SYSTEM AND METHOD FOR A COMPUTERIZED LEARNING SYSTEM

• US 20120196261A1
• Filed: 01/31/2011
• Published: 08/02/2012
• Est. Priority Date: 01/31/2011
• Status: Active Grant

• Current Assignee: Fast Track Technologies, Inc.
• Original Assignee: Fast Track Technologies, Inc.
• Inventors: Kim, Surrey, Kim, Borrey, Kouritzin, Michael Alexander, Rieger, Garret
• Granted Patent: US 8,761,658 B2
• Time in Patent Office: Days
• US Class Current: 434/322
• CPC Class Codes: G09B 5/062 Combinations of audio and printed presentations, e.g. magnetically striped cards, talking books, magnetic tapes with printed texts thereon
• CPC Class Codes: G09B 7/02 of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student

Abstract

There is a computerized learning system and method which updates a conditional estimate of a user signal representing a characteristic of a user based on observations including observations of user behavior. The conditional estimate may be updated using a non-linear filter. Learning tools may be generated using the computerized learning system based on distributions of desired characteristics of the learning tools. The learning tools may include educational items and assessment items. The learning tools may be requested by a user or automatically generated based on estimates of the user'"'"'s characteristics. Permissions may be associated with the learning tools which may only allow delegation of permissions to other users of lower levels. The learning system includes a method for annotating learning tools and publishing those annotations. In-line text editors of scientific text allow users to edit and revised previously published documents.

Claims

1. A method for updating and using a conditional estimate of a signal in a computerized learning system, comprising:

obtaining observations of user behavior through user interaction with the computerized learning system;

updating a conditional estimate of a user signal representing a characteristic of a user based on the observations; and

using the conditional estimate of the user signal to generate at least one of the following;

(a) a learning tool, and

(b) a report.

2. The method of claim 1 in which the method further comprises updating a conditional estimate of a learning tool signal representing a characteristic of the or a second learning tool based on the observations and based on the estimate of the user signal.

3. The method of claim 2 in which the user signal and the learning tool signal are modeled using a combined signal.

4. The method of claim 1 in which updating the conditional estimate of the user signal comprises applying a non-linear particle filter.

5. The method of claim 1 in which updating the conditional estimate of the user signal comprises applying a non-linear discrete filter.

6. The method of claim 1 further comprises:

initializing an initial conditional estimate;

updating the conditional estimate based on received observations; and

reporting on a state of the signal.

7. The method of claim 6 in which the state of the signal is a present state of the signal.

8. The method of claim 6 in which the state of the signal is a future state of the signal.

9. The method of claim 6 in which the state of the signal is a past state of the signal.

10. The method of claim 1 in which the conditional estimate of the signal is used to generate a learning tool and in which the characteristic of the user is a learning characteristic.

11. The method of claim 10 in which the learning tool is selected based on deficiencies in the learning characteristic of the user and in which the learning tool includes content corresponding to the deficiencies of the learning characteristic of the user.

12. The method of claim 10 in which the learning tool is an assessment item, and the assessment item is selected based on proficiencies of the learning characteristic of the user.

13. The method of claim 2 in which the learning tool signal representing a characteristic of the or a second learning tool represents a difficulty rating of the or a second learning item.

14. The method of claim 1 further comprising using the conditional estimate of the user signal to generate a report, in which the characteristic of the user further comprises a conditional estimate of the identity of the user, and in which generating the report further comprises generating a notice if a comparison between the conditional estimate of the identity of the user for a current session and the conditional estimate of the identity of the user for a previous session does not exceed a threshold.

15. The method of claim 14 in which the current session is an exam writing session and in which the notice further comprises a message sent to a proctor of the exam writing session.

16. The method of claim 1 in which the conditional estimate of the user signal is used to generate a report and in which generating the report further comprises generating a recommendation for the user to communicate with a second user.

17. The method of claim 16 in which the second user is a tutor.

18. The method of claim 1 in which the conditional estimate of the user signal is used to generate a report and in which the report further comprises a recommendation for the user to access a learning resource.

19. The method of claim 1 in which the conditional estimate of the user signal is used to generate a report and in which the report further comprises a grading report for the user related to a graded content item.

20. The method of claim 19 in which obtaining observations further comprises identifying incorrect answers given in response to a graded content item that demonstrate an understanding of a learning objective of the graded content item and in which the grading report includes an award of partial marks for the demonstrated understanding of the learning objective of the graded content item.

