APP RECOMMENDATION USING CROWD-SOURCED LOCALIZED APP USAGE DATA

• US 20130325856A1
• Filed: 03/15/2013
• Published: 12/05/2013
• Est. Priority Date: 06/04/2012
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Huang, Ronald K., Marti, Lukas, Soto Matamala, Leonardo A., Tu, Xiaoyuan
• Granted Patent: US 9,510,141 B2
• Time in Patent Office: Days
• US Class Current: 707/724
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• CPC Class Codes: G06F 16/958 Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
• CPC Class Codes: H04L 12/16 Arrangements for providing special services to substations
• CPC Class Codes: H04L 43/106 using time related information in packets, e.g. by adding timestamps
• CPC Class Codes: H04M 7/0024 Services and arrangements where telephone services are combined with data services arrangements which combine a telephonic equipment and a computer H04M7/0012
• CPC Class Codes: H04W 12/02 Protecting privacy or anonymity, e.g. protecting personally identifiable information [PII]
• CPC Class Codes: H04W 12/03 Protecting confidentiality, e.g. by encryption
• CPC Class Codes: H04W 4/02 Services making use of location information
• CPC Class Codes: H04W 4/021 Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
• CPC Class Codes: H04W 4/21 for social networking applications
• CPC Class Codes: H04W 40/242 aging of topology database entries
• CPC Class Codes: H04W 8/18 Processing of user or subscriber data, e.g. subscribed services, user preferences or user profiles; Transfer of user or subscriber data

Abstract

Apps may be tagged with location data when they are used. Mobile device may anonymously submit app usage data. Aggregated app usage data from many mobile devices may be analyzed to determine apps that are particularly relevant to a given location (i.e., exhibiting a high degree of localization). Analysis may include determining the app usage intensity, whether hotspots exist or not at a given location, the spatial entropy of a particular app, the device populations in a particular area, etc. Based on the localized app analysis, apps may be ranked according to local relevance, and, based on this ranking, app recommendations may be provided to a user.

Claims

1. A method comprising:

receiving, at an application recommendation system, a plurality of app usage records from a plurality of mobile devices, wherein the plurality of app usage records each comprise an application identifier corresponding to an application, a usage location corresponding to an execution of the application, and a usage timestamp corresponding to an execution of the application;

analyzing, by the application recommendation system, the plurality of app usage records to;

determine the app usage records for a first application; and

for each of one or more locations;

calculate a statistical value measuring a localized usage at the respective location relative to other locations;

compare the statistical value to a threshold; and

use respective locations when the statistical value exceeds the threshold to identify one or more hotspots of the first application.

2. The method of claim 1 further comprising:

decimating the plurality of app usage records received from the plurality of mobile devices.

3. The method of claim 1 further comprising:

providing the first application to a first user as a recommendation when the first user is at a first location, wherein the first location is a hotspot for the first application.

4. The method of claim 1 further comprising:

providing the first application to a first user as a recommendation when the first user submits a search relating to a first location, wherein the first location is a hotspot for the first application.

5. The method of claim 1, wherein each of the one or more locations is defined as a polygon on a two dimensional map.

6. The method of claim 1, wherein the app recommendation system is distributed across a plurality of server computers.

7. The method of claim 6, wherein the servers utilize map reduce convolution to calculate the statistical value measuring a localized usage at the respective location relative to other locations.

8. A method of partitioning a domain of interest comprising:

receiving, at a server, a plurality of location records each comprising a location and a timestamp from a plurality of mobile devices;

analyzing, by the server, the plurality of location records to determine a device population over the domain of interest; and

based on device population, partitioning the domain of interest into non-uniform regions based on device population.

9. The method of claim 8 further comprising:

detecting device population hotspots over the domain of interest.

10. The method of claim 9, wherein the portioning of the domain of interest uses Voronoi tessellations.

11. The method of claim 10, wherein an input to the Voronoi tessellation is a set of device population hotspots over the domain of interest.

12. The method of claim 8 wherein the partitioned domain of interest is used to analyze local app usage data.

13. The method of claim 8 wherein the partitioned domain of interest is used to asynchronously deliver local app recommendations.

14. The method of claim 8 further comprising:

generating a plurality of buffer polygons around each device population hotspot, wherein the buffer polygons have a predetermined size.

15. The method of claim 14:

extracting a plurality of vertices from each of the buffer polygons;

generating a Voronoi tessellation based on the plurality of vertices and the device population hotspots.

16. A computer readable storage medium having program code stored thereon, the program code including instructions that, when executed by a processor in a device, cause the processor to execute a method comprising:

receiving a plurality of usage records each comprising a location and a timestamp from a plurality of mobile devices;

analyzing the plurality of usage records to determine a device population over the domain of interest;

detecting device population hotspots; and

partitioning the domain of interest into non-uniform regions based on device population hotspots.

17. The computer readable storage medium of claim 16, wherein the portioning of the domain of interest uses Voronoi tessellations.

18. The computer readable storage medium of claim 16, wherein the partitioned domain of interest is used to analyze local app usage data.

19. The computer readable storage medium of claim 16, wherein the method further comprises:

generating a plurality of buffer polygons around each device population hotspot, wherein the buffer polygons have a predetermined size.

20. The computer readable storage medium of claim 19, wherein the method further comprises:

extracting a plurality of vertices from each of the buffer polygons;

generating a Voronoi tessellation based on the plurality of vertices and the device population hotspots.