Life arcs as an entity resolution feature

• US 8,423,525 B2
• Filed: 03/30/2010
• Issued: 04/16/2013
• Est. Priority Date: 03/30/2010
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Jonas, Jeffrey James
• Primary Examiner(s): Ruiz, Angelica
• Application Number:
  US12/750,289
• Publication Number:
  US 20110246492A1
• Time in Patent Office: 1,113 Days
• Field of Search: None
• US Class Current: 707/705
• CPC Class Codes: G06F 16/10 File systems; File servers
• CPC Class Codes: G06F 16/284 Relational databases
• CPC Class Codes: G06F 17/00 Digital computing or data processing equipment or methods, specially adapted for specific functions information retrieval, database structures or file system structures therefor G06F16/00
• CPC Class Codes: G06Q 10/10 Office automation; Time management

Abstract

Techniques are disclosed for performing identity resolution using life arcs as a feature. Space and time data may be received for an entity. A life arc template may be provided that specifies data that a life arc for each entity should include. A life arc may be generated for the entity based on the space and time data and the life arc template. An assertion for identity resolution may be made for the entity, based on the generated life arc.

Claims

1. A computer-implemented method to provide a restricted set of candidate entities for entity resolution, based on a life arc, the method comprising:

resolving a received data record into an existing entity, resulting in a conjoined entity representing a subject selected from a person, a vehicle, and an object;

generating a life arc for the conjoined entity based on a life arc criterion and space and time data contained in the received data record, wherein the life arc represents that the subject was at each of a specified plurality of distinct geographical locations during a respective, specified time period that is distinct;

generating a restricted set of candidate entities from a plurality of available entities greater in number than the restricted set of candidate entities and by operation of one or more computer processors, wherein each of the plurality of available entities represents a distinct subject in the entity resolution system, wherein the restricted set of candidate entities includes;

(i) a first candidate entity selected based on the first candidate entity having a life arc matching the life arc generated for the conjoined entity and (ii) a second candidate entity selected based on a matching attribute that is not a life arc; and

determining whether the first candidate entity refers to the conjoined entity based on a comparison of at least one attribute of the first candidate entity and the conjoined entity, wherein the at least one attribute compared between the first candidate entity and the conjoined entity is not a life arc, wherein at least one of the first candidate entity and the conjoined entity are output responsive to a request from a requesting entity.

2. The computer-implemented method of claim 1, further comprising:

upon determining that the candidate entity refers to the conjoined entity, resolving the candidate entity into the conjoined entity.

3. The computer-implemented method of claim 2, further comprising:

upon determining that the candidate entity does not refer to the conjoined entity, not conjoining the candidate entity into the conjoined entity.

4. The computer-implemented method of claim 3, wherein the space and time data is selected from at least one of an address history, a credit history, and geolocational movement data, wherein the geolocational movement data comprises a latitude, a longitude, and a time stamp.

5. The computer-implemented method of claim 4, wherein the definition for the life arc includes at least one temporal constraint, and wherein each life arc is further generated based on a life arc template specifying a life arc criterion for the respective life arc.

6. The computer-implemented method of claim 5, wherein the life arc characterizes the space and time data obtained for the conjoined entity, wherein the at least one candidate entity shares at least one attribute with the conjoined entity, and wherein the at least one attribute comprises the life arc.

7. A computer-readable storage medium containing a program which, when executed, performs an operation to provide a restricted set of candidate entities for entity resolution, based on a life arc, the operation comprising:

resolving a received data record into an existing entity, resulting in a conjoined entity representing a subject selected from a person, a vehicle, and an object;

generating a life arc for the conjoined entity based on a life arc criterion and space and time data contained in the received data record, wherein the life arc represents that the subject was at each of a specified plurality of distinct geographical locations during a respective, specified time period that is distinct;

generating a restricted set of candidate entities from a plurality of available entities greater in number than the restricted set of candidate entities and by operation of one or more computer processors when executing the program, wherein each of the plurality of available entities represents a distinct subject in the entity resolution system, wherein the restricted set of candidate entities includes;

(i) a first candidate entity selected based on the first candidate entity having a life arc matching the life arc generated for the conjoined entity and (ii) a second candidate entity selected based on a matching attribute that is not a life arc; and

determining whether the first candidate entity refers to the conjoined entity based on a comparison of at least one attribute of the first candidate entity and the conjoined entity, wherein the at least one attribute compared between the first candidate entity and the conjoined entity is not a life arc, wherein at least one of the first candidate entity and the conjoined entity are output responsive to a request from a requesting entity.

