Methods and systems for providing a service for producing structured data elements from free text sources
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.
Claims32
A system for providing a service to identify and structure free text databases, comprising:
- a processing element;
- one or more data access ports, said ports providing access to data by said processing element;
- a set of one or more input devices readable by said processing element;
- a storage device, said storage device containing instructions executable by said processing element to perform the functions of:
- (i) reading an access reference through said input device set, the access reference referencing a customer's source of unstructured data, the unstructured data including free text;
- (ii) accessing the source of unstructured data;
- (iii) identifying text records within the free text;
- (iv) linguistically parsing the identified text records;
- (v) identifying roles within the parsed text records, said identifying producing attribute extractions, each of said attribute extractions containing attribute information of the derived source text;
- (v) applying caseframes to the attribute extractions, said applying caseframes producing a filtered set of attributes extractions;
- and
- (vi) producing a structured data element containing the filtered set of extractions.
A method for providing a service to identify and structure free text databases, comprising the steps of:
- reading an access reference through said input device set, the access reference referencing a customer's source of unstructured data, the unstructured data including free text;
- accessing the source of unstructured data;
- identifying text records within the free text;
- linguistically parsing the identified text records;
- identifying roles within the parsed text records, said identifying producing attribute extractions, each of said attribute extractions containing attribute information of the derived source text;
- applying caseframes to the role extractions, said applying caseframes producing a filtered set of attribute extractions;
- and
- producing a structured data element containing the filtered set of extractions.
Dependencies are inferred from the claim text.