Focused probabilistic entity resolution from multiple data sources
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.
1. A computer-implemented method, comprising:
retrieving a plurality of data objects;
creating an aggregated data object for a first entity, wherein creating the aggregated data object for the first entity comprises:
determining a confidence value for an association between one or more first data objects of the plurality of data objects and the first entity based at least in part upon one or more attribute types and attribute values associated with the one or more first data objects; and
generating metadata associating the one or more first data objects with the first entity based at least in part on the confidence value, wherein the metadata is stored separately from the one or more first data objects;
causing presentation, in a user interface, of a plurality of entities comprising the first entity and a second entity;
receiving, via the user interface, a user selection to combine the first entity and the second entity; and
in response to receiving the user selection, creating an updated data object for the first entity and the second entity, wherein creating the updated data object for the first entity and the second entity comprises:
identifying one or more second data objects associated with the second entity; and
generating updated metadata associating the one or more first data objects and the one or more second data objects, wherein the updated metadata is stored separately from the one or more first data objects and the one or more second data objects, and wherein the one or more first data objects and the one or more second data objects are configured to be used by one or more additional applications.
2. The computer-implemented method of claim 1 , wherein determining the confidence value further comprises:
determining that an attribute type has corresponding attribute values associated with at least two data objects from the one or more first data objects.
3. The computer-implemented method of claim 2 , wherein the attribute type comprises at least one of a location attribute type or a time attribute type.
4. The computer-implemented method of claim 2 , wherein the attribute type is associated with a weight, and wherein determining the confidence value further comprises incorporating the weight into the confidence value.
5. The computer-implemented method of claim 1 , wherein determining the confidence value further comprises:
determining that an attribute type has a first attribute value associated with a first data object of the one or more first data objects and a second attribute value associated with a second data object of the one or more first data objects; and
determining that the first attribute value and the second attribute value are different.
6. The computer-implemented method of claim 1 , wherein generating the metadata based at least in part on the confidence value further comprises:
determining that the confidence value satisfies a threshold confidence level.
7. The computer-implemented method of claim 1 , wherein creating the aggregated data object for the first entity further comprises:
creating a first attribute value copy from a first attribute value associated with a first data object of the one or more first data objects;
creating a second attribute value copy from a second attribute value associated with a second data object of the one or more first data objects; and
storing the first attribute value copy and the second attribute value copy in the aggregated data object.
8. The computer-implemented method of claim 1 , further comprising:
generating a score for the aggregated data object using a scoring model.
9. The computer-implemented method of claim 8 , wherein generating the score for the aggregated data object using the scoring model further comprises:
extracting one or more attributes from the aggregated data object; and
applying a machine learning model to the one or more attributes to output the score.
10. The computer-implemented method of claim 8 , wherein generating the score for the aggregated data object further comprises:
identifying an event object associated with the first entity, the one or more first data objects comprising the event object;
determining that the event object corresponds to a particular type of event; and
in response to determining that the event object corresponds to the particular type of event, updating the score.
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:
receive a plurality of data objects;
create an aggregated data object for a first entity, wherein creating the aggregated data object for the first entity comprises:
determining a confidence value for an association between one or more first data objects of the plurality of data objects and the first entity based at least in part upon one or more attribute types and attribute values associated with the one or more first data objects; and
generating metadata associating the one or more first data objects with the first entity based at least in part on the confidence value, wherein the metadata is stored separately from the one or more first data objects;
cause presentation, in a user interface, of a plurality of entities comprising the first entity and a second entity;
receive, via the user interface, a user selection to combine the first entity and the second entity; and
in response to receiving the user selection, create an updated data object for the first entity and the second entity, wherein creating the updated data object for the first entity and the second entity comprises:
identifying one or more second data objects associated with the second entity; and
generating updated metadata associating the one or more first data objects and the one or more second data objects, wherein the updated metadata is stored separately from the one or more first data objects and the one or more second data objects, and wherein the one or more first data objects and the one or more second data objects are configured to be used by one or more additional applications.
12. The computer system of claim 11 , wherein determining the confidence value further comprises:
determining that an attribute type has corresponding attribute values associated with at least two data objects from the one or more first data objects.
13. The computer system of claim 12 , wherein the attribute type comprises at least one of a location attribute type or a time attribute type.
14. The computer system of claim 12 , wherein the attribute type is associated with a weight, and wherein determining the confidence value further comprises:
incorporating the weight into the confidence value.
15. The computer system of claim 11 , wherein determining the confidence value further comprises:
determining that an attribute type has a first attribute value associated with a first data object of the one or more first data objects and a second attribute value associated with a second data object of the one or more first data objects; and
determining that the first attribute value and the second attribute value are different.
16. The computer system of claim 11 , wherein generating the metadata based at least in part on the confidence value further comprises:
determining that the confidence value satisfies a threshold confidence level.
17. The computer system of claim 11 , wherein creating the aggregated data object for the first entity further comprises:
creating a first attribute value copy from a first attribute value associated with a first data object of the one or more first data objects;
creating a second attribute value copy from a second attribute value associated with a second data object of the one or more first data objects; and
storing the first attribute value copy and the second attribute value copy in the aggregated data object.
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:
generate a score for the aggregated data object using a scoring model.
19. The computer system of claim 18 , wherein generating the score for the aggregated data object using the scoring model further comprises:
extracting one or more attributes from the aggregated data object; and
applying a machine learning model to the one or more attributes that outputs the score.
20. The computer system of claim 18 , wherein generating the score for the aggregated data object further comprises:
identifying an event object associated with the first entity, the one or more first data objects comprising the event object;
determining that the event object corresponds to a particular type of event; and
updating the score based at least in part on the event object corresponding to the particular type of event.