IP Library Granted Patent US 11,005,997
Granted Patent B1
US 11,005,997 · App. 15/933,020 · Granted May 11, 2021

Automated chatbot transfer to live agent

Inventors: Kristin H. Deegan (Sausalito, CA); Matthew G. Vanhouten (Moraga, CA); Uma Meyyappan (Freemont, CA); Jennifer Toby Whateley (Fremont, CA); Balinder Singh Mangat (Castro Valley, CA); Upul D. Hanwella (San Francisco, CA); Kimarie Pike Matthews (Burlingame, CA); Maria J. Latorre (Alameda, CA); Scott Edward Pitchford (Danville, CA)
Assignee: Wells Fargo Bank, N.A.
H04M3/5191G06F40/295G06F40/30H04L51/02H04L51/04H04L51/32
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,005,997
App. No.
15/933,020
Granted
May 11, 2021
Kind
B1
Abstract

Disclosed are methods, systems, and machine-readable mediums which provide for customer chatbots that detect a customer handoff condition and in response, transferring the customer to a communication session with a live agent. The handoff condition may comprise an inability to understand the customer, an inability to answer the customer's question, expressions of frustration or anger on the part of the customer, a customer's express request to be transferred, or the like. The live agent may receive a complete history of the conversation with the chatbot so that the customer does not have to repeat him or herself to the live agent. The chatbot chat session may be linked to a social networking account of the customer and may take place in association with a social networking profile page of the company.

Claims (82)

1. A method for redirecting a digital communication, the method comprising:

receiving, from a social networking service and during a conversation between a chatbot of a chat service and a user on a first chat page of the social networking service, a message entered into the first chat page of the social networking service, the message posted by a user, and the message received, by the chat service, through a callback web address of the chat service provided to the social networking service;

processing the message using natural language processing;

detecting a handoff condition during the processing of the message;

determining, based upon detecting the handoff condition, that the chat on the first chat page of the social networking service should be handed off from an automated chatbot to a human agent, the handoff condition comprising one or more of:

presence of a keyphrase;

presence of a key word;

an inability to determine a meaning of the message; or

an inability to provide an answer to the message that is above a predetermined level of confidence in answering the message;

determining a hyperlink to a second chat page of the social networking service, the second chat page of the social networking service registered to an agent service that routes communications with the second chat page of the social networking service to the human agent, the hyperlink linking to a Universal Resource Locator (URL); and

causing the link to be posted to the first chat page of the social networking service as a message to the user and from the chat service by sending the hyperlink to the first chat page of the social networking service.

2. The method of claim 1 , comprising:

receiving, from the social networking service, an earlier message before the message, the earlier message entered into the first chat page of the social networking service, the earlier message posted by the user, the earlier message received through the callback web address provided to the social networking service;

processing the earlier message;

determining from the earlier processed message that the handoff condition is not indicated;

determining a response to the earlier process message, the response generated without human intervention; and

sending the response to the social networking service for posting to the first chat page.

3. The method of claim 2 , comprising:

receiving content from an information service over a network; and

inserting the content into the response.

4. The method of claim 3 , wherein the information service is an account information service and the content is information on an account of the user at the information service.

5. The method of claim 1 , wherein determining from the processed message that the handoff condition is indicated in the message comprises:

inputting the processed message to a machine learning algorithm; and

receiving an output of the machine learning algorithm indicating that the handoff condition is indicated.

6. The method of claim 5 , comprising:

training the machine learning algorithm with past chat logs annotated indicating a handoff condition.

7. The method of claim 1 , wherein determining the hyperlink to the second chat page of the social networking service comprises receiving the hyperlink from the agent service over a network.

8. A non-transitory machine-readable medium comprising instructions for causing a redirection of a digital communication, the instructions, when executed by a machine, causing the machine to perform operations comprising:

receiving, from a social networking service and during a conversation between a chatbot of a chat service and a user on a first chat page of the social networking service, a message entered into the first chat page of the social networking service, the message posted by a user, and the message received, by the chat service, through a callback web address of the chat service provided to the social networking service;

processing the message using natural language processing;

detecting a handoff condition during the processing of the message;

determining, based upon detecting the handoff condition, that the chat on the first chat page of the social networking service should be handed off from an automated chatbot to a human agent, the handoff condition comprising one or more of:

presence of a keyphrase;

presence of a key word;

an inability to determine a meaning of the message; or

an inability to provide an answer to the message that is above a predetermined level of confidence in answering the message;

determining a hyperlink to a second chat page of the social networking service, the second chat page of the social networking service registered to an agent service that routes communications with the second chat page of the social networking service to the human agent, the hyperlink linking to a Universal Resource Locator (URL); and

causing the link to be posted to the first chat page of the social networking service as a message to the user and from the chat service by sending the hyperlink to the first chat page of the social networking service.

