Analysis and Optimization of Teaching and Learning Paths in Universities Based on Association Data Mining

There are challenges in maximizing the allocation of teaching and learning routes and teaching resources due to the high number of disciplines offered and the big number of students in universities. Because students attend different schools and work in different departments, there is a strong relationship between the students’ overall grade point average and their performance in individual classes. Such discrepancies and correlations may be properly studied and analyzed using the Apriori method. In order to increase the accuracy and speed of computations, this article uses the Material Point approach (MPM) approach. This method treats each data point as a particle, and the Lagrangian method in MPM can effectively track the trajectory of the particles, avoid unnecessary polling, reduce data dissipation and improve computational accuracy. Therefore, based on the MPM method, the improved Apriori algorithm can efficiently explore the interrelationships between conventional courses and computer-related comprehensive teaching and professional teaching, providing highly feasible teaching and learning path suggestions, enabling teaching management and course design to achieve high quality, while also enhancing the quality of teaching. The experimental results show that the improved Apriori algorithm proposed in this article can update the parameters of certain nodes, thus greatly improving the query and search efficiency of data and resources.