Predicting the next application that you are going to use on aviate

• US 9,971,972 B2
• Filed: 12/30/2014
• Issued: 05/15/2018
• Est. Priority Date: 12/30/2014
• Status: Active Grant

• Current Assignee: Yahoo AD Tech LLC
• Original Assignee: Oath Inc. (Verizon Communications Inc.)
• Inventors: Silvestri, Fabrizio, Baeza-Yates, Ricardo, Harrison, Beverly, Jiang, Di
• Primary Examiner(s): Gonzalez, Amancio
• Application Number:
  US14/586,635
• Publication Number:
  US 20160189049A1
• Time in Patent Office: 1,232 Days
• Field of Search: 455418
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 4/20 Services signaling; Auxiliary data signalling, i.e. transmitting data via a non-traffic channel

Abstract

In one embodiment, a current context of a mobile device may be ascertained, where the current context includes an indication of a last application opened via the mobile device, wherein the last application opened is one of a plurality of applications installed on the mobile device. A probability, for each of the plurality of applications, that a user of the mobile device will use the corresponding application under the current context may be determined, where the probability for at least a portion of the plurality of applications is determined by applying a computer-generated model to the current context, wherein the computer-generated model is associated with the mobile device. One or more of the plurality of the applications may be identified based, at least in part, upon the probability, for each one of the plurality of applications, that the user of the mobile device will use the corresponding application.

Claims

1. A method, comprising:

ascertaining a current context of a mobile device, the current context including an indication of a last application opened via the mobile device, wherein the last application opened is one of a plurality of applications installed on the mobile device;

determining a probability, for each of the plurality of applications, that a user of the mobile device will use the corresponding application under the current context, wherein the probability for at least a portion of the plurality of applications is determined by applying a computer-generated model to the current context, wherein the computer-generated model is associated with the mobile device;

identifying one or more of the plurality of the applications based, at least in part, upon the probability, for each one of the plurality of applications, that the user of the mobile device will use the corresponding application; and

determining that a particular one of the plurality of applications is a newly installed application;

wherein determining a probability, for each of the plurality of applications, that a user of the mobile device will use the corresponding application includes ascertaining a probability that a user of the mobile device will use the newly installed application based, at least in part, upon information pertaining to at least one other mobile device.

2. The method as recited in claim 1, further comprising:

recommending the identified one or more of the plurality of applications, launching the identified one or more of the plurality of applications, or providing an advertisement pertaining to the identified one or more of the plurality of applications.

3. The method as recited in claim 1, wherein the current context further comprises a value associated with one or more of a Last Location Update, Last Charge Cable, Last Audio Cable, Last Context Trigger, or a Last Context Pulled.

4. The method as recited in claim 1, further comprising:

collecting contextual information via the mobile device, the contextual information including a context pertaining to one or more actions detected via the mobile device, wherein at least one of the one or more actions pertains to usage of the at least a portion of the plurality of applications installed on the mobile device; and

training the computer-generated model associated with the mobile device using at least a portion of the collected contextual information.

5. The method as recited in claim 4, wherein the one or more actions comprise at least one of an application open action, a location update action, a charge cable action, an audio cable action, a context trigger action, or a context pulled action.

6. The method as recited in claim 4, wherein the context indicates a sequential pattern of actions detected by the mobile device prior to one of the one or more actions and/or after the one of the one or more actions.

7. The method as recited in claim 1, further comprising:

determining whether the newly installed application is a short-term application or a long-term application; and

wherein determining a probability, for each of the plurality of applications, that a user of the mobile device will use the corresponding application includes ascertaining a probability that a user of the mobile device will use the newly installed application based, at least in part, upon whether the newly installed application is a short-term application or a long-term application.

8. The method as recited in claim 1, further comprising:

determining that the newly installed application is a short-term application; and

wherein determining a probability, for each of the plurality of applications, that a user of the mobile device will use the corresponding application includes ascertaining a probability that a user of the mobile device will use the newly installed application based, at least in part, upon historical data pertaining to a plurality of other mobile devices with respect to the particular one of the plurality of applications.

9. The method as recited in claim 1, further comprising:

determining that the newly installed application is a long-term application; and

wherein determining a probability, for each of the plurality of applications, that a user of the mobile device will use the corresponding application includes ascertaining a probability that a user of the mobile device will use the newly installed application based, at least in part, upon historical data, wherein the historical data indicates a number of openings of the plurality of applications on the mobile device and an average opening probability of the particular application on other mobile devices.

