检索增强生成技术支持下的校园问答系统研究

贾春燕; 方伟杰; 谢宇威; 凌在盈

doi:10.11959/j.issn.1000-436x.2024259

您当前的位置：

首页 >

文章列表页 >

检索增强生成技术支持下的校园问答系统研究

人工智能应用 | 更新时间：2024-12-31

- 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
- 通信学报 2024年45卷第Z2期页码：248-254
- 作者机构：
  
  1.浙江大学信息技术中心，浙江杭州 310027
  2.杭州师范大学信息科学与技术学院，浙江杭州 310027
- 作者简介：
  
  [ "贾春燕（1982-），女，山西昔阳人，浙江大学工程师，主要研究方向为教育信息化、信息检索、教育大模型研究及应用等。" ]
  [ "方伟杰（1975-），男，浙江杭州人，浙江大学高级工程师，主要研究方向为教育信息化、教育数字化转型等。" ]
  [ "谢宇威（1988-），男，浙江杭州人，浙江大学工程师，主要研究方向为人工智能、网络通信、用户服务数据挖掘分析、网络服务分析、运维服务一体化等。" ]
  [ "凌在盈（1982-），男，山东临沂人，杭州师范大学工程师，主要研究方向为生态遥感、水色遥感、遥感工程等。" ]
- 基金信息：
- DOI：10.11959/j.issn.1000-436x.2024259
  中图分类号： TP391
- 收稿日期：2024-10-22，
  
  纸质出版日期：2024-11-30
- 稿件说明：
移动端阅览
贾春燕,方伟杰,谢宇威等.检索增强生成技术支持下的校园问答系统研究[J].通信学报,2024,45(Z2):248-254.

JIA Chunyan,FANG Weijie,XIE Yuwei,et al.Research on campus question answering system supported by retrieval-augmented generation technology[J].Journal on Communications,2024,45(Z2):248-254.
贾春燕,方伟杰,谢宇威等.检索增强生成技术支持下的校园问答系统研究[J].通信学报,2024,45(Z2):248-254. DOI： 10.11959/j.issn.1000-436x.2024259.

JIA Chunyan,FANG Weijie,XIE Yuwei,et al.Research on campus question answering system supported by retrieval-augmented generation technology[J].Journal on Communications,2024,45(Z2):248-254. DOI： 10.11959/j.issn.1000-436x.2024259.

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.

关键词

Keywords

references

Tony H , Stewart T , Kristin T . 第四范式:数据密集型科学发现 [M ] .潘教峰, 张晓林, 等译. 北京 : 科学出版社 , 2012 .

陈帅朴 , 刘芳霖 , 钱宇星 , 等 . 检入新境: 大语言模型引领的信息检索主题与知识关联演化分析 [J/OL ] . 图书情报知识 ,( 2024-06-27 )[ 2024-10-20 ] .

CHEN S P , LIU F L , QIAN Y X , et al . Topic and Knowledge Association Evolution in the Field of Large Language Model-enabled Information Retrieval [J/OL ] .Documentation,Information & Knowledge,( 2024-06-27 )[ 2024-10-20 ] .

赵鑫 , 窦志成 , 文继荣 . 大语言模型时代下的信息检索研究发展趋势 [J ] . 中国科学基金 , 2023 , 37 ( 5 ): 786 - 792 .

ZHAO X , DOU Z C , WEN J R . The development of information retrieval in the era of large language model [J ] . Bulletin of National Natural Science Foundation of China , 2023 , 37 ( 5 ): 786 - 792 .

曹培杰 , 谢阳斌 , 武卉紫 , 等 . 教育大模型的发展现状、创新架构及应用展望 [J ] . 现代教育技术 , 2024 , 34 ( 2 ): 5 - 12 .

CAO P J , XIE Y B , WU H Z , et al . The development status, innovation architecture and application prospects of educational big models [J ] . Modern Educational Technology , 2024 , 34 ( 2 ): 5 - 12 .

苗逢春 . 生成式人工智能技术原理及其教育适用性考证 [J ] . 现代教育技术 , 2023 , 33 ( 11 ): 5 - 18 .

MIAO F C . Examination of the technique principle of generative AI and its educational applicability [J ] . Modern Educational Technology , 2023 , 33 ( 11 ): 5 - 18 .

余胜泉 , 熊莎莎 . 基于大模型增强的通用人工智能教师架构 [J ] . 开放教育研究 , 2024 , 30 ( 1 ): 33 - 43 .

YU S Q , XIONG S S . General artificial intelligence teacher architecture based on enhanced pre-trained large models [J ] . Open Education Research , 2024 , 30 ( 1 ): 33 - 43 .

齐思洋 , 胡慧云 , 李洪冰 , 等 . 融合大语言模型的领域问答系统构建方法 [J ] . 北京邮电大学学报 , 2024 : doi.org/10.13190/j.jbupt.2023-279.

