Method, device and equipment for following up incoming call customers based on speech recognition

Abstract

The present invention provides a voice recognition-based method, device and equipment for following up incoming customers, wherein the method includes: storing the recording of incoming calls and synchronizing the data of incoming calls in real time. Follow up the caller; receive the label selected in the customer service call, and establish an initial follow-up table according to the label; obtain the voice of the incoming call, and use the softmax function and CTC loss function to complete the speech recognition model established by the LSTM long-short memory network Recognize the voice of the incoming call to obtain the recognized text; extract the target label according to the recognized text, and supplement the initial follow-up table according to the target label to obtain the target follow-up table. This solution realizes intelligent follow-up of incoming customers, improves follow-up efficiency, and ensures full coverage and accuracy of follow-up.

Description

technical field [0001] The invention relates to the technical field of computer communication, in particular to a voice recognition-based method, device and equipment for following up an incoming caller. Background technique [0002] In the real estate industry, answering the phone is an indispensable method for real estate consultants (customer service) to attract and maintain customers. However, for this part of the customers who call, the real estate consultant (customer service) cannot intuitively see the customer's phone number, and needs to check the phone number, or ask the customer to leave their name and mobile phone number, so it is difficult to associate the customer file with the calling customer. In this way, it is impossible to make some judgments on customer information in a timely manner, such as judgments on new and old customers, and follow-up on relevant intentions. It is easy to cause the loss of calling customers and the loss of key intentional content....

AI Technical Summary

Problems solved by technology

However, for this part of the customers who call, the real estate consultant (customer service) cannot intuitively see the customer's phone number, and needs to check the phone number, or ask the customer to leave their name and mobile phone number, so it is difficult to associate the customer file with the calling customer

In this way, it is impossible to make some judgments on customer information in a timely manner, such as judgments on new and old customers, follow-up of relevant intentions

It is easy to cause the loss of calling customers and the loss of key intention content

Images