To address the shortcomings of traditional teaching methods in personalized support, real-time feedback, and comprehensive evaluation, this study proposes an AI-driven instructional model. The model provides students with personalized learning paths and structured resources through intelligent recommendation systems and knowledge graphs; optimizes the learning process by integrating blended learning to achieve a closed-loop system encompassing self-directed pre-class preparation, interactive in-class engagement, and targeted post-class reinforcement; and establishes a multidimensional evaluation system that combines formative assessment with competency-based evaluations of competition performance and practical skills, thereby fostering students’ comprehensive development. The findings demonstrate that this model not only significantly enhances students’ mastery of theoretically challenging courses such as Probability and Mathematical Statistics, but also improves learning initiative and practical application skills, offering a scalable intelligent solution for the reform of mathematics education in higher education institutions.
Bai et al. (Fri,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: