ENTITY CLASSIFICATION AND/OR RELATIONSHIP IDENTIFICATION

• US 20160357870A1
• Filed: 06/05/2015
• Published: 12/08/2016
• Est. Priority Date: 06/05/2015
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Hentschel, Martin, Alonso, Omar
• Granted Patent: US 10,505,884 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/288 Entity relationship models
• CPC Class Codes: G06F 16/367 Ontology
• CPC Class Codes: G06F 16/9024 Graphs; Linked lists G06F16/9027 takes precedence
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 51/52 for supporting social networking services

Abstract

One or more techniques and/or systems are provided for identifying relationships between entities and/or for classifying entities into sectors. Social network commentary of users may be evaluated to select comments having co-occurrences of entity identifiers and/or co-occurrences of entity identifiers with sector identifiers. For example, a microblog message “I love these stores!! $CO(A) $CO(B) #ShoeShopping” may have a co-occurrence of entity identifiers $CO(A) of a Company (A) entity and $CO(B) of a Company (B) entity along with co-occurrence with a #ShoeShopping sector identifier of a Retail Clothing sector. A relationship between the Company (A) entity and the Company (B) entity may be specified based upon the co-occurrence of the entity identifiers. A sector classification of the Retail Clothing sector may be assigned to the Company (A) entity and to the Company (B) entity based upon the co-occurrence of the entity identifiers $CO(A) and $CO(B) with the #ShoeShopping sector identifier.

Claims

1. A method for providing enhanced computer search results with one or more computing devices while reducing consumption of processing resources, the method comprising:

obtaining, by the one or more computing devices, social network data comprising a first textual comment by a first user, the first textual comment comprising both a first entity identifier of a first entity and a second entity identifier of a second entity;

generating, at the one or more computing devices, a relationship metric indicative of a relationship between the first entity and the second entity based upon co-occurrence of the first entity identifier and the second entity identifier within the first textual comment;

receiving, at the one or more computing devices, a search query corresponding to the first entity; and

generating, by the one or more computing devices, search results responsive to the received search query, the generated search results comprising both the first entity and at least one of;

a related search suggestion suggesting the second entity or a supplemental search result providing information about the second entity;

wherein the generating the search results to comprise the at least one of the related search suggestion or the supplemental search result is performed due to the generated relationship metric.

2. The method of claim 1, wherein the first entity is a first company and the second entity is a second, different company.

3. The method of claim 1, wherein the generating the relationship metric comprises:

building a graph comprising a set of nodes connected by a set of edges, the set of nodes comprising a first node representing the first entity and a second node representing the second entity, the set of edges comprising an edge between the first node and the second node, the edge representing the relationship.

4. The method of claim 3, comprising:

displaying, on a display device communicationally coupled to a computing device receiving the search results, an interactive graph interface derived from the graph, wherein the interactive graph interface comprises a visual representation of

the edge that is visually indicative of a strength of the relationship between the first entity and the second entity as reflected by the generated relationship metric.

5. The method of claim 3, comprising:

displaying, on a display device communicationally coupled to a computing device receiving the search results, an interactive graph interface derived from the graph, wherein the interactive graph interface comprises a visual representation of

the edge, the first node, and the second node wherein a color of at least one of the edge, the first node, or the second node is based upon at least one of a first entity type of the first entity or a second entity type of the second entity.

6. The method of claim 3, comprising:

identifying one or more related entity clusters based upon the graph.

7. The method of claim 1, wherein the generating the search results to comprise:

the at least one of the related search suggestion or the supplemental search result is only performed if the generated relationship metric exceeds a threshold.

8. The method of claim 1, comprising:

obtaining updated social network data comprising a second textual comment by a second user that was generated after the obtaining of the social network data that comprised the first textual comment by the first user; and

updating the relationship metric based upon the updated social network data.

9. The method of claim 1, comprising:

filtering individual textual comments of the social network data based upon at least one of a spam score or a quality score assigned to the individual textual comments.

10. The method of claim 1, comprising:

generating a ranked list of entities having relationships with the first entity above a threshold, the ranked list of entities comprising an entity for the second entity, the entity comprising a link to a search for the second entity.

11. A method for providing enhanced computer search results with one or more computing devices while reducing consumption of processing resources, the method comprising:

obtaining, by the or more computing devices, social network data comprising a first textual comment by a first user, the first textual comment comprising both first entity identifier of first entity and a first sector identifier of a first sector;

generating, at the one or more computing devices, a sector classification of the entity as being part of the first sector based upon co-occurrence of the first entity identifier and the first sector identifier within the first textual comment;

receiving, at the one or more computing devices, a sector search query; and

generating, by the one or more computing devices, search results responsive to the received sector search query, the generated search results comprising a list of entities that also have sector classifications that classify those entities as also being part of the first sector, the list of entities comprising the first entity.

12. The method of claim 11, wherein the first entity is a company.

13. The method of claim 11, wherein the generating the sector classification comprises:

normalizing a set of textual comments, from the obtained social media data, that all have co-occurrences of the first entity identifier and the first sector identifier based upon an overall entity identifier count.

14. The method of claim 11, wherein the generating the search results comprises:

a sector identifier element for the first sector, the sector identifier element comprising a link to a search for the first sector.

15. The method of claim 11, wherein the first sector is a type of company.

16. The method of claim 11, comprising:

obtaining updated social network data comprising a second textual comment by a second user that was generated after the obtaining of the social network data that comprised the first textual comment by the first user; and

updating the sector classification based upon the updated social network data.

17. The method of claim 11, comprising:

generating a second sector classification of the first entity as also being part of a second sector, which differs from the first sector, based upon co-occurrence of the first entity identifier and a second sector identifier of the second sector within a second comment by a second user, the second comment also being part of the obtained social network data.

18. The method of claim 11, wherein the generating the sector classification comprises:

generating a knowledge graph based upon sector classifications that are assigned to entities using the obtained social network data.

19. A computing device providing enhanced search results while reducing consumption of processing resources, the computing device comprising:

one or more processing units; and

memory comprising instructions that when executed by the one or more processing units cause the computing device to;

obtain social network data comprising a first textual comment by a first user, the first textual comment comprising both a first entity identifier of a first entity and a second entity identifier of a second entity, the social network data further comprising a second textual comment by a second user, the second textual comment comprising both the first entity identifier of the first entity and a first sector identifier of a first sector;

generate a relationship metric indicative of a relationship between the first entity and the second entity based upon co-occurrence of the first entity identifier and the second entity identifier within the first textual comment;

generate a sector classification of the first entity as being part of the first sector based upon co-occurrence of the first entity identifier and the first sector identifier within the second comment.

20. The computing device of claim 19, wherein the memory comprises further instructions that when executed by the one or more processing units cause the computing device to perform at least one of:

update the generated relationship metric based upon updated social network data that comprises a third textual comment by a third user that was generated after the obtaining of the social network data that comprised the first textual comment by the first user and the second textual comment by the second user, or

update the sector classification based upon the updated social network data.