Automatic Recommendation Algorithm for Video Background Music Based on Deep Learning

Abstract

As one of the traditional entertainment items, video background music has gradually changed from traditional consumption to network consumption, which naturally also has the problem of information overload. From the perspective of model design and auxiliary information, this paper proposes a tightly coupled fusion model based on deep learning and collaborative filtering to alleviate the problem of poor prediction accuracy due to sparse matrix in the scoring prediction problem. In the use of auxiliary information, this paper uses crawler technology to obtain auxiliary information on the user side and the video background music side and compensates for the model’s sensitivity to the sparsity of the score matrix from a data perspective. In terms of model design, this paper conducts auxiliary information mining based on the diversity and structural differences of auxiliary information, uses an improved stack autoencoder to learn user’s interests, and uses convolutional neural networks to mine hidden features of video background music. Based on the idea of probabilistic matrix decomposition, the tightly coupled fusion of multiple deep learning models and collaborative filtering is realized. By comprehensively considering user’s interest and video background music characteristics, the collaborative filtering process is supervised, and the optimized prediction result is finally obtained. The performance test and function test of the system were carried out, respectively, to verify the effectiveness of the hybrid recommendation algorithm and the effect of the system for recommendation. Through experimental analysis, it is proved that the algorithm designed in this paper can improve the recommendation quality and achieve the expected goal.

Research on Expanding Grassroots Employment Space for College Students in the Context of Rural Revitalization + Data Platform

“…The data collection methods in the university grassroots employment data platform include automatic crawlers, third-party data, and manual collection [20][21]. Most of the data are obtained by automatic crawlers, and the data collected by third-party data are mainly data indicators in various employment business scenarios of universities, which are too large, and the collection process is more complicated.…”

Music Tone Synthesis based Anti-Interference Dynamic Integral Neural Network optimized with Artificial Hummingbird Optimization Algorithm

“…Current music recognition technology primarily consists of a basic fusion of all musical features, which falls short of the high technical requirements for music appreciation [9][10][11]. The next research area for the existing music appreciation model is feature selection, screening, and combination [12]. Two essential pieces of technological equipment for the cepstral area assessment are the Mel frequency cepstral factor and the straight predictive cepstral factor.…”

Video Background Music Recognition and Automatic Recommendation Based on Gmm Model

“…The system's suggested songs for users are now more accurate thanks to several manual and easy mining techniques, but the architecture of such video music in the background itself has not seen a proportional improvement in terms of analysis and processing power. Considering the connotations of the video background music themselves, it's possible that only a skilled composer or music critic could properly get the essence of such video background music and be able to identify its genre while listening to it [2]. Ancient music; environment; sustainable development With the fast expansion of China's economy, traditional music has had to contend with an increasingly acute issue of existence; many of these genres are now at their breaking point or in danger of extinction.…”