ADAPTIVE COGNITIVE SKILLS ASSESSMENT AND TRAINING

• US 20150279226A1
• Filed: 03/26/2015
• Published: 10/01/2015
• Est. Priority Date: 03/27/2014
• Status: Abandoned Application

• Current Assignee: Mycognition Limited
• Original Assignee: Mycognition Limited
• Inventors: Harrison, John Edward, Van Rijswijk, Jurriaan Hubrecht, Sparrowhawk, Keiron Thomas, Knight, Duncan Andrew
• Application Number:
  US14/670,239
• Publication Number:
  US 20150279226A1
• Time in Patent Office: Days
• US Class Current: 1/1
• 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

A method for cognitive assessment and adaptive cognitive skills training is disclosed. The method involves obtaining a plurality of test performance results associated with a user based on a plurality of tests, generating a training recipe based on the test performance results and at least one of a plurality of test weights and a plurality of baseline distributions, each corresponding to the plurality of tests, wherein the plurality of test weights comprises a weight assigned to a plurality of cognitive domains tested by the plurality of tests, identifying one of the plurality of cognitive domains of the user requiring improvement based on the test performance results, obtaining, via an online video game played by the user, activity performance results associated with the user based on a training round completed by the user, wherein the training round comprises a plurality of video game activities in the online video game selected using the training recipe and specifically targeted to the cognitive domain of the user requiring improvement.

Claims

1. A method for cognitive assessment and adaptive cognitive skills training, comprising:

obtaining a plurality of test performance results associated with a user based on a plurality of tests completed by the user;

generating a training recipe based on the test performance results and at least one selected from a group consisting of a plurality of test weights and a plurality of baseline distributions, each corresponding to the plurality of tests, wherein the plurality of test weights comprises a weight assigned to a plurality of cognitive domains tested by the plurality of tests;

identifying one of the plurality of cognitive domains of the user requiring improvement based on the test performance results;

obtaining, via an online video game played by the user, activity performance results associated with the user based on a training round completed by the user, wherein the training round comprises a plurality of video game activities in the online video game selected using the training recipe and specifically targeted to the cognitive domain of the user requiring improvement; and

presenting a report indicating a change in the cognitive domain of the user based on the plurality of tests and the plurality of activities.

2. The method of claim 1, wherein generating a training recipe comprises:

determining a latency and an error percentage of the user for each of the plurality of tests;

comparing the latency and the error percentage of the user in each of the plurality of tests to a baseline distribution obtained from an initial test data set; and

normalizing the latency and the error percentage of the user for each of the plurality of tests based on the percentile of the baseline distributions within which the user latency and error percentage fall to obtain a normalized cognitive health score for the user.

3. The method of claim 2, wherein a weighted average is applied to the normalized cognitive health score based on weights for each cognitive domain, and wherein a weighted average is applied to the activity performance results from the online video game using a plurality of activity performance weights to correlate the video game scores to the plurality of cognitive domains.

4. The method of claim 3, wherein the weights applied to the normalized results of the user for each of the plurality of tests are assigned and monitored by experts in the field.

5. The method of claim 1, wherein the latency and error percentage is measured by each keystroke performed by the user during the tests.

6. The method of claim 1, wherein the plurality of baselines is obtained from an initial test data set comprising psychological test results of a general population, and wherein the plurality of baselines is stored in a repository.

7. The method of claim 6, wherein an iterative process is employed to update and adjust the weights applied to the cognitive domains based on collection of data over time.

8. The method of claim 1, wherein results from the video gaming activities are correlated to the test performance data to obtain a relationship between the video gaming activities and cognitive health.

9. The method of claim 1, wherein the training recipe is unique to a user and is based on a user profile including the user'"'"'s age, the user'"'"'s gender, and the user'"'"'s education level.

10. The method of claim 2, wherein the general distribution is a binomial distribution.

11. The method of claim 2, wherein a fit algorithm is applied to the weighted and normalized cognitive health score of the user to determine the weights for the video gaming activities.