21. The method of claim 2 in which the user interacted with the or a second learning tool at a previous time tk, and the method further comprising updating the conditional estimate of the learning tool signal using historical smoothing of user signal at the time tk.

27. The method of claim 1 further comprises:

initializing an initial conditional estimate;

updating the conditional estimate based on received observations; and

reporting on a state of the signal.

22-23. -23. (canceled)

24. A method for updating and using a conditional estimate of a signal in a computerized learning system, comprising:

obtaining observations through user interaction with the computerized learning system;

updating a conditional estimate of a signal representing at least one of a characteristic of a learning tool and a characteristic of a user based on the observations using a non-linear filter; and

using the conditional estimate of the signal to generate at least one of the following;

(a) the or a second learning tool, and

(b) a report.

25. The method of claim 24 in which using a filter comprises applying a non-linear particle filter.

26. The method of claim 24 in which using a filter further comprises applying a non-linear discrete filter.

28. The method of claim 24 in which the state of the signal is a present state or a future state of the signal.

29. The method of claim 24 in which the state of the signal is a past state of the signal.

30. The method of claim 24 in which the conditional estimate of the signal is used to generate the or a second learning tool and in which the characteristic of the user is a learning characteristic.

31. The method of claim 30 in which the or a second learning tool is selected to improve the learning characteristic of the user.

32. The method of claim 31 in which the selected learning tool is a remedial learning tool.

33. The method of claim 32 in which the remedial learning tool is selected based on deficiencies in the learning characteristic of the user and in which the remedial learning tool includes content corresponding to the deficiencies of the learning characteristic of the user.

34. The method of claim 24 in which the signal represents a characteristic of the learning tool and the characteristic of the learning tool is a difficulty rating of the or a second learning item.

35. The method of claim 24 further comprising using the conditional estimate of the signal to generate a report based on the conditional estimate of the signal, in which the characteristic of the user further comprises a conditional estimate of the identity of the user, and in which generating the report further comprises generating a notice that the conditional estimate of the identity of the user for a current session does not correspond to a conditional estimate of the identity of the user for a previous session.

36. The method of claim 35 in which the current session is an exam writing session and in which the notice further comprises a message sent to a proctor of the exam writing session.

37. The method of claim 24 in which the conditional estimate of the signal is used to generate a report and in which generating the report further comprises generating a recommendation for the user to communicate with a second user.

38. The method of claim 37 in which the second user is a tutor.

39. The method of claim 24 in which the conditional estimate of the signal is used to generate a report and in which the report further comprises a recommendation for the user to access a learning resource.

40. The method of claim 24 in which the conditional estimate of the user signal is used to generate a report and in which the report further comprises a grading report for the user related to a graded content item.

41. The method of claim 40 in which obtaining observations of a signal representing a characteristic of a user further comprises identifying incorrect answers given in response to a graded content item that demonstrate an understanding of a learning objective of the graded content item and in which the grading report includes an award of partial marks for the demonstrated understanding of the learning objective of the graded content item.

42. The method of claim 24 in which the signal the user interacted with the or a second learning tool at a previous time tk, and the method further comprising updating the conditional estimate of the learning tool signal using historical smoothing of user signal at the time tk.

45. The method of claim 24 in which the signal further comprising:

storing a plurality of the characteristic of a user in a computerized learning system; and

assigning the plurality of the user a probabilistic distribution.

43-44. -44. (canceled)

46. A method of generating learning tools within a computerized learning system, comprising:

storing a plurality of learning tools within a database, each one of the plurality of learning tools being associated with a plurality of characteristics;

receiving a request in the form of a distribution of desired characteristics; and

generating a subset of the plurality of learning tools having a plurality of characteristics satisfying the requested distribution of desired characteristics.

47. The method of claim 46 further comprising transmitting the generated subset of the plurality of learning tools to at least one user.

48. The method of claim 46 further comprising:

obtaining observations through user interaction with the computerized learning system;

updating a conditional estimate of a user signal representing a characteristic of a learning tool and a characteristic of a user based on the observations; and

in which generating a subset of the plurality of learning tools having a plurality of characteristics satisfying the requested distribution of desired character further comprises using the conditional estimate of the signal to generate the plurality of learning tools.

49. The method of claim 46 in which the distribution of desired characteristics are selected by a user.

50. The method of claim 48 in which generating a subset of the plurality of learning tools having a plurality of characteristics satisfying the distribution of desired characteristics is repeated for a plurality of users and in which the generated subsets of the plurality of learning tools for each of the plurality of users are unique.

