A Robust Recommendation Algorithm for Campus Cultural Education Resources Based on Collaborative Filtering

In order to improve the recommendation accuracy of teaching resources, a recommendation algorithm for campus cultural education resources based on collaborative filtering is designed. The method proposes to build a user interest model, dynamically fine-tune the teacher and student models as the amount of data continues to increase, and acquire students' interest models in a course in real time. Based on the collaborative filtering algorithm, the similarity of recommended resources is calculated, and the similarity between students' interests and the course is calculated; the recommendation algorithm of campus cultural education resources is designed, and the recommendation method of teaching resources is obtained. Comparing several different resource recommendation algorithms, it can be seen from the experimental data that when the similarity threshold is the same, the accuracy of the collaborative filtering method is the maximum among the three comparison methods, and the recall rate is the minimum. The average absolute error of the four algorithms can reach the minimum value when the similarity threshold is 0.3-0.4. At this time, the error value of the collaborative filtering method is 0.62, and the average absolute errors of the other two methods are 0.63 and 0.88, respectively. It can be seen that the recommendation accuracy of this method is better than the other two methods.