Utilizing classification and text analytics for optimizing processes in documents

• US 9,779,076 B2
• Filed: 06/25/2014
• Issued: 10/03/2017
• Est. Priority Date: 09/04/2013
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Emanuel, Barton W., Nonnenkamp, Robert J.
• Primary Examiner(s): Bloomquist, Keith
• Application Number:
  US14/314,767
• Publication Number:
  US 20150067468A1
• Time in Patent Office: 1,196 Days
• Field of Search: None
• CPC Class Codes: G06F 40/169 Annotation, e.g. comment data or footnotes
• CPC Class Codes: G06F 40/194 Calculation of difference between files

Abstract

Classification and text analytics are used to evaluate passages, extract text, identify concepts, and provide displayable and searchable notations to assist document editors in identifying and evaluating conflicting or duplicate directives (also called policies or rules) within a large document.

Claims

1. A computer-implemented method for analyzing a document comprising:

receiving the document;

extracting text of the document from a native form of the document, wherein the text of the document comprises a glossary including a lexical ontology;

separating the document into two or more physical sections;

identifying, using text analytics on the lexical ontology of the glossary and without user-input, one or more directives within the text;

generating, based on the one more directives, one or more annotations within the two or more physical sections;

comparing the annotations to identify duplicate annotations and conflicting annotations within the text; and

displaying the annotations and results of the comparison of the annotations in a searchable interface.

2. The computer-implemented method of claim 1, wherein the separating the document into two or more physical sections is configurable based on one or more logical attributes of the document.

3. The computer-implemented method of claim 1, wherein the one or more directives comprise a policy.

4. The computer-implemented method of claim 1, wherein the one or more directives are based on and selected from a group consisting of a part of speech, a phrase, a proper name, a location, a business entity, a domain specific keyword or concept, and a relationship referenced by one of the one or more directives.

5. The computer-implemented method of claim 1, further comprising:

extracting a glossary within the one or more documents to be used for identifying the one or more directives.

6. The computer-implemented method of claim 1, further comprising:

classifying the annotations into groups based on one or more attributes of the directives; and

wherein the comparing is further based on the groups.

7. The computer-implemented method of claim 1, further comprising:

indexing the annotations; and

combining the annotations with second annotations from another document; and

wherein the comparing comprises comparing the annotations with the second annotations.

8. The computer-implemented method of claim 1, further comprising:

highlighting the text that contains one or more directives; and

highlighting the text that contains one or more annotations.

9. The computer-implemented method of claim 1, wherein the comparing and displaying steps are performed dynamically while the document is being edited.