부산대학교 도서관

Users are facing an increasingly challenging challenge, which is how to identify the music that they enjoy amid the huge amount of music available online, given the rapid development in the number of digital songs. The music recommendation system creates individualized recommendations for users by evaluating the previous behavior of users' on-demand music. This can help users feel less overwhelmed by information and provide a better overall experience for users. The purpose of this research is to present an algorithm for recommending piano music that takes into account time-frequency information. Then, it determines the preference of one user for an author based on the tag ratings of other users who are similar to the author in order to select music for suggestion that is more in line with the user's preferences..