Education, Science, Technology, Innovation and Life
Open Access
Sign In

Research on the Construction of Intelligent Q&A System for University Scientific Research Management Based on Retrieval-Augmented Generation

Download as PDF

DOI: 10.23977/jaip.2026.090204 | Downloads: 0 | Views: 63

Author(s)

Yang Lei 1

Affiliation(s)

1 Yunnan Open University, Kunming, China

Corresponding Author

Yang Lei

ABSTRACT

With the deepening of digital transformation in university scientific research management, traditional manual consultation services can no longer meet the growing demand for research management inquiries. Taking the research qualification review scenario at Yunnan Open University as a case study, this paper designs and implements an intelligent question-answering system based on Retrieval-Augmented Generation (RAG) technology. The system innovatively adopts a four-layer hybrid architecture integrating a Drools rule engine, vector retrieval, large language models, and knowledge graphs. By deploying open-source large models locally and constructing a multi-source knowledge base with vector and graph databases, the system effectively addresses the hallucination problem and insufficient interpretability of LLMs in the compliance review scenario of research management. This study provides a replicable, low-cost technical path and practical reference for the intelligent transformation of university research management services.

KEYWORDS

Retrieval-Augmented Generation; Large Language Model; Research Management; Intelligent Question-Answering System; Educational Digital Transformation

CITE THIS PAPER

Yang Lei. Research on the Construction of Intelligent Q&A System for University Scientific Research Management Based on Retrieval-Augmented Generation. Journal of Artificial Intelligence Practice (2026). Vol. 9, No. 2, 34-40. DOI: http://dx.doi.org/10.23977/jaip.2026.090203.

REFERENCES

[1] Liu Bangqi, Yu Yankun, Wang Tao, et al. Large Educational Models of Artificial Intelligence: System Architecture and Key Technical Strategies[J]. Open Education Research, 2024, 30(5): 76-86. DOI:10.13966/j.cnki.kfjyyj.2024.05.008.
[3] Xie Panke, Guo Weixiu, Wu Shaojing, et al. Research on AI-Driven Smart Campus Service System — A Case Study of Central China Normal University[J]. Modern Educational Technology, 2025, 35(10): 118-126.
[4] Chen Jianlong, Wang Xincai, Shao Yan, et al. Integrated Resource Service Guidance Report of University Libraries[J]. Journal of Academic Libraries, 2025, 43(1): 38-48. DOI:10.16603/j.issn1002-1027.2025.01.005.
[5] Zhang Tian. Intelligent Question-Answering System for Libraries Based on Large Language Models[J]. Computer Programming Skills & Maintenance, 2026, (4): 109-111. DOI:10.16184/j.cnki.comprg.2026.04.018.
[6] Zhang Qiang, Qu Pengyu, Zuo Lina. Intelligent Q&A System Based on Large Language Model and Improved RAG[J/OL]. Computer Systems & Applications: 1-10[2026-08-16]. https://doi.org/10.15888/j.cnki.csa.010297.
[7] Liu Xueying, Yun Jing, Li Bo, et al. A Survey of Retrieval-Augmented Generation Based on Large Language Models[J]. Computer Engineering and Applications, 2025, 61(13): 1-25.
[8] Ding Ning, Song Yuxin, Shan Zetian, et al. Exploration on the Construction of Medical Teaching-Assisted Intelligent Q&A System Based on Retrieval-Augmented Generation (RAG) Technology[J]. China Medical Education Technology, 2025, 39(1): 1-5. DOI:10.13566/j.cnki.cmet.cn61-1317/g4.202501001.
[9] Pan Xuefeng. Construction and Application of University Library Intelligent Reference Consultation System Based on RAG Architecture[J]. Journal of Academic Library & Information Science, 2026. https://openurl.ebsco.com/contentitem/gcd:195323047?sid=ebsco:plink:crawler-gcd&id=ebsco:gcd:195323047&crl=c&jrnl=10061525.
[10] Wang Huazhen, Lin Haibin, Lin Xinyu, et al. Research on Construction of University AI Project Tutors under the Collaboration of Large Language Model and Knowledge Graph — Taking "AI Innovative Project Design" as an Example[J]. Digital Education, 2024, 10(5): 70-76.
[11] Sun Haoran, Wang Zhihao, Wu Yifan, et al. Educational Large Model Q&A Enhancement Method Based on Re-ranking and Post-Retrieval Reflection[J]. Big Data, 2025, 11(5): 4-17.
[12] Li Shengfei, Lu Yujie, Chen Xiaoying, et al. Implementation of Construction Engineering Management Knowledge Q&A Model Based on Retrieval-Augmented Generation[J]. Science Technology and Engineering, 2025, 25(25): 10840-10849.

Downloads: 27137
Visits: 939479

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.