Method and system for leveraging ocr and machine learning to uncover reuse opportunities from collaboration boards
AssigneeJPMorgan Chase Bank, N.A.
InventorsShawn Wesley ALEXANDER, Richard John CAREY
Life of this patent
Estimating the term…
Abstract
An embodiment of the present invention is directed to capturing collaboration boards in images, applying OCR and/or other recognition technology to read the collaboration boards and leveraging machine learning to query metadata repositories to identify reuse opportunities.
Claims20
A computer-implemented method that leverages optical character recognition (OCR) and machine learning to uncover reuse opportunities from collaboration interfaces, the method comprising the steps of:
- receiving recorded features and requirements on a collaboration interface;
- receiving captured one or more digital images associated with the collaboration interface;
- uploading the one or more digital images to one or more servers;
- processing the one or more digital images on the one or more servers into text and graphics via optical character recognition (OCR);
- applying a machine learning algorithm to extract key phrases and concepts from the text and graphics;
- identifying potential reuse opportunities by searching the extracted key phrases and concepts in one or more repositories of metadata associated with existing or work-in-progress systems;
- calculating a confidence score for each identified potential reuse opportunity;
- and
- ranking the potential reuse opportunities based at least in part on calculated confidence score.
A computer implemented system that leverages optical character recognition (OCR) and machine learning to uncover reuse opportunities from collaboration interfaces, the system comprising:
- an electronic input configured to receive image data from one or more cameras associated with a collaborative interface;
- a database that stores and manages image data from one or more collaborative interfaces;
- a server, coupled to the electronic input and the database, configured to perform the steps of:
- receiving, via the electronic input, recorded features and requirements on a collaboration interface;
- receiving, via the one or more cameras, captured digital images associated with the collaboration interface;
- uploading the one or more digital images to the server;
- processing, via optical character recognition (OCR) processor, the one or more digital images on the one or more servers into text and graphics;
- extracting, via a machine learning engine, key phrases and concepts from the text and graphics;
- identifying potential reuse opportunities by searching the extracted key phrases and concepts in one or more repositories of metadata associated with existing or work-in-progress systems;
- calculating a confidence score for each identified potential reuse opportunity;
- and
- ranking the potential reuse opportunities based at least in part on calculated confidence score.
Dependencies are inferred from the claim text.