Music Recommendation System and Recommendation Model Based on Convolutional Neural Network

Abstract

In today’s era of big data with excess information, music is common and everyday, which shows the huge amount of music data. How to obtain one’s favorite music from the massive music database has become a problem, and the emergence of music recommendation systems is also inevitable. In this paper, we take digital piano music as the research object, form comprehensive features using spectrum and notes, design classification methods using convolutional neural networks, and further process the classification results and design recommendation algorithms. The basic method of music recommendation of this algorithm is to determine the structure of the network model, determine the corresponding training model, and improve the parameters on the basis of the typical source network model used in the system experiment. Historical behavior chooses to collect information. Then, it reads the audio data on the system and retrieves it from Mel, which reveals the identity of the music. The classification proposal achieves its goal by denying the similarity between customer preferences and the potential of two musical characteristics. Two recommended methods based on convolutional neural networks are tested in this article. On the whole, the accuracy of the user’s comprehensive feature, recommendation method is higher than the recommendation accuracy rate of the multicategory user. In the comparison experiment of the single-category and multicategory recommendation methods, the average accuracy rate of single-category user feature recommendation is 50.35%; and the recommendation accuracy rate of multicategory user features is higher than the recommendation accuracy rate of single-category user features. The experimental results show that the two recommendation methods can achieve better recommendation results.

Intelligent Recommendation Method for Talent Resources Based on Big Data

“…The talent resource samples used in this experiment are from a talent recruitment website, as shown in Table 1. Based on the talent resource data shown in Table 1, and using the root mean square error between predicted and actual scores, as well as the recommendation accuracy of talent resources, this method was compared and validated with the methods in reference [4] and [5].…”

“…The smaller the root mean square error between actual and predicted values, the more accurate the rating of talent resources. The root mean square error results of talent resource scoring for this method and reference [4] and reference [5] methods are shown in Figure 5. From Figure 5, it can be intuitively seen that among the three methods, the root mean square error of talent resource scoring prediction in this paper is the smallest, with a value of 0.787, while the root mean square error decibels of scoring prediction in reference [4] method and reference [5] method are 1.354 and 0.932.…”

“…However, there is a significant deviation in the recommendation results of this method. Reference [5] proposes a recommendation method based on graph convolutional neural networks, which constructs a user target bipartite graph and obtains user neighborhood preference information through continuous convolutional layers in the graph convolutional neural network to complete resource recommendation. However, this method has the problem of significant loss.…”

A CNN Sound Classification Mechanism Using Data Augmentation

“…Sound is a complex, feature-rich signal, and sound classification is receiving strong interest in a growing number of application areas, from speech recognition [ 1 , 2 ], music analysis and recommendation [ 3 , 4 ], environmental sound monitoring [ 5 , 6 ], and anomaly detection and security [ 7 , 8 ].…”

“…Music analysis and recommendation [ 3 , 4 ]: Sound classification allows for the analysis and categorization of music based on various features, such as genre, tempo, mood, and instrumentation. This classification enables personalized music recommendations, playlist generation, music organization, and automatic tagging.…”