Associating user identities with different unique identifiers

• US 8,620,942 B1
• Filed: 01/26/2012
• Issued: 12/31/2013
• Est. Priority Date: 04/09/2007
• Status: Active Grant

• Current Assignee: LiveRamp, Inc. (LiveRamp Holdings, Inc.)
• Original Assignee: LiveRamp, Inc. (LiveRamp Holdings, Inc.)
• Inventors: Hoffman, Auren, Lizt, Jeremy, Sodera, Vivek, Shah, Manish
• Primary Examiner(s): Fleurantin, Jean B
• Application Number:
  US13/359,228
• Time in Patent Office: 705 Days
• Field of Search: 707/765, 707/766, 707/784, 709/206, 380/202, 380/241
• US Class Current: 707/766
• CPC Class Codes: G06F 16/40 of multimedia data, e.g. slideshows comprising image and additional audio data retrieval of still image data G06F16/50; retrieval of audio data G06F16/60; retrieval of video data G06F16/70
• CPC Class Codes: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]
• CPC Class Codes: G06Q 40/03 Credit; Loans; Processing thereof
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A user correlation system uses aggregated data and matching/comparison in order to assign an association score that determines likelihood that unique identifiers are associated with the same user.

Claims

1. An apparatus, comprising:

one or more processors configured to;

identify a first website containing information associated with a first identifier;

extract a first set of data from the information associated with the first identifier;

identify a second website containing information associated with a second identifier;

extract a second set of data from the information associated with the second identifier;

search for similarities between the first set of data and the second set of data; and

generate an association score that indicates a confidence factor that the first identifier is associated with the second identifier according to the similarities between the first set of data and the second set of data, wherein the one or more of the processors are further configured to assign different weights to content within the first and second set of data based on a probability of the content uniquely identifying an entity.

2. The apparatus according to claim 1 wherein the one or more of the processors are further configured to:

identify a first profile or account on the first website associated with the first identifier;

identify a second profile or account on the second website associated with the second identifier;

extract the first set of data from the first profile or account; and

extract the second set of data from the second profile or account.

3. The apparatus according to claim 1 wherein the first set of data includes a first user name for a first account on the first website and the second set of data includes a second user name for a second account on the second website.

4. The apparatus according to claim 1 wherein:

the first set of data includes a first list of friends; and

the second set of data includes a second list of friends.

5. The apparatus according to claim 4 wherein the association score is based on a percentage of matches between the first list of friends and the second list of friends.

6. A method comprising:

receiving, by a computing device, a request to verify association of a unique identifier with an entity;

searching, by the computing device, for profile information associated with the unique identifier;

comparing, by the computing device, the profile information with reference information associated with the unique identifier;

identifying, by the computing device, similarities between the profile information and the reference information;

identifying, by the computing device, unique types of data associated with high association scores; and

increasing weightings for the unique types of data identified as similar in the profile information and the reference information; and

generating, by the computing device, an association score based on the similarities between the profile information and the reference information, wherein the association score indicates a confidence level that the unique identifier is associated with the entity.

7. The method of claim 6 further comprising searching different online website locations for the profile information.

8. The method according to claim 6, further comprising:

identifying a name in the unique identifier; and

deriving the association score based on the similarities between the name and the profile information.

10. The method according to claim 6 further comprising deriving the association score based the similarities between the unique identifier and user names in the profile information.

9. A method comprising:

receiving, by a computing device, a request to verify association of a unique identifier with an entity;

searching, by the computing device, for profile information associated with the unique identifier;

comparing, by the computing device, the profile information with reference information associated with the unique identifier;

identifying, by the computing device, similarities between the profile information and the reference information;

generating, by the computing device, an association score based on the similarities between the profile information and the reference information, wherein the association score indicates a confidence level that the unique identifier is associated with the entity; and

identifying a domain extension in the unique identifier and generating the association score based on the similarities between the domain extension and the profile information.

11. A computer device containing instructions that when executed by a computer result in:

receiving, by a computing device, a request for an association indicator between a first identifier and a second identifier;

identifying, by the computing device, data sources associated with the first identifier and the second identifier;

extracting, by the computing device, from the data sources a first set of information associated with the first identifier;

extracting, by the computing device, from the data sources a second set of information associated with the second identifier;

search for similarities between the first set of information and the second set of information;

generating, by the computing device, an association score indicating a likelihood the first identifier is associated with the second identifier according to similarities between the first set of information with the second set of information;

searching through an additional data source for a third set of information associated with the first identifier;

comparing the first set of information with the third set of information; and

adjusting the association score according to similarities between the first set of information and the third set of information.

12. The computer device according to claim 11, wherein the first set of information and the second set of information comprises at least one of the following:

photos,

a circle of friends,

usernames, or

address information.

13. The computer device according to claim 11, further comprising:

identifying email signatures associated with the first identifier and the second identifier;

comparing the email signatures; and

generating the association score based on similarities between the email signatures.

14. The computer device according to claim 11, further comprising:

identifying “

from”

, “

reply to”

, or “

on behalf”

of email addresses for emails associated with the first and second identifier; and

generating the association score based on the similarities between the “

from”

, “

reply to”

, or “

on behalf”

of email addresses.

15. The computer device according to claim 11, further comprising:

identifying user profiles or accounts in the data sources;

comparing information identified in the user profiles or accounts; and

generating the association score according to the similarities of the information in the user profiles or accounts.

16. The computer device according to claim 15, further comprising:

identifying an email address in the second set of information associated with the second identifier; and

linking the email address to the first identifier based on the association score.

17. The computer device according to claim 11, wherein:

the first set of information comprises manually entered client information; and

the association score is based on similarities between the client information and the second set of information.