Research on the Diagnosis and Feedback Paths of Digital Intelligence Teaching Ability among Normal University Students Driven by Multimodal Data

Abstract

Effective diagnosis and precise feedback on normal university students' teaching abilities are key links in ensuring teacher education quality, but traditional methods have long faced challenges such as strong subjectivity and lagging feedback. The rise of multimodal learning analysis technology has provided new possibilities for automated diagnosis and precise feedback in the teaching process; however, existing methods still fall short in terms of data interpretation systematization and interpretability of feedback. Based on an overview of the current research status of teaching ability diagnosis and feedback for normal university students, this study constructs a diagnostic and feedback path model that includes four core components: multimodal data collection, intelligent diagnostic analysis, precise feedback intervention, and ability development tracking. The implementation mechanism is explained from four dimensions: data layer, analysis layer, feedback layer, and tracking layer. The research aims to provide a reference theoretical framework and practical path for diagnosing and providing feedback on intelligent teaching abilities empowered by intelligent technology for normal university students.