Title: The knowledge city and regional application of labour insurance supply management from big data algorithms

Authors: Yanhua Wang; Jie Duan; Wei Gu; Jing Duan; Haitao Liu

Addresses: State Grid Information and Telecommunication Co, of SKPC, Taiyuan, Shanxi, 030000, China ' State Grid Information and Telecommunication Co, of SKPC, Taiyuan, Shanxi, 030000, China ' State Grid Information and Telecommunication Co, of SKPC, Taiyuan, Shanxi, 030000, China ' State Grid Information and Telecommunication Co, of SKPC, Taiyuan, Shanxi, 030000, China ' State Grid Information and Telecommunication Co, of SKPC, Taiyuan, Shanxi, 030000, China

Abstract: This paper investigated the effectiveness of labour insurance supply management in knowledge cities and regional applications through the use of big data (BD) algorithms. It compared the Big Data Algorithm-Based Management (BDAM) model with the traditional rule-based management (RBM) model across key metrics, including efficiency, safety, innovation, sustainability, costs, and resource utilisation. Results indicated that the BDAM model significantly outperformed the RBM model, with higher resource allocation efficiency (16% to 39% vs. 17.54% to 67.71%), superior safety levels (53.49% to 62.10% vs. 29.32% to 36.57%), and better innovation and sustainability scores. Although the BDAM model incurred higher initial costs, it demonstrated cost savings over time, with costs decreasing from 18.95 to 16.25, and maintained higher resource utilisation efficiency (0.737 to 0.810 vs. 0.573 to 0.635). The study emphasised the BDAM model's flexibility, scalability, and potential for integration with other smart city components.

Keywords: big data algorithms; labour insurance supply management; knowledge city; regional applications; resource utilisation efficiency.

DOI: 10.1504/IJTPM.2026.152560

International Journal of Technology, Policy and Management, 2026 Vol.26 No.1, pp.1 - 19

Received: 30 Sep 2024
Accepted: 17 Mar 2025
Published online: 27 Mar 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article