Suggesting actions based on machine learning
This document describes techniques for suggesting actions based on machine learning. These techniques determine a task that a user desires to perform, and presents a user interface through which to perform the task. To determine this task, the techniques can analyze content displayed on the user device or analyze contexts of the user and user device. With this determined task, the techniques determine an action that may assist the user in performing the task. This action is further determined to be performable through analysis of functionalities of an application, which may or may not be executing or installed on the user device. With some subset of the application's functionalities determined, the techniques presents the subset of functionalities via the user interface. By so doing, the techniques enable a user to complete a task more easily, quickly, or using fewer computing resources.
1. A method comprising:
displaying first content in a window occupying a portion of a display of a user device, the first content including at least one of text content, image content, or video content, the window associated with a first application with which a user is interacting;
displaying a subset of functionalities of a second application through a slice window, the subset of functionalities comprising a suggested action to be performed by the user based on the first content and via the second application, the slice window occupying a portion of the display and including one or more selectable controls through which to instruct the second application to perform the subset of functionalities; and
responsive to receiving a selection of the one or more selectable controls by the user, displaying second content, the second content including a result of the second application performing the suggested action.
2. The method of claim 1 , wherein displaying the second content comprises displaying the second content in another window occupying at least a portion of the display of the user device.
3. The method of claim 2 , wherein the other window comprises another slice window.
4. The method of claim 2 , wherein the other window is associated with the second application.
5. The method of claim 1 , wherein:
the second application comprises a calendar application;
the suggested action comprises at least one of creating an event, modifying an event, creating a contact list entry, or modifying a contact list entry; and
the second content comprises at least a portion of the first content.
6. The method of claim 1 , wherein:
the first application comprises a media application; and
the suggested action comprises at least one of purchasing media or purchasing a ticket to a media event.
7. The method of claim 1 , wherein:
the first application comprises a social media application;
the suggested action comprises contacting an individual; and
the second application comprises at least one of another social media application, an email application, or a messaging application.
8. The method of claim 1 , wherein:
the suggested action comprises at least one of translating text, translating audio content, converting currency, reading text-to-speech, autofilling passwords, capturing an image, or providing codes.
9. The method of claim 1 , wherein the slice window is a limited-function user interface for the second application.
10. The method of claim 1 , the method further comprising:
launching the second application on the user device,
wherein the slice window includes content associated with the at least one of text content, image content, or video content and the suggested action.
11. The method of claim 1 , wherein determining the suggested action to be performed is further based on a context associated to the user or the user device.
12. An apparatus comprising:
a display;
a processor; and
computer-readable storage media storing instructions that, upon execution by the processor, cause the apparatus to:
display first content in a window occupying a portion of the display, the first content including at least one of text content, image content, or video content, the window associated with a first application;
display a subset of functionalities of a second application through a slice window, the subset of functionalities comprising a suggested action to be performed based on the first content and via the second application, the slice window occupying a portion of the display and including one or more selectable controls through which to instruct the second application to perform the subset of functionalities; and
responsive to receiving a selection of the one or more selectable controls by a user, display second content, the second content including a result of the second application performing the suggested action.
13. The apparatus of claim 12 , the computer-readable storage media storing further instructions that, upon execution by the processor to display the second content, cause the apparatus to:
display the second content in another window occupying at least a portion of the display.
14. The apparatus of claim 13 , wherein the other window comprises another slice window.
15. The apparatus of claim 13 , wherein the other window is associated with the second application.
16. The apparatus of claim 12 , wherein:
the second application comprises a calendar application;
the suggested action comprises at least one of creating an event, modifying an event, creating a contact list entry, or modifying a contact list entry; and
the second content comprises at least a portion of the first content.
17. The apparatus of claim 12 , wherein:
the first application comprises a media application; and
the suggested action comprises at least one of purchasing media or purchasing a ticket to a media event.
18. The apparatus of claim 12 , wherein:
the first application comprises a social media application;
the suggested action comprises contacting an individual; and
the second application comprises at least one of another social media application, an email application, or a messaging application.
19. The apparatus of claim 12 , wherein:
the suggested action comprises at least one of translating text, translating audio content, converting currency, reading text-to-speech, autofilling passwords, capturing an image, or providing codes.
20. A method comprising:
displaying first content in a window occupying a portion of a display of a user device, the first content including at least one of text content, image content, or video content, the window associated with a first application with which a user is interacting;
displaying a subset of functionalities of a second application through a slice window, the subset of functionalities comprising a suggested action to be performed by the user via the second application and based on the first content and an association between a context associated with the user or the user device, the context based on a current time, location, situation, sensor data, or activity associated with the user or the user device, the slice window occupying a portion of the display and including one or more selectable controls through which to instruct the second application to perform the subset of functionalities; and
responsive to receiving a selection of the one or more selectable controls by the user, displaying second content, the second content including a result of the second application performing the suggested action.