Research on the Mechanism of Analyzing Student Learning Behaviors in Flipped Classrooms and Recommending Resources Based on Knowledge Graphs

This study proposes a knowledge graph-based mechanism for analyzing students' learning behaviors and recommending resources for educational intelligence. The framework includes processes such as multi-source data integration. The key components include data preprocessing, behavior classification, graph inference, and resource recommendation. Data preprocessing uses statistical methods to ensure data availability. Behavioral classification is based on cluster analysis of standardized values. Graph reasoning uses vectorization techniques to identify weak points. Resources are recommended based on the analysis results to provide reference for educational intelligence.