Design of a personalized music theory knowledge pushing system using artificial bee colony algorithm in music education

Abstract

The application mode of “intelligent algorithm + education industry” has a broad application prospect nowadays. The article explores the design of intelligent algorithms in personalized music theory knowledge delivery system from the perspective of intelligent music education. Aiming at the problems of low recommendation efficiency and large computation in traditional collaborative filtering algorithms, a K-means clustering collaborative recommendation algorithm based on improved artificial bee colony algorithm is proposed. The artificial bee colony algorithm is improved through initialization and fitness function, combined with K-means iteration to get more accurate clustering effect, and then merged into collaborative filtering algorithm to complete the music theory knowledge recommendation. The experimental analysis proves that the algorithm reduces the average absolute error value, shortens the running time, and improves the recommendation quality and recommendation efficiency. The system is used in S-school for practical teaching. Students' scores increased from 61.52 to 69.96. T-test results show that there is a significant difference in music scores with a significant probability of P=0.019 (0.01<P<0.05). It shows that the music theory knowledge pushing system based on IABC's K-means clustering collaborative filtering algorithm can make music education more visualized and intelligent, and have a far-reaching impact on the music teaching career.