System and method for dynamic knowledge construction

• US 7,389,208 B1
• Filed: 09/08/2000
• Issued: 06/17/2008
• Est. Priority Date: 06/30/2000
• Status: Expired due to Fees

• Current Assignee: Accord Solutions, Inc.
• Original Assignee: Accord Solutions, Inc.
• Inventors: Solinsky, James C.
• Primary Examiner(s): Cabrera; Zoila
• Assistant Examiner(s): Ochoa; Juan Carlos
• Application Number:
  US09/658,275
• Time in Patent Office: 2,839 Days
• Field of Search: 706/17, 706/15, 706/33, 706/41, 706/44, 703/2, 382/115, 382/156
• US Class Current: 703/2
• CPC Class Codes: G06F 18/213 Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
• CPC Class Codes: G06N 3/02 Neural networks
• CPC Class Codes: G06V 10/7715 Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods

Abstract

A system and method responsive to input stimuli is provided by incorporating a computer software program, hardware processing engine, or a specialized ASIC chip processor apparatus to capture concurrent inputs that are responsive to training stimulation, store a model representing a synthesis of the captured inputs, and use the stored model to generate outputs in response to real-world stimulation. Human user forced-choice approval/disapproval generated descriptions and decisions may be dynamically mapped with conventionally presented information and sensor and control data. The model mapping is stored into and out of a conventional mass storage device, such as is used in a relational database for use in generating a response to the stimuli. By accessing commonly stored mappings, the system can be incorporated into a mixture of multiple domains and disciplines of users and can create a common understanding of knowledge and design concept contained within it through mutual interaction, and subsequent automatic modifications to a common relational database. The system and method is applicable to conventional storage and presentation devices, making it easily incorporated into a variety of commercial products, utilizing current commercial human-machine interfaces (e.g. Human-Machine Interface graphical user interface, or Graphical User Interface) and current mass storage devices. The system uses N-dimensional descriptions of observations and concepts in an infinitely expandable space, embracing elements of human thought. This allows the user to tailor this system to control operation of automated devices and appliances to reflect the individual'"'"'s wishes and desires as a dynamic representation and mapping of user descriptions and decisions with information, sensor data, and device controls.

Claims

1. A method of generating outputs in response to real world stimulation comprising:

capturing two or more simultaneous user inputs that are responsive to training stimulation;

synthesizing the captured user inputs;

generating a user memory model representation of the synthesized user inputs, the model comprising objects and object links in a partially orthogonal N-dimensional object space;

storing the generated model; and

using the stored model to generate signals for controlling an effector or for output by a user interface in response to real-world stimulation.

2. The method according to claim 1, further comprising:

using a forced choice interaction to generate one or more additional user inputs;

capturing the additional user inputs; and

incorporating the additional user inputs into the model.

3. The method according to claim 1, wherein the model comprises a worldline of linked object diagram exemplars.

4. The method according to claim 1, wherein

the real world stimulation comprises simultaneous user inputs that are compared to the stored model, and

the output signals are based on the results of the comparison.

5. The method according to claim 1, wherein the method is performed at least partly in accordance with computer-executable instructions stored on a computer-readable medium.

6. The method according to claim 1, wherein the method is performed at least partly by a hardware processing engine.

7. The method according to claim 1, wherein the method is performed by at least partly by an application specific integrated circuit.

8. The method according to claim 1, wherein the method is performed at least partly by a netlist integrated into other integrated circuits.

9. A method of generating outputs in response to control command stimulation comprising:

capturing two or more simultaneous user inputs that are responsive to training stimulation;

synthesizing the captured user inputs;

generating a user memory model representation of the synthesized user inputs, the model comprising objects and object links in a partially orthogonal N-dimensional object space;

storing the generated model; and

using the stored model to generate signals for controlling an effector or for output by a user interface in response to control command stimulation.

10. The method according to claim 9, further comprising:

using forced choice interaction to generate one or more additional users inputs;

capturing the additional user inputs; and

incorporating the additional user inputs into the model.

