Highly Reliable Robust Mining of Educational Data Features in Universities Based on Dynamic Semantic Memory Networks

To improve the accuracy and robustness of data feature mining, a highly reliable and robust feature mining method for university education data based on dynamic semantic memory network is proposed. Firstly, educational data was collected and extracted; Secondly, the range transformation method is used to transform and process scattered data, achieving reasonable classification of data feature attributes. Then, based on the classified results, the k-nearest neighbor method is used to perform equivalent classification on the data subset, reducing the search range for optimal values. And use floating search to reduce feature dimensionality. Finally, remove educational interference information data, update the position and step size of information elements in college English education data, and optimize the feature mining function of dynamic semantic memory network data using Levy function based on this to achieve highly reliable and robust mining. The experimental results show that the method proposed in this paper can maintain high data feature mining accuracy and robustness under both 5G network overload and attack intensity states; And it effectively improves the recall rate of data feature mining, with high reliability of data feature mining features.