A method for pushing remote teaching materials based on knowledge graph and user profile

In order to improve the accuracy of teaching resource delivery and reduce delivery latency, this study proposes a remote teaching material delivery method based on knowledge graph and user profile. Firstly, the graph is divided into subsets to search for similar users, and a multi-layer RNN-based entity prediction model is used to complete the target platform user relationships. Secondly, comprehensive spatial and temporal data from multiple sources are collected to form personalised user profiles. Finally, a precise remote teaching resource delivery model based on support vector machine is constructed to achieve real-time delivery of personalised learning resources. The combination of knowledge graph and user profile enables precise delivery of learning resources through accurate user relationship completion and personalised feature analysis. Experimental results demonstrate that the proposed method consistently maintains accuracy above 96% in testing and exhibits significantly lower delivery latency compared to other methods.