Method and system for creating entity records using existing data sources

US10614102B2 · kind B2 · utility

Assignee

• Innoplexus AG · DE

Inventors

• Gaurav Tripathi · Pune, IN
• Vatsal Agarwal · Rampur, IN
• Yannik T. H. Schelske · Eschborn, DE
• Nikhil Vinod Fulzele · Nagpur, IN
• Arpan Sheetal · Hasanganj, IN

Key dates

• Filing date: Dec 27, 2017
• Grant date: Apr 7, 2020
• Expiry date: Oct 3, 2038

Classification

• Technology area (CPC G): Physics
• CPC primary: G06F40/295
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

A method and a system for creating entity records. The method includes extracting data records from existing data sources, the data records including entity names and attributes associated therewith; identifying the entity names and attributes corresponding thereto, in each extracted data record; classifying identified entity attributes, based on attribute signatures associated therewith; clustering data records based on similar classified entity attributes and/or similar entity names; comparing entity attributes in clustered data records to identify entity attributes with missing attributes data; assigning representative attributes data to entity attributes with missing attributes data; combining clustered data records to form entity record segments; clustering entity record segments based on similar identity signatures thereof; comparing relevant entity attributes of clustered entity record segments to identify entity record segments having a relation therebetween; and combining related entity record segments to form entity records.