Application of Semantic Similarity Calculation Based on Knowledge Graph for Personalized Study Recommendation Service

With the coming of the era of big data and the introduction of personalized education concept, how to provide students to value their valuable resources quickly has become hotspot. The efficiency of personalized recommendation service of large educational data is mainly reflected in the accuracy of the recommended algorithm. Semantic similarity computation is essential to be improved for the accuracy of calculation. The research will provide guidance for big data in education area. The development of the Semantic Web has led to new breakthroughs in many fields, such as semantic search, knowledge engineering, knowledge maps, and data connections. The core of the Semantic Web lies in the representation and representation of knowledge in the ontology layer. At the same time, it involves relevant rules and reasoning. Many research fields are based on the ontology lay-er and carry out related research. The semantic similarity technology is a major is-sue in these research fields. Due to the large-scale, heterogeneous, and loosely organized nature of Internet content, it poses a challenge for people to obtain in-formation and knowledge effectively. The Knowledge Graph has powerful open organization capabilities and semantic processing capabilities, laying the foundation for the knowledge-based organization and intelligent applications in the Internet era. At present, the work of the main semantic similarity methods focuses on the structure of the semantic network between concepts (eg, path length and depth), or only on the conceptual information content (IC), and at the same time uses the ontology-related properties for calculations. However, there are some flaws. Therefore, this paper proposes a semantic similarity method, wpath, which com-bines these two methods and uses IC to weight the shortest path length between concepts. In the experiment, it is verified that the proposed method has a certain degree of feasibility and credibility in computing semantic similarity in knowledge graphs. Compared with other methods, the results are superior to other methods.