Artificial intelligence routing strategy in online customer service system
A technology of artificial intelligence and customer service system, applied in the direction of customer relationship, biological neural network model, computing model, etc., can solve the problem that robot customer service is difficult to give user answers, can not be solved in a timely and efficient manner, to optimize user experience, improve Accuracy and the effect of improving service quality
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Publication Date
- 2020-02-25
Smart Images

Figure 1
Abstract
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...
Examples
Embodiment Construction
[0023] The present invention will be described in detail below in conjunction with the accompanying drawings, so that those of ordinary skill in the art can implement it after referring to this specification.
[0024] Such as figure 1 As shown, an artificial intelligence routing strategy in an online customer service system includes the following steps:
[0025] S1. After judging that the robot customer service cannot accurately answer the questions raised by the user, acquire the conversation features in at least one round of conversations between the robot customer service and the user;
[0026] S2. Input the session feature and the user's state feature into a preset intelligent routing score evaluation model for evaluation, and obtain an intelligent routing score evaluation value for the user;
[0027] S3. Judging whether the evaluation value of the intelligent routing score of the user satisfies the predetermined transfer to manual customer service conditions; if yes, the...