Abstract

Background: Interdisciplinary learning is increasingly emphasized in industrial design education. Yet teaching practice continues to face challenges, including uneven disciplinary foundations, fragmented knowledge integration, and limited responsiveness to diverse learning needs. Purpose: This study intends to construct and validate an AI-mediated hierarchical teaching path, which supports interdisciplinary learning in industrial design education against the backdrop of emerging engineering education by aligning instructional content with students’ differentiated learning profiles. Methods: Drawing on precision teaching theory and a constructivist learning perspective, an AI-mediated hierarchical teaching path was designed and implemented. Students’ learning profiles were identified through an AI-based diagnostic process and grouped into three levels: basic, improvement-oriented, and innovation-oriented. Differentiated interdisciplinary learning activities were provided for each level, and teaching strategies were iteratively adjusted based on ongoing learning analytics and instructional collaboration. Results: The implementation led to the establishment of a curriculum system integrating professional core courses, interdisciplinary modules, and AI-supported collaborative learning platforms. Results indicate improved interdisciplinary collaboration among basic-level students, enhanced design feasibility among improvement-oriented students, and a 28% increase in national-level design competition awards among innovation-oriented students compared with previous cohorts. Conclusion: The findings demonstrate that AI-mediated hierarchical teaching can effectively enhance the adaptability of interdisciplinary instruction in industrial design education. This approach supports stratified student development and targeted instructional support, offering practical implications for interdisciplinary curriculum design and faculty development in higher education.