Sistemas de informação e aprendizagem de máquina na gestão da produtividade de equipes de campo de telecomunicações

Abstract

The appliance of information systems in managing the productivity of field teams is a natural way to solve the various challenges for the evolution of management practices in service companies particularly in sectors that use field teams such as telecommunications, energy, logistics, sanitation, or maintenance. Field teams are responsible for much of the operational work and have a significant impact on customer satisfaction, directly affecting the company's financial performance. A system to replace the coercive control of dispatch supervision teams needs to have the intelligence to cross data from different monitoring mechanisms, learning from the behavior of the teams and encouraging people to collaborate naturally with information. The question to be answered in the research is how to monitor activities productivity of people in autonomous and remote work. The main objective of this work is to develop a model, using machine learning in image recognition, to the implementation of an information system for monitoring the service provision process of telecommunications companies. To this end, it presents a most important processes of telecommunications field service mapping and a detailed description of collecting useful data opportunities. The research methodology adopted was CRISP-DM in its six phases that include: understanding the problem, understanding the data, data preparation, modeling, assessment, and application. As a result, the research contributes to an automatic productivity monitoring approach, with minimal operator requirements and team adherence in an organic and systemic way. In addition, the research presents the implementation models for the proposed system.