Method and system for providing targeted content to a surfer

• US 8,954,539 B2
• Filed: 07/31/2012
• Issued: 02/10/2015
• Est. Priority Date: 07/25/2008
• Status: Active Grant

• Current Assignee: LivePerson Incorporated
• Original Assignee: LivePerson Incorporated
• Inventors: Lahav, Shlomo
• Primary Examiner(s): BILGRAMI, ASGHAR H
• Application Number:
  US13/563,708
• Publication Number:
  US 20130036202A1
• Time in Patent Office: 924 Days
• Field of Search: 709/219, 709/203, 705/14.4, 705/14.41, 705/14.49
• US Class Current: 709/219
• CPC Class Codes: G06F 16/9577 Optimising the visualization of content, e.g. distillation of HTML documents
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0251 Targeted advertisements

Abstract

Providing targeted content to a surfer by determining which content object of a group of content objects, will be best suited for presentation in association with a link on a requested web page. Content objects may include the text, topic, font, color or other attribute of an external or internal advertisement, as well as the specific design of the object, an image, the design of the page in which the object is presented, etc. Selection of a content object can be based on predictive information that is associated with the request (i.e. day and time of receipt, IP address of request, etc.) or historical information about the surfer.

Claims

1. A computer-implemented method, comprising:

receiving, at a computing device, one or more records of events in which an object appeared in one or more web pages and was selected or not selected;

storing, in a success database, one or more records of events in which the object appeared in the one or more web pages and was selected;

storing, in a failure database, one or more records of events in which the object appeared in the one or more web pages and was not selected;

combining records of events from the success database and the failure database into a combined database, wherein the combined database includes predictive information retrieved from one or more requests for the one or more web pages;

determining one or more predictive factors for the object, wherein the one or more predictive factors are determined using the records from the combined database and the predictive information; and

generating a predictive model for the object using the one or more predictive factors, wherein a separate predictive model is generated for each object in a plurality of objects, wherein each predictive model is independent of other predictive models, wherein a predictive model includes predictive factors, wherein the predictive factors are used to calculate a predictive value, and wherein a predictive value corresponds to a likelihood that an object will be selected when presented in a configuration of a web page.

2. The method of claim 1, wherein the predictive information includes behavioral information and information associated with the one or more requests for the one or more web pages.

3. The method of claim 2, wherein the behavioral information includes a time of one or more previous visits in a domain that includes a requested web page, a time that the web page was last requested, a number of visits in the domain, a number of times that the object has been presented, and a number of times that the object has been selected.

4. The method of claim 3, wherein the behavioral information is from a single resource.

5. The method of claim 3, wherein the behavioral information is stored in a cookie.

6. The method of claim 2, wherein the information associated with the one or more requests for the one or more web pages includes a receipt time of a request, a uniform resource locator key associated with the request, an internet protocol address, or a type of browser application.

19. The method of claim 1, further comprising:

receiving a request for a web page;

retrieving predictive information related to the request;

receiving input corresponding to a selection of an object presented with the web page;

determining a relevancy of each of one or more predictive factors included within a predictive model associated with the selected object, wherein the relevancy is determined based on the selection of the selected object;

determining a success value for each of the one or more predictive factors based on the relevancy of each of the one or more predictive factors, wherein a success value corresponds to an effect each of the one or more predictive factors has on a probability that the object will be selected;

updating the one or more predictive factors using the retrieved predictive information; and

updating the predictive model associated with the selected object, wherein the predictive model is updated using the one or more updated predictive factors and the success value for each of the one or more predictive factors.

22. The method of claim 19, wherein the relevancy of each of the one or more predictive factors is further determined based on a minimum number of appearances of the predictive factor.

7. A system, comprising:

a processor; and

a non-transitory computer-readable storage medium containing instructions configured to cause the processor to perform operations including;

receiving one or more records of events in which an object appeared in one or more web pages and was selected or not selected;

storing, in a success database, one or more records of events in which the object appeared in the one or more web pages and was selected;

storing, in a failure database, one or more records of events in which the object appeared in the one or more web pages and was not selected;

combining records of events from the success database and the failure database into a combined database, wherein the combined database includes predictive information retrieved from one or more requests for the one or more web pages;

determining one or more predictive factors for the object, wherein the one or more predictive factors are determined using the records from the combined database and the predictive information; and

generating a predictive model for the object using the one or more predictive factors, wherein a separate predictive model is generated for each object in a plurality of objects, wherein each predictive model is independent of other predictive models, wherein a predictive model includes predictive factors, wherein the predictive factors are used to calculate a predictive value, and wherein a predictive value corresponds to a likelihood that an object will be selected when presented in a configuration of a web page.

