Design and Empirical Analysis of Artificial Intelligence-Based Decision Aid Models for College Management

This paper first outlines the requirements for an intelligent college teaching management decision support system, outlines the system framework based on these requirements, and then discusses several key technologies, including data warehouses, data mining, and online analysis. The basic concepts and algorithms of association rules are also described, and the association rule algorithms are applied to the inter-course correlation analysis and the execution evaluation of the university teaching management decision support system. Mining and analyzing students’ grades and daily performance through the intelligent university teaching management decision support system, the results show that in science courses, the percentage of female students’ grades in the range of 60-80 is about 80%, while male students’ grades are mainly concentrated in the range of 70-90. There is a positive correlation between students’ classroom attendance and course grades; when the attendance rate is 120%, the grades are mainly concentrated in the 60-100 range. Grades in the Situation and Policy course were associated with multiple courses. Instructional management implementation was rated better at 83%. Therefore, this paper successfully constructs an intelligent college teaching management system and applies it to specific projects to achieve better results.