An innovative model of digitally empowered teaching of ideological and political courses for university students

In this paper, a large amount of data related to the teaching of ideological and political courses is collected using information technology and preprocessed in the four dimensions of data cleaning, missing value processing, sample labeling, and expert sample data. Aiming at the problem of underfitting of traditional neural network algorithm in the evaluation of digital teaching effect of ideological and political courses, the RBF neural network is improved and optimized by combining radial basis function and radial basis interpolation, and a teaching evaluation model based on the enhanced RBF network is constructed. The combination of statistical and simulation analysis is used to analyze the learning behavior of digitally empowered ideological and political courses. The results show that among the five types of teaching activities, participation in after-class discussion (-1.6443) performs better compared to the other four types of teaching activities (-1.7541, -1.6815, 1.7331, -1.8265), indicating that the neural network algorithm based on the Improved RBF accurately reflects the learning behavior of the group in the teaching of Digital Empowerment Ideology and Politics Course. This study realizes the scientific, modern and intelligent development of digitally empowered ideological and political course teaching. It promotes digital ideological and political course teaching to be more and more scientific and philosophical.