8. The computer-readable storage medium of claim 7, wherein the operation further comprises:

upon determining that the candidate entity refers to the conjoined entity, resolving the candidate entity into the conjoined entity.

9. The computer-readable storage medium of claim 8, wherein the operation further comprises:

upon determining that the candidate entity does not refer to the conjoined entity, not conjoining the candidate entity into the conjoined entity.

10. The computer-readable storage medium of claim 9, wherein the space and time data is selected from at least one of an address history, a credit history, and geolocational movement data, wherein the geolocational movement data comprises a latitude, a longitude, and a time stamp.

11. The computer-readable storage medium of claim 10, wherein the definition for the life arc includes at least one temporal constraint, and wherein each life arc is further generated based on a life arc template specifying a life arc criterion for the respective life arc.

12. The computer-readable storage medium of claim 11, wherein the life arc characterizes the space and time data obtained for the conjoined entity, wherein the at least one candidate entity shares at least one attribute with the conjoined entity, and wherein the at least one attribute comprises the life arc.

13. A system to provide a restricted set of candidate entities for entity resolution, based on a life arc, the system comprising:

one or more computer processors;

a memory containing a program which, when executed by the one or more computer processors, is configured to perform an operation comprising;

resolving a received data record into an existing entity, resulting in a conjoined entity representing a subject selected from a person, a vehicle, and an object;

generating a life arc for the conjoined entity based on a life arc criterion and space and time data contained in the received data record, wherein the life arc represents that the subject was at each of a specified plurality of distinct geographical locations during a respective, specified time period that is distinct;

generating a restricted set of candidate entities from a plurality of available entities greater in number than the restricted set of candidate entities, wherein each of the plurality of available entities represents a distinct subject in the entity resolution system, wherein the restricted set of candidate entities includes;

(i) a first candidate entity selected based on the first candidate entity having a life arc matching the life arc generated for the conjoined entity and (ii) a second candidate entity selected based on a matching attribute that is not a life arc; and

determining whether the first candidate entity refers to the conjoined entity based on a comparison of at least one attribute of the first candidate entity and the conjoined entity, wherein the at least one attribute compared between the first candidate entity and the conjoined entity is not a life arc, wherein at least one of the first candidate entity and the conjoined entity are output responsive to a request from a requesting entity.

14. The system of claim 13, wherein the operation further comprises:

upon determining that the candidate entity refers to the conjoined entity, resolving the candidate entity into the conjoined entity.

15. The system of claim 14, wherein the operation further comprises:

upon determining that the candidate entity does not refer to the conjoined entity, not conjoining the candidate entity into the conjoined entity.

16. The system of claim 15, wherein the space and time data is selected from at least one of an address history, a credit history, and geolocational movement data, wherein the geolocational movement data comprises a latitude, a longitude, and a time stamp.

17. The system of claim 16, wherein the definition for the life arc includes at least one temporal constraint, and wherein each life arc is further generated based on a life arc template specifying a life arc criterion for the respective life arc.

18. The system of claim 17, wherein the life arc characterizes the space and time data obtained for the conjoined entity, wherein the at least one candidate entity shares at least one attribute with the conjoined entity, and wherein the at least one attribute comprises the life arc.

19. The system of claim 18, wherein the identity record is matched against each candidate entity in the restricted set of candidate entities and not matched against at least one available entity not in the restricted set of candidate entities, to avoid incurring processing costs associated with matching against the at least one available entity;

wherein each distinct geographical location pertains to the physical world and is associated with a distinct time period characterizing the conjoined entity, wherein each distinct geographical location represents that the conjoined entity is at the respective distinct geographical location during the associated distinct time period, wherein the life arc of the first candidate entity matching the life arc of the conjoined entity includes matching geographical locations and matching time periods.

20. The system of claim 19, wherein the first candidate entity is determined to refer to the conjoined entity based on satisfying a predefined similarity score computed based on matching attributes between the first candidate entity and the conjoined entity, wherein the matching life arc has a higher contribution to the similarity score than the matching attribute that is not a life arc;

wherein the life arc is disqualified from being used in generating candidate entities for the received data record and one or more subsequently received data records, upon determining that the life arc has generated a count of candidate entities exceeding a predefined disqualification threshold.