Determining user-to-user similarities in an online media environment

• US 8,640,163 B2
• Filed: 09/30/2008
• Issued: 01/28/2014
• Est. Priority Date: 09/30/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Weare, Christopher, Gibson, Chad, Zahn, Jessica
• Primary Examiner(s): Beliveau, Scott
• Assistant Examiner(s): FOGG, CYNTHIA M
• Application Number:
  US12/242,601
• Publication Number:
  US 20100083318A1
• Time in Patent Office: 1,946 Days
• Field of Search: None
• US Class Current: 725/34
• CPC Class Codes: G06F 16/437 Administration of user profiles, e.g. generation, initialisation, adaptation, distribution
• CPC Class Codes: G11B 27/105 of operating discs
• CPC Class Codes: H04N 21/252 Processing of multiple end-users' preferences to derive collaborative data
• CPC Class Codes: H04N 21/4667 Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
• CPC Class Codes: H04N 21/6582 Data stored in the client, e.g. viewing habits, hardware capabilities, credit card number arrangements where receivers interact with the broadcast H04H20/38

Abstract

The determination of similarities between users in an online entertainment environment is disclosed. For example, one disclosed embodiment comprises a method of operating an entertainment server, wherein the method includes receiving user information that comprises user demographic information and user media selection information from each user of a plurality of users. For a current user, a plurality of similarity values are determined that each quantifies a similarity of the current user to another user based upon similarities between the user information of the current user and the user information of the other user. Then, the method comprises determining a list of other users to present to the current user based upon the similarity values determined, and sending the list of other users to the current user.

Claims

1. A method of operating an entertainment server computing device, the method comprising:

receiving at the computing device via a computer network input items of user information comprising user demographic information and user media selection information from each user of a plurality of users;

for a current user, determining on the computing device a plurality of similarity values that each quantifies a similarity of the current user to another user based upon similarities between the input items of user information of the current user and the input items of user information of the other user, where each similarity value is based on one or more weighting factors applied to the input items of user information for each of the current user and the other user;

determining on the computing device a list of zero or more other users to present to the current user based upon the similarity values determined;

sending the list of zero or more other users to the current user via the computer network;

receiving from the current user via the computer network a request for interaction regarding a user on the list; and

modifying a weighting factor applied to one or more input items of user information for use in future similarity value determinations on the computing device by

increasing the weighting factor a first amount if the request for interaction comprises a request to view a page of the user; and

increasing the weighting factor a second amount greater than the first amount if the request for interaction comprises one or more of communicating with the user and a request for media content associated with the user.

2. The method of claim 1, further comprising determining a similarity value for each user-user pair of the plurality of users.

3. The method of claim 1, wherein determining a list comprises ordering the list based upon similarity values of the other users.

4. The method of claim 3, wherein determining a list further comprises weighting the similarity value of each user in the list based upon a calculated reputation of each user in the list.

5. The method of claim 4, further comprising adjusting the calculated reputation of each user on the list based upon actions performed by the user.

6. The method of claim 1, wherein the request for interaction regarding the user on the list comprises a request for information regarding the user.

7. The method of claim 1, wherein the request for interaction regarding the user on the list comprises a request to block the user.

8. The method of claim 1, wherein

communicating with the user comprises one or more of a request to send a message to the user and a request to friend the user, and wherein a request for media content associated with the user comprises a request to play a song on the page of the user.

9. The method of claim 1, wherein determining a plurality of similarity values comprises determining the plurality of similarity values via a cosine similarity calculation.

10. The method of claim 9, wherein each similarity value is determined on the computing device according to the relationship:

11. The method of claim 1, wherein determining a plurality of similarity values comprises determining the plurality of similarity values via a map-reduce calculation.

12. A method of interacting with an entertainment server, comprising:

receiving an input of current user demographic information from a current user;

receiving an input of current user media selection information from the current user;

sending the current user demographic information and the current user media selection information to the entertainment server;

receiving a list of similar other users from the entertainment server, where the list of similar other users is based on a plurality of similarity values that each quantifies a similarity of the current user to another user based upon one or more weighting factors applied to input current user demographic information and input current user media selection information received from the current user and the other user;

displaying the list of similar other users on a user interface;

receiving a selection of a selected other user from the list of similar users;

modifying a weighting factor applied to one or more of the input current user demographic information and/or the input current user media selection information in a similarity value determinations by

increasing the weighting factor by a first amount if the selection of the selected other user comprises a request to view a page of the user; and

increasing the weighting factor by a second amount greater than the first amount if the selection of the selected other user comprises one or more of communicating with the other user and a request for media content associated with the user;

sending the selection of the selected other user from the list of similar users to the entertainment server; and

if the selection of the selected other user comprises a request for information regarding the selected other user,

receiving information about the selected other user from the entertainment server, and

displaying the information about the selected other user on the user interface.

13. The method of claim 12, further comprising receiving from the current user an input requesting transmission of a media item selection from the information about the selected other user, sending a request for the media item selection to the entertainment server, and receiving the media item selection from the entertainment server.

14. The method of claim 12, wherein the current user demographic information comprises one or more of age, gender and location.

15. The method of claim 12, wherein the current user media selection information comprises one or more of media selections made by the current user, media item preferences, fan club memberships, mailing list memberships, social group memberships, and user self-descriptions.

16. An entertainment server, comprising:

a logic subsystem; and

memory comprising instructions executable by the logic subsystem to perform a method comprising;

receiving input items of user information from each user of a plurality of users;

for each user-user pair of the plurality of users, determining a similarity value that quantifies a similarity of the user-user pair based upon similarities between the input items of user information of each user of the user-user pair, where the similarity value is based on one or more weighting factors applied to each input item of user information of each user of the user-user pair;

receiving a request from a current user to connect to the entertainment server;

connecting the current user to the entertainment server;

determining a list of zero or more other users to present to the current user based upon the similarity values of user-user pairs that include the current user;

sending the current user the list of zero or more other users;

receiving from the current user a request for interaction regarding a user on the list; and

modifying a weighting factor applied to one or more input items of user information in a similarity value determination by

increasing the weighting factor a first amount if the request for interaction comprises a request to view a page of the user; and

increasing the weighting factor a second amount greater than the first amount if the request for interaction comprises one or more of a request to send a message to the user, a request to friend the user, and a request to play a song on the page of the user.

17. The entertainment server of claim 16, wherein the instructions are executable to determine the list by weighting each user in the list based upon a calculated reputation of each user in the list.

18. The entertainment server of claim 17, wherein the instructions are further executable to adjust the calculated reputation of each user on the list based upon actions of each user on the list.

19. The entertainment server of claim 16, wherein the weighting factor is selected from a plurality of weighting factors, and wherein the instructions are executable to determine a similarity value for each user-user pair by:

applying one or more of the plurality of weighting factors to types of user information used as inputs in the similarity value determination;

collecting information on each type of user information used in the similarity value determination;

determining a usefulness of each type of user information used in the similarity value determination;

and adjusting the weighting factor of each type of user information used in the similarity determination based upon the usefulness.

20. The entertainment server of claim 16, wherein the request for interaction regarding the user on the list comprises one or more of a request for information regarding the user and a request to block the user.