Rendering advertisements with documents having one or more topics using user topic interest information

• US 8,296,285 B2
• Filed: 11/29/2011
• Issued: 10/23/2012
• Est. Priority Date: 06/30/2003
• Status: Expired due to Term

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Bharat, Krishna
• Primary Examiner(s): Casanova, Jorge A
• Application Number:
  US13/305,910
• Publication Number:
  US 20120072291A1
• Time in Patent Office: 329 Days
• Field of Search: 707999003-999006, 707/709, 705/14.54
• US Class Current: 707/709
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0207 Discounts or incentives, e.g. coupons or rebates
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0273 Determination of fees for advertising
• CPC Class Codes: H04L 12/1859 adapted to provide push services, e.g. data channels
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99934 Query formulation, input preparation, or translation
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99936 Pattern matching access

Abstract

Ambiguities with respect to a user topic interest may be resolved so that useful topic-relevant ads can be presented. Such ambiguities may be resolved by monitoring user behavior, determining a user topic interest (e.g., from a plurality of different candidate topics) based on the monitored behavior, and serving ads relevant to the determined user topic interest.

Claims

1. A computer-implemented method comprising:

a) determining, by a computer system including at least one computer on a network, a topic for each of a plurality of document regions of a document, wherein the plurality of document regions are intrinsic to the document, and wherein the document is a single Web page;

b) determining, by the computer system, a topic that a user is interested in, from among the plurality of determined topics, using at least monitored actions of the user with respect to at least one of the regions of the document;

c) adjusting, by the computer system, scores of candidate advertisements using at least the determined topic that the user is interested in, wherein an amount by which the score of a candidate advertisement is adjusted is greater for a first type of monitored action of the user with respect to at least one of the regions of the document than a second type of monitored action of the user with respect to at least one of the regions of the document; and

d) controlling, by the computer system, serving of at least one of the candidate advertisements in association with the document using the adjusted scores of one or more of the candidate advertisements.

2. The computer-implemented method of claim 1 wherein the plurality of document regions are defined by at least one of (A) links included in the document, (B) section tags included in the document, or (C) a statistical analysis of text included in the document.

3. The computer-implemented method of claim 1 wherein the plurality of document regions are a plurality of different spatial portions of the document.

4. The computer-implemented method of claim 1 wherein the plurality of document regions are a plurality of different temporal segments of the document.

5. The computer-implemented method of claim 1 wherein the document is an email document.

6. A computer-implemented method comprising:

a) monitoring, by a computer system including at least one computer on a network, actions of a user with respect to a document including a plurality of regions associated with a plurality of topics, wherein the plurality of document regions are intrinsic to the document, and wherein the document is a single Web page;

b) determining, by the computer system, a region of the document that the user is interested in using at least the monitored actions of the user;

c) determining, by the computer system, the topic associated with the determined region;

d) determining, by the computer system, scores of candidate advertisements using at least the determined topic; and

e) controlling, by the computer system, serving of at least one of the candidate advertisements in association with the document using the scores of one or more of the candidate advertisements.

7. The computer-implemented method of claim 6 wherein the plurality of regions are a plurality of different spatial portions of the document.

8. The computer-implemented method of claim 6 wherein the plurality of regions are a plurality of different temporal segments of the document.

9. The computer-implemented method of claim 6 wherein the document is an email document.

10. Apparatus comprising:

a) one or more processors; and

b) one or more storage devices storing program instructions which, when executed by the one or more processors, cause the one or more processors to perform a method including

1) determining a topic for each of a plurality of document regions of a document, wherein the plurality of document regions are intrinsic to the document, and wherein the document is a single Web page,

2) determining a topic that a user is interested in, from among the plurality of determined topics, using at least monitored actions of the user with respect to at least one of the regions of the document,

3) adjusting scores of candidate advertisements using at least the determined topic that the user is interested in, wherein an amount by which the score of a candidate advertisement is adjusted is greater for a first type of monitored action of the user with respect to at least one of the regions of the document than a second type of monitored action of the user with respect to at least one of the regions of the document; and

4) controlling serving of at least one of the candidate advertisements in association with the document using the adjusted scores of one or more of the candidate advertisements.

11. A computer-implemented method comprising:

a) serving, by a computer system including at least one computer on a network, a plurality of candidate advertisements with a document such that an initial subset of the candidate advertisements will be rendered with the document, wherein the document includes a plurality of regions associated with a plurality of topics, wherein the plurality of document regions are intrinsic to the document, wherein the document is a single Web page, and wherein each of the candidate advertisements has an initial score;

b) monitoring, by the computer system, actions of a user with respect to the document;

c) determining, by the computer system, a region of the document that the user is interested in using at least the monitored actions of the user;

d) determining, by the computer system, the topic associated with the determined region;

e) adjusting, by the computer system, the initial scores of candidate advertisements using at least the determined topic to generate an adjusted score for each of the candidate advertisements; and

f) selecting, by the computer system and using the adjusted scores of the candidate advertisements, a new subset of the candidate advertisements such that the new subset of candidate advertisements will be rendered with the document.

12. The computer-implemented method of claim 11 wherein the plurality of regions are a plurality of different spatial portions of the document.

13. The computer-implemented method of claim 11 wherein the plurality of regions are a plurality of different temporal segments of the document.

14. The computer-implemented method of claim 11 wherein the document is an email document.

15. A computer-implemented method comprising:

a) serving, by a computer system including at least one computer on a network, a plurality of candidate advertisements with a document such that the candidate advertisements will be rendered with the document, with an initial set of relative presentation attributes, wherein the document includes a plurality of regions associated with a plurality of topics, wherein the plurality of document regions are intrinsic to the document, wherein the document is a single Web page, and wherein each of the candidate advertisements has an initial score;

b) monitoring, by the computer system, actions of a user with respect to the document;

c) determining, by the computer system, a region of the document that the user is interested in using at least the monitored actions of the user;

d) determining, by the computer system, the topic associated with the determined region;

e) adjusting, by the computer system, the initial scores of candidate advertisements using at least the determined topic to generate an adjusted score for each of the candidate advertisements; and

f) determining, by the computer system and using the adjusted scores of the candidate advertisements, a new set of relative presentation attributes for the candidate advertisements such that the candidate advertisements will be rendered with the document, with the new set of relative presentation attributes.

16. The computer-implemented method of claim 15 wherein the initial and new sets of relative presentation attributes each define an ordering of the candidate advertisements.

17. The computer-implemented method of claim 15 wherein the initial and new sets of relative presentation attributes each define whether or not each of the candidate advertisements will include an enhanced feature.

18. The computer-implemented method of claim 15 wherein the plurality of regions are a plurality of different spatial portions of the document.

19. The computer-implemented method of claim 15 wherein the plurality of regions are a plurality of different temporal segments of the document.

20. The computer-implemented method of claim 15 wherein the document is an email document.