Design of Interactive Music Teaching System for Wireless Communication Application by Convolutional Neural Network Optimization and Edge-Cloud Computing

This study aims to improve the effectiveness of online music teaching and optimize the current interactive system of online teaching. Firstly, the basic connotation of Convolutional Neural Network (CNN), edge-cloud computing and their application principles are discussed. Then, the basic principles of wireless communication and its comprehensive optimization methods are discussed. Finally, the Softmax Convolutional Neural Network-Long Term Evolution (SCNN-LTE) model based on CNN to optimize wireless communication technology is designed. Model skills are comprehensively assessed. The results show that, compared with other models, the comprehensive performance of the designed CNN model has been greatly improved. The evaluation found that the recall value of the Softmax Convolutional Neural Network (SCNN) model is around 0.9-1.0, and the precision value is around 0.8–0.9. Additionally, CNN models are applied to wireless communication technologies for performance evaluation. The accuracy of the SCNN-LTE model is generally between 0.7 and 0.9. The designed model not only optimizes the CNN model to a certain extent but also deeply optimizes the wireless communication technology. Therefore, the model can be better applied to the online music teaching interactive system, providing important technical support for its effect optimization. This study not only provides a technical reference for the optimization of wireless communication technology but also contributes to the performance enhancement of the online music teaching interactive system.