Key points are not available for this paper at this time.
With the advent of the big data era, knowledge graphs, as important tools for organizing, managing, and understanding massive amounts of information, are gradually becoming a research hotspot in the field of artificial intelligence. This article focuses on the research and practice of automated construction and application of knowledge graphs in the field of university courses, aiming to improve the efficiency and accuracy of knowledge graph construction and provide strong support for the application in related fields.This study integrated publicly available datasets, mainstream online education platforms, and course explanation texts. Using rule-based and deep learning information extraction methods, combined with a large language model, the automatic extraction of entities, attributes, and relationships was successfully achieved, and an initial course knowledge graph was constructed based on this. Furthermore, by calculating the similarity between course description texts and combining the extracted course prerequisite and peer relationships from the texts, the study not only enriches the structure and content of the course knowledge graph, but also enhances its accuracy and practicality. In order to provide more personalized course recommendation services, this article combines sequence based recommendation algorithms and graph embedding algorithms, fully utilizing the information of the course itself and the dependency information of the course sequence, designing a unique personalized recommendation algorithm, and verifying its effectiveness and accuracy through experiments. This study not only provides strong knowledge graph support for online education platforms, but also provides strong technical support for personalized learning recommendations.
Chen et al. (Mon,) studied this question.