Article Details

Abstract

Since computer science courses involve numerous abstract concepts and complex theories, the overall learning difficulty is relatively high. To assist students in mastering the difficult points in professional knowledge and reduce their learning difficulty, a course knowledge precise question-answering system is designed. In response to the hallucination problem in Large Language Models, a precise question-answering system implementation method combining a Large Language Model and a Knowledge Graph is proposed. This method combines a Large Language Model with a Knowledge Graph based on collaborative question-answering strategy, conducts a three-level search on user questions, achieves precise keyword matching, and finally summarizes the retrieved results through the Large Language Model to generate answers. Experimental results show that the proposed method can effectively improve the accuracy of question answering.

Keywords

Large Language Model; Knowledge Graph; precise question-answering; course knowledge

References

1. [1] Wang Fan, Liu Yongqiang, Zhou Tianhua Artificial Intelligence Leads the Digital Innovation Development of Higher Education [J]. China Higher Education, 2024 (Z1): 9-12
2. [2] Ning Zhenhu, Zhang Teng, Xue Fei Exploration of the Construction of Computer Operating System Curriculum System [J]. Computer Education, 2024 (9): 137-140
3. [3] WU T Y，HE S Z，LIU J P，et al. A Brief Overview of ChatGPT: The History, Status Quo and Potential Future Development [J].IEEE/CAA Journal of Automatica Sinica，2023，10（5）：1122-1136.
4. [4] Zhang Zhixin, Ming Chenxi, Liu Jie, etc Intelligent knowledge Q&A technology for water related laws and regulations based on JRAG [J]. People's Yangtze River, 2025, 56 (2): 240-247
5. [5] Zhang Jiachen Ultrasound Medical Q&A System Based on Knowledge Graph [D]. Nanchang: Nanchang University, 2024
6. [6] Chen Qing, Liu Yusheng, Duan Lianda, etc Research on Wind Power Operation and Maintenance Question and Answer System Integrating Large Language Model and Knowledge Graph [J]. Integrated Smart Energy, 2024, 46 (9): 61-68
7. [7] Ma Bingqi, Zhou Yinghai, Wang Ziyu, etc A Threat Intelligence Information Extraction Method Based on Large Language Model [J]. Journal of Cybersecurity Science, 2024, 2 (2): 36-46
8. [8] Wang Lei, Yang Wang, Han Quanye Research on Building a Multimodal Curriculum Graph for Open Education Based on Large Models and Its Value Logic [J]. Journal of Shaanxi Open University, 2025, 27 (1): 18-23
9. [9] Chen Xueying, Li Shujian, Zhou Chengning, etc A review of the research on the technical system of fault knowledge graph [J]. Computer Measurement and Control, 2025, 33 (5): 1-12
10. [10] Zhu Guohui, Chen Chunxia Reliability Study of Large Language Model Applied in Aesthetic Restoration of Anterior Teeth [J]. Journal of Practical Stomatology, 2025, 41 (1): 88-92
11. [11] Wang Hailong Research and Implementation of Crop Knowledge Question Answering System Based on Large Language Model [D]. Chongqing: Southwest University, 2024
12. [12] Translated by Zhang He, Wang Xin, Han Lifan, etc Research on Question Answering System Based on Large Language Model Fusion Knowledge Graph [J]. Computer Science and Exploration, 2023, 17 (10): 2377-2388

Funding

Key Project of Natural Science Research in Universities of Anhui Province (2022AH050597); Undergraduate Teaching Quality and Teaching Reform Project of Anhui University of Finance and Economics (acjyyb2024016); Anhui University of Finance and Economics College Student Innovation and Entrepreneurship Training Program Project (X202510378496)

About the authors

Zhang Wei (1985-), male, Han ethnicity, from Huainan, Anhui Province, associate professor, PhD, research direction: based on image processing algorithms.