Targeting users based on persona data

• US 8,751,305 B2
• Filed: 05/23/2011
• Issued: 06/10/2014
• Est. Priority Date: 05/24/2010
• Status: Active Grant

• Current Assignee: 140 PROOF
• Original Assignee: 140 Proof, Inc. (AcuityAds Holdings, Inc.)
• Inventors: Manoogian, John III, Elvekrog, Jon
• Primary Examiner(s): Gartland, Scott D
• Application Number:
  US13/113,905
• Publication Number:
  US 20110288939A1
• Time in Patent Office: 1,114 Days
• Field of Search: 705/14.49, 705/14.66, 705/14.53
• US Class Current: 705/14.49
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0271 Personalized advertisement
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A method of targeted advertisement distribution based on persona data derived from a social network, wherein the social network includes a plurality of content streams, each content stream associated with a user and a user summary. The method includes the steps of receiving an advertisement request from a third party environment with associated content, identifying a content stream that includes a reference to the third party content, identifying a persona based on the user associated with the identified content stream, and serving an advertisement to the third party environment based on the identified persona.

Claims

1. A method of targeted advertisement distribution based on persona data derived from a social network, the social network including a plurality of content streams, each associated with a user summary, the method comprising the steps of:

at a server, receiving an advertisement request from a third party environment with associated content in response to third art environment access by an unknown user, the third party environment having a different domain than the social network;

at the server, detecting a first explicit reference to the third party content in a first content stream generated by a first user and a second explicit reference to the third party content in a second content stream generated by a second user;

at the server, generating a persona based on the first and second user summaries associated with the first and second content streams, respectively;

at the server, selecting an advertisement from a plurality of advertisements for the unknown user by determining the similarity between the advertisement and the generated persona; and

at the server, serving the selected advertisement to the third party environment for the unknown user.

2. The method of claim 1, wherein the first and second explicit references are of the same reference type.

3. The method of claim 2, wherein the reference type is a universal resource identifier linking to the third party content.

4. The method of claim 1, wherein generating a persona based on the first and second user summaries includes the steps of:

abstracting the attributes of the first and second user summaries;

determining the similarities between the abstracted attributes of the first and second user summaries; and

creating a persona from the determined similarities.

5. The method of claim 1, wherein the advertisement includes an advertisement summary comprising a plurality of attributes, determining the similarity between the advertisement and the generated persona comprises calculating a similarity score between the advertisement summary and the persona, and selecting an advertisement comprises selecting the advertisement when the similarity score is above a predetermined threshold.

6. A method of targeted advertisement distribution based on persona data derived from a social network, the social network including a plurality of content streams, each associated with a user and a user summary, the method comprising the steps of:

at a server, receiving an advertisement request from a third party environment for an unknown user, the third party environment hosting an article and having a different domain than the social network;

at a server, detecting a keyword mention in the article;

at a server, detecting the keyword in a first and a second content stream generated by a first and second user, respectively;

at a server, generating a persona based on the first and second user summaries associated with the first and second content streams, respectively;

at a server, selecting an advertisement from a plurality of advertisements by determining the similarity between the advertisement and the generated persona; and

at a server, serving the selected advertisement to the third party environment for the unknown user.

7. The method of claim 6, wherein the keyword is a username.

8. The method of claim 6, wherein the keyword mention in the third party content is detected by detecting an alphanumeric tag.

9. The method of claim 6, wherein the first content stream includes feeds generated from the keyword.

10. The method of claim 6, wherein the second content stream includes content generated by the associated user, the generated content comprising the keyword.

11. The method of claim 6, wherein the step of detecting a keyword mention in the article includes detecting a keyword tagging convention.

12. A method of targeted advertisement distribution based on persona data derived from a social network, the social network including a plurality of content streams, each associated with a user and a user summary, the method comprising the steps of:

at a server, receiving an advertisement request from a third party environment for an unknown user, the third party environment having third party content and a different domain than the social network;

at a server, identifying a content stream generated by a user from the plurality of content streams that includes a reference to the third party content;

at a server, identifying a persona based on the user associated with the identified content stream; and

at a server, serving an advertisement to the third party environment for the unknown user based on the identified persona.

13. The method of claim 12, wherein the third party content is a webpage instance.

14. The method of claim 12, wherein the reference is implicit and includes feeds generated from a keyword.

15. The method of claim 14, wherein the keyword is a username.

16. The method of claim 12, wherein the reference is an explicit reference to the third party content.

17. The method of claim 16, wherein the reference is a link to the third party content.

18. The method of claim 12, wherein the step of identifying a content stream identifies a plurality of content streams including the reference and the step of identifying a persona comprises generating a persona from the plurality of user summaries associated with the plurality of identified content streams.

19. The method of claim 18, wherein the step of generating a persona from the plurality of users includes extracting common attributes from the plurality of user summaries, the persona comprising the common attributes.

20. The method of claim 19, wherein the step of generating a persona from the plurality of users includes abstracting the attributes within each user summary before common attributes are extracted.

21. The method of claim 12, wherein the step of identifying a persona comprises identifying a predefined persona associated with the user with the identified content stream.

22. The method of claim 12, wherein the advertisement includes an associated advertisement summary comprising a list of keywords, the identified persona comprises a list of keywords, and the step of serving an advertisement comprises selecting an advertisement based on the similarity between the associated advertisement summary and the persona.

23. The method of claim 22, wherein the advertisement is selected by calculating a similarity score between the advertisement summary and the persona, and selecting an advertisement comprises selecting the advertisement when the similarity score is above a predetermined threshold.

24. The method of claim 12, wherein the step of identifying a content stream identifies a first content stream with an implicit reference to the third party content and a second content stream with an explicit reference to the third party content, and the step of identifying a persona comprises identifying the persona based on the first and second users associated with the first and second content streams, respectively.