Developing a chatbot using NLP- neural network techniques and integrating speech recognition for supporting advising education enrolment

Abstract

The question-answer system is now widely used and helps individuals by automatically responding to frequently asked questions in a variety of industries. These systems, however, are dependent on the user's context, training data, and the learning strategies used. As a result, creating such a solid dataset and comprehensive contexts is required, however it is a difficult task. Through numerous layers of inquiries, Deep Neural Network may assist in inferring semantic information and offer useful responses to user enquiries. This thesis suggests a novel Deep Neural Network-based chatbot model to automatically produce appropriate contextual answers. The suggested chatbot includes a case study on admissions counseling at International University-Vietnam National University in Ho Chi Minh City. To see how the system responds to various inquiries, three experiments were run. The first test looks at the loss experienced when the DNN model is being trained, the second test is based on a survey and evaluation of nearby users, and the third test is based on a practical test consisting of 40 questions covering a variety of topics. varying degrees of difficulty and pass judgment. The main function of the chatbot is to answer questions related to international university admissions accurately and clearly according to the context, moreover with the integration of voice asking will make it easier for users. According to test results, a chatbot powered by Deep Neural Network can provide in-depth responses. The outcomes are examined to demonstrate the viability and potential of the suggested chatbot.