Increasing a number of relevant advertisements using a relaxed match

• US 7,647,242 B2
• Filed: 09/30/2003
• Issued: 01/12/2010
• Est. Priority Date: 09/30/2003
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Bem, Jeremy
• Primary Examiner(s): Stamber; Eric W
• Assistant Examiner(s): Nguyen; Tri V
• Application Number:
  US10/674,888
• Publication Number:
  US 20050071325A1
• Time in Patent Office: 2,296 Days
• Field of Search: 705/14, 707/3
• US Class Current: 705/14.26
• CPC Class Codes: G06F 16/9032 Query formulation
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0225 Avoiding frauds
• CPC Class Codes: G06Q 30/0244 Optimization
• CPC Class Codes: G06Q 30/0249 based upon budgets or funds
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0254 based on statistics
• CPC Class Codes: G06Q 30/0257 User requested
• CPC Class Codes: G06Q 30/0277 Online advertisement

Abstract

The number of ads potentially relevant to search query information may be increased by relaxing the notion of search query keyword matching. This may be done, for example, by expanding a set of ad request keywords to include both query keywords and related keywords. The scores of ads served pursuant to a relaxed notion of matching (those with keyword targeting criteria that matched words related to words in the search query, but not the words from the search query) may be discounted relative to the scores of ads served pursuant to a stricter notion of matching. This may be done by using a score modification parameter, such as an ad performance multiplier (when an ad score is a function of ad performance information) The score modification parameter may be updated to reflect observed performance data, such as that associated with {word-to-related word} mappings.

Claims

1. A computer-implemented method comprising:

a) accepting, by a computer system including at least one computer, search query information including a word;

b) determining, by the computer system, one or more words related to the word included in the accepted search query;

c) generating, by the computer system, an item request including

i) the word included in the accepted search query, and

ii) the one or more words determined to be related to the word included in the accepted search query;

d) retrieving, by the computer system, items using the item request;

e) determining, by the computer system, a score for each of the retrieved items;

f) adjusting, by the computer system, the scores of any items retrieved on the basis of the one or more words determined to be related to the word included in the accepted search query relative to any items retrieved on the basis of the word included in the accepted search query to generate adjusted scores, wherein the act of adjusting the scores includes multiplying each of the scores by a multiplier that is less than one;

g) serving, by the computer system, at least some of the items to a client device for rendering to a user, wherein the serving is controlled, at least in part, using the adjusted scores; and

h) updating, by the computer system, the multiplier using performance information,

wherein the retrieved items are advertisements,

wherein the act of determining a score for each of the retrieved items uses at least one of ad performance information and ad price information, and

wherein the act of updating the multiplier is performed using the formula;

2. The computer-implemented method of claim 1 wherein the act of adjusting the scores includes decreasing the scores.

3. The computer implemented method of claim 1 wherein the performance information includes ad selection information.

4. The computer implemented method of claim 1 wherein the performance information includes ad conversion information.

5. The computer implemented method of claim 1 wherein the act of updating the multiplier is performed using a function that causes the updated multiplier to converge to observed user behavior relevant to performance divided by predicted user behavior relevant to performance.

6. The computer-implemented method of claim 1 wherein the user behavior is selection.

7. The computer-implemented method of claim 1 wherein the user behavior is conversion.

8. The method of claim 1 wherein the act of retrieving ads using the ad request retrieves ads relevant to any one of the words of the generated ad request.

9. A computer-implemented method comprising:

a) accepting, by a computer system including at least one computer, search query information including a word;

b) determining, by the computer system, one or more words related to the word included in the accepted search query;

c) generating, by the computer system, an item request including

i) the word included in the accepted search query, and

ii) the one or more words determined to be related to the word included in the accepted search query;

d) retrieving, by the computer system, items using the item request;

e) determining, by the computer system, a score for each of the retrieved items;

f) adjusting, by the computer system, the scores of any items retrieved solely on the basis of the one or more words determined to be related to the word included in the accepted search query relative to any items retrieved on the basis of the word included in the accepted search query to generate adjusted scores,

wherein the act of adjusting the scores includes multiplying each of the scores by a multiplier that is less than one;

g) serving, by the computer system, at least some of the items to a client device for rendering to a user, wherein the serving is controlled, at least in part using the adjusted scores; and

h) updating, by the computer system, the multiplier using performance information,

wherein the retrieved items are advertisements,

wherein the act of determining a score for each of the retrieved items uses at least one of ad performance information and ad price information, and

wherein the act of updating the multiplier is performed using the formula;

10. The computer-implemented method of claim 9 wherein the act of adjusting the scores includes decreasing the scores.

11. The computer-implemented method of claim 9 wherein the performance information includes ad selection information.

12. The computer-implemented method of claim 9 wherein the performance information includes ad conversion information.

13. The computer-implemented method of claim 9 wherein the act of updating the multiplier is performed using a function that causes the updated multiplier to converge to observed user behavior relevant to performance divided by predicted user behavior relevant to performance.