11. The method according to claim 9, wherein the model comprises a worldline of linked object diagram exemplars.

12. The method according to claim 9, wherein

the real world stimulation comprises simultaneous user inputs that are compared to the stored model, and

the output signals are based on the results of the comparison.

13. The method according to claim 9, wherein the method is performed at least partly in accordance with computer-executable instructions stored on a computer-readable medium.

14. The method according to claim 9, wherein the method is performed at least partly by a hardware processing engine.

15. The method according to claim 9, wherein the method is performed at least partly by an application specific integrated circuit.

16. The method according to claim 9, wherein the method is performed at least partly by a netlist integrated into other integrated circuits.

17. A system for generating outputs in response to real world stimulation comprising:

input capture circuitry that captures two or more simultaneous user inputs that are responsive to training stimulation;

processing circuitry for synthesizing the captured user inputs and generating a user memory model representation of the synthesized user inputs, the model comprising objects and object links in a partially orthogonal N-dimensional object space; and

a memory that stores the generated model; and

an output generator that uses the stored model to generate signals for controlling an effector or for output by a user interface in response to real world stimulation.

18. The system according to claim 17, wherein the input capture circuitry further captures one or more additional user inputs generated from a forced choice interaction and the additional user inputs are incorporated into the model.

19. The system according to claim 17, wherein the model comprises a worldline of linked object diagram exemplars.

20. The system according to claim 17, wherein the real world stimulation comprises simultaneous user inputs that are compared to the stored model, and the output signals are based on the results of the comparison.

21. The system according to claim 17, wherein at least part of said system is implemented in a computer software program.

22. The system according to claim 17, wherein at least part of said system is implemented as a hardware processing engine.

23. The system according to claim 17, wherein at least part of said system is implemented as an application specific integrated circuit.

24. The system according to claim 17, wherein at least part of said system is implemented as a net list integrated into other integrated circuits.

25. A system for generating outputs in response to control command stimulation comprising:

input capture circuitry that captures two or more simultaneous user inputs that are responsive to training stimulation;

processing circuitry for synthesizing the captured user inputs and generating a user memory model representation of the synthesized user inputs, the model comprising objects and object links in a partially orthogonal N-dimensional object space; and

a memory that stores the generated model; and

an output generator that uses the stored model to generate signals for controlling an effector or for output by a user interface in response to control command stimulation.

26. The system according to claim 25, wherein the input capture circuitry further captures one or more additional inputs generated from a forced choice interaction and the additional inputs are incorporated into the model.

27. The system according to claim 25, wherein the model comprises a worldline of linked object diagram exemplars.

28. The system according to claim 25, wherein the real world stimulation comprises simultaneous inputs that are compared to the stored model, and the output signals are based on the results of the comparison.

29. The system according to claim 25, wherein at least part of said system is implemented in a computer software program.

30. The system according to claim 25, wherein at least part of said system is implemented as a hardware processing engine.

31. The system according to claim 25, wherein at least part of said system is implemented as an application specific integrated circuit.

32. The system according to claim 25, wherein at least part of said system is implemented as a net list integrated into other integrated circuits.

33. A method of generating outputs in response to real world stimulation comprising:

capturing two or more simultaneous user inputs that are responsive to training stimulation;

synthesizing the captured user inputs through a dynamic, user memory model-based response generation from the captured user inputs with correlated congruence to two or more data input channels;

storing the model representation of the synthesis generation as mapped into a partially orthogonal N-dimensional representation; and

using the stored model to generate signals for controlling an effector or for output by a user interface in response to real world stimulation through temporally sensitive similarity matching.

34. The method according to claim 33, further comprising:

using a forced choice interaction of dynamic temporal events to generate one or more additional simultaneous user inputs, which are physically/mentally linked pattern responses;

capturing the additional user inputs; and

incorporating the additional user inputs into the model.

35. A method of generating outputs in response to real world stimulation comprising:

receiving two or more simultaneous inputs supplied by a user in response to training stimulation;

generating a model comprising objects and object links in a partially orthogonal N-dimensional object space, the model representing a synthesis of the simultaneous user inputs;

mapping the N-dimensional object space to one or more M-dimensional sub-spaces to compare the model representing the synthesis of the simultaneous user inputs to subsequently received simultaneous user inputs; and

generating signals for controlling an effector or for output by a user interface in response to the comparing.

