Granted Patent B2

US 11,354,376 · App. 16/917,715 · Granted Jun 7, 2022

Inventors: Timothy J Catlin (San Mateo, CA); Richard E Chatwin (Sunnyvale, CA); Benjamin D Foster (Campbell, CA); Matthew R McEachen (El Granada, CA); Murthy V Nukala (San Mateo, CA); Veeravich T Thumasathit (Los Altos, CA)

Assignee: Zeta Global Corp.

G06F16/9577G06F16/9535G06Q30/02G06Q30/0244G06Q30/0251G06Q30/0277

Abstract

Claims (58)

1. A method comprising:

initializing a set of earner page components comprising a plurality of instances of feature variations each feature variation each having performance estimates;

receiving, by one or more computer systems, a request for a landing page to be presented to a current visitor, the landing page having one or more landing-page components each of which results from combining different ones of the feature variations;

predicting, by the one or more computer systems, a plurality of responses of a current visitor to possible instances of the landing page based on a current visitor context; the possible feature variations of the possible instances of the landing page,

selecting, by the one or more computer systems, one of the possible instances of the landing page for the current visitor based on the predicted responses;

constructing, by the one or more computer systems, one of the possible instances of the landing page based on the selected one of the possible instances of the landing page;

transmitting, by the one or more computer systems, the constructed instance of the landing page to the current visitor;

receiving response from the current visitor to the constructed instance of the landing page; and

updating the performance estimates based on the response from e current visitor.

2. The method of claim 1 , wherein the current-visitor context comprises one or more of:

one or more demographic data of the current visitor;

one or more conditions of a current web-browsing session;

one or more network-access data of the current web-browsing session;

or one or more network-traffic data of the current web-browsing session.

3. The method of claim 2 , wherein the current-visitor context comprises one or more of:

one or more actions taken by the current visitor;

one or more responses of the current visitor to the constructed landing page; or

a traffic source from which the current visitor is accessing the constructed landing page.

4. The method of claim 2 :

further comprising accessing one or more previous-visitor contexts of one or more previous visitors to the constructed landing page in previous web-browsing sessions; and

wherein:

the one of the possible instances of the landing page is selected based on the previous-visitor contexts in addition to the current-visitor context; and

the one of the possible instances of the web page is substantially most likely to generate a highest expected outcome from interaction with the web page by the current visitor as indicated by the previous-visitor context as well as the current-visitor context.

5. The method of claim 4 , wherein previous web-browsing sessions are analogous to current web-browsing sessions.

6. The method of claim 5 , wherein the previous-visitor contexts comprise one or more of:

one or more demographic data of the previous visitors;

one or more background data of the previous visitors;

one or more conditions of the previous web-browsing sessions;

one or more network-access data of the previous web-browsing sessions; or

one or more network-traffic data of the previous web-browsing sessions.

7. The method of claim 5 , wherein the previous-visitor contexts comprise one or more of:

one or more actions taken by the previous visitors;

one or more responses of the previous visitors to the web page; or

one or more traffic sources from which the previous visitors accessed the web page.

8. The method of claim 2 , wherein:

the constructed landing page has one or more web-page components that each have one or more possible feature variations; and

the plurality of possible instances of the landing page result from different combinations of different ones of the possible feature variations of the web-page components.

9. The method of claim 8 , wherein the features are selected from the group consisting of background color, audio element, video element, text element, size, dimension, and web-page layout.

10. The method of claim 2 , wherein the constructed landing page comprises one or more advertisements.

11. The method of claim 10 , wherein one or more of the advertisements are banner advertisements.

12. The method of claim 11 , wherein one or more of the advertisements are text-based.

13. A system comprising:

one or more processors and a memory storing executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising, at least:

initializing a set of earner page components comprising a plurality of instances of feature variation each having performance estimates;

compiling a plurality of possible instances of web pages for presentation eligibility at a position in a web page flow, each web page having possible feature variations;

accessing a current-visitor context of a current visitor to a web page in a current web-browsing session, the current-visitor context comprising data associated with the current visitor including background data about the current visitor, the web page including possible feature variations;

predicting, by the one or more processors, a plurality of responses of the current visitor to at least one of the possible instances of the web page based on the current visitor context, the possible feature variations of the possible instances of the web page, one or more previous visitor contexts of one or more previous visitors to whom one or more previous actual instances of the web page have been presented, each of the previous actual instances of the web page having been constructed for one of the previous visitors based on one of the possible instances of the web page selected for the one of the one or more previous visitors and one or more actual responses of the previous visitors to the previous actual instances of the web page;

selecting one of the possible instances of the web page for the current visitor based at least on the predicted responses;

constructing a current actual instance of the web page based on the selected one of the possible instances of the web page;

transmitting the current actual instance of the web page to the current visitor;

receiving response from the current visitor to the actual instance of the web page; and

updating the performance estimates on the response from the current visitor.

14. A non-transitory machine-readable medium including instructions which, when read by a machine, cause the machine to perform operations comprising, at least:

compiling a plurality of possible instances of web pages for presentation eligibility at a position in a web page flow, each web page having possible feature variations;

accessing a current-visitor context of a current visitor to a web page in a current web-browsing session, the current-visitor context comprising data associated with the current visitor including background data about the current visitor, the web page including possible feature variations;

predicting a plurality of responses of the current visitor to at least one of the possible instances of the web page based on the current visitor context, the possible feature variations of the possible instances of the web page; one or more previous visitor contexts of one or more previous visitors to whom one or more previous actual instances of the web page have been presented, each of the previous actual instances of the web page having been constructed for one of the one or more previous visitors based on one of the possible instances of the web page selected for the one of the one or more previous visitors and one or more actual responses of the previous visitors to the previous actual instances of the landing selecting one of the possible instances of the web page for the current visitor based at least on the predicted responses;

constructing a current actual instance of the web page based on the selected one of the possible instances of the web page; and

transmitting the current actual instance of the web page to the current visitor.

Assignments (9)

Continuity (5)

Cited By (1)

US 12,518,855