Design and Empirical Analysis of a Artificial Intelligence-based Human Resource Management Processing Systems for Detecting Personal Stress Geetha Manoharan School of Business SR University Warangal, Telangana, India. geethamanoharan1988@gmail.com Akshay Kumar Assistant Professor Management (MBA) Rajkumar Goel Institute of Technology Ghaziabad, Uttar Pradesh, India. chaudharyakshay234@gmail.com Vinay Kumar Sharma Assistant Professor Department of Computer Science & Engineering School of Computing Science & Engineering Galgotias University Gautam Budha Nagar, Uttar Pradesh. vny_sarma@yahoo.co.in Dr. Bijaya Bijeta Nayak Assistant Professor Mechanical Engineering KIIT Deemed to be University Bhubaneshwar, Odisha, India. bijaya.nayakfme@kiit.ac.in Dr. Melanie Lourens Deputy Dean Faculty of Management Sciences Durban University of Technology South Africa. melaniel@dut.ac.za Dr. Punamkumar Hinge Associate Professor Business Management Indus Business School Pune, Maharashtra, India. punamkumar.hinge@gmail.com Abstract - Artificial intelligence (AI), deep learning (DL), and automated processes have been quickly advancing, considerably boosting the significance of information technology (IT) within corporate procedures. Rising AI-based responses in human resource management (HRM) have been rapidly being used to handle time-consuming and difficult activities within HRM capabilities.Workers in most businesses are currently experiencing high work stress, which has an adverse impact on efficiency, security, and wellness. To cope with personal stress, it is critical for the HR sector to handle stress efficiently, connecting the barrier between administration and stressed personal. This research creates 2 stress prediction frameworks and also 2 neural network designs. This research use data from personal to train these 2 stress prediction systems. Investigations on 2 real-world databases, indicate that the suggested DL-driven method can accurately predict personal' stress condition with 71.2 percent accuracy in the classification method model and 11.1 prediction decline in the regression framework. The HRM of businesses can be enhanced by precisely forecasting personal' stress levels using this approach. Keywords:Artificial intelligence, Deep learning, Human resource management, and Personal stress. I. INTRODUCTION Artificial intelligence (AI) has been introduced by the so-called "Industry 4.0" [1]. As information and communication technologies (ICT) continue to advance, events like AI can have a significant impact on many facets of modern life, making them among the most important factors in all potential changes. Numerous examples of how managers and employees behave in a complicated environment marked by quick digital contacts, quick cycle periods, technical intensity, as well as the gig economy are provided by a recent study [2]. The environment in which employees and managers function is changing due to an ideal storm of technological progress. The rhetoric regarding the advantages and drawbacks (dark side) of using contemporary technologies at work is pervasive in the popular press [3]. The next phase of human resources (HR) is both AI and human, according to a recent Forbes article, indicating the critical role that contemporary technology play in human resource management (HRM) [4]. Although the industrial revolution marks the beginning of HRM's technological development, this was only a little alteration of either mental or physical services [5]. Nevertheless, modern advancements are progressively offering substitutes for HR in tasks that historically required human connection and communication, altering organizational frameworks as well as the type of employment. AI and human assistance machines, for example, are gaining additional commercial emphasis [6]. Conventional HR practices have been transformed through these smart "beings," which not just present major challenges to HRM, such as career-specific breakdown, but also generate capabilities and potential [7]. Simultaneously, ML techniques, smart devices, and the Internet of Things (IoT) can considerably assist cross-border organizations by promoting considerably better engagement and collaboration [8]. Additionally, the advancement of digital human resource information systems (HRIS) and other technological advances offers various opportunities to