ARTIFICIAL INTELLIGENCE SYSTEM

• US 20080235162A1
• Filed: 03/06/2008
• Published: 09/25/2008
• Est. Priority Date: 03/06/2007
• Status: Active Grant

• Current Assignee: Cognitive Code Corp.
• Original Assignee: Cognitive Code Corp.
• Inventors: Spring, Leslie
• Granted Patent: US 8,126,832 B2
• Time in Patent Office: Days
• US Class Current: 706/11
• CPC Class Codes: G06F 40/20 Natural language analysis semantic analysis of natural language G06F40/30
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding

Abstract

An artificial intelligence system and method for interpreting input from a user and generating a response to the user. The input is converted into an array of concepts which are compared to a database of interrelated concepts. A response is generated based on the concepts in the database and their relationship to the concepts in the input array. The system and method may be implemented in a number of electronic or computer devices to interact with humans or computer systems.

Claims

1. A method for a computer system to interpret an input from a user and generate a response, comprising:

receiving a user input;

converting the user input into an input array having a plurality of concepts;

determining if any of the plurality of concepts in the input array is derived from a root concept;

if any of the plurality of concepts is derived from a root concept,

replacing each such derived concept with the corresponding root concept,

identifying one or more related concepts that relate to the root concept, and

generating a multi-dimensional array based on the input array that includes the one or more related concepts;

correlating a concept in the multi-dimensional array to a first element in a database, wherein the first element in the database includes a link to a second element in the database;

determining a plurality of possible responses to the user input based on the correlation of the multi-dimensional array and the database; and

generating a response to the user input.

2. The method of claim 1 wherein the response is presented in a textual, audio, visual, or audiovisual format.

3. The method of claim 1, further comprising determining if any two or more concepts in the input array comprise a composite concept, and if so, replacing the two or more concepts with the composite concept.

4. The method of claim 1, wherein the response to the user input is generated based on a selection of one of the plurality of possible responses.

5. The method of claim 1, wherein the response to the user input is generated based on a selection of predefined output elements that correlate to the one or more concepts in the multi-dimensional array.

6. The method of claim 5, wherein the selection of the predefined output elements is based on an identification of one or more closest correlations to the one or more concepts in the multi-dimensional array.

7. The method of claim 1, wherein the multi-dimensional array comprises a plurality of tokens and wherein each token corresponds to a concept.

8. The method of claim 1, wherein generating a response comprises:

analyzing a plurality of possible responses for the response that more closely relates to the correlation than the other possible responses;

generating a set of tokens to form the response that more closely relates to the correlation.

9. The method of claim 1, wherein generating a response to the user input comprises executing at least one transaction.

10. The method of claim 9, wherein the transaction is selected from the group comprising:

execution of a script, invocation of a web service, execution of an API call, and interacting with an external system.

11. The method of claim 1, wherein the link is a pointer.

12. The method of claim 1, further comprising generating an output array to use in responding to the user input, wherein the output array is based on an analysis of a selection of predetermined output elements.

13. The method of claim 1 further comprising identifying a first token from the multi-dimensional array as data to be stored in memory for later use.

15. The method of claim 1 wherein the user is a human.

16. The method of claim 1 wherein the user is a computer.

49. The method of claim 1 wherein the user is a human.

50. The method of claim 1 wherein the user is a computer.

14. A method for a computer system to interpret an input from a user and generate a response, comprising:

receiving the user input in a first format;

converting the user input into a second format comprising a one-dimensional token array having at least one token, wherein each token corresponds to a portion of the user input;

generating a root token array, corresponding to the one-dimensional token array, having at least one root token, wherein each root token corresponds to the root from which one of the one-dimensional tokens is derived;

generating a multi-dimensional token array, based on the root token array, having a plurality of tokens, wherein each token corresponds to at least one root token; and

correlating a token in the multi-dimensional token array to a first element in a database, wherein the first element in the database includes a link to a second element in the database; and

generating a response to the user input.

17. The method of claim 14, further comprising determining if any two or more tokens in the input array comprise a composite token, and if so, replacing the two or more tokens with the composite token.

18. The method of claim 14, further comprising determining a plurality of possible responses to the user input based on the correlation of the multi-dimensional array and the database.

19. The method of claim 18, wherein the response to the user input is generated based on a selection of predetermined output elements that correlate to tokens in the multi-dimensional array.

20. The method of claim 19 wherein generating a response further comprises:

analyzing a plurality of possible responses for the response that more closely relates to the correlation than the other possible responses;

selecting one or more predetermined output elements to form the response that more closely relate to the correlation.

21. The method of claim 19, wherein the selection of the predetermined output elements is based on an identification of one or more closest correlations to the tokens in the multi-dimensional array.

22. The method of claim 14, wherein the multi-dimensional token array comprises a plurality of tokens, wherein each token corresponds to a concept.

23. The method of claim 14, wherein generating a response comprises:

analyzing a plurality of possible responses for the response that more closely relates to the correlation than the other possible responses;

generating a set of tokens to form the response that more closely relates to the correlation.

24. The method of claim 14, wherein generating a response to the user comprises executing at least one transaction.

25. The method of claim 24, wherein the transaction is selected from the group comprising:

execution of a script, invocation of a web service, execution of an API call, and interacting with an external system.

26. The method of claim 14, wherein the link is a pointer.

27. The method of claim 14, further comprising generating an output array to use in responding to the user input, wherein the output array is based on an analysis of a selection of predetermined output elements.

28. The method of claim 14, wherein each token is an integer.

29. The method of claim 14, further comprising assigning each token a corresponding integer.

30. The method of claim 14, wherein each token corresponds to a concept.

31. The method of claim 14 wherein the response is presented in a textual, audio, visual, or audiovisual format.

32. The method of claim 14 wherein the user is a human.

33. The method of claim 14 wherein the user is a computer.

34. A method for a computer system to interpret an input from a user and generate a response, comprising:

receiving the user input in a first format;

converting the user input into a second format comprising a one-dimensional token array having at least one token, wherein each token corresponds to a portion of the user input;

generating a root token array, corresponding to the one-dimensional token array, having at least one root token, wherein each root token corresponds to the root from which one of the one-dimensional tokens is derived;

generating a multi-dimensional token array, based on the root token array, having a plurality of tokens, wherein each token corresponds to at least one root token;

determining a match between the multi-dimensional token array and the one-dimensional token array; and

generating a response to the user input using a combination of tokens.

35-48. -48. (canceled)

51-108. -108. (canceled)