Evaluating Benefits and Managing Diversity in Human Resource Management using CNN+BiRNN+CRF

The increase in occupational stress in recent years has adversely affected worker health, safety, and productivity. Diversity management in human resource management is crucial for fostering an inclusive work environment and alleviating workplace stress. Moreover, neural networks are transforming human resource management decisions in the technology sector, particularly with promotions and recruiting. Human resources departments facilitate communication between worried management and employees, hence playing a crucial role in diversity management and stress alleviation in the workplace. Effectively assessing professional stress necessitates understanding its sources and the potential anxiety levels of personnel. The proposed methodology comprises three stages: preprocessing, feature selection, and model training. Feature selection is conducted by PCA, while preprocessing involves normalisation and discretisation. The selected properties are then employed to train the CNN-BiRNN-CRF model, which surpasses well-known alternatives like CNN and BiRNN. The study revealed an accuracy rate of 98.45%, indicating that the strategy is effective in assessing and managing occupational stress. These findings underscore the need of employing advanced machine learning techniques for diversity management in human resource management. The remarkable accuracy suggests significant potential for improving workplace wellbeing, refining HRM decision-making, and sustaining a cohesive and effective staff amid evolving workplace dynamics.