Construction of a University Computer Resource Repository Based on Knowledge Graph
University computer courses produce a large number of teaching materials in various forms. Slides, videos, exercises, experiment reports and project cases are usually in different systems and do not have semantic links; therefore, retrieval is inefficient and resource reuse is not possible. This paper employs a knowledge graph to construct a repository of university computer resources. A course ontology is designed to organize concepts, competencies, and resources within a unified framework. Entity and relation extraction are performed on course materials, followed by knowledge fusion and human-in-the-loop quality control. A graph-based repository was constructed in Neo4j and tested with real data from three computer courses. The constructed graph has 1864 entities and 5213 triples. The F1 score for knowledge extraction is 0.87, and the mean query response time has fallen from 2.8 seconds to 0.6 seconds after switching to keyword search.
[1] Abu-Salih B, Alotaibi S, 2024, A Systematic Literature Review of Knowledge Graph Construction and Application in Education. Heliyon, 10(3): e25383.
[2] Li Y, Liang Y, Yang R, et al., 2024, CourseKG: An Educational Knowledge Graph Based on Course Information for Precision Teaching. Applied Sciences, 14(7): 2710.
[3] Deng C, Yuan B, 2026, Research on an Intelligent Tutoring System Based on Automatic Construction of Multimodal Knowledge Graphs and Retrieval-Augmented Generation. Frontiers in Computer Science, 8: 1777749.
[4] Ren J, Wang X, 2026, Knowledge Graph-Based Design of Digital-Intelligent Curriculum Modules and Teaching Reform in Auditing. Frontiers in Education, 11: 1757383.
[5] Chen G, Song T, Wang Q, et al., 2025, Knowledge Graph and Large Language Model Integration With an Emphasis on Educational Applications: A Survey. Neurocomputing, 654: 131230.
[6] Lin Y, Wu Z, 2025, Learning Path Recommendation Based on Knowledge Tracing and Large Language Models. Electronics, 14(22): 4385.
[7] Luo G, Gu H, Dong X, et al., 2025, HA-LPR: An Adaptive Learning Path Recommendation. Education and Information Technologies, 30(10): 14597–14627.
[8] Zanellati A, Di Mitri D, Gabbrielli M, et al., 2024, Hybrid Models for Knowledge Tracing: A Systematic Literature Review. IEEE Transactions on Learning Technologies, 17: 1021–1036.
[9] Zhou L, Wang Y, 2025, Simulation of Personalized English Learning Path Recommendation System Based on Knowledge Graph and Deep Reinforcement Learning. Scientific Reports, 15(1): 34554.
[10] Yang Y, Peng X, Chen M, et al., 2025, An Explainable Graph-Based Course Recommendation Model Based on Multiple Interest Factors. Expert Systems with Applications, 264: 125889.