12. The method of claim 3, further comprising:

iteratively feed the test performance results and normalized cognitive health score into the online video game to obtain the activity performance results, and

iteratively feed the activity performance results into the training recipe for the user,

wherein the test performance results and the activity performance results are used to adjust the plurality of test weights and the plurality of activity weights to keep the cognitive health scores within an expected range.

13. A system for cognitive assessment and adaptive cognitive skills training, comprising:

a network interface controller;

a memory; and

a computer processor, communicatively coupled to the network interface controller and the memory, for executing a cognitive training application configured to generate the user training recipes using the baseline distribution and the plurality of weights, wherein the cognitive training application is configured to;

obtain a plurality of test performance results associated with a user based on a plurality of tests completed by the user;

generate a training recipe based on the test performance results and at least one selected from a group consisting of a plurality of test weights and a plurality of baseline distributions, each corresponding to the plurality of tests, wherein the plurality of test weights comprises a weight assigned to the plurality of cognitive domains tested by the plurality of tests;

identify one of the plurality of cognitive domains of the user requiring improvement based on the test performance results;

obtain, via an online video game presented to the user on a webpage, activity performance results associated with the user based on a training round completed by the user, wherein the training round comprises a plurality of video game activities in the online video game selected using the training recipe and specifically targeted to the cognitive domain of the user requiring improvement;

present a report indicating a change in the cognitive domain of the user based on the plurality of tests and the plurality of activities.

14. The system of claim 13, wherein generating a training recipe comprises:

determining a latency and an error percentage of the user for each of the plurality of tests;

comparing the latency and the error percentage of the user in each of the plurality of tests to a general distribution obtained from an initial test data set; and

normalizing the latency and the error percentage of the user for each of the plurality of tests based on the percentile of the baseline distributions within which the user latency and error percentage fall to obtain a normalized cognitive health score for the user.

15. The system of claim 13, wherein the baseline distributions are binomial distributions for each of the plurality of tests.

16. The system of claim 13, wherein the plurality of test weights applied to normalized results of the user for each of the plurality of tests are assigned and monitored by experts in the field.

17. The system of claim 13, wherein the latency and error percentage is measured by each keystroke or touch input performed by the user during the plurality of tests.

18. The system of claim 13, further comprising a data repository configured to store:

the plurality of test weights used to compute the weighted average of a cognitive health score of the user for each of the plurality of cognitive domains;

the plurality of baseline distributions with which the user'"'"'s cognitive health score is compared to obtain a normalized cognitive health score of the user; and

a user profile for the user comprising user training recipes and the performance data comprising test performance results and activity performance results of the user obtained by playing the online video game.

19. The system of claim 18, wherein the cognitive training application is further configured to:

iteratively feed the test performance results and normalized cognitive health score into the online video game to obtain the activity performance results, and

iteratively feed the activity performance results into the training recipe for the user,

wherein the test performance results and the activity performance results are used to adjust the plurality of test weights and the plurality of activity weights to keep the cognitive health scores within an expected range.

20. A non-transitory computer-readable medium storing instructions, that when executed, perform a method for cognitive assessment and adaptive cognitive skills training, comprising:

obtaining a plurality of test performance results associated with a user based on a plurality of tests completed by the user;

generating a training recipe based on the test performance results and at least one selected from a group consisting of a plurality of test weights and a plurality of baseline distributions, each corresponding to the plurality of tests, wherein the plurality of test weights comprises a weight assigned to a plurality of cognitive domains tested by the plurality of tests;

identifying one of the plurality of cognitive domains of the user requiring improvement based on the test performance results;

obtaining, via an online video game presented to the user on a webpage, activity performance results associated with the user based on a training round completed by the user, wherein the training round comprises a plurality of video game activities in the online video game selected using the training recipe and specifically targeted to the cognitive domain of the user requiring improvement; and

presenting a report indicating a change in the cognitive domain of the user based on the plurality of tests and the plurality of activities.