AI Customer Service System with Pre-trained Language and Response Ranking Models for University Admissions

Abstract

The application of chatbots in the field of customer service systems is already an indispensable technology. In the admissions of colleges and universities, the customer service system is one of the most important models. The objective of this study is to evaluate the efficacy of an intelligent enrollment customer service robot system established using the Generative Pre-Training-2 (GPT-2) model. In this study, we combine the customer service field of chat robots with the enrollment field to construct a customer service system with enrollment as the field. This study uses the GPT-2 natural language processing model proposed by OpenAI to construct a customer service system in the university admissions field. BLEU is utilized to generate an evaluation model to evaluate the similarity between the text generated by the university admissions customer service system and the reference text to determine if the generated text by this model is good or bad. The research contributions of this paper are that we proposed an artificial intelligence (AI) customer service system with a pre-trained language model and a response-ranking model for university admissions and conducted a user evaluation of the proposed AI system.