Adaptive content recommendation for distance education based on fuzzy logic and knowledge graph

Intending to the issue that existing adaptive content recommendation methods for distance education ignore the dynamic uncertainty of learners' cognitive level, the top-down approach is first used to construct the distance education KG (DEKG), and the TransR model is utilised to vectorise the representation of the DEKG. Secondly, based on fuzzy logic, the cognitive level of the learners is determined, and the matching degree and cognitive level are combined to calculate the similarity of knowledge points. Then, the degree of learner preference was measured using fuzzy logic to represent the knowledge point similarity as a vector over the content labels. Subsequently, a corresponding rating prediction formula is designed to realise more effective and accurate mining of distance education content that meets learners' characteristics for recommendation. The experimental results show that the proposed method improves the recall and F1 by at least 3.21%.