Description:FIELD OF THE INVENTION
This invention relates to the field of Human Resource Management. The challenge of enabling decision-making, prediction, and decision validation in a human resource management system is addressed by the innovation. An innovative intelligent decision support system for HR procedures is addressed in the study. Machine learning algorithms have been offered as fundamental instruments for the monitoring of many designated HR indicators in the system's analytical route, which has been built and put into practise. The description of the suggested technique and a discussion of the findings from a few chosen trials are both included in the proposed invention.

BACKGROUND OF THE INVENTION
Human resource management (HRM) as a whole is a complicated topic since it deals with unexpected elements of human behaviour, whether it be in a person, a group, or a whole organisation. It is challenging for human resource managers to anticipate a variety of complicated patterns, such as the relationships between factors affecting employee happiness, staff turnover and manpower attrition, employee engagement and employee motivation levels, and similar phenomena. The influence of human resources operations on the bottom line is thought to be something that can be assessed. Before, experts in organisational development and analysis employed a variety of data-based techniques to pinpoint areas that needed improvement in terms of productivity levels, employee happiness, work-life balance strategies, etc. However, it took a lot of time and often concentrated on only one topic rather than covering all aspects of HRM. The introduction of automated systems like the Human Resources Information System (HRIS) in the 1980s expanded the reach of HR managers and allowed them to utilise such systems to filter through data and extract important information 2. However, it was uncommon for information analysis to be done properly, and managers were instead allowed to make decisions based on their judgement and expertise. Application of eHRM meant that HR managers lacked decision-making tools and were unable to adequately analyse the factors when exposed to a scenario and come up with an appropriate solution for a crisis or project they were working on, despite having access to large amounts of data via HRIS. Decisions were often made based mostly on gut feelings. It was risky to make decisions without any supporting evidence, relying only on intuition rather than employing scientific techniques to allocate resources, set timelines for projects, pick candidates for key roles, and evaluate HR effectiveness efforts. The opportunity to introduce technology into the field of HR management was improved by the rapid growth of IT and growing globalisation. In order to conduct HR operations and accomplish goals, it was necessary to make use of technology and analytics to identify the best ways and courses of action among a variety of factors.
SUMMARY OF THE INVENTION
The issue of human resource management is the main emphasis of the suggested innovation (HRM). Making wise selections is very crucial in management today. Such wise choices must be made specifically in the administration of human resources field. It also implies that a proper HRM system is a key element in an organization's success. The accuracy of judgments made in the HR field may be affected by a variety of variables. It is clear that decisions made in the HR process may be influenced by human perceptions and preferences, but for a choice to be more suitable, the evolving social and economic landscape must also be taken into consideration. It implies that a sizable number of various elements (factors or indications) must be taken into account while making HR choices. On the other hand, decision-making in this HR sector is become more and more important, and this is true regardless of what any organisation does. As a result, there is justification for using decision support systems in this area (DSS). The DSS is often described as a tool that assists management decision-makers in making precise and timely choices by utilising data and models to address given issues [2]. The intricacy of the issues with human resource management leads to the need for very sophisticated systems. The intelligent decision support systems (IDSS) are the solution to these problems, however their implementation and clever procedures need a lot of time and work. However, intelligent decision systems for human resource management (HR IDSS) may already have a big impact on management, and they're only going to become bigger. The constantly shifting social and economic situations, shifting labour market choices, and a comparatively high employee turnover are the causes of this. Today's DSS applications must be able to learn, adapt, and perform better. These applications are often designed as embedded parts of larger systems. These intelligent modules must be able to forecast values for various HR indicators, such as those related to hiring new employees, talent management, employee behaviour, and how employees will react to changes in the labour market.

BRIEF DESCRIPTION OF THE DRAWINGS

Fig. 1. Basic arras of HR management opened for AI implementations

Fig.2. HCM: 21 Model

Fig. 3. Use case diagram of the framework for HR decision-making system

Fig. 4. Example changes in the effectiveness indicator value for the monitored HR process

