Multi-profile chat environment

Patent metadata

Field	Value
Publication number	US-10979370-B2
Application number	US-202016854439-A
Country	US
Kind code	B2
Filing date	Apr 21, 2020
Priority date	Mar 1, 2018
Publication date	Apr 13, 2021
Grant date	Apr 13, 2021

Abstract

A multi-profile chat system may receive a chat request comprising a user identifier and chat data. The system may process the chat data to determine a chat profile request, a request topic, and/or a request sentiment. The system may retrieve a user profile and/or a user chat record based on the user identifier. The system may determine a chat profile based on the chat profile request, the request topic, the request sentiment, the user profile, and/or the user chat record. The system may generate a chat response based on the chat request and the chat profile.

First claim

What is claimed is:

1. A method, comprising:
updating, by a chat environment, a plurality of chat profiles based at least in part on a machine learning analysis of user chat data associated with a plurality of user identifiers;
generating, by the chat environment, a first chat response based at least in part on a first chat request associated with a user identifier and a first chat profile of the plurality of chat profiles;
receiving, by the chat environment, a second chat request associated with the user identifier;
determining, by the chat environment, a second chat profile from the plurality of chat profiles that differs from the first chat profile in response to analyzing the second chat request; and
generating, by the chat environment, a second chat response based at least in part on the second chat request and the second chat profile.

2. The method of claim 1 , wherein analyzing the second chat request further comprises determining that a topic of the second chat request differs from a topic of the first chat request.

3. The method of claim 1 , wherein analyzing the second chat request further comprises determining that a sentiment of the second chat request differs from a sentiment of the first chat request.

4. The method of claim 1 , wherein analyzing the second chat request further comprises determining that the second chat request provides additional detail regarding an error included in the first chat request or an inquiry included in the first chat request.

5. The method of claim 1 , further comprising:
determining that the second chat request corresponds to a group chat function; and
wherein the second chat response is generated further based at least in part on the first chat profile.

6. The method of claim 1 , wherein the second chat profile is determined based at least in part on historical user chat data associated with the user identifier.

7. The method of claim 1 , wherein the second chat profile is determined based at least in part on transaction account data associated with the user identifier.

8. A system, comprising:
at least one computing device; and
instructions executable by the at least one computing device, wherein the instructions, when executed, cause the at least one computing device to at least:
update a plurality of chat profiles based at least in part on a machine learning analysis of user chat data associated with a plurality of user identifiers;
receive a chat request associated with a user identifier;
determine a chat profile from the plurality of chat profiles that differs from the a previously selected chat profile for the user identifier in response to an analysis of the chat request; and
generate a chat response based at least in part on the chat request and the chat profile.

9. The system of claim 8 , wherein the analysis of the chat request determines that a topic of the chat request differs from a topic of a previous chat request associated with the user identifier.

10. The system of claim 8 , wherein the analysis of the chat request determines that a sentiment of the chat request differs from a sentiment of a previous chat request associated with the user identifier.

11. The system of claim 8 , wherein the analysis of the chat request determines that the chat request provides additional detail regarding an error included in a previous chat request associated with the user identifier.

12. The system of claim 8 , wherein the analysis of the chat request determines that the chat request provides additional detail regarding an inquiry included in a previous chat request associated with the user identifier.

13. The system of claim 8 , wherein the instructions, when executed, further cause the at least one computing device to at least:
determine that the chat request corresponds to a group chat function; and
wherein the chat response is generated further based at least in part on the previously selected chat profile.

14. The system of claim 8 , wherein the chat profile is determined based at least in part on historical user chat data associated with the user identifier.

15. The system of claim 8 , wherein the chat profile is determined based at least in part on transaction account data associated with the user identifier.

16. A non-transitory computer-readable medium embodying instructions executable by at least one computing device, wherein the instructions, when executed, cause the at least one computing device to at least:
update a plurality of chat profiles based at least in part on a machine learning analysis of user chat data associated with a plurality of user identifiers;
generate a first chat response based at least in part on a first chat request associated with a user identifier and a first chat profile of the plurality of chat profiles;
receive a second chat request associated with the user identifier;
determine a second chat profile from the plurality of chat profiles that differs from the first chat profile in response to analyzing the second chat request; and
generate a second chat response based at least in part on the second chat request and the second chat profile.

17. The non-transitory computer-readable medium of claim 16 , wherein analyzing the second chat request further comprises at least one of:
determining that a topic of the second chat request differs from a topic of the first chat request;
determining that a sentiment of the second chat request differs from a sentiment of the first chat request; or
determining that the second chat request provides additional detail regarding an error included in the first chat request or an inquiry included in the first chat request.

18. The non-transitory computer-readable medium of claim 16 , wherein the instructions, when executed, further cause the at least one computing device to at least:
determine that the second chat request corresponds to a group chat function; and
wherein the second chat response is generated further based at least in part on the first chat profile.

19. The non-transitory computer-readable medium of claim 16 , wherein the second chat profile is determined based at least in part on historical user chat data associated with the user identifier.

20. The non-transitory computer-readable medium of claim 16 , wherein the second chat profile is determined based at least in part on transaction account data associated with the user identifier.

Assignees

• American Express Travel Related Services Co Inc

Inventors

• Basheer Sibish
• Bruno John

Classifications

• H04L51/02 Primary

  using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages · CPC title

• H04L51/04

  Real-time or near real-time messaging, e.g. instant messaging [IM] · CPC title

• G06F16/951

  Indexing; Web crawling techniques · CPC title

• G06F16/3329

  Natural language query formulation · CPC title

• G06F40/35

  Discourse or dialogue representation · CPC title