It is provided a method of matching pairs of persons. The method includes receiving from the persons personal opinions on other persons, and based on a collaborative filtering algorithm, calculating from the personal opinions a first estimated opinion of a first person on a second person and a second estimated opinion of the second person on the first person. The method also includes matching the two persons in accordance with the estimated opinions and connecting them for a predetermined time duration. The first estimated opinions may be the estimated probability that the first person wants to be matched to the second person. The matching of the two persons is done in accordance with the product of the probabilities. Matching order is determined by a difference between a highest and a second highest product of a person in two different pairs.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
Claims not yet imported for this patent.
Claims are being imported from USPTO data. Check back soon!
See the raw claims text section below.
Original claims text from the patent document.
Claim 1: . A method of matching one or more pairs of persons out of four or more persons, the method comprising:
Claim 2: . The method offurther comprising connecting the first person and the second person.
Claim 3: . The method of, wherein said connecting is limited to a predetermined time duration.
Claim 4: . The method of, wherein said connecting is done using a communications channel selected from a group of channels consisting of text chat over internet protocol, voice over internet protocol, video over internet protocol, and electronic mail.
Claim 5: . The method of, wherein subsequent to the step of:
Claim 6: . The method of, further comprising providing mutual communication details to said first person and to said second person in accordance with said first personal opinion and said second personal opinion.
Claim 7: . The method of, wherein said communication details are selected from a group consisting of: electronic mail address, phone number, instant messaging address and physical address.
Claim 8: . The method ofwherein the method includes estimating a probability that the first person wants to be matched to the second person, and a probability that the second person wants to be matched to the first person.
Claim 9: . The method ofwherein the matching of said first person and said second person is done in accordance with the result of a multiplication of the probabilities.
Claim 10: . The method ofwherein order of matching is determined in accordance with a difference between a highest multiplication result of a person in a pair with any other person and the second highest multiplication result said person has in a different pair.
Claim 11: . A program storage device readable by a computerized apparatus, tangibly embodying a program of instructions executable by the computerized apparatus to perform the method of.
Claim 12: . A server connected to a wide area network, for matching one or more pairs of persons out of four or more persons, the persons communicating with the server using the wide area network, the server comprising:
Claim 13: 13. A method of matching one or more pairs of persons out of a group of persons to be matched including at least four persons, the method comprising:
Claim 14: 14. The method offurther comprising connecting the first person and second person.
Claim 15: 15. The method of, wherein said connecting is limited to a predetermined time duration.
Claim 16: 16. The method of, wherein said connecting is done using a communications channel selected from a group of channels consisting of text chat over internet protocol, voice over internet protocol, video over internet protocol, and electronic mail.
Claim 17: 17. The method of, wherein subsequent to connecting the first person and the second person, the method further comprising receiving a first personal opinion of the first person on the second person and a second personal opinion of the second person on the first person.
Claim 18: 18. The method of, further comprising providing mutual communication details to said first person and to said second person in accordance with said first personal opinion and said second personal opinion.
Claim 19: 19. The method of, wherein said communication details are selected from the group consisting of: electronic mail address, phone number, instant messaging address and physical address.
Claim 20: 20. The method of, wherein said first estimated opinion is an estimated probability that the first person wants to be matched to the second person, and said second estimated opinion is the estimated probability that the second person wants to be matched to the first person.
Claim 21: 21. The method of, wherein the matching of said first person and said second person is done in accordance with a result of one or more multiplications of said probabilities.
Claim 22: 22. The method of, wherein order of matching is determined in accordance with a difference between a highest multiplication result of a person in a pair with any other person and a second highest multiplication result said person has in a different pair.
Claim 23: 23. A program storage device readable by a computerized apparatus, tangibly embodying a program of instructions executable by the computerized apparatus to perform the method of.
Claim 24: 24. A server connected to a wide area network, for matching one or more pairs of persons out of a group of persons, the group of persons comprising at least four persons, the persons communicating with the server using the wide area network, the server comprising:
Claim 25: 25. The server of, wherein dividing the group of persons to be matched into the two or more smaller groups includes putting at least one person of the group of persons into two or more different smaller groups to be processed separately.
Claim 26: 26. The server of, wherein the dividing the group of persons into the smaller groups is based on age such that the at least one smaller group comprises one or more persons of similar age.
Claim 27: 27. The server of, wherein the dividing the group of persons into the smaller groups is based on location such that the at least one smaller group comprises one or more persons of similar location.
Claim 28: 28. A method implemented by a server connected to a wide area network, for matching one or more pairs of persons out of a group of persons, the group of persons comprising four persons, the persons communicating with the server using the wide area network, the method comprising the server performing the following:
Claim 29: 29. The method of, wherein dividing the group of persons to be matched into the two or more smaller includes putting at least one person of the group of persons into two or more different smaller groups to be processed separately.
Claim 30: 30. The method of, wherein the dividing the group of persons into the smaller groups is based on age such that the at least one smaller group comprises one or more persons of similar age.
