Methods for geotemporal fingerprinting

• US 8,924,433 B2
• Filed: 11/08/2012
• Issued: 12/30/2014
• Est. Priority Date: 11/08/2012
• Status: Active Grant

• Current Assignee: Mastercard International Incorporated (MasterCard Incorporated)
• Original Assignee: Mastercard International Incorporated (MasterCard Incorporated)
• Inventors: Howe, Justin Xavier
• Primary Examiner(s): Saeed, Usmaan
• Assistant Examiner(s): Perez-Arroyo, Raquel
• Application Number:
  US13/671,791
• Publication Number:
  US 20140129596A1
• Time in Patent Office: 782 Days
• Field of Search: 707/803, 705/16, 705/39, 705/64, 705/21, 705/26.1, 455/410, 455/411, 455/456.1, 419/38
• US Class Current: 707/803
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/958 Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
• CPC Class Codes: G06F 21/31 User authentication
• CPC Class Codes: G06F 2221/2111 Location-sensitive, e.g. geographical location, GPS
• CPC Class Codes: G06Q 20/3224 Transactions dependent on location of M-devices
• CPC Class Codes: G06Q 20/4015 using location information
• CPC Class Codes: H04L 63/0876 based on the identity of the terminal or configuration, e.g. MAC address, hardware or software configuration or device fingerprint
• CPC Class Codes: H04W 12/06 Authentication
• CPC Class Codes: H04W 12/63 Location-dependent; Proximity-dependent
• CPC Class Codes: H04W 12/71 Hardware identity
• CPC Class Codes: H04W 4/02 Services making use of location information
• CPC Class Codes: H04W 4/029 Location-based management or tracking services

Abstract

Records of geotemporal data for a plurality of users from a database associated with on-line and/or mobile cellular activities are used to generate a geotemporal fingerprint of a user. The geolocation history associated with the user'"'"'s on-line and/or mobile cellular activities from one such database can be correlated with a user'"'"'s geolocation data from a separate on-line database associated with a different activity. For example, the geolocation history or geotemporal fingerprints associated with on-line and/or mobile cellular activities from one particular database can be correlated with those associated with payment card usage. Such information can be used to authenticate a user, for example, as a security measure for payment card users and issuers, for registrationless credit security applications, and for gathering relevant data for advertising campaigns.

Claims

1. A method for linking a first user account associated with a first database comprising geotemporal data records for a plurality of users with a second user account associated with a second database comprising geotemporal data records for the plurality of users, each of the geotemporal data records comprising temporal data and a geolocation indicating a time and place the geotemporal data record is generated and a User ID associated with one of the plurality of users, the method comprising:

retrieving geotemporal data records for a first user from the first database generated over a predetermined period of time, each of the geotemporal data records retrieved comprising a first User ID associated with the first user;

determining fields for defining for each user a geotemporal fingerprint associated with the user from the geotemporal data records comprising the corresponding User ID, the fields distinguishing the user from other users associated with the first database;

generating a first geotemporal fingerprint corresponding to the first User ID based on the determined fields;

retrieving geotemporal data records from the second database generated for the plurality of users over the predetermined period of time, each of the geotemporal data records retrieved from the second database comprising a second User ID associated with one of the plurality of users;

generating, based on the determined fields, a set of second geotemporal fingerprints from the geotemporal data records retrieved from the second database, each second geotemporal fingerprint of the set being generated from geotemporal data records comprising the second User ID; and

determining, from the set of second geotemporal fingerprints generated from the second database, a best match to the first geotemporal fingerprint, comprising identifying a set of geotemporal data record pairs occurring within a predefined time period of one another, each pair comprising a geotemporal data record corresponding to the first User ID and a geotemporal data record corresponding to one of the second User IDs, and calculating a parameter indicating a geographical distance between the geolocations of each of the geotemporal data record pairs, to identify the best match to the first geotemporal fingerprint,

linking the second User ID corresponding to the best match with the first User ID corresponding to the first geotemporal fingerprint.

2. The method according to claim 1, further comprising identifying and recording a georegion encompassing the geolocation for each of the geotemporal data records retrieved from the first database and the second database, wherein the fields comprise at least a primary georegion, the primary georegion corresponding to the georegion in which each of the plurality of users is located for a longest time period within the predetermined period of time, the method further comprising calculating a total length of time from the temporal data associated with each of the georegions for each User ID, identifying the primary georegion for each User ID from the calculated total length of time, and generating the geotemporal fingerprint comprising the primary georegion associated with each User ID.

3. The method according to claim 2, further comprising identifying geotemporal fingerprints from the set generated from the second database for which the georegion identified as the primary georegion is the same as the georegion identified as the primary georegion of the first geotemporal fingerprint as potential matches;

and

comparing the geolocation and temporal data of the geotemporal data records in the fields of the first geotemporal fingerprint with the geolocation and temporal data in the fields of the geotemporal data records associated with each of the potential matches to identify the best match.

4. The method of claim 3, wherein the parameter is a great circle distance between the geolocations of each of the geotemporal data record pairs, the method further comprising calculating the great circle distance calculated for each of the geotemporal data record pairs within the set for each potential match.

5. The method of claim 4, wherein the best match is the one of the potential matches having a lowest mean great circle distance.

6. The method of claim 1, wherein the first database comprises cell phone ping data and the second database comprises geotemporal data records generated by payment card usage for the plurality of users.

7. The method of claim 1, wherein at least one of the first database and the second database comprises geotemporal data records generated by a social network activity.

8. The method of claim 7, wherein the geolocations and temporal data recorded in the geotemporal data records generated by the social network activity comprise at least one of internet protocol (IP) addresses, global positioning system (GPS) data, cellular phone ping data, call record details, and time-stamped textual data.

9. The method of claim 7, wherein the first database comprises geotemporal data records generated by the social network activity and the second database comprises geotemporal data records generated by payment card usage for the plurality of users.

10. The method of claim 2, wherein the fields for generating each geotemporal fingerprint further comprise a secondary georegion, the secondary georegion corresponding to the georegion in which each of the plurality of users is located for a second longest time period within the predetermined period of time, the method further comprising identifying the secondary georegion for each User ID from the calculated total length of time, and generating the geotemporal fingerprint further comprising the secondary georegion associated with each User ID.