Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 2/26/2025 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1-2, 4-10, 12-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Vankina et. al. (United States Patent Application Publication US 20250218205 A1) in view of Sureka et. al. (United States Patent Application Publication US 2026/0051194 A1).
Regarding claim 1, Vankina et. al. discloses a system for enhanced accuracy of image data obtained through optical character recognition (OCR) processing, the system comprising: at least one non-transitory storage device; and at least one processor coupled to the at least one non-transitory storage device, wherein the at least one processor is configured to: perform OCR processing on the first image file to generate an OCR data file (Vankina et. al. abstract, Fig. 3-5, [0007]-[0012]: The ML-based computing method further comprises converting, by the one or more hardware processors, one or more formats of the one or more electronic documents into one or more first images associated with the one or more electronic documents based on one or more industry standard image-conversion tools.); input the OCR data file into at least two machine learning engines, wherein the at least two machine learning engines are configured to operate in parallel (Vankina et. al. Fig. 3-5, [0007]- [0012]: convolutional neural network (CNN) based machine learning model and you only look once (YOLO) architecture based machine learning model); based on an output of the at least two machine learning engines, generate a confidence score associated with the OCR data file (Vankina et. al. [0020]: generating, by the one or more hardware processors, one or more confidence scores to analyze confidence level of the you only look once (YOLO) architecture-based machine learning model).
However, Vankina et. al. fails to disclose a processor configured to receive a first image file obtained by an image capture device, and based on the confidence score, process the OCR data file over a real-time settlement rail.
Sureka et. al. teaches a processor configured to receive a first image file obtained by an image capture device, and based on the confidence score, process the OCR data file over a real-time settlement rail (Sureka et. al. Fig. 4A-4E, [0032]- [0033], [0041]: This mobile application uses image processing software from a client operating system to control the camera and capture video having frames containing the document. The mobile application benefits from the implementation of machine-learning models, such as neural network architectures, of the image processing software and mobile applications to improve results. [0048]: The provider servers can include an automated clearing house (ACH) or an addressable location for further entities. For example, the server can cause a check image (e.g., a composite check image) to be conveyed to initiate an ACH transaction for a deposit or settlement thereof.).
PNG
media_image1.png
602
652
media_image1.png
Greyscale
PNG
media_image2.png
594
884
media_image2.png
Greyscale
PNG
media_image3.png
836
548
media_image3.png
Greyscale
PNG
media_image4.png
786
656
media_image4.png
Greyscale
PNG
media_image5.png
785
652
media_image5.png
Greyscale
These features are important to the claimed invention because the two parallel machine learning systems improve verification of financial document security, validation, and authentication through accurate information extraction of tabular and non-tabular data often seen in checks or other financial documents. Thus, it would have been obvious to one skilled in the art prior to the effective filing date of the claimed invention to have combined the teachings of Vankina et. al. and Sureka et. al. so that the mobile image capturing device can be combined with the machine learning algorithms of Vankina et. al. to arrive at the solution of the claimed invention.
Regarding claim 9, which discloses a computer program product for enhanced accuracy of image data obtained through optical character recognition (OCR) processing, the computer program product comprising a non-transitory computer-readable medium comprising code causing an apparatus to carry out the system of claim 1, which the rejection analysis is incorporated herein.
Regarding claim 17, which discloses a method for enhanced accuracy of image data obtained through optical character recognition (OCR) processing, the method comprising the system of claim 1, which the rejection analysis is incorporated herein.
Regarding claim 2, 10, and 18 Vankina et. al. further discloses the system of claim 1, the computer program product of claim 9, and the method of claim 17, wherein the at least one processor is further configured to: receive a second image file obtained by the image capture device; perform OCR on the second image file to generate a second OCR data file (Vankina et. al. [0021]: the ML-based computing method further comprises training, by the one or more hardware processors, the you only look once (YOLO) architecture based machine learning model, by: (a) obtaining, by the one or more hardware processors, one or more second datasets associated with the one or more second images for training the you only look once (YOLO) architecture based machine learning model); and append the second OCR data file to the OCR data file to generate a combined OCR data file (Vankina et. al. [0023]: (b) adding, by the one or more hardware processors, the one or more second training data with the one or more second training datasets to generate one or more updated second training datasets; (c) re-training, by the one or more hardware processors, the you only look once (YOLO) architecture based machine learning model based on the one or more updated second training datasets).
Regarding claim 4, 12, and 19 Vankina et. al. further discloses the system of claim 1, the computer program product of claim 9, and the method of claim 17, wherein the at least one processor is further configured to: based on the confidence score, store the OCR data file in a data repository; and train the at least two machine learning engines using the data repository (Vankina et. al. [0020], Fig. 4-5: YOLO and CNN machine learning engines and architecture).
