# US 12,183,100 B2 · System and method for generating best potential rectified data based on past recordings of data > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,183,100 B2 - Document ID: US12183100B2 - Status: Granted - Kind: B2 - Application number: 17/653,999 - Filed: 2022-03-08 - Published: 2023-07-27 - Granted: 2024-12-31 - Earliest claimed: 2022-01-22 - Assignees: JPMorgan Chase Bank, N.A. - Applicants: JPMorgan Chase Bank, N.A. - Inventors: Aditya Sharma - Web page: https://patentgrep.com/patent/US12183100B2 ## CPC - G06V 30/133: {Evaluation of quality of the acquired characters} - G06F 3/04817: using icons (graphical or visual programming using iconic symbols G06F8/34) - G06F 3/0482: Interaction with lists of selectable items, e.g. menus - G06F 40/166: Editing, e.g. inserting or deleting - G06N 20/00: Machine learning - G06V 10/945: {User interactive design; Environments; Toolboxes} - G06V 30/127: {with the intervention of an operator} - G06V 30/19133: {Interactive pattern learning with a human teacher} - G06V 30/1916: {Validation; Performance evaluation} - G06V 30/26: Techniques for post-processing, e.g. correcting the recognition result - G06V 30/262: using context analysis, e.g. lexical, syntactic or semantic context - G06V 30/41: Analysis of document content (recognition of printed characters based on code marks G06V30/224) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Various methods, apparatuses/systems, and media for data processing are disclosed. A processor receives a digital document; applies an optical character recognition (OCR) algorithm on said received digital document by utilizing an OCR tool; identifies defective data extracted by the OCR tool resulted from relatively inferior image quality of the received digital document; implements an auto rectification algorithm on the identified defective data; automatically generates, in response to implementing the auto rectification algorithm, corresponding auto-rectified data for each identified defective data; records the defective data and corresponding auto-rectified data at a field level; receives user input data on said recorded auto-rectified data; determines whether the auto-rectified data is correct or not; and populates, based on determining that the auto-rectified data is correct, a machine learning model with said received user input data to be utilized for subsequently received digital document. ## Claims ### Claim 1 A method for data processing by utilizing one or more processors along with allocated memory, the method comprising: receiving a digital document; applying an optical character recognition (OCR) algorithm on said received digital document by utilizing an OCR tool; identifying defective data extracted by the OCR tool resulted from relatively inferior image quality of the received digital document; implementing an auto rectification algorithm on the identified defective data; automatically generating, in response to implementing the auto rectification algorithm, corresponding auto-rectified data for each identified defective data; recording the defective data and corresponding auto-rectified data at a field level; receiving user input data on said recorded auto-rectified data; determining whether the auto-rectified data is correct or not; populating, based on determining that the auto-rectified data is correct, a machine learning model with said received user input data to be utilized for subsequently received digital document; generating a plurality of first selectable icons, wherein each of said first selectable icon is configured to display corresponding auto-rectified field data when user input is received by clicking or hovering over the first selectable icon; receiving user input data that the auto-rectified field data is not correct based on user's comparing comparison of the auto-rectified field data with a corresponding original image data of the digital document; and receiving user input data indicating a user defined correct field data replacing the auto-rectified field data. ### Claim 2 (depends on 1) The method according to claim 1, wherein the defective data includes one or more of the following data: unwanted extraction data, partial data, incomplete data, junk data, and perfect but incomplete extraction data. ### Claim 3 (depends on 1) The method according to claim 1, further comprising: receiving user input data indicating approval of the auto-rectified field data when a difference between an auto-rectified data value and user input data value is equal to or more than a predetermined threshold value. ### Claim 4 (depends on 1) The method according to claim 1, further comprising: receiving user input data indicating disapproval of the auto-rectified field data when a difference between an auto-rectified data value and user input data value is below a predetermined threshold value. ### Claim 5 (depends on 4) The method according to claim 4, further comprising: generating a plurality of second selectable icons, wherein each of said second selectable icon is configured to display, upon receiving user input via clicking or hovering over the second selectable icon, corresponding suggested potential match field data for a corresponding disapproval of the auto-rectified field data based on historical patterns data that was generated previously in correcting the disapproved auto-rectified field data; receiving user input in approving the suggested potential match field data; and populating the machine learning model with said approved suggested potential match field data to be utilized for subsequently received digital document. ### Claim 6 (depends on 5) The method according to claim 5, wherein when suggested potential match field data is not available for a certain extracted or user populated data, the method further comprising: receiving user input data that accepts the certain extracted or the user populated data as a new field data for subsequent suggestions; and populating the machine learning model with said new field data to be utilized for subsequently received digital document. ### Claim 7 A system for data processing, the system comprising: a processor; and a memory operatively connected to the processor via a communication interface, the memory storing computer readable instructions, when executed, causes the processor to: receive a digital document; apply an optical character recognition (OCR) algorithm on said received digital document by utilizing an OCR tool; identify defective data extracted by the OCR tool resulted from relatively inferior image quality of the received digital document; implement an auto rectification algorithm on the identified defective data; automatically generate, in response to implementing the auto rectification algorithm, corresponding auto-rectified data for each identified defective data; record the defective data and corresponding auto-rectified data at a field level; receive user input data on said recorded auto-rectified data; determine whether the auto-rectified data is correct or