System and method of extracting data from structured and unstructured sources of data using automated joins
AssigneeAtlantic Technical Organization
InventorsArturo Geigel, Victor Rivera
Life of this patent
Estimating the term…
Loading patent…
AssigneeAtlantic Technical Organization
InventorsArturo Geigel, Victor Rivera
Estimating the term…
System and method for creating enabling the user to select fields from a database, semi structured or unstructured documents that produces an automated process of joining the database tables, semi structured or unstructured documents into a feature vector that can be further processed by machine learning algorithms or preprocessing routines and filters. The full join performed starts by producing a graph representation of the links between data tables/documents and then restructuring the information into the most efficient join tree. The join tree then extracts the data in the form of a feature vector.
A computer operable method to extract data from a database wherein said database includes a plurality of record sources and a plurality of relationships therebetween, said method comprising:
A system, comprising:
The system of claim 17, wherein said central processing system comprises a structured data source collection.
The system of claim 17, wherein said central processing system comprises a unstructured data source collection.
The system of claim 17, wherein said data storage comprises a database schema to store said meta information.
Dependencies are inferred from the claim text.