App recommendation using crowd-sourced localized app usage data

摘要

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.

主权项

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 and a usage location 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; identifying partitions in a region over a geographical area, wherein the partitions make up a grid over the geographical area; incrementing a plurality of counters based on the usage locations of the plurality of app usage records, each counter corresponding to a different partition; and for each of one or more of the partitions:
calculating a statistical value measuring a localized usage of the first application within the respective partition relative to a plurality of other partitions based on a counter of the respective partition and counters of the other partitions;comparing the statistical value to a threshold; andidentifying the first application as locally relevant to the respective partition in the region of the geographical area when the statistical value exceeds the threshold.