The AI enabled Chatbot Framework for Intelligent Citizen-Government Interaction for Delivery of Services

Abstract

Semantic modeling of domain knowledge for natural language question-answering based on conversational assistants nowadays has gained popularity with the development of chatbots and voice assistants. Chatbots based on artificial intelligence and interactive technologies are helping organizations and governments to interact and accomplish tasks such as question answering, instant messaging, and promoting any ideas or services. As various government services are provided to fellow citizens through manual interaction or through electronic means. This causes a huge burden of works on various government departments and many queries of the citizens remain unresolved. Nowadays, intelligent chatbots can mimic humans and help users who are not acquainted with technologies to avail answers to their domain-specific queries. However, providing answers with domain-specific capabilities still remain a challenge. In this paper, we present the design of a conversational assistant for answering user queries and administrative support. It is developed using Google Dialogflow and trained on a domain-specific semantic model with intelligent abilities to answer user queries and process service requests. On analysis, we observed that the developed chatbot performs with approx. 95% accuracy in responding to the queries. The chatbot has been deployed in NIC for assistance to user queries regarding e-District services.