摘要：This paper designs and implements a music style prediction system using an improved sparse neural network, aiming to provide users with personalized music lists that match their interests. This paper firstly introduces how to combine the restricted Boltzmann machine model and recommendation algorithm and proposes a method to extract data features—setting a threshold to extract data features, and then, based on this, this paper introduces an improved K-Item RBM by weighted fusion of RBM recommendation algorithm and Item’s recommendation algorithm. Finally, the algorithm model is trained and predicted by the extracted features, and the experimental comparison analysis shows that the K-Item RBM algorithm can reduce the error between the predicted data and the real data and improve the performance of the recommendation system; in addition, to improve the accuracy of the recommendation, this paper introduces an improved CNN-CF neural network recommendation algorithm, which uses a convolutional neural network (CNN) to extract. The algorithm uses a convolutional neural network (CNN) to extract text features from the dataset, then trains the algorithm model, and finally makes personalized recommendations to users. The system can crawl user and music data and complete preprocessing of data such as deduplication, word separation, and keyword extraction. In this paper, we define the prediction evaluation criteria with the evaluation index F as the core and compare and analyse the prediction effect of four models longitudinally. The experimental results show that the music style prediction model based on the improved sparse neural network has a higher evaluation index value F and better prediction performance than the two-time series prediction models; compared with the general sparse neural network music style prediction model, the improved sparse neural network music style prediction model has an increased evaluation index value F for prediction ability, and the overall prediction effect is better and the prediction ability is significantly improved. The system can judge the appropriate recommendation algorithm according to the actual situation of the user and music data information and realize the continuously personalized music list recommendation for users to meet their music needs.