10. A method, comprising:

ascertaining whether a threshold amount of contextual information pertaining to usage of at least a portion of a plurality of applications installed on a mobile device is available, the contextual information including a context pertaining to one or more actions detected via the mobile device;

determining a probability, for each of the plurality of applications, that a user of the mobile device will use the corresponding application under a current context, based, at least in part, upon whether a threshold amount of contextual information pertaining to usage of at least a portion of the plurality of applications installed on the mobile device is available; and

identifying one or more of the plurality of the applications based, at least in part, upon the ascertained probability, for each one of the plurality of applications, that the user of the mobile device will use the corresponding application.

11. The method as recited in claim 10, wherein ascertaining whether a threshold amount of contextual information pertaining to usage of at least a portion of a plurality of applications installed on a mobile device is available comprises ascertaining that a threshold amount of contextual information pertaining to usage of at least a portion of the plurality of applications installed on the mobile device is not available, and wherein determining a probability, for each of the plurality of applications, that a user of the mobile device will use the corresponding application, based, at least in part, upon whether a threshold amount of contextual information pertaining to usage of at least a portion of the plurality of applications installed on the mobile device is available comprises:

obtaining information associated with at least one other mobile device having applications installed thereon that include the plurality of applications, the information including historical data or the information being generated via at least one computer-generated model associated with the at least one other mobile device; and

determining a probability, for each of the plurality of applications, based, at least in part, upon the information.

12. The method as recited in claim 10, wherein the one or more actions comprise at least one of an application open action, a location update action, a charge cable action, an audio cable action, a context trigger action, or a context pulled action.

13. The method as recited in claim 10, wherein the current context comprises one or more of a Last Location Update, Last Charge Cable, Last Audio Cable, Last Context Trigger, Last Context Pulled, or a Last Application Open for each application installed on the mobile device.

14. The method as recited in claim 10, further comprising:

determining that a particular one of the plurality of applications is a newly installed application such that contextual information pertaining to usage of the newly installed application on the mobile device cannot be ascertained or is limited; and

determining whether the newly installed application is a short-term application or a long-term application;

wherein determining a probability, for each of the plurality of applications, that a user of the mobile device will use the corresponding application includes ascertaining a probability that a user of the mobile device will use the newly installed application based, at least in part, upon whether the newly installed application is a short-term application or a long-term application.

15. The method as recited in claim 10, further comprising:

determining that a particular one of the plurality of applications is a newly installed application such that contextual information pertaining to usage of the newly installed application on the mobile device cannot be ascertained or is limited; and

determining that the newly installed application is a short-term application;

wherein determining a probability, for each of the plurality of applications, that a user of the mobile device will use the corresponding application includes ascertaining a probability that a user of the mobile device will use the newly installed application based, at least in part, upon historical data pertaining to a plurality of other mobile devices with respect to the particular one of the plurality of applications.

16. The method as recited in claim 10, further comprising:

determining that a particular one of the plurality of applications is a newly installed application such that contextual information pertaining to usage of the newly installed application on the mobile device cannot be ascertained or is limited; and

determining that the newly installed application is a long-term application;

wherein determining a probability, for each of the plurality of applications, that a user of the mobile device will use the corresponding application includes ascertaining a probability that a user of the mobile device will use the newly installed application based, at least in part, upon historical data, wherein the historical data indicates a number of openings of the plurality of applications on the mobile device and an average opening probability of the particular application on other mobile devices.

17. The method as recited in claim 10, further comprising:

recommending the identified one or more of the plurality of applications or providing an advertisement pertaining to the identified one or more of the plurality of applications.

18. An apparatus, comprising:

a processor; and

a memory storing thereon computer-readable instructions, the computer-readable instructions being configured to;

ascertain a current context of a mobile device, the current context including an indication of a last application opened via the mobile device, wherein the last application opened is one of a plurality of applications installed on the mobile device;

determine a probability, for each of the plurality of applications, that a user of the mobile device will use the corresponding application under the current context, wherein the probability for at least a portion of the plurality of applications is determined by applying a computer-generated model to the current context, wherein the computer-generated model is associated with the mobile device; and

identify one or more of the plurality of the applications based, at least in part, upon the probability, for each one of the plurality of applications, that the user of the mobile device will use the corresponding application.

19. The apparatus as recited in claim 18, the computer-readable instructions being further configured to:

recommend the identified one or more of the plurality of applications, launch the identified one or more of the plurality of applications, or provide an advertisement pertaining to the identified one or more of the plurality of applications.

20. The apparatus as recited in claim 18, wherein the current context further comprises a value associated with one or more of a Last Location Update, Last Charge Cable, Last Audio Cable, Last Context Trigger, or a Last Context Pulled.