Abstract:

The use of rule-based expert systems improves the quality of the decision to be taken, since it projects a clear and precise comparison of the observed values in relation to the expected ones. In the context of companies, the quality of services is, in a way, directly linked to the performance of employees, since, individually, the expert system can be used as a tool to classify productivity and identify skills and development opportunities. Training and investing in corporate education improve both the soft skills and the hard skills of employees; therefore, it becomes necessary to elaborate on a more complete and immersive mechanism for training and human development. Technology has played a leading role in helping managers, as decision-making involves building important choices that will affect the future of the company and its employees. This requires that leadership consider the company's goals, mission, and people while also considering the products or services the company offers. In the past, those who had experience in certain areas of knowledge were responsible for making decisions in real time, a skill that made them experts in each task due to tacit knowledge. However, it is possible to implement a system that uses human knowledge captured from technological devices such as computers, smartphones, and tablets to develop a system that converts it into explicit knowledge. This type of system imitates the thought process of an human expert to solve a range of problems in order to support decision-making in certain domains. In this way, this work presents an intelligent decision support system, in which the knowledge in several technical subjects can be evaluated. Based on this context, this prototype was modeled with the aim of helping leaders in their decision-making during the development process of employees. The system, developed in Python with the Experta inference engine framework, is able to understand people's level of knowledge in technical matters and, based on the results, promote specific training, determined from each level of knowledge assessed. Thus, the aim is to improve the productivity of leaders in the evaluation and identification of possible deficits in the technical skills of their subordinates, to encourage the development and professional training of employees, in addition to supporting the interview process by identifying candidates who present the skills relevant to the job.

Keywords:

Expert systems, training, forward chaining, decision support, personal assessment.