Scholarlink

With the escalation of climate change, extreme weather events have become increasingly common, posing significant challenges to the architectural domain. Only focusing on the design methods and characteristics of buildings in typical climates is no longer enough to cope with future weather challenges. Therefore, the study of architectural design under extreme climates has become an emerging and important topic. However, China's research and engagement on extreme climate architecture lag behind many other countries, resulting in related architectural knowledge in this domain being scattered and fragmented, and even in the gray area of information retrieval, making it difficult for architects to use. This paper explores how to systematically categorize, organize, and present information on extreme climate architecture in a way that is easily accessible and beneficial to architects, thereby supporting well-informed design decisions. It proposes a top-down approach to constructing a knowledge graph for extreme climate architecture. By leveraging architectural programming theory, the study constructs an ontology model and employs ChatGPT for the extraction of knowledge from unstructured data. Additionally, it uses web crawlers to gather relevant information from general encyclopedias, integrating these into a triplet form. Compiled Data is then stored in Neo4j, facilitating efficient domain knowledge querying and visualization. Furthermore, this research presents a Q&A application demo named Extreme-Architecture-Graph based on the constructed knowledge graph. This application aims to transform extreme climate architectural knowledge into actionable insights, enabling architects to acquire a comprehensive understanding of design objectives under extreme climate conditions in the early stages of planning and design. In summary, this study constructs a knowledge graph for architecture in extreme environments to enhance preparedness for the unforeseen risks posed by extreme weather conditions, and explores the usability of multi-source heterogeneous data in the field of architecture in the era of artificial intelligence.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Constructing a Knowledge Graph for Extreme Climate Architecture Based on Large Language Models (LLMs)

  • 会议论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年

查看全文
  • Shaotsu Tu,
  • Weimin Zhuang,
  • Fei Ren

摘要

With the escalation of climate change, extreme weather events have become increasingly common, posing significant challenges to the architectural domain. Only focusing on the design methods and characteristics of buildings in typical climates is no longer enough to cope with future weather challenges. Therefore, the study of architectural design under extreme climates has become an emerging and important topic. However, China's research and engagement on extreme climate architecture lag behind many other countries, resulting in related architectural knowledge in this domain being scattered and fragmented, and even in the gray area of information retrieval, making it difficult for architects to use. This paper explores how to systematically categorize, organize, and present information on extreme climate architecture in a way that is easily accessible and beneficial to architects, thereby supporting well-informed design decisions. It proposes a top-down approach to constructing a knowledge graph for extreme climate architecture. By leveraging architectural programming theory, the study constructs an ontology model and employs ChatGPT for the extraction of knowledge from unstructured data. Additionally, it uses web crawlers to gather relevant information from general encyclopedias, integrating these into a triplet form. Compiled Data is then stored in Neo4j, facilitating efficient domain knowledge querying and visualization. Furthermore, this research presents a Q&A application demo named Extreme-Architecture-Graph based on the constructed knowledge graph. This application aims to transform extreme climate architectural knowledge into actionable insights, enabling architects to acquire a comprehensive understanding of design objectives under extreme climate conditions in the early stages of planning and design. In summary, this study constructs a knowledge graph for architecture in extreme environments to enhance preparedness for the unforeseen risks posed by extreme weather conditions, and explores the usability of multi-source heterogeneous data in the field of architecture in the era of artificial intelligence.