Natural language processing system and method for documents
AssigneeThoughtTrace, Inc.
InventorsNicholas E. Vandivere, Michael B. Kuykendall
Life of this patent
Estimating the term…
Abstract
In various embodiments, the disclosed systems and methods may receive documents, analyze the documents, categorize portions of the analyzed documents, and present the images of the documents and at least a portion of the categories. The analysis may include identification of categories and the presentation may include indicia of the portion of the image of the document related to the category. The systems and methods disclosed may allow querying and/or reporting of a plurality of documents to facilitate processing.
Claims31
A method for producing a user interface comprising a navigable document image and a list of concepts contained within text of the document image, the method comprising:
- receiving, by a processor, an electronic document;
- receiving, by a trained machine learning model, a text of the electronic document, the machine learning model generating one or more categories and one or more subcategories based on respective analysis of paragraphs and sentences in the received text, the categories corresponding to concepts related to a content of the text, the one or more subcategories are associated with locations corresponding to the text based upon which the machine learning model generated the one or more subcategories;
- associating, by the processor, the one or more categories and the one or more subcategories with locations within the electronic document, wherein the locations correspond to the text based upon which the machine learning model generated the one or more categories and the one or more subcategories;
- and
- generating, by the processor, a graphical user interface that, when presented on a display device, simultaneously displays:
- a navigable image of the electronic document, wherein a user may view different areas of the electronic document by interacting with the graphical user interface;
- and
- a list of the one or more categories and the one or more subcategories generated by the machine learning model, each listed category and subcategory selectable and operably linked with the navigable image of the electronic document;
- wherein the navigable image of the electronic document navigates to a location within the navigable image of the electronic document in response to the user selecting a listed category or a listed subcategory, the location associated with the selected listed category or the listed subcategory.
A system for producing a user interface comprising a navigable document image and a list of concepts contained within text of the document image, the system comprising:
- a processor;
- and
- a memory storing instructions, the instructions comprising:
- receiving an electronic document;
- receiving, by a trained machine learning model, a text of the electronic document, the machine learning model generating one or more categories and one or more subcategories based on respective analysis of paragraphs and sentences in the received text, the categories corresponding to concepts related to a content of the text, the one or more subcategories are associated with locations corresponding to the text based upon which the machine learning model generated the one or more subcategories;
- associating the one or more categories and the one or more subcategories with locations with the electronic document, the locations corresponding to the text based upon which the machine learning model generated the one or more categories and the one or more subcategories;
- and
- generating a graphical user interface that, when presented on a display device, simultaneously displays:
- a navigable image of the electronic document, wherein a user may view different areas of the electronic document by interacting with the graphical user interface;
- and
- a list of the one or more categories and the one or more subcategories generated by the machine learning model, each listed category and subcategory selectable and operably linked with the navigable image of the electronic document;
- navigable image of the electronic document in response to the user selecting a listed category or a listed subcategory, the location associated with the selected listed category or the listed subcategory.
Dependencies are inferred from the claim text.