Abstract

Conversational systems are rapidly changing and modifying the ways in which humans interact with machines. A basic classification divides these systems into two fundamental groups: classical systems based on NLU techniques and systems based on LLM models. In this context, the number of application scenarios for these systems and their impact on business efficiency is increasing. In this sense, opportunities for applications in reservation management, information retrieval and the execution of actions in information systems are identified. In this sense, it was identified that the construction of the training bases for these systems is costly in time and effort. In the methods section of this work, the IADESCom software ecosystem is presented. This ecosystem is made up of a set of COTS components that allow the application of conversational systems in different scenarios. In the results section, the different components are validated and the applicability of the ecosystem is demonstrated. Finally, the conclusions and future work are presented.