not; populate, based on determining that the auto-rectified data is correct, a machine learning model with said received user input data to be utilized for subsequently received digital document; generate a plurality of first selectable icons, wherein each of said first selectable icon is configured to display corresponding auto-rectified field data when user input is received by clicking or hovering over the first selectable icon; receive user input data that the auto-rectified field data is not correct based on user's comparing comparison of the auto-rectified field data with a corresponding original image data of the digital document; and receive user input data indicating a user defined correct field data replacing the auto-rectified field data. ### Claim 8 (depends on 7) The system according to claim 7, wherein the defective data includes one or more of the following data: unwanted extraction data, partial data, incomplete data, junk data, and perfect but incomplete extraction data. ### Claim 9 (depends on 7) The system according to claim 7, wherein the processor is further configured to: receive user input data indicating approval of the auto-rectified field data when a difference between an auto-rectified data value and user input data value is equal to or more than a predetermined threshold value. ### Claim 10 (depends on 7) The system according to claim 7, wherein the processor is further configured to: receive user input data indicating disapproval of the auto-rectified field data when a difference between an auto-rectified data value and user input data value is below a predetermined threshold value. ### Claim 11 (depends on 10) The system according to claim 10, wherein the processor is further configured to: generate a plurality of second selectable icons, wherein each of said second selectable icon is configured to display, upon receiving user input via clicking or hovering over the second selectable icon, corresponding suggested potential match field data for a corresponding disapproval of the auto-rectified field data based on historical patterns data that was generated previously in correcting the disapproved auto-rectified field data; receive user input in approving the suggested potential match field data; and populate the machine learning model with said approved suggested potential match field data to be utilized for subsequently received digital document. ### Claim 12 (depends on 11) The system according to claim 11, wherein when suggested potential match field data is not available for a certain extracted or user populated data, the processor is further configured to: receive user input data that accepts the certain extracted or the user populated data as a new field data for subsequent suggestions; and populate the machine learning model with said new field data to be utilized for subsequently received digital document. ### Claim 13 A non-transitory computer readable medium configured to store instructions for data processing, wherein, when executed, the instructions cause a processor to perform the following: receiving a digital document; applying an optical character recognition (OCR) algorithm on said received digital document by utilizing an OCR tool; identifying defective data extracted by the OCR tool resulted from relatively inferior image quality of the received digital document; implementing an auto rectification algorithm on the identified defective data; automatically generating, in response to implementing the auto rectification algorithm, corresponding auto-rectified data for each identified defective data; recording the defective data and corresponding auto-rectified data at a field level; receiving user input data on said recorded auto-rectified data; determining whether the auto-rectified data is correct or not; populating, based on determining that the auto-rectified data is correct, a machine learning model with said received user input data to be utilized for subsequently received digital document; generating a plurality of first selectable icons, wherein each of said first selectable icon is configured to display corresponding auto-rectified field data when user input is received by clicking or hovering over the first selectable icon; receiving user input data that the auto-rectified field data is not correct based on user's comparing comparison of the auto-rectified field data with a corresponding original image data of the digital document; and receiving user input data indicating a user defined correct field data replacing the auto rectified field data. ### Claim 14 (depends on 13) The non-transitory computer readable medium according to claim 13, wherein the defective data includes one or more of the following data: unwanted extraction data, partial data, incomplete data, junk data, and perfect but incomplete extraction data. ### Claim 15 (depends on 13) The non-transitory computer readable medium according to claim 13, wherein the instructions, when executed, cause the processor to further perform the following: receiving user input data indicating approval of the auto-rectified field data when a difference between an auto-rectified data value and user input data value is equal to or more than a predetermined threshold value. ### Claim 16 (depends on 13) The non-transitory computer readable medium according to claim 13, wherein the instructions, when executed, cause the processor to further perform the following: receiving user input data indicating disapproval of the auto-rectified field data when a difference between an auto-rectified data value and user input data value is below a predetermined threshold value. ### Claim 17 (depends on 16) The non-transitory computer readable medium according to claim 16, wherein the instructions, when executed, cause the processor to further perform the following: generating a plurality of second selectable icons, wherein each of said second selectable icon is configured to display, upon receiving user input via clicking or hovering over the second selectable icon, corresponding suggested potential match field data for a corresponding disapproval of the auto-rectified field data based on historical patterns data that was generated previously in correcting the disapproved auto-rectified field data; receiving user input in approving the suggested potential match field data; and populating the machine learning model with said approved suggested potential match field data to be utilized for subsequently received digital document. ### Claim 18 (depends on 17) The non-transitory computer readable medium according to claim 17, wherein when suggested potential match field data is not available for a certain extracted or user populated data, the instructions, when executed, cause the processor to further perform the following: receiving user input data that accepts the certain extracted or the user populated data as a new field data for subsequent suggestions; and populating the machine learning model with said new field data to be utilized for subsequently received digital document.