节点文献

检索增强生成技术支持下的校园问答系统研究

Research on campus question answering system supported by retrieval-augmented generation technology

  • 推荐 CAJ下载
  • PDF下载
  • 不支持迅雷等下载工具,请取消加速工具后下载。

【作者】 贾春燕方伟杰谢宇威凌在盈

【Author】 JIA Chunyan;FANG Weijie;XIE Yuwei;LING Zaiying;Information Technology Center, Zhejiang University;School of Information Science and Engineering, Hangzhou Normal University;

【通讯作者】 方伟杰;

【机构】 浙江大学信息技术中心杭州师范大学信息科学与技术学院

【摘要】 针对高等学校师生用户从海量校园信息中获取有效信息的困难,以校务领域知识为数据源,基于检索增强生成技术,设计了一个校园智能问答系统。融合大语言模型和垂直领域专业知识,以学校百事通项目为依托,将包括办事指南、常见问题、规范性文件等校务信息作为外挂数据语料库,应用检索增强生成专用的Infinity数据库,构建校务知识库,采用提示词工程,增强大语言模型生成答案。通过检索增强生成技术进行教育领域特定的校园问答,旨在以互动方式为用户提供各种校务服务信息,有助于解决校园常见问题,简化师生咨询流程,减轻学校管理工作负担。

【Abstract】 To solve the problem of obtaining effective information from the vast amount of campus information for teachers and students, an intelligent campus question answering(QA) system based on RAG was designed. An approach that integrates large language models and domain knowledge for QA system construction was proposed, relying on the campus’ s Everything You Need to Know project, and using campus information such as procedural guides, frequently asked questions, and normative documents as an external data corpus. A campus knowledge database was constructed, with the RAG Infinity database. To improve the retrieval efficiency of domain knowledge and the accuracy of answers, the prompt approach was proposed. Using RAG for campus QA, the system provides users various service information in an interactive manner, which helps to solve common campus issues, simplify the consultation process for teachers and students, and alleviate the burden on campus management, and enrich campus knowledge resources.

  • 【文献出处】 通信学报 ,Journal on Communications , 编辑部邮箱 ,2024年S2期
  • 【分类号】TP391.1;G647
  • 【下载频次】56
节点文献中: 

本文链接的文献网络图示:

本文的引文网络