Adaptive testing and training tool

• US 20040041829A1
• Filed: 08/28/2002
• Published: 03/04/2004
• Est. Priority Date: 08/28/2002
• Status: Active Grant

• Current Assignee: Kelly Properties Incorporated (Kelly Services Incorporated)
• Original Assignee: Kelly Properties Incorporated (Kelly Services Incorporated)
• Inventors: Carter, Diane, Moore, Gilbert, Cahill, Francis, Cleveland, J. Wesley, Vulfs, Vilnis E., Heinz, William
• Granted Patent: US 6,925,601 B2
• Time in Patent Office: Days
• US Class Current: 345/707
• 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: G09B 7/04 characterised by modifying the teaching programme in response to a wrong answer, e.g. repeating the question, supplying a further explanation

Abstract

An adaptive training system for use with an adaptive testing tool includes a user interface receptive of a field of application selection from a user. A plurality of task items are stored in a data store. The plurality of task items are organized by field of application and ranked by difficulty level. An adaptive item selector selects unfamiliar task items as training items based on the selected field of application and a user ability. These training items range in order of difficulty from items slightly below a user'"'"'s ability to items sufficiently far above that level to allow for learning effects. The user ability is a function of previous user performance on an adaptive test in the selected field of application. The main purpose of the adaptive item selector is to ensure that training items are neither too easy nor too difficult for a person.

Claims

1. An adaptive training system for use with an adaptive testing tool, the system comprising:

a user interface receptive of a field of application selection from a user;

a plurality of task items stored in a data store, the plurality of task items organized by field of application and ranked by difficulty level; and

an item selector operable to select an unfamiliar task item as a training task item based on the selected field of application and a user ability, wherein the user ability is a function of previous user performance relating to task items of the selected field of application.

2. The system of claim 1 comprising an ability evaluation module operable to determine a level of user ability as a function of previous user performance relating to a plurality of task items, wherein the plurality of task items relate to the selected field of application.

3. The system of claim 2, wherein said ability evaluation module is operable to compute the user ability as a sum of average difficulty level of task items previously performed correctly by the user and a natural log of a quotient of a number of task items performed correctly by the user and a number of task items performed incorrectly by the user.

4. The system of claim 1, wherein said item selector is operable to select an easier, unfamiliar task item having a difficulty level below the user ability, and a more difficult, unfamiliar task item having a difficulty level above the user ability.

5. The system of claim 1, wherein difficulty level of task items is defined in terms of logits, and wherein said item selector is operable to select unfamiliar task items in a range substantially defined as one logit below the user ability to two and one-half logits above the user ability.

6. The system of claim 1, wherein said item selector is operable to select a missed task item as a training task item.

7. The system of claim 1, wherein at least one cut point is defined in terms of user ability as an indicator of minimum user proficiency level relating to a field of application, and wherein said item selector is operable to vary a total number of selected training items based on a comparison between the user ability and the defined cut point.

8. The system of claim 1, wherein said user interface is receptive of user performance information corresponding to results of a paper and pencil test.

9. The system of claim 1 comprising previous training session results organized by user and stored in memory operable with a data processing system, wherein said item selector has an learning management system operable to access said previous training session results and retrieve user performance information.

10. The system of claim 1 comprising tests results organized by user and stored in memory operable with a data processing system, wherein said item selector has an learning management system operable to access said test results and retrieve user performance information.

11. The system of claim 1, wherein an unfamiliar training task item corresponds to a task item not selected as a testing task item in a last testing procedure.

12. The system of claim 1, wherein an unfamiliar training task item corresponds to a task item not selected as a training task item in a last training session.

13. The system of claim 1, wherein said item selector is operable to select as training task items a plurality of unfamiliar task items having difficulty levels in a predefined range of difficulty relating to the user ability, thereby selecting at least one unfamiliar task item having a difficulty level less than the user ability, and at least one unfamiliar task item having a difficulty level higher than the user ability.

14. An adaptive training method for use with an adaptive testing tool, comprising:

determining a user ability as a function of previous user performance relating to task items of a selected field of application, wherein a task items has a predefined difficulty level;

defining a difficulty range for training task items on which to train a user, wherein the difficulty range relates to the user ability; and

selecting a plurality of unfamiliar task items as training task items, wherein the unfamiliar task items have a difficulty level falling within the difficulty range.

15. The method of claim 14, wherein said selecting a plurality of unfamiliar training task items comprises selecting an easier, unfamiliar task item as a training task item and a more difficult, unfamiliar task item as a training task item, wherein the easier, unfamiliar task item has a difficulty level below the user ability, and the more difficult, unfamiliar task item has a difficulty level above the user ability.

16. The method of claim 14, wherein said determining a user ability comprises computing the user ability as a sum of average difficulty level of task items performed correctly by the user and a natural log of a quotient of a number of task items performed correctly by the user and a number of task items performed incorrectly by the user.

17. The method of claim 14, wherein difficulty level of task items is defined in terms of logits, and wherein said defining a difficulty range for training task items comprises setting difficulty range limits substantially corresponding to one logit below the user ability to two and one-half logits above the user ability.

18. The method of claim 14 comprising selecting a missed task item as a training task item.

19. The method of claim 14 comprising receiving a field of application selection.

20. The method of claim 14 comprising receiving previous user performance information.

21. The method of claim 14 comprising training a user on the selected training task items.

22. The method of claim 14 comprising recording a training session history.

23. The method of claim 14 comprising determining a total number of selected training task items based on a comparison between the user ability and a defined cut point, wherein at least one cut point is defined in terms of user ability as an indicator of minimum user proficiency level relating to a field of application.

24. An adaptive testing and training system, comprising:

a user interface receptive of a field of application selection from a user;

a plurality of task items organized by field of application, ranked by difficulty level, and stored in memory operable with a data processing system;

an adaptive testing module operable to select a task item as a testing task item based on the field of application selection and user performance relating to a previously selected testing task item; and

an adaptive training module operable to select a plurality of unfamiliar training task items based on the selected field of application and a user ability, wherein the user ability is a function of selected testing task item difficulty in a most recent test, and wherein an unfamiliar training task item corresponds to a task item not selected as a testing task item in the most recent test, and not selected as a training task item in a most recent training session.

25. The system of claim 24, wherein said adaptive training module is operable to compute the user ability as a sum of average difficulty level of task items performed correctly by the user and a natural log of a quotient of a number of task items performed correctly by the user and a number of task items performed incorrectly by the user.

26. The system of claim 24, wherein difficulty level of task items is defined in terms of logits, and wherein said adaptive training module is operable to select the plurality of training task items according to a range of difficulty level substantially defined as one logit below the user ability to two and one-half logits above the user ability.

27. The system of claim 24, wherein at least one cut point is defined in terms of user ability as an indicator of minimum user proficiency level relating to the field of application, and wherein said adaptive training tool is operable to vary a total number of selected training task items based on a comparison between the user ability and the defined cut point.