System and method for finding matches between users in a networked environment

• US 9,824,123 B2
• Filed: 11/20/2013
• Issued: 11/21/2017
• Est. Priority Date: 11/20/2013
• Status: Active Grant

• Current Assignee: Match Group, LLC (Match Group, Inc.)
• Original Assignee: Match.com LLC (Match Group, Inc.)
• Inventors: Ochandio, Ernesto, Sundaram, Devaraj, Klawitter, Monica, Thombre, Amarnath, Fisher, Helen, Lam, Sydney, Carrico, Todd
• Primary Examiner(s): Mobin, Hasanul
• Application Number:
  US14/084,723
• Publication Number:
  US 20150142839A1
• Time in Patent Office: 1,462 Days
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

Finding a match for an end user on an online social platform is not a trivial task. To improve match making, various methods and systems are disclosed which are configured to compute heuristics for various end users, which help to predict the likelihood that two end users would ultimately engage in some form of communication with each other. The heuristics are used in an algorithm (i.e., a statistical/predictive model) for providing a set of matches to an end user. These heuristics may be computed based on varying forms of communication which indicate different levels of engagement between end users, and/or based on some other indication of how an end user may react to another end user.

Claims

1. A method for selecting one or more matching end users for an end user seeking a match on an online social platform where end users participate in different forms of electronic communications with varying levels of engagement with other end users, the method comprising:

receiving, by a server, responses from the end users to a plurality of questions provided by the online social platform, wherein a response comprises a user selection, via an endpoint, from a plurality of photographs of celebrities presented by a question;

improving a likelihood of the server identifying a successful match for the end user seeking the match based on past communication actions of a pool of end users by;

converting, by the server, the responses received from the pool of end users to a similarity score that quantifies how similar each end user in the pool of end users is to the end user seeking the match based on which of the plurality of photographs of celebrities is selected in the responses, wherein the similarity score is computed for each end user in the pool of end users based on the responses received from the end user being matched and the responses received from the end users in the pool of end users;

selecting, by the server, a first set of end users from the pool of end users using the similarity score;

determining, by the server, a second set of end users, wherein the end users in the second set of end users have participated in a first form of electronic communication with the end users in the first set of end users;

selecting, by the server, one or more end users from the second set of end users as the one or more matching end users; and

transmitting an indication of the one or more matching end users from the server to an endpoint associated with the end user seeking the match.

2. The method of claim 1, wherein:

for each end user in the pool of end users, the similarity score is computed based on;

a similarity variable per question based on whether the user selection made by the end user being matched and the user selection made by the end user from the pool of end users are the same; and

a rarity variable per question based on the number of end users who made the same user selection divided by the number of end users in the pool of end users.

3. The method of claim 2, wherein the similarity variable contributes positively to the similarity score, and the rarity variable contributes negatively to the similarity score.

4. The method of claim 2, wherein:

computing the similarity score comprises dividing the similarity variable by the rarity variable for each question to obtain a quotient for each question; and

the similarity score comprises a sum of the quotients.

5. The method of claim 1, wherein:

selecting a first set of end users from the pool of end users comprises selecting end users from the pool of end users having a similarity score meeting a similarity threshold.

6. The method of claim 1, wherein:

the first form of electronic communication involves two-way electronic message or mail communication between two end users.

7. The method of claim 1, further comprising:

if the second set of end users is an empty set, determining a third set of end users, wherein the end users in the third set of end users have participated in a second form of electronic communication with the end users in the first set of end users;

wherein a level of engagement indicated by the second form of electronic communication is less than a level of engagement indicated by the first form of electronic communication; and

selecting one or more end users from the third set of end users as the one or more matching end users.

8. The method of claim 1, further comprising:

determining a match score for each end user in the second set of end users, wherein the match score is determined for a particular end user in the second set of end users based on the similarity scores computed for the end users in the first set of end users with which the particular end user in the second set of end users participated in the first form of electronic communication.

9. The method of claim 8, wherein the match score comprises a sum of the similarity scores computed for the end users in the first set of end users with which the particular end user in the second set of end users participated in the first form of electronic communication.

10. The method of claim 8, wherein the match score for an end user in the second set of end users is based further on:

a triangulation score based on the number of end users with whom both the end user seeking the match and the end user in the second set of end users have participated in the first form of electronic communication.