Claim 31: 31. The method of, wherein the dividing the group of persons into the smaller groups is based on location such that the at least one smaller group comprises one or more persons of similar location.
Claim 32: 32. The method of, wherein said matching is at least partially based on a determination that said first person and said second person have expressed an interest in at least one of: a romantic relationship, a non-romantic social relationship, or a business relationship.
Complete technical specification and implementation details from the patent document.
Notice: More than one reissue application has been filed for the reissue of U.S. Pat. No. 8,195,673. The present application is a continuation reissue application of application Ser. No. 17/584,044 filed Jan. 25, 2022 which is a reissue application of application Ser. No. 12/574,713 filed Oct. 7, 2009, issued as U.S. Pat. No. 8,195,673 on Jun. 5, 2012. The present application is also a reissue of U.S. Pat. No. 8,195,673.
The present invention relates to a method and system for finding matches between people, and more specifically to matching people connected to an online dating service.
The Internet has become a popular medium for creating social relationships, and especially romantic relationships.
Many online dating websites exist, which allow user to view other users' profiles and contact those they are interested in.
Some dating websites try to match people according to their answers to a set of questions. Examples of these include www.chemistry.com, www.eharmony.com, and www.okcupid.com. Drawbacks of such methods are that they don't take into account physical appearance and that questionnaires may fail to capture many aspects of ones' personality.
U.S. Pat. No. 7,203,674 describes a method and system for connecting and matching users in an electronic dating service. Users are connected for a brief period, and are allowed further contact with each other if both request so.
Collaborative Filtering is the concept of predicting the opinion of one user on an item, based on his opinion on other items, and the opinions of other users on that item and the other items.
The publication “Item-Based Top-N Recommendation Algorithms” by Mukund Deshpande and George Karypis (published in “ACM Transactions on Information Systems” Volume 22, Issue 1, pp. 143-177, 2004) describes one Collaborative Filtering algorithm.
The publication “Recommender System for Online Dating Service” by Lukas Brozovsky and Vaclav Petricek, proposes using Collaborative Filtering in online dating. However, as the authors acknowledge, Collaborative Filtering is not well suited for online dating, for the following reasons:
There is an evident need for an efficient method for finding matches between people.
It is provided a method of matching several pairs out of a plurality of persons. The method includes receiving from the persons personal opinions on other persons, based on at least a collaborative filtering algorithm, calculating from the personal opinions a first estimated opinion of a first person on a second person and a second estimated opinion of the second person on the first person, and matching the first person and the second person in accordance with the first and second estimated opinions. The collaborative filtering algorithm is a method of estimating opinion of a person on a certain object based on opinions of the person on other objects, and opinions of other persons on the certain object and some of the other objects. The method may include connecting the first person and the second person for a predetermined time duration. The connecting is done using a communications channel like text chat over internet protocol, voice over internet protocol, video over internet protocol, and electronic mail. The method may further include receiving a first personal opinion of the first person on the second person and a second personal opinion of the second person on the first person. Also, the method may include providing mutual communication details to the first person and to the second person in accordance with the first personal opinion and the second personal opinion. Exemplary communication details are electronic mail address, phone number, instant messaging address and physical address.
In some embodiments, the first estimated opinion is the estimated probability that the first person wants to be matched to the second person, and the second estimated opinion is the estimated probability that the second person wants to be matched to the first person. The matching of the first person and the second person is done in accordance with the result of the multiplication of the probabilities. The order of matching may be determined in accordance with a difference between a highest multiplication result of a person in a pair with any other person and the second highest multiplication result said person has in a different pair.
In some embodiments, a program storage device readable by a computerized apparatus, is tangibly embodying a program of instructions executable by the computerized apparatus to perform the method of matching pairs of several persons.
It is provided a computerized system for matching several pairs out a plurality of persons. The persons are communicating with the system using a wide area network. The system is configured to execute the aforementioned methods.
The present invention will now be described in terms of specific example embodiments. It is to be understood that the invention is not limited to the example embodiments disclosed. It should also be understood that not every feature of the methods and system handling the method is necessary to implement the invention as claimed in any particular one of the appended claims. Various elements and features of the method are described to fully enable the invention. It should also be understood that throughout this disclosure, where a method is shown or described, the steps of the method may be performed in any order or simultaneously, unless it is clear from the context that one step depends on another being performed first.
Before explaining several embodiments of the invention in detail, it is to be understood that the invention is not limited in its application to the details as set forth in the following description or illustrated in the drawings. The invention is capable of other embodiments or of being practiced or carried out in various ways. Also, it is to be understood that the phraseology and terminology employed herein is for the purpose of description and should not be regarded as limiting.
Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The systems, methods, and examples provided herein are illustrative only and not intended to be limiting.
In the description and claims of the present application, each of the verbs “comprise”, “include” and “have”, and conjugates thereof, are used to indicate that the object or objects of the verb are not necessarily a complete listing of members, components, elements or parts of the subject or subjects of the verb.
It is an object of the present invention to allow effective matching between people by using Collaborative Filtering.
