Practical Teaching Reform of the “Deep Learning and Applications” Course Through the Collaboration of Knowledge Graphs and AI Agents

Tong Su; Siyuan Bei

doi:10.63313/ESW.9175

Authors

Tong Su School of Computer Science and Artificial Intelligence, Shanghai Lixin University of Accounting and Finance, Shanghai 201209, China Author
Siyuan Bei School of Computer Science and Artificial Intelligence, Shanghai Lixin University of Accounting and Finance, Shanghai 201209, China Author

DOI:

https://doi.org/10.63313/ESW.9175

Keywords:

Deep Learning and Applications, Knowledge Graph, AI Agent, Generative AI, Practical Teaching Reform

Abstract

Addressing issues such as high programming barriers, fragmented resources, delayed feedback, and limited pathways for innovation in the practical instruction of the “Deep Learning and Applications” course, this paper proposes a reform plan for practical teaching centered on a knowledge graph and featuring generative AI agents as bidirectional interfaces. This proposal leverages the ChaoXing platform to construct a course knowledge graph comprising three types of nodes—conceptual, operational, and problem-based—and utilizes generative AI to develop a teaching agent for code practice. This forms a closed-loop support system encompassing four stages: semantic parsing, code framework generation, error diagnosis, and case expansion. Consequently, it establishes two implementation pathways: precise student assistance and refined teaching support for instructors, complemented by multi-stakeholder collaborative evaluation and AI usage constraints. This plan has undergone two rounds of iterative implementation, accumulating process-based data that can serve as a reference for practical teaching reforms in artificial intelligence courses.

References

[1] Cao, F.Y, Zhao, X.W, and Gao, X.F, et al. (2025) Teaching Reform of Data Mining and Machine Learning Courses in the Context of Building First-Class Courses. Computer Education, 7: 155-159.

[2] Xin, Y, Chen, Y.F, and Li, G.Q, et al. (2025) Construction and Teaching Exploration of a Knowledge Graph for Big Data Majors in Higher Education. Computer Education, 8: 170–176.

[3] Yan, Z.H, Wu, H.Y, and Li, L.P. (2026) Exploring a Student-Assistance and Teaching-Support Model for Machine Learning Courses Driven by Knowledge Graphs and AI Agents. Educational Advances, 164: 1564–1575.

[4] Wang, Z, Zhou, X.W, and Hu, H.D, et al. (2026) “Knowledge Graphs + Intelligent Agents” Empowering a New Mechanism for Collaborative Education in Dual Classrooms. China Electric Power Education, 07: 52–53

[5] Peng, T. (2025) Application of Baidu Paddle AI Studio Platform in Machine Learning Course Instruction. Journal of Higher Education, 117: 122-125.

[6] Zhang, T.S, Shen, S.J, and Zhang, Z.C, et al. (2026) A Study on Entity Relationship Extraction from General Question-Answering on Weakly Structured Data Based on Large Language Models. Theory and Practice of Information Science, 492: 179–188.

[7] Sun, M.Q, and Li, S.N. (2026) An Empirical Study on the Distorting Impact of AI Code Generation Tools on Undergraduates’ Underlying Logical Thinking in Programming. Curriculum Education and Application, 7: 11

[8] Liu, K, et al. (2026) Knowledge graph-AI agent collaborative framework: a case study and effectiveness analysis of higher education teaching practice based on an integrated teaching platform. Information, 17(8): 742.