Displaying search results with edges/entity relationships in regions/quadrants on a display device

• US 9,317,569 B2
• Filed: 12/10/2014
• Issued: 04/19/2016
• Est. Priority Date: 04/09/2010
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Nie, Zaiqing, Liu, Xiaojiang, Zhu, Jun, Wen, Ji-Rong
• Primary Examiner(s): VINCENT, DAVID ROBERT
• Application Number:
  US14/566,480
• Publication Number:
  US 20150095316A1
• Time in Patent Office: 496 Days
• Field of Search: 706/12, 706/45
• US Class Current: 1/1
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/36 Creation of semantic tools, e.g. ontology or thesauri
• CPC Class Codes: G06F 16/9038 Presentation of query results
• CPC Class Codes: G06F 16/958 Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 7/00 Computing arrangements based on specific mathematical models
• CPC Class Codes: G06Q 10/10 Office automation; Time management

Abstract

Methods and systems for Web-scale entity relationship extraction are usable to build large-scale entity relationship graphs from any data corpora stored on a computer-readable medium or accessible through a network. Such entity relationship graphs may be used to navigate previously undiscoverable relationships among entities within data corpora. Additionally, the entity relationship extraction may be configured to utilize discriminative models to jointly model correlated data found within the selected corpora.

Claims

1. One or more computer-readable media storage devices storing computer-executable instructions that, when executed, cause one or more processors to perform acts comprising:

obtaining web documents based at least in part on a search term;

extracting a plurality of entities and entity relationships from the web documents, each of the plurality of entities related to, but distinct from, the search term;

displaying at a display device in communication with the one or more processors, representations indicating each of the plurality of entities;

displaying at the display device, edges to define pairs of the displayed representations, the edges indicated by the entity relationships;

displaying at the display device, a representation of the search term and edges from the representation of the search term to each of the representations of the plurality of entities;

receiving user input indicating an edge between representations of two particular entities; and

displaying, at the display device, a description of a relationship between the two particular entities in response to the received user input.

2. One or more computer-readable media storage devices as recited in claim 1, wherein the displaying representations indicating each of the plurality of entities comprises:

displaying representations of entities connected by edges to more entities in a size larger than representations of entities connected by edges to fewer entities; and

displaying the representation of the search term in a size larger than representations indicating each of the plurality of entities.

3. One or more computer-readable media storage devices as recited in claim 1, further comprising:

clustering relationship data obtained by extracting the entity relationships; and

grouping together the representations indicating each of the plurality of entities based at least in part on the clustering.

4. One or more computer-readable media storage devices as recited in claim 1, wherein the edges from the representation of the search term to each of the representations of the plurality of entities comprise:

relationships of the search term to each of the plurality of entities.

5. One or more computer-readable media storage devices as recited in claim 1, wherein each representation of an entity is displayed as a circle having a diameter size based at least in part on a number of relationships of that entity with other entities.

6. One or more computer-readable media storage devices as recited in claim 1, wherein the user input comprises a cursor hovering over the edge between representations of two particular entities.

7. One or more computer-readable media storage devices as recited in claim 1, wherein each representation of an entity is connected to the representation of the search term and to at least one other representation of an entity.

8. A method comprising:

under control of one or more processors configured with executable instructions;

obtaining web documents based at least in part on a search term;

extracting a plurality of entities and entity relationships from the web documents, each of the plurality of entities related to, but distinct from, the search term;

clustering relationship data obtained by extracting the entity relationships;

causing display of representations indicating each of the plurality of entities, wherein the representations are grouped together on the display based at least in part on the clustering such that representations having the same or similar relationship data are closer together than representations not having the same or similar relationship data;

causing display of edges to define pairs of the displayed representations, the edges indicated by the entity relationships;

causing display of a representation of the search term and edges from the representation of the search term to each of the representations of the plurality of entities.

9. The method as recited in claim 8, wherein the causing display of representations indicating each of the plurality of entities comprises:

causing display of representations of entities connected by edges to more entities in a size larger than representations of entities connected by edges t fewer entities; and

causing display of the representation of the search term in a size larger than representations indicating each of the plurality of entities.

10. The method as recited in claim 8, wherein the edges from the representation of the search term to each of the representations of the plurality of entities comprise:

relationships of the search term to each of the plurality of entities.

11. The method as recited in claim 8, wherein each representation of an entity is displayed as a circle having a diameter size based at least in part on a number of relationships of that entity with other entities.

12. The method as recited in claim 8, wherein the user input comprises a cursor hovering over the edge between representations of two particular entities.

13. The method as recited in claim 8, wherein each representation of an entity is connected to the representation of the search term and to at least one other representation of an entity.

14. A system comprising:

one or more processors;

memory, in communication with the one or more processors;

a module, defined in the memory, executable by the one or more processors, and configured to;

obtain web documents based at least in part on a search term;

extract a plurality of entities and entity relationships from the web documents, each of the plurality of entities related to, but distinct from, the search term;

cause display of representations indicating each of the plurality of entities;

cause display of edges to define pairs of the displayed representations, the edges indicated by the entity relationships;

cause display of a representation of the search term and edges from the representation of the search term to each of the representations of the plurality of entities;

receive user input indicating an edge between representations of two particular entities; and

cause display of a description of a relationship between the two particular entities in response to the received user input.

15. The system as recited in claim 14, wherein the processor causes display of representations indicating each of the plurality of entities by:

causing display of representations of entities connected by edges to more entities in a size larger than representations of entities connected by edges to fewer entities; and

causing display of the representation of the search term in a size larger than representations indicating each of the plurality of entities.

16. The system as recited in claim 14, wherein the module is further configured to:

cluster relationship data obtained by extracting the entity relationships; and

group together the representations indicating each of the plurality of entities based at least in part on the clustering.

17. The system as recited in claim 14, wherein the edges from the representation of the search term to each of the representations of the plurality of entities comprise:

relationships of the search term to each of the plurality of entities.

18. The system as recited in claim 14, wherein each representation of an entity is displayed as a circle having a diameter size based at least in part on a number of relationships of that entity with other entities and

wherein each representation of an entity is connected to the representation of the search term and to at least one other representation of an entity.

19. The system as recited in claim 14, wherein the user input comprises a cursor hovering over the edge between representations of two particular entities.

20. The system as recited in claim 14, wherein each representation of an entity is connected to the representation of the search term and to at least one other representation of an entity.