In order to overcome the limitations of low knowledge recommendation accuracy, low knowledge utilisation rate of, and high total management cost in traditional methods of comprehensive management of educational knowledge, a comprehensive management strategies method of educational knowledge from the perspective of digital humanities is proposed. Educational knowledge data are collected through web crawling technology, annotated using the GPT model, and then integrated with TransE model and collaborative filtering algorithm to achieve knowledge recommendation. After determining the recommended content of educational knowledge, comprehensive management strategies are designed for educational knowledge from multiple aspects such as constructing a comprehensive educational knowledge graph, strengthening knowledge sharing and communication, and promoting knowledge innovation and application. The case test results show that the accuracy of the proposed method for educational knowledge recommendation varies between 93.9% and 97.1%, with a maximum utilisation rate of 75.9%, and the total management cost is 2,163,100 yuan.
Jianlei Zhang (Thu,) studied this question.