Supporting conversations between customers and customer service agents

Abstract

The present disclosure describes various methods, computer-readable media, and apparatuses for supporting automation of customer service. The automation of customer service may be based on support for automation of conversations between customers and customer service agents. The automation of customer service based on support for automation of conversations between customers and customer service agents may be based on use of images provided by the customers to control the conversations between customers and customer service agents. The support for automation of conversations between customers and customer service agents based on use of images provided by the customers may include processing the images to obtain information for the conversations between the customers and the customer service agents and controlling the conversations between the customers and the customer service agents based on the information for the conversations between the customers and the customer service agents.

What is claimed is: 
     
         1 . A method comprising:
 sending, by a processing system including at least one processor, a request for an image associated with a conversation between a customer service agent and a customer, wherein the customer service agent comprises a chatbot, and wherein the request for the image associated with the conversation between the customer service agent and the customer is sent based on detection of content within the conversation between the customer service agent and the customer;   receiving, by the processing system, the image associated with the conversation between the customer service agent and the customer;   processing, by the processing system, the image associated with the conversation between the customer service agent and the customer, wherein the processing comprises:
 processing, by the processing system based on a first model, the image to obtain a set of features of the image; and 
 processing, by the processing system based on a second model, the set of features of the image to generate text which describes a need of the customer; and 
   controlling, by the processing system based on the need of the customer, continuation of the conversation between the customer service agent and the customer.   
     
     
         2 . The method of  claim 1 , wherein the image associated with the conversation between the customer service agent and the customer is related to a topic of the conversation between the customer service agent and the customer. 
     
     
         3 . The method of  claim 1 , wherein the request for the image associated with the conversation between the customer service agent and the customer is sent within the conversation between the customer service agent and the customer. 
     
     
         4 . The method of  claim 1 , wherein the image associated with the conversation between the customer service agent and the customer is received within the conversation between the customer service agent and the customer. 
     
     
         5 . The method of  claim 1 , wherein the first model comprises an image processing model. 
     
     
         6 . The method of  claim 5 , wherein the image processing model comprise a convolutional neural network. 
     
     
         7 . The method of  claim 1 , wherein the second model comprises an information generation model. 
     
     
         8 . The method of  claim 7 , wherein the information generation model comprises a neural network model. 
     
     
         9 . The method of  claim 1 , wherein the second model comprises an information extraction model. 
     
     
         10 . The method of  claim 9 , wherein the information extraction model comprises at least one of a classification model and a prediction model. 
     
     
         11 . The method of  claim 10 , wherein the need of the customer comprises an answer for the customer. 
     
     
         12 . The method of  claim 1 , wherein the controlling is further based on an answer for the customer. 
     
     
         13 . The method of  claim 1 , wherein the controlling continuation of the conversation between the customer service agent and the customer comprises:
 sending, by the processing system within the conversation between the customer service agent and the customer, a message including the need of the customer.   
     
     
         14 . The method of  claim 13 , wherein the message further includes a request for the customer to verify the need of the customer. 
     
     
         15 . The method of  claim 1 , wherein the first model is an image caption model. 
     
     
         16 . An apparatus comprising:
 a processing system including at least one processor; and   a computer-readable medium storing instructions which, when executed by the processing system, cause the processing system to perform operations, the operations comprising:
 sending a request for an image associated with a conversation between a customer service agent and a customer, wherein the customer service agent comprises a chatbot, and wherein the request for the image associated with the conversation between the customer service agent and the customer is sent based on detection of content within the conversation between the customer service agent and the customer; 
 receiving the image associated with the conversation between the customer service agent and the customer; 
 processing the image associated with the conversation between the customer service agent and the customer, wherein the processing comprises:
 processing, based on a first model, the image to obtain a set of features of the image; and 
 processing, based on a second model, the set of features of the image to generate text which describes a need of the customer; and 
 
 controlling, based on the need of the customer, continuation of the conversation between the customer service agent and the customer. 
   
     
     
         17 . The apparatus of  claim 16 , wherein the first model comprises an image processing model. 
     
     
         18 . The apparatus of  claim 16 , wherein the first model comprises an image caption model. 
     
     
         19 . A method comprising:
 receiving, by a processing system including at least one processor, a request for an image associated with a conversation between a customer service agent and a customer, wherein the customer service agent comprises a chatbot;   obtaining, by the processing system, the image associated with the conversation between the customer service agent and the customer;   sending, by the processing system, the image associated with the conversation between the customer service agent and the customer; and   receiving, by the processing system within the conversation between the customer service agent and the customer, a message including information for the conversation between the customer service agent and the customer, wherein the information for the conversation between the customer service agent and the customer is based on processing of the image by the customer service agent, and wherein the processing comprises using a first model that processes the image to obtain a set of features of the image and using a second model that processes the set of features of the image to generate text which describes the information for the conversation between the customer service agent and the customer.   
     
     
         20 . The method of  claim 19 , wherein the first model is an image caption model.