and Real Estate Management (ICCREM), 248–254. Beijing: China.
Zhou, Y.-C., Z. Zheng, J.-R. Lin, and X.-Z. Lu. 2022. “Integrating NLP and context-free grammar for complex rule interpretation towards automated compliance checking.” Comput. Ind. 142 (Nov): 103746. https://doi.org/10.1016/j.compind.2022.103746.
Information & Authors
Information
Published In
Journal of Construction Engineering and Management
Volume 150 • Issue 5 • May 2024
Copyright
© 2024 American Society of Civil Engineers.
History
Received: Aug 30, 2023
Accepted: Dec 21, 2023
Published online: Mar 11, 2024
Published in print: May 1, 2024
Discussion open until: Aug 11, 2024
ASCE Technical Topics:
- Analysis (by type)
- Automation and robotics
- Business management
- Construction engineering
- Construction management
- Engineering fundamentals
- Engineering profession
- Hybrid methods
- Laws and regulations
- Legal affairs
- Methodology (by type)
- Network analysis
- Occupational safety
- Practice and Profession
- Professional development
- Public administration
- Public health and safety
- Safety
- Social network
- Systems engineering
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.