基于大语言模型的知识图谱构建及在灾害应急中的应用  

Knowledge Graph Construction Based on Large Language Model and Its Application in Disaster Emergency

作　　者：徐欢 吴梦飞 孙文学 XU Huan;WU Mengfei;SUN Wenxue(School of Electronic Information,Huzhou College,Huzhou 313000,China)

机构地区：[1]湖州学院电子信息学院,浙江湖州313000

出　　处：《现代信息科技》2025年第8期146-151,156,共7页Modern Information Technology

基　　金：湖州学院校级科研项目(2024HXKM09)。

摘　　要：中国是世界上自然灾害最为严重的国家之一,台风、地震、洪涝等灾害频繁发生,对人民生命财产安全构成巨大威胁。面对灾害应急管理的复杂性与紧迫性,知识图谱技术凭借其在信息整合、关系挖掘和知识推理方面的优势,逐渐成为该领域的研究热点。然而,灾害数据的异构性和质量不统一,限制了传统自然语言处理方法在抽取知识图谱信息方面的能力。因此,文章提出了基于分布提示策略的大语言模型知识抽取方法。通过需求提示、领域知识提示和少样本提示,大语言模型能够自动从非结构化数据中提取出实体和关系,提高了知识图谱构建的自动化程度和精确性。为了验证基于大语言模型的知识图谱在实际应用中的效果,文章以台风灾害应急预案为例,构建了相应的知识图谱及其智能问答系统。China is one of the countries with the most serious natural disasters in the world.Typhoons,earthquakes,floods and other disasters occur frequently,posing a huge threat to the safety of people's lives and property.Facing the complexity and urgency of disaster emergency management,Knowledge Graph technology has gradually become a research hotspot in thisfield by virtue of its advantages in information integration,relationship mining and knowledge reasoning.However,the heterogeneity and quality of disaster data are not uniform,which limits the ability of traditional Natural Language Processing methods to extract Knowledge Graph information.Therefore,this paper proposes a Large Language Model knowledge extraction method based on distributed prompt strategy.Through requirement hints,domain knowledge hints and few-shot hints,the Large Language Model can automatically extract entities and relationships from unstructured data,which improves the automation and accuracy of Knowledge Graph construction.In order to verify the effect of Knowledge Graph based on Large Language Model in practical application,this paper takes the typhoon disaster emergency plan as an example to construct the corresponding Knowledge Graph and its intelligent question and answer system.

关 键 词：知识图谱 大语言模型 知识抽取 智能问答 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]