Dynamically evolving cognitive architecture system based on a natural language intent interpreter

• US 9,633,317 B2
• Filed: 08/18/2014
• Issued: 04/25/2017
• Est. Priority Date: 06/20/2013
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Viv Labs, Inc. (Samsung Electronics Co. Ltd.)
• Inventors: Gabel, Mark, Brigham, Christopher, Cheyer, Adam
• Primary Examiner(s): BROPHY, MATTHEW J
• Application Number:
  US14/461,861
• Publication Number:
  US 20140380285A1
• Time in Patent Office: 981 Days
• Field of Search: None
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition

Abstract

A dynamically evolving cognitive architecture system based on a natural language intent interpreter is described. A system forms an intent based on a user input, and creates a plan based on the intent. The plan includes a first action object that transforms a first concept object associated with the intent into a second concept object and also includes a second action object that transforms the second concept object into a third concept object associated with a goal of the intent. The first action object and the second action object are selected from multiple action objects. The system executes the plan, and outputs a value associated with the third concept object.

Claims

1. A system for a dynamically evolving cognitive architecture based on a natural language intent interpreter, the system comprising:

one or more processors; and

a non-transitory computer readable medium storing a plurality of instructions, which

when executed, cause the one or more processors to;

match a first object provided by a first third-party developer with a first span of natural language from a user input and a second object provided by a second third-party developer with a second span of natural language from the user input, the first object comprising one of an input action object, an input concept object, and an output concept object, and the second object comprising another one of the input action object, the input concept object, and the output concept object;

form an intent based on the user input;

create a plan based on the intent, the plan comprising the input action object that transforms the input concept object associated with the intent into an intermediate concept object, and the output action object that transforms another intermediate concept object into the output concept object associated with a goal of the intent, the other intermediate concept object comprising one of a same object as the intermediate concept object and a different object from the intermediate concept object, the input action object and the output action object being selected from a plurality of action objects;

execute the plan; and

output a value associated with the output concept object to a user interface associated with user the intent.

2. The system of claim 1, wherein matching the first object with the first span of natural language from the user input is based on a corresponding first matching confidence score exceeding a first threshold and matching the second object with the second span of natural language from the user input is based on a corresponding second matching confidence score exceeding a second threshold, and wherein the plan comprises another action object based on a corresponding third matching confidence score associated with the other action object exceeding a third threshold.

3. The system of claim 1, wherein at least one of the intermediate concept object and the output action object lacks a match with any span of natural language from the user input.

4. The system of claim 1, wherein the input action object is provided by a first third-party developer and the output action object is provided by a second third-party developer.

5. The system of claim 1, wherein the plurality of instructions, when executed, will further cause the one or more processors to receive a span of natural language annotated with an object from a third-party developer, wherein creating the plan is based on the annotated span of natural language, and wherein the annotating object comprises one of the input action object, the output action object, the input concept object, the intermediate concept object, the other intermediate concept object and the output concept object.

6. The system of claim 5, wherein the plurality of instructions, when executed, will further cause the one or more processors to:

create a second plan based on the intent, wherein the second plan differs from the first plan by at least one concept object and by at least one action object; and

select the plan for execution based on at least one of an action object cost, an action object quality, a number of planned action objects, and a confidence score associated with the annotated span of natural language.

7. The system of claim 1, wherein the plurality of instructions, when executed, will further cause the one or more processors to output a prompt, based on the plan, which requests an additional user input, wherein executing the plan is based on the additional user input.

8. A computer-implemented method for a dynamically evolving cognitive architecture system based on a natural language intent interpreter, the method comprising:

matching a first object provided by a first third-party developer with a first span of natural language from a user input and a second object provided by a second third-party developer with a second span of natural language from the user input, the first object comprising one of an input action object, an input concept object, and an output concept object, and the second object comprising another one of the input action object, the input concept object, and the output concept object;

forming an intent based on the user input;

creating a plan based on the intent, the plan comprising the input action object that transforms the input concept object associated with the intent into an intermediate concept object, and the output action object that transforms another intermediate concept object into the output concept object associated with a goal of the intent, the other intermediate concept object comprising one of a same object as the intermediate concept object and a different object from the intermediate concept object, the input action object and the output action object being selected from a plurality of action objects;

executing the plan; and

outputting a value associated with the output concept object to a user interface associated with the user input.

