Research on the method of combining artificial intelligence technology to improve the effectiveness of teaching analytical chemistry in colleges and universities

In this paper, a TDINA model is proposed to enhance the effectiveness of analytical chemistry teaching in colleges and universities by combining the cognitive ability level, personalized learning needs, knowledge mastery and other personality characteristics of student users. Firstly, it introduces the existing common models for cognitive diagnosis of students’ knowledge mastery level, combines the information of students’ historical answer situation, introduces the relevant influence factors on the calculation of the key positive answer rate, and establishes a TDINA model for analyzing the effectiveness of students’ chemistry learning. Then the comparison experiments of different cognitive diagnostic models were conducted in different test sets and the experimental effects were evaluated, and the model proposed in this paper was also used for the empirical analysis of chemistry teaching effectiveness. The validity of the TDINA model proposed in this paper for acquiring students’ cognitive ability levels in chemistry was confirmed. After analyzing the probability of students’ attribute mastery, it was found that the probability of mastery of all attributes for all students ranged from 0.7 to 1.0, which led to the conclusion that the overall mastery of reaction rates and limits of chemistry learning was good after applying the methodology of this paper.