The Application of Big Data Technology in University English Teaching Mode Innovation and Effect Analysis

Abstract

Abstract In the dynamic planning of reinforcement learning algorithms based on inverse recursion, this research shows how well Q-learning performs in finding the optimal decision function for accurate English teaching intervention in colleges and universities using data simulation. This simultaneously contrasts the two scenarios of calculating the best decision function independently and in a single stage using the Q-learning method. The correlation analysis between the innovative English teaching model and learners’ learning effectiveness was carried out by demonstrating the great clusters of the subset of English teaching data in colleges and universities. The results show that the correlation coefficients of English innovative teaching mode and learning outcomes are 0.385 and 0.276, respectively, in which H2-P1 and H2-P2 involve the structure of students’ personalized learning of English, whether it is an edge or a node, and the learning behaviors are not completely autonomous processes. This study proposes innovative strategies for improving the quality of university English teaching and laying a good educational foundation for students’ English learning.