Systems and methods for intent-based natural language processing

Patent metadata

Field	Value
Publication number	US-11914952-B2
Application number	US-202117510116-A
Country	US
Kind code	B2
Filing date	Oct 25, 2021
Priority date	Apr 27, 2021
Publication date	Feb 27, 2024
Grant date	Feb 27, 2024

Abstract

A method may include for intent-based natural language processing may include conversation engine: receiving from a conversation program executed on a user electronic device, a unique identifier for a user; calling an external controls program with the unique identifier and a type of the user electronic device, wherein the external controls program identifies a directive of intent and an alternate action; receiving the directive of intent and the alternate action; receiving text of an utterance in a conversation from the conversation program; selecting one of a plurality a priority of intents based on the text of the utterance; receiving a plurality of potential intents and a confidence score for each potential intent from a natural language understanding computer program; selecting a selected intent; determining that the directive of intent matches the selected intent; and executing the alternate action.

First claim

What is claimed is:

1. A method for intent-based natural language processing, comprising:
receiving, at a channel adapter for a conversation engine and from a conversation program executed on a user electronic device, a unique identifier for a user;
calling, by the conversation engine, an external controls program with the unique identifier and a type of the user electronic device, wherein the external controls program applies a rule to the unique identifier and/or the type of user electronic device to identify a directive of intent and an alternate action for the directive of intent;
receiving, by the conversation engine and from the external controls program, the directive of intent and the alternate action;
receiving, by the conversation engine, text of an utterance in a conversation from the conversation program;
selecting, by the conversation engine, one of a plurality of priorities of intents based on the text of the utterance;
communicating, by the conversation engine, the text of the utterance to a natural language understanding computer program;
receiving, by the conversation engine, a plurality of potential intents and a confidence score for each potential intent from the natural language understanding computer program;
selecting, by the conversation engine, a selected intent based on the selected priority of intents, the potential intents, and the confidence scores;
determining, by the conversation engine, that the directive of intent matches the selected intent; and
executing, by the conversation engine, the alternate action;
wherein the intents in a first of the plurality of priorities of intents are ordered as a flow intent and a command intent, and the intents in a second of the plurality of priority intents are ordered as an expected answer intent, a command intent, and a flow intent.

2. The method of claim 1 , wherein the rule is based on an account type, an account balance, an account status, a type of the user electronic device, and/or a past experience with the conversation engine for the user.

3. The method of claim 1 , wherein the alternate action is based on a type of the electronic device.

4. The method of claim 1 , wherein the alternate action is based on a past experience with the conversation engine for the user.

5. The method of claim 1 , further comprising:
caching, by the conversation engine, the directive of intent and the alternate action.

6. The method of claim 1 , further comprising:
storing, by the conversation engine, a session identifier for the conversation and a conversation state for the conversation in a database; and
updating, by the conversation engine, the conversation state in the database based on the executed alternate action.

7. The method of claim 1 , further comprising:
returning, by the conversation engine, a response to the conversation program based on the executed alternate action.

8. An electronic device, comprising:
a memory storing a conversation engine computer program; and
a computer processor;
wherein, when executed by the computer processor, the conversation engine computer processor causes the computer processor to:
receive, from a channel adapter, a unique identifier for a user and a type of a user electronic device;
call an external controls program with the unique identifier and the type of the user electronic device, wherein the external controls program applies a rule to the user identifier and/or the type of user electronic device to identify a directive of intent and an alternate action for the directive of intent;
receive, from the external controls program, the directive of intent and the alternate action;
receive text of an utterance in a conversation from the conversation program;
select one of a plurality of priorities of intents based on the text of the utterance;
communicate the text of the utterance to a natural language understanding computer program;
receive a plurality of potential intents and a confidence score for each potential intent from the natural language understanding computer program;
select a selected intent based on the selected priority of intents, the potential intents, and the confidence scores;
determine that the directive of intent matches the selected intent; and
execute the alternate action;

wherein the intents in a first of the plurality of priorities of intents are ordered as a flow intent and a command intent, and the intents in a second of the plurality of priority intents are ordered as an expected answer intent, a command intent, and a flow intent.

9. The electronic device of claim 8 , wherein the rule is based on an account type, an account balance, an account status, a type of the user electronic device, and/or a past experience with the conversation engine for the user.

10. The electronic device of claim 8 , wherein the alternate action is based on a type of the electronic device.

11. The electronic device of claim 8 , wherein the alternate action is based on a past experience with the conversation engine for the user.

12. The electronic device of claim 8 , wherein the conversation engine computer program further causes the computer processor to cache the directive of intent and the alternate action.

13. The electronic device of claim 8 , wherein the conversation engine computer program further causes the computer processor to store a session identifier for the conversation and a conversation state for the conversation in a database; and
updating, by the conversation engine, the conversation state in the database based on the alternate action.

14. The electronic device of claim 8 , wherein the conversation engine computer program further causes the computer processor to return a response to the conversation program based on the executed alternate action.

15. A method for intent-based natural language processing, comprising:
receiving, at a channel adapter for a conversation engine and from a conversation program executed on a user electronic device, a unique identifier for a user;
calling, by the conversation engine, an external controls program with the unique identifier and a type of the user electronic device;
receiving, by the conversation engine and from the external controls program, an alternate action;
receiving, by the conversation engine, text of an utterance in a conversation from the conversation program;
selecting, by the conversation engine, one of a plurality of priorities of intents based on the text of the utterance;
communicating, by the conversation engine, the text of the utterance to a natural language understanding computer program;
receiving, by the conversation engine, a plurality of potential intents and a confidence score for each potential intent from the natural language understanding computer program;
selecting, by the conversation engine, a selected intent based on the selected priority of intents, the potential intents, and the confidence scores;
identifying, by the conversation engine, a flag or a value in a conversation flow; and
executing, by the conversation engine, the alternate action;
wherein the intents in a first of the plurality of priorities of intents are ordered as a flow intent and a command intent, and the intents in a second of the plurality of priority intents are ordered as an expected answer intent, a command intent, and a flow intent.

16. The method of claim 15 , wherein the alternate action is based on a type of the electronic device.

17. The method of claim 15 , wherein the alternate action is based on the unique identifier.

18. The method o

Assignees

• Jpmorgan Chase Bank Na

Inventors

• White Ben
• Gordon Janie
• Miller Honey L
• Kumar Amit
• Bisht Piyush

Classifications

• G06F40/20 Primary

  Natural language analysis (semantic analysis of natural language G06F40/30) · CPC title

• G06F16/3329

  Natural language query formulation · CPC title

• G06F40/35

  Discourse or dialogue representation · CPC title

• G06F40/30 Primary

  Semantic analysis · CPC title