Intelligent tutoring methodology using consistency rules to improve meaningful response

• US 6,540,520 B2
• Filed: 01/25/2001
• Issued: 04/01/2003
• Est. Priority Date: 01/26/2000
• Status: Expired due to Fees

• Current Assignee: Benny G. Johnson, Dale A. Holder
• Original Assignee: Benny G. Johnson, Dale A. Holder
• Inventors: Holder, Dale A., Johnson, Benny G.
• Primary Examiner(s): Cheng, Joe H.
• Assistant Examiner(s): MOSSER, KATHLEEN MICHELE
• Application Number:
  US09/769,910
• Publication Number:
  US 20010044098A1
• Time in Patent Office: 796 Days
• Field of Search: 434/118, 434/322, 434/323, 434/276, 434/298, 706/927, 706/16, 706/27, 706/47, 706/32, 706/19, 706/25
• US Class Current: 434/322
• 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
• CPC Class Codes: Y10S 706/927 Education or instruction

Abstract

A computerized method for providing a meaningful response in an intelligent tutor. The method includes the steps of receiving an input from a user solving a problem and determining if the input violates at least one consistency rule. The consistency rules are rules implemented to allow a constraint of the input to be evaluated and compared to a fundamental rule set for the problem. The fundamental rule set includes a plurality of principles that impose the constraints on a resulting solution. A student'"'"'s mistake is applied to the consistency rules to allow the artificial intelligence program to respond to the answer by either providing a necessary principle overlooked by the student, or allows the program to, at a minimum, generate feedback to say something educationally useful to the student. This can be done even when buggy rules have failed to match and provide a rationale for the mistake.

Claims

1. A computerized method for providing a meaningful response in an intelligent tutor, comprising:

receiving an input from a user solving a problem;

determining if said input violates at least one consistency rule, wherein a constraint of said input is evaluated and compared to a fundamental rule set for said problem; and

,

generating conceptual feedback to said user, wherein said feedback is generated even when said input is not anticipated by said intelligent tutor.

2. The method of claim 1, wherein said constraint is imposed on said input by at least one fundamental rule of said fundamental rule set.

3. The method of claim 1, wherein said feedback involves telling said user said input is wrong because it violates said fundamental rule.

4. A computerized method for providing a meaningful response in an intelligent tutor, comprising:

accepting a problem;

determining if said problem has a solution consistent with a plurality of applicable constraints;

receiving an input having at least one of said constraints imposed thereon from a user solving said problem;

determining if said input violates a consistency rule, wherein said at least one of said constraints is evaluated and compared to a fundamental rule set; and

,

generating conceptual feedback to said user, wherein said feedback is generated even when said input is not anticipated by said intelligent tutor.

5. The method of claim 4, wherein said feedback involves telling said user said input is wrong because said input violates at least one fundamental rule of said fundamental rule set.

6. The method of claim 4, further comprising the step of explaining inconsistencies in said problem when said problem does not have a solution consistent with all applicable constraints.

7. A computerized method for providing a meaningful response in an intelligent tutor, comprising:

receiving an input from a user solving a problem;

determining if said input violates at least one consistency rule, wherein a constraint of said input is evaluated and compared to a fundamental rule set for said problem;

generating a conflict set when said input does not violate said consistency rule, thereby forming a consistency-checked conflict set;

determining if said input is in said consistency-checked conflict set; and

,

generating feedback to said user.

8. The method of claim 7, wherein said conflict set comprises a plurality of steps produced by production rules.

9. The method of claim 8, wherein said plurality of steps are compared to said fundamental rule set.

10. The method of claim 7, wherein after the step of determining if said input is in said consistency-checked conflict set, said input is held as being premature for later feedback.

11. The method of claim 7, wherein said feedback involves telling said user said input is correct.

12. A computer-readable medium having computer executable instructions for performing a method for providing a meaningful response in an intelligent tutor, the method comprising:

receiving an input from a user solving a problem;

determining if said input violates at least one consistency rule, wherein a constraint of said input is evaluated and compared to a fundamental rule set for said problem; and

,

generating conceptual feedback to said user, wherein said feedback is generated even when said input is not anticipated by said intelligent tutor.

13. The medium of claim 12, wherein said constraint is imposed on said input by at least one fundamental rule of said fundamental rule set.

14. The medium of claim 12, wherein said feedback involves telling said user said input is wrong because it violates said fundamental rule.

15. A computer-readable medium having computer executable instructions for performing a method for providing a meaningful response in an intelligent tutor, the method comprising:

receiving an input from a user solving a problem;

determining if said input violates at least one consistency rule, wherein a constraint of said input is evaluated and compared to a fundamental rule set for said problem;

generating at least one conflict set when said input does not violate said consistency rule, thereby forming a consistency-checked conflict set;

determining if said input is in said consistency-checked conflict set; and

,

generating feedback to said user.

16. The medium of claim 15, wherein after the step of determining if said input is in said consistency-checked conflict set, said input is held as being premature for later feedback.

17. The medium of claim 15, wherein said feedback involves telling said user said input is correct.