Systems and methods for context aware redirection based on machine-learning

1. A method for providing a redirection, the method comprising:

receiving information associated with an activity;

analyzing the information to identify a first pattern and a second pattern, wherein the first pattern is related to work activities of a user and the second pattern is associated with a recovery activity in response to the work activities of the user, wherein the recovery activity comprises recreational environments other than an office or workplace where the work activities are performed;

generating a customized recommendation model for the second pattern based on the first pattern, wherein the customized recommendation model is generated based on, for each transition from the second pattern into the first pattern, correlating feedback information associated with a respective second pattern with positive performance measurements of a respective first pattern after transitioning into the respective first pattern from the respective second pattern;

in response to a detected trigger indicating a transition to the second pattern from the first pattern, assessing context factors to verify the transition to the second pattern without interrupting the first pattern;

in response to verifying the transition to the second pattern,

determining a recovery plan for the second pattern to improve performance in the first pattern transitioned into from the second pattern by applying the customized recommendation model, the recovery plane comprising one or more of mental stimuli, physical stimuli, and social stimuli correlated to positive performance in the first pattern, and

providing the redirection for the second pattern including the determined recovery plan;

receiving feedback information associated with the second pattern and performance measurements of the first pattern; and

when the user repeatedly rejects a recommended activity for the recovery plan, updating the customized recommendation model to recommend a modified or different recovery plan based on the context factors and the received feedback information.

2. The method of claim 1 , wherein analyzing further comprises:

identifying triggers that indicate a transition from the first pattern to the second pattern; and

determining context factors associated with the first pattern that are inconsistent with the second pattern.

3. The method of claim 1 , wherein the recovery plan includes displaying an electronic game that directs a user to a location within a workplace setting.

4. The method of claim 1 , wherein the customized recommendation model is generated using machine-learning associated with one or more of training data, user preferences, environmental controls, clinical guidelines, safety regulations, and social graphs.

5. The method of claim 1 , wherein the detected trigger indicating a transition to the second pattern is based on one or more of tracking a user's body movements, location, and eye gaze.

6. The method of claim 1 , wherein assessing context factors to verify the transition to the second pattern comprises identifying one or more of sensed data, pinpoint data, and environment data associated with the first pattern that override the trigger.

7. The method of claim 1 , wherein the information includes one or more of sensed data, pinpoint data, and environment data.

8. The method of claim 1 , wherein the information comprises one or more of location data, physiological data, computer usage, phone usage, and sensor data.

9. The method of claim 1 ,

wherein the feedback information comprises one or more of a duration for returning to the first pattern, tracking co-presence of another user, user location data, user survey, and post-break activity.

10. The method of claim 1 , wherein the detected trigger indicating a transition to the second pattern is based on eye gaze.

11. The method of claim 1 , the detected trigger is from a first source and the context factors are from at least a second source different from the first source.

12. A system for providing a redirection comprising:

a memory;

a processor operatively coupled to the memory, the processor configured to:

obtain information associated with an activity;

analyze the information to identify a first pattern and a second pattern, wherein the first pattern is related to work activities of a user and the second pattern is associated with a recovery activity in response to the work activities of the user, wherein the recovery activity comprises recreational environments other than an office or workplace where the work activities are performed;

generate a customized recommendation model for the second pattern based on the first pattern, wherein the customized recommendation model is generated based on, for each transition from the second pattern into the first pattern, correlating feedback information associated with a respective second pattern with positive performance measurements of a respective first pattern after transitioning into the respective first pattern from the respective second pattern; and

in response to a detected trigger indicating a transition to the second pattern from the first pattern, assess context factors to verify the transition to the second pattern without interrupting the first pattern;

in response to verifying the transition to the second pattern,

determine a recovery plan for the second pattern to improve performance in the first pattern transitioned into from the second pattern by applying the customized recommendation model, the recovery plane comprising one or more of mental stimuli, physical stimuli, and social stimuli correlated to positive performance in the first pattern, and

provide the redirection for the second pattern including the determined recovery plan;

receive feedback information associated with the second pattern and performance measurements of the first pattern; and

when the user repeatedly rejects a recommended activity for the recovery plan, update the customized recommendation model to recommend a modified or different recovery plan based on the context factors and the received feedback information.

13. The system of claim 12 , wherein to analyze the information to identify a first pattern and a second pattern the processor further configured to:

identify triggers that indicate a transition from the first pattern to the second pattern; and

determine context factors associated with the first pattern that are inconsistent with the second pattern.

14. The system of claim 12 , wherein the customized recommendation model is generated using machine-learning associated with one or more of training data, user preferences, environmental controls, clinical guidelines, safety regulations, and social graphs.

15. The system of claim 12 , wherein to assess context factors to verify the transition to the second pattern, the processor further is configured to:

identify one or more of sensed data, pinpoint data, and environment data associated with the first pattern that override the trigger.

16. The system of claim 12 , wherein feedback information comprises one or more of duration for returning to the first pattern, tracking co-presence of another user, user location data, user survey, and post-break activity.

17. A non-transitory computer readable medium, comprising instructions that when execute by a processor, the instructions to:

obtain information associated with an activity;

analyze the information to identify a first pattern and a second pattern, wherein the first pattern is related to work activities of a user and the second pattern is associated with a recovery activity in response to the work activities of the user, wherein the recovery activity comprises recreational environments other than an office or workplace where the work activities are performed;

generate a customized recommendation model for the second pattern based on the first pattern, wherein the customized recommendation model is generated based on, for each transition from the second pattern into the first pattern, correlating feedback information associated with a respective second pattern with positive performance measurements of a respective first pattern after transitioning into the respective first pattern from the respective second pattern; and

in response to a detected trigger indicating a transition to the second pattern from the first pattern, assess context factors to verify the transition to the second pattern without interrupting the first pattern;

in response to verifying the transition to the second pattern,

determine a recovery plan for the second pattern to improve performance in the first pattern transitioned into from the second pattern by applying the customized recommendation model, the recovery plane comprising one or more of mental stimuli, physical stimuli, and social stimuli correlated to positive performance in the first pattern, and

provide the redirection for the second pattern including the determined recovery plan;

receive feedback information associated with the second pattern and performance measurements of the first pattern; and

when the user repeatedly rejects a recommended activity for the recovery plan, update the customized recommendation model to recommend a modified or different recovery plan based on the context factors and the received feedback information.

18. The non-transitory computer readable medium of claim 17 , wherein to analyze the information to identify a first pattern and a second pattern the instructions are further to:

identify triggers that indicate a transition from the first pattern to the second pattern; and

determine context factors associated with the first pattern that are inconsistent with the second pattern.

19. The non-transitory computer readable medium of claim 17 , wherein the customized recommendation model is generated using machine-learning associated with one or more of training data, user preferences, environmental controls, clinical guidelines, safety regulations, and social graphs.

20. The non-transitory computer readable medium of claim 17 , wherein to assess context factors to verify the transition to the second pattern, the instructions are further to:

identify one or more of sensed data, pinpoint data, and environment data associated with the first pattern that override the trigger.

21. The non-transitory computer readable medium of claim 17 , wherein feedback information comprises one or more of duration for returning to the first pattern, tracking co-presence of another user, user location data, user survey, and post-break activity.