Intelligent Diagnosis of Classroom Teaching Structure under TESTII Framework

Abstract

Analyzing and diagnosing the classroom teaching structure is the fundamental way to improve the quality of education and teaching. However, traditional analysis methods have limitations such as over-reliance on experts, low analysis efficiency, and difficulty in scale. The purpose of this study is to use artificial intelligence technology to improve the efficiency of classroom teaching diagnosis. Based on the TESTII (Teaching Events, SPS, Time coding, Interpretation, Improvement) framework, using such as speech recognition, natural language understanding, combined with artificial labeling and proofreading, identifying teaching events, dividing teaching stages, and exploring whole-class teaching methods The order of the structure. The study found that text extraction can greatly improve the analysis efficiency of the teaching event coding method, and the analysis results can directly serve as a reference for ST coding and ITIAS coding; the Sequencing of Pedagogical Structure matches the role tags of teachers and students, which is a necessary supplement to SPS and aso forms a classroom The premise of the results of teaching analysis; This study conducted a small sample analysis of 12 course examples, and the results were very similar to the award distribution results evaluated by human experts.