Research on Training and Application of Artificial Intelligence Models Based on Digital Resource Libraries
DOI:
https://doi.org/10.70088/0nrh2s32Keywords:
Artificial Intelligence, Digital Resource Library, Mechanical Drawing, Vocational Education, Personalized Learning, Knowledge GraphAbstract
This study conducts research on the construction and application of an AI-assisted teaching system, supported by the digital teaching resource library of the Shanghai Excellent Course "Mechanical Drawing" and the AI model of the Chaoxing website. By integrating diverse digital resources such as existing course videos, animations, and exercises, the research builds a knowledge graph containing 128 knowledge point nodes and 326 semantic association relationships, trains an AI Q&A robot integrated with over 500 typical question-answer pairs, and develops a dynamic learning analytics module, thus forming a solution for applying AI in teaching. The research shows that the AI system can effectively improve teaching efficiency and learning quality, confirming that customized training to achieve deep integration between AI models and professional teaching resources is the key to AI empowering vocational education. It provides a replicable and promotable practical paradigm for the intelligent transformation of vocational education courses. The results indicate that the AI model system can effectively enhance students' learning efficiency and classroom participation, reduce teachers' teaching burden, and offer a replicable practical paradigm for the intelligent transformation of vocational education courses.References
Ministry of Education, China, “National Strategy for AI Integration in Vocational Education,” Chinese Vocational and Technical Education, vol. 42, no. 12, p. 115, 2023.
Z. Wang et al., “AI-Driven Virtual Drafting Assistant for Vocational Training,” Simulation & Gaming, vol. 54, no. 4, pp. 456–472, 2023.
M. Zhou and Y. Gu, “Ethical Considerations of AI in Mechanical Drafting Education,” International Journal of Technology and Design Education, vol. 35, no. 3, pp. 679–695, 2025.
P. Hao et al., “Digital Resource Library-Driven AI Model Customization in Vocational Education,” Chinese Journal of Mechanical Engineering (English Edition), vol. 38, no. 3, p. 112, 2025.
H. L. Xiang et al., “Chaoxing AI Platform in Vocational Mechanical Education: A Multi-Case Study,” Journal of Educational Technology & Society, vol. 28, no. 2, pp. 234–247, 2025.
Idaho State Department of Education, “AI-Enhanced Competency Mapping for Mechanical Drafting Careers,” Career and Technical Education Research, vol. 49, no. 2, pp. 111–128, 2024.
Y. Liu et al., “Ontology-Driven Knowledge Graph Construction for Mechanical Drawing,” Knowledge-Based Systems, vol. 283, p. 109567, 2024.
Y. Li, Y. Gu, and L. Zhang, “Knowledge Graph-Enhanced Personalized Learning for Mechanical Drawing: A Vocational Education Case,” Computers & Education, vol. 205, p. 104682, 2025.
H. Chen et al., “Domain-Specific Q&A Robot Training for Mechanical Drafting: A Vocational Education Perspective,” IEEE Transactions on Learning Technologies, vol. 17, no. 3, pp. 654–667, 2024.
M. Li et al., “Continual Learning for Mechanical Drafting Q&A Robots,” Applied Intelligence, vol. 55, no. 5, pp. 7890–7905, 2025.
X. Chen et al., “Visual Analytics for Mechanical Drawing Learning Trajectories,” Computers in Human Behavior, vol. 145, p. 107682, 2023.
L. Zhao and C. Liu, “Cognitive Diagnosis of Mechanical Drawing Skills via AI-Learning Analytics,” International Journal of Engineering Education, vol. 41, no. 2, pp. 567–578, 2025.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Yunlu Gu (Author)

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









