Using relationships in candidate discovery
AssigneeInternational Business Machines Corporation
InventorsGregery G. Adair, Jeffrey J. Jonas
Life of this patent
Estimating the term…
Abstract
Techniques are disclosed for adding entities to a group of entity resolution candidates by selecting entities that have a minimum threshold of similarity to a candidate, allowing a greater number of resolutions in an entity resolution system. To resolve an incoming identity record, an initial group of candidates may be selected from known entities by identifying entities that match a candidate building attribute of the incoming identity record. Additional candidates may be selected by identifying entities with some information that is similar to one of the candidate entities.
Claims21
A computer-implemented method of resolving entities in an entity resolution system storing identity records related to a plurality of entities, the method comprising:
- receiving a new identity record;
- identifying a set of candidate entities, from the plurality of entities, based upon a match between an attribute of the new identity record and corresponding attributes of one or more of the plurality of entities;
- for each entity in the set of candidate entities, determining a likeness score between a respective entity in the set of candidate entities and each entity in the plurality of entities not included in the set of candidate entities;
- adding, to the set of candidate entities, each entity in the plurality of entities not included in the set of candidate entities having a likeness score satisfying predefined criteria, relative to one of the entities in the set of candidate entities;
- and
- in response to determining that the new identity record refers to a candidate entity in the set of candidate entities, including any added entities, associating the new identity record with the candidate entity.
A computer program product comprising a computer useable medium having a computer readable program, wherein the computer readable program, when executed on a computer causes the computer to perform an operation for resolving entities in an entity resolution system storing identity records related to a plurality of entities, the operation comprising:
- receiving a new identity record;
- identifying a set of candidate entities, from the plurality of entities, based upon a match between an attribute of the new identity record and corresponding attributes of one or more of the plurality of entities;
- for each entity in the set of candidate entities, determining a likeness score between a respective entity in the set of candidate entities and each entity in the plurality of entities not included in the set of candidate entities;
- adding, to the set of candidate entities, each entity in the plurality of entities not included in the set of candidate entities having a likeness score satisfying predefined criteria, relative to one of the entities in the set of candidate entities;
- and
- in response to determining that the new identity record refers to a candidate entity in the set of candidate entities, including any added entities, associating the new identity record with the candidate entity.
A system, comprising:
- a processor;
- and
- a memory containing a program, which when executed by the processor, performs an operation for resolving entities in an entity resolution system storing identity records related to a plurality of entities by performing the steps of:
- receiving a new identity record;
- identifying a set of candidate entities, from the plurality of entities, based upon a match between an attribute of the new identity record and corresponding attributes of one or more of the plurality of entities;
- for each entity in the set of candidate entities, determining a likeness score between a respective entity in the set of candidate entities and each entity in the plurality of entities not included in the set of candidate entities;
- adding, to the set of candidate entities, each entity in the plurality of entities not included in the set of candidate entities having a likeness score satisfying predefined criteria, relative to one of the entities in the set of candidate entities;
- and
- in response to determining that the new identity record refers to a candidate entity in the set of candidate entities, including any added entities, associating the new identity record with the candidate entity.
Dependencies are inferred from the claim text.