Title | Isa: Intuit Smart Agent, A Neural-Based Agent-Assist Chatbot |
Publication Type | Conference Paper |
Year of Publication | 2018 |
Authors | Xue, Zijun, Ko, Ting-Yu, Yuchen, Neo, Wu, Ming-Kuang Daniel, Hsieh, Chu-Cheng |
Conference Name | 2018 IEEE International Conference on Data Mining Workshops (ICDMW) |
Date Published | nov |
Keywords | artificial intelligence, B2C companies, BiLSTM, call centers, call centres, Companies, conversation agents, conversational agent, conversational AI, Currencies, customer experience, customer service agents, customer services, customer support agents, customer wait time, electronic commerce, feature extraction, goal oriented chatbot, Human Behavior, internal group messaging channels, Intuit Smart Agent system, Isa system, Metrics, multi-agent systems, Neural networks, neural-based agent-assist chatbot, pubcrawl, recurrent neural nets, Scalability, software agents, Task Analysis |
Abstract | Hiring seasonal workers in call centers to provide customer service is a common practice in B2C companies. The quality of service delivered by both contracting and employee customer service agents depends heavily on the domain knowledge available to them. When observing the internal group messaging channels used by agents, we found that similar questions are often asked repetitively by different agents, especially from less experienced ones. The goal of our work is to leverage the promising advances in conversational AI to provide a chatbot-like mechanism for assisting agents in promptly resolving a customer's issue. In this paper, we develop a neural-based conversational solution that employs BiLSTM with attention mechanism and demonstrate how our system boosts the effectiveness of customer support agents. In addition, we discuss the design principles and the necessary considerations for our system. We then demonstrate how our system, named "Isa" (Intuit Smart Agent), can help customer service agents provide a high-quality customer experience by reducing customer wait time and by applying the knowledge accumulated from customer interactions in future applications. |
DOI | 10.1109/ICDMW.2018.00202 |
Citation Key | xue_isa:_2018 |