Volume 10,Issue 9
Construction of Machine Learning Classroom Knowledge System and Intelligent Guidance Practice under the Dual‑Driven Concept
*Author to whom correspondence should be addressed.
With the full arrival of the artificial intelligence era, machine learning has gradually become a core compulsory course for majors such as computer science, big data, and artificial intelligence in universities. It also acts as a key hub connecting basic theories with industrial implementation. Traditional machine learning classrooms have long adopted the one‑way indoctrination teaching mode. Prominent problems, including fragmented knowledge systems and homogenized teaching adaptation, make it difficult to meet the personalized, intelligent, and practical talent‑training demands of the new era. The “dual‑driven concept” mentioned in this paper refers to machine‑learning‑oriented teaching reform jointly supported by a course knowledge graph and an intelligent agent. The knowledge graph undertakes structural organization, relationship presentation, and dynamic updating of course knowledge, while the intelligent agent is responsible for teaching interaction support, Q&A assistance, learning‑situation analysis, and personalized recommendation. The two form a collaborative linkage through the loop of “knowledge supply–behavioral feedback–iterative optimization.”
[1] Du W, Zhu H, Zhao J, et al., 2025, Teaching Reform of “Lecture‑Practice Split‑Class” for Machine Learning Based on Rain Classroom. Computer Education, (11): 142–147.
[2] Hou H, 2025, Machine‑Learning‑Based Prediction of Secondary Vocational School Students’ Academic Performance and Personalized Teaching Design: A Case Study of the Secondary Vocational Course Computer Network, thesis, Shandong Normal University.
[3] Wei Z, 2025, Research on Course Recommendation Algorithm for Online‑Education Enterprises Based on Machine Learning, thesis, China University of Geosciences.
[4] Guo M, Xiong X, Zhan G, 2025, Optimization and Verification of Machine‑Learning Training for Regression Model of Classroom‑Silence Influencing Factors. Research and Exploration in Laboratory, 44(4): 108–113.
[5] Bai Z, 2025, Design and Research and Development of Senior‑High‑School Artificial Intelligence School‑Based Curriculum From the Perspective of Disciplinary Big Concepts, thesis, Southwest University.
[6] Zhao H, 2025, Research on Classroom‑Behavior Recognition and Prediction System Based on Machine Learning. Journal of Changchun University, 35(2): 8–12.
[7] Jian X, Cui C, 2024, Design and Practice of Blended Teaching for the Machine‑Learning Course. Computer Education, (12): 143–147.
[8] Liu J, Wang X, Yuan X, 2024, Exploration on Teaching Reform of Postgraduate Machine‑Learning Course Based on CDIO Concept. Journal of Science and Education, (19): 135–137.
[9] Peng H, 2024, Practical Research on Optimizing the Teaching of Secondary‑Vocational C‑Language Programming Course Through Learning‑Behavior Data Analysis, thesis, Shandong Normal University.
[10] Hu X, 2024, Research on the Application of Blended‑Teaching Mode for Machine‑Learning Course Under OBE Concept. Papermaking Equipment and Materials, 53(1): 178–180.
[11] Cao S, Song T, 2023, Exploration of Comprehensive Classroom‑Teaching Mode for Programming‑Oriented Courses — Taking Python Machine Learning Course of China Jiliang University as an Example. Education Teaching Forum, (44): 154–157.
[12] Zhang T, 2022, Development and Practice of the School‑Based Machine‑Learning Curriculum for Compulsory‑Education Stage — A Case Study of P‑School in Shanghai, thesis, East China Normal University.
[13] Zhu D, Li X, Jin Z, et al., 2020, Efficient‑Classroom Design for Full‑English Machine‑Learning Courses Based on Technology‑Application Procedures. Computer Education, (5): 133–136 + 140.
[14] Zheng Y, Zheng Y, 2019, Systematic Design of Smart‑Classroom Implementation Schemes — Taking Statistics and Machine‑Learning Fields as Examples. Journal of Tongling University, 18(6): 102–106.
[15] Mo L, 2019, Exploration of Blended‑Teaching Mode for Postgraduate Degree Courses From the Perspective of Innovative Engineering Education — Taking Machine‑Learning Course as an Example. Coal Higher Education, 37(6): 111–115.
