Research on Sports Dance Video Recommendation Method Based on Style

Abstract

At present, sports dance teaching still tends to “demonstration” training. Students have limited time and space for autonomous learning, and their enthusiasm for participation is not high, which leads to a decline in classroom learning efficiency. In view of this, video teaching has become popular in sports dance classrooms, providing a new model for sports dance teaching. Video recommendation is particularly important for the improvement of teaching quality. A sports dance video recommendation method based on style is proposed. The factorization machine model is used to combine features and process high-dimensional sparse features, the deep neural network model is adopted as the value function network of the deep Q-learning algorithm, and the deep Q-learning algorithm is used as the decision function to solve the recommendation accuracy and diversity question. Through the application experiment of sports dance video recommendation, it is resulted that the recommendation accuracy of the proposed model is slightly higher than that of traditional recommendation algorithm and the recommendation diversity is obviously better than that of traditional recommendation algorithm. The advantages and feasibility of the proposed model are verified.