BRIEF DESCRIPTION OF THE INVENTION

It is emphasised that continuous access to information about employees and the findings of data analysis, including various anticipated values, is necessary for successful management of the company. Only when the DSSs are implemented using artificial intelligence (AI) techniques is access to the data feasible. For HR IDSS, these patterns, difficulties, and development directions have been shown. A research referenced in a different report (issued by Pricewaterhouse Coopers) demonstrates that information technology using artificial intelligence capabilities will soon unquestionably enhance HR procedures inside the firm. The deployment of artificial intelligence has difficulties due to, among other things, the complexity of HR issues. The application of artificial intelligence technologies to help HR operations or instances of intelligent HR management systems may be found in literature. For the purpose of predicting employee turnover inside businesses, for instance, gives a thorough overview and evaluation of supervised machine learning algorithms. General criteria for the trustworthy analysis of HR datasets have been offered, along with evaluations of a few chosen machine learning technologies. The suggested Intelligent Human Resource Information System uses machine learning techniques to find relevant information or knowledge from historical data and experience to aid decision-making. Review of studies on data mining techniques for managing human resources is also offered. This innovation presents the use of machine learning methods for the prediction of specified HR variables. To be more specific, machine learning technologies have been put into place for assessing and forecasting HR activities, as well as for connection detection and linkages between quantitative and qualitative components that make up the HR processes (Fig.1). The underlying premise was that understanding these linkages and continuously monitoring them might reveal potential or essential actions (solutions) to implement in order to address the organization's recognised issues. The fundamental objective of the system under discussion was to advise users on actions and solutions that would optimise HR processes and exclude or minimise the consequences of observable and unwanted behaviours in a particular HRM area. The study describes a machine learning-based implementation of the HR IDSS. The paper's contribution is a suggestion for tracking a variety of HR indicators and forecasting, using historical data, the actions that need be taken to mitigate the impacts of observed changes in the HR domain. The system under consideration was created as part of a development effort. The project is very briefly discussed in this article, which also outlines the fundamental presumptions behind the machine learning methods used to monitor and assess various HR metrics. Finally, the findings from the chosen studies, which evaluated and validated the advantages of using machine learning techniques to HRM, are given. The act of studying data sets to make inferences about the information they contain is known as data analytics (DA), and it is increasingly done with the use of specialised hardware and software. Scientists and researchers often utilise data analytics to confirm or refute scientific models, ideas, and hypotheses in the commercial sector to help firms make better business choices. 8 The use of sequential procedures (algorithms) or transformations to provide insights from processed datasets gave rise to the development of DA. DA primarily refers to a range of applications, from fundamental business intelligence and online analytical processing to other types of advanced analytics (Fig.2.). The introduction of analytics into the HR sector and its subsequent widespread application worldwide came much later.
Since there has been a rising need for and use of HR analytics in management decision-making processes over the past ten years, the field of HR analytics has developed significantly and consistently. These are also referred to as "Workforce Analytics" or "People Analytics". Its relevance has grown as a result of the spread of HR analytics across more businesses and the extending of its usage to a range of users, including hierarchy of executives, business managers, analysts, and other knowledge workers inside various organisations. It was often described as a decision science branch for better using human capital11. Analytics has made it possible to both internally improve the organisation and, at the same time, preserve enough flexibility to meet the unexpected and unpredictable in a world of gradually rising data quantities and increasing pace, when operating on instinct is no longer an option. As a result, HR analytics became a common and essential tool for HR management.
The structure of the HR intelligent decision-making system is presented in this section. Fig. 3 displays the use case diagram for the framework for HR decision-making system under discussion. Modern methodologies and algorithms should be the foundation of decision support tools since they should make it possible to gain and retain a continual strategic advantage. The obvious conclusion was that the analytical system's dependence on artificial intelligence capabilities, particularly machine learning techniques, was the best method for assessing and certifying the efficacy of HR operations.
By examining changes in quantitative and qualitative markers, processes' quality is evaluated. Within the acceptable limitations set by the system's user, the fluctuation of indicator values is taken for granted as a natural event that doesn't involve administrative choices. Figure 4 illustrates how the chosen indicator's value evolves over time. The lines "minimum value" and "maximum value" provide the range of values that are acceptable for the monitored indicator. The average value, or so-called level of stability, is shown on the "reference value" line. The circles indicate readings of the monitored indicator that are higher than permitted levels. Such recognised circumstances cause the analytics and process assessment module to be activated, ultimately proposing actions for the user to take (manager).
According to one of the pioneers of the analytics movement: "Analytics will undoubtedly significantly transform HR. Business intelligence is a must for sustained performance, and analytics is its heart. Although analytics have been used for many years in manufacturing, marketing, and finance, HR has been able to dodge it. That evasive behaviour will prevent HR from ever becoming a strategic decision-making partner. The good news is that there are currently many businesses operating successfully in this area. Hard proof has replaced the era of anecdotal reporting in journalism." 13 As a result, the term "HR analytics" refers to the application of analytical techniques to the human resources department of a corporation in order to enhance employee performance and maximise return on investment. HR analytics collects information on employee productivity as well as insight into each process by acquiring, storing, and processing data before using that knowledge to make informed judgments about how to improve those processes. More than half of the 200+ organisations that responded to a survey said that they intended to considerably increase their HR Analytics capabilities in the next few years. An expanding amount of evidence supports the following: A new study of more than 3,000 corporate leaders, managers, and analysts from firms throughout the globe found that top-performing organisations use analytics five times more often than poorer performing organisations do. Profits rose by at least 11% as a result of HR analytics, while revenue per employee increased by 6%.
AI and Future of Human Resource Management

