IP Library Granted Patent US 9,965,812
Granted Patent B2
US 9,965,812 · App. 15/159,516 · Granted May 8, 2018

Generating a supplemental description of an entity

Inventors: Anmol Bhasin (Los Altos, CA); Jiong Wang (San Ramon, CA); Abhishek Gupta (San Francisco, CA); Alexis Pribula (Menlo Park, CA); Ramesh Dommeti (San Jose, CA); Christian Posse (Forster City, CA)
Assignee: Microsoft Technology Licensing, LLC
G06Q50/01G06F17/3053G06F17/30554G06F17/30702G06F17/30867G06Q10/10G06Q10/1053H04L67/30H04L67/306
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 9,965,812
App. No.
15/159,516
Granted
May 8, 2018
Kind
B2
Abstract

A statistically overrepresented token in the descriptions of users associated with a target entity may be descriptive of the target entity. This may be true regardless of whether a primary description of the entity includes the overrepresented token. Accordingly, the entity description machine may access multiple descriptions of multiple users associated with the target entity. A portion of the multiple descriptions may each include a token descriptive of the target entity and of a subset of the multiple users. The entity description machine may determine that the token is overrepresented among the tokens within the multiple descriptions and generate a supplemental description of the target entity, where the supplemental description includes the overrepresented token. Once the supplemental description is generated, the entity description machine may use the supplemental description in referencing the target entity.

Claims (63)

1. A method comprising:

by an access module that comprises one or more processors of a machine, accessing textual submissions contributed by members of a social network managed by a social network system, each of the textual submissions referencing a common entity described by an entity profile stored by the social network system, a subset of the accessed textual submissions each including a common token that is absent from the entity profile;

by a determination module that comprises one or more processors of the machine:

generating a first probability that the common token occurs within the accessed textual submissions;

accessing a second probability that the common token occurs within a superset of textual submissions that includes the accessed textual submissions; and

determining that the common token is descriptive of the common entity based on a statistical divergence between the first and second probabilities, the statistical divergence indicating that the common token is overrepresented among other tokens common to the accessed textual submissions; and

by a generation module that comprises one or more processors of the machine;

generating a supplemental profile that describes the common entity and includes the overrepresented common token.

2. The method of claim 1 , wherein:

the entity profile indicates that the common entity is a business; and

the accessed textual submissions are contributed by employees of the business.

3. The method of claim 1 , wherein:

the entity profile indicates that the common entity is a first member of the social network; and

the accessed textual submissions are contributed by second members of the social network, the social network indicating that the second members are connected to the first member.

4. The method of claim 1 , wherein:

the entity profile indicates that the common entity is a group of members of the social network; and

the accessed textual submissions are contributed by members that are included in the group of members of the social network.

5. The method of claim 1 , wherein:

the entity profile indicates that the common entity is an event scheduled in a calendar database that indicates attendees of the event; and

the accessed textual submissions are contributed by members that are attendees of the event.

6. The method of claim 1 , wherein:

the entity profile indicates that the common entity is an available job at a business; and

the accessed textual submissions are contributed by members that are applicants to the available job at the business.

7. The method of claim 1 , wherein:

the entity profile indicates that the entity is a news article having viewers; and

the accessed textual submissions are contributed by members that are viewers of the news article.

8. The method of claim 1 , wherein:

the entity profile indicates that the entity is a discussion in an online forum having participants; and

the accessed textual submissions are contributed by members that are participants in the discussion in the online form.

9. The method of claim 1 , further comprising:

displaying a search result that references the common entity, the displaying of the search result being based on the generated supplemental profile that describes the common entity and includes the overrepresented common token.

10. The method of claim 1 , further comprising:

ranking a search result that references the common entity, the ranking of the search result being based on the generated supplemental profile that describes the common entity and includes the overrepresented common token.

11. The method of claim 1 , further comprising:

providing a recommendation that recommends the common entity the providing of the recommendation being based on the generated supplemental description that describes the common entity and includes the overrepresented common token.

12. The method of claim 1 , further comprising:

providing a suggestion that the entity profile be modified based on the overrepresented common token determined to be descriptive of the common entity.

13. The method of claim 12 , wherein:

the providing of the suggestion includes communicating the suggestion to an author of the entity profile.

14. A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:

accessing textual submissions contributed by members of a social network managed by a social network system, each of the textual submissions referencing a common entity described by an entity profile stored by the social network system; a subset of the accessed textual submissions each including a common token that is absent from the entity profile;

generating a first probability that the common token occurs within the accessed textual submissions;

accessing a second probability that the common token occurs within a superset of textual submissions that includes the accessed textual submissions;

determining that the common token is descriptive of the common entity based on a statistical divergence between the first and second probabilities, the statistical divergence indicating that the common token is overrepresented among other tokens common to the accessed textual submissions; and

generating a supplemental profile that describes the common entity and includes the overrepresented common token.

15. The non-transitory machine-readable storage medium of claim 14 , wherein the operations further comprise:

displaying a search result that references the common entity, the displaying of the search result being based on the generated supplemental profile that describes the common entity and includes the overrepresented common token.

16. The non-transitory machine-readable storage medium of claim 14 , wherein the operations further comprise:

ranking a search result that references the common entity, the ranking of the search result being based on the generated supplemental profile that describes the common entity and includes the overrepresented common token.

17. A system comprising:

one or more processors; and

a memory storing instructions that, when executed by at least one processor among the one or more processors, cause the system to perform operations comprising:

accessing textual submissions contributed by members of a social network managed by a social network system, each of the textual submissions referencing a common entity described by an entity profile stored by the social network system, a subset of the accessed textual submissions each including a common token that is absent from the entity profile;

generating a first probability that the common token occurs within the accessed textual submissions;

accessing a second probability that the common token occurs within a superset of textual submissions that includes the accessed textual submissions;

determining that the common token is descriptive of the common entity based on a statistical divergence between the first and second probabilities, the statistical divergence indicating that the common token is overrepresented among other tokens common to the accessed textual submissions; and

generating a supplemental profile that describes the common entity and includes the overrepresented common token.

18. The system of claim 17 , wherein the operations further comprise:

providing a recommendation that recommends the common entity, the providing of the recommendation being based on the generated supplemental description that describes the common entity and includes the overrepresented common token.

19. The system of claim 17 , wherein the operations further comprise:

providing a suggestion that the entity profile be modified based on the overrepresented common token determined to be descriptive of the common entity.

20. The system of claim 17 , wherein:

the providing of the suggestion includes communicating the suggestion to an author of the entity profile.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 1, 2017
From: LINKEDIN CORPORATION
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 044746/0001 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 25, 2016
From: BHASIN, ANMOL; WANG, JIONG; GUPTA, ABHISHEK; PRIBULA, ALEXIS; DOMMETI, RAMESH; POSSE, CHRISTIAN
To: LINKEDIN CORPORATION
Reel/Frame 038719/0016 →
Continuity (4)
Continuation 14496914 · Sep 25, 2014
Continuation 13428412 · Mar 23, 2012
Provisional Application 61577628 · Dec 19, 2011
Related Publication 20160343088A1 · Nov 24, 2016