Automatically generating ads and ad-serving index

• US 8,326,686 B2
• Filed: 03/30/2006
• Issued: 12/04/2012
• Est. Priority Date: 03/30/2006
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Datar, Mayur, Garg, Ashutosh
• Primary Examiner(s): SORKOWITZ, DANIEL M
• Application Number:
  US11/394,135
• Publication Number:
  US 20070239530A1
• Time in Patent Office: 2,441 Days
• Field of Search: None
• US Class Current: 705/14.49
• 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 30/0256 User search
• CPC Class Codes: G06Q 30/0276 Advertisement creation

Abstract

Advertiser repository information (e.g., a list of HTML pages) may be used to automatically generate a page-ad and associated ad information for each page using a subset of features of the page. Subsequently, a page-ad index for all pages from different advertisers may be created. After creating a page-ad index, if a client issues a query (e.g., from a search engine), candidate page-ads may be selected using the page-ads index. If necessary (e.g., if there are more candidate page-ads than requested ads), the candidate page-ads may be entered into an arbitration (e.g., auction). Then, the arbitration may determine a set of one or more winning page-ads to be served for rendering.

Claims

1. A computer-implemented method comprising:

a) accepting, for each of at least one advertiser, by an advertising system including one or more computers, information from at least one advertiser document, wherein the at least one advertiser document defines an inventory of at least one of products and services offered on an online Website of the at least one advertiser;

b) generating ads for the at least one advertiser, by the advertising system, each of the generated ads including

i) a creative, and

ii) offer information,

using the accepted information from the at least one advertiser document;

c) generating, by the advertising system, an index mapping information extracted from the at least one advertiser document to one of (A) advertiser document identifiers for the at least one advertiser document on which the extracted information is found, and (B) ad identifiers for ads generated from the at least one advertiser document on which the extracted information is found;

d) accepting, by the advertising system, additional information, wherein the additional information is one of (A) search query information and (B) document relevance information;

e) determining, by the advertising system, one or more ads relevant to the additional information using the index generated and the additional information; and

f) serving at least one of the determined one or more relevant ads for rendering on a client device,

wherein the offer information is expressed procedurally.

2. The computer-implemented method of claim 1, wherein the at least one advertiser document is a product Web page.

3. The computer-implemented method of claim 1, wherein the at least one advertiser document is a product Web page of an e-commerce Website.

4. The computer-implemented method of claim 1, wherein the at least one advertiser document is a service Web page.

5. The computer-implemented method of claim 1, wherein the offer information is one of (A) an offer per ad impression, (B) a maximum offer per ad impression, (C) an offer per ad selection, (D) a maximum offer per ad selection, (E) an offer per ad conversion and (F) a maximum offer per ad conversion.

6. The computer-implemented method of claim 1, wherein the offer information is expressed in terms of a set currency.

7. The computer-implemented method of claim 1, wherein the offer information is expressed formulaically, and wherein the formula includes a product price extracted from the at least one advertiser document.

8. The computer-implemented method of claim 1, wherein the at least one advertiser document includes a unique online address,

wherein each of the generated ads is associated with a specified landing page to be loaded upon ad selection, and

wherein the specified landing page is set to the unique online address of the at least one advertiser document from which the ad was generated.

9. The computer-implemented method of claim 1, wherein the at least one advertiser document is a Web page including a URL address,

wherein each ad further includes a specified landing page to be loaded upon ad selection, and

wherein the specified landing page is set to the URL address of the Web page from which the ad was generated.

10. The computer-implemented method of claim 1, wherein each of the ad creatives is generated using accepted text from the at least one advertiser document by selecting only some of the accepted text using at least one of (A) font size, (B) font attributes, and (C) Meta information.

11. The computer-implemented method of claim 1, wherein, in the index generated, the one of (A) advertiser document identifiers for the at least one advertiser document on which the extracted information is found, and (B) ad identifiers for ads generated from the at least one advertiser document on which the extracted information is found, includes weights.

