AI for Online Customer Service: Intent Recognition and Slot Filling Based on Deep Learning Technology

Abstract

Cloud/edge computing and deep learning greatly improve the performance of semantic understanding systems, where cloud/edge computing provides flexible, pervasive computation and storage capabilities to support variant applications, and deep learning models can comprehend text inputs by consuming computing and storage resources. We propose implementing an intelligent online customer service system powered by both technologies. This method jointly models two subtasks, intent recognition and slot filling, in an end-to-end neural network, enhancing feature representation using attention schemes and context information. We deploy this method in an intelligent dialogue system for electrical customer service, with experiments showing promising results on both public and self-collected datasets.

Yirui Wu

Young Professor, CCF Senior Member

My research interests include Computer Vision, Artifical Intelligence, Multimedia Computing and Intelligent Water Conservancy.