主管：中华人民共和国应急管理部
主办：应急管理部天津消防研究所
ISSN 1009-0029  CN 12-1311/TU
消防科学与技术

消防科学与技术 ›› 2025, Vol. 44 ›› Issue (11): 1670-1676.

• • 上一篇    下一篇

基于大语言模型的消防标准问答系统设计与实现

郭歌1,2,3,胡  锐4， 任常兴1,2,3, 黄近朱5, 魏纪东5   

  1. （1.应急管理部天津消防研究所，天津 300381；2.工业与公共建筑火灾防控技术应急管理部重点实验室，天津 300381；3.天津市消防安全技术重点实验室，天津 300381；4.国家消防救援局，北京100097；5.天津大学 电气自动化与信息工程学院，天津 300072）
  • 收稿日期:2025-04-03 修回日期:2025-08-04 出版日期:2025-11-20 发布日期:2025-11-15
  • 作者简介:郭 歌，应急管理部天津消防研究所，副研究员，主要从事消防标准化相关工作，天津市南开区卫津南路110号，300081。
  • 基金资助:
    国家自然科学基金资助项目（52376137）；中央基本科研业务费项目（2025SJ09）；天津大学人工智能赋能课程建设专项项目（天大校教〔2024〕18号）

Design and implementation of fire protection standards question answering system using large language model

Guo Ge1,2,3, Hu Rui4, Ren Changxing1,2,3, Huang Jinzhu5, Wei Jidong5   

  1. (1. Tianjin Fire Science and Technology Research Institute of MEM, Tianjin 300381, China; 2. Key Laboratory of Fire Protection Technology for Industry and Public Building, Ministry of Emergency Management, Tianjin 300381, China; 3. Tianjin Key Laboratory of Fire Safety Technology, Tianjin 300381, China; 4. National Fire and Rescue Administration, Beijing 100097, China; 5. School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China)
  • Received:2025-04-03 Revised:2025-08-04 Online:2025-11-20 Published:2025-11-15

摘要： 消防标准作为设计、施工与监管的权威规范，对安全生产起着关键保障作用，然而其解读与实施长期依赖专业人员经验化操作与人工核验。为此，本文基于大语言模型和检索增强生成技术设计了消防标准问答系统，实现了消防标准规范专业领域的知识问答。系统包括大语言模型、外挂知识库和用户交互界面。为提高知识库检索质量，提出了一种专业词汇加权的检索算法；构建了一套适用于消防标准的问题优化模板，以提升用户问题描述精度和系统回答质量；考虑数据安全性，实现了轻量化本地部署。运行实测表明，问答系统能够准确解答消防标准相关问题，具备良好的稳定性和实用性。该系统的研发，为消防标准的智能化表达识别与内容解析开拓了新思路，是大语言模型技术在智慧消防领域的有益探索。

关键词: 消防标准, 问答系统, 大语言模型, 检索增强生成, 智慧消防

Abstract: As an authoritative standard for design, construction, and supervision, fire protection standards play a crucial role in ensuring work safety. However, the interpretation and implementation of standards have relied on the experienced operations of professionals and manual verification. To address this issue, this paper designs a question-answering system for fire protection standards based on large language models and retrieval augmented generation, realizing the knowledge question-answering function in the professional field of fire protection standards and specifications. The system consists of a large language model, an external knowledge base, and a user interface. To improve the retrieval quality of the knowledge base, a retrieval algorithm weighted by professional terms is proposed. A set of question optimization templates suitable for fire protection standards is constructed to enhance the accuracy of users' question and the quality of the system's answers. Considering data security, a lightweight local deployment is achieved. The practical tests show that the question-answering system can accurately answer questions related to fire protection standards and has good stability and practicality. The development of system has opened up new ideas for the intelligent expression recognition and content analysis of fire protection standards, and it represents a beneficial exploration of large language model technology in the field of smart fire protection.

Key words: fire protection standards, question and answer system, large language model, retrieval augmented generation, smart fire protection