Network education recommendation and teaching resource sharing based on improved neural network

Abstract

Intelligent network teaching system provides learners with abundant teaching resources and convenient, excellent and efficient learning environment. However, network teaching resources are widely distributed and difficult to centralize. Resource sharing has become a key problem to be solved in the network environment. The current research on online education resource recommendation mainly focuses on offline education, and there are few studies on online education resources. Based on this, this study studies the link prediction methods in online education and establishes appropriate models for online education. In the research, through improved analysis of traditional algorithms, an improved neural network path sorting algorithm based on path sorting method is proposed. At the same time, we use the path sorting algorithm based on random walk model and neural network-path sorting algorithm to realize the link prediction problem in the online learning knowledge base. In addition, the performance analysis of the algorithm is carried out by contrast method, and the performance comparison analysis is carried out by combining various common traditional recommendation algorithms with the research algorithm of this study.