Advising Agent for Service-Providing Live-Chat Operators

TL;DR

This paper presents a domain-independent advising agent for live-chat call center operators, designed to improve service quality by providing real-time assistance, with demonstrated effectiveness in a specific domain.

Contribution

It introduces a novel, domain-independent algorithm and method for training and deploying advising agents in live-chat customer service environments.

Findings

The advising agent effectively supports operators in a real-world domain.

The system can be integrated with minimal effort into new domains.

Experimental results show improved operator performance and customer satisfaction.

Abstract

Call centers, in which human operators attend clients using textual chat, are very common in modern e-commerce. Training enough skilled operators who are able to provide good service is a challenge. We suggest an algorithm and a method to train and implement an assisting agent that provides on-line advice to operators while they attend clients. The agent is domain-independent and can be introduced to new domains without major efforts in design, training and organizing structured knowledge of the professional discipline. We demonstrate the applicability of the system in an experiment that realizes its full life-cycle on a specific domain and analyze its capabilities.