Browse Prior Art Database

Method for Locating Key Pieces of Missing Information in Unstructured Text using Text Analytics

IP.com Disclosure Number: IPCOM000250508D
Publication Date: 2017-Jul-26
Document File: 1 page(s) / 66K

Publishing Venue

The IP.com Prior Art Database

Abstract

A method is disclosed for locating key pieces of missing information in unstructured text using text analytics.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 60% of the total text.

Method for Locating Key Pieces of Missing Information in Unstructured Text using Text Analytics

In many fields, it is important that employees document information in full entirety. In particular, some companies have required procedures that need to be documented (i.e.: address, insurance, employer, etc.). The companies might have a procedure that requires certain materials and need a way to identify if a required material is missing from documentation. Many companies train employees to ensure that each of them include the required information in documentation but it potentially allows for human error mistakes. Natural language text analytics is currently being used to identify phrases and information from unstructured text but it is not being utilized to identify whether or not the unstructured text is missing key pieces of information.

Disclosed is a method for locating key pieces of missing information in unstructured text using text analytics. The method utilizes natural language processing (NLP) and rule- based techniques to highlight or indicate missing information from the unstructured text, and records all necessary information either in real-time or near real-time. The recorded necessary information is then verified in accordance with context of the unstructured text, by developing and using text analytics annotators.

In accordance with the method, an aggregate parsing rule w.r.t scope of a sentence from the text is generated, which in turn creates an annotation (Pa...