Human Memory Enhancement Using Machine Learning

• US 20140067730A1
• Filed: 08/30/2012
• Published: 03/06/2014
• Est. Priority Date: 08/30/2012
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Kozloski, James R., Pickover, Clifford, Rish, Irina
• Granted Patent: US 9,177,257 B2
• Time in Patent Office: Days
• US Class Current: 706/12
• CPC Class Codes: A61B 5/369 Electroencephalography [EEG] devices for psychotechnics A61B5/16
• CPC Class Codes: A61B 5/4088 Diagnosing of monitoring cognitive diseases, e.g. Alzheimer, prion diseases or dementia
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G16H 20/70 relating to mental therapies, e.g. psychological therapy or autogenous training

Abstract

A system and an article of manufacture for providing a prompt for real-time cognitive assistance include analyzing input from at least one environmental sensor to identify context information pertaining to a user situation, identifying a likely subsequent cognitive task of the user in the user situation based on the context information and use of a learned model, determining an action with respect to information to be suggested to the user via a corresponding prompt, wherein the determining is based on the likely subsequent cognitive task, the context information and information learned from at least to one previous user situation, computing a confidence value to represent a level of certainty in the action, and providing the prompt to the user if the action has a confidence value greater than a threshold value corresponding to the action.

Claims

1. A non-transitory article of manufacture comprising a computer readable storage medium having computer readable instructions tangibly embodied thereon which, when implemented, cause a computer to carry out a plurality of method steps comprising:

analyzing input from at least one environmental sensor to identify context information pertaining to a user situation;

identifying a likely subsequent cognitive task of the user in the user situation based on the context information and use of a learned model;

determining an action with respect to information to be suggested to the user via a corresponding prompt, wherein the determining is based on the likely subsequent cognitive task, the context information and information learned from at least one previous user situation;

computing a confidence value to represent a level of certainty in the action; and

providing the prompt to the user if the action has a confidence value greater than a threshold value corresponding to the action.

2. The article of manufacture of claim 1, wherein the threshold value corresponding to the action is modified based on feedback pertaining to the action.

3. The article of manufacture of claim 1, wherein the method steps comprise:

analyzing user input to identify a cognitive state of the user.

4. The article of manufacture of claim 3, wherein the user input comprises brain wave activity and/or an electroencephalogram (EEG).

5. The article of manufacture of claim 3, wherein the user input comprises information from a stored user profile that specifies at least one aspect of the user.

6. The article of manufacture of claim 5, wherein the at least one aspect of the user includes a state of a user disease, nationality of the user, location of the user, language of the user, and/or employment of the user.

7. The article of manufacture of claim 1, wherein the input includes audio, video and/or text-based input.

8. The article of manufacture of claim 1, wherein the method steps comprise:

to analyzing input provided by an individual to supplement identification of the user situation.

9. The article of manufacture of claim 8, wherein the individual comprises the user and/or an additional individual.

10. The article of manufacture of claim 1, wherein the method steps comprise:

using a learned model to identify a state of an environment involved in the user situation.

11. The article of manufacture of claim 1, wherein identifying a likely subsequent cognitive task comprises performing an analysis of at least one word combination and/or word association of the user.

12. The article of manufacture of claim 1, wherein identifying a likely subsequent cognitive task comprises analyzing at least one word combination used by at least one additional individual.

13. The article of manufacture of claim 1, wherein identifying a likely subsequent cognitive task comprises determining at least one set of words commonly used in a particular context.

14. The article of manufacture of claim 1, wherein determining an action with respect to information to be suggested to the user via a corresponding prompt comprises incorporating input from at least one Internet source.

15. The article of manufacture of claim 1, wherein the method steps comprise:

updating the confidence value at a specified interval.

16. The article of manufacture of claim 1, wherein the confidence value can be indicated via a visual indicator, an audio indicator, a textual change, and/or a speech change.

17. The article of manufacture of claim 1, wherein the method steps comprise:

implementing machine-learning capability to learn from at least one previously observed situation and the user'"'"'s past behavior to adapt the determining step to a user'"'"'s cognitive tasks and environment.

18. The article of manufacture of claim 1, wherein the prompt is a speech output and/or a visual output.

19. The article of manufacture of claim 1, wherein the method steps comprise:

generating a summary of the user situation and the context information; and

distributing the summary to a pre-configured set of individuals for feedback.

20. A system for providing a prompt for real-time cognitive assistance, comprising:

at least one distinct software module, each distinct software module being embodied on a tangible computer-readable medium;

a memory; and

at least one processor coupled to the memory and operative for;

analyzing input from at least one environmental sensor to identify context information pertaining to a user situation;

identifying a likely subsequent cognitive task of the user in the user situation based on the context information and use of a learned model;

determining an action with respect to information to be suggested to the user via a corresponding prompt, wherein the determining is based on the likely subsequent cognitive task, the context information and information learned from at least one previous user situation;

computing a confidence value to represent a level of certainty in the action; and

providing the prompt to the user if the action has a confidence value greater than a threshold value corresponding to the action.