GUIDING USER MODERATION BY CONFIDENCE LEVELS

• US 20100082640A1
• Filed: 09/30/2008
• Published: 04/01/2010
• Est. Priority Date: 09/30/2008
• Status: Active Grant

• Current Assignee: Yahoo Assets LLC
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Joshi, Deepa, Wexler, Mike
• Granted Patent: US 8,615,512 B2
• Time in Patent Office: Days
• US Class Current: 707/748
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

Methods for guiding user moderation at a topic page by confidence levels includes presenting a topic page in response to a query. The topic page includes a plurality of modules with content that match the query. The topic page is associated with a confidence level and with one or more page attributes that define the characteristics of the topic page and the modules included therein. One or more modifications to the topic page are received as part of customization of the topic page. The modifications include a plurality of page attributes that define the modification and a plurality of user attributes of a user performing the modification. The modifications are evaluated based on the page attributes and user attributes including confidence levels associated with the topic page and the user. The modifications are implemented based on the evaluation. The implemented modifications enhance the quality and confidence level of the topic page.

Claims

1. A method for guiding user moderation at a topic page by confidence levels, comprising:

presenting a topic page in response to a query, the topic page including a plurality of modules with content that match the query, the topic page associated with a confidence level and one or more page attributes that define characteristics of the topic page and the modules contained therein;

receiving modifications to the topic page, the modifications including one or more page attributes associated with the modifications and one or more user attributes, the user attributes including a confidence level and one or more user attributes associated with a user making the modifications;

evaluating the modifications to the topic page based on the confidence levels associated with the topic page and the user, one or more page attributes and user attributes; and

implementing the modifications to the topic page based on the evaluation of the relative confidence levels of the topic page and the user.

2. The method of claim 1, wherein presenting a topic page further includes,

identifying the plurality of modules with content that match one or more dimensions of the query, the dimensions of the query defining one or more categories including a purpose for the query;

generating a topic page with the identified modules;

computing a confidence level based on the plurality of modules that make up the topic page; and

associating the confidence level and one or more page attributes to the topic page.

3. The method of claim 2, further includes generating the topic page automatically through an algorithm or manually by the user, wherein the plurality of modules include one or more user defined modules.

4. The method of claim 2, wherein evaluating the modifications further includes,

obtaining the confidence level of the topic page before the modifications;

computing a new confidence level for the topic page based on the modifications using attributes associated with the topic page and the user making the modifications; and

comparing the confidence level of the topic page without the modifications against a threshold value and against the new confidence level of the topic page with the modifications.

5. The method of claim 4, wherein implementing the modifications further includes,

automatically preventing any modifications to the topic page when the confidence level of the topic page is above a threshold value.

6. The method of claim 4, wherein implementing the modifications further includes,

when the confidence level of the topic page is below the threshold value,

accepting the modifications to the topic page when the new confidence level of the topic page with the modifications is greater than the confidence level of the topic page without the modifications;

and

rejecting the modifications to the topic page when the new confidence level of the topic page with modifications is lesser than or equal to the confidence level of the topic page without the modifications.

7. The method of claim 4, wherein implementing the modifications further includes,

identifying the confidence level of the user making the modifications to the topic page;

comparing the confidence level of the user against the threshold value;

automatically accepting the modifications to the topic page when the confidence level of the user is greater than the threshold value; and

rejecting the modifications to the topic page when the confidence level of the user is less than or equal to the threshold value.

8. The method of claim 4, wherein implementing the modifications further includes,

automatically accepting the modifications to the topic page when the confidence level of the topic page is below a threshold value.

9. The method of claim 2, wherein evaluating the modifications further includes,

identifying a user generated topic page for the query;

receiving an algorithmically generated topic page for the query; and

examining content and confidence level of the user generated topic page against the algorithmically generated topic page.

10. The method of claim 9, wherein implementing of the modifications further includes,

replacing the user generated topic page with the algorithmically generated topic page when the content of the user generated topic page is older than the algorithmically generated topic page and the confidence level of the user generated topic page is lower than the confidence level of the algorithmically generated topic page.

11. The method of claim 2, wherein one or more dimensions include one or more of topic category, one or more intents and geo-location,

wherein the page attributes include one or more of page ID, topic category, one or more intents, geo-location, page confidence level, list of modules, an intent for each module, confidence level of each module;

normalized query frequency, number and quality of the modules, engagement metrics from topic page usage; and

wherein user attributes include user ID, confidence level of the user, user status, user level, user geo location, frequency of change implemented by the user and user reputation.

12. A method for guiding user moderation at a topic page by confidence levels, comprising:

presenting a plurality of topic pages, each of the plurality of topic pages containing a plurality of modules that match the query, each of the plurality of topic pages associated with a confidence level and one or more page attributes that define characteristics of the corresponding topic page and the modules contained therein;

receiving modifications to a topic page selected from the presented plurality of topic pages, the modifications including one or more user attributes and one or more page attributes, the user attributes associated with a user making the modifications, the user attributes including a confidence level of the user;

evaluating the modifications to the topic page based on the confidence levels associated with the topic page and the user using the page attributes and user attributes; and

implementing the modifications to the topic page based on the evaluation of the modifications to the topic page,

wherein the confidence level of each of the topic pages presented in response to the query is below a threshold value, the modifications to the topic page is to boost the quality of the topic page.

13. The method of claim 12, further includes generating the topic pages automatically through an algorithm or manually, wherein the plurality of modules includes one or more user generated modules.

14. The method of claim 12, wherein evaluating the modifications further includes,

obtaining the confidence level of the topic page before the modifications;

computing a new confidence level for the topic page based on the modifications using attributes associated with the topic page and the user making the modifications; and

comparing the new confidence level of the topic page with the modifications against the confidence level of the topic page without the modifications.

15. The method of claim 14, wherein implementing the modifications further includes,

accepting the modifications to the topic page when the new confidence level for the topic page with the modifications is greater than the confidence level of the topic page without the modifications;

and

rejecting the modifications to the topic page when the new confidence level of the topic page with modifications is lesser than or equal to the confidence level of the topic page without the modifications.

16. The method of claim 14, wherein implementing the modifications further includes,

identifying the confidence level of the user making the modifications to the topic page;

comparing the confidence level of the user against the threshold value;

accepting the modifications to the topic page when the confidence level of the user is greater than the threshold value; and

rejecting the modifications to the topic page when the confidence level of the user is less than or equal to the threshold value.

17. The method of claim 14, wherein implementing the modifications further includes,

automatically accepting the modifications to the topic page when the confidence level of the topic page is below the threshold value.

18. An algorithm embedded in a server of a computing system for guiding user moderation at a topic page by confidence levels, comprising:

a topic page generator algorithm configured to receive a query, analyze and categorize the query, select a plurality of modules that match the query, place and rank the plurality of modules in the topic page, the topic page generator algorithm associating one or more page parameters that define characteristics of the topic page; and

a moderation algorithm configured to receive the modifications to the topic page, evaluate and implement the modifications based on one or more attributes associated with the modifications, the modifications including one or more page attributes and one or more user attributes, wherein the user attributes are associated with a user making the modifications.

19. The algorithm of claim 18, wherein the algorithm includes logic to interact with a plurality of sources to obtain one or more modules that match the query.

20. The algorithm of claim 18, wherein the algorithm includes logic to interact with a topic page repository to obtain one or more topic pages for the query and to store one or more topic pages for the query.

21. The algorithm of claim 18, further includes an insider tool to provide guidance and resources for providing modifications to the topic page, the modifications used to improve a confidence level of the topic page.