Search engine with augmented relevance ranking by community participation

• US 8,521,734 B2
• Filed: 07/28/2011
• Issued: 08/27/2013
• Est. Priority Date: 06/28/2005
• Status: Active Grant

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Walther, Eckart, Lu, Qi, Ku, David, Xu, Zhichen, Tam, Chung-Man, Mao, Jiangchang, Berkin, Pavel, Rose, Dan
• Primary Examiner(s): LE, THU NGUYET T
• Application Number:
  US13/193,077
• Publication Number:
  US 20120233161A1
• Time in Patent Office: 761 Days
• Field of Search: 707/732, 707/723, 707/733, 707/734
• US Class Current: 707/732
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/313 Selection or weighting of terms for indexing
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: Y10S 707/99932 Access augmentation or optimizing
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching

Abstract

Embodiments of the present invention provide systems and methods for ranking a result set. The method according to one embodiment comprises selecting an item from the result set, selecting a user profile from one or more user profiles and selecting one or more items of personalized information from the selected user profile. A rank is calculated for the item on the basis of the selected one or more items of personalized information and the selected item in the result set is ranked in accordance with the calculated rank.

Claims

1. A method of ranking one or more items in a result set, the method comprising:

receiving a query from a user comprising one or more search terms;

identifying users in a social network of the user, the social network of the user determined by identifying at least one other user with whom the user has a direct relationship and a plurality of other users with whom the user has an indirect relationship up to a threshold number of degrees of separation, the social network identified by traversing a user profile data store comprising a plurality of user profiles, each of the plurality of user profiles comprising personalized interaction data regarding content items, including a location, tags, annotations, saved pages, and navigation history associated with each of a plurality of content items, and personalized social interaction data, including trust values associated with the other users with whom the user has a direct or indirect relationship;

generating a result set responsive to the query, the result set comprising a list of content items identified by traversing the user profiles within the social network of the user, the result set generated based on relevance of the one or more terms of the query with the personalized interaction data regarding content items in the user profiles within the social network of the user;

ranking the content items in the results set on the basis of at least on the personalized interaction data regarding content items and a trust value between the user submitting the query and the at least one other user associated with the selected user profile; and

causing at least one interface screen to be displayed to the user comprising the list of content items in the result set.

2. The method of claim 1 wherein the social network of the user is determined by indirect relationships up to a threshold number of degrees of separation specified by the user.

3. The method of claim 1 wherein the direct and indirect relationships include a direction and strength of the relationships.

4. The method of claim 1 wherein ranking the content items includes ranking the content items higher in the results set on the basis of how recent the at least one other user with whom the user has a direct relationship and a plurality of other users with whom the user has an indirect relationship has saved, tagged, and annotated the content items.

5. The method of claim 1 wherein the personalized interaction data regarding content items further includes records of purchases through interaction with the content items.

6. The method of claim 1 further comprising selecting at least one additional user profile, said additional user profile comprising one or more items of personalized information and calculating a rank for the content items in the result set on the basis of the personalized interaction data and a second personalized interaction data.

7. The method of claim 1 wherein the trust value is computed by determining a feature vector for a plurality of users from information contained in the profile of each of the users, the plurality of users comprising the user of the selected profile and the user submitting the query, determining a similarity measure between the feature vectors of the user of the selected profile and the user submitting the query that an implied relationship exists between the user of the selected profile and the at least one other user, and the trust value is computed on the basis of the similarity measure between vectors.

8. The method of claim 1 wherein computing a trust value comprises utilizing a machine-learned trust function.

9. A system for ranking one or more items in a result set, the system comprising:

at least one search provider computer coupled to a plurality of client devices over a network, the search provider computer operative to;

receive a query from a user comprising one or more search terms;

identify users in a social network of the user, the social network of the user determined by identifying at least one other user with whom the user has a direct relationship and a plurality other users with whom the user has an indirect relationship up to a threshold number of degrees of separation, the social network identified by traversing a user profile data store comprising a plurality of user profiles, each of the plurality of user profiles comprising personalized interaction data regarding content items, including a location, tags, annotations, saved pages, and navigation history associated with each of a plurality of content items, and personalized social interaction data, including trust values associated with the other users with whom the user has a direct or indirect relationship;

generate a result set responsive to the query, the result set comprising a list of content items identified by traversing the user profiles within the social network of the user, the result set generated based on relevance of the one or more terms of the query with the personalized interaction data regarding content items in the user profiles within the social network of the user;

rank the content items in the results set on the basis of at least on the personalized interaction data regarding content items and a trust value between the user submitting the query and the at least one other user associated with the selected user profile; and

cause at least one interface screen to be displayed to the user comprising the list of content items in the result set.

10. The system of claim 9 wherein the social network of the user is determined by indirect relationships up to a threshold number of degrees of separation specified by the user.

11. The system of claim 9 wherein the direct and indirect relationships include a direction and strength of the relationships.

12. The system of claim 9 wherein ranking the content items includes ranking the content items higher in the results set on the basis of how recent the at least one other user with whom the user has a direct relationship and a plurality of other users with whom the user has an indirect relationship has saved, tagged, and annotated the content items.

13. The system of claim 9 wherein the personalized interaction data regarding content items further includes records of purchases through interaction with the content items.

14. The system of claim 9 wherein said search provider is further operative to select at least one additional user profile, said additional user profile comprising one or more items of personalized information and calculating a rank for the content items in the result set on the basis of the personalized interaction data and a second personalized data.

15. The system of claim 9 wherein the trust value is computed by determining a feature vector for a plurality of users from information contained in the profile of each of the users, the plurality of users comprising the user of the selected profile and the user submitting the query, determining a similarity measure between the feature vectors of the user of the selected profile and the user submitting the query that an implied relationship exists between the user of the selected profile and the at least one other user, and the trust value is computed on the basis of the similarity measure between vectors.

16. The system of claim 9 wherein computing a trust value comprises utilizing a machine-learned trust function.

17. Non-transitory computer readable media comprising program code that when executed by a programmable processor causes execution of a method for processing a real time increase in search requests for a common event, the computer readable media comprising:

computer program code for receiving a query from a user comprising one or more search terms;

computer program code for identifying users in a social network of the user, the social network of the user determined by identifying at least one other user with whom the user has a direct relationship and a plurality of other users with whom the user has an indirect relationship up to a threshold number of degrees of separation, the social network identified by traversing a user profile data store comprising a plurality of user profiles, each of the plurality of user profiles comprising personalized interaction data regarding content items, including a location, tags, annotations, saved pages, and navigation history associated with each of a plurality of content items, and personalized social interaction data, including trust values associated with the other users with whom the user has a direct or indirect relationship;

computer program code for generating a result set responsive to the query, the result set comprising a list of content items identified by traversing the user profiles within the social network of the user, the result set generated based on relevance of the one or more terms of the query with the personalized interaction data regarding content items in the user profiles within the social network of the user;

computer program code for ranking the content items in the results set on the basis of at least on the personalized interaction data regarding content items and a trust value between the user submitting the query and the at least one other user associated with the selected user profile; and

computer program code for causing at least one interface screen to be displayed to the user comprising the list of content items in the result set.

18. The computer readable media of claim 17 wherein the direct and indirect relationships include a direction and strength of the relationships.

19. The computer readable media of claim 17 wherein the computer program code for ranking the content items includes program code for ranking the content items higher in the results set on the basis of how recent the at least one other user with whom the user has a direct relationship and a plurality of other users with whom the user has an indirect relationship has saved, tagged, and annotated the content items.

20. The computer readable media of claim 17 wherein the personalized interaction data regarding content items further includes records of purchases through interaction with the content items.