Providing user confidence information to third-party systems

• US 8,402,548 B1
• Filed: 09/03/2010
• Issued: 03/19/2013
• Est. Priority Date: 09/03/2010
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Muriello, Daniel Gregory, Brill, Jacob Andrew, Kar, Siddharth, Rice, Alexander Steven, McGeehan, Ryan
• Primary Examiner(s): McNally, Michael S
• Application Number:
  US12/876,078
• Time in Patent Office: 928 Days
• Field of Search: 726/26
• US Class Current: 726/26
• CPC Class Codes: G06F 21/31 User authentication
• CPC Class Codes: G06F 21/60 Protecting data
• CPC Class Codes: G06F 2221/2133 Verifying human interaction, e.g., Captcha
• CPC Class Codes: H04L 63/08 for authentication of entities cryptographic mechanisms or cryptographic arrangements for entity authentication H04L9/32
• CPC Class Codes: H04L 63/10 for controlling access to devices or network resources
• CPC Class Codes: H04L 63/20 for managing network security; network security policies in general filtering policies H04L63/0227

Abstract

An online services system includes a mechanism for providing user confidence information to an external data consumer, and for determining user contribution quality. Using stored information about user actions and interactions, user confidence is evaluated for one or more parameters associated with the validity of the user'"'"'s account and/or quality of the user'"'"'s contributions to the online services system. Confidence values are assigned to each parameter, and the values are exposed to external data consumers. Using stored information, user actions and interactions are correlated with contribution quality to produce a metric indicative of user contribution quality. Users with low quality parameter metrics may have their contributions shown to a smaller audience or have a lower prominence in a news feed.

Claims

1. A method comprising:

receiving social data collected from interactions between users of an online services system;

determining, for a user of the online services system, a value for a confidence evaluation parameter based on an analysis of a portion of the social data related to the user, wherein the confidence evaluation parameter represents a measure of whether an account for the user is indicative of a unique account for a real person; and

providing to an external data consumer the value for the confidence evaluation parameter determined for the user.

2. The method of claim 1, further comprising:

collecting the social data from the interactions between the users of online services system.

3. The method of claim 1, further comprising:

receiving a request from the external data consumer for the value of the confidence evaluation parameter for the user.

4. The method of claim 1, wherein the confidence evaluation parameter further represents a measure of validity of an account associated with the user.

5. The method of claim 4, wherein the measure of validity is whether a current user session is trusted.

6. The method of claim 4, wherein the measure of validity is whether a history of an account associated with the user indicates an incidence of the account having been compromised.

7. The method of claim 4, wherein the measure of validity is determined based in part on whether the user has overcome a challenge issued by the online services system.

8. The method of claim 1, wherein the confidence evaluation parameter further represents a measure of quality of contributions by the user.

9. The method of claim 8, wherein the measure of quality is based upon feedback about the contributions by the user from other users of the online services system.

10. The method of claim 9, wherein the feedback about the contributions by the user from the other users comprises implicit feedback about the contributions by the user based on the other user'"'"'s interactions with the contributions.

11. The method of claim 1, wherein:

the analyzing comprises comparing the social data for the user to a predetermined condition for the confidence evaluation parameter; and

the value assigned to the user corresponds to whether the condition is satisfied.

12. The method of claim 1, wherein:

the analyzing comprises comparing the social data for the user to data constraints for established values of the confidence evaluation parameter; and

the value assigned to the user is selected from one of the established values.

13. The method of claim 1, wherein:

the analyzing comprises comparing the social data for the user to typical user data for the confidence evaluation parameter; and

the value assigned to the user is based upon a degree of similarity to the typical user data for the confidence evaluation parameter.

14. The method of claim 1, wherein the determining of the confidence evaluation parameter further comprises:

training a machine learning algorithm using historical data for the users of the online services system; and

inputting the collected social data into the trained machine learning algorithm to obtain the confidence evaluation parameter.

15. A method comprising:

receiving social data collected from interactions between users of an online services system;

determining, for a user of the online services system, a value for a confidence evaluation parameter based on an analysis of a portion of the social data related to the user, wherein the confidence evaluation parameter represents a measure of whether an account for the user is indicative of a unique account for a real person, and wherein the determining of the confidence evaluation parameter further comprises;

training a machine learning algorithm using historical data for the users of the online services system; and

inputting the collected social data into the trained machine learning algorithm to obtain the confidence evaluation parameter;

receiving a request from the external data consumer for the value of the confidence evaluation parameter for the user; and

providing to an external data consumer the value for the confidence evaluation parameter determined for the user.

16. A method comprising:

receiving social data collected from interactions between users of an online services system;

a step for determining, for a user of the online services system, a value for a confidence evaluation parameter based on an analysis of a portion of the social data related to the user, wherein the confidence evaluation parameter represents a measure of whether an account for the user is indicative of a unique account for a real person; and

providing to an external data consumer the value for the confidence evaluation parameter determined to the user.