Gurucharan Singh Saluja, N. Maheswari*, T. S Pradeep Kumar, M. Sivagami School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India
Download Citation:
|
Download PDF
Automation is the way through which the machine can interact with data as well as a user for proper work or communication. A chatbot is a system which accepts user inputs as queries and respond with suggestions based on the previous inputs and trained models. In this paper, a travel chatbot is being modelled using Deep Neural Network (DNN) where it improves the human and machine interaction seamlessly as the user of the bot does not aware whether he/she is interacting with a machine or a human being. This chatbot suggest safest possible routes, secure and cheaper stay, best places for shopping, etc. to the users. This chatbot respond in a minimal time compared to other systems of similar nature. It also uses Long Short Term Memory (LSTM) to understand the sentence and form the sentence according to the previous reply. It also integrates various open APIs to get the recommended ratings from the internet. As per our analytical results, our chatbot outperforms by at least 20% in handling the user queries and suggest possible recommendations to the end users.ABSTRACT
Keywords:
Long short term memory, Natural language processing, Artificial intelligence, Deep neural network, Deep NLP.
Share this article with your colleagues
REFERENCES
ARTICLE INFORMATION
Received:
2020-12-16
Accepted:
2021-01-06
Available Online:
2021-06-01
Saluja, G.S., Maheswari, N., Kumar, T.S.P., Sivagami, M. 2021. AI based intelligent travel chatbot for content oriented user queries, International Journal of Applied Science and Engineering, 18, 2020333. https://doi.org/10.6703/IJASE.202106_18(2).007
Cite this article:
Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.