Provided is a personalized teaching resource recommendation method for large-scale users, comprising: obtaining user interaction data, and performing data pre-processing of the user interaction data to obtain a user resource scoring matrix; performing feature dimensionality reduction on the user resource scoring matrix to obtain a user's teaching resource feature matrix; clustering the teaching resource feature matrix to obtain clusters of teaching resources, and sorting the teaching resources in the teaching resource clusters; obtaining user ratings of all teaching resources, and using a teaching resource interest model in sequence to calculate the user's degree of interest in the teaching resources, and arranging all teaching resources in descending order according to the degree of interest to generate a list of recommended teaching resources. The method can provide a large number of users with fast and accurate digital teaching resource recommendation services, thus enhancing user experience, and provide a set of effective solutions for the personalized utilization of teaching resources at a smart campus.
展开▼