Design & Algorithm Optimization for Talent Evaluation Management System of Skilled Higher Vocational Institutions under the New Dual-High Plan

DOI: https://doi.org/10.62517/jhve.202616402

Author(s)

Yan Jin, Zhen Cai*

Affiliation(s)

Computer College, Wuhan City Polytechnic, Wuhan, Hubei, China *Corresponding Author

Abstract

Under the New-Dual High Plan (2025-2029),the way colleges and universities evaluate skilled talent is being quietly recast away from crediting what a person has already accumulated, and toward weighing what they can still contribute going forward. This study investigates a framework for differentiated evaluation models targeting three types of talents: technological breakthrough and process improvement-oriented, technical service and promotion-oriented, and standard development and teaching transformation-oriented. A seven-dimensional evaluation indicator system is designed, encompassing demand responsiveness, problem-solving capability, service contribution, outcome transformation, standard development, educational feedback, and collaborative construction. Through data sample analysis and algorithmic optimization reasoning, the adaptability and superiority of AHP, TOPSIS, and GWO-KELM in the two core processes of scoring and prediction are demonstrated. Finally, a management information system covering six major modules talent profiling, ranking engine, trajectory prediction, task mapping, differentiated evaluation, and performance application is designed, forming a complete business circle from data collection to decision support.

Keywords

Indicator System; Scientific and Technological Talent Evaluation; AHP; TOPSIS; GWO-KELM

References

[1]Chinese Academy of Personnel Science. Blue Book of Chinese Talents. Beijing: Social Sciences Academic Press, 2025. [2]Pan J F. Logic and Path of Scientific and Technological Talent Evaluation Reform. Bulletin of Chinese Academy of Sciences, 2024, 39(3): 425-438. [3]Saaty T L. The Analytic Hierarchy Process [M]. New York: McGraw-Hill, 1980. [4]Hwang C L, Yoon K. Multiple Attribute Decision Making. Berlin: Springer-Verlag, 1981. [5]Huang G B, et al. Extreme learning machine: Theory and applications. Neurocomputing, 2006, 70(1-3): 489-501. [6]Mirjalili S, et al. Grey wolf optimizer. Advances in Engineering Software, 2014, 69: 46-61. [7]Chen Y J. Research on Teacher Evaluation Indicaor Systems in Higher Vocational Colleges under the Double High-Initiative. China University Science & Technology, 2025(9): 45-53. [8]McMahan B, et al. Communication-efficient learning of deep networks from decentralized data. AISTATS, 2017: 1273-1282. [9]Qi Z Y. Empirical Research on Differentiated Evaluation of Scientific and Technological Talents at Skill-Oriented Higher Education Institutions. Journal of South China Normal University, 2025(4): 113-133. [10]Lundberg S M, Lee S I. A unified approach to interpreting model predictions. NeurIPS, 2017: 4765-4774.