Exploring the innovation path of daily management mode of college students in the new era based on big data technology

Abstract

Abstract This paper uses big data technology to focus on the clustering and correlation analysis of students’ daily behavior. The daily management workflow of students is constructed by analyzing the main algorithms of big data technology and the application scope. The association degree rules are combined to calculate students’ associated behaviors’ minimum support and confidence degree. The clustering algorithm was used to classify the daily management patterns of students into learning, closed, and active types. The student daily management clustering process was improved by using Newton interpolation to improve the inheritance and compatibility of node changes. In the correlation analysis, the support of the association label for regular type 1 was 0.441 in support and 0.852 in confidence, and the support of more regular type 2 was 0.425 in support and 0.846 in confidence.