9. The computer-implemented method of claim 8, wherein matching the first object with the first span of natural language from the user input is based on a corresponding first matching confidence score exceeding a first threshold and matching the second object with the second span of natural language from the user input is based on a corresponding second matching confidence score exceeding a second threshold, wherein the plan comprises another action object based on a corresponding third matching confidence score associated with the other action object exceeding a third threshold, and wherein at least one of the intermediate concept object and the output action object lacks a match with any span of natural language from the user input.

10. The computer-implemented method of claim 8, wherein the input action object is provided by a first third-party developer and the output action object is provided by a second third-party developer.

11. The computer-implemented method of claim 8, wherein the method further comprises receiving a span of natural language annotated with an object from a third-party developer, wherein creating the plan is based on the annotated span of natural language, and wherein the annotating object comprises one of the input action object, the output action object, the input concept object, the intermediate concept object, the other intermediate concept object and the output concept object.

12. The computer-implemented method of claim 11, wherein the method further comprises:

creating a second plan based on the intent, wherein the second plan differs from the first plan by at least one concept object and by at least one action object; and

selecting the plan for execution based on at least one of an action object cost, an action object quality, a number of planned action objects, and a confidence score associated with the annotated span of natural language.

13. The computer-implemented method of claim 8, wherein the method further comprises outputting a prompt, based on the plan, which requests an additional user input, wherein executing the plan is based on the additional user input.

14. A computer program product, comprising a non-transitory computer-readable medium having a computer-readable program code embodied therein to be executed by one or more processors, the program code including instructions to:

match a first object provided by a first third-party developer with a first span of natural language from a user input and a second object provided by a second third-party developer with a second span of natural language from the user input, the first object comprising one of an input action object, an input concept object, and an output concept object, and the second object comprising another one of the input action object, the input concept object, and the output concept object;

form an intent based on the user input;

create a plan based on the intent, the plan comprising the input action object that transforms the input concept object associated with the intent into an intermediate concept object, and the output action object that transforms another intermediate concept object into the output concept object associated with a goal of the intent, the other intermediate concept object comprising one of a same object as the intermediate concept object and a different object from the intermediate concept object, the input action object and the output action object being selected from a plurality of action objects;

execute the plan; and

output a value associated with the output concept object to a user interface associated with the user input.

15. The computer program product of claim 14, wherein matching the first object with the first span of natural language from the user input is based on a corresponding first matching confidence score exceeding a first threshold and matching the second object with the second span of natural language from the user input is based on a corresponding second matching confidence score exceeding a second threshold, and wherein the plan comprises another action object based on a corresponding third matching confidence score associated with the other action object exceeding a third threshold.

16. The computer program product of claim 14, wherein at least one of the intermediate concept object and the output action object lacks a match with any span of natural language from the user input.

17. The computer program product of claim 14, wherein the input action object is provided by a first third-party developer and the output action object is provided by a second third-party developer.

18. The computer program product of claim 14, wherein the program code includes further instructions to receive a span of natural language annotated with an object from a third-party developer, wherein creating the plan is based on the annotated span of natural language, and wherein the annotating object comprises one of the input action object, the output action object, the input concept object, the intermediate concept object, the other intermediate concept object and the output concept object.

19. The computer program product of claim 18, wherein the program code includes further instructions to:

create a second plan based on the intent, wherein the second plan differs from the first plan by at least one concept object and by at least one action object; and

select the plan for execution based on at least one of an action object cost, an action object quality, a number of planned action objects, and a confidence score associated with the annotated span of natural language.

20. The computer program product of claim 14, wherein the program code includes further instructions to output a prompt, based on the plan, which requests an additional user input, wherein executing the plan is based on the additional user input.