Design of smart teaching evaluation management system based on K-means clustering and machine learning

Teaching quality is the foundation of educational institutions, and good teaching quality can attract more students. The emergence of smart education has further promoted the reform of teaching, but there is currently no systematic evaluation method for smart education. To further improve the teaching quality in universities, a teaching quality management approach on the grounds of K-means clustering and Apriori algorithm is designed. This method adopts violent analysis technology to cluster the teaching quality of university teachers and then analyzes the influence of internal causes of teachers on teaching quality through Apriori algorithm. The results show that in the same university, teaching methods and teaching attitudes are more likely to affect the teaching quality, while the teaching content basically has basically no impact on the teaching quality. The confidence degree that teaching methods and teaching attitudes have a greater impact on teaching quality can reach more than 95%, and the support degree can also reach more than 25%. Research and design of teaching quality management method can directly evaluate the influence of teachers' internal factors on teaching quality, which provides a future optimization direction for teaching quality management in colleges and universities.