Research on Intelligent Optimization of Teacher Education Teaching Strategies Driven by Big Data in the Perspective of Basic Theory of Education

Abstract

To clarify the teaching strategies and effects of teachers in educating students from the perspective of big data, this paper proposes a K-means algorithm based on density optimization. The behavioral data generated by different students are classified into classes for students with similar types. Then, the FP-growth algorithm is used to mine the correlation between students' learning effects and their learning behaviors. Provide students with a more targeted educational management model and better services. The results show that there is a positive correlation between joint entropy time and space and students' frequency of campus activities and grades, and there is a strong correlation between the total number of times students go to the library, the number of times they consume in the cafeteria, and students' grades; 54% of the students in the campus have a regular time and space behaviors, and 55.08% of the students show low intensity in their study behavioral inputs. In this paper, four class clusters of students were obtained by clustering students' consumption behavior, library borrowing behavior and students' sports behavior respectively. In the process of teaching, teachers should guide students in the first category to strengthen sports and participate in activities in moderation; let students in the second category take more important roles in the team to show and develop their leadership skills; for students in the third and fourth categories, they can cultivate their ability to socialize with others by recommending them to read books and works that are rich in philosophical and interpersonal behaviors.