Predicting HR Management Strategies and Employee Satisfaction in Enterprises Based on Deep Generative Models

• Published in: Applied mathematics and nonlinear sciences Vol. 10; no. 1
• Main Author: Kang, Ping
• Format: Journal Article
• Language: English
• Published: Beirut Sciendo 01.01.2025; De Gruyter Poland
• Subjects: 68T05; Deep generative model; Employees; Enterprise management optimisation; Facial recognition; Human resource management; Job satisfaction
• ISSN: 2444-8656; 2444-8656
• DOI: 10.2478/amns-2025-0043

With the arrival of the digital era, the digital environment has brought new operation modes and work styles for enterprises, and at the same time, it also requires enterprises to make innovations and reforms in human resource management. The use of a deep generative model is used to generate facial expression recognition technology after optimizing the human resource management strategy in this paper. This technology extracts the facial expression features of employees and analyzes their emotional predictions in various simulated scenarios, all within the context of the optimized enterprise human resource management strategy. This, in turn, reflects the employees’ satisfaction with their work. Firstly, in order to verify the accuracy of the recognition technology proposed in this paper, recognition experiments are carried out on the Cohn-Kanade expression library, and from the analysis results, it is known that the recognition technology of this paper achieves a recognition rate of 98.25% in the Cohn-Kanade expression library, which is a high recognition rate. Finally, the selected 618 subjects were divided into 4 groups for the context simulation experiment to analyze mood prediction. The findings show that subjects’ positive mood is higher in different contexts, which suggests that employees are more content with their jobs in an optimized enterprise management environment.