CONTEXT-BASED DEVICE ACTION PREDICTION

• US 20130173513A1
• Filed: 12/30/2011
• Published: 07/04/2013
• Est. Priority Date: 12/30/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Chu, David, Kansal, Aman, Liu, Jie, Yan, Tingxin
• Granted Patent: US 9,189,252 B2
• Time in Patent Office: Days
• US Class Current: 706/14
• CPC Class Codes: G06F 9/445 Program loading or initiating bootstrapping G06F9/4401; security arrangements for program loading or initiating G06F21/57
• CPC Class Codes: G06F 9/451 Execution arrangements for user interfaces
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

The described implementations relate to automatically performing device actions. One implementation can obtain a contextual value of a contextor. The implementation can decide, using a decision engine, whether to perform an action on a computing device based on the contextual value. In an instance when the decision engine decides that the action is to be performed, the implementation can perform the action on the computing device. The implementation can also update the decision engine using feedback related to the action. As a specific example, the action can be prelaunching an application before a user has requested to execute the application. Prelaunching the application can reduce application latency relative to waiting for the user to request to execute the application before launching the application.

Claims

1. A method comprising:

obtaining one or more contextual values from one or more contextors;

deciding, using a decision engine comprising one or more decision rules, whether to perform an action on a computing device based on the one or more contextual values and the one or more decision rules;

performing the action on the computing device in an instance when the decision engine decides that the action is to be performed; and

updating the decision rules of the decision engine using feedback related to the action.

2. The method according to claim 1, wherein an individual contextual value is obtained from a physical sensor on the computing device.

3. The method according to claim 1, wherein an individual contextual value reflects activity by a user of the computing device or activity of other users on other computing devices.

4. The method according to claim 3, the activity comprising the user executing an application on the computing device.

5. The method according to claim 3, the activity comprising the user communicating with another individual using the computing device.

6. The method according to claim 1, wherein an individual contextual value reflects a current time or current location of the computing device.

7. The method according to claim 1, further comprising enabling the action using a graphical user interface (GUI) while leaving at least one other action disabled via the GUI.

8. The method according to claim 1, further comprising enabling an individual contextor using a graphical user interface (GUI) while leaving another individual contextor disabled via the GUI.

9. A method comprising:

identifying an application to prelaunch based on one or more contextual values;

prelaunching the application to place the application into a prelaunched state; and

receiving feedback relating to the prelaunching.

10. The method according to claim 9, wherein the feedback indicates whether a user requested to execute the application within a predetermined time after the application was prelaunched.

11. The method of claim 9, wherein the prelaunching comprises:

allocating computational resources to the application;

loading at least some application code associated with the application from storage into memory; and

executing the loaded application code.

12. The method of claim 11, further comprising:

evicting at least one other application from the memory.

13. The method according to claim 9, further comprising:

receiving a user request to execute the application after prelaunching the application;

adjusting an individual configuration parameter of the application based on the one or more contextual values; and

executing the application from the prelaunched state, wherein the prelaunched state reflects the adjusted individual configuration parameter.

14. A system comprising:

a context-based action module; and

a computing device configured to execute the context-based action module,

wherein the context-based action module is configured to;

in a first instance;

obtain a contextual value of a contextor;

use a decision engine to decide not to perform an action on the computing device based on the contextual value; and

not perform the action on the computing device;

provide feedback related to the action to the decision engine, wherein the decision engine is updated to learn to perform the action when the contextor has the contextual value;

in a second instance that is subsequent to the first instance;

obtain the same contextual value of the contextor that was obtained in the first instance;

use the updated decision engine to decide to perform the action on the computing device based on the same contextual value; and

perform the action on the computing device.

15. The system according to claim 14, wherein the context-based action module comprises computer-readable instructions and the computing device comprises at least one processor configured to execute the computer-readable instructions.

16. The system according to claim 14, wherein the context-based action module is distributed across the computing device and a server such that the decision engine is provided by and updated on the server.

17. The system according to claim 14, wherein the decision engine comprises a decision tree.

18. The system according to claim 17, wherein the decision tree comprises a very fast decision tree.

19. The system according to claim 14, wherein the decision engine comprises a Bayesian classifier.

20. The system according to claim 19, wherein the Bayesian classifier is a naive Bayesian classifier.