Constructing graphs from attributes of member profiles of a social networking service

Patent metadata

Field	Value
Publication number	US-10412189-B2
Application number	US-201514953943-A
Country	US
Kind code	B2
Filing date	Nov 30, 2015
Priority date	Aug 31, 2015
Publication date	Sep 10, 2019
Grant date	Sep 10, 2019

Abstract

This disclosure is directed to determining various economic graph indices and, in particular, to systems and methods that leverage a graph analytic engine and framework to determine values assigned to graph nodes extracted from one or more member profiles, and visualizing said values to correlate skills, geographies, and industries. The disclosed embodiments include a client-server architecture where a social networking server has access to a social graph of its social networking members. The social networking server includes various modules and engines that import the member profiles and then extracts certain defined attributes from the member profiles, such as employer (e.g., current employer and/or past employers), identified skills, educational institutions attended, and other such defined attributes. Using these attributes as nodes, the social networking server constructs a graph using various graph processing techniques. The resulting graph is then used to correlate and rank the various attributes that define the graph.

First claim

The invention claimed is:

1. A system comprising:
a machine-readable medium storing computer-executable instructions; and
at least one hardware processor communicatively coupled to the machine-readable medium that, when the computer-executable instructions are executed, the at least one hardware processor is configured to:
extract a first plurality of attributes from a plurality of member profiles of a social networking service, each member profile including a second plurality of attributes, where each attribute is a characteristic of a member corresponding to the member profile;
define a plurality of nodes corresponding to each attribute of the first plurality of attributes;
assign a first plurality of values to a first subset of the plurality of nodes, each node of the first subset being assigned a corresponding value;
determine a second plurality of values for a second subset of the plurality of nodes, wherein:
each node of the second subset is associated with at least one edge connecting the node with at least one other node, wherein the at least one edge is associated with a corresponding propagation equation;
the second plurality of values are determined through a graph propagation technique using the first plurality of values and the corresponding propagation equation associated with a node selected from the second subset; and
each node of the second subset is associated with a corresponding value selected from the second plurality of values;

determine a third plurality of values for a third subset of the plurality of nodes, wherein:
each node of the third subset of the plurality of nodes is associated with a determined value of the third plurality of values;
the third plurality of values are determined based on the first plurality of values;

correlate one or more nodes from the third subset of nodes with one or more nodes from the second subset of nodes;
generate an index that includes:
the correlation between the one or more nodes of the third subset of nodes with one or more nodes from the second subset of nodes; and
a ranking of at least one attribute corresponding to a node selected from the second subset of the plurality of nodes, the ranking being based on the value assigned to the node corresponding to the at least one attribute; and

provide the index for display by a client device in communication with the at least one hardware processor.

2. The system of claim 1 , wherein the nodes of the first subset of the plurality of nodes each correspond to an employer of one or more members associated with the plurality of member profiles.

3. The system of claim 1 , wherein:
the first subset of the plurality of nodes correspond to a first type of attribute selected from the first plurality of attributes;
the second subset of the plurality of nodes correspond to a second type of attribute selected from the first plurality of attributes; and
the first type of attribute is different than the second type of attribute.

4. The system of claim 1 , wherein the second plurality of values are further determined based on at least one constraint corresponding to at least one edge connecting at least one node selected from second subset of the plurality of nodes with at least one node selected from the first subset of the plurality of nodes.

5. The system of claim 1 , wherein the at least one hardware processor is further configured to define a plurality of edges connecting the first subset of nodes, the second subset of nodes, and the third subset of nodes based on the type of attribute corresponding to the nodes selected from a given subset.

6. The system of claim 1 , wherein the at least one hardware processor is further configured to receive an input from the client device identifying which of the attributes from the second plurality of attributes are to be extracted as the first plurality of attributes.

7. A method comprising:
extracting, by at least one hardware processor, a first plurality of attributes from a plurality of member profiles of a social networking service, each member profile including a second plurality of attributes, where each attribute is a characteristic of a member corresponding to the member profile;
defining a plurality of nodes corresponding to each attribute of the first plurality of attributes;
assigning a first plurality of values to a first subset of the plurality of nodes, each node of the first subset being assigned a corresponding value;
determining a second plurality of values for a second subset of the plurality of nodes, wherein:
each node of the second subset is associated with at least one edge connecting the node with at least one other node, wherein the at least one edge is associated with a corresponding propagation equation;
the second plurality of values are determined through a graph propagation technique using the first plurality of values and the corresponding propagation equation associated with a node selected from the second subset; and
each node of the second subset is associated with a corresponding value selected from the second plurality of values;

determining a third plurality of values for a third subset of the plurality of nodes, wherein:
each node of the third subset is associated with a determined value selected from the third plurality of values; and
the third plurality of values are determined based on the first plurality of values;

correlating one or more nodes of the third subset of nodes with one or more nodes of the second subset of nodes;
generating an index that includes:
the correlation between the one or more nodes of the third subset of nodes with the one or more nodes of the second subset of nodes; and
a ranking of at least one attribute corresponding to a node selected from the second subset of the plurality of nodes, the ranking being based on the value assigned to the node corresponding to the at least one attribute; and

providing the index for display by a client device in communication with the at least one hardware processor.

8. The method of claim 7 , wherein the nodes of the first subset of the plurality of nodes each correspond to an employer of one or more members associated with the plurality of member profiles.

9. The method of claim 7 wherein:
the first subset of the plurality of nodes correspond to a first type of attribute selected from the first plurality of attributes;
the second subset of the plurality of nodes correspond to a second type of attribute selected from the first plurality of attributes; and
the first type of attribute is different than the second type of attribute.

10. The method of claim 7 , wherein the second plurality of values are further determined based on at least one constraint corresponding to at least one edge connecting at least one node selected from second subset of the plurality of nodes with at least one node selected from the first subset of the plurality of nodes.

11. The method of claim 7 , further comprising:
defining a plurality of edges connecting the first subset of nodes, the second subset of nodes, and the third subset of nodes based on the type of attribute corresponding to the nodes selected from a given subset.

12. The method of claim 7 , further comprising:
receiving an input from a client device that identifies which of the attributes from the second plurality of attributes are to be extracted as the first plurality of attributes;
providing the index for display by a client device in communication with the at least one hardware processor.

13. A machine-readable medium storing computer-executable instructions thereon that, when executed by at least one hardware processor,

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Bollinger Jacob
• Hardtke David
• Zhao Bo

Classifications

• H04W4/21

  for social networking applications · CPC title

• G06F16/9024

  Graphs; Linked lists (G06F16/9027 takes precedence) · CPC title

• H04L67/306 Primary

  User profiles · CPC title