Artificial intelligence routing strategy in online customer service system

Abstract

The invention discloses an artificial intelligence routing strategy in an online customer service system, and the strategy comprises the following steps: S1, obtaining a session feature from at leastone round of session between a robot customer service and a user after judging that the robot customer service cannot accurately answer a question proposed by the user; S2, inputting the session features and the state features of the user into a preset intelligent routing sub-evaluation model for evaluation to obtain an intelligent routing sub-evaluation value for the user; S3, judging whether theintelligent routing sub-evaluation value of the user meets a predetermined manual customer service transfer condition or not; if so, transferring the user to the manual customer service with the highest matching degree with the user; and otherwise, adopting the original robot customer service to serve the user. The optimal customer service staff can be recommended to the user for online matchingservice, the user satisfaction degree and the customer service quality are effectively improved, and the user experience degree of the online customer service system is optimized.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to an artificial intelligence routing strategy in an online customer service system. Background technique [0002] With the development of the Internet, virtual robots based on artificial intelligence technology are more and more widely used in the field of enterprise user services. Robot customer service does not need to rest, it can respond to users' questions more quickly and standardizedly, communicate with users in the form of voice dialogue or text chat, and liberate human customer service from a large number of repetitive questions and answers. However, for some unconventional user questions, it is often difficult for robot customer service to give satisfactory answers to users. At present, the most commonly used structure of the customer service center is the coexistence of robot customer service and manual customer service. By default, the robot custome...

AI Technical Summary

Problems solved by technology

However, for some unconventional user questions, it is often difficult for robot customer service to give satisfactory answers to users

At present, the most commonly used structure of the customer service center is the coexistence of robot customer service and manual customer service. By default, the robot customer service will receive the user first. When the robot customer service cannot solve the user's problem, it will be transferred to the human customer service. The following methods are used for the user to transfer to the manual customer service: Implement a simple polling allocation mechanism, or a random allocation mechanism, or a simple queuing mechanism, so that the customer service personnel who receive the user at the end may not be able to solve the problems encountered by the current user in a timely and efficient manner

Images