Adaptive Generation and Analysis of Classical Music Style Based on Big Data

With the in-depth research on artificial intelligence, it has undergone profound industrial changes in various fields. The research aims to explore the use of generative artificial intelligence in music creation by combining big data. This study uses big data analysis and machine learning algorithms to extract features and model styles from a large number of classical music works, achieving adaptive generation of classical music styles. Afterwards, this study conducts performance tests on the model, and the results showed that the maximum error rate of our method was 10 %, and the highest accuracy was 100 %. In the evaluation of generated music segments, the average accuracy of the music generated by our model in terms of style can reach 81 %, and the average evaluation on other indicators is above 7 points. The experimental results demonstrate that this study provides a new perspective and tool for the creation and analysis of classical music, effectively promoting the adaptive generation and innovative development of music styles, and demonstrating the enormous potential of big data and machine learning technology in the field of music creation.