Artificial intelligence has made it possible to manage people with less human interaction and a more objective viewpoint. Our lives have already been changed by AI. Amazon's Alexa is capable of a wide range of tasks, like turning on and off lights, unlocking automobiles, reading messages, and making phone calls. Over 3000 talents are included in the programme, and more are added daily. Advanced HR analytics and AI now make use of cutting-edge technology and creative techniques.
Combining descriptive and prescriptive analytics is known as causal analytics. In recent studies on intellectual capital, causal models have been utilised to better explain the diverse results of antecedent arrangements of intangible asset components. Cognitive computing is the digital emulation of how people think. The computer may imitate how the human brain functions by using self-learning algorithms that employ data mining, pattern recognition, and natural language processing. This makes it possible to better understand how people behave.
Machine learning is a method for systems and computers to acquire knowledge over time in order to accelerate future computations and decision-making. By examining patterns created by earlier computations and judgments, this is done.
A chatbot, which functions similarly to a robot, is a programme that can communicate with people online. A reasonably popular example of artificial intelligence being used to replace human interaction is chatbots. Chatbots provide up new possibilities for efficiency and reactivity in the HR sector. Talla, an HR chatbot created by a Boston startup, can assist in finding the appropriate people in addition to performing a wide range of HR tasks. Chatbots are being used by organisations like the US army to engage with prospective recruits and respond to common questions. IBM's Watson - At the IBM Watson programme, artificial intelligence and deep learning make it possible to recognise patterns and forecast outcomes. A collection of cutting-edge AI-based HR solutions called Watson introduces cognitive technology to HR. It handles crucial HR tasks related to hiring, talent development, workforce analytics, career coaching, and employee HR support. Artificial Intelligence (Chatbot), Augmented Reality (AR), and Virtual Reality (VR) are being combined for a realistic learning experience in virtual reality simulations. Integration of these technologies was covered during the 2018 SHRM Conference in Hyderabad, which took place in April27. Although chatbots are a common and affordable alternative for deployment, augmented reality and virtual reality are highly helpful for high-risk, safety-driven learning and growth.
Network examination. The examination of how the workforce uses the network, as well as the platforms and tools they use for communication, identifies low communication loads, inflection points, and practical ways to employ individual loads. By balancing workload and agile architecture, several networks may be analysed in real time and used for efficiency. The study of workload and resource allocations is helpful for HR managers. The network analysis handles privacy concerns as well, which are crucial in the current environment.
lecturers' assistants The teaching assistants replace official physical teachers for learning and development roles29 thanks to Knowledge Based Artificial Intelligence systems like Jill Watson created by Prof. Ashok Goel of Georgia Institute of Technology. Jill Watson, who was named after the IBM Watson programme that was mentioned, has the capacity to respond to 10,000 inquiries and has served as a master's programme assistant at Georgia University with distinction.
, Claims:CLAIMS
1. The invention describes a novel intelligent decision-making system dedicated to supporting HR process in organizations. This system has the ability to collect values of different HR indicators as well as their fluctuation monitoring and notice when these indicators grow or decrease to critical levels.
2. The main core of the discussed system is to a prediction of the character and kind of actions (decisions) which must be taken to eliminate negative effect of these fluctuations.
3. The decision prediction is carried-out by the implementation of the machine learning tools within the system. The contribution of the invetion is to evaluate the impact of the selection of machine learning algorithm on the performance of the system and accuracy of the predicted decision.
4. The obtained results also show that the designed system can be considered as an alternative approach for HR decision making support. The computational experiment confirms the basic assumptions on a structure of the data and learning on the data using machine learning tools. So, it can be concluded that the initial obtained results are beneficial.
5. HR Analytics have been proliferated in most large and medium enterprises, including smaller technology based ones. However, it lacks the full potential as offered by AI. India has large share in high technology and is in forefront of development of AI applications in the world.
6. AI is extension of advanced analytics and finds greatest potential in five functional areas of HR: Analytics and metrics, time and attendance, talent acquisition, training and development and compensation management. The ability to analyse, predict and yield personalized inferences is most desirable from application of AI.