Innovation Series: Advanced Science (ISSN 2938-9933, CNKI Indexed)

Construction of an AI-Driven Stratified Adaptive Teaching Model for Mathematics in Vocational Undergraduate Education

Shi Wang*

Hainan Vocational University of Science and Technology, Haikou 571126, China

Corresponding Author: Shi Wang (ws10121@126.com)

Abstract: Against the backdrop of typological orientation and the high-quality development of vocational undergraduate education, the structure of student intake has become increasingly diverse. Significant disparities exist in students’ mathematical foundations and learning abilities. Traditional uniform teaching models struggle to effectively meet these differentiated learning needs. Drawing on the principles of stratified instruction, adaptive learning and learning analytics, this study explores the integration of artificial intelligence technologies into mathematics teaching in vocational undergraduate education, with the aim of developing an AI-driven, stratified, adaptive teaching model. Based on a clear delineation of conceptual connotations, the study systematically identifies key features including data-driven decision-making, dynamic adaptation, personalized support and human-machine collaboration. The study also develops a closed-loop operational framework of ‘diagnosis-stratification-implementation-feedback-regulation’ and explains its operational mechanisms from the perspectives of instructional processes, technological support and organizational forms. The findings indicate that the proposed model enhances instructional precision and process regulation capabilities. However, effectiveness depends on coordinated support in terms of data quality, teachers’ digital literacy, a stratified resource system and institutional guarantees.

Keywords: Vocational Undergraduate Education; Mathematics Teaching; Artificial Intelligence; Stratified Instruction; Adaptive Learning; Learning Analytics

References