Abstract

In recent years, gradual improvements in communication and connectivity technologies have enabled new technical possibilities for the adoption of chatbots across diverse sectors such as customer services, trade, and marketing. The chatbot is a platform that uses natural language processing, a subset of artificial intelligence, to find the right answer to all users’ questions and solve their problems. Advanced chatbot architecture that is extensible, scalable, and supports different services for natural language understanding (NLU) and communication channels for interactions of users has been proposed. The paper describes overall chatbot architecture and provides corresponding metamodels as well as rules for mapping between the proposed and two commonly used NLU metamodels. The proposed architecture could be easily extended with new NLU services and communication channels. Finally, two implementations of the proposed chatbot architecture are briefly demonstrated in the case study of “ADA” and “COVID-19 Info Serbia”.

Highlights

  • Academic Editors: Cataldo Musto and George A

  • Driven by the promise of intelligent digital assistants that will always be at disposal for fast and consistent resolution of client requests, chatbots are becoming increasingly useful

  • The advantages offered by proposed chatbot architecture are the following:

Read more

Summary

Introduction

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. The use of chatbots evolved rapidly in numerous fields in recent years, including customer services, e-commerce, marketing, supporting systems, education, healthcare, cultural heritage, and entertainment. The advanced extensible microservice chatbot architecture has been proposed, allowing easy switching from one NLU provider to another (e.g., because of better support for the Serbian language or due to cost issues). The novelties of our approach are: The proposed chatbot architecture is extensible, supporting new natural language understanding services and communication channels for user interactions. Logical architecture has been presented with the detailed specification of the components of the proposed architecture

Related Work and Motivation
NLU Support
Proposed Chatbot Architecture
Architecture
The Component Structure of the Bot Engine
NLU Metamodels and Corresponding Mapping Rules
Example of Mapping Model
Two Case Studies and Their Implementations
Findings
Conclusions
Full Text
Published version (Free)

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