Human-machine interactions

• US 7,526,465 B1
• Filed: 03/18/2005
• Issued: 04/28/2009
• Est. Priority Date: 03/18/2004
• Status: Active Grant

• Current Assignee: National Technology & Engineering Solutions Of Sandia LLC (Honeywell International Inc.)
• Original Assignee: Sandia Corporation (Martin Marietta Corporation)
• Inventors: Brannon, Nathan G., Abbott, Robert G., Speed, Ann E., Bernard, Michael L., Forsythe, J. Chris, Xavier, Patrick G.
• Primary Examiner(s): STARKS, WILBERT L
• Application Number:
  US11/083,428
• Time in Patent Office: 1,502 Days
• Field of Search: 706/55, 706/46, 706/45, 717/100, 717/141
• US Class Current: 706/55
• CPC Class Codes: G06N 3/004 Artificial life, i.e. computing arrangements simulating life

Abstract

Digital technology utilizing a cognitive model based on human naturalistic decision-making processes, including pattern recognition and episodic memory, can reduce the dependency of human-machine interactions on the abilities of a human user and can enable a machine to more closely emulate human-like responses. Such a cognitive model can enable digital technology to use cognitive capacities fundamental to human-like communication and cooperation to interact with humans.

Claims

1. An apparatus for enhancing human task performance, the apparatus comprising:

a first input for obtaining a first set of data descriptive of a current environment;

a first modeler for creating a first representation of the current environment based on the first set of data;

a second input for obtaining a second set of data descriptive of at least one action of a user;

a second modeler for creating a second representation of the current environment including the at least one action of the user based on the second set of data;

a detector for detecting at least one difference between the first representation and the second representation; and

an interface for providing the at least one difference to the user.

2. The apparatus of claim 1, wherein said first modeler includes:

a library for storing a set of information representative or environments previously encountered by the apparatus;

an episodic memory unit for providing a history of previously performed actions taken in environments previously encountered by the apparatus, said episodic memory unit using the set of information from the library to create the history;

a pattern recognizer for recognizing a pattern between the current environment and the history; and

a semantic unit for receiving the first set of data and preparing the first set of data for pattern recognition by said pattern recognizer.

3. The apparatus of claim 2, wherein said semantic unit includes a network of associations.

4. The apparatus of claim 3, wherein the network of associations is a network of associations between a set of concepts.

5. The apparatus of claim 3 wherein the network of associations is a network of associations between a set of cues.

6. The apparatus of claim 1 wherein said second modeler includes:

a library for storing a set of information representative of environments previously encountered by the apparatus;

a pattern recognizer for recognizing a pattern between the second set of data and the second set of information; and

a semantic unit for receiving the second set of data and preparing the second set of data for pattern recognition by said pattern recognizer.

7. The apparatus of claim 6, wherein said semantic unit includes a network of associations.

8. The apparatus of claim 7, wherein the network of associations is a network of associations between a set of concepts.

9. The apparatus of claim 7 wherein the network of associations is a network of associations between a set of cues.

10. The apparatus of claim 1 wherein said detector includes a comparator for comparing the first representation and the second representation.

11. A method, practiced on an electronic device, for enhancing human task performance, the method comprising:

obtaining a first set of data descriptive of a current environment;

creating a first representation of the current environment based on the first set of data;

obtaining a second set of data descriptive of at least one action of a user;

creating a second representation of the current environment including the at least one action of the user based on the second set of data;

detecting at least one difference between the first representation and the second representation; and

providing the at least one difference to the user.

12. The method of claim 11, wherein said first creating step includes:

accessing a set of information representative of environments previously encountered;

creating, based on the set of information, a history of previously performed actions taken in environments previously encountered;

preparing the first set of data for pattern recognition; and

recognizing a pattern between the first set of data and the history.

13. The method of claim 12, wherein said recognizing step includes developing a network of associations.

14. The method of claim 13, wherein said developing step includes developing a network of associations between a set of concepts.

15. The method of claim 13 wherein said developing step includes developing a network of associations between a set of cues.

16. The method of claim 11 wherein said second creating step includes:

storing a set of information representative of environments previously encountered by the apparatus;

preparing the second set of data for pattern recognition; and

recognizing a pattern between the second set of data and the set of information.

17. The method of claim 16, wherein said recognizing step includes developing a network of associations.

18. The method of claim 17, wherein said developing step includes developing a network of associations between a set of concepts.

19. The method of claim 17 wherein said developing step includes developing a network of associations between a set of cues.

20. The method of claim 11 wherein said detecting step includes comparing the first representation and the second representation.