Geotargeting of content by dynamically detecting geographically dense collections of mobile computing devices

Patent metadata

Field	Value
Publication number	US-2016196577-A1
Application number	US-201615072616-A
Country	US
Kind code	A1
Filing date	Mar 17, 2016
Priority date	Feb 14, 2014
Publication date	Jul 7, 2016
Grant date	—

Abstract

Provided is a process of selectively providing content to computing devices based on geographic proximity to dynamically detected events drawing crowds, the process including: obtaining, with one or more computers, data indicative of current geolocations of more than 5,000 mobile computing devices based on information reported by an application executing on the mobile computing devices; inferring, with one or more computers, that an event with a crowd is occurring based on the data indicative of the geolocations indicating an amount of people and a proximity of the people; selecting, with one or more computers, content in response to the inference; and sending, with one or more computers, the selected content to one or more user computing devices for presentation based on proximity between the one or more user computing devices and a geographic location of the event with the crowd.

First claim

What is claimed is:

1 . A method of selectively providing content to computing devices based on geographic proximity to dynamically detected events drawing crowds, the method comprising:
obtaining, with one or more computers, data indicative of current geolocations of more than 5,000 mobile computing devices based on information reported by an application executing on the mobile computing devices; inferring, with one or more computers, that an event with a crowd is occurring based on the data indicative of the geolocations indicating an amount of people and a proximity of the people; selecting, with one or more computers, content in response to the inference; and sending, with one or more computers, the selected content to one or more user computing devices for presentation based on proximity between the one or more user computing devices and a geographic location of the event with the crowd.

2 . The method of claim 1 , wherein inferring that an event with a crowd is occurring comprises clustering the geolocations into a plurality of clusters based on geolocation and time.

3 . The method of claim 2 , wherein the clustering comprises:
for each of more than 50 geographic coordinates among the data indicative of current geolocations of more than 5,000 mobile computing devices:
determining that at least a first plurality of the geographic coordinates have more than a threshold amount of the geographic coordinates within a first threshold distance;
determining that a second plurality of the geographic coordinates, different from the first plurality of the geographic coordinates, are reachable from the first plurality of geographic coordinates, wherein the second plurality of the geographic coordinates are determined to be reachable, at least in part, by:
determining that each of the first plurality of geographic coordinates are within a second threshold distance of at least one of the other first plurality of geographic coordinates; and
determining that each of the second plurality of geographic coordinates is within a third threshold distance of at least one of the first plurality of geographic coordinates.

4 . The method of claim 2 , comprising:
segmenting at least some of the data indicative of current geolocations of more than 5,000 mobile computing devices according to geographic areas into a first segment and a second segment, wherein clustering the geolocations comprises determining whether geolocations in the first segment form clusters without determining whether geolocations in the second segment form clusters with geolocations in the first segment.

5 . The method of claim 1 , wherein inferring that an event with a crowd is occurring comprises performing steps for clustering geolocations.

6 . The method of claim 2 , comprising:
accessing past data indicative of past geolocations of at least some of the mobile computing devices, the past data including geolocations having time stamps more than one day in the past; determining that given geolocations among the data indicative of current geolocations appear more than a threshold amount in the past data in association with a respective corresponding mobile computing device; and in response to the determination, excluding the given geolocations from clustering the geolocations into a plurality of clusters based on geolocation and time.

7 . The method of claim 6 , wherein determining that given geolocations among the data indicative of current geolocations appear more than a threshold amount in the past data in association with a respective corresponding mobile computing device comprises:
determining that at least one of the given geolocations for a given mobile computing device is within a threshold distance of a plurality of past geolocations of the given mobile computing device with greater than a threshold temporal frequency.

8 . The method of claim 6 , wherein determining that given geolocations among the data indicative of current geolocations appear more than a threshold amount in the past data in association with a respective corresponding mobile computing device comprises:
performing steps for determining whether a current geolocation is a routine geolocation of a user.

9 . The method of claim 2 , comprising:
for at least a given one of the plurality of clusters, determining a bounding geographic area of the given cluster at least in part by:
selecting a first geolocation among a plurality of geolocations constituting the given cluster;
selecting a second geolocation among the plurality of geolocations constituting the given cluster;
determining, based on an angle of a line extending between the first geolocation and the second geolocation, whether the line between the first geolocation and the second geolocation defines part of the bounding geographic area.

10 . The method of claim 2 , comprising:
for at least some of the plurality of clusters, performing steps for determining a bounding geographic area.

11 . The method of claim 1 , wherein inferring that an event with a crowd is occurring comprises:
obtaining, based on the data indicative of the geolocations, a measure of mobile-computing device geographic population density sensed by a given one of the mobile computing devices and a geolocation of the given mobile computing device.

12 . The method of claim 11 , wherein the measure of mobile-computing device geographic population density is based on an inventory of wireless beacons in range of the given mobile computing device.

13 . The method of claim 11 , wherein the measure of mobile-computing device geographic population density is determined based on an acoustic signal sensed by the given mobile computing device at least in part by:
determining features of the acoustic signal with a Fourier transform of the acoustic signal; and classifying the acoustic signal as indicating crowd noise based on the features.

14 . The method of claim 1 , wherein inferring that an event with a crowd is occurring comprises:
clustering geolocations among the data indicative of current geolocations of more than 5,000 mobile computing devices; determining a bounding geographic area of a resulting cluster; determining a density of geolocations of the resulting cluster based on the bounding geographic area; and determining that the density is greater than a threshold density.

15 . The method of claim 1 , wherein obtaining data indicative of current geolocations of more than 5,000 mobile computing devices based on information reported by an application executing on the mobile computing devices comprises:
receiving latitude and longitude coordinates determined based on wireless signals received by at least some of the mobile computing devices; and determining that the latitude and longitude coordinates are fresher than a threshold age.

16 . The method of claim 1 , wherein inferring that an event with a crowd is occurring based on the data indicative of the geolocations indicating an amount of people and a proximity of the people comprises:
accessing a record of past events with crowds that have occurred at a given location corresponding to the inferred event with the crowd inferring that the event with the crowd is occurring based on the record indicating a pattern of crowd formation.

17 . The method of claim 1 , wherein selecting content in response to the inference comprises:
querying a business listing to obtain a web address of a business having a geographic location of the event with the crowd; crawling a website accessible through the web address

Assignees

• Retailmenot Inc

Inventors

• Reese David John
• Taberner-Miller Annette
• Adam Lipphei
• Bell Rachel Renee
• Shiffert Nicholas James

Classifications

• G06Q30/0261

  based on user location · CPC title

• G06Q30/0252 Primary

  based on events or environment, e.g. weather or festivals · CPC title

• H04W4/023

  using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds · CPC title

• G06Q30/0259

  based on store location · CPC title

• H04W4/021

  Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences · CPC title