AI BASED CHATBOT TO ANSWER FAQs

Abstract

People interact with systems more and more through voice assistants and chatbots. The days of solely engaging with a service through a keyboard are over. These new modes of user interaction are aided in part by This research will investigate how advancements in Artificial Intelligence and Machine Learning technology are being used to improve many services. In particular it will look at the development of chatbots as a channel for information distribution. This project aimed to implement a web-based chatbot to assist with online banking, using tools that expose artificial intelligence methods such as natural language understanding. Allowing users to interact with the chatbot using natural language input and to train the chatbot using appropriate methods so it will be able to generate a response. The chatbot will allow users to view all their personal banking information all from within the chatbot. In an industry with low user satisfaction rates and limited technology to increase accessibility. It is clear the chatbot overcomes the challenges that many firms face to increase the use of their services and gain a competitive edge over leading competitors. With many people adopting Smart Assistant Devices such as Google Home or Amazon’s Alexa. The chatbot was tested across a range of devices such as Google Home and Assistant on android devices to outline the key differences between the two modes of interaction, spoken and text dialog. These test were carried out to identify the value in integrating such technology surrounding the recent interest in EEE521 Final Year Project 2017/18 B00659303 2 chatbots and conversational interfaces. Proving chatbots can be applied to a specific domain to enhance accessibility, reaffirming that they are more than just a passing fad and have a viable use. Keywords : Chatbot, AI, NLP, ML, NLTK, Data set.