Identification of feature groups in feature graph databases

The method 4, wherein the plurality of feature-to-feature relationship types includes at least one of:

• a related-to relationship type;
• a subset-of-relationship type;
• a derived-from relationship type;
• a same-as-but-disjoint-from relationship type;
• or
• a partially-overlapping relationship type.

A non-transitory computer-readable medium storing instructions which, when executed by a processing system including at least one processor, cause the processing system to perform operations, the operations comprising:

• applying a community detection process to a feature graph database representing one or more data tables of telecommunication network operational data to identify a plurality of communities of features within the feature graph database, where each of the one or more data tables comprises a plurality of rows and a plurality of columns, wherein the feature graph database comprises:
• a plurality of objects, each of the plurality of objects representing a feature of a plurality of features, wherein each of the plurality of features comprises a column of the one or more data tables, the column comprising a vector of values of a particular data type;
• and
• a plurality of relationships between the plurality of objects, wherein the community detection process is applied only with respect to a plurality of feature-to-feature relationships of the plurality of relationships within the feature graph database, wherein each of the plurality of feature-to-feature relationships represents a column-to-column relationship between respective columns of the one or more data tables;
• labeling a first plurality of features of the feature graph database with at least a first community label, wherein the first plurality of features comprises features of at least a first community of the plurality of communities;
• obtaining a search associated with at least one feature of the feature graph database, wherein the at least one feature is a part of the at least the first plurality of features of the at least the first community;
• and
• providing the first plurality of features in response to the search for detecting duplicate features.

A device comprising:

• a processor system including at least one processor;
• and
• a computer-readable medium storing instructions which, when executed by the processing system, cause the processing system to perform operations, the operations comprising:
• applying a community detection process to a feature graph database representing one or more data tables of telecommunication network operational data to identify a plurality of communities of features within the feature graph database, where each of the one or more data tables comprises a plurality of rows and a plurality of columns, wherein the feature graph database comprises:
• a plurality of objects, each of the plurality of objects representing a feature of a plurality of features, wherein each of the plurality of features comprises a column of the one or more data tables, the column comprising a vector of values of a particular data type;
• and
• a plurality of relationships between the plurality of objects, wherein the community detection process is applied only with respect to a plurality of feature-to-feature relationships of the plurality of relationships within the feature graph database, wherein each of the plurality of feature-to-feature relationships represents a column-to-column relationship between respective columns of the one or more data tables;
• labeling a first plurality of features of the feature graph database with at least a first community label, wherein the first plurality of features comprises features of at least a first community of the plurality of communities;
• obtaining a search associated with at least one feature of the feature graph database, wherein the at least one feature is a part of the at least the first plurality of features of the at least the first community;
• and
• providing the first plurality of features in response to the search for detecting duplicate features.