Dynamically evolving cognitive architecture system planning

• US 10,083,009 B2
• Filed: 06/17/2014
• Issued: 09/25/2018
• 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): Nguyen, Mongbao
• Application Number:
  US14/306,903
• Publication Number:
  US 20140380268A1
• Time in Patent Office: 1,561 Days
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06F 8/00 Arrangements for software engineering testing or debugging G06F11/36; administrative, planning or organisation aspects of software project management G06Q10/06
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation

Abstract

Dynamically evolving cognitive architecture system planning 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 computer-implemented method for a dynamically evolving cognitive architecture system planning, the method comprising:

forming an intent based on a user input using a natural language intent interpreter, the intent being associated with an input concept object;

creating a first plan based on the intent, the first plan comprising a first input action object that transforms the input concept object into an intermediate concept object and a first output action object that transforms another intermediate concept object into an 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 first input action object and the first output action object being selected from a plurality of action objects;

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

comparing the first plan with the second plan, the first plan and the second plan each having an action object cost, an action quality cost, and a number of planned action objects;

selecting a plan from the first plan and the second plan for execution based on the comparison of the first plan to the second plan, the selected plan having at least one of a lower action object cost, a best action object quality, and a fewer number of planned action objects;

executing the selected plan, and

outputting a value associated with the output concept object of the selected plan.

2. The method of claim 1, wherein forming the intent comprises associating user data in the user input with the input concept object.

3. The method of claim 1, wherein forming the intent comprises outputting dialog that requests an additional user input.

4. The method of claim 3, wherein executing the first plan comprises using the additional user input to transform the input concept object into the output concept object.

5. The method of claim 1, wherein executing the first plan comprises using at least one of a user decision, a user preference, and user application contextual information to transform the input concept object into the output concept object.

6. A system for a dynamically evolving cognitive architecture planning, 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;

form an intent based on a user input using a natural language intent interpreter, the intent being associated with an input concept object;

create a first plan based on the intent, the first plan comprising a first input action object that transforms the input concept object into an intermediate concept object and a first output action object that transforms another intermediate concept object into an 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 first input action object and the first output action object being selected from a plurality of action objects;

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

compare the first plan with the second plan, the first plan and the second plan each having an action object cost, an action quality cost, and a number of planned action objects;

select a plan from the first plan and the second plan for execution based on the comparison of the first plan to the second plan, the selected plan having at least one of a lower action object cost, a best action object quality, and a fewer number of planned action objects;

execute the selected plan, and

output a value associated with the output concept object of the selected plan.

7. The system of claim 6, wherein forming the intent comprises associating user data in the user input with the input concept object.

8. The system of claim 6, wherein forming the intent comprises outputting dialog that requests an additional user input.

9. The system of claim 8, wherein executing the first plan comprises using the additional user input to transform the input concept object into the output concept object.

10. The system of claim 6, wherein executing the first plan comprises using at least one of a user decision, a user preference, and user application contextual information to transform the input concept object into the output concept object.

11. The system of claim 6, wherein the user input is provided via at least one of typed entry of text via a keyboard, touch gestures, mouse gestures, and speech.

12. 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:

form an intent based on a user input using a natural language intent interpreter, the intent being associated with an input concept object;

create a first plan based on the intent, the first plan comprising a first input action object that transforms the input concept object into an intermediate concept object and a first output action object that transforms another intermediate concept object into an 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 first input action object and the first output action object being selected from a plurality of action objects;

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

compare the first plan with the second plan, the first plan and the second plan each having an action object cost, an action quality cost, and a number of planned action objects;

select a plan from the first plan and the second plan for execution based on the comparison of the first plan to the second plan, the selected plan having at least one of a lower action object cost, a best action object quality, and a fewer number of planned action objects;

execute the selected plan, and

output a value associated with the output concept object of the selected plan.

13. The computer program product of claim 12, wherein forming the intent comprises associating user data in the user input with the input concept object.

14. The computer program product of claim 12, wherein forming the intent comprises outputting dialog that requests an additional user input.

15. The computer program product of claim 14, wherein executing the first plan comprises using the additional user input to transform the input concept object into the output concept object.

16. The computer program product of claim 12, wherein executing the first plan comprises using at least one of a user decision, a user preference, and user application contextual information to transform the input concept object into the output concept object.

17. The computer program product of claim 12, wherein the user input is provided via at least one of typed entry of text via a keyboard, touch gestures, mouse gestures, and speech.