Aiming at the shortcomings of current recommendation algorithms in capturing changes in user interests, an innovative university aesthetic education teaching resource recommendation algorithm based on collaborative filtering is proposed. In the process of developing collaborative filtering recommendation algorithms, the core features of university aesthetic education teaching resources were deeply explored, and data clustering was successfully implemented to optimize the recommendation effect of educational resources. Designed an exclusive recommendation algorithm for aesthetic education teaching resources in universities. By constructing an interest model for college students, we can accurately calculate the similarity between individuals and achieve personalized recommendation of aesthetic education teaching resources to meet the needs of aesthetic education teaching in universities The experimental data shows that the algorithm achieved a low MAE value, demonstrating excellent accuracy, and high user feedback satisfaction, proving its significant advantage in recommendation performance.