Space and time for entity resolution

Patent metadata

Field	Value
Publication number	US-9230258-B2
Application number	US-75238610-A
Country	US
Kind code	B2
Filing date	Apr 1, 2010
Priority date	Apr 1, 2010
Publication date	Jan 5, 2016
Grant date	Jan 5, 2016

Abstract

Provided are techniques for receiving a record, wherein the received record has a space-time feature, selecting candidate entities using the space time feature, performing space time analysis to determine whether the received record should be conjoined with a candidate entity from the candidate entities, and, in response to determining that the received record should be conjoined with the candidate entity, making an entity resolution assertion by conjoining the received record and the candidate entity to form a newly conjoined entity.

First claim

The invention claimed is:

1. A method, comprising:
receiving, with a computer including a processor, a record, wherein the received record has a space-time feature indicating a first location of an entity and a first time at which the entity is at the first location; and
in response to a space-time analysis determining that the first location of the entity matches a second location of a candidate entity to a space precision based on a distance of the first location and the second location from a set of coordinates and that the first time at which the entity is at the first location matches a second time at which the candidate entity is at the second location to a time precision based on the first time and the second time being within a specified period of time,
determining that the entity and the candidate entity are a same entity;
determining that the received record should be conjoined with a candidate record for the candidate entity; and
making an entity resolution assertion by conjoining the received record and the candidate record to form a newly conjoined entity.

2. The method of claim 1 , further comprising:
selecting the candidate entity using the space-time feature and at least one additional feature of the received record.

3. The method of claim 1 , further comprising:
generating a new entity resolution assertion based on determining that the received record should be conjoined with a new candidate entity based on a feature other than the space-time feature;
overriding the new entity resolution assertion based on a disagreement between the space-time feature of the received record and at least one space-time feature of the new candidate entity; and
based on the disagreement, making an assertion that the entity and the new candidate entity are not the same entity.

4. The method of claim 1 , further comprising:
prior to making the entity resolution assertion by conjoining the received record and the candidate entity record to form a newly conjoined entity, determining that a different candidate entity and the candidate entity that are not the same entity; and
after making the entity resolution assertion by conjoining the received record and the candidate entity record to form a newly conjoined entity,
performing space-time analysis to identify the different candidate entity as a candidate for the newly conjoined entity; and
making an entity resolution assertion that the newly conjoined entity and the different candidate entity are the same entity based on the space-time feature of the received record.

5. The method of claim 1 , further comprising:
performing the space-time analysis to determine whether any previously resolved records in the newly conjoined entity no longer belong to that newly conjoined entity based on a space-time feature for the newly conjoined entity; and
separating a previously resolved record that no longer belongs in the newly conjoined entity.

6. The method of claim 1 , wherein the candidate entity is at least one of a person, thing or place.

7. The method of claim 1 , wherein the space feature includes the distance precision, and wherein the space-time analysis compares the first location and the second location while taking the distance precision into account.

8. The method of claim 1 , wherein the time feature includes the time precision, and wherein the space-time analysis compares the first time and the second time while taking the time precision into account.

9. A system, comprising:
a processor; and
a storage device coupled to the processor, wherein the storage device stores a computer readable program, and wherein the processor is configured to execute the computer readable program to perform operations, the operations comprising:
receiving a record, wherein the received record has a space-time feature indicating a first location of an entity and a first time at which the entity is at the first location; and
in response to a space-time analysis determining that the first location of the entity matches a second location of a candidate entity to a space precision based on a distance of the first location and the second location from a set of coordinates and the first time at which the entity is at the first location matches a second time at which the candidate entity is at the second location to a time precision based on the first time and the second time being within a specified period of time,
determining that the entity and the candidate entity are a same entity;
determining that the received record should be conjoined with a candidate record for the candidate entity; and
making an entity resolution assertion by conjoining the received record and the candidate record to form a newly conjoined entity.

10. The system of claim 9 , wherein the operations further comprise:
selecting the candidate entity using the space-time feature and at least one additional feature of the received record.

11. The system of claim 9 , wherein the operations further comprise:
generating a new entity resolution assertion based on determining that the received record should be conjoined with a new candidate entity based on a feature other than the space-time feature;
overriding the new entity resolution assertion based on a disagreement between the space-time feature of the received record and at least one space-time feature of the new candidate entity; and
based on the disagreement, making an assertion that the entity and the new candidate entity are not the same entity.

12. The system of claim 9 , wherein the operations further comprise:
prior to making the entity resolution assertion by conjoining the received record and the candidate entity record to form a newly conjoined entity, determining that a different candidate entity and the candidate entity that are not the same entity; and
after making the entity resolution assertion by conjoining the received record and the candidate entity record to form a newly conjoined entity,
performing space-time analysis to identify the different candidate entity as a candidate for the newly conjoined entity; and
making an entity resolution assertion that the newly conjoined entity and the different candidate entity are the same entity based on the space-time feature of the received record.

13. The system of claim 9 , wherein the operations further comprise:
performing the space-time analysis to determine whether any previously resolved records in the newly conjoined entity no longer belong to that newly conjoined entity based on a space-time feature for the newly conjoined entity; and
separating a previously resolved record that no longer belongs in the newly conjoined entity.

14. The system of claim 9 , wherein the candidate entity is at least one of a person, thing or place.

15. The system of claim 9 , wherein the space feature includes the distance precision, and wherein the space-time analysis compares the first location and the second location while taking the distance precision into account.

16. The system of claim 9 , wherein the time feature includes the time precision, and wherein the space-time analysis compares the first time and the second time while taking the time precision into account.

17. A computer program product comprising a computer readable storage medium including a computer readable program, wherein the computer readable program when executed by a processor on a computer causes the computer to:
receive a record, wherein the received record has a space-time feature indicating a first location of an entity and a first time at which the entity is at th

Assignees

• Adair Gregery Gene
• Jonas Jeffrey James
• IBM

Inventors

• Adair Gregery Gene
• Jonas Jeffrey James

Classifications

• H04W4/02

  Services making use of location information · CPC title

• G06F17/3015

  Physics · mapped topic

• G06F17/30241

  Physics · mapped topic

• G06Q30/02 Primary

  Marketing; Price estimation or determination; Fundraising · CPC title

• G06F16/29

  Geographical information databases · CPC title