Back to results
US 9,286,280 B2Granted
Utilizing classification and text analytics for optimizing processes in documents
AssigneeInternational Business Machines Corporation
InventorsBarton W. Emanuel, Robert J. Nonnenkamp
Life of this patent
Estimating the term…
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.
Claims16
A computer program product for analyzing a document, the computer program product comprising a non-transitory computer readable storage medium having program code embodied therewith, the program code executable by a device to:
- receive, by the device, the document;
- extract, by the device, text of the document from a native form of the document, wherein the text of the document comprises a glossary including a lexical ontology;
- separate, by the device, the document into two or more physical sections;
- identify, by the device, using text analytics on the lexical ontology of the glossary and without user-input, one or more directives within the text;
- generate, by the device, based on the one or more directives, one or more annotations within the two or more physical sections;
- compare, by the device, the annotations to identify duplicate annotations and conflicting annotations within the text;
- and
- display, by the device, the annotations and results of the comparison of the annotations in a searchable interface.
5 more elements
A system for analyzing a document comprising:
- a text extractor configured to extract text of the document from a native form of the document, wherein the text of the document comprises a glossary including a lexical ontology;
- a separator configured to separate the document into two or more physical sections;
- a text analyzer configured to:
- identify, using text analytics on the lexical ontology of the glossary and without user-input, one or more directives within the text;
- and
- generate, based on the one or more directives, one or more annotations within the two or more physical sections;
- a comparator configured to compare the annotations to identify duplicate annotations and conflicting annotations within the text;
- and
- a searchable interface configured to display the annotations and results of the comparison of the annotations.
6 more elements
Dependencies are inferred from the claim text.