Peer To Patent

Home > Archived Applications > 20080059576 > Prior Art > Detail

Pre-Grant Publication Number: 20080059576

Recommending contacts in a social network

Please help the USPTO examine the application by evaluating the relevance of the publicly submitted prior art to the patent application. Peer To Patent forwards the Top 10 most relevant prior art submissions and their annotations to the USPTO.

Review this prior art and click on the thumbs up (or down) to indicate whether this submission should be forwarded to the USPTO.
If you login then you can add an annotation by typing in the box at the bottom of the screen to comment on the relevance of the prior art to the claims of the patent application.

Prior Art Detail

Annotations(1)

#182Political Artifacts and Personal Privacy: The Yenta Multi-Agent Distributed Matchmaking System

Applies to Claims 1,10,16

Submitted by: Thad StarnerLast updated: about 5 years ago

2 thumbs up 0 thumbs down

Summary / Description

Summary / Description

Lenny Foner's PhD thesis on Yenta describes a privacy-aware matchmaking system based on the contents of a user's profile. The thesis caps much of the work, some published some not, of Pattie Maes's group at the MIT Media Lab during the mid-1990s. I would argue that this group's work pre-dates and was a superset of much of the social network tools now popular. Foner's thesis provides pointers to much of this

Basic Information

Type of Prior Art	Print Publication

Publication Title *	Personal Privacy: The Yenta Multi-Agent Distributed Matchmaking System

Author	Leonard Foner

ISBN

Page Range

Medium	Other printed publication

Publication Date *	April 30, 1999

URL	http://foner.www.media.mit.edu/...

Notes / To Do

Notes	It would be good to download Foner's code and show how it could be used in the manner described here (even though it would be missing a lot of the power of the Yenta idea). Also, it would be good to look for the papers by Upendra Shardanand and Pattie Ma

Excerpt

Excerpt

While Foner's system is more general and privacy-aware, the claims here would seem to be a specific subset of his implementation. The document is quite exhaustive on these ideas, but doing a quick search yields the following relevant bits. "If the pending-contact list is kept sorted by desirability—presumably, by sorting the pending agents to contact by the result of the comparison metric—then A is executing a hill-climbing algorithm to finding a good match. In other words, if we model a landscape in which the height of any given hill is its similarity to some characteristic of A’s, and A’s current set of candidates as some point on the hillside, A should attempt to always travel in the direction of maximum upward gradient, essentially climbing hills in this space until it reaches a maximum. Note that we are climbing a different landscape, composed of different hills, for each characteristic. .... This procedure acts somewhat like human word of mouth. If Sally asks Joe, “What should I look for in a new stereo?” Joe may respond, “I have no idea, but Alyson was talking to me recently about stereos and may know better.” In effect, this has put Alyson into Sally’s pending-contact list (and, if Joe could quote something Alyson said that Sally found appropriate, perhaps into Sally’s cluster cache as well). Sally now repeats the process with Alyson, essentially hill-climbing her way towards someone with the expertise to answer her question.

Relevance

Claims

A system for recommending potential contacts for a target user, comprising:a data store containing contact lists of users, including a contact list for the target user;

a component that identifies, from the contact lists, contact paths from the target user to other users that are within a maximum contact path length;

a component that ranks users on the identified contact paths based on path lengths of the contact paths;

a component that filters out users on the identified contact paths who do not satisfy a recommendation criterion; and

a component that presents to the target user an indication of the ranking of the non-filtered-out users as recommendations for potential contacts.

Relevance

Foner's Yenta did this in a general form: "In the case of Yenta (see Section 4.4.4), these characteristics are sets of weighted vectors of keywords, and the comparison is performed by dotting vectors together." A simple way to do the implementation suggested in the claim is for the yenta to contain the contact lists of users. Dotting the vectors would yield dependent claim 7 (multiple paths). The thesis goes on to describe ways of doing path lengths through recommendations of recommendations (see the excerpt above).

Claim Chart

All

A system for identifying a social path between a first user and a second user, the social path being within a maximum social path length, comprising:a data store containing contact lists of users, including a contact list for the first user and a contact list for the second user;

a component that identifies, from the contact lists, contact paths from the first user to other users that are within a first maximum contact path length and contact paths from the second user to other users that are within a second maximum contact path length, wherein the sum of the first maximum contact path length and the second maximum contact path length equals the maximum social path length; and

a component that, when there is a contact path from the first user to another user and a contact path from the second user to that same other user, indicates that a social path exists from the first user to the second user.

Relevance

See claim 1 relevance.

Claim Chart

All

A computer-readable medium containing instructions for controlling a computing system to identify potential contacts for a target user, by a method comprising:identifying from a contact list of the target user contact paths from the target user to other users that are within a maximum contact path length;

ranking users on the identified contact paths;

filtering out users on the identified contact paths who do not satisfy a recommendation criterion; and

storing an indication of the ranking of the non-filtered-out users as an identification of potential contacts.

Relevance

This functionality is the basis of the yenta.

Claim Chart

All

0 days left