Automatically selecting addressees for receiving a content item

Patent metadata

Field	Value
Publication number	US-9798811-B2
Application number	US-201514625985-A
Country	US
Kind code	B2
Filing date	Feb 19, 2015
Priority date	Mar 28, 2014
Publication date	Oct 24, 2017
Grant date	Oct 24, 2017

Abstract

A system, method, and apparatus are provided for distributing a content item toward target recipients solely via first degree connections (e.g., in a professional network, in a social network). For a selected content item and identified target recipients of the item, when a user initiates a message to forward or otherwise convey the content item, one or more schemes are applied to select and automatically populate the message with suitable addressees. In one scheme, values are computed for each neighbor of the sender, to indicate the value of delivering the item to that neighbor; the message is automatically addressed to the highest-value neighbors. In another scheme, user communities that encompass the target recipients are identified and the message is automatically addressed to neighbors that are best able to disseminate the item throughout a community. In another scheme a minimal set of neighbors having connections to all target recipients is identified.

First claim

What is claimed is:

1. A method of automatically populating a message with one or more selected addressees, the method comprising:
selecting a content item to be distributed via automatically addressed messages;
identifying multiple target recipients of the content item;
identifying one or more communities comprising the target recipients; and
upon notification of generation of a message comprising the content item by a message initiator, operating one or more processors to:
identify, within a network comprising the message initiator, a sub-network comprising first degree connections of the message initiator;
if the message initiator is a member of an identified community, rank the first degree connections by their connectedness within the identified communities;
select as addressees one or more of the first degree connections that have not previously received the content item; and
automatically address the message to the selected addressees; and
transmit the message toward the selected addressees.

2. The method of claim 1 , wherein selecting as addressees one or more of the first degree connections comprises:
for each first degree connection, calculating an associated value of delivering the content item to the first degree connection.

3. The method of claim 2 , wherein calculating a value associated with a given first degree connection comprises:
obtaining a weight corresponding to the given first degree connection, wherein the weight is proportional to similarities between characteristics of the content item and corresponding attributes of the first degree connection;
identifying first degree connections of the given first degree connection;
for each first degree connection of the given first degree connection, calculating a value of delivering the content item to the corresponding first degree connection;
summing the values of delivering the content item to the corresponding first degree connections of the given first degree connection;
multiplying the sum by a probability that the given first degree connection will initiate a message to transmit the content item, to yield a probable value; and
combining the probable value and the weight corresponding to the given first degree connection to yield the value associated with the given first degree connection.

4. The method of claim 2 , wherein selecting as addressees one or more of the first degree connections further comprises:
ranking the first degree connections by said calculated values.

5. The method of claim 1 , further comprising operating the one or more processors to:
if the message initiator is not a member of at least one identified community, rank the first degree connections by their proximities to the identified communities.

6. The method of claim 1 , wherein selecting as addressees one or more of the first degree connections comprises:
identifying a minimal set of the first degree connections through which the message initiator is connected to the target recipients.

7. The method of claim 1 , wherein automatically addressing the message comprises:
inserting addresses of the selected addressees into an addressee field of the message.

8. The method of claim 1 , wherein the message initiator is unable to remove any of the selected addressees from the message.

9. The method of claim 1 , wherein the message initiator is unable to add to the message any addressees other than the selected addressees.

10. An apparatus for automatically populating a message with one or more selected addressees, comprising:
one or more processors; and
a memory storing instructions that, when executed by the one or more processors, cause the apparatus to:
select a content item to be distributed via automatically addressed messages;
identify multiple target recipients of the content item;
identify one or more communities comprising the target recipients; and
upon notification of generation of a message comprising the content item by a message initiator:
identify, within a network comprising the message initiator, a sub-network comprising first degree connections of the message initiator;
if the message initiator is a member of an identified community, rank the first degree connections by their connectedness within the identified communities;
select as addressees one or more of the first degree connections that have not previously received the content item; and
automatically address the message to the selected addressees; and
transmit the message toward the selected addressees.

11. The apparatus of claim 10 , wherein selecting as addressees one or more of the first degree connections comprises:
for each first degree connection, calculating an associated value of delivering the content item to the first degree connection.

12. The apparatus of claim 11 , wherein calculating a value associated with a given first degree connection comprises:
obtaining a weight corresponding to the given first degree connection, wherein the weight is proportional to similarities between characteristics of the content item and corresponding attributes of the first degree connection;
identifying first degree connections of the given first degree connection;
for each first degree connection of the given first degree connection, calculating a value of delivering the content item to the corresponding first degree connection;
summing the values of delivering the content item to the corresponding first degree connections of the given first degree connection;
multiplying the sum by a probability that the given first degree connection will initiate a message to transmit the content item, to yield a probable value; and
combining the probable value and the weight corresponding to the given first degree connection to yield the value associated with the given first degree connection.

13. The apparatus of claim 11 , wherein selecting as addressees one or more of the first degree connections further comprises:
ranking the first degree connections by said calculated values.

14. The apparatus of claim 10 , the memory further storing instructions that, when executed by the one or more processors, cause the apparatus to:
if the message initiator is not a member of at least one identified community, rank the first degree connections by their proximities to the identified communities.

15. The apparatus of claim 10 , wherein selecting as addressees one or more of the first degree connections comprises:
identifying a minimal set of the first degree connections through which the message initiator is connected to the target recipients.

16. A system for automatically populating a message with one or more selected addressees, the system comprising:
one or more processors;
network data describing a user network of nodes representing users and edges representing connections between users;
a recipient selection module comprising a non-transitory computer readable medium storing instructions executable by the one or more processors to:
identify multiple target recipients of a selected content item;
a community identification module comprising a non-transitory computer readable medium storing instructions executable by the one or more processors to:
identify one or more user communities comprising the target recipients;
a community ranking module comprising a non-transitory computer readable medium storing instructions executable by the one or more processors to:
if the first user is a member of an identified user community, rank network neighbors of a first user by their connectedness within the identified user communities;
an addres

Assignees

• Linkedin Corp

Inventors

• Andrews June H
• Schissel Jason R

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• G06F16/951

  Indexing; Web crawling techniques · CPC title

• G06F16/908 Primary

  using metadata automatically derived from the content · CPC title

• G06Q50/01

  Physics · mapped topic

• H04L51/32

  Electricity · mapped topic