Personalized Recommendation Method of Online Distance Teaching Resources Based on User Profiles

The problem of online learning resource overload makes it difficult for online learning users to access learning resources that are of interest or value to them in a timely manner, resulting in interruptions in the online learning process or low learning efficiency. In this regard, a personalized recommendation method for online remote teaching resources based on user profiles is studied. Collect user related data, preprocess user data through data mining techniques, select appropriate user tags to describe users, and construct a user profile system. Based on user profiling, the density peak clustering algorithm is used to calculate the preference similarity between the target user and other users. By comparing the similarity between the target user and other users, identify the user group that is most similar to the target user. Then, personalized recommendations of online remote teaching resources are made based on the interests and preferences of these similar users. The experimental results show that the coverage and diversity of the recommendation method based on user profiles reach the highest of 0.9 and 4.5, indicating that the recommendation effect of the proposed recommendation method in this article is relatively ideal and superior to previous recommendation algorithms.