Most relevant application recommendation based on crowd-sourced application usage data

• US 10,108,748 B2
• Filed: 09/30/2014
• Issued: 10/23/2018
• Est. Priority Date: 05/30/2014
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Marti, Lukas M., Zhou, Zehua, Bartunek, Jeffrey Michael, Shao, Weili, Popescu, Liviu Teodor, Cao, Lili, Huang, Ronald K.
• Primary Examiner(s): Hasan, Syed H
• Application Number:
  US14/501,961
• Publication Number:
  US 20150347437A1
• Time in Patent Office: 1,484 Days
• Field of Search: None
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/90324 using system suggestions
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0205 Location or geographical consideration
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products

Abstract

Crowd-sourced localized application usage data is collected from mobile devices at a usage location and sent to a network-based service. The network-based service analyzes the data to determine a single most relevant application correlated to the usage location. Once the most relevant application is determined, a recommendation for the application is sent to client devices operating at the usage location. In some implementations the data is processed to determine whether the usage location is a chained venue, a large venue or an event. Once the usage location has been determined, the most relevant application can be selected for recommendation.

Claims

1. A method comprising:

receiving, at a server computer and from a plurality of mobile devices, anonymous, localized application usage data correlated to a usage location where the mobile devices are operating;

determining a set of applications that are relevant to the usage location based on the anonymous, localized application usage data;

correlating the set of applications with point-of-interest (POI) data associated with a chained venue based on the usage location, wherein the chained venue is one of multiple venues that share a brand;

identifying the usage location as the chained venue based on the correlating;

selecting an application for the chained venue from the set of applications based on the identifying; and

sending, by the server computer to a client device operating at the usage location, a link to the chained venue application.

2. The method of claim 1, wherein identifying the usage location as a chained venue, further comprises:

pairing POIs with the set of applications based on usage location to generate application-POI pairings;

for each application in an application-POI pairing, determining a POI score for each POI based on a number of times the POI is included in a pairing;

creating a first list of POI scores for each application;

application based on a number of times the application is included in a pairing;

for each POI in an application-POI pairing, determining an application score for each

creating a second list of application scores for each POI;

comparing the first and second lists to determine names of applications and POIs that match;

creating a third list of applications and POIs with matching names; and

identifying the usage location as a chained venue based on the third list of applications and POIs with matching names.

3. The method of claim 2, further comprising:

comparing names of matched applications and POIs in the third list with category names; and

filtering out the matched applications and POIs that have names that do not match the category names.

4. The method of claim 2, wherein comparing the first and second lists further comprises:

sorting the first list by POI score;

sorting the second list by application score; and

comparing the sorted first and second lists to determine names of applications and POIs that match.

5. The method of claim 1, further comprising:

calculating a percentage of a maximum application score for the set of relevant applications for the usage location; and

reducing a usage area for one or more applications in the set of applications based on the calculated percentage.

6. A method comprising:

receiving, at a server computer and from a plurality of mobile devices, anonymous, localized application usage data correlated to a usage location where the mobile devices are operating;

determining a set of applications that are relevant to the usage location based on the anonymous, localized application usage data;

identifying the usage location as an event location by;

determining a usage ratio for each application in the set of applications;

determining a spatial entropy for each application in the set of applications based on its respective usage ratio;

determining a local burstiness score for each application in the set of applications based on its respective usage ratio and spatial entropy;

detecting an event start based on the local burstiness scores;

selecting an event application from the set of applications based on its local burstiness score; and

sending, by the server computer to a client device operating at the usage location, a link to the event application.

7. The method of claim 6, further comprising:

determining an end of the event by monitoring the collective local burstiness of the set of applications over a period of time.

8. A system comprising:

one or more processors;

memory including instructions, which, when executed by the one or more processors, cause the one or more processors to perform operations comprising;

receiving, from a plurality of mobile devices, anonymous, localized application usage data correlated to a usage location where the mobile devices are operating;

determining a set of applications that are relevant to the usage location based on the anonymous, localized application usage data;

correlating the set of applications with point-of-interest (POI) data associated with a chained venue based on the usage location, wherein the chained venue is one of multiple venues that share a brand;

identifying the usage location as the chained venue based on the correlating;

selecting an application for the chained venue from the set of applications based on the identifying; and

sending to a client device operating at the usage location, a link to the chained venue application.

9. The system of claim 8, wherein identifying the usage location as a chained venue, further comprises:

pairing POIs with the set of applications based on usage location to generate application-POI pairings;

for each application in an application-POI pairing, determining a POI score for each POI based on a number of times the POI is included in a pairing;

creating a first list of POI scores for each application;

for each POI in an application-POI pairing, determining an application score for each application based on a number of times the application is included in a pairing;

creating a second list of application scores for each POI;

comparing the first and second lists to determine names of applications and POIs that match;

creating a third list of applications and POIs with matching names; and

identifying the usage location as a chained venue based on the third list of applications and POIs with matching names.

10. The system of claim 9, the operations further comprising:

comparing names of matched applications and POIs in the third list with category names; and

filtering out the matched applications and POIs that have names that do not match the category names.

11. The system of claim 9, wherein comparing the first and second lists further comprises:

sorting the first list by POI score;

sorting the second list by application score; and

comparing the sorted first and second lists to determine names of applications and POIs that match.

12. The system of claim 8, the operations further comprising:

calculating a percentage of a maximum application score for the set of relevant applications for the usage location; and

reducing a usage area for one or more applications in the set of applications based on the calculated percentage.

13. A system comprising:

one or more processors;

memory including instructions, which, when executed by the one or more processors, cause the one or more processors to perform operations comprising;

receiving, from a plurality of mobile devices, anonymous, localized application usage data correlated to a usage location where the mobile devices are operating;

determining a set of applications that are relevant to the usage location based on the anonymous, localized application usage data;

identifying the usage location as an event location by;

determining a usage ratio for each application in the set of applications;

determining a spatial entropy for each application in the set of applications based on its respective usage ratio;

determining a local burstiness score for each application in the set of applications based on its respective usage ratio and spatial entropy;

detecting an event start based on the local burstiness scores;

selecting an event application from the set of applications based on its local burstiness score; and

sending, to a client device, operating at the usage location, a link to the event application.

14. The system of claim 13, the operations further comprising:

determining an end of the event by monitoring a local burstiness of the set of applications over a period of time.