System and method for genealogical entity resolution

A non-transitory computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

• extracting a first set of features from a first set of tree data and a second set of features from a second set of tree data, wherein the first set of tree data corresponds to a first tree person from a first genealogical tree and the second set of tree data corresponds to a second tree person from a second genealogical tree, and wherein each of the first genealogical tree and the second genealogical tree comprise a plurality of interconnected nodes representing relationships between tree persons;
• generating, utilizing a feature comparator to compare the first set of features and the second set of features:
• an individual-level similarity vector comprising paired individual-level features from paired tree persons, wherein the paired tree persons include:
• i) one or more of the first tree person or a first relative related to the first tree person and ii) one or more of the second tree person or a second relative related to the second tree person;
• and
• a family-level similarity score from features across familial relationships of the paired tree persons;
• generating, utilizing an individual-level machine learning model to analyze the individual-level similarity vector, an individual-level similarity score defining a similarity between the paired tree persons;
• determining, utilizing a family-level machine learning model based on the individual-level similarity score and the family-level similarity score, that the first tree person and the second tree person are duplicates of a single individual;
• and
• modifying a cluster database based on determining that the first tree person and the second tree person are duplicates of the single individual.

A system comprising:

• one or more processors;
• and
• a computer-readable medium comprising instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
• extracting a first set of features from a first set of tree data and a second set of features from a second set of tree data, wherein the first set of tree data corresponds to a first tree person from a first genealogical tree and the second set of tree data corresponds to a second tree person from a second genealogical tree, and wherein each of the first genealogical tree and the second genealogical tree comprise a plurality of interconnected nodes representing relationships between tree persons;
• generating, utilizing a feature comparator to compare the first set of features and the second set of features:
• an individual-level similarity vector comprising paired individual-level features from paired tree persons, wherein the paired tree persons include:
• i) one or more of the first tree person or a first relative related to the first tree person and ii) one or more of the second tree person or a second relative related to the second tree person;
• and
• a family-level similarity score from features across familial relationships of the paired tree persons;
• generating, utilizing an individual-level machine learning model to analyze the individual-level similarity vector, an individual-level similarity score defining a similarity between the paired tree persons;
• determining, utilizing a family-level machine learning model based on the individual-level similarity score and the family-level similarity score, that the first tree person and the second tree person are duplicates of a single individual;
• and
• modifying a cluster database based on determining that the first tree person and the second tree person are duplicates of the single individual.