QI S Y , HU H Y , LI H B , et al . Domain question answering system construction approach integrated with large language model [J ] . Journal of Beijing University of Posts and Telecommunications , 2024 : doi.org/10.13190/j.jbupt.2023-279.

文森 , 钱力 , 胡懋地 , 等 . 基于大语言模型的问答技术研究进展综述 [J ] . 数据分析与知识发现 , 2024 , 8 ( 6 ): 16 - 29 .

WEN S , QIAN L , HU M D , et al . Review of research progress on question-answering techniques based on large language models [J ] . Data Analysis and Knowledge Discovery , 2024 , 8 ( 6 ): 16 - 29 .

张金营 , 王天堃 , 么长英 , 等 . 基于大语言模型的电力知识库智能问答系统构建与评价 [J/OL ] . 计算机科学 . 2024 , https://link.cnki.net/urlid/50.1075.TP.20240528.0931.002(网络首发地址)（网络首发日期： 2024-05-28 ）

ZHANG J Y , WANG T K , YAO C Y , et al . Construction and Evaluation of Intelligent Question Answering System for Electric Power Knowledge Base based on Large Language Model [J/OL ] . Computer Science , 2024 , https://link.cnki.net/urlid/50.1075.TP.20240528.0931.002 https://link.cnki.net/urlid/50.1075.TP.20240528.0931.002

竹倩叶 , 鄂海红 . 基于大语言模型的垂直领域问答系统研究 [J ] . 新一代信息技术 , 2023 , 6 ( 17 ): 8 - 16 .

ZHU Q Y, E H H, Research on Vertical Domain Dialogue Systems Based on Large Language Model [J ] . New Generation Of Information Technology , 2023 , 6 ( 17 ): 8 - 16 .

卢宇 , 余京蕾 , 陈鹏鹤 , 等 . 生成式人工智能的教育应用与展望: 以ChatGPT系统为例 [J ] . 中国远程教育 , 2023 ( 4 ): 24 - 31, 51 .

LU Y , YU J L , CHEN P H , et al . Educational application and prospect of generative artificial intelligence: taking ChatGPT system as an example [J ] . Chinese Journal of Distance Education , 2023 ( 4 ): 24 - 31, 51 .

OpenAI . GPT-4 technical report [J ] . arXiv Preprint , arXiv: 2303.08774 , 2023 .

TOUVRON H , MARTIN L , STONE K R , et al . Llama 2: open foundation and fine-tuned chat models [J ] . arXiv Preprint , arXiv: 2307.09288 , 2023 .

ZENG A H , LIU X , DU Z X , et al . GLM-130B: an open bilingual pre-trained model [J ] . arXiv Preprint , arXiv: 2210 . 02414 v 2 , 2022 .

DEVLIN J , CHANG M , LEE K , et al . BERT: pre- training of deep bidirectional transformers for language understanding [C ] // Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies . Stroudsburg : ACL Press , 2019 : 4171 - 4186 .

VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [J ] . Advances in Neural Information Processing Systems , 2017 ( 30 ): 5998 - 6008 .

CHANG Y P , WANG X , WANG J D , et al . A survey on evaluation of large language models [J ] . ACM Transactions on Intelligent Systems and Technology , 2024 , 15 ( 3 ): 1 - 45 .

NEUPANE S , HOSSAIN E , KEITH J , et al . From questions to insightful answers: building an informed chatbot for university resources [J ] . arXiv Preprint , arXiv: 2405.08120 , 2024 .

LEWIS P , PEREZ E , PIKTUS A , et al . Retrieval-augmented generation for knowledge-intensive NLP tasks [C ] // Proceedings of the 34th International Conference on Neural Information Processing Systems . Massachusetts : MIT Press , 2020 : 9459 - 9474 .

OpenAI . Our approach to alignment research [EB/OL ] . ( 2023-07-05 ) [ 2024-10-22 ] .

JI Z , LEE N , FRIESKE R , et al . Survey of hallucination in natural language generation [J ] . ACM Computing Surveys , 2023 , 12 ( 55 ): 1 - 38 .

PETRONI F , ROCKTÄSCHEL T , LEWIS P , et al . Language models as knowledge bases? [J ] . arXiv Preprint , arXiv: 1909.01066 , 2019 .

RAGFlow . 端到端的检索增强生成引擎 [EB/OL ] . ( 2024-04-01 ) [ 2024-10-22 ] .

RAGFlow . End-to-end retrieval-augmented generation engine [EB/OL ] . ( 2024-04-01 )[ 2024-10-22 ] .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

利用检索增强生成技术开发本地知识库应用

大语言模型在教育信息化中的实践：规范、框架与应用

基于大语言模型的网络威胁情报知识图谱构建技术研究

基于大语言模型的多模态社交媒体信息流行度预测研究