Focused probabilistic entity resolution from multiple data sources

• US 10,437,840 B1
• Filed: 08/19/2016
• Issued: 10/08/2019
• Est. Priority Date: 08/19/2016
• Status: Active Grant

• Current Assignee: Palantir Technologies Incorporated
• Original Assignee: Palantir Technologies Incorporated
• Inventors: Poh, Andrew, Prasad, Anshuman, Ding, James, Holgate, John, Sen, Ranajay, Zheng, Shuo
• Primary Examiner(s): Moser, Bruce M
• Application Number:
  US15/242,335
• Time in Patent Office: 1,145 Days
• CPC Class Codes: G06F 16/2455 Query execution
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/2477 Temporal data queries
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence

Abstract

Various systems and methods are provided for performing soft entity resolution. A plurality of data objects are retrieved from a plurality of data stores to create aggregated data objects for one or more entities. One or more retrieved data objects may be associated with the same entity, based at least in part upon one or more attribute types and attribute values of the data objects. In response to a determination that the one or more of the retrieved data objects should be associated with the same entity, metadata is generated that associates the data objects with the entity, the metadata being stored separately from the data objects, such that the underlying data objects remain unchanged. In addition, one or more additional attributes may be determined for the entity, based upon the data objects associated with the entity.

Claims

1. A computer system, comprising:

one or more computer readable storage mediums configured to store computer executable instructions; and

one or more computer processors in communication with the one or more computer readable storage mediums and configured to execute the computer executable instructions in order to cause the computer system to;

retrieve a plurality of data objects from a plurality of data stores, the data stores comprising at least a first data store containing data objects corresponding to entities, and a second data store containing data objects corresponding to events; and

create aggregated data objects for one or more entities, wherein creating an aggregated data object for an entity comprises;

determining a confidence value for an association between one or more of the retrieved data objects the entity based at least in part upon one or more attribute types and attribute values associated with the one or more data objects;

generating metadata associating the one or more data objects with the entity based at least in part on the confidence value, wherein the metadata is stored separately from the one or more data objects, such that the one or more data objects are unchanged; and

determining one or more additional attributes for the entity, based upon the data objects associated with the entity.

2. The computer system of claim 1, wherein the one or more computer processors are further configured to:

identify at least a portion of the attributes associated with the one or more entities as scoring factors;

generate one or more scores for the one or more entities, based at least in part upon one or more values for the scoring factors for the entities determined using the data objects and additional attributes associated with the entities; and

generate user interface information for displaying at least a portion of the entities, based at least in part upon the generated scores for the entities.

3. The computer system of claim 2, wherein generating scores for the one or more entities comprises, for an entity of the one or more entities:

processing the one or more scoring factors associated with the entity using a scoring model; and

generating a score for the entity using the scoring model.

4. The computer system of claim 3, wherein the scoring model comprises one or more weights associated with the one or more scoring factors.

5. The computer system of claim 2, wherein the user interface information for displaying at least a portion of the entities is further based at least in part upon one or more user attributes.

6. The computer system of claim 5, wherein the one or more user attributes comprises a user location.

7. The computer system of claim 1, wherein the one or more additional attributes comprises a history attribute generated based at least in part upon one or more event data objects associated with the entity.

8. The computer system of claim 1, wherein the data objects are associated with the entity if the confidence value exceeds a threshold confidence.

9. The computer system of claim 1, wherein the one or more computer processors are further configured to:

receive an indication of an event;

associate the event with one or more scoring factors;

in substantially real-time, update the one or more scoring factors based at least in part upon the event;

re-generate scores for at least some of the one or more entities, based upon the updated scoring factors; and

generate user interface information for displaying at least a portion of the entities, based at least in part upon the re-generated scores.

10. The computer system of claim 9, wherein the one or more scoring factors are updated based upon a relationship between an entity attribute and an attribute value associated with the event.

11. The computer system of claim 9, wherein the user interface information further comprises information for displaying a basis for a change in a score of a displayed entity, based upon the updated scoring factors.

12. A computer-implemented method for performing probabilistic entity resolution, comprising:

retrieving a plurality of data objects from a plurality of data stores, the data stores comprising at least a first data store containing data objects corresponding to entities, and a second data store containing data objects corresponding to events; and

creating aggregated data objects for one or more entities, wherein creating an aggregated data object for an entity comprises;

determining a confidence value for an association between one or more of the retrieved data objects and the entity based at least in part upon one or more attribute types and attribute values associated with the one or more data objects;

generating metadata associating the one or more data objects with the entity based at least in part on the confidence value, wherein the metadata is stored separately from the one or more data objects, such that the one or more data objects are unchanged; and

determining one or more additional attributes for the entity, based upon the data objects associated with the entity.

13. The computer-implemented method of claim 12, further comprising:

identifying at least a portion of the attributes associated with the one or more entities as scoring factors;

generating one or more scores for the one or more entities, based at least in part upon one or more values for the scoring factors for the entities determined using the data objects and additional attributes associated with the entities; and

generating user interface information for displaying at least a portion of the entities, based at least in part upon the generated scores for the entities.

14. The computer-implemented method of claim 13, wherein generating scores for the one or more entities comprises, for an entity of the one or more entities:

processing the one or more scoring factors associated with the entity using a scoring model; and

generating a score for the entity using the scoring model.

15. The computer-implemented method of claim 13, wherein the user interface information for displaying at least a portion of the entities is further based at least in part upon one or more user attributes.

16. The computer-implemented method of claim 12, wherein the one or more additional attributes comprises a history attribute generated based at least in part upon one or more event data objects associated with the entity.

17. The computer-implemented method of claim 12, wherein the data objects are associated with the entity if the confidence value exceeds a threshold confidence.

18. The computer-implemented method of claim 12, further comprising:

receiving an indication of an event;

associating the event with one or more scoring factors;

in substantially real-time, updating the one or more scoring factors based at least in part upon the event;

re-generating scores for at least some of the one or more entities, based upon the updated scoring factors; and

generating user interface information for displaying at least a portion of the entities, based at least in part upon the re-generated scores.

19. The computer-implemented method of claim 18, wherein the one or more scoring factors are updated based upon a relationship between an entity attribute and an attribute value associated with the event.

20. The computer-implemented method of claim 18, wherein the user interface information further comprises information for displaying a basis for a change in a score of a displayed entity, based upon the updated scoring factors.