PNG
media_image6.png
590
680
media_image6.png
Greyscale
Regarding claim 5 and 13, Vankina et. al. further discloses the system of claim 1, and the computer program product of claim 9, wherein a first machine learning engine of the at least two machine learning engines is configured to generate orientation data associated with the first image file (Vankina et. al. [0023]- [0024]: the extracted one or more first data comprising one or more texts in one or more structured tables, based on a preprocessing model, by: (a) sorting, by the one or more hardware processors, the one or more texts in a descending order based on one or more Y-coordinate values, Fig. 6-7).
PNG
media_image7.png
670
654
media_image7.png
Greyscale
Regarding claim 6 and 14, Sureka et. al. further discloses the system of claim 1, and the computer program product of claim 9, wherein a second machine learning engine of the at least two machine learning engines is configured to generate stylization data associated with the first image file (Sureka et. al. [0051], [0087]- [0088]).
PNG
media_image8.png
460
650
media_image8.png
Greyscale
PNG
media_image9.png
516
646
media_image9.png
Greyscale
Regarding claim 7 and 15, Sureka et. al. further discloses the system of claim 1, and the computer program product of claim 9, wherein the at least one processor is further configured to: input the OCR data file into at least three machine learning engines, wherein the at least three machine learning engines are configured to operate in parallel and wherein a third machine learning engine of the at least three machine learning engines is configured to generate alteration data associated with the first image file (Sureka et. al. [0050]: third feature extraction model).
PNG
media_image10.png
240
672
media_image10.png
Greyscale
Regarding claim 8 and 16, Sureka et. al. further discloses the computer program product of claim 7, and the computer program product of claim 15, wherein the at least one processor is further configured to: input the OCR data file into at least four machine learning engines, wherein the at least four machine learning engines are configured to operate in parallel and wherein a fourth machine learning engine of the at least four machine learning engines is configured to generate word comprehension data associated with the first image file (Sureka et. al. [0050]: fourth feature extraction model).
PNG
media_image11.png
404
650
media_image11.png
Greyscale
Regarding claim 20, Sureka et. al. further discloses the method of claim 17, wherein a first machine learning engine of the at least two machine learning engines is configured to generate orientation data associated with the first image file and a second machine learning engine of the at least two machine learning engines is configured to generate stylization data associated with the first image file (Sureka et. al. [0076], [0051], [0087]- [0088]).
PNG
media_image12.png
779
546
media_image12.png
Greyscale
Claim(s) 3 and 11 is/are rejected under 35 U.S.C. 103 as being unpatentable over Vankina et. al. (United States Patent Application Publication US 20250218205 A1) in view of Sureka et. al. (United States Patent Application Publication US 2026/0051194 A1) as applied to claim 1 above, and further in view of Verstraeten et. al. (United States Patent US 12719680 B2).
Regarding claim 3 and 11, Vankina et. al. and Sureka et. al. discloses the system of claim 1 and the computer program product of claim 9. However, Vankina et. al. and Sureka et. al. fails to disclose wherein processing the OCR data file over a real-time settlement rail further comprises converting the OCR data file to an ISO 20022 message.
Verstraeten et. al. teaches wherein processing the OCR data file over a real-time settlement rail further comprises converting the OCR data file to an ISO 20022 message (Verstraeten et. al. Col 13, lines 37-41: the communication data can include formatting instructions, such as, but not limited to, ISO 8583, ISO 20022, appropriate API commands, and/or any other suitable format capable of including data described herein. Col 16, lines 4-8: After determining whether or not to authorize the interaction, the authorizing entity computer can generate an authorization response message. The authorization response message can include an indication of whether or not the interaction is authorized. Col 16, lines 35-44: The authorizing entity computer can then format the confirmation request message based on the standard of ISO 20022 as known to one of skill in the art. The authorizing entity computer can convert one type of message to another type of message using communication data. For example, the authorizing entity computer can convert an ISO 8583 message (E.g. the authorization request message) into an ISO 20022 message (e.g., the confirmation request message), or an HTTP message.).
This is important to the claimed invention because the ISO 20022 serves as the confirmation request message between the bank and the user regarding the authorization of the financial settlement. Thus, it would have been obvious to one skilled in the art prior to the effective filing date of the claimed invention to have combined the teachings of Vankina et. al., Sureka et. al., and Verstraeten et. al. so that the OCR data file is converted to an ISO 20022 message.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JESSICA YIFANG LIN whose telephone number is (571)272-6435. The examiner can normally be reached M-F 7:00am-6:15pm, with optional day off.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Vu Le can be reached at 571-272-7332. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/JESSICA YIFANG LIN/Examiner, Art Unit 2668 August 29, 2026
/VU LE/Supervisory Patent Examiner, Art Unit 2668
Prosecution Insights