성과공개

홈 성과공개 상세 정보

상세 정보

논문
AUTOMATED NATURAL LANGUAGE BUILDING DESCRIPTOR FOR BUILDING INFORMATION MODELS
연도
5차
분류
구성기술2
연구기관
연세대학교
Yonsei University
구분2
학술발표
논문명
AUTOMATED NATURAL LANGUAGE BUILDING DESCRIPTOR FOR BUILDING INFORMATION MODELS
AUTOMATED NATURAL LANGUAGE BUILDING DESCRIPTOR FOR BUILDING INFORMATION MODELS
학술지명

CIB W78
ISSN
학술지 볼륨번호
게재일
20205.07.14
논문페이지
1-8
주저자명
장수형
Suhyung Jang
교신저자명
이강
Ghang Lee
공동저자명

Andre Borrmann
논문 초록

Recent large language models (LLMs) with enhanced
multimodal capabilities can interpret drawings and
generate building descriptions, yet their capabilities are
still
limited to simple two-dimensional spatial
configurations. This study proposes a method to
automatically generate natural language descriptions of
spatial programs and the connections between spaces
from building information models (BIMs) using
threshold-enhanced
triangle
intersection
(TETI)
algorithm and reasoning LLMs (OpenAI-o1 and
DeepSeek-R1). For validation, the inclusion rate of spaces
and the correctness of topological extraction are assessed.
Results show that the extracted BIM data effectively
capture key features, supporting the potential for natural
language-based automated BIM description generation.
첨부파일
AUTOMATED NATURAL LANGUAGE BUILDING DESCRIPTOR FOR BUILDING .pdf
목록