Method and system for personalizing web page layout

Patent metadata

Field	Value
Publication number	US-10061860-B2
Application number	US-201113193889-A
Country	US
Kind code	B2
Filing date	Jul 29, 2011
Priority date	Jul 29, 2011
Publication date	Aug 28, 2018
Grant date	Aug 28, 2018

Abstract

Method and system for generating personalizing website layout. The method and system monitors a user's behaviors and assigns a user to a user group, which has an assigned personalized template. The templates are personalized in response to the user's behaviors and arranges content to be displayed to the user based on that behavior.

First claim

We claim:

1. A method for generating a personalized layout of content, implemented on a machine having at least one processor, storage, and a communication platform connected to a network, comprising:
monitoring web browsing activities of a user in a web browsing session, via the communication platform;
determining a view distribution for the user based on the monitored activities of the user with respect to each portion of each of a plurality of web pages viewed by the user within the web browsing session, wherein the view distribution comprises a list of numbers each of which represents a number of times the user viewed a respective portion of the plurality of web pages;
adaptively assigning the user to a user group from a plurality of user groups based on the view distribution, the adaptive assignment including detecting a change in the user's web browsing activities and reassigning the user to a different user group;
selecting a layout template for the user based on the user group assignment, wherein the layout template specifies a layout of content and is selected such that space on the layout template prioritizes a web page portion that received most views per the view distribution, and wherein the prioritization includes allocating more space for content provided at the web page portion;
arranging a plurality of pieces of content according to the layout template;
providing the arranged plurality of pieces of content to the user, wherein the arranging is based on the user group assignment;
determining statistics associated with a plurality of users in the user group to which the user is assigned;
updating a record associated with a content provider in connection with the layout template based on the statistics; and
receiving a payment made in association with the layout template and computed based on the record.

2. The method of claim 1 , wherein the monitoring of web browser activities includes monitoring at least one of the following:
web site visits, content selection, user profile data, book marks, module selections, radio button selections, module controls, module players, widget controllers, inputting data to online forums, text messaging, updating social network status, and search queries.

3. The method of claim 1 , further comprising:
responsive to the reassignment, selecting a new layout template that prioritizes the space to a different web page portion; and
rearranging the plurality of pieces of content according to the new layout template.

4. The method of claim 1 , wherein the user is assigned to the user group because the user's view distribution is similar to view distributions of other users in the user group.

5. The method of claim 1 , wherein the layout template is assigned to the user group based on at least one of the following:
user interests, user behavior, advertisement placement, paid for content placement, media type placement, content availability, content features availability, and performance of previous template assignments.

6. The method of claim 1 , further comprising:
determining whether the user has an existing profile;
responsive to a determination that the user does not have an existing profile, assigning a default template to the user;
determining whether the view distribution includes enough information about the user's behavior to be able to assign the user to a group,
wherein the user is adaptively assigned to the user group responsive to a determination that the view distribution includes enough information about the user's behavior.

7. The method of claim 1 , further comprising:
determining a plurality of user groups using K-means clustering algorithm, wherein a number of the user groups is predetermined;
training a machine learning classifier based on output of the K-means clustering algorithm,
wherein the adaptive assignment is performed using the trained classifier.

8. A method implemented on a machine having at least one processor, storage, and a communication platform connected to a network, comprising steps of:
analyzing, via a clustering engine running on one of the at least one processor of the machine, a plurality of user identifiers to cluster one or more users into a user group from a plurality of user groups based on their view distributions, wherein each view distribution corresponding to a particular user is determined with respect to each portion of each of a plurality of web pages viewed by the particular user within a given web browsing session and comprises a list of numbers each of which represents a number of times the particular user viewed a respective portion of the plurality of web pages, the web page viewing of the particular user being monitored such that the particular user is adaptively assigned to the user group, the adaptive assignment including detecting a change in the particular user's web page viewing and reassigning the particular user to a second user group;
generating, via a template generation engine running on one of the at least one processor of the machine, a display template that specifies a layout of content for display of a plurality of pieces of content to one or more users of the user group, such that space on the display template prioritizes a web page portion that received most views per the view distribution, wherein the prioritization includes allocating more space for content provided at the web page portion; and
arranging the plurality of pieces of content for display to the one or more users, wherein the arranging of the plurality of pieces of content is based on the user group assignment and according to the display template generated;
determining statistics associated with a plurality of users in the user group to which the user is assigned;
updating a record associated with a content provider in connection with the display template based on the statistics; and
receiving a payment made in association with the display template and computed based on the record.

9. The method of claim 8 , further comprising:
generating a second display template based on the reassignment; and
updating the arrangement of the plurality of pieces of content on the user's display based on the second display template, and wherein the reassignment is responsive to the detection of the change in the user's web page viewing such that the second display template is generated that prioritizes the space to a different web page portion.

10. The method of claim 9 , wherein the arrangement is not updated until at least one of a next login, next day, next session, or a change in context, the change in context including where the user has moved on to a new task or where available content to be displayed has significantly shifted.

11. The method of claim 9 , wherein the reassignment is based in part on online user feedback.

12. The method of claim 8 , wherein the display template is generated based on which group the user is assigned.

13. The method of claim 8 , wherein the generating comprises:
selecting a template from a template library based on a certain criterion appropriate to the user group.

14. The method of claim 8 , wherein the display template is generated based on at least one of the following:
the user's profile data, user-provided data, search behaviors, search history, click history, book marking activities, and relation to other users.

15. The method of claim 8 , wherein the plurality of pieces of content are determined with respect to an underlying topic of interest of the user, and
wherein the display template is generated based on the underlying topic.

16. The method of cla

Assignees

• Daly Jr Timothy P
• Makeev Evgeniy
• Cheng Annie
• Budzinski Jeff
• Roy Scott
• Oath Inc

Inventors

• Daly Jr Timothy P
• Makeev Evgeniy
• Cheng Annie
• Budzinski Jeff
• Roy Scott

Classifications

• G06Q30/0277

  Online advertisement · CPC title

• G06Q30/0251

  Targeted advertisements · CPC title

• G06F16/9577

  Optimising the visualization of content, e.g. distillation of HTML documents · CPC title

• G06F40/103

  Formatting, i.e. changing of presentation of documents (automatic justification G06F40/189; automatic line break hyphenation G06F40/191) · CPC title

• G06F16/972 Primary

  Access to data in other repository systems, e.g. legacy data or dynamic Web page generation · CPC title