Key points are not available for this paper at this time.
On the basis of the existing research data, this study deeply analyzes the influence of artificial intelligence on college students' learning by establishing a mathematical model, and discusses the complex relationship between the two. First, according to the data characteristics of the problem, it is subdivided into three categories: no sequence feature, sequence feature and multi-label. Then, different methods such as label coding, serial number coding and multi-label coding are used to digitize the data. Factor analysis and Bartlett test were used to conduct in-depth analysis of the validity and reliability of the data, and the reliability and validity of the data were verified. The reliability coefficient Cronbach's reached 0. 857. Then, according to the characteristics of the survey respondents, the impact of artificial intelligence, and future prospects, the data is divided into three categories using cluster analysis based on the K -means algorithm. On this basis, the TOPSIS comprehensive evaluation model based on entropy weight method is established. Combined with the selected indicators, the respective weight coefficients are calculated, and the TOPSIS method is used to solve the comprehensive score of each student, so as to evaluate the specific impact of artificial intelligence on learning. Through the comprehensive use of a variety of analysis methods, this study deeply explored the mechanism of artificial intelligence's influence on college students' learning, and provided an important reference and guidance for further understanding and application of artificial intelligence in the field of education.
Chen et al. (Tue,) studied this question.