Trend estimation model of students' thought and behavior based on big data

Abstract

With the rapid development of global informatization, the ways for contemporary college students to acquire knowledge are enriched. College students have active thinking, strong ability to accept new things, easy to be influenced by various cultures, open-minded, and novel values. College students' ideas have gradually matured, but they are highly malleable and likely to be influenced by the external environment. In order to quantitatively analyze the trend of students' thinking and behavior, an estimation model of students' thinking and behavior trend based on big data is proposed. Constructing semantic ontology big data distribution set of students' thought and behavior trends, establishing semantic ontology fusion feature distribution set of students' thought and behavior trend estimation by adopting multi-source parameter distributed reconstruction and phase space fusion analysis methods, analyzing the parameter feature quantity of students' thought and behavior trend distribution fusion by combining ambiguity detection and information feature matching methods, and constructing association rule distribution set of students' thought and behavior trend estimation by adopting global ambiguity reconstruction and feature reconstruction methods. Through fuzzy detection and information fusion, the semantic structure characteristics of students' ideological and behavioral trends are analyzed. By matching ideological and behavioral characteristics and mining statistical information, students' ideological and behavioral trends are estimated and self-adaptive convergence control is realized, and the optimal solution of students' ideological and behavioral trends estimation is obtained. The simulation results show that this method is highly adaptive and stable in estimating the trend of students' thinking and behavior, and improves the accurate probability of estimating the trend of students' thinking and behavior.