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.

Highlights

  • Robot and artificial intelligence appeared a lot of time ago in the design of the “Leonardo's mechanical knight” [1] and earlier in the 12th century by Al-Jazari [2]

  • The method proposed in this paper is based on dynamical information system capable toimplement a universal multi-level virtual front-office made by from an archive of questions and answers (FAQs) and chatbot self-learning systems.We describe statistics and tests necessary to validate the solution, and report acomparison between neural network and AIML results

  • The execution speed is greater, especially in conjunction with large archives of texts to be managed

Read more

Summary

Introduction

Robot and artificial intelligence appeared a lot of time ago in the design of the “Leonardo's mechanical knight” [1] and earlier in the 12th century by Al-Jazari [2]. As robots enables mechanical automatisms, chatbot implementing AI allows the information automatism. A chatbot is a computer program designed to simulate conversation with human users, especially over Internet; it acts like a human computer interface created to facilitate communication between human and computer, understanding natural language questions and answering with actual answers. After ELIZA have been developed a lot of chatbots, for example to simulate the interaction with different personalities [6], matching with web-based search engines (AskJevees) [7], and with open-source initiatives like ALICE [8] [9] implementing artificial intelligent applications called AIML (Artificial Intelligence Markup Language) [8]. Some researchers implemented long short-term memory (LSTM) neural networks [22], which automatically generate responses for users requests on social media. -gradually overcoming the barrier due to the training of model including colloquial usage forms

Case study
System design
Data model
Self-learning algorithm
Automated AIML patterns production
AIML vs neural network architecture
AIML optimizer
Automated neural network
One-hot encoding
Neural network based chatbot
Tools and development
Results
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.