Online advertising valuation apparatus and method

• US 8,027,876 B2
• Filed: 06/14/2007
• Issued: 09/27/2011
• Est. Priority Date: 08/08/2005
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Yoogli Incorporated
• Inventors: Taylor, David C.
• Primary Examiner(s): Weiss, John
• Assistant Examiner(s): CHORNESKY, ADAM B
• Application Number:
  US11/763,408
• Publication Number:
  US 20070288503A1
• Time in Patent Office: 1,566 Days
• Field of Search: 705/14, 705/14.49, 705/14.52, 705/14.66, 707/102, 707/E17, 707/999.102, 707/E17.109
• US Class Current: 705/14.49
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0242 Determining effectiveness of advertisements
• CPC Class Codes: G06Q 30/0248 Avoiding fraud
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0254 based on statistics
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface

Abstract

A method comprising for determining the value provided to an advertiser through the advertiser'"'"'s online advertisements. The method may begin with providing an online advertisement linked to content. A macro-context may be obtained that quantifies the affinity of the content for a plurality of domains corresponding to a semantic space. A personalization vector may be obtained that quantifies the affinity of at least one aspect of a user for the plurality of domains. The user may then select the online advertisement. A match value may be calculated that quantifies the similarity between the personalization vector and the macro-context. The advertiser may then be charged a monetary amount for the user'"'"'s “click.” The monetary amount may be based, at least in part, on the match value.

Claims

1. A method comprising:

providing an online advertisement linked to content;

obtaining, by a computer system, a macro-context numerically quantifying the affinity of the content for each subject matter domain of a plurality of subject matter domains;

obtaining, by the computer system, a personalization vector numerically quantifying the affinity of a user for each subject matter domain of the plurality of subject matter domains;

selecting, by the user, the online advertisement;

directing, by the computer system in direct response to the selecting, the user to the first content;

calculating, by the computer system, a match value quantifying the similarity between the personalization vector and the macro-context.

2. The method of claim 1, further comprising selecting a match threshold corresponding to a particular level of similarity between the personalization vector and the macro-context.

3. The method of claim 2, wherein the match threshold is selected by an advertiser associated with the online advertisement.

4. The method of claim 2, further comprising billing the advertiser a first amount when the match value is less than the match threshold.

5. The method of claim 4, further comprising billing the advertiser a second amount when the match value is more than the match threshold.

6. The method of claim 5, wherein the second amount is greater than the first amount.

7. The method of claim 6, wherein calculating the match value begins upon selection by the user of the online advertisement.

8. The method of claim 7, wherein the personalization vector is derived at least in part from an online search and click history of the user.

9. The method of claim 8, wherein calculating a match value comprises multiplying together the macro-context and the personalization vector.

10. The method of claim 9, wherein multiplying comprises using one of a dot product and a weighted dot product.

11. The method of claim 1, further comprising billing an advertiser associated with the online advertisement a greater amount when the match value is above a match threshold.

12. The method of claim 1, further comprising billing an advertiser associated with the online advertisement a greater amount when the match value is above a match threshold selected by the advertiser.

13. The method of claim 1, wherein calculating the match value begins upon selection by the user of the online advertisement.

14. The method of claim 1, wherein the personalization vector is derived at least in part from an online search and click history of the user.

15. The method of claim 1, wherein calculating a match value comprises multiplying together the macro-context and the personalization vector.

16. The method of claim 1, wherein calculating a match value comprises multiplying together the macro-context and the personalization vector using one of a dot product and a weighted dot product.

17. A method comprising:

viewing, by a user via a computer system, first content;

obtaining, by the computer system, a first vector containing numerical values quantifying the affinity of the first content for each subject matter domain of a plurality of subject matter domains;

providing an online advertisement linked to second content;

obtaining, by the computer system, a second vector containing numerical values quantifying the affinity of the second content for each subject matter domain of the plurality of subject matter domains;

obtaining, by the computer system, a user vector containing numerical values quantifying the affinity of the user for each subject matter domain of the plurality of subject matter domains, the user vector being derived as least in part from the first vector;

selecting, by the user, the online advertisement;

directing, by the computer system in direct response to the selecting, the user to the second content; and

calculating, by the computer system, a match value quantifying the similarity between the second vector and the user vector.

18. The method of claim 17, wherein the user vector is derived at least in part from a third vector corresponding to a third content viewed by the user via the computer system, the third vector containing numerical values quantifying the affinity of the third content for each subject matter domain of the plurality of subject matter domains.

19. The method of claim 18, wherein the user vector is derived at least in part from a fourth vector corresponding to a fourth content viewed by the user via the computer system, the fourth vector containing numerical values quantifying the affinity of the fourth content for each subject matter domain of the plurality of subject matter domains.

20. A method comprising:

providing an online advertisement linked to content;

obtaining, by a computer system, a first vector containing numerical values quantifying the affinity of the content for each subject matter domain of a plurality of subject matter domains;

obtaining, by the computer system, a second vector containing numerical values quantifying the affinity of a user for each subject matter domain of the plurality of subject matter domains;

selecting, by the user, the online advertisement;

directing, by the computer system in direct response to the selecting, the user to the content;

calculating, by the computer system, a match value quantifying the similarity between the first vector and the second vector;

identifying an advertiser associated with the online advertisement; and

using the match value in calculating the monetary amount charged the advertiser for the selection of the online advertisement.