Article: Impact of personalised learning system based on generative AI on students' higher-order thinking ability and reconstruction of teachers' roles Journal: International Journal of Information and Communication Technology (IJICT) 2026 Vol.27 No.98 pp.26 - 52 Abstract: To investigate the impact of a generative artificial intelligence (AI) personalised learning system on students' higher-order thinking and teacher role reconstruction, this paper proposes a generative AI-based personalised learning system via DKT and PPO (GAP-DP). That integrates a dynamic concept graph and a metacognitive strategy prompt library. The system addresses the limitations of existing approaches in precise diagnosis, dynamic planning, and human-AI collaboration. It employs a graph-sequence dual-channel to diagnose cognitive states and uses hierarchical rewards to guide instructional pathways aimed at enhancing analysis, evaluation, and creativity. Simulation experiments show that training loss converges to 0.082 and instructional action exploration utilisation reaches 96%. In real classroom settings, diagnostic accuracy for knowledge modules attains 87.7%, students' higher-order thinking skills assessment score increases to 4.25, and teachers' role reconstruction perception score reaches 4.43. By deeply integrating precise diagnosis with metacognitive guidance, GAP-DP effectively empowers students' higher-order thinking development and facilitates teachers' transformation into thinking guides and human-AI collaborators. Inderscience Publishers - linking academia, business and industry through research

Title: Impact of personalised learning system based on generative AI on students' higher-order thinking ability and reconstruction of teachers' roles

Authors: Duo Zhang; Mingqiang Wu; Shuping Liu; Qiuyun Song

Addresses: Faculty of Humanities and Arts, Xi'an FanYi University, Xi'an, 710105, China ' International College, Phetchabun Rajabhat University, Phetchabun, 67000, Thailand ' Dancing College, Hunan Vocational College of Art, Changsha, 410100, China ' Teachers College, Guizhou University of Engineering Science, Bijie, 551700, China

Abstract: To investigate the impact of a generative artificial intelligence (AI) personalised learning system on students' higher-order thinking and teacher role reconstruction, this paper proposes a generative AI-based personalised learning system via DKT and PPO (GAP-DP). That integrates a dynamic concept graph and a metacognitive strategy prompt library. The system addresses the limitations of existing approaches in precise diagnosis, dynamic planning, and human-AI collaboration. It employs a graph-sequence dual-channel to diagnose cognitive states and uses hierarchical rewards to guide instructional pathways aimed at enhancing analysis, evaluation, and creativity. Simulation experiments show that training loss converges to 0.082 and instructional action exploration utilisation reaches 96%. In real classroom settings, diagnostic accuracy for knowledge modules attains 87.7%, students' higher-order thinking skills assessment score increases to 4.25, and teachers' role reconstruction perception score reaches 4.43. By deeply integrating precise diagnosis with metacognitive guidance, GAP-DP effectively empowers students' higher-order thinking development and facilitates teachers' transformation into thinking guides and human-AI collaborators.

Keywords: generative AI; personalised learning system; deep knowledge tracking; proximal strategy optimisation; higher-order thinking ability; HOTA; teacher role reconstruction; TRR.

DOI: 10.1504/IJICT.2026.156260

International Journal of Information and Communication Technology, 2026 Vol.27 No.98, pp.26 - 52

Received: 30 Jan 2026
Accepted: 26 Mar 2026
Published online: 08 Sep 2026 *

Title: Impact of personalised learning system based on generative AI on students' higher-order thinking ability and reconstruction of teachers' roles

Keep up-to-date