Research on Personalized Learning Path Construction of College Short Video Platform Based on Dynamic Content Optimization Algorithm

Abstract

The study designed a dynamic genetic algorithm based on dynamic content with multi-adaptation by setting stopping criterion, cost function optimization and other strategies, and constructed personalized learning paths in short video platforms in colleges and universities by this algorithm. In order to more accurately realize the personalized learning path recommendation, the learner model and the learning resource model are constructed, and at the same time, according to the mapping relationship between the two, multiple objective functions such as the cognitive level of the learner and the learning style are determined. Combined with the improved optimization algorithm, the personalized learning path construction problem is solved to complete the personalized learning path construction under the short video platform. The algorithm in this paper iterates 140 times, and the objective function converges to about 12, which is faster and better than the convergence speed of the comparison algorithm. Through personalized learning path recommendation, the average grade of students in the experimental group is improved by 7.4 points compared with the control group, which is a significant difference. Under the personalized learning path recommendation, the average time for students to learn the knowledge points in the college short video platform drops dramatically, and the average learning time is only 65.36 min. the multidimensional scores of the students for the personalized learning path are 4.12-4.72, in which the path needs to be further improved for the improvement of learning efficiency.