Keywords
Knowledge graph
Large model
Literature analysis
Intelligent teaching
Submitted : 2026-05-13
Accepted : 2026-05-28
Published : 2026-06-12
Abstract
Objective: To explore the development path of computer education driven by the dual wheels of knowledge graph and large model, and provide theoretical references for technological iteration and method innovation. Methods: Through literature combing, analyze the application status, empowering value, and limitations of large models in computer education, and propose a collaborative development framework combined with the technical characteristics of knowledge graphs. Results and Conclusion: The integration of knowledge graphs and large models can reshape the innovative ecology of computer education, forming new breakthroughs in fields such as interdisciplinary resource development, dynamic knowledge graph construction, and human-machine collaborative intelligent teaching.
References
Dai D, 2026, Technical Risks and Governance Paths of Artificial Intelligence Large Models. Journal of Hanjiang Normal University, 46(01): 96–101.
Zha Y, Guo C, Ju H, 2025, Design and Implementation of an Intelligent Learning Assistant Based on Large Language Models. Modern Information Technology, 9(03): 50–55.
Sun C, Xie P, Shan L, et al., 2025, Research on Automatic Question Answering Method Based on Large Language Models. Software Guide, 24(11): 9–14.
Xu S, Tong J, Hu X, 2024, Next-Generation Personalized Learning: Generative Artificial Intelligence-Enhanced Intelligent Tutoring Systems. Open Education Research, 30(02): 13–22.
Zhang Q, Liu J, Li W, et al., 2025, Exploration of the Application of Large Language Models in Automatic Code Grading. Educational Information Technology, (10): 62–66.
Mao X, Dong W, Yin L, et al., 2025, Exploration of Large Language Model-Assisted Software Development Practice. Research in Higher Education of Engineering, (06): 33–38.
Zhao M, Zou Q, Yao H, 2025, Construction of a Personalized Learning System for Computer Courses Based on Large Models. Information Industry Report, (11): 0158–0160.
Leng X, Xiong B, Xu J, et al., 2025, Construction of Computer Programming Course Resources Assisted by Large Language Models. Journal of Higher Education, 11(34): 21–24.
Wu P, Guo P, Geng P, et al., 2025, Research on the Construction of Course Knowledge Graphs Based on Large Models and Multi-Source Learning Resource Data. China Information Technology Education, (21): 97–101.
Gui X, He Q, 2024, Systematic Reform Exploration of University Computer General Education Empowered by AI. China University Teaching, (04): 4–11 + 2.
Zhang Y, 2023, Research on Data-Driven Student Programming Behavior Analysis and Personalized Recommendation Methods, dissertation, Beijing University of Chemical Technology.
Tian R, Song J, Zhu B, 2025, Exploration and Practice of GAI in College Computer Programming Teaching and Learning. China Light Industry Education, 28(05): 68–78.
Bo J, Qiao Y, Qi Q, et al., 2024, Exploring the Application Potential and Challenges of AIGC Technology in College Programming Courses. Computer Technology and Development, 34(06): 214–220.
Ma Q, 2024, Research on Plagiarism Detection and Evaluation System for Review-Type Assignments, dissertation, South China University of Technology.
Zhang S, Meng X, Wang T, et al., 2025, Computer Education Based on Large Language Models: Opportunities, Challenges and Teaching Strategy Innovation. Computer Knowledge and Technology, 21(12): 171–173.