Intellective switching between tasks

1. A method comprising:

identifying, by one or more processor, a current task;

obtaining, by the one or more processor, an indicator of a commencement of a switching event, wherein the switching event comprises a transition originating from the current task and concluding at a new task;

obtaining, by the one or more processor, behavior analysis data relating to a plurality of past switching events, wherein each past switching event of the plurality of past switching events comprises a transition originating from the current task and concluding at one of a plurality of target tasks, the behavior analysis data comprising a timestamp for each past switching event;

determining, by the one or more processor, based on the behavior analysis data, at least one recommended task, wherein the at least one recommended task comprises at least one target task of the plurality of target tasks; and

assigning, by the one or more processor, a weighted value to each past switching event based on the timestamps;

wherein magnitude of the weighted value assigned to each past switching event corresponds to proximity of the timestamp for each past switching event to a current time;

wherein the behavior analysis data further comprises the weighted value of each past switching event; and

wherein the determining is performed so that a second of the plurality of past switching events occurring subsequent to a first of the plurality of past switching events is assigned a larger weight than the first of the plurality of past switching events based on second of the plurality of past switching events occurring closer in time to the current time than the first of the plurality of past switching events.

2. The method of claim 1 , further comprising:

providing, by the one or more processor, the at least one recommended task to a client;

obtaining, by the one or more processor, an indicator of a conclusion of the switching event;

identifying, by the one or more processor, the new task; and

updating, by the one or more processor, the behavior analysis data with information related to the switching event, wherein the information related to the switching event comprises a timestamp of a time of the transition originating from the current task and concluding at the new task.

3. The method of claim 1 , wherein the at least one recommended task comprises the new task.

4. The method of claim 1 , wherein the determining further comprises:

selecting, by the one or more processor, the at least one recommended task based on a count of each past switching event of the plurality of past switching events concluding at the at least one recommended task and the weighted value assigned to each past switching event of the plurality of past switching events concluding at the at least one recommended task.

5. The method of claim 1 , wherein the timestamp for each past switching event of the plurality of past switching events is within a predefined window of time.

6. The method of claim 1 , further comprising:

determining, by the one or more processor, a category for the current task and for each of the plurality of target tasks, wherein the behavior analysis data further comprises the category for the current task and for each of the plurality of target tasks in the behavior analysis data.

7. The method of claim 6 , wherein a task of the at least one recommended task and the current task have a common category.

8. The method of claim 1 , wherein the timestamp for each past switching event is within a given window of time, and wherein the obtaining behavior analysis data comprises obtaining a portion of data smaller than a predefined maximum amount of data and greater than a predefined minimum amount of data.

9. The method of claim 1 , wherein the obtaining an indicator occurs prior to conclusion of the transition originating from the current task and concluding at a new task.

10. The method of claim 1 , wherein the determining occurs prior to conclusion of the transition originating from the current task and concluding at a new task.

11. The method of claim 1 , wherein the at least one recommended task is a task for initiation by a user to improve efficiency with which the user switches to the new task.

12. The method of claim 1 , wherein the method includes presenting the one or more recommended task as a displayed option on a display for selection by a user, and wherein the method includes performing a recommended task of the one or more recommended task presented on the display responsively to action of the user.

13. The method of claim 1 , wherein the determining includes predicting based on the behavior analysis data, for each target task of the plurality of target tasks, a likelihood of the target task being a next task transitioned to by a user, and specifying the one or more recommended task based on the predicting.

14. The method of claim 1 , wherein the method includes specifying a target task of the plurality of target task as a recommend task of the at least one recommended task based on a predicting that the target task is a likely next task to be transitioned to by a user.

15. A computer program product comprising:

a computer readable storage medium readable by one or more processor and storing instructions for execution by the one or more processor for performing a method comprising:

identifying, by one or more processor, a current task;

obtaining, by the one or more processor, an indicator of a commencement of a switching event, wherein the switching event comprises a transition originating from the current task and concluding at a new task;

obtaining, by the one or more processor, behavior analysis data relating to a plurality of past switching events, wherein each past switching event of the plurality of past switching events comprises a transition originating from the current task and concluding at one of a plurality of target tasks, the behavior analysis data comprising a timestamp for each past switching event;

determining, by the one or more processor, based on the behavior analysis data, at least one recommended task, wherein the at least one recommended task comprises at least one target task of the plurality of target tasks; and

assigning, by the one or more processor, a weighted value to each past switching event based on the timestamps;

wherein magnitude of the weighted value assigned to each past switching event corresponds to proximity of the timestamp for each past switching event to a current time;

wherein the behavior analysis data further comprises the weighted value of each past switching event; and

wherein the determining is performed so that a second of the plurality of past switching events occurring subsequent to a first of the plurality of past switching events is assigned a larger weight than the first of the plurality of past switching events based on second of the plurality of past switching events occurring closer in time to the current time than the first of the plurality of past switching events.

16. The computer program product of claim 15 , further comprising:

providing, by the one or more processor, the at least one recommended task to a client;

obtaining, by the one or more processor, an indicator of a conclusion of the switching event;

identifying, by the one or more processor, the new task; and

updating, by the one or more processor, the behavior analysis data with information related to the switching event, wherein the information related to the switching event comprises a timestamp of a time of the transition originating from the current task and concluding at the new task.

17. The computer program product of claim 15 , wherein the determining further comprises:

assigning, by the one or more processor, a weighted value to each past switching event based on the timestamps,

wherein magnitude of the weighted value assigned to each past switching event corresponds to proximity of the timestamp for each past switching event to a current time, and

wherein the behavior analysis data further comprises the weighted value of each past switching event.

18. A system comprising:

a memory;

one or more processor in communication with the memory; and

program instructions executable by the one or more processor via the memory to perform a method, the method comprising:

identifying, by the one or more processor, a current task;

obtaining, by the one or more processor, an indicator of a commencement of a switching event, wherein the switching event comprises a transition originating from the current task and concluding at a new task;

obtaining, by the one or more processor, behavior analysis data relating to a plurality of past switching events, wherein each past switching event of the plurality of past switching events comprises a transition originating from the current task and concluding at one of a plurality of target tasks, the behavior analysis data comprising a timestamp for each past switching event;

determining, by the one or more processor, based on the behavior analysis data, a recommended task, wherein the recommended task comprises a target task of the plurality of target tasks, and wherein the determining includes predicting, for each target task of the plurality of target tasks a likelihood of the target task being a next task transitioned to, and specifying as the recommended task a target task of the plurality of target tasks predicted most likely to be the next task; and

assigning, by the one or more processor, a weighted value to each past switching event based on the timestamps;

wherein magnitude of the weighted value assigned to each past switching event corresponds to proximity of the timestamp for each past switching event to a current time;

wherein the behavior analysis data further comprises the weighted value of each past switching event; and

wherein the determining is performed so that a second of the plurality of past switching events occurring subsequent to a first of the plurality of past switching events is assigned a larger weight than the first of the plurality of past switching events based on second of the plurality of past switching events occurring closer in time to the current time than the first of the plurality of past switching events.