대한건축학회논문집 (Journal of the Architectural Institute of Korea)

  • 제40권9호
  • /
  • Pages.81-90
  • /
  • 2024
  • /
  • 2733-6239(pISSN)
  • /
  • 2733-6247(eISSN)
대한건축학회 (Architectural Institute of Korea)
권호 표지
DOI QR코드

DOI QR Code

대규모 언어모델(LLM)을 활용한 건축민원 대응 효율화 방안 연구

A Study on the Efficient Response to Architectural Civil Complaints Using Large Language Models(LLM)

  • 조상규 (건축공간연구원 ) ;
  • 김신성 (건축공간연구원, 서울대학교 협동과정 조경학전공)
  • Cho, Sang-Kyu (Architecture & Urban Research Institute) ;
  • Kim, Shin-Sung (Architecture & Urban Research Institute, Interdisciplinary Program in Landscape Architecture, Seoul National University)
  • 투고 : 2024.06.19
  • 심사 : 2024.08.14
  • 발행 : 2024.09.30
⟨ 이전 논문 다음 논문 ⟩

초록

This study addresses the complexity of architectural laws and regulations and their administrative burden, focusing on improving efficiency in the interpretation and query-response processes using large-scale language models. The research centers around the development and implementation of the SPARC (Semantic Processing for Architecture Regulation Compliance) engine, primarily utilizing data from inquiries and complaints submitted to the Ministry of Land, Infrastructure, and Transport regarding architectural laws. This prototype system is designed to augment reference information necessary for legal interpretation, and its effectiveness was validated through a quality assessment of system responses to actual complaint data. The results show that the system achieved an accuracy rate of over 80% for general inquiry complaints with clear conclusions and 70% to 100% for more complex cases requiring legal interpretation by the legislative affairs office. This research represents the first attempt to apply AI in the field of regulatory administration, providing a critical technical and policy foundation for the development and operation of AI-based systems for interpreting architectural regulations.

키워드

참고문헌

  1. Carbonell, J., & Goldstein, J. (1998, August 24-28). The use of MMR, diversity-based reranking for reordering documents and producing summaries [Paper presentation]. SIGIR98: 21st Annual ACM/SIGIR International Conference on Research and Development in Information Retrieval, Melbourne, Australia. 335-336.
  2. Casey, M. (2023, May 25). Large language models: their history, capabilities and limitations. Snorkel.ai. https://snorkel.ai/large-language-models-llms
  3. Choi, J. H., & Kim, I. H. (2014). A Study on the application of pre-processing to develop the open BIM-based code checking system for building administration process. Journal of The Architectural Institute of Korea Planning & Design, 30(9), 3-12.
  4. Eom, S. J. (2021). Democracy and public administration in the age of artificial intelligence: focusing on the case of 「e-People」 system advancement. The Korean Journal of Public Administration, 30(2), 35-64.
  5. Government Legislation Support Center. (n.d.). Case Exampl es of Legal Interpretation. Retrieved November 10, 2023 fr om https://www.lawmaking.go.kr/nl4li/lsItptEmp/list?mode=all
  6. Keith, D. (2023, December 28). A Brief History of Large Language Models. Dataversity. https://www.dataversity.net/ a-brief-history-of-large-language-models/
  7. Korean Law Information Center. (n.d.). Architectural Law Hierarchical Structure. Retrieved November 10, 2023 from https://www.law.go.kr/
  8. Lee, G. (2019). What should be submitted in a BIM project? An introduction to the IDM Toolkit project. Review of Architecture and Building Science, 63(6), 56-58.
  9. Ministry of Land, Infrastructure and Transport. (n.d.). Case Examples of Legal Interpretation: Whether Multiple Exceptions Can Be Applied Concurrently Under the 'Building Act . Retrieved November 10, 2023 from https://moleg.go.kr/lawinfo/nwLwAnInfo.mo?mid=a10106020000&cs_seq=400576
  10. OpenAI.(n.d.). OpenAI Platform Models. Retrieved November 10, 2023 from https://platform.openai.com /docs/models
  11. Ryu, S. Y., Kim, M. J., Cho, Y. J., & Yu, K. H. (2017). A Study on the analysis of civil appeals to building regulations. Journal of The Architectural Institute of Korea Planning & Design, 33(2), 13-21.
  12. ScribbleData.io. (n.d.). Large Language Models 101: hist ory, evolution and future. ScribbleData.io. Retrieved Dece mber 15, 2023 from https://www.scribbledata.io/blog/large-language-models-history-evolutions-and-future/
  13. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30.
  14. Yang, H. C., Park, K. B., Um, M. J., & Mok, E. J. (2020). A Study on the application of artificial intelligence for the administrative innovation of science and technology. Science & Technology Policy Institute.
  15. Yi, S. J. (2014). A study on improvement of the legislative system for advanced building law. Korea Legislation Research Institute.