Enterprise knowledge graphs using user-based mining

A method of managing an entity record within a knowledge graph, comprising

• performing, by a user-based mining system, a mining of a set of enterprise source documents within an enterprise intranet to determine a plurality of entity names that are trending and active in the enterprise intranet based on enterprise users and enterprise user activity;
• generating an entity record within a knowledge graph for a mined entity name from the entity names based on an entity schema and ones of the set of enterprise source documents associated with the mined entity name, the entity record including attributes aggregated from the ones of the set of enterprise source documents associated with the mined entity name;
• displaying an entity page including at least a portion of the attributes of the entity record based on permissions to view the ones of the set of enterprise source documents associated with the mined entity name, wherein the mining comprises:
• comparing the set of enterprise source documents to a set of templates defining potential entity attributes to identify a number of instances of a name being used within the set of enterprise source documents;
• performing incremental clustering on the number of the instances to determine potential entity names;
• and
• linking potential entity names determined from the number of instances to existing entities in the knowledge graph based on metadata contained in the entity record defining supporting enterprise source documents for each of the attributes of the entity record, the linking performed using a clustering process, the clustering process comprising an unsupervised machine learning process for updating a machine learning model by loading the instances into memory and calculating clustering metadata defining probability distributions between the instances until a stable probability distribution is reached, thus causing the machine learning model to link additional data to the mined entity name;
• and
• updating the knowledge graph based on the generated entity record.

A non-transitory computer-readable medium storing computer-executable instructions that when executed by a computer processor cause the computer processor to:

• performing a mining of a set of enterprise source documents within an enterprise intranet to determine a plurality of entity names that are trending and active in the enterprise intranet based on enterprise users and enterprise user activity;
• generating an entity record within a knowledge graph for a mined entity name from the entity names based on an entity schema and ones of the set of enterprise source documents associated with the mined entity name, the entity record including attributes aggregated from the ones of the set of enterprise source documents associated with the mined entity name;
• displaying an entity page including at least a portion of the attributes of the entity record based on permissions to view the ones of the set of enterprise source documents associated with the mined entity name, wherein the mining comprises:
• comparing the set of enterprise source documents to a set of templates defining potential entity attributes to identify a number of instances of a name being used within the set of enterprise source documents;
• performing incremental clustering on the number of the instances to determine potential entity names;
• and
• linking potential entity names determined from the number of instances to existing entities in the knowledge graph based on metadata contained in the entity record defining supporting enterprise source documents for each of the attributes of the entity record, the linking performed using a clustering process, the clustering process comprising an unsupervised machine learning process for updating a machine learning model by loading the instances into memory and calculating clustering metadata defining probability distributions between the instances until a stable probability distribution is reached, thus causing the machine learning model to link additional data to the mined entity name;
• and
• updating the knowledge graph based on the generated entity record.