Determining relevant information based on third party information and user interactions

1. A device, comprising:

a memory; and

at least one processor configured to:

receive application data from one or more applications, the application data including features related to user activity from the one or more applications, the one or more applications including applications local to the device that are stored in the memory and applications external to the device;

provide, using a machine learning (ML) model, a relevance score for each of one or more user interface (UI) elements based on each of the features, wherein the relevance score is based at least in part on weights assigned to features based on the user activity and respective variance values of the features;

sort one or more UI elements based on a ranking of the relevance scores; and

provide, as output, the one or more UI elements based at least in part on the ranking.

2. The device of claim 1 , wherein the relevance score is based at least in part on a sum of respective Gaussian curves.

3. The device of claim 1 , wherein the relevance score is further based on a value indicating a likelihood that a user will click on or tap a particular UI element.

4. The device of claim 1 , wherein a first variance value of a first feature indicates a first confidence associated with the first feature, and a second variance value of a second feature indicates a second confidence associated with the second feature, wherein the first variance value is higher than the second variance value indicating that the first confidence is lower than the second confidence, and wherein the first feature is assigned a greater weight than the second feature for providing the relevance score.

5. The device of claim 1 , wherein the features include a signal based on a location or time.

6. The device of claim 1 , wherein the application data is provided by the one or more applications using one or more application programming interfaces.

7. The device of claim 1 , wherein the weights assigned to features are adjusted over time as new application data related to user activity is received.

8. The device of claim 1 , wherein the features are included in different groups.

9. The device of claim 8 , wherein the different groups include a group of features that are shared across the applications and a second group of features that are specific to a particular application.

10. The device of claim 8 , wherein the device comprises a wearable electronic device and each UI element is provided for display by the wearable electronic device in accordance with the ranking, and wherein the each UI element corresponds to a watch face graphical element.

11. A method comprising:

receiving application data from one or more applications, the application data including features related to user activity from the one or more applications, the one or more applications including applications local to a device and applications external to the device;

providing, using a machine learning (ML) model, a relevance score for each of one or more user interface (UI) elements based on each of the features, wherein the relevance score is based at least in part on weights assigned to features based on the user activity and respective variance values of the features;

sorting one or more UI elements based on a ranking of the relevance scores; and

providing, as output, the one or more UI elements based at least in part on the ranking.

12. The method of claim 11 , wherein the device is a first device, and wherein the applications external to the device comprise applications that have run on a second device that is associated with the first device.

13. The method of claim 12 , wherein the first device is a wearable electronic device that works in conjunction with the second device.

14. A computer program product comprising code stored in a non-transitory computer-readable storage medium, the code comprising:

code to receive application data from one or more applications, the application data including features related to user activity from the one or more applications, the one or more applications including applications local to a device and applications external to the device;

code to provide, using a machine learning (ML) model, a relevance score for each of one or more user interface (UI) elements based on each of the features, wherein the relevance score is based at least in part on weights assigned to features based on the user activity and respective variance values of the features;

code to sort one or more UI elements based on a ranking of the relevance scores; and

code to provide, as output, the one or more UI elements based at least in part on the ranking.

15. The device of claim 1 , wherein the device is a first device, and wherein the applications external to the device comprise applications that have run on a second device that is associated with the first device.

16. The device of claim 15 , wherein the first device comprises a wearable electronic device, and wherein the second device comprises a portable computing device.

17. The device of claim 16 , wherein the wearable electronic device comprises a smart watch, and wherein the portable computing device comprises a smartphone, a tablet device, or a laptop computer.

18. The device of claim 15 , wherein each of the UI elements is a UI element associated with at least one of the one or more applications.

19. The device of claim 18 , further comprising a display, wherein the at least one processor is configured to provide the output by displaying, on the display, a scrollable list of the one or more UI elements in an order determined based on the sorting of the one or more UI elements.

20. The computer program product of claim 14 , wherein the device is a first device, and wherein the applications external to the device comprise applications that have run on a second device that is associated with a same user account as the first device.