LOCATION-BASED ANALYTIC PLATFORM AND METHODS

• US 20150199699A1
• Filed: 03/24/2015
• Published: 07/16/2015
• Est. Priority Date: 01/04/2013
• Status: Active Grant

• Current Assignee: PlaceIQ, Inc.
• Original Assignee: PlaceIQ, Inc.
• Inventors: Milton, Stephen, McCall, Duncan
• Granted Patent: US 10,262,330 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• 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: H04W 4/029 Location-based management or tracking services

Abstract

Provided is a process of learning an audience member function, the process including: obtaining a training set of geographic data describing geolocation histories of a plurality of mobile devices, wherein members of the training set are classified according to whether the respective member of the training set is a member of an audience; retrieving attributes of geolocations in the geolocation histories from a geographic information system; learning feature functions of an audience member function based on the training set, wherein at least some of the feature functions are a function of the retrieved attributes of geolocation, wherein the feature functions are learned, at least in part, by calculating a plurality of impurity measures for candidate feature functions and selecting one of the candidate feature functions based on the relative values of the impurity measures; and storing the feature functions of the audience member function in an audience repository.

Claims

1. A method of learning an audience member function, the method comprising:

obtaining, with one or more processors, a training set of geographic data describing geolocation histories of a plurality of mobile devices, wherein members of the training set are classified according to whether the respective member of the training set is a member of an audience;

retrieving, with one or more processors, attributes of geolocations in the geolocation histories from a geographic information system;

learning, with one or more processors, feature functions of an audience member function based on the training set, wherein at least some of the feature functions are a function of the retrieved attributes of geolocation, wherein the feature functions are learned, at least in part, by calculating a plurality of impurity measures for candidate feature functions and selecting one of the candidate feature functions based on the relative values of the impurity measures; and

storing, with one or more processors, the feature functions of the audience member function in an audience repository.

2. The method of claim 1, comprising:

after storing the feature functions of the audience member function in the audience repository, performing steps comprising;

receiving data describing a content request from a given mobile device at a given time at a given geographic location;

retrieving the audience member function from the audience repository;

determining audience membership, at least in part, by inputting the given device, the given time, and the given geographic location into the audience membership function;

in response to the determination, selecting content corresponding to the audience;

causing the selected content to be sent to the given mobile device.

3. The method of claim 1, wherein:

the audience member function is a weighted combination of the feature functions.

4. The method of claim 1, wherein feature functions include an adaptive basis function learned according to the training set.

5. The method of claim 1, wherein the feature functions are learned, at least in part, by performing steps comprising:

selecting a subset of the training set that has a selected dimension larger than a threshold value;

for each of a plurality of other dimensions, and for each of a plurality of values of each of the plurality of other dimensions, calculating an impurity measure corresponding to respective value in the respective other dimension;

selecting another dimension and a value based on the smallest impurity measure among the calculated impurity measures.

6. The method of claim 5, wherein the impurity measure is based on an entropy of the subset greater than the respective value in the respective other dimension.

7. The method of claim 5, comprising:

determining that more than a threshold amount of training set is greater than the respective value in the respective dimension.

8. The method of claim 5, comprising:

before calculating impurity measures, determining both that at least some of the subset is part of the audience and that at least some of the subset is not part of the audience.

9. The method of claim 1, comprising:

sampling the training set a plurality of times to form a plurality of subsets;

learning intermediate feature functions on each of the plurality of subsets; and

determining aggregate feature functions from the intermediate feature functions.

10. A method of selecting content based on audience membership, the method comprising:

receiving, with one or more processors, data describing a content request from a given mobile device at a given time at a given geographic location;

obtaining, with one or more processors, audience membership vector function having a plurality of audience member functions;

calculating, with one or more processors, the audience membership vector, at least in part, by inputting the given device, the given time, and the given geographic location into each of the plurality of audience membership functions;

determining, with one or more processors, that some components of the audience membership vector function satisfy a respective threshold for the respective component;

in response to the determination, selecting, with one or more processors, content corresponding to the components of the audience membership vector function that satisfy the respective threshold;

causing, with one or more processors, the selected content to be sent to the given device.

11. The method of claim 10, wherein:

calculating the audience membership vector is performed before receiving the data describing the content-request

12. The method of claim 10, wherein causing the selected content to be sent to the given device comprises sending the selected content or sending a value upon which a determination is made to send the selected content.

13. The method of claim 10, comprising:

determining the audience membership functions based on user profiles formed, at least in part, by attributing attributes of geographic areas in which users have been geolocated to the respective user.

14. The method of claim 13, comprising:

obtaining attributes of a geographic area;

augmenting records in a geographic information system by attributing the attributes of the geographic area to geographic locations in the geographic area based on population profiles in the geographic area for the respective geographic locations; and

determining the audience membership functions based on patterns in the augmented records corresponding to user geolocations.

15. The method of claim 13, comprising:

detecting that two different user device identifiers have related patterns in location history;

designating the two different user device identifiers as corresponding to the same given user profile based on the detected related patterns in location history, wherein the audience membership functions are determined based, in part, on the given user profile and location histories corresponding to the two different user device identifiers.

16. The method of claim 10, comprising:

obtaining a history of geolocations from a provider of the content request, the history of geolocations being geolocations of a plurality of user mobile devices sending a plurality of requests for content at different times;

calculating a measure of quality of geolocation data from the provider based on one or more distributions in the history of geolocations; and

selecting the content based on the measure of quality.

17. The method of claim 10, comprising:

after causing the content to be sent, determining that the given mobile device visited a geographic location to which the content relates;

estimating an amount of visits to the geographic location based on the determination and an estimated amount of undetected visits by users sharing an attribute with a user of the given mobile device; and

calculating an effectiveness of the content in causing visits to the geographic location based on the estimated amount of visits.

18. The method of claim 10, comprising:

obtaining location histories of a plurality of mobile devices, each location history including time-stamped geographic locations of a respective mobile device among the plurality of mobile devices;

abstracting the location histories into a sequence of states by clustering the plurality of location histories;

analyzing the sequence of states to ascertain the significance of the states to an event relating to a consumer behavior; and

selecting a feature of at least one of the audience membership functions based on the analysis.