The neural network conversation model enables the commonly asked student query agents

Abstract

One of the challenges in academic counselling is to provide an automated service system for students. There several query questions asking the faculty staffs about related-academic services each semester. Offered the communication interface more convenience, the novel approach based on neural network model is introduced to investigate the automated conversational agent. The pre-defined dialogue sentences were collected manually from the student query questions and used as the training dataset. The questions have been varied and grouped by topic-categorizing queried from the registration help desk of the department. Artificial intelligence and machine learning have contributed each other to build the conversational agent so-call KUSE-ChatBOT plugged and used in the modern messenger application, LINE. The system is also included the dialogue back-end management system to use in further deep learning model updating. Tensorflow, the machine learning development platform originated by Google, was performed and obtained the learning model using Python development kits. The LINE Messaging APIs is then contributed as the user interface where users could have FAQs' conversation via the LINE application. The KUSE-ChatBOT is outperformed and efficient by providing automated consultation to the students precisely with the accuracy rate over 75 percent. The system could assist the staffs to be able to lessen the workload of answering the same question repeatedly and give response to the student timely.