Answers are grounded in this paper and cite their sources.
Algorithm development demonstrates 89.2% matching accuracy for career paths in vocational textile students, highlighting a scalable approach for smart education.
To address the mismatch between the employability of higher vocational students and the evolving requirements of the textile and garment industry, this study proposes an employment ability modeling framework and path optimization algorithm based on a dual-helix competency model integrating craft inheritance and digital innovation. A capability–job coupling matrix is established by incorporating regional industrial characteristics, industry-specific coefficients, and practical training constraints, while an improved NSGA-II algorithm with three-dimensional objective functions and a skill transfer probability mechanism is developed to generate personalized competency enhancement paths. Considering the increasing deployment of intelligent manufacturing systems, industrial Internet platforms, and wireless information acquisition technologies, efficient capability modeling and adaptive decision-making have become essential for supporting digital industrial ecosystems and future smart education infrastructures. Experimental results demonstrate that the proposed method achieves a matching accuracy of 89.2% with superior path diversity and stability compared with shortest-path, greedy, rule-based, and industry recommendation approaches, while effectively balancing resource consumption and optimization efficiency. The proposed framework provides a scalable solution for intelligent vocational education and offers methodological references for data-driven talent cultivation and information interaction in next-generation industrial environments related to electromagnetic-enabled communication and sensing systems.
No takes yet. Share an insight, caveat, or question.
M. T. Li (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: