Contained in:
Book Chapter

Transforming Building Industry Knowledge Management: A Study on the Role of Large Language Models in Fire Safety Planning

  • Ori Ashkenazi
  • Shabtai Isaac
  • Alberto Giretti
  • Alessandro Carbonari
  • Dilan Durmus

This paper discusses the potential use of AI in general, and large language models (LLMs) in particular, to support knowledge management (KM) in the building industry. The application of conventional methods and tools for KM in the building industry is currently limited due to the large variability of buildings, and the industry’s fragmentation. Instead, relatively labor-intensive methods need to be employed to curate the knowledge gained in previous projects and make it accessible for use in future projects. The recent development of LLMs has the potential to develop new approaches to KM in the building industry. These may include querying a variety of relatively unstructured documents from previous projects and other textual sources of technical expertise, processing these data to create knowledge, identifying patterns, and storing knowledge for future use. A proposed framework is defined for the use of LLMs for KM in construction. We will perform preliminary analyses on how to train models that can generate information and knowledge required to make decisions in the development of specific tasks of fire safety planning

  • Keywords:
  • Large Language Models (LLMs),
  • Knowledge Management (KM),
  • Fire Safety Planning,
  • Expert Systems (ESs),
  • Artificial Intelligence (AI),
  • Knowledge Graph,
  • Ontology,
+ Show More

Ori Ashkenazi

Ben-Gurion University of the Negev, Israel

Shabtai Isaac

Ben-Gurion University of the Negev, Israel - ORCID: 0000-0001-8601-7601

Alberto Giretti

Università Politecnica delle Marche, Italy - ORCID: 0000-0001-7208-0845

Alessandro Carbonari

Università Politecnica delle Marche, Italy - ORCID: 0000-0002-0721-631X

Dilan Durmus

Università Politecnica delle Marche, Italy - ORCID: 0009-0007-9831-8875

  1. Duval, R.F., 2006. NFPA Case Study: nightclub fires. National Fire Protection Association, Fire Investigations Department.
  2. Fekri-Ershad, S., Tajalizadeh, H., & Jafari, S. (2013). Design and Development of an Expert System to Help Head of University Departments. arXiv preprint arXiv:1308.0356.
  3. Goldstein, I., & Papert, S. (1977). Artificial intelligence, language, and the study of knowledge. Cognitive science, 1(1), 84-123.
  4. Kodur, V., Kumar, P., & Rafi, M. M. (2019). Fire hazard in buildings: Review, assessment and strategies for improving fire safety. PSU Research Review, 4(1), 1–23. DOI: 10.1108/PRR-12-2018-0033
  5. Law, A., & Spinardi, G. (2021). Performing Expertise in Building Regulation: ‘Codespeak’ and Fire Safety Experts. Minerva, 59(4), 515–538. DOI: 10.1007/s11024-021-09446-5
  6. Liu, L. Y. (1995). Digital data-collection device for construction site documentation: Proceedings of the 2nd Congress on Computing in Civil Engineering. Part 1 (of 2). Computing in Civil Engineering (New York), 2, 1287–1293.
  7. Maiellaro, N. (1997). Using expert systems to check building applications. 19.
  8. Nikolic, B., & Dakic, J. (2015). Knowledge management in the function of risk assessment. 3(2).
  9. National Fire Protection Association (Ed.). (2017). NFPA 101: Life safety code 2018 (2018 edition). National Fire Protection Association.
  10. OpenAI. (2023). Fine-tuning Retrieved 2nd of May 2023 from https://platform.openai.com/docs/guides/fine-tuning/fine-tuning
  11. Parsamehr, M., Perera, U. S., Dodanwala, T. C., Perera, P., & Ruparathna, R. (2023). A review of construction management challenges and BIM-based solutions: Perspectives from the schedule, cost, quality, and safety management. Asian Journal of Civil Engineering, 24(1), 353–389. DOI: 10.1007/s42107-022-00501-4
  12. Saka, A., Taiwo, R., Saka, N., Salami, B., Ajayi, S., Akande, K., & Kazemi, H. (2023). GPT Models in Construction Industry: Opportunities, Limitations, and a Use Case Validation. arXiv preprint arXiv:2305.18997.
  13. Shanahan, M. (2023). Talking About Large Language Models (arXiv:2212.03551). arXiv. DOI: 10.48550/arXiv.2212.03551
  14. Stefik, M. (2014). Introduction to knowledge systems. Elsevier.
  15. Tofiło, P., Konecki, M., Gałaj, J., Jaskółowski, W., Tuśnio, N., & Cisek, M. (2013). Expert System for Building Fire Safety Analysis and Risk Assessment. Procedia Engineering, 57, 1156–1165. DOI: 10.1016/j.proeng.2013.04.146
  16. Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., ... & Zhou, D. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35, 24824-24837.
PDF
  • Publication Year: 2023
  • Pages: 729-738

XML
  • Publication Year: 2023

Chapter Information

Chapter Title

Transforming Building Industry Knowledge Management: A Study on the Role of Large Language Models in Fire Safety Planning

Authors

Ori Ashkenazi, Shabtai Isaac, Alberto Giretti, Alessandro Carbonari, Dilan Durmus

DOI

10.36253/979-12-215-0289-3.73

Peer Reviewed

Publication Year

2023

Copyright Information

© 2023 Author(s)

Content License

CC BY-NC 4.0

Metadata License

CC0 1.0

Bibliographic Information

Book Title

CONVR 2023 - Proceedings of the 23rd International Conference on Construction Applications of Virtual Reality

Book Subtitle

Managing the Digital Transformation of Construction Industry

Editors

Pietro Capone, Vito Getuli, Farzad Pour Rahimian, Nashwan Dawood, Alessandro Bruttini, Tommaso Sorbi

Peer Reviewed

Publication Year

2023

Copyright Information

© 2023 Author(s)

Content License

CC BY-NC 4.0

Metadata License

CC0 1.0

Publisher Name

Firenze University Press

DOI

10.36253/979-12-215-0289-3

eISBN (pdf)

979-12-215-0289-3

eISBN (xml)

979-12-215-0257-2

Series Title

Proceedings e report

Series ISSN

2704-601X

Series E-ISSN

2704-5846

129

Fulltext
downloads

64

Views

Export Citation

1,331

Open Access Books

in the Catalogue

2,094

Book Chapters

3,709,757

Fulltext
downloads

4,300

Authors

from 904 Research Institutions

of 65 Nations

65

scientific boards

from 347 Research Institutions

of 43 Nations

1,246

Referees

from 379 Research Institutions

of 38 Nations