| spelling |
oapen-20.500.12657-890592024-04-03T02:23:00Z Chapter Transforming Building Industry Knowledge Management: A Study on the Role of Large Language Models in Fire Safety Planning Ashkenazi, Ori Isaac, Shabtai Giretti, Alberto Carbonari, Alessandro Durmus, Dilan Large Language Models (LLMs) Knowledge Management (KM) Fire Safety Planning Expert Systems (ESs) Artificial Intelligence (AI) Knowledge Graph Ontology thema EDItEUR::C Language and Linguistics::CF Linguistics thema EDItEUR::D Biography, Literature and Literary studies::DS Literature: history and criticism 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 2024-04-02T15:45:13Z 2024-04-02T15:45:13Z 2023 chapter ONIX_20240402_9791221502893_28 2704-5846 9791221502893 https://library.oapen.org/handle/20.500.12657/89059 eng Proceedings e report application/pdf n/a 9791221502893_73.pdf https://books.fupress.com/doi/capitoli/979-12-215-0289-3_73 Firenze University Press 10.36253/979-12-215-0289-3.73 10.36253/979-12-215-0289-3.73 bf65d21a-78e5-4ba2-983a-dbfa90962870 9791221502893 137 10 Florence open access
|
| description |
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
|
