Artificial intelligence system

• US 8,504,508 B2
• Filed: 02/27/2012
• Issued: 08/06/2013
• Est. Priority Date: 03/06/2007
• Status: Active Grant

• Current Assignee: Cognitive Code Corp.
• Original Assignee: Cognitive Code Corp.
• Inventors: Spring, Leslie
• Primary Examiner(s): Gaffin, Jeffrey A
• Assistant Examiner(s): BROWN JR, NATHAN H
• Application Number:
  US13/405,966
• Publication Number:
  US 20120158158A1
• Time in Patent Office: 526 Days
• Field of Search: 706/46
• US Class Current: 706/46
• 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 generating a response to a user input to a microprocessor based device, comprising:

generating sequential conceptual tokens from the user input;

using the sequential conceptual tokens to extract conceptual sub-strings from a database;

replacing sequential conceptual tokens with corresponding stored values;

assembling an output string using relationships to the stored values;

presenting the output string to the user; and

storing the output string in memory.

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

3. The method of claim 1 wherein the output string is stored as a log file or as results to be stored in a database.

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

5. The method of claim 4 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.

6. A method for dynamically constructing an output, comprising:

sampling a source of data;

identifying a set of tokens preferred for the output;

selecting a first token based on predetermined criteria including a set of selectable data and based on the set of tokens preferred for the output;

analyzing the source of data, using the first token, to determine a first subset of data to be used for selection of a second token;

selecting the second token based on the first token, the first subset of data, and the tokens remaining from the set of tokens preferred for the output;

analyzing the source of data, using the first token and the second token, to determine a second subset of data to be used for selection of a third token;

selecting a third token based on the first token, the second token, the second subset of data, and the tokens remaining from the set of tokens preferred for the output; and

generating the output using the first token, the second token and the third token.

7. The method of claim 6 wherein the set of tokens preferred for the output are required for the output.

8. The method of claim 6 wherein the set of selectable data is a limited set of data.

9. The method of claim 6 wherein the first subset of data and the second subset of data are at least one of partially non-overlapping and partially overlapping.

10. The method of claim 6 wherein the output is a first output and further comprising repeating the steps of claim 6 to generate a second output;

comparing the first output to the second output; and

selecting the first output or the second output based on which of the first output and the second output provides a better response to the user input.

11. The method of claim 6 wherein generating the output further comprises:

determining whether any combination of two or more tokens corresponds to a new token stored in a database;

if a combination of two or more tokens corresponds to a new token stored in a database, then substituting the combination of tokens for the new token; and

if the new token corresponds to a plurality of tokens in the database, replacing the new token with the plurality of tokens.

12. The method of claim 6 wherein generating the output further comprises:

determining a possible replacement token that corresponds to one of the tokens; and

selecting between the possible replacement token and the old token based on predetermined criteria.

13. The method of claim 6 wherein the output is in the form of speech generation, text output, graphical displays, audio output, or execution of a program.

14. A method for automatically generating an output to a user input, comprising:

receiving a user input;

transforming the user input into tokenized conceptual data;

annotating the tokenized conceptual data;

filtering annotated tokenized conceptual data to extract core conceptual data;

pushing at least one of filtered annotated tokenized conceptual data and non-filtered annotated tokenized conceptual data onto a stack;

statistically sampling the stack of annotated tokenized conceptual data for relevant conceptual tokens, giving more recent additions priority;

filtering selected conceptual tokens; and

generating an output based on the filtered selected conceptual tokens.

15. The method of claim 14 implemented as at least one of a user interface to a device and a customer service system.

16. The method of claim 15 wherein the device is at least one of a camera, telephone, personal digital assistant, toy, or automobile.

17. The method of claim 16, wherein the toy is a doll.

18. The method of claim 15 wherein the customer service system is at least one of a telephone call center or a webpage.

19. The method of claim 14 implemented in a plurality of devices.

20. The method of claim 19 wherein the plurality of devices communicate with each other.

21. The method of claim 20 wherein the plurality of devices comprise toys.

22. The method of claim 14 implemented on a primary device which directs the actions of a plurality of secondary devices.

23. The method of claim 22 wherein the secondary devices are toys.

24. The method of claim 14 wherein the output is an audiovisual avatar in a computer environment.

25. The method of claim 24 wherein the computer environment is at least one of a customer service web page or a game.

26. The method of claim 14 wherein the output is generated in at least one of an audio format for the visually impaired or a visual format for the hearing impaired.

27. The method of claim 15 wherein the user interface is a universal interface.

28. The method of claim 27 wherein the universal interface allows a user to interact with an operating system.