METHODS AND SYSTEMS FOR EVALUATING PERFORMANCE

• US 20150242797A1
• Filed: 02/27/2015
• Published: 08/27/2015
• Est. Priority Date: 02/27/2014
• Status: Active Application

• Current Assignee: University of Alaska Anchorage
• Original Assignee: University of Alaska Anchorage
• Inventors: Hoanca, Bogdan, Mock, Kenrick, Smith, Timothy
• Application Number:
  US14/633,692
• Publication Number:
  US 20150242797A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06Q 10/06398 Performance of employee with respect to a job function

Abstract

Methods and systems for evaluating performance comprise receiving, by a computer system, first movement data of a first part of a user, wherein the user is performing a task. A first plurality of metrics can be determined based on the first movement data of the first part. A level of proficiency of the user performing the task is determined using a trained classifier based on the first plurality of metrics.

Claims

1. A method comprising:

receiving, by a computer system, first movement data of a first part of a user, wherein the user performs a task;

determining, by the computer system, a first plurality of metrics based on the first movement data of the first part of the user; and

determining, by the computer system, a level of proficiency of the user to perform the task using a trained classifier based on the first plurality of metrics.

2. The method of claim 1, further comprising:

receiving, by the computer system, second movement data of a second part of the user that corresponds to movement of the first part of the user; and

determining, by the computer system, a second plurality of metrics based on the second movement data of the second part of the user.

3. The method of claim 2, further comprising:

determining, by the computer system, the level of proficiency of the user to perform the task using the trained classifier based on the first plurality of metrics and the second plurality of metrics.

4. The method of claim 1, further comprising:

tracking, by the computer system, one or more spatial factors of an instrument;

determining, by the computer system, a third plurality of metrics based on the one or more spatial factors; and

determining, by the computer system, the level of proficiency of the user to perform the task using the trained classifier based on the first plurality of metrics and the third plurality of metrics.

5. The method of claim 1, further comprising determining, by the computer system, using the trained classifier based on the first plurality of metrics, the task being performed by the user.

6. The method of claim 1, wherein the first part of the user comprises one or more eyes.

7. The method of claim 2, wherein the second part of the user comprises one or more hands.

8. The method of claim 1, wherein the first plurality of metrics is one or more of a backtrack duration, a backtrack count, a fixation mean, a fixation maximum, a uniformity, a non-uniformity, a velocity, a spatial factor, an acceleration, a range of motion, beats per unit time, a vibration spectrum, a note accuracy, and an audio quality.

9. The method of claim 1, wherein determining, by the computer system, a level of proficiency of the user to perform the task using a trained classifier based on the first plurality of metrics, comprises using a machine-learning based classifier that was trained on a set of one or more users each having a respective level of proficiency.

10. The method of claim 3, wherein classifying, by the computer system, a level of proficiency of the user on the task using a trained classifier based on the first plurality of metrics and the second plurality of metrics further comprises:

detecting movement of the second part relative to one or more user devices; and

determining whether the performed activity of the second part of the user is an expected activity based on the first plurality of metrics and the movement of the second part relative to one or more user devices.

11. The method of claim 1, wherein the task is one or more of, using a tool, using an instrument, using a musical instrument, playing a video game, reading text, typing text, reading a foreign language, typing a foreign language, and interacting with a user device via a user interface.

12. A method, comprising:

receiving, by a computer system, position data of a sequence of movements of a first part of a user, wherein the user is performing a task;

determining, by the computer system, a plurality of metrics based on the position data of the sequence of movements; and

determining, by the computer system, a level of proficiency of the user performing the task using a trained classifier based on the plurality of metrics.

13. The method of claim 12, wherein receiving, by the computer system, position data of the sequence of movements of the first part of the user comprises:

determining a prescribed sequence for a plurality of areas of interest in a visual field of the user between a start area of interest and ending with a last area of interest; and

tracking a duration of a fixation of the first part of the user at each area of interest of the plurality of areas of interest in the visual field, wherein the first part of the user is one or more eyes.

14. The method of claim 13, wherein receiving, by the computer system, position data of the sequence of movements of the first part of the user comprises:

identifying a fixation of the first part of the user,

beginning the tracking when the fixation of the eye is determined to be in the first area of interest; and

concluding the tracking when the fixation of the eye is determined to be in the last area of interest.

15. The method of claim 13, wherein the first plurality of metrics is one or more of a backtrack duration, a backtrack count, a fixation mean, a fixation maximum, a uniformity, a non-uniformity, a velocity, a spatial factor, an acceleration, a range of motion, beats per unit time, a vibration spectrum, a note accuracy, and an audio quality.

16. The method of claim 12, wherein determining, by the computer system, a level of proficiency of the user performing the task using a trained classifier based on the determined plurality of metrics comprises:

comparing the plurality of metrics with a predetermined pattern;

assigning a score for each of the plurality of metrics based on the comparison with the predetermined pattern; and

determining an overall score for the task based on the assigned scores.

17. A method, comprising:

receiving, by a computer system, movement data for a plurality of users, wherein the users perform a task;

determining, by the computer system, a plurality of metric sets based on the movement data; and

selecting, by the computer system, at least one of the plurality of metric sets for classifying a pattern of the task.

18. The method of claim 17, wherein the movement data comprises eye movement data.

19. The method of claim 18, wherein receiving, by the computer system, movement data for a plurality of users further comprises:

receiving a plurality of fixation points associated with the plurality of users; and

receiving a plurality of times associated with the plurality of fixation points.

20. The method of claim 17, wherein selecting, by the computer system, at least one of the plurality of metric sets for classifying the pattern of the task, comprises selecting one or more ideal metric sets.