36. The method according to claim 35, wherein N>

3.

37. The method according to claim 35, wherein the N-dimensional space is mapped to the one or more M-dimensional sub-spaces using subspace projection operators.

38. The method according to claim 37, wherein the subspace projection operators project densities to the M-dimensional space.

39. The method according to claim 38, wherein the subspace projection operators project the densities onto axes of the object space model.

40. The method according to claim 38, wherein the subspace projection operators include subspace projection operators for obtaining attribute densities.

41. The method according to claim 38, wherein the subspace projection operators include subspace projection operators for obtaining object link densities.

42. The method according to claim 35, wherein the object links comprise a worldline connecting the objects.

43. The method according to claim 35, wherein the subsequently received simultaneous user inputs are provided in response to a forced choice interaction with the user.

44. The method according to claim 35, wherein the method is performed at least partly in accordance with computer-executable instructions stored on a storage medium.

45. The method according to claim 35, wherein the method is performed at least partly by a hardware processing engine.

46. The method according to claim 35, wherein the method is performed at least partly by an application specific integrated circuit.

47. The method according to claim 35, wherein the method is performed at least partly by a netlist integrated into other integrated circuits.

48. The method according to claim 35, wherein the output signals comprise display signals.

49. The method according to claim 35, wherein the output signals comprise control signals.

50. A method of generating outputs in response to real world stimulation comprising:

receiving two or more simultaneous inputs supplied by a user in response to training stimulation;

generating a model comprising objects and object links in an N-dimensional object space, the model representing a synthesis of the simultaneous user inputs, wherein the objects include objects of two or more different object classes;

mapping the N-dimensional object space to one or more M-dimensional sub-spaces to compare the model representing the synthesis of the simultaneous user inputs to subsequently received simultaneous user inputs; and

generating signals for controlling an effector or for output by a user interface in response to the comparing.

51. The method according to claim 50, wherein the object links comprise worldlines each connecting the objects of a respective one of the different classes.

52. The method according to claim 50, wherein the different object classes correspond to different user training sessions.

53. A system for generating outputs in response to real world stimulation comprising:

inputs for receiving two or more simultaneous inputs supplied by a user in response to training stimulation;

storage for storing a model comprising objects and object links in a partially orthogonal N-dimensional object space, the model representing a synthesis of the simultaneous user inputs;

a processing system for mapping the N-dimensional object space to one or more M-dimensional sub-spaces to compare the model representing the synthesis of the simultaneous user inputs to subsequently received simultaneous user inputs; and

outputs for outputting signals for controlling an effector or for output by a user interface based on the comparing.

54. The system according to claim 53, wherein the output signals comprise display signals.

55. The system according to claim 53, wherein the output signals comprise control signals.

56. A system for generating outputs in response to real world stimulation comprising:

inputs for receiving two or more simultaneous inputs supplied by a user in response to training stimulation;

storage for storing a model comprising objects and object links in an N-dimensional object space, the model representing a synthesis of the simultaneous user inputs, wherein the objects include objects of two or more different object classes;

a processing system for mapping the N-dimensional object space to one or more M-dimensional sub-spaces to compare the model representing the synthesis of the simultaneous user inputs to subsequently received simultaneous user inputs; and

outputs for outputting signals for controlling an effector or for output by a user interface based on the comparing.

57. The system according to claim 56, wherein the output signals comprise display signals.

58. The system according to claim 56, wherein the output signals comprise control signals.

59. A method of generating outputs in response to real world stimulation comprising:

capturing two or more simultaneous user inputs that are responsive to training stimulation;

synthesizing the captured user inputs;

generating a user memory model representation of the synthesized user inputs, the model comprising objects and object links in a partially orthogonal N-dimensional object space;

storing the generated model; and

using the stored model to generate display signals in response to real-world stimulation.