Personalized recommendation algorithm based on domain knowledge

In the context of big data, the recommendation system came into being. The recommendation system consists of three components: recommendation candidates, users and recommendation strategies. In terms of recommendation strategy, collaborative filtering algorithm is widely used because it can meet the needs of personalized recommendation. The algorithm itself is also evolving. The domain of knowledge as a personalized recommendation and intelligent guidance of the combination of points, goals and evaluation-oriented, to provide users with recommendations to adapt to their own characteristics. Using vector space model to represent the domain knowledge and introducing domain knowledge into the recommendation strategy, the learner's model is used to describe the learner's characteristics, combined with the content-based recommendation algorithm and the collaborative filtering recommendation algorithm, A test question recommendation algorithm based on domain knowledge is proposed. The algorithm has good interpretability, validity and recommendation accuracy.