51. The method of claim 50 in which each of the plurality of learning tools are generated after the occurrence of an event.

52. The method of claim 51 where the event is triggered by one of the plurality of users selecting an option.

53. The method of claim 52 in which selecting an option comprises clicking a labelled button on a display.

54. The method of claim 51 in which each of the plurality of learning tools are generated simultaneously for each user.

55. The method of claim 48 in which a user selects a locked subset of the subset of the plurality of learning tools to be included within each of the subsets of the plurality of learning tools being generated for each of the plurality of users.

56. The method of claim 46 in which the subset of the plurality of learning tools are generated through a request by an individual user and the method further comprising distributing the plurality of generated learning tools to a plurality of additional users.

57. The method of claim 46 in which generating the subset of the plurality of learning tools satisfying the distribution of desired characteristics further comprises re-publishing a pre-existing subset of the plurality of learning tools which satisfies the distribution of desired characteristics.

58. The method of claim 46 in which the requested distribution of desired characteristics comprises scheduling characteristics.

59. The method of claim 46 in which the generated subset of the plurality of learning tools comprises courseware.

60. The method of claim 59 in which the courseware comprises a collection of both educational items and assessment items.

61. The method of claim 46 in which a previously generated plurality of learning tools has been generated before the at least one of the learning tool and the report is generated, and in which the distribution of desired characteristics is selected based on the previously generated plurality of learning tools.

62. The method of claim 46 in which the distribution of desired characteristics is selected based on a normalized filter variance distribution.

63. The method of claim 46 in which the distribution of desired characteristics is selected based on a determined probability of causing a desired action based on a filter estimate and model.

64. The method of claim 46 in which the distribution of desired characteristics is selected based on an optimal action strategy model.

65. A method of generating learning tools for a user within a computerized learning system, comprising:

submitting a request for a learning tool satisfying a distribution of desired characteristics; and

receiving the learning tool from a server, the learning tool satisfying a distribution of desired characteristics for the learning tool.

66-67. -67. (canceled)

68. A method for assigning rights associated with learning tools in a computerized learning system, comprising:

assigning for an action corresponding to a learning tool associated with a user a permission object, wherein the permission object is capable of being assigned each one of the following permissions;

a super grant permission, wherein the user is capable of performing the action and the user is capable of delegating any level of permission related to the action to a subsequent user;

a grant permission, wherein the user is capable of performing the action and the user is capable of delegating a yes permission related to the action to the subsequent user;

the yes permission, wherein the user is capable of performing the action and the user is unable to delegate any level of permission related to the action to the subsequent user; and

a no permission, wherein the user cannot perform the action and the user is unable to delegate any level of permission related to the action to the subsequent user.

69-70. -70. (canceled)

71. A method of adapting an educational and assessment system for a user, comprising:

storing educational items and assessment items in a database;

repeating for a plurality of users, a plurality of assessment items and a plurality of educational items;

updating a characteristic of a user of the plurality of users and a characteristic of an assessment item of the plurality of assessment items based on interaction between the user and assessment item;

updating the characteristic of the user of a plurality of users and a characteristic of a first educational item based on interaction between the user and the first educational item; and

presenting at least one of an educational item of the plurality of educational items, an assessment item of the plurality of assessment items to a selected user of the plurality of users to generate a desired effect on the user based on the characteristic of the user.

72-73. -73. (canceled)

74. A method of integrating scientific symbols in-line with text in content within a computerized learning system, comprising:

switching from text mode into scientific mode;

converting plain-language text input into scientific code;

displaying a graphical representation of the scientific code in-line with the text; and

adaptively predicting plain-language text input using context-based prediction.

75. The method of claim 74 further comprising generating a message when the plain-language input does not correlate with known symbols within the scientific code.

76. The method of claim 74 further comprising adaptively predicting solutions to equalities in a scientific equation based on the plain-language text input in scientific mode.

77. A method for annotating learning tools within a computerized learning system, comprising:

storing a first user'"'"'s annotation of a learning tool in the computerized learning system, the learning tool having a plurality of characteristics;

permitting at least a second user of a plurality of users to have access to the annotated learning tool; and

creating a learning tool object corresponding to the annotated learning tool, the annotated learning tool having a plurality of characteristics; and

setting a subset of the plurality of characteristics of the annotated learning tool to be the same as a corresponding subsets of the plurality of characteristics of the learning tool.