An intelligent customer service method and system

Abstract

The invention relates to the technical field of intelligent man-machine interaction, and provides an intelligent customer service method which comprises the following steps: receiving a customer inputtext; Performing type identification on the input text; If the input text is the questionnaire, performing theme recognition on the input text based on a preset short text classification model; And distributing a customer service based on an identification result, and replying to the input text. According to the intelligent customer service method provided by the embodiment of the invention, thetext input by the customer is identified, and the corresponding customer service is distributed based on the identification result, so that the reply rate and the professional degree of the customer service can be improved to a certain extent. In addition, the invention further provides an intelligent customer service system.

Description

Technical field [0001] The invention relates to the technical field of intelligent human-computer interaction, in particular to an intelligent customer service method and system. Background technique [0002] With the rapid development of the Internet and the improvement of people's service awareness, online customer service has spread to all walks of life and penetrates into all aspects of daily business services. [0003] The current customer service system usually consists of machine customer service and manual customer service. The machine customer service is generally a web-based instant messaging tool, which can be implemented based on an intelligent chat robot or FAQ system. In the intelligent customer service scenario, after the customer asks a question, It is often necessary to first calculate the similarity between the question asked by the customer and the question stored in the knowledge base (FQA), and then locate the most similar question, extract the corresponding an...

AI Technical Summary

Problems solved by technology

[0004] However, due to the large number of users on the Internet, when facing various questions raised by different customers, smart customers need to traverse the knowledge base and calculate the similarity between the customer's questions and the questions in the knowledge base one by one. All calculation structures locate the question with the highest similarity to obtain the corresponding answer. In this way, the slow response speed caused by the large amount of data processing will bring a bad user experience and lead to customer loss

Images