Prioritizing a content item for a user

• US 9,069,864 B2
• Filed: 09/21/2012
• Issued: 06/30/2015
• Est. Priority Date: 09/21/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Liu, Yifang
• Primary Examiner(s): Lipman, Jacob
• Application Number:
  US13/624,831
• Publication Number:
  US 20140090038A1
• Time in Patent Office: 1,012 Days
• Field of Search: 726/7
• US Class Current: 1/1
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: H04L 12/1822 Conducting the conference, e.g. admission, detection, selection or grouping of participants, correlating users to one or more conference sessions, prioritising transmission

Abstract

The disclosed subject matter relates to methods for prioritizing a content item for a user. In one aspect, a method includes receiving user authentication events corresponding to a user account. A user is associated with the user account. The method further includes determining a time distribution of the received user authentication events. The method further includes constructing, based on the determination, a content prioritization user model corresponding to the user associated with the user account. The method further includes receiving a content item associated with the user. The method further includes associating, based on the content prioritization user model, a content priority value with the content item. The content priority value corresponds to a predicted aspect of the user.

Claims

1. A method comprising:

receiving user authentication events, each authentication event comprising an identity verification for the user in connection with accessing an online resource;

determining a time distribution of the received user authentication events;

constructing, based on the determining, a content prioritization user model corresponding to the user, wherein the content prioritization model is based on at least one decision variable and at least one user model variable, the at least one decision variable corresponding to the time distribution of the received user authentication events, and the at least one user model variable corresponding to at least one of a location of the user or an interest of the user;

receiving a content item associated with the user; and

associating, based on the content prioritization user model, a content priority value with the content item, wherein the content priority value corresponds to a predicted aspect of the user.

2. The method of claim 1, further comprising:

providing for processing, a prioritized content item, wherein the prioritized content item is the content item prioritized based on the associated content priority value.

3. The method of claim 1, further comprising:

updating the content prioritization user model based on a user feedback, wherein the user feedback comprises a reaction of the user in response to a prioritized content item, wherein the prioritized content item is the content item prioritized based on the associated content priority value.

4. The method of claim 1, wherein the predicted aspect of the user comprises at least one of a predicted interest of the user or a predicted location corresponding to the user.

5. The method of claim 1, wherein the time distribution of the received user authentication events comprises a mean and a variance respectively of the time of the user authentication events.

6. The method of claim 1, wherein the constructing the content prioritization user model comprises:

selecting the at least one decision variable from a plurality of decision variables;

selecting the at least one user model variable from a plurality of user model variables;

implementing a statistical model based on the selected at least one decision variable and the selected at least one user model variable; and

training the statistical model based on a training set, wherein the training set comprises tuples of the selected at least one decision variable and the selected at least one user model variable.

7. The method of claim 6, wherein the statistical model comprises logistic regression using the at least one decision variable and at least one user model variable.

8. The method of claim 1, wherein the received user authentication events correspond to authentication based on user account associated with the user.

9. The method of claim 8, wherein the online resource comprises at least one of a website, a service, or an Application Programming Interface (“

API”

).

10. A system comprising:

a memory comprising instructions; and

a processor configured to execute the instructions to;

receive user authentication events, each authentication event comprising an identity verification for the user in connection with accessing an online resource;

determine a time distribution of the received user authentication events;

construct, based on the determination, a content prioritization user model corresponding to the user, wherein the content prioritization model is based at least one decision variable and at least one user model variable, the at least one decision variable corresponding to the time distribution of the received user authentication events, and the at least one user model variable corresponding to at least one of a location of the user or an interest of the user;

receive a content item associated with the user; and

associate, based on the content prioritization user model, a content priority value with the content item, wherein the content priority value corresponds to a predicted aspect of the user.

11. The system of claim 10, wherein the processor is further configured to:

provide for display, a prioritized content item, wherein the prioritized content item is the content item prioritized based on the associated content priority value.

12. The system of claim 10, wherein the processor is further configured to:

update the content prioritization user model based on a user feedback, wherein the user feedback comprises a reaction of the user in response to a prioritized content item, wherein the prioritized content item is the content item prioritized based on the associated content priority value.

13. The system of claim 10, wherein the predicted aspect of the user comprises at least one of a predicted interest of the user or a predicted location corresponding to the user.

14. The system of claim 10, wherein the online resource comprises at least one of a website, a service, or an Application Programming interface (“

API”

).

15. The system of claim 10, wherein to construct the content prioritization user model, the processor is further configured to:

select the at least one decision variable from a plurality of decision variables;

select the at least one user model variable from a plurality of user model variables;

implement a statistical model based on the selected at least one decision variable and the selected at least one user model variable, and wherein the statistical model comprises logistic regression using the at least one decision variable and at least one user model variable; and

train the statistical model based on a training set, wherein the training set comprises tuples of the selected at least one decision variable and the selected at least one user model variable.

16. The system of claim 10, wherein the time distribution of the received user authentication events comprises a mean and a variance respectively of the time of the user authentication events.

17. A machine-readable storage medium comprising machine-readable instructions for causing a processor to execute a method, the method comprising:

receiving user authentication events, each authentication event comprising an identity verification for the user in connection with accessing an online resource;

determining a time distribution of the received user authentication events;

constructing, based on the determining, a content prioritization user model corresponding to the user, wherein the content prioritization model is based on at least one decision variable and at least one user model variable, the at least one decision variable corresponding to the time distribution of the received user authentication events, and the at least one user model variable corresponding to at least one of a location of the user or an interest of the user;

receiving a content item associated with the user;

associating, based on the content prioritization user model, a content priority value with the content item, wherein the content priority value corresponds to a predicted aspect of the user; and

providing for display, a prioritized content item, wherein the prioritized content item is the content item prioritized based on the associated content priority value,

18. The machine-readable medium of claim 17, wherein the constructing the content prioritization user model further comprises:

selecting the at least one decision variable from a plurality of decision variables;

selecting the at least one user model variable from a plurality of user model variables;

implementing a statistical model based on the selected at least one decision variable and the selected at least one user model variable; and

training the statistical model based on a training set, wherein the training set comprises tuples of the selected at least one decision variable and the selected at least one user model variable.