Search

Constructing a Digital Talent Supply Index in AI-Enabled Vocational Education Scenarios "A Statistical Evaluation Approach Based on Multi-Source Teaching Big Data Case"

Author(s)

Xinran Niu

Affiliation(s)

Wuhan City Polytechnic, Wuhan, Hubei, China

Abstract

As the demand for digitally skilled workers continues to grow, vocational education has become increasingly important in preparing learners for a changing labour market. Existing approaches to talent assessment, however, are often limited by fragmented data, subjective judgement, and delayed feedback. This study therefore proposes a practical indicator system derived from authentic records generated by AI-enabled classrooms and multiple institutional databases. The framework covers four dimensions: teaching resources, the digital competencies of teachers and students, the use and effects of AI in classroom practice, and graduates’ performance in the workplace. Because most of the required information is already collected by vocational institutions, the framework can be incorporated into routine teaching and administrative processes. It can also be refreshed as new records become available, allowing digital talent supply to be evaluated on an ongoing basis. We used entropy‑weight calculation. Basic weighted‑sum math gave our final index scores. Put these datasets together. You see the true state of local digital‑talent training.

Keywords

AI Empowerment; Higher Vocational Education; Digital Talent; Supply Index; Multi-Source Big Data; Statistical Evaluation

References

[1] Ministry of Education. Implementation Plan of the Digital Strategic Action for Vocational Education. 2022. [2] Wu Qiuchen, Zhou Yingwen. Action research on developing a digital talent cultivation evaluation system in higher vocational colleges. Vocational Education Forum, 2025, 41(7): 17‑24. [3] Zhou Chiliang. Value representation, ethical challenges, and countermeasures of digital‑intelligent technology‑empowered vocational education teaching evaluation. China Vocational and Technical Education, 2024, (35): 77‑84. [4] Han Fei, Guo Guangshuai. The value implication, practical dilemmas, and breakout paths of artificial intelligence‑empowered vocational education teaching reform. Journal of Chengdu. [5] Gao Weiting. Construction of a digital competency evaluation index system for vocational college teachers in the age of artificial intelligence. Vocational and Technical Education, 2023, 44(2): 74‑79. [6] Fan Jianli, Zhang Xinping. Research on the digital‑intelligent competency model of teachers in the era of big data + intelligence. Journal of Distance Education, 2022, 40(4): 65‑74. DOI:10.15881/j.cnki.cn33‑1304/g4.2022.04.001. [7] Sun Ying. Research on the reform path of AI‑empowered vocational education teaching evaluation// China Smart Engineering Research Association. Proceedings of the 2026 Young and Middle‑aged Teacher Development Experience Exchange Conference – Challenges and Opportunities of Education under the Background of Artificial Intelligence. [Publisher unknown], 2026: 42‑44. DOI:10.26914/c.cnkihy.2026.038722. [8] Ji Yilong, Lu Xing, Zhang Jiahua, et al. Intelligent technology‑empowered teacher teaching evaluation: theoretical framework and practical directions. Contemporary Educational Science, 2024, (2): 71‑80. [9] Li Feng, Gu Xiaoqing, Cheng Liang, et al. Policy logic, internal driving forces, and promotion paths of digital transformation in education. Open Education Research, 2022, 28(4): 93‑101. DOI:10.13966/j.cnki.kfjyyj.2022.04.011. [10]Wang Yi. Research on the digital talent cultivation system in higher vocational education programme clusters. Chengdu: Southwestern University of Finance and Economics Press, 2025