9. The machine-readable medium of claim 8 , wherein the operations further comprise:

receiving, from the social networking service, an earlier message before the message, the earlier message entered into the first chat page of the social networking service, the earlier message posted by the user, the earlier message received through the callback web address provided to the social networking service;

processing the earlier message;

determining from the earlier processed message that the handoff condition is not indicated;

determining a response to the earlier process message, the response generated without human intervention; and

sending the response to the social networking service for posting to the first chat page.

10. The machine-readable medium of claim 9 , wherein the operations further comprise:

receiving content from an information service over a network; and

inserting the content into the response.

11. The machine-readable medium of claim 10 , wherein the information service is an account information service and the content is information on an account of the user at the information service.

12. The machine-readable medium of claim 8 , wherein the operations of determining from the processed message that the handoff condition is indicated in the message comprises:

inputting the processed message to a machine learning algorithm; and

receiving an output of the machine learning algorithm indicating that the handoff condition is indicated.

13. The machine-readable medium of claim 12 , wherein the operations further comprise:

training the machine learning algorithm with past chat logs annotated indicating a handoff condition.

14. The machine-readable medium of claim 8 , wherein the operations of determining the hyperlink to the second chat page of the social networking service comprises receiving the hyperlink from the agent service over a network.

15. A computing device comprising:

a processor;

a memory, the memory storing instructions, which when executed by the processor, cause the processor to perform operations comprising:

receiving, from a social networking service and during a conversation between a chatbot of a chat service and a user on a first chat page of the social networking service, a message entered into the first chat page of the social networking service, the message posted by a user, and the message received, by the chat service, through a callback web address of the chat service provided to the social networking service;

processing the message using natural language processing;

detecting a handoff condition during the processing of the message;

determining, based upon detecting the handoff condition, that the chat on the first chat page of the social networking service should be handed off from an automated chatbot to a human agent, the handoff condition comprising one or more of:

presence of a keyphrase;

presence of a key word;

an inability to determine a meaning of the message; or

an inability to provide an answer to the message that is above a predetermined level of confidence in answering the message;

determining a hyperlink to a second chat page of the social networking service, the second chat page of the social networking service registered to an agent service that routes communications with the second chat page of the social networking service to the human agent, the hyperlink linking to a Universal Resource Locator (URL); and

causing the link to be posted to the first chat page of the social networking service as a message to the user and from the chat service by sending the hyperlink to the first chat page of the social networking service.

16. The computing device of claim 15 , wherein the operations further comprise:

receiving, from the social networking service, an earlier message before the message, the earlier message entered into the first chat page of the social networking service, the earlier message posted by the user, the earlier message received through the callback web address provided to the social networking service;

processing the earlier message;

determining from the earlier processed message that the handoff condition is not indicated;

determining a response to the earlier process message, the response generated without human intervention; and

sending the response to the social networking service for posting to the first chat page.

17. The computing device of claim 16 , wherein the operations further comprise:

receiving content from an information service over a network; and

inserting the content into the response.

18. The computing device of claim 17 , wherein the information service is an account information service and the content is information on an account of the user at the information service.

19. The computing device of claim 15 , wherein the operations of determining from the processed message that the handoff condition is indicated in the message comprises:

inputting the processed message to a machine learning algorithm; and

receiving an output of the machine learning algorithm indicating that the handoff condition is indicated.

20. The computing device of claim 19 , wherein the operations further comprise:

training the machine learning algorithm with past chat logs annotated indicating a handoff condition.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 28, 2018
From: DEEGAN, KRISTIN H; VANHOUTEN, MATTHEW G; MEYYAPPAN, UMA; WHATELEY, JENNIFER TOBY; MANGAT, BALINDER SINGH; HANWELLA, UPUL D; MATTHEWS, KIMARIE PIKE; LATORRE, MARIA J; PITCHFORD, SCOTT EDWARD
To: WELLS FARGO BANK, N.A.
Reel/Frame 047001/0127 →
Continuity (1)
Provisional Application 62475681 · Mar 23, 2017
Cited By (6)
US 12,323,414 US 12,355,713 US 12,381,961 US 12,592,899 US 12,676,145 US 12,744,848