Techniques for displaying impressions in documents delivered over a computer network

• US 8,086,697 B2
• Filed: 10/31/2005
• Issued: 12/27/2011
• Est. Priority Date: 06/28/2005
• Status: Active Grant

• Current Assignee: Gula Consulting Limited Liability Company (Intellectual Ventures LLC)
• Original Assignee: Claria Innovations LLC
• Inventors: Goulden, David L., Shevach, Matthew A., Bennett, Dominic
• Primary Examiner(s): Hamza, Faruk
• Application Number:
  US11/263,501
• Publication Number:
  US 20060294226A1
• Time in Patent Office: 2,248 Days
• Field of Search: 709/200, 709/203, 709217-219, 709/224, 709/227, 705/14.4
• US Class Current: 709/218
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

In one embodiment, an impression to be displayed in a placement of a web page is selected from candidate impressions that may be displayed in the placement. The candidate impression may be chosen based on behavioral data and a placement identifier particularly identifying the placement. The behavioral data may include categories of websites visited by an end-user on the client computer. The candidate impressions may be in learning modes, and the impression displayed in the placement may be selected based on its learning mode and revenue generation capability.

Claims

1. A method comprising:

(A) receiving, from a client computer, a request for an impression to be displayed in a placement of a web page, the request being made by the client computer as a result of said client computer receiving the web page;

(B) receiving from the client computer a placement identifier particularly identifying a placement for the impression in the web page, the placement identifier having been embedded in the web page received at the client computer;

(C) receiving behavioral data from the client computer, the behavioral data being indicative of client actions taken on multiple websites previously visited by the client computer and indicative of impressions previously received at the client computer;

(D) determining a plurality of candidate impressions that may be displayed in the placement of the web page, based, at least in part, on the behavioral data;

(E) determining a learning mode of each impression in the plurality of candidate impressions, the learning mode of each said impression being indicative of a number of times said each impression in the plurality of candidate impressions has been served to web pages in client computers on the Internet,

wherein said learning mode is one of a plurality of learning modes, said plurality of learning modes comprising at least a first learning mode, a second learning mode, and a third learning mode,

wherein, impressions that have been served less than a first predetermined threshold number of times are in said first learning mode, and

wherein impressions that have been served more than said first predetermined number of times and less than a second predetermined threshold number of times are in said second learning mode, and

wherein impressions that have been served more than a third predetermined threshold number of times are in a third learning mode, said second predetermined threshold being greater than said first predetermined threshold, and said third predetermined threshold being greater than said second predetermined threshold;

(F) selecting a selected impression from the plurality of candidate impressions based at least in part on the learning mode of each of the impressions; and

(G) serving the selected impression to the client computer,

wherein selecting the selected impression from the plurality of candidate impressions in (F) comprises;

(f1) if all impressions in the plurality of candidate impressions are in said first learning mode, then randomly selecting the selected impression from the plurality of candidate impressions; and

(f2) if all impressions in the plurality of candidate impressions are in said second learning mode, then selecting a highest revenue generating impression in the plurality of candidate impressions as the selected impression; and

(f3) if all of the impressions in the plurality of candidate impressions are in said third learning mode, then selecting a highest revenue generating impression in the plurality of candidate impressions as the selected impression; and

(f4) if at least some impressions in the plurality of candidate impressions are in different learning modes, then selecting, as a final set of candidate impressions, impressions in the plurality of candidate impressions that are either;

(i) all in the first learning mode, or (ii) all in the second learning mode, or (iii) all in the third learning mode, and then selecting the selected impression from the final set of candidate impressions.

2. The method of claim 1 wherein determining the plurality of candidate impressions in (D) comprises:

using at least the behavioral data and the placement identifier to determine a first set of impressions that may be displayed in the web page;

generating a second set of impressions from the first set of impressions by applying business rules to the first set of impressions, the business rules being designed to increase a likelihood that the end-user will be interested in impressions in the second set of impressions.

3. The method of claim 2 wherein the business rules include a rule that impressions previously displayed in the client computer are not included in the second set of impressions.

4. The method of claim 1 wherein the placement identifier comprises a hypertext markup language (HTML) tag.

5. The method of claim 1 wherein each impression in the plurality of candidate impressions comprises a message and an associated creative, the creative being a design of how the message is to be presented to the end-user.

6. The method of claim 5 wherein the plurality of candidate impressions comprise:

a first message with an associated first creative;

the first message with an associated second creative; and

the first message with an associated third creative;

wherein the first, second, and third creatives are different from each other.

7. The method of claim 1 wherein:

said first learning mode is a non-scaled learning mode;

said second learning mode is a globally scaled learning mode; and

said third learning mode is a fully scaled learning mode.

8. The method of claim 1 wherein the behavioral data are received in a cookie.

9. The method of claim 1 wherein the placement identifier is received as part of the request.

10. The method of claim 1 wherein selecting the selected impression from the final set of candidate impressions in (f4) comprises:

if all impressions in the final set of candidate impressions are in the first learning mode, then randomly selecting the selected impression from the final set of candidate impressions; and

if all impressions in the final set of candidate impressions are in the second learning mode or the third learning mode, then selecting a highest revenue generating impression in the final set of candidate impressions as the selected impression.

