Defining attribute feature vectors for matching data entities
AssigneeInternational Business Machines Corporation
InventorsAbhishek Seth, Soma Shekar Naganna, James Albert O'Neill, Jr., Lars Bremer, Mariya Chkalova
Life of this patent
Estimating the term…
Abstract
Matching records in an entity resolution system by defining entity attribute feature vectors, determining an entity attribute matching score according to a distance between two entity attribute feature vectors, assigning a statistical weight to an entity attribute matching score, adjusting the entity attribute matching score according to the statistical weight and an entity attribute frequency of occurrence, and determining an aggregate entity attribute matching score.
Claims20
A computer implemented method for matching records in an entity resolution system, the method comprising:
- defining, by one or more computer processors, entity attribute feature vectors;
- determining, by the one or more computer processors, an entity attribute matching score according to a distance between two of the entity attribute feature vectors;
- assigning, by the one or more computer processors, a statistical weight to the entity attribute matching score;
- adjusting, by the one or more computer processors, the entity attribute matching score according to the statistical weight and an entity attribute frequency of occurrence;
- and
- determining, by the one or more computer processors, an aggregate entity attribute matching score based, at least in part, on the entity attribute matching score and at least one additional entity attribute matching score.
A computer program product for matching records in an entity resolution system, the computer program product comprising one or more computer readable storage devices and stored program instructions on the one or more computer readable storage devices, the stored program instructions comprising:
- program instructions to define, by one or more computer processors, entity attribute feature vectors;
- program instructions to determine an entity attribute matching score according to a distance between two entity attribute feature vectors;
- program instructions to assign a statistical weight to an entity attribute matching score;
- program instructions to adjust the entity attribute matching score according to the statistical weight and an entity attribute frequency of occurrence;
- and
- program instructions to determine an aggregate entity attribute matching score.
A computer system for matching records in an entity resolution system, the computer system comprising:
- one or more computer processors;
- one or more computer readable storage devices;
- and
- stored program instructions on the one or more computer readable storage devices for execution by the one or more computer processors, the stored program instructions comprising:
- program instructions to define, by one or more computer processors, entity attribute feature vectors;
- program instructions to determine an entity attribute matching score according to a distance between two entity attribute feature vectors;
- program instructions to assign a statistical weight to an entity feature matching score;
- program instructions to adjust the entity attribute matching score according to the statistical weight and an entity attribute frequency of occurrence;
- and
- program instructions to determine an aggregate entity attribute matching score.
Dependencies are inferred from the claim text.