Automated Self-learning Chatbot Initially Build as a FAQs Database Information Retrieval System: Multi-level and Intelligent Universal Virtual Front-office Implementing Neural Network

Abstract

In this paper we propose a novel approach of an automatic creation of a chatbot exploiting only a questions-answers archive. The described model is not bound to a particular context or language, and it allows to initially retrieve information from a FAQs database using natural language, by allowing successively the automation of customer support services for the optimization of human resources thus implementing a self-learning chatbot system. We also propose a solution based on dynamical information system capable of exploiting the potential of the proposed model in a universal virtual front-office, including the statistics and tests necessary to validate the solution, and a comparison between neural network and AIML results.