AI 기반 건축 초기 설계 프로세스에 대한 연구 - LLM 및 생성형 AI를 중심으로 -
A Study on the AI Aided Early Architectural Design Process – Focusing on LLM and Generative AI –
- 발행
- 2024 등록이 논문은 발행 시점을 확인하지 못해 원문 등록일을 적었습니다. KCI가 2005~2008년에 옛 논문을 몰아서 올린 탓에, 그 시기 등록분은 발행보다 평균 3~5년 늦습니다. 실제 발행연도는 더 이를 수 있습니다.
- 소속·발행
- 성균관대학교 글로벌스마트시티융합전공
- 출처
- 국내 KCI
- DOI
- 10.7315/CDE.2024.112
- 원문
- 원문 보기 ↗
개념
키워드
Architectural design process, Computer aided architectural design (CAAD), Deep learning, Generative ai, Large language model (LLM), Architectural design process, Computer aided architectural design (CAAD), Deep learning, Generative ai, Large language model (LLM)
초록
AI's role in architectural design is shifting architects' roles from leading to guiding AI in the design process. While AI shows potential in automating design, its integration in CAD/BIM tools is still emerging. This research identifies architectural design tasks that AI can enhance, particularly in CAAD and BIM, proposing an AI Assistant for task automation and intuitive interface use. The research proposes an early design process using LLM and image-generating AI based on previous research. This process emphasizes user-centered communication using image-recognition-enabled LLM and image GAI, demonstrating that AI can assist in most early design tasks. In this research, a prototype AI Assistant module integrated into a CAD/BIM tool is proposed, showing that image GAI can generate various building interior alternatives, and image recognition LLM can extract furniture features from these images. With proper prompt- ing and data processing, the LLM can recommend similar furniture elements from the user's BIM library, automating design tasks. This bridges the gap between AI's theoretical potential and practical application in architectural design.