12. The computer-implemented method of claim 11, wherein the information from the at least one advertiser document includes terms, each of the terms including one of a word and a phrase,

wherein the index generated maps terms extracted from the at least one advertiser document back to one of (A) advertiser document identifiers for the at least one advertiser document on which the extracted terms are found, and (B) ad identifiers for ads generated from the at least one advertiser document on which such terms are found, and

wherein the weights are determined as a function of at least one of (A) font size, (B) font attributes, and (C) Meta information, of the terms in the at least one advertiser document.

13. The computer-implemented method of claim 1, wherein the at least one advertiser document is a product Web page of an e-commerce Website, which Web page is arranged in a hierarchy defined by product categories.

14. The computer-implemented method of claim 13, wherein at least some of the information for a particular product Web page is inherited from an ancestor Web page.

15. The computer-implemented method of claim 13, wherein offer information for an ad associated with a particular product Web page is inherited from an ancestor Web page.

16. The computer-implemented method of claim 1, wherein the information from the at least one advertiser document includes terms, each of the terms including one of a word and a phrase,

wherein the index generated maps the terms extracted from the at least one advertiser document back to one of (A) advertiser document identifiers for the at least one advertiser document on which such terms are found, and (B) ad identifiers for ads generated from the at least one advertiser document on which such terms are found such that the terms are used as targeting keywords,

wherein the at least one advertiser document is a plurality of product Web pages of an e-commerce Website, which Web pages are arranged in a hierarchy defined by product categories, and

wherein at least one of the terms is inherited from an ancestor Web page.

17. The computer-implemented method of claim 1, wherein the act of finding one or more relevant ads using the index generated and the search query information includes using terms of the search query to lookup at least one of (A) advertiser document identifiers for the at least one advertiser document on which such terms are found, and (B) ad identifiers for ads generated from the at least one advertiser document on which such terms are found.

18. The computer-implemented method of claim 1, further comprising:

g) determining a set of one or more ads using the one or more ads determined to be relevant to the additional information, as candidate ads by

scoring the candidate ads, and

accepting a subset of the candidate ads based on their scores.

19. The computer-implemented method of claim 18 wherein the act of scoring candidate ads uses offer information associated with the ads.

20. The computer-implemented method of claim 18 wherein the act of scoring candidate ads uses performance information associated with the ads.

21. The computer-implemented method of claim 18 wherein the act of scoring candidate ads uses a degree of relevance associated with the ads.

22. The computer-implemented method of claim 18 wherein the act of scoring candidate ads uses information on other pages in the hierarchy of the page for which this ad was created.

23. The computer-implemented method of claim 1 wherein the offer information is expressed procedurally using an embedded set of instructions.

24. The computer-implemented method of claim 1, further comprising:

g) generating, by the advertising system, another index mapping one of (A) advertiser document identifiers and (B) ad identifiers for ads generated from the at least one advertiser document, to information extracted from the at least one advertiser document.

25. Apparatus comprising:

a) at least one processor;

b) an input device; and

c) at least one storage device storing a computer executable code which, when executed by the at least one processor, performs a method of

1) accepting, for each of at least one advertiser, information from at least one advertiser document, wherein the at least one advertiser document defines an inventory of at least one of products and services offered on an online Website of the at least one advertiser,

2) generating ads for the at least one advertiser, each of the generated ads including

i) a creative, and

ii) offer information,

using the accepted information from the at least one advertiser document,

3) generating an index mapping information extracted from the at least one advertiser document to one of (A) advertiser document identifiers for the at least one advertiser document on which the extracted information is found, and (B) ad identifiers for ads generated from the at least one advertiser document on which the extracted information is found,

4) accepting additional information, wherein the additional information is one of (A) search query information and (B) document relevance information;

5) determining one or more ads relevant to the additional information using the index generated and the additional information, and

6) serving at least one of the determined one or more relevant ads for rendering on a client device,

wherein the offer information is expressed procedurally.

26. The apparatus claim 25 wherein the offer information is expressed procedurally using an embedded set of instructions.