KG-LECR-IMS: a knowledge graph-driven intelligent management system for labor education curriculum resources in universities

In view of the multi-source development of labor education in colleges and universities, there are currently problems such as insufficiently rapid response and inaccurate recommendation in the management mode. This paper proposes an intelligent system integrating various multi-source heterogeneous information collection, online knowledge graphs, visual interpretation and hybrid recommendation strategies, and uses Neo4j technology to achieve rapid graph indexing to meet the needs of graph expansion and update as well as parallel operations. Introduce students' behavioral habits and preferences to improve the accuracy of personalized recommendations; The tests show that the system response time is 1.2 seconds, the accuracy rate reaches 85%, the recall rate reaches 82%, the user satisfaction increases by 15%, and the course completion rate increases by 10%. Meanwhile, AES-256 encryption and RBAC mode are introduced to ensure data security and integrity and achieve the optimal system performance.