8. The system of claim 7, wherein the predictive information includes behavioral information and information associated with the one or more requests for the one or more web pages.

9. The system of claim 8, wherein the behavioral information includes a time of one or more previous visits in a domain that includes a requested web page, a time that the web page was last requested, a number of visits in the domain, a number of times that the object has been presented, and a number of times that the object has been selected.

10. The system of claim 9, wherein the behavioral information is from a single resource.

11. The system of claim 9, wherein the behavioral information is stored in a cookie.

12. The system of claim 8, wherein the information associated with the one or more requests for the one or more web pages includes a receipt time of a request, a uniform resource locator key associated with the request, an internet protocol address, or a type of browser application.

20. The system of claim 7, further comprising instructions which when executed on the one or more data processors, cause the one or more processors to perform operations including:

receiving a request for a web page;

retrieving predictive information related to the request;

receiving input corresponding to a selection of an object presented with the web page;

determining a relevancy of each of one or more predictive factors included within a predictive model associated with the selected object, wherein the relevancy is determined based on the selection of the selected object;

determining a success value for each of the one or more predictive factors based on the relevancy of each of the one or more predictive factors, wherein a success value corresponds to an effect each of the one or more predictive factors has on a probability that the object will be selected;

updating the one or more predictive factors using the retrieved predictive information; and

updating the predictive model associated with the selected object, wherein the predictive model is updated using the one or more updated predictive factors and the success value for each of the one or more predictive factors.

23. The system of claim 20, wherein the relevancy of each of the one or more predictive factors is further determined based on a minimum number of appearances of the predictive factor.

13. A computer-program product, tangibly embodied in a non-transitory machine-readable medium, including instructions configured to cause a data processing apparatus to:

receive one or more records of events in which an object appeared in one or more web pages and was selected or not selected;

store, in a success database, one or more records of events in which the object appeared in the one or more web pages and was selected;

store, in a failure database, one or more records of events in which the object appeared in the one or more web pages and was not selected;

combine records of events from the success database and the failure database into a combined database, wherein the combined database includes predictive information retrieved from one or more requests for the one or more web pages;

determine one or more predictive factors for the object, wherein the one or more predictive factors are determined using the records from the combined database and the predictive information; and

generate a predictive model for the object using the one or more predictive factors, wherein a separate predictive model is generated for each object in a plurality of objects, wherein each predictive model is independent of other predictive models, wherein a predictive model includes predictive factors, wherein the predictive factors are used to calculate a predictive value, and wherein a predictive value corresponds to a likelihood that an object will be selected when presented in a configuration of a web page.

14. The computer-program product of claim 13, wherein the predictive information includes behavioral information and information associated with the one or more requests for the one or more web pages.

15. The computer-program product of claim 14, wherein the behavioral information includes a time of one or more previous visits in a domain that includes a requested web page, a time that the web page was last requested, a number of visits in the domain, a number of times that the object has been presented, and a number of times that the object has been selected.

16. The computer-program product of claim 15, wherein the behavioral information is from a single resource.

17. The computer-program product of claim 15, wherein the behavioral information is stored in a cookie.

18. The computer-program product of claim 14, wherein the information associated with the one or more requests for the one or more web pages includes a receipt time of a request, a uniform resource locator key associated with the request, an internet protocol address, or a type of browser application.

21. The computer-program product of claim 13, further including instructions configured to cause a data processing apparatus to:

receive a request for a web page;

retrieve predictive information related to the request;

receive input corresponding to a selection of an object presented with the web page;

determine a relevancy of each of one or more predictive factors included within a predictive model associated with the selected object, wherein the relevancy is determined based on the selection of the selected object;

determine a success value for each of the one or more predictive factors based on the relevancy of each of the one or more predictive factors, wherein a success value corresponds to an effect each of the one or more predictive factors has on a probability that the object will be selected;

update the one or more predictive factors using the retrieved predictive information; and

update the predictive model associated with the selected object, wherein the predictive model is updated using the one or more updated predictive factors and the success value for each of the one or more predictive factors.

24. The computer-program product of claim 21, wherein the relevancy of each of the one or more predictive factors is further determined based on a minimum number of appearances of the predictive factor.