11. The method of claim 1, wherein selecting one or more end users from the second set of end users as the one or more matching end users comprises checking whether the one or more end users meet, within a buffer, a search criteria requirement provided by the end user seeking the match, wherein the buffer relaxes the search criteria requirement.

12. The method of claim 11, wherein the buffer is provided if the one or more end users or the end user seeking the match meets one or more conditions.

13. The method of claim 11, wherein the buffer is not provided if the one or more end users or the end user seeking the match meets one or more conditions.

14. One or more non-transitory tangible media that includes code for execution and when executed by a processor is operable to perform operations selecting one or more matching end users for an end user seeking a match on an online social platform where end users participate in different forms of electronic communications with varying levels of engagement with other end users, the operations comprising:

receiving, by a server, responses from the end users to a plurality of questions provided by the online social platform, wherein a response comprises a user selection, via an endpoint, from a plurality of photographs of celebrities presented by a question;

improving a likelihood of the server identifying a successful match for the end user seeking the match based on past communication actions of a pool of end users by;

converting, by the server, the responses received from the pool of end users to a similarity score that quantifies how similar each end user in the pool of end users is to the end user seeking the match based on which of the plurality of photographs of celebrities is selected in the responses, wherein the similarity score is computed for each end user in the pool of end users based on the responses received from the end user being matched and the responses received from the end users in the pool of end users;

selecting, by the server, a first set of end users from the pool of end users using the similarity score;

determining, by the server, a second set of end users, wherein the end users in the second set of end users have participated in a first form of electronic communication with the end users in the first set of end users;

selecting, by the server, one or more end users from the second set of end users as the one or more matching end users; and

transmitting an indication of the one or more matching end users from the server to an endpoint associated with the end user seeking the match.

15. The one or more non-transitory tangible media of claim 14, wherein the operations further comprises:

if the second set of end users is an empty set, determining a third set of end users, wherein the end users in the third set of end users have participated in a second form of electronic communication with the end users in the first set of end users;

wherein a level of engagement indicated by the second form of electronic communication is less than a level of engagement indicated by the first form of electronic communication; and

selecting one or more end users from the third set of end users as the one or more matching end users.

16. The one or more non-transitory tangible media of claim 14, wherein the similarity variable contributes positively to the similarity score, and the rarity variable contributes negatively to the similarity score.

17. The one or more non-transitory tangible media of claim 14, wherein:

computing the similarity score comprises dividing the similarity variable by the rarity variable for each question to obtain a quotient for each question; and

the similarity score comprises a sum of the quotients.

18. A server for selecting one or more matching end users an end user seeking the match on an online social platform where end users participate in different forms of electronic communications with varying levels of engagement with other end users, the server comprising:

a memory for storing a log of the different forms of electronic communications among the end users; and

a processor for;

receiving responses from end users to a plurality of questions provided by the online social platform, wherein a response comprises a user selection from a plurality of photographs of celebrities presented by a question;

improving a likelihood of the server identifying a successful match for the end user seeking the match based on past communication actions of a pool of end users by;

converting the responses received from the pool of end users to a similarity score that quantifies how similar each end user in the pool of end users is to the end user seeking the match, wherein the similarity score is computed for each end user in the pool of end users based on the responses received from the end user being matched and the responses received from the end users in the pool of end users;

selecting a first set of end users from the pool of end users using the similarity score;

determining a second set of end users, wherein the end users in the second set of end users have participated in a first form of electronic communication with the end users in the first set of end users;

selecting one or more end users from the second set of end users as the one or more matching end users; and

transmitting an indication of the one or more matching end users from the server to an endpoint associated with the end user seeking the match.

19. The server of claim 18, wherein the processor is further for:

if the second set of end users is an empty set, determining a third set of end users, wherein the end users in the third set of end users have participated in a second form of electronic communication with the end users in the first set of end users;

wherein a level of engagement indicated by the second form of electronic communication is less than a level of engagement indicated by the first form of electronic communication; and

selecting one or more end users from the third set of end users as the one or more matching end users.

20. The server of claim 19, wherein for each end user in the pool of end users, the processor computes the similarity score based on:

a similarity variable per question based on whether the user selection made by the end user being matched and the user selection made by the end user from the pool of end users are the same, and

a rarity variable per question based on the number of end users who made the same user selection divided by the number of end users in the pool of end users; and

wherein the similarity variable contributes positively to the similarity score, and the rarity variable contributes negatively to the similarity score.