Focused probabilistic entity resolution from multiple data sources

Patent metadata

Field	Value
Publication number	US-12229154-B2
Application number	US-202318330746-A
Country	US
Kind code	B2
Filing date	Jun 7, 2023
Priority date	Aug 19, 2016
Publication date	Feb 18, 2025
Grant date	Feb 18, 2025

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.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
creating an aggregated data object for an entity, wherein creating the aggregated data object for the entity comprises:
determining a confidence value for an association between one or more of a plurality of data objects and the entity based at least in part upon one or more attribute values associated with the one or more data objects; and
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; and

in response to receiving one or more events:
calculating a score for the aggregated data object; and
providing an alert associated with the score.

2. The computer-implemented method of claim 1 , wherein calculating the score for the aggregated data object further comprises:
applying a scoring model to the aggregated data object, wherein applying the scoring model further comprises:
extracting a plurality of scoring factors associated with the aggregated data object; and
combining the plurality of scoring factors and a plurality of weights, wherein combining the plurality of scoring factors and the plurality of weights results in the score.

3. The computer-implemented method of claim 2 , further comprising:
receiving training data comprising a plurality of entities and a plurality of events; and
training the scoring model with the training data.

4. The computer-implemented method of claim 1 , wherein calculating the score for the aggregated data object further comprises:
determining that an event corresponds to a certain type of event; and
in response to determining that the event corresponds to the certain type of event, increasing a value of the score to an updated score.

5. The computer-implemented method of claim 1 , wherein calculating the score for the aggregated data object further comprises:
determining that a plurality of events occurred within a period of time; and
in response to determining that a plurality of events occurred within the period of time, increasing a value of the score to an updated score.

6. The computer-implemented method of claim 1 , wherein calculating the score for the aggregated data object further comprises:
extracting a first attribute from the aggregated data object, wherein the first attribute indicates a first geographic location of the entity;
extracting a second attribute from an event, wherein the second attribute indicates a second geographic location of the event;
determining that the first geographic location is within a threshold distance of the second geographic location; and
in response to determining that the first geographic location is within the threshold distance of the second geographic location, increasing a value of the score to an updated score.

7. The computer-implemented method of claim 1 , further comprising:
causing presentation, in a user interface, of (i) a representation of the entity and (ii) the score.

8. The computer-implemented method of claim 7 , further comprising:
causing presentation, in the user interface, of (i) representations for a plurality of entities and (ii) a corresponding score for each entity of the plurality of entities.

9. The computer-implemented method of claim 8 , further comprising:
causing presentation, in the user interface, of a geographic location associated with each entity of the plurality of entities.

10. The computer-implemented method of claim 1 , wherein providing the alert further comprises:
transmitting the alert to a user computing device.

11. 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 to cause the computer system to:
create an aggregated data object for an entity, wherein creating the aggregated data object for the entity comprises:
determining a confidence value for an association between one or more of a plurality of data objects and the entity based at least in part upon one or more attribute values associated with the one or more data objects; and
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; and

in response to receive one or more events:
calculate a score for the aggregated data object; and
provide an alert associated with the score.

12. The computer system of claim 11 , wherein calculating the score for the aggregated data object further comprises:
applying a scoring model to the aggregated data object, wherein applying the scoring model further comprises:
extracting a plurality of scoring factors associated with the aggregated data object; and
combining the plurality of scoring factors and a plurality of weights, wherein combining the plurality of scoring factors and the plurality of weights results in the score.

13. The computer system of claim 12 , wherein the one or more computer processors are configured to execute the computer executable instructions to further cause the computer system to:
receive training data comprising a plurality of entities and a plurality of events; and
train the scoring model with the training data.

14. The computer system of claim 11 , wherein calculating the score for the aggregated data object further comprises:
determining that an event corresponds to a certain type of event; and
in response to determining that the event corresponds to the certain type of event, increasing a value of the score to an updated score.

15. The computer system of claim 11 , wherein calculating the score for the aggregated data object further comprises:
determining that a period of time has passed following an event; and
in response to determining that the period of time has passed following the event, decreasing a value of the score to an updated score.

16. The computer system of claim 15 , wherein decreasing the value of the score further comprises:
decreasing a weight associated with the event.

17. The computer system of claim 11 , wherein calculating the score for the aggregated data object further comprises:
extracting a first attribute from the aggregated data object, wherein the first attribute indicates a first geographic location of the entity;
extracting a second attribute from an event, wherein the second attribute indicates a second geographic location of the event;
determining that the first geographic location is within a threshold distance of the second geographic location; and
in response to determining that the first geographic location is within the threshold distance of the second geographic location, increasing a value of the score to an updated score.

18. The computer system of claim 11 , wherein the one or more computer processors are configured to execute the computer executable instructions to further cause the computer system to:
cause presentation, in a user interface, of (i) a representation of the entity and (ii) the score.

19. The computer system of claim 18 , wherein the one or more computer processors are configured to execute the computer executable instructions to further cause the computer system to:
cause presentation, in the user interface, of (i) representations for a plurality of entitie

Assignees

• Palantir Technologies Inc

Inventors

• Poh Andrew
• Prasad Anshuman
• Ding James
• Holgate John
• Sen Ranajay
• Zheng Shuo

Classifications

• G06F16/335

  Filtering based on additional data, e.g. user or group profiles (filtering in web context G06F16/9535, G06F16/9536) · CPC title

• G06F16/93

  Document management systems · CPC title

• G06F16/2455

  Query execution · CPC title

• G06F3/04842

  Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence) · CPC title

• G06F16/2477

  Temporal data queries · CPC title