Dynamic updating mechanism of teaching content driven by both artificial intelligence and big data within an efficient classroom

Abstract

The new curriculum reform requires teachers to focus not only on the transmission of knowledge in efficient classroom teaching but also on the promotion of students’ comprehensive development, ensuring the diversification of teaching and the dynamic updating of teaching content. Based on the integration of “artificial intelligence + big data” technology in teaching and learning, this paper proposes a dynamic adjustment model of teaching content based on the conceptual graph. The Bayesian network structure learning method is employed as a test method to determine the independence of variables and create directed graphs. Meanwhile, the K2 and LPG algorithms are being improved to establish the C-IK2 model for automatic concept map generation. Sequentially, the data is processed in stages of preprocessing, generating complete graphs, and constructing minimum spanning trees to construct a model for dynamic updating and adjustment of teaching content. Through experimental analysis, the model is applied to the actual teaching work. The experimental results show that after the dynamic updating and adjustment of teaching content, Student 1 reached the highest score rate of 68.16% in the first semester of the first year. The degree of improvement of the score rate score in the two semesters of the second year was 13.21% and 17.1%, respectively. The model of the dynamic updating and adjustment of teaching content is more helpful to the students. The academic performance of the students in class A of the research object was significantly improved. The overall average score reached 82.93 points, compared with the pre-test improved by 5.85 points. At the same time, the number of the 60-70 score band was reduced to 3. The proposed model in this paper effectively improved the academic level of the students.