System for Customer Service Automatic Answering Of Domain-Specific Questions From Documentation Guide

Abstract

One of the ways to acquire knowledge is Question Answering (QA). For customers to acquire information in a more efficient way than the traditional way of agents answering to generic queries of the customer, this research intends to design an automatic answering system for customer queries by utilizing the documentation dataset. Generally, companies establish manual service systems for answering customer questions.

This research intends to contribute to reducing the cost of customer support for generic queries such as a set of frequently repeated questions from most end users. Researchers realize that the professional QA system can play the role of intelligent customer service, saving lots of costs, having the widespread commercial value and the prospects for development. This report proposes a customer service automatic answering system with a high-quality knowledge base of documentation using latest models in natural language processing and information retrieval.