TY - GEN
T1 - An AHP-QFD and Generative AI Integrated Approach for Deep Learning in Design Education
AU - Liu, Shuo Fang
AU - Jiang, Min
AU - Liu, Hua
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2027.
PY - 2027
Y1 - 2027
N2 - Against the backdrop of artificial intelligence (AI) increasingly transforming design education, integrating technological tools into classroom instruction to foster students’ deep learning has become a critical challenge. This study focuses on the Furniture Modeling Design course and proposes an innovative teaching model that synergistically integrates the Analytic Hierarchy Process–Quality Function Deployment (AHP–QFD) framework with generative large language model (LLM) technology. First, the core pedagogical requirements of the course are systematically quantified using AHP; integrated with QFD, the abstract construct of “deep learning” is rigorously decomposed into concrete, actionable teaching elements. Second, we develop a curriculum framework anchored in the “concept–practice–reflection” pedagogical model—operationalized and enhanced through LLM. During classroom implementation, AI functions not as a replacement but as a scaffolded cognitive tool to guide students’ reflective design practice. Third, multimodal large models—leveraging image recognition—are employed to objectively assess both student engagement and assignment quality. By conceptualizing AHP–QFD as a “deep learning goal deconstruction mechanism” and AI as a “pedagogical scaffolding tool”, this research contributes both theoretical insights and empirically grounded strategies for advancing intelligent, learner-centered innovation in design education.
AB - Against the backdrop of artificial intelligence (AI) increasingly transforming design education, integrating technological tools into classroom instruction to foster students’ deep learning has become a critical challenge. This study focuses on the Furniture Modeling Design course and proposes an innovative teaching model that synergistically integrates the Analytic Hierarchy Process–Quality Function Deployment (AHP–QFD) framework with generative large language model (LLM) technology. First, the core pedagogical requirements of the course are systematically quantified using AHP; integrated with QFD, the abstract construct of “deep learning” is rigorously decomposed into concrete, actionable teaching elements. Second, we develop a curriculum framework anchored in the “concept–practice–reflection” pedagogical model—operationalized and enhanced through LLM. During classroom implementation, AI functions not as a replacement but as a scaffolded cognitive tool to guide students’ reflective design practice. Third, multimodal large models—leveraging image recognition—are employed to objectively assess both student engagement and assignment quality. By conceptualizing AHP–QFD as a “deep learning goal deconstruction mechanism” and AI as a “pedagogical scaffolding tool”, this research contributes both theoretical insights and empirically grounded strategies for advancing intelligent, learner-centered innovation in design education.
UR - https://www.scopus.com/pages/publications/105046322583
UR - https://www.scopus.com/pages/publications/105046322583#tab=citedBy
U2 - 10.1007/978-3-032-32115-2_26
DO - 10.1007/978-3-032-32115-2_26
M3 - Conference contribution
AN - SCOPUS:105046322583
SN - 9783032321145
T3 - Lecture Notes in Computer Science
SP - 263
EP - 273
BT - Innovative Technologies and Learning - 9th International Conference, ICITL 2026, Proceedings
A2 - Lin, Chia-Ju
A2 - Istenic, Andreja
A2 - Istenic, Andreja
A2 - Istenic, Andreja
A2 - Huang, Tien-Chi
A2 - Huang, Yueh-Min
PB - Springer Science and Business Media Deutschland GmbH
T2 - 9th International Conference on Innovative Technologies and Learning, ICITL 2026
Y2 - 4 August 2026 through 6 August 2026
ER -