METHODS AND APPARATUS TO DE-DUPLICATE IMPRESSION INFORMATION

• US 20150046579A1
• Filed: 12/30/2013
• Published: 02/12/2015
• Est. Priority Date: 08/12/2013
• Status: Active Grant

• Current Assignee: Nielsen Company (US) LLC (RR Donnelley & Sons Company)
• Original Assignee: Nielsen Company (US) LLC (RR Donnelley & Sons Company)
• Inventors: Perez, Albert Ronald, Zhang, Mimi
• Granted Patent: US 9,313,294 B2
• Time in Patent Office: Days
• US Class Current: 709/224
• CPC Class Codes: G06F 16/23 Updating
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06Q 30/0246 Traffic
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34

Abstract

Example methods and apparatus to de-duplicate impression information. An example method includes accessing a first set of cookies and a set of user identifiers, the cookies and user identifiers corresponding to devices accessing media via the Internet, identifying a pattern in the first set of cookies, obtaining impression information from a database proprietor, the impression information comprising a second set of cookies, identifying a subset of the second set of cookies that are associated with a same person based on the pattern, and associating impressions corresponding to the identified subset with the same person.

Claims

1. A method, comprising:

accessing a first set of cookies and a set of user identifiers, the cookies and user identifiers corresponding to devices accessing media via the Internet;

identifying, using a processor, a pattern in the first set of cookies;

obtaining impression information from a database proprietor, the impression information comprising a second set of cookies;

identifying, using the processor, a subset of the second set of cookies that are associated with a same person based on the pattern; and

associating, using the processor, impressions corresponding to the identified subset with the same person.

2. A method as defined in claim 1, wherein identifying the pattern comprises:

identifying a potential pattern in the first set of cookies;

determining a first error between a first demographic estimate based on the potential pattern in the first set of cookies and a second demographic estimate based on the user identifiers; and

when the first error is less than a threshold, determining the potential pattern to be the pattern.

3. A method as defined in claim 2, wherein the threshold is a lowest error associated with another potential pattern in the second set of cookies.

4. A method as defined in claim 1, wherein identifying the pattern comprises iteratively determining an error based on patterns identified from different portions of data payloads of the cookies.

5. A method as defined in claim 4, wherein each iteration corresponds to a different portion of the data payloads of the cookies.

6. A method as defined in claim 1, wherein the cookies in the second set of cookies are not uniquely associated with individual persons.

7. A method as defined in claim 1, wherein the first set of cookies are associated with the database proprietor.

8. A method as defined in claim 1, wherein the first set of cookies and the set of user identifiers are collected from an audience measurement panel.

9. A method as defined in claim 1, wherein associating impressions corresponding to the identified subset with the same person comprises reducing a number of unique users associated with the identified subset to be one unique user.

10. An apparatus, comprising:

a cookie pattern identifier to access a first set of cookies and a set of user identifiers and to identify a pattern in the first set of cookies, the cookies and user identifiers corresponding to devices accessing media via the Internet;

an impression collector to access impression information from a database proprietor, the impression information comprising a second set of cookies; and

an impression de-duplicator to identify a subset of the second set of cookies that are associated with a same person based on the pattern, and associate impressions corresponding to the identified subset with the same person.

11. An apparatus as defined in claim 10, further comprising:

a pattern evaluator to determine a first error between a first demographic estimate based on a potential pattern in the first set of cookies and a second demographic estimate based on the user identifiers, the cookie pattern identifier to identify the potential pattern in the first set of cookies and, when the first error is less than a threshold, determine the potential pattern to be the pattern.

12. An apparatus as defined in claim 11, wherein the pattern evaluator is to determine the first error as an overcount of the first demographic estimate relative to a count of users based on the user identifiers.

13. An apparatus as defined in claim 10, wherein the cookie pattern identifier is to identify the pattern by iteratively determining an error based on patterns identified from different portions of data payloads of the cookies.

14. An apparatus as defined in claim 13, wherein each iteration corresponds to a different portion of the data payloads of the cookies.

15. An apparatus as defined in claim 10, wherein the cookies in the second set of cookies are not uniquely associated with individual persons.

16. An apparatus as defined in claim 10, wherein the impression de-duplicator is to associate impressions corresponding to the identified subset with the same person by reducing a number of unique users associated with the identified subset to be one unique user.

17. A tangible computer readable storage medium comprising computer readable instructions which, when executed, cause a processor to at least:

access a first set of cookies and a set of user identifiers, the cookies and user identifiers corresponding to accessing media via the Internet;

identify a pattern in the first set of cookies;

obtain impression information from a database proprietor, the impression information comprising a second set of cookies;

identify a subset of the second set of cookies that are associated with a same person based on the pattern; and

associate impressions corresponding to the subset with the same person.

18. A storage medium as defined in claim 17, wherein the instructions cause the processor to identify the pattern by:

identifying a potential pattern in the first set of cookies;

determining first error between a first demographic estimate based on the potential pattern in the first set of cookies and a second demographic estimate based on the user identifiers; and

when the first error is less than a threshold, determining the potential pattern to be the pattern.

19. A storage medium as defined in claim 18, wherein the threshold is a lowest error associated with another potential pattern in the second set of cookies.

20. A storage medium as defined in claim 17, wherein the instructions cause the processor to identify the pattern by iteratively determining an error based on patterns identified from portions of a data payload of the cookies.

21. A storage medium as defined in claim 20, wherein each iteration corresponds to a different portion of the data payload of the cookies.

22. A storage medium as defined in claim 17, wherein the second set of cookies are not uniquely associated with individual persons.

23. A storage medium as defined in claim 17, wherein the first set of cookies are associated with the database proprietor.

24. A storage medium as defined in claim 17, wherein the first set of cookies and the set of user identifiers are collected from an audience measurement panel.