Optimization of Teaching Path of Artificial Intelligence Programming Course in the Context of New Engineering Construction

Abstract

Under the background of new engineering construction and the requirements of new curriculum reform, the problem of using big data technology to combine with the teaching of the “Artificial Intelligence Programming” course has caused many educational researchers to focus on the problem. In this paper, we propose data mining based on a clustering algorithm to build a teaching management system to optimize the teaching path of the Artificial Intelligence Programming course and build a web-based teaching management system based on clustering analysis and clustering validity index. Then the system structure and database are designed through the teaching system requirements, and the course teaching evaluation index system is built based on the teaching objectives of Artificial Intelligence Programming. Finally, the course’s teaching efficiency is analyzed using the teaching system with 20 weeks of teaching Artificial Intelligence Programming in one semester. The results show the clustering algorithm: the average course teaching efficiency is 39.95%, and the BP neural algorithm: the average course teaching efficiency is 34.71%. Genetic algorithm: the average course teaching efficiency is 33.96%. Based on the clustering algorithm teaching system improves the course teaching efficiency by 39.95% compared with the other two better performances, which is conducive to improving the quality of course teaching and teaching reform. This study provides better information technology support for new engineering construction and engineering teaching optimization and has reference guiding value for course teaching research.