Improving knowledge capture and retrieval in the BIM environment: combining case-based reasoning and natural language processing

Hao Wang*, Xianhai Meng, Xingyu Zhu

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

20 Citations (Scopus)

Abstract

Most knowledge management (KM) techniques capture knowledge at the end of a project, leading to knowledge loss. Building information modeling (BIM) is a building information management process throughout the project lifecycle. This study uses BIM for lifecycle knowledge capture to address knowledge loss. Knowledge in construction projects is intricate, intensifying the challenges of knowledge retrieval. This study combines natural language processing (NLP) and case-based reasoning (CBR) to improve knowledge retrieval, which not only takes advantage of CBR for retrieving knowledge case context through attributes but also obtains the benefits of NLP for retrieving text descriptions of knowledge cases. The parameters created in BIM correspond to the CBR attributes and NLP case descriptions. Quantitative test and case study confirm that the novel approach proposed in this study can improve knowledge retrieval performance and prevent knowledge loss. It also provides new insights into the transformation from BIM to building knowledge modeling (BKM).

Original languageEnglish
Article number104317
JournalAutomation in Construction
Volume139
Early online date06 May 2022
DOIs
Publication statusPublished - 01 Jul 2022

Fingerprint

Dive into the research topics of 'Improving knowledge capture and retrieval in the BIM environment: combining case-based reasoning and natural language processing'. Together they form a unique fingerprint.

Cite this