Modelo de inteligencia artificial en atención al ciudadano para entidades de economía mixta

Abstract

In a developing world that demands results, excellence in customer service is a determining factor for business success. However, the process of handling PQRS (requests, complaints, claims and suggestions) can be challenging for both organizations and dissatisfied customers. In this context, data-driven artificial intelligence emerges as a powerful tool capable of completely transforming this crucial area. Using natural language processing algorithms, backed by data analysis, quick and personalized responses can be provided, generating a significant impact on the customer experience. In the context of the user service process, machine learning, the basis of artificial intelligence, plays a fundamental role in allowing us to automate and improve the quality of responses. Using algorithms, machine learning systems can process large volumes of information, identify patterns and trends, and learn from feedback to continually improve their performance. These systems are capable of analyzing and understanding the content of requests, whether text, voice or other formats, and generating accurate and relevant responses. Additionally, they can be adapted and customized to meet individual user needs, delivering an exceptional customer service experience. Through a need, it will be explored how a mixed economy entity will be able to develop its citizen service process with a basis of machine learning based on data in the management of complaints and claims, achieving tangible improvements in efficient problem resolution and reduction of response times, generating efficiency in the process. This thesis offers a practical and theoretical way for mixed economy entities interested in optimizing their citizen service processes, especially in the handling of complaints and claims. By reading it, you will understand how data-driven artificial intelligence can drive operational efficiency and overall business success. It is of great importance to highlight how industrial engineering, with its focus on the analysis and design of complex systems, has established itself as a fundamental pillar for identifying and solving problems in industrial processes. By combining these data analysis and continuous simulation tools with advances in artificial intelligence in natural language processing, a world of possibilities opens up to further optimize these processes. Additionally, artificial intelligence and simulation can facilitate decision-making by providing recommendations based on data, considering multiple variables and scenarios. This allows industrial engineers to optimize processes more quickly and efficiently, minimizing costs, maximizing productivity and reducing response times. The combination of industrial engineering tools with artificial intelligence opens a new horizon of opportunities for process optimization. This thesis explores one of the many lines of these techniques that have generated significant improvements in various industries. It is hoped that the research will be of interest to you and the opportunity to present the results of the work is appreciated.