现代信息科技2025，Vol.9Issue(20)：40-43,4.DOI:10.19850/j.cnki.2096-4706.2025.20.008
基于GraphRAG的物流知识问答系统应用研究
Research on the Application of Logistics Knowledge Question Answering System Based on GraphRAG
摘要
Abstract
In view of the problems existing in traditional logistics knowledge processing methods,such as knowledge extraction relying on manual labeling,high cost and time consumption,this paper proposes a logistics Knowledge Graph construction method based on a Large Language Model.By designing prompt words and with the help of the semantic understanding and reasoning capabilities of the Large Language Model,knowledge is extracted from logistics-related data,and the extracted knowledge is stored in the Neo4j graph database.In the implementation of the question answering system,GraphRAG technology is used to retrieve relevant entities,relationships and their attributes from the logistics Knowledge Graph,so as to enhance and optimize the prompt words,provide reliable background knowledge support for the Large Language Model to generate answers,and effectively reduce the illusion phenomenon of Large Language Model.System tests show that this method effectively alleviates the problems of knowledge fragmentation and logical jump in traditional question answering systems.关键词
物流知识/问答系统/大语言模型/知识图谱/GraphRAGKey words
logistics knowledge/question answering system/Large Language Model/Knowledge Graph/GraphRAG分类
信息技术与安全科学引用本文复制引用
张立安,李雨淳,陈公兴,王源庆..基于GraphRAG的物流知识问答系统应用研究[J].现代信息科技,2025,9(20):40-43,4.基金项目
2024年度清远市哲学社会科学规划课题(QYSK2024184) （QYSK2024184）
2024校级科研项目(GDKM2024-53) （GDKM2024-53）
2024校级科研项目(GDKM2024-93) （GDKM2024-93）
