Individualized Recommendation Method of Multimedia Network Teaching Resources Based on Classification Algorithm in a Smart University

Abstract

Abstract Current recommendation methods of multimedia network teaching resources cannot classify the resources with high precision, which leads to large deviation of recommendation results and low recall. Therefore, a personalized recommendation method of multimedia network teaching resources based on classification algorithm is proposed. Adaptive sliding window mutual information method is used to process historical and incremental data of teaching resources and extract the characteristics of multimedia network teaching resources. Two-step clustering algorithm combined with business identifier code criteria are used to complete resource classification. Based on structured query language (SQL) multimedia network teaching resources data recommendation database, document query and processing, combined with SQL structure, a personalized recommendation of multimedia network teaching resources is completed. The experimental results show that the recall of the classification results is higher than 99.58 %, and the highest F1 value is 97.28 %. The precision of personalized recommendation of multimedia network teaching resources is always higher than 90 %, and the recall rate is also higher.