14. The computer-implemented method of claim 9 wherein the user behavior is selection.

15. The computer implemented method of claim 9 wherein the user behavior is conversion.

16. A computer-implemented method comprising:

a) accepting, by a computer system having at least one computer, search query information including a word;

b) determining, by the computer system, one or more words related to the word included in the accepted search query;

c) generating, by the computer system, an item request including

i) the word included in the accepted search query, and

ii) the one or more words determined to be related to the word included in the accepted search query;

d) retrieving, by the computer system, items using the item request;

e) determining, by the computer system, a score for each of the retrieved items, wherein a score component is adjusted for any items retrieved on the basis of the one or more words determined to be related to the word included in the accepted search query relative to any items retrieved on the basis of the word included in the accepted search query, wherein the act of adjusting the score component includes multiplying the score component by a multiplier that is less than one;

f) transmitting, by the computer system, at least some of the retrieved items towards a client device for rendering to a user; and

g) updating, by the computer system, the multiplier using performance information,

wherein the retrieved items are advertisements,

wherein the score component is at least one of ad performance information and ad price information, and

wherein the act of updating the multiplier is performed using the formula;

17. The computer-implemented method of claim 16 wherein the act of adjusting the score component includes decreasing the score component.

18. The computer-implemented method of claim 16 wherein the performance information includes ad selection information.

19. The computer implemented method of claim 16 wherein the performance information includes ad conversion information.

20. The computer-implemented method of claim 16 wherein the act of updating the multiplier is performed using a function that causes the updated multiplier to converge to observed user behavior relevant to performance divided by predicted user behavior relevant to performance.

21. The computer implemented method of claim 16 wherein the user behavior is selection.

22. The computer-implemented method of claim 16 wherein the user behavior is conversion.

23. Apparatus comprising:

a) an input for accepting search query information including a word;

b) at least one processor; and

c) at least one storage device storing machine executable instructions which, when executed by the at least one processor, perform a method including

1) determining one or more words related to the word included in the accepted search query,

2) generating an item request including

i) the word included in the accepted search query, and

ii) the one or more words determined to be related to the word included in the accepted search query,

3) retrieving items using the item request,

4) determining a score for each of the retrieved items,

5) adjusting the scores of any items retrieved on the basis of the one or more words determined to be related to the word included in the accepted search query relative to any items retrieved on the basis of the word included in the accepted search query to generate adjusted scores wherein the act of adjusting uses a multiplier,

6) serving at least some of the items to a client device for rendering to a user, wherein the serving is controlled, at least in part, using the adjusted scores, and

7) updating the multiplier using performance information,

wherein the retrieved items are advertisements,

wherein the means for determining a score for each of the retrieved items use at least one of ad performance information and ad price information, and

wherein the act of updating the multiplier uses the formula;

24. The apparatus of claim 23 wherein the performance information includes ad selection information.

25. The apparatus of claim 23 wherein the performance information includes ad conversion information.

26. The apparatus of claim 23 wherein the act of updating the multiplier uses a function that causes the updated multiplier to converge to observed user behavior relevant to performance divided by predicted user behavior relevant to performance.

27. The apparatus of claim 23 wherein the user behavior is selection.

28. The apparatus of claim 23 wherein the user behavior is conversion.

29. Apparatus comprising:

a) an input for accepting search query information including a word;

b) at least one processor; and

c) at least one storage device storing machine executable instructions which, when executed by the at least one processor, perform a method including

1) determining one or more words related to the word included in the accepted search query,

2) generating an item request including

i) the word included in the accepted search query, and

ii) the one or more words determined to be related to the word included in the accepted search query,

3) retrieving items using the item request,

4) determining a score for each of the retrieved items,

5) adjusting the scores of any items retrieved solely on the basis of the one or more words determined to be related to the word included in the accepted search query relative to any items retrieved on the basis of the word included in the accepted search query to generate adjusted scores, wherein the act of adjusting uses a multiplier,

6) serving at least some of the items to a client device for rendering to a user, wherein the serving is controlled, at least in part, using the adjusted scores, and

7) updating the multiplier using performance information,

wherein the retrieved items are advertisements,

wherein the means for determining a score for each of the retrieved items uses at least one of ad performance information and ad price information, and

wherein the act of updating the multiplier uses the formula;

30. The apparatus of claim 29 wherein the performance information includes ad selection information.

31. The apparatus of claim 29 wherein the performance information includes ad conversion information.

32. The apparatus of claim 29 wherein the act of updating the multiplier uses a function that causes the updated multiplier to converge to observed user behavior relevant to performance divided by predicted user behavior relevant to performance.

33. The apparatus of claim 29 wherein the user behavior is selection.

34. The apparatus of claim 29 wherein the user behavior is conversion.

35. Apparatus comprising:

a) an input for accepting search query information including a word;

b) at least one processor; and

c) at least one storage device storing machine executable instructions which, when executed by the at least one processor, perform a method including,

1) determining one or more words related to the word included in the accepted search query,

2) generating an item request including

i) the word included in the accepted search query, and

ii) the one or more words determined to be related to the word included in the accepted search query,

3) retrieving items using the item request,

4) determining a score for each of the retrieved items, wherein a score component is adjusted for any items retrieved on the basis of the one or more words determined to be related to the word included in the accepted search query relative to any items retrieved on the basis of the word included in the accepted search query, wherein the score component is adjusted using a multiplier,

5) transmitting at least some of the retrieved items towards a client device for rendering to a user, and

6) updating the multiplier using performance information,

wherein the retrieved items are advertisements,

wherein the score component is at least one of ad performance information and ad price information, and

wherein the act of updating the multiplier uses the formula;

36. The apparatus of claim 35 wherein the performance information includes ad selection information.

37. The apparatus of claim 35 wherein the performance information includes ad conversion information.

38. The apparatus of claim 35 wherein the act of updating the multiplier uses a function that causes the updated multiplier to converge to observed user behavior relevant to performance divided by predicted user behavior relevant to performance.

39. The apparatus of claim 35 wherein the user behavior is selection.

40. The apparatus of claim 35 wherein the user behavior is conversion.