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.

Authors

  • Alessandro Massaro Dyrecta Lab
  • Vincenzo Maritati Dyrecta Lab
  • Angelo Galiano

DOI:

https://doi.org/10.31449/inf.v42i4.2173

Downloads

Published

11/06/2018

How to Cite

Massaro, A., Maritati, V., & Galiano, A. (2018). Automated Self-learning Chatbot Initially Build as a FAQs Database Information Retrieval System: Multi-level and Intelligent Universal Virtual Front-office Implementing Neural Network. Informatica, 42(4). https://doi.org/10.31449/inf.v42i4.2173

Issue

Vol. 42 No. 4 (2018)

Section

Regular papers

License

Authors retain copyright in their work. By submitting to and publishing with Informatica, authors grant the publisher (Slovene Society Informatika) the non-exclusive right to publish, reproduce, and distribute the article and to identify itself as the original publisher.

All articles are published under the Creative Commons Attribution license CC BY 3.0. Under this license, others may share and adapt the work for any purpose, provided appropriate credit is given and changes (if any) are indicated.

Authors may deposit and share the submitted version, accepted manuscript, and published version, provided the original publication in Informatica is properly cited.