AI-Enabled Research on Competency-Oriented Interdisciplinary Split-Track Task-Driven Instruction
International Journal of Learning and Teaching · 01.01.2026 · 12 (2) · 107
DOI: 10.18178/ijlt.12.2.107-112 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Learning and Teaching, online erschienen am 01.01.2026. Verfasst von Yongxiang Yu und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Aiming at the problems of insufficient task suitability and a single evaluation dimension in personalized teaching, this paper proposes an Artificial Intelligence (AI)-empowered competency-oriented interdisciplinary split-track task-driven teaching framework. The framework takes the background of super-discipline integration education, uses AI empowerment and causal analysis to achieve precise matching of task competence and elimination of confounding variables, and realizes the goal of multidimensional competence enhancement through assessment and evaluation optimization. In the case of information security teaching implementation, the F-test results show that the variance of students’ competence is significantly reduced from 20.97 to 10.41, reflecting the effectiveness of the framework. The framework provides a new methodological paradigm and useful reference for AI-enabled personalized teaching.
Zitieren
APA
Yu, Y., Duan, B., & Xiao, Y. (2026). AI-Enabled Research on Competency-Oriented Interdisciplinary Split-Track Task-Driven Instruction. International Journal of Learning and Teaching, 12(2), 107. https://doi.org/10.18178/ijlt.12.2.107-112
Vancouver
Yu Y, Duan B, Xiao Y. AI-Enabled Research on Competency-Oriented Interdisciplinary Split-Track Task-Driven Instruction. International Journal of Learning and Teaching. 2026;12(2):107. doi:10.18178/ijlt.12.2.107-112
BibTeX
@article{Yu2026,
author = {Yu, Yongxiang and Duan, Bin and Xiao, Yao},
title = {AI-Enabled Research on Competency-Oriented Interdisciplinary Split-Track Task-Driven Instruction},
journal = {International Journal of Learning and Teaching},
year = {2026},
volume = {12},
number = {2},
pages = {107},
doi = {10.18178/ijlt.12.2.107-112}
}
EUVIMED