Matching social network users
First Claim
Patent Images
1. A process for recommending prospects to social network users, the process comprising:
- obtaining personal attribute information from a first plurality of the users;
obtaining desired-prospect attribute information from a second plurality of the users;
recommending prospects to a third plurality of the users, wherein the recommended prospects have acceptable proximities to the third plurality of users based upon ratings, the desired-prospect attribute information and the personal attribute information, wherein the ratings reflect a quality of match;
wherein at least some of the users are also prospects, the process further comprising identifying users that have rated each other high and low, and using these identifications in conjunction with an estimate of how similar one user is to the other to derive ratings as estimates of how the users will rate other users that they have not yet rated;
wherein recommending comprises scoring user-prospect matches to indicate quality of match between respective prospects and users, wherein the scores are derived from weighting plural matched attribute information of the prospects to the users'"'"' desired-prospect attributes.
2 Assignments
0 Petitions
Accused Products
Abstract
Systems and methods are disclosed for matching of individuals to one another using a matching model. The matching model matches social network users based on ratings given by users one to another, as well as, as appropriate and available, explicit attributes indicated by users and other data such as location data and system usage data.
-
Citations
25 Claims
-
1. A process for recommending prospects to social network users, the process comprising:
-
obtaining personal attribute information from a first plurality of the users; obtaining desired-prospect attribute information from a second plurality of the users; recommending prospects to a third plurality of the users, wherein the recommended prospects have acceptable proximities to the third plurality of users based upon ratings, the desired-prospect attribute information and the personal attribute information, wherein the ratings reflect a quality of match; wherein at least some of the users are also prospects, the process further comprising identifying users that have rated each other high and low, and using these identifications in conjunction with an estimate of how similar one user is to the other to derive ratings as estimates of how the users will rate other users that they have not yet rated; wherein recommending comprises scoring user-prospect matches to indicate quality of match between respective prospects and users, wherein the scores are derived from weighting plural matched attribute information of the prospects to the users'"'"' desired-prospect attributes. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12)
-
-
13. An apparatus comprising a machine readable storage memory storing a program having instructions which when executed by a processor will cause the processor to recommend prospects to social network users, the instructions of the program for:
-
obtaining personal attribute information from a first plurality of the users; obtaining desired-prospect attribute information from a second plurality of the users; recommending prospects to a third plurality of the users, wherein the recommended prospects have acceptable proximities to the third plurality of users based upon ratings, the desired-prospect attribute information and the personal attribute information, wherein the ratings reflect a quality of match; wherein at least some of the users are also prospects, the instructions of the program further for identifying users that have rated each other high and low, and using these identifications in conjunction with an estimate of how similar one user is to the other to derive ratings as estimates of how the users will rate other users that they have not yet rated; wherein recommending comprises scoring user-prospect matches to indicate quality of match between respective prospects and users, wherein the scores are derived from weighting plural matched attribute information of the prospects to the users'"'"' desired-prospect attributes. - View Dependent Claims (14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25)
-
Specification