Development of Artificial Intelligence Based Chat bot for Project Assistance in Automotive Applications
DOI:
https://doi.org/10.46243/jst.2022.v7.i01.pp62-71Keywords:
Artificial Intelligence, Chatbot, Chatterbot, Project Assistance, Answering SystemAbstract
Improvements in Technology helps human to lead life easier when compared to ancient times. With new developments in software technology, apps and software tools are become part of life. Chatbots that are developing
for many applications will find applications in our daily lives also for many personal usages. Even though Chabot
concept is developing one, it is being rapidly adapted for many applications in various areas because this makes the work simpler and easier for the customer. Chatbots are artificial intelligence based tool that chat with one like a person replying from the other side. Project assistance Chatbot is an interactive tool that contains the knowledge base of a particular project or process. The Chatbot will be trained with the data of the particular project. The Chatbot will be able to identify the keywords given by the user, match it with the knowledge that has been fed to it. Finally, it will give the result to the user by logically connecting all the obtained results. Sequence to sequence model has been used to build this Chatbot, which uses encoder and decoder arrangement. The Chatbot model has been implemented with two sets of Recurrent Neural Networks (RNN) using the software Python TensorFlow. Sequence of symbols is encoded by one RNN into fixed-length vector representation and the vectors are decoded into sequence of symbols by the second RNN. The Chatbot has been trained with volume of data and it responds to the user queries.
References
K. Nimavat, and T. Champaneria, “Chatbots: An overview Types, Architecture, Tools and Future Possibilities,” Int. J. for Scientific Res. & Dev., vol. 5, no.7, pp.1019-1024, Oct. 2017
J. Cahn, “CHATBOT: Architecture, Design, & Development,” Senior Thesis, University of Pennsylvania, School of Engineering and Applied Science, Department of Computer and Information Science, 26 Apr. 2017
T. Mitchell, “Machine Learning,” New York, NY, USA: McGraw-Hill Science/ Engineering/Math, Mar. 1997, pp.2-5
T. O. Ayodele, “Types of Machine Learning Algorithms,” Yagang Zhang (Ed.), ISBN: 978-953-307-034-6, InTech, Feb. 2010. Available from: http://www.intechopen.com/books/new-advances-in-machine-learning/types-of-machine-learning-algorithms
H. Ninomiya and A. Sasaki, “A study on generalization ability of 3-layer recurrent neural networks,” In Proc. IJCNN'02 (Cat. No.02CH37290), HI, USA, 2002, vol.2, pp. 1063-1068 doi: 10.1109/IJCNN.2002.1007641
Y. Denny Prabowo, H. L. H. S. Warnars, W. Budiharto, A. I. Kistijantoro, Y. Heryadi and Lukas, “LSTM and Simple RNN Comparison in the Problem of Sequence to Sequence on Conversation Data Using Bahasa Indonesia,” In Proc. INAPR, Jakarta, Indonesia, 2018, pp. 51-56. doi: 10.1109/INAPR.2018.8627029
G. Aalipour, P. Kumar, S. Aditham, T. Nguyen and A. Sood, “Applications of Sequence to Sequence Models for Technical Support Automation,” IEEE Int. Conf. on Big Data, Seattle, WA, USA, Dec. 10-13, 2018, pp. 4861-4869. doi: 10.1109/BigData.2018.8622395
Learn Python Programming, [Online]. Available: https://www.programiz.com/python-programming
Anaconda, [Online]. Available: https://www.anaconda.com/products/individual
