Design and Practical Effectiveness Evaluation of Intelligent Teaching Platform for Music Education in Colleges and Universities

Abstract

The development of the Internet, artificial intelligence, and other technologies has put forward new requirements for intelligent music education in colleges and universities. This paper utilizes Internet technology to construct an intelligent teaching platform for music education in colleges and universities, incorporating the intelligence of music appreciation, online examination, and music knowledge learning. The forward neural network multi-feature fusion algorithm in the music appreciation module constructs the music emotion classification model, arranging the content based on the appreciation content and emotion type. The online examination module uses the simulated annealing method to improve the genetic algorithm, which then intelligently groups papers. The method of hierarchical analysis is used to quantitatively and qualitatively analyze the students’ satisfaction and design evaluation indexes for music-intelligent teaching platforms from the perspectives of teaching content and teaching quality. The music education classroom of a southern university is selected to apply the intelligent teaching platform for testing, and as the number of students gradually rises to 300 and above, the stability of the platform still performs well. Simultaneously, the evaluation results of the teaching platform indicate that the teaching quality and grouping rationality index scores are 8.94 and 9.02, respectively. These scores indicate that the platform significantly meets the students’ needs in terms of teaching effectiveness and grouping rationality.