US 12,260,416 B2
Agnostic image digitizer to automate compliance filings
James Siekman, Charlotte, NC (US); Aubrey Breon Farrar, Sr., Waldorf, MD (US); Mohamed Faris Khaleeli, Charlotte, NC (US); Patricia Ann Albritton, Charlotte, NC (US); Sheila Page, Charlotte, NC (US); Mark Alan Odiorne, Waxhaw, NC (US); and Marcus R. Matos, Richardson, TX (US)
Assigned to Bank of America Corporation, Charlotte, NC (US)
Filed by Bank of America Corporation, Charlotte, NC (US)
Filed on Jul. 27, 2022, as Appl. No. 17/874,720.
Prior Publication US 2024/0037565 A1, Feb. 1, 2024
Int. Cl. G06Q 30/018 (2023.01); G06F 16/23 (2019.01)
CPC G06Q 30/018 (2013.01) [G06F 16/2365 (2019.01)] 14 Claims
OG exemplary drawing
 
1. A method for automating submission of compliance filings with a regulatory authority, the method comprising:
receiving, at a computer hardware processor, a first set of documents comprising two or more documents in a first format, the first format comprising a format that the computer hardware processor cannot use to extract data, said first set of documents are stored on a computer server;
converting, using the computer hardware processor to perform optical character recognition (OCR), the first set of documents from the first format into a second format, the second format comprising a format that the computer hardware processor can use to extract data from a document;
accessing, using the computer hardware processor, a first set of compliance filings with a regulatory authority comprising two or more compliance filings in the second format from the computer server, wherein the first set of compliance filing relates to a submission of the first set of documents by an entity to an organization and the first set of documents is in a format that is poorly compatible with a database of the organization;
populating, using the computer hardware processor, the database with data extracted from the first set of documents in the second format and the first set of compliance filings in the second format, where the database is stored on the computer server;
training, using a graphics processing unit (GPU) and the database, a first statistical model, the first statistical model comprising a deep learning artificial intelligence (AI) system, to determine a type of compliance filing to file based on the first set of documents and the first set of compliance filings with a regulatory authority;
training, using the GPU and the database, a second statistical model based on a receipt of a document, the second statistical model comprising a deep learning AI system, to, after receiving the type of compliance filing from the first statistical model, populate a compliance filing;
receiving, at the computer hardware processor, a second document from an entity in the first format, where the second document is populated with data;
converting, using the computer hardware processor to perform OCR, the second document into the second format;
running, using the GPU and the second document, the first statistical model to determine the type of compliance filing to file;
using the type of compliance filing to file as determined by the first statistical model, running, using the GPU and the second document, the second statistical model to populate a compliance filing for submission to a first regulatory authority; and
submitting to the first regulatory authority, using the computer hardware processor, the compliance filing populated with data;
wherein:
the second document and the compliance filing relate to a change in information relating to an arrangement the entity has with the organization.