System and method for serving multiple customers by a live agent

Patent metadata

Field	Value
Publication number	US-12022026-B2
Application number	US-202217698717-A
Country	US
Kind code	B2
Filing date	Mar 18, 2022
Priority date	Mar 18, 2022
Publication date	Jun 25, 2024
Grant date	Jun 25, 2024

Abstract

A system and method for allowing a single live customer service agent to simultaneously serve multiple customers. According to various embodiments, a virtual agent operates at the front end to receive and attempt to handle customer issues. The virtual agent employs speech recognition and intent mapping in order to generate a proposed response that attempts to identify and resolve customer issues. In some scenarios, the proposed response includes both a response message and a response action to be taken. A chat history and the proposed response is then provided to the live agent. The live agent reviews the information provided, and determines whether the proposed response is appropriate. The live agent then approves the response or revises or replaces the response. The final response is sent back to the virtual agent for processing and providing to the customer.

First claim

What is claimed is:

1. A virtual customer service response agent, comprising:
a communication interface configured to communicate with a customer and to exchange information with a live agent; and
one or more processors configured to:
receive a message from the customer via the communication interface;
map an intent of the received message;
generate a response to the message based on the mapped intent;
transmit, via a transceiver, the generated response to the live agent;
receive a final response from the live agent; and
transmit, via the transceiver, the final response to the customer.

2. The virtual customer service response agent of claim 1 , wherein the received message is a voice message, and
wherein the one or more processors are further configured to convert the voice message to text.

3. The virtual customer service response agent of claim 2 , wherein the received final response is a text message, and
wherein the one or more processors are further configured to convert the text message to speech.

4. The virtual customer service response agent of claim 3 , wherein the one or more processors are further configured to synthesize the speech so as to mimic a particular speaking style.

5. The virtual customer service response agent of claim 1 , wherein the one or more processors are further configured to record the received message and the final response in a transcript.

6. The virtual customer service response agent of claim 5 , wherein the one or more processors are further configured to record the intent and the generated response in the transcript.

7. The virtual customer service response agent of claim 5 , wherein the transcript is in a text format.

8. A live agent workstation for simultaneously servicing a plurality of customers, comprising:
a communication interface configured to exchange information with a virtual agent server;
one or more input devices configured to receive input information from a live agent;
one or more output devices configured to provide output information to the live agent; and
one or more processors configured to:
receive, from the live agent, a selection of an active customer from among a plurality of current customers being serviced by the live agent;
provide to the live agent via the one or more output devices a chat history and a proposed response;
receive a final response from the live agent via the one or more input devices; and
transmit, via the communication interface, the final response to the virtual agent server.

9. The live agent workstation of claim 8 , wherein the one or more processors are further configured to:
receive an approval command from the live agent,
wherein the proposed response becomes the final response in response to the approval command.

10. The live agent workstation of claim 8 , wherein the one or more processors are further configured to:
receive an edit command from the live agent;
provide a text editing interface to the live agent that includes the proposed response in editable format; and
receive an edited response via the text editing interface; and
transmit the edited response to the virtual agent server as the final response.

11. The live agent workstation of claim 8 , wherein the one or more processors are further configured to:
receive a replacement command from the live agent;
active the one or more input devices in response to the receiving of the replacement command; and
receive a replacement message via the one or more input devices,
wherein the one or more input devices includes a microphone.

12. The live agent workstation of claim 11 , wherein the one or more processors are further configured to transmit the received replacement message to the virtual agent server in real-time without waiting until receipt of an entirety of the replacement message.

13. The live agent workstation of claim 8 , wherein the one or more processors are further configured to:
receive a step-in command from the live agent; and
transfer, in response to the receiving of the step-in command, the plurality of current customers being serviced by the live agent other than the active customer to another live agent.

14. The live agent workstation of claim 13 , wherein the one or more processors are further configured to connect the live agent to the virtual agent server in real time.

15. A method for servicing a plurality of current customers by a live agent, the method comprising:
receiving a message from an active customer from among the plurality of current customers currently being serviced by the live agent;
perform an intent analysis of the received message;
generate a proposed response message to the received message based on the intent analysis;
provide the proposed response message to the live agent;
receive a final response message from the live agent; and
provide the final response message to the active customer of the plurality of current customers.

16. The method of claim 15 , wherein the received message is a voice message, the method further comprising converting the voice message to text.

17. The method of claim 15 , wherein the final response message is received from the live agent in a text format, the method further comprising converting the received final response message to speech.

18. The method of claim 15 , further comprising recording the received message and the final response in a transcript.

19. The method of claim 18 , further comprising recording results of the intent analysis and the proposed response in the transcript.

20. The method of claim 15 , further comprising:
receiving a step-in command from the live agent;
transferring each of the plurality of current customers other than the active customer to other agents; and
connecting the live agent to the active customer for real-time communication.

Assignees

• Capital One Services Llc

Inventors

• Edwards Joshua
• Bonilla Guadalupe
• Maiman Tyler
• Mossoba Michael
• KHANAGHA Vahid
• Can Aysu Ezen
• Rodriguez Mia
• Qiu Feng
• Lin Alexander
• Critzer Meredith L

Classifications

• H04M3/5133

  Operator terminal details · CPC title

• H04M2201/39

  using speech synthesis · CPC title

• H04M3/5191

  interacting with the Internet · CPC title

• G06F40/166

  Editing, e.g. inserting or deleting · CPC title

• G06F40/30

  Semantic analysis · CPC title