11. The method of claim 10 wherein selecting the selected impression from the final set of candidate impressions comprises:

if all impressions in the final set of candidate impressions are in the first learning mode, then randomly selecting the selected impression from the final set of candidate impressions; and

if all impressions in the final set of candidate impressions are in the second learning mode or the third learning mode, then selecting a highest revenue generating impression in the final set of candidate impressions as the selected impression.

12. A system for serving an impression to a web page, the system comprising:

an impressions server computer configured

(A) to receive from a client computer;

(i) a request for an impression to be displayed in a placement of a web page on the client computer, the request being provided by the client computer as a result of said client computer receiving the web page,

(ii) a placement identifier particularly identifying the placement of the impression in the web page, the placement identifier having been embedded in the web page received at the client computer, and

(iii) behavioral data comprising information indicative of client actions taken on multiple websites previously visited by an end-user of the client computer and information indicative of impressions previously displayed on the client computer;

(B) to select a set of candidate impressions from a set of impressions using at least the behavioral data and the placement identifier,

wherein each impression in the set of candidate impressions has a corresponding learning mode associated therewith, the learning mode of each said impression being indicative of a number of times said each impression has been served to web pages on the Internet,

wherein said learning mode is one of a plurality of learning modes, said plurality of learning modes comprising a first learning mode, a second learning mode, and a third learning mode,

wherein, impressions that have been served less than a first predetermined threshold number of times are in said first learning mode, and

wherein impressions that have been served more than said first predetermined number of times and less than a second predetermined threshold number of times are in said second learning mode, and

wherein impressions that have been served more than a third predetermined threshold number of times are in a third learning mode, said third predetermined threshold being greater than said second predetermined threshold; and

then

(C) to select a selected impression based at least in part on a learning mode of each impression in the set of candidate impressions, by;

(c1) if all impressions in the set of candidate impressions are in the first learning mode, then the impressions server computer is configured to randomly select the selected impression from the set of candidate impressions; and

(c2) if all impressions in the set of candidate impressions are in the second learning mode, then the impressions server computer is configured to select a highest revenue generating impression in the set of candidate impressions as the selected impression; and

(c3) if all impressions in the set of candidate impressions are in the third learning mode, then the impressions server computer is configured to select a highest revenue generating impression in the plurality of candidate impressions as the selected impression; and

(c4) if at least some impressions in the set of candidate impressions are in different learning modes, then the impressions server computer is configured to select impressions in the set of candidate impressions that are either in the first learning mode, or the second learning mode, or the third learning mode to be in a final set of candidate impressions, and then to select the selected impression from the final set of candidate impressions; and

(D) to forward the selected impression to the client computer for display in the placement of the web page.

13. The system of claim 12 wherein the behavioral data are stored in a cookie received by the impressions server computer from the client computer.

14. The system of claim 13 wherein the client computer comprises:

a behavior monitor comprising computer-readable program code for monitoring online-activities of the end-user, the behavior monitor being configured to facilitate storage in the cookie categories of websites visited by the end-user.

15. A method comprising:

(A) receiving from a client computer a request for an impression to be displayed in a placement of a web page in the client computer, the request being provided by the client computer as a result of said client computer receiving the web page;

(B) receiving a cookie from the client computer, the cookie comprising data including behavioral data indicative of categories of websites previously visited by an end-user on the client computer; and

(C) using at least the behavioral data to select a selected impression from a plurality of candidate impressions that may be displayed in the placement of the web page, the selected impression being selected from the plurality of candidate impressions based at least in part on anticipated revenue generation,

wherein selecting the selected impression from the plurality of candidate impressions comprises;

(c1) if all impressions in the plurality of candidate impressions are in a first learning mode, then randomly selecting the selected impression from the plurality of candidate impressions; and

,

(c2) if all impressions in the plurality of candidate impressions are in a second learning mode, then selecting a highest revenue generating impression in the plurality of candidate impressions as the selected impression; and

,

(c3) if all of the impressions in the plurality of candidate impressions are in a third learning mode, then selecting a highest revenue generating impression in the plurality of candidate impressions as the selected impression

wherein impressions in the first learning mode comprise impressions that have been served less than a first predetermined threshold number of times, and

wherein impressions in the second learning mode comprise impressions that have been served more than said first predetermined number of times and less than a second predetermined threshold number of times, and

wherein impressions in the third learning mode comprise impressions that have been served more than a third predetermined threshold number of times, said third predetermined threshold being greater than said second predetermined threshold.

16. The method of claim 15 further comprising:

receiving a placement identifier particularly identifying the placement.

17. The method of claim 15 wherein the plurality of candidate impressions comprise:

a first message with an associated first creative;

the first message with an associated second creative; and

the first message with an associated third creative;

wherein the first, second, and third creatives being different from each other.

18. The method of claim 15 wherein selecting the selected impression from the plurality of candidate impressions comprises further comprises:

(c4) if at least some impressions in the plurality of candidate impressions are in different learning modes, then selecting, as a final set of candidate impressions, impressions in the plurality of candidate impressions that are either (i) all in the first learning mode, or (ii) all the second learning mode, or (iii) all in the third learning mode, and then selecting the selected impression from the final set of candidate impressions.

19. The method of claim 15 wherein each impression in the plurality of candidate impressions comprises a message and an associated creative, the creative being a design of how the message is to be presented to the end-user.

20. The method of claim 15 wherein:

said first learning mode is a non-scaled learning mode;

said second learning mode is a globally scaled learning mode; and

said third learning mode is a fully scaled learning mode.