Systems and methods for intelligent labeling of instance data clusters based on knowledge graph

A system comprising:

• a cluster labeling engine in communication with a knowledge graph;
• wherein the knowledge graph comprises a plurality of nodes and a plurality of edges connecting the plurality of nodes, wherein the plurality of nodes represent objects and the plurality of edges represent relationship between the objects;
• wherein the cluster labeling engine comprises a user interface configured to receive a plurality of input instances, and access the knowledge graph;
• an instance matching operator configured to, for at least some selected input instances, identify respective matching objects represented by corresponding nodes of the knowledge graph, wherein a selected input instance shares a common label with the corresponding matching object;
• and
• a common class object finder configured to, for identified matching objects, identify a common class object represented by a corresponding node of the knowledge graph, wherein a percentage of identified matching objects are descendants of the common class object, wherein the percentage is greater than a predefined threshold;
• wherein the cluster labeling engine is configured to associate a label of the common class object with the plurality of input instances.

One or more computer-readable media having encoded thereon computer-executable instructions causing one or more processors to perform a method comprising:

• receiving a plurality of input instances selected from a column of data in a database table;
• accessing a knowledge graph comprising a plurality of nodes and a plurality of edges connecting the plurality of nodes, wherein the plurality of nodes represent objects and the plurality of edges represent relationship between the objects;
• for the plurality of input instances, identifying respective matching objects represented by corresponding nodes of the knowledge graph, wherein an input instance shares a common label with the corresponding matching object;
• for identified matching objects, identifying a common class object represented by a corresponding node of the knowledge graph, wherein a percentage of identified matching objects are descendants of the common class object, wherein the percentage is greater than a predefined threshold;
• assigning a label of the common class object to the column of data in the database table;
• translating the label associated with the plurality of input instances to an equivalent label defined in an ontology dictionary, wherein the ontology dictionary maps ontology of the knowledge graph to ontology of a data repository;
• and
• replacing the label assigned to the column of data in the database table to the equivalent label, and adding the column of data in the database table and the equivalent label to the data repository.