Knowledge graph-based analysis and intelligent recommendation of entrepreneurship course content

This research presents a knowledge graph-driven recommendation system for entrepreneurship courses, incorporating data collection, pre-processing, entity recognition, graph analysis, and recommendation algorithms. By combining semantic relationships with collaborative filtering, the system enhances personalisation, improving both accuracy and user satisfaction. Knowledge graphs provide a structured representation of entities and their relationships, enabling more relevant and context-aware recommendations. Leveraging this capability, the system aligns course suggestions with learners preferences and educational goals. Prior studies highlight the effectiveness of knowledge graphs in domains such as tourism, education, and e-commerce for improving recommendation precision. The proposed workflow follows sequential stages, including data pre-processing, knowledge extraction, graph construction, analysis, and algorithm development. integrating top-down ontology design with bottom-up entity extraction, guides knowledge graph creation. Experiments on a dataset of over 6,000 educational resources achieved stable accuracy after 80 training epochs using the BERT-BiGRU-MHSA-CRF framework. User evaluations confirmed higher engagement and satisfaction compared to baseline models.