LLM과 RAG 기반 BIM 지식 전문가 에이전트 연구

• 영문명: BIM Knowledge Expert Agent Research Based on LLM and RAG
• 발행기관: 한국BIM학회
• 저자명: 강태욱(Tae-Wook Kang) 박승화(Seung-Hwa Park)
• 간행물 정보: 『KIBIM Magazine』14권 3호, 22~30쪽, 전체 9쪽
• 주제분류: 공학 > 건축공학
• 파일형태: PDF
• 발행일자: 2024.09.30

국문 초록

Recently, LLM (Large Language Model), a rapidly developing generative AI technology, is receiving much attention in the smart construction field. This study proposes a methodology for implementing an knowledge expert system by linking BIM (Building Information Modeling), which supports data hub functions in the smart construction domain with LLM. In order to effectively utilize LLM in a BIM expert system, excessive model learning costs, BIM big data processing, and hallucination problems must be solved. This study proposes an LLM-based BIM expert system architecture that considers these problems. This study focuses on the RAG (Retrieval- Augmented Generation) document generation method and search algorithm for effective BIM data retrieval, with the goal of implementing an LLM-based BIM expert system within a small GPU resource. For performance comparison and analysis, a prototype of the designed system is developed, and implications to be considered when developing an LLM-based BIM expert system are derived.

목차

1. 서 론

2. LLM 기반 BIM 전문가 에이전트 구현 프로세스

3. 프로토타입 구현 및 성능 분석

4. 결 론

감사의 글

References

키워드

대형언어모델 지식 전문가 검색증강생성 프로세스 검색자 BIM IFC AI LLM Knowledge Expert RAG Process Retriever