AUTOMATED SOCIAL NETWORKING GRAPH MINING AND VISUALIZATION

• US 20110283205A1
• Filed: 05/14/2010
• Published: 11/17/2011
• Est. Priority Date: 05/14/2010
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Luo, Gang, Liu, Xiaojiang, Nie, Zaiqing, Zhang, Bo, Cao, Yong, Ma, Yunxiao, Wen, Ji-Rong, Zhang, Ruochi, Xu, Ying-Qing
• Granted Patent: US 9,990,429 B2
• Time in Patent Office: Days
• US Class Current: 715/763
• CPC Class Codes: G06F 16/9024 Graphs; Linked lists G06F16/9027 takes precedence
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9536 Search customisation based on social or collaborative filtering
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

The automated social networking graph mining and visualization technique described herein mines social connections and allows creation of a social networking graph from general (not necessarily social-application specific) Web pages. The technique uses the distances between a person'"'"'s/entity'"'"'s name and related people'"'"'s/entities names on one or more Web pages to determine connections between people/entities and the strengths of the connections. In one embodiment, the technique lays out these connections, and then clusters them, in a 2-D layout of a social networking graph that represents the Web connection strengths among the related people'"'"'s or entities'"'"' names, by using a force-directed model.

Claims

1. A computer-implemented process for identifying social connections among entities, comprising:

using a computing device for;

receiving a set of Web pages that identify social connections between entities;

parsing the content of each of the Web pages into information blocks;

identifying names of the entities in the information blocks;

ranking the social connections among the entities'"'"' names in the information blocks considering position and surrounding text of the names in the information blocks; and

integrating the ranked social connections from all the information blocks to determine strengths of the connections between the entities associated with the entities'"'"' names.

2. The computer-implemented process of claim 1, further comprising creating a social networking graph based on the strengths of the connections between the entities associated with the entities'"'"' names.

3. The computer-implemented process of claim 1, wherein ranking the social connections among the entities'"'"' names further comprises associating connection weights with entities'"'"' names.

4. The computer-implemented process of claim 1 wherein parsing the content of each of the Web pages comprises using a visual parser to parse the content into information blocks.

5. A computer-implemented process for graphing social connections among entities'"'"' names extracted from general Web pages by creating a 2-D graph with a set of vertices representing names, and a set of edges representing social connections, comprising:

using a computing device to perform;

inputting a ranked list of social connections between a social graph owner and additional entities;

placing the social graph owner in the center of the 2D graph as a center vertex;

for each of the additional entities, placing a vertex representing a name of an entity in the ranked list in a difference orbit around the center vertex where the shorter the orbit'"'"'s radius is, the stronger a social connection between the vertex in the orbit and the center vertex is;

clustering the vertices into different clusters according to connectivity between the vertices;

placing the vertices in the same cluster closer to each other than to vertices in other clusters;

placing clusters of vertices so that clusters of vertices do not overlap each other; and

using a force-directed model to improve the uniformity of the 2D layout.

6. The computer-implemented process of claim 5 wherein the force directed model further comprises a repulsive force between each two vertices and wherein each vertex is either radially or tangentially free or both radially and tangentially free so that it can move according to the repulsive force.

7. The computer-implemented process of claim 5 wherein the force directed model further comprises an attractive force among the edges and wherein each edge is either radially or tangentially free or both radially and tangentially free so that the edge can move according to the attractive force.

8. The computer-implemented process of claim 5 wherein the force directed model further comprises a repulsive force between adjacent orbits and wherein each orbit is either radially or tangentially free or both radially and tangentially free so that the orbit can move according to the repulsive force.

9. The computer-implemented process of claim 5 wherein the force directed model further comprises creating an unpenetratable boundary to isolate the clusters that have no connection between to other.

10. The computer-implemented process of claim 9 wherein each unpenetratable boundary is either radially or tangentially free or both radially and tangentially free so that each unpenetratable boundary can move to isolate clusters that have no connection to each other.

11. The computer-implemented process of claim 5 further comprising minimizing energy in the force-directed model in order to optimize the uniformity of the 2D layout.

12. A system for displaying the social connections among entities'"'"' names extracted from general web pages in the form of creating a 2-D graph with a set of vertices representing names, and a set of edges representing social connections, comprising:

a general purpose computing device;

a computer program comprising program modules executable by the general purpose computing device, wherein the computing device is directed by the program modules of the computer program to,

input a ranked list of social connections between a social graph owner and additional entities;

place the social graph owner in the center of the 2D graph as a center vertex;

for each entity in the ranked list, place a vertex representing a name of an entity in the ranked list in a difference orbit around the center vertex where the shorter the orbit'"'"'s radius is, the stronger the social connection between the vertex in the orbit and the center vertex is;

cluster the vertices into different clusters according to the connectivity between the vertices;

use a force-directed model to optimize the uniformity of the 2D layout, wherein the force-directed model comprises;

a repulsive force between each two vertices;

an attractive force among the edges;

a repulsive force between adjacent orbits; and

an unpenetratable boundary boundary to isolate clusters that have no connection to each other.

13. The system of claim 12 wherein each vertex, edge, orbit and unpenetratable boundary are either radially or tangentially free or both radially and tangentially free so as to allow movement according to a force.

14. The system of claim 12, further comprising a graphical user interface for displaying the 2D graph on a display and allowing a user to manipulate the 2D graph.

15. The system of claim 12, wherein the graphical user interface further displays the vertices of the 2D graph in color and wherein vertices that are close to each other are displayed in similar colors.

16. The system of claim 15 wherein the color of the vertices changes according to polar coordinates of the vertices'"'"' locations from 0°

to 360°

.

17. The system of claim 15 wherein the graphical user interface further comprises animation comprising, when user a selects a vertex, the 2D graph will change to a new 2D graph.

18. The system of claim 17, further comprising during the transition to the new 2D graph, displaying the kinds of animations wherein:

a) originally displayed vertices which will not be on the new 2D graph are no longer displayed.

b) originally displayed vertices which will still be in the new 2D graph will move to a new position; and

c) new vertices which were not in the original 2D graph will appear and move to position.

19. The system of claim 12, wherein an entity can be one of a group comprising:

a person;

an organization; and

a key word.

20. The computer-implemented process of claim 12 wherein the ranked list is ranked by relationship weight between two names defined by a distance measure of a relationship and a context measure of a relationship.