Integration of structured data with free text for data mining
AssigneeAttensity Corporation
InventorsTodd D. Wakefield, David L. Bean
Life of this patent
Estimating the term…
Abstract
Disclosed herein are systems, methods and products for interpreting and structuring free text records utilizing extractions of several types including syntactic, role, thematic and domain extractions. Also disclosed herein are systems, methods and products for integrating interpretive extractions with structured data into unified structures that can be analyzed with, among other tools, data mining and data visualization tools.
Claims38
A computer program product located to one or more storage media devices usable to perform integration of mixed format data, said computer program product comprising instructions executable by a computer to perform the functions of:
- accessing a database of structured data, the structured data comprising a set of data tuples;
- accessing a source of unstructured data, the unstructured data including free text relatable to the data tuples of the structured data;
- interpreting the free text to produce a set of construed data reflecting at least one relational fact conveyed in the free text, each construed datum relatable to a data tuple of the structured data;
- integrating the produced data with the data tuples of the structured data, said integrating producing integrated data;
- and
- data mining the integrated data.
A computer program product located to one or more storage media devices usable to perform integration of mixed format data, said computer program product comprising instructions executable by a computer to perform the functions of:
- accessing a database of structured data, the structured data comprising a set of data tuples;
- accessing a source of unstructured data, the unstructured data including free text relatable to the data tuples of the structured data;
- interpreting the free text to produce a set of construed data reflecting at least one relational fact conveyed in the free text, each construed datum relatable to a data tuple of the structured data;
- integrating the produced data with the data tuples of the structured data, said integrating producing integrated data;
- providing the integrated data to a data mining application.
A method for integrating mixed format data, comprising the steps of:
- accessing a database of structured data, the structured data comprising a set of data tuples;
- accessing a source of unstructured data, the unstructured data including free text relatable to the data tuples of the structured data;
- interpreting the free text to produce a set of construed data reflecting at least one relational fact conveyed in the free text, each construed datum relatable to a data tuple of the structured data;
- integrating the produced data with the data tuples of the structured data;
- and
- data mining the integrated data.
Dependencies are inferred from the claim text.