The System
is a diagram of the environment in which the system operates. The Systemis preferably software running on a Server, connected to the Internet. Usersconnect to the Internet using Devicesrunning Internet Browsers such as Microsoft Internet Explorer or Mozilla FireFox. The Usersdirect their Browsers to connect to the Server, where they are presented with a User Interface to the System.The Processis a diagram of the process performed by the System once Users are connected to it:
In stepsome or all of the Users are each connected to another User. This connection may be done using text chat, voice, video, email or any other suitable medium. The System may additionally present to each User information about the other User, such as age, gender, location, a picture etc. In one preferred embodiment, the connection is limited in time.
In stepeach of the connected Users is asked for his opinion about the User he was just connected to. The opinion may be a score or a decision on whether he would like to further communicate with the other User. The opinions are stored.
The System then attempts to match between Users. The System's goal is to find matches that have a relatively high likelihood of being successful (i.e. a match in which each User has a positive opinion on the other).
The System matches Users by estimating the opinion each User would have on all or some of the other Users, and choosing the matches in which both Users are estimated to have a positive opinion on the other User.
In step, the System uses Collaborative Filtering to estimate opinions. In other words, the opinions the User gave on other Users is compared to the opinions other Users gave, in order to predict the opinion of the User on Users for which he did not yet give an opinion. Any effective Collaborative Filtering algorithm may be used for this purpose.
Once the System has estimated opinions of all Users on all (or some of the) other Users, it attempts to make one-to-one matches that create the overall highest number of successful matches.
In order to simplify the matching process, in stepthe System first normalizes all estimated opinions to represent the likelihood (between 0 and 1) that a User will have a positive opinion on another User. The system then multiplies each likelihood by the opposite likelihood (that the other User will have a positive opinion on the first User), thereby reaching the likelihood that both Users will have a positive opinion on each other.
In step, the system then calculates for each User the difference between his highest likelihood match and his second highest likelihood match (“likelihood difference”). The likelihood difference represents the ‘importance’ of matching that User to his most likely match.
In step, the system finds the User who had the highest likelihood difference, and matches him to his most likely match.
The two matched Users are removed from the list, and the process is repeated from stepuntil no more Users remain or no more effective matches (i.e. matches with high likelihood of mutual positive opinion) can be found.
Once the matching process is complete, each User is connected to their match, as in step, and the process is repeated. In each iteration of the process, more information about Users' opinions is accumulated, which should result in higher accuracy of the Collaborative Filtering algorithm and overall matching.
In a preferred embodiment of the present invention, additional filtering is applied to the matches. For example, a female user may require to be matched only to male users aged 25-30. This may be enforced in stepby placing a likelihood of 0 for the match between that female user and all users not matching the criteria. This process can also be applied to all user-pairs who were already connected, thereby preventing repeated matches.
In one embodiment of the present invention, if both Users provided in stepa positive opinion on the other, then they are provided mutual communication details such as email address, phone number, instant messaging address, or physical address.
Since the process described above involves checking the match between all possible user-pairs, processing time may become unacceptable when servicing a large number of Users. In such a case, the System may divide the Users to smaller groups, and run the process on each group separately. This may of course cause the System to miss possible matches. To reduce this effect, the System may place each User in several groups, as well as choose groups that are a-priori more likely to create good matches (e.g. group together Users of similar age and location).
Referring now to, which describes another embodiment of the current invention, it is provided a methodof matching several pairs out of a plurality of persons. The method includes stepof connecting persons to each other, stepof receiving from the persons personal opinions on other persons, stepof calculating from the personal opinions a first estimated opinion of a first person on a second person and a second estimated opinion of the second person on the first person, based on at least a collaborative filtering algorithm, stepof multiplying mutual estimated opinions for user-pairs, and stepof matching the first person and the second person in accordance with the first and second estimated opinions.
In some embodiments, the method may include the stepof connecting the first person and the second person for a predetermined time duration. The connecting is done using a communications channel like text chat over internet protocol, voice over internet protocol, video over internet protocol, and electronic mail. The method may further include the stepof receiving a first personal opinion of the first person on the second person and a second personal opinion of the second person on the first person. Also, the method may include the stepof providing mutual communication details to the first person and to the second person in accordance with the first personal opinion and the second personal opinion. Exemplary communication details are electronic mail address, phone number, instant messaging address and physical address.
In some embodiments, the first estimated opinion is the estimated probability that the first person wants to be matched to the second person, and the second estimated opinion is the estimated probability that the second person wants to be matched to the first person. The matchingof the first person and the second person is done in accordance with the result of the multiplication of the probabilities.
While the present invention mainly discusses aspects related to online dating, it will be appreciated by persons skilled in the art that it may be easily extended to other situations applicable to matching people, such as non-romantic social relationships and business relationships.
While particular embodiments of the invention have been shown and described, it will be obvious to those skilled in the art that changes and modifications may be made without departing from the invention in its broader aspects, and therefore, the aim in the appended claims is to cover all such changes and modifications as fall within the true spirit and scope of the invention.
Unknown
April 14, 2026
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.