The Application of Bayesian Network Deep Learning to The Assessment of Human Resource Efficiency Using Massive Data
Main Article Content
Abstract
The importance of human resource management in helping businesses plan for the future and increase their competitiveness cannot be overstated. Due to its inherent limitations and lack of objectivity, the traditional human resource performance appraisal model has historically struggled to keep up with the highly integrated development needs of today's enterprises as they've emerged in response to the advent of new technologies like the knowledge economy and big data. Therefore, the purpose of this research is to serve as a theoretical guide for contemporary business human resource management by advancing the study of a human resource performance assessment model based on Bayesian networks using big data analysis and cutting-edge technology methods. To begin, it provided a high-level overview of performance appraisal and its central role in enterprise management; then, it delved into the specifics of human resources performance appraisal indices and the connections between them; and finally, it detailed the fundamentals of putting together a performance appraisal system. Second, it suggested a performance assessment model based on Bayesian networks to meet the requirements of corporate human resources management, summarizing the relevant theory of Bayesian networks and their benefits in handling complicated random issues. Finally, a performance assessment system was constructed using the balanced scorecard approach, and the performance appraisal model suggested in this research was experimentally evaluated and compared to the conventional method. This paper's findings demonstrated that the suggested performance evaluation model offered substantial benefits and could be more effectively applied to the performance assessment management of business human resources. This paper's findings have applications beyond only business human resource allocation and management; they may also be used as a benchmark in the evaluation of performance in other areas.