DETAILED ACTION
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 .
The action is responsive to the following communication: an application filed on 04/26/2023 where:
Claims 1-20 currently pending.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 10/03/2025 is in compliance with the provisions of 37 CFR 1.97 and 37 CFR 1.98. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 103
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.
Claims 1-5, and 14-20 are rejected under 35 U.S.C. 103 as being unpatentable over Gogel (US 12462063) in view of VASANTH et al. (WO 2021/086837 hereinafter Vasanth).
Regarding claim 1, Gogel teaches: A method (FIG. 2 is a block diagram of systems, devices, methods, and computer program products for authorizing access to account-based online resources using image data, according to various embodiments described herein.) of using an artificial intelligence (AI) system to classify documents, the method comprising the steps of:
receiving, at a platform server running the AI system, a file comprising a document (Col. 13, lines 4-25, Once captured, one or more images can be processed to generate image data. The image data can be analyzed, using image processing techniques incorporating AI software and/or hardware algorithmic technology, to determine the QR code or other embedded identification data. In some embodiments, the images and image data can be processed, such as using the mobile device 202 or the online resource provider 212, to identify or classify one or more of the images).
Gogel does not explicitly teach: conducting optical character recognition (OCR) on the document to extract text content of the document;
identifying a document candidate based on the text content, wherein the document candidate has an expected document shape; detecting a shape of the document in the file;
classifying the document at least in part by determining whether the shape of the document matches the expected document shape; and
upon determining that the shape of the document matches the expected shape, verifying that the document candidate is correctly classified.
However, Vasanth teaches: conducting optical character recognition (OCR) on the document to extract text content of the document ([0034], The document being examined (referred to as the subject document herein) for authenticity is provided as an image. The image may be obtained by one or more of a photograph, a scan, OCR, or other suitable process.);
identifying a document candidate based on the text content, wherein the document candidate has an expected document shape ([0034], As shown in the figure, the document may include elements or features such as a logo 102, a photo or similar image 104, a hologram of other specific form of "watermark" or marker 106, one or more data fields 108 containing alphanumeric characters (identified as Header. Field 1, and Field 2 in the figure), and additional text 110);
detecting a shape of the document in the file ([0036], detect logo, a hologram etc.);
classifying the document at least in part by determining whether the shape of the document matches the expected document shape ([0036], the system and methods described are not limited to processing documents having a specific set of characteristics or attributes and may be applied to any document for which a reliable template or example is available or can be generated.); and
upon determining that the shape of the document matches the expected shape, verifying that the document candidate is correctly classified ([0037], Figure 1(b) is a flowchart or flow diagram illustrating an example process, operation, method, or function 120 for authenticating/verifying a document. Access Set of Document Templates and Data Describing Invariable Attributes Associated with Each Template; and Determine Most Likely Document Templates that "Match" Subject Document Based on Invariable Attributes; Fig. 1B).
The motivation for the combination is that Gogel and Vasanth are in the same field of endeavor, namely a document type classification.
Therefore, the Applicant's claimed invention would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Gogel to include conducting optical character recognition (OCR) on the document to extract text content of the document; identifying a document candidate based on the text content, wherein the document candidate has an expected document shape; detecting a shape of the document in the file; classifying the document at least in part by determining whether the shape of the document matches the expected document shape; and upon determining that the shape of the document matches the expected shape, verifying that the document candidate is correctly classified as taught by Vasanth. The motivation/suggestion would have been to further enhance/improve the document type classification since doing so will allow for authentication/verification of the uploaded document.
Regarding claim 2, Gogel and Vasanth teach: The method of claim 1, wherein the step of identifying the document candidate based on the text content relies on the AI system having been trained via machine learning using a training set of known document types (Vansanth, [0068]).
Regarding claim 3, Gogel and Vasanth teach: The method of claim 1, further comprising the step of detecting a visual feature of the document, wherein the step of identifying the document candidate is also based on the visual feature (Vasanth, fig. 2C, accuracy heatmap, [0019], Figure 2(c) is a diagram illustrating an example of a "hear map representing a confidence level in the accuracy of extracted document attributes, and which provides a visual indication of the verification accuracy of regions of a document subjected to processing by an embodiment of the system and methods described herein).
Regarding claim 4, Gogel and Vasanth teach: The method of claim 1, further comprising the step of detecting, by the AI system, a first filetype and, based on the first filetype, determining whether to convert the file to a second filetype (Vansanth, [0048], As mentioned, as part of the document authentication/verification processing, a transformation or transformations may be applied, where the transformation may be used to convert the original image of the subject document into a standard format so that it is easier and more accurately represented for further processing).
Regarding claim 5, Gogel and Vasanth teach: The method of claim 1, further comprising the step of detecting and decoding a machine-readable zone (Gogel, Col. 13, lines 4-25, Once captured, one or more images can be processed to generate image data. The image data can be analyzed, using image processing techniques incorporating AI software and/or hardware algorithmic technology, to determine the QR code or other embedded identification data. In some embodiments, the images and image data can be processed, such as using the mobile device 202 or the online resource provider 212, to identify or classify one or more of the images).
Regarding claim 14, Gogel teaches: A method (FIG. 2 is a block diagram of systems, devices, methods, and computer program products for authorizing access to account-based online resources using image data, according to various embodiments described herein.) of using an artificial intelligence (AI) system to classify documents, the method comprising the steps of:
receiving, at a platform server running the AI system, a file comprising a document (Col. 13, lines 4-25, Once captured, one or more images can be processed to generate image data. The image data can be analyzed, using image processing techniques incorporating AI software and/or hardware algorithmic technology, to determine the QR code or other embedded identification data. In some embodiments, the images and image data can be processed, such as using the mobile device 202 or the online resource provider 212, to identify or classify one or more of the images); detecting whether a barcode is present in the document (col. 13, lines 4-25, The image data can be analyzed, using image processing techniques incorporating AI software and/or hardware algorithmic technology, to determine the QR code);
upon detecting a barcode on the document, decoding the barcode to extract barcode data (Col. 13, lines 4-25, Scanning and processing the QR code reveals the embedded identification data).
Gogel does not explicitly teach: conducting optical character recognition (OCR) on the document to extract text content;
detecting a visual feature present on the document;
detecting a document shape; detecting a shape of the document;
identifying a document candidate based on at least one of (a) the text content and
(b) the visual feature, wherein the document candidate has an expected document shape; determining that the shape of the document matches the expected document shape; and
classifying the document with verification that classification is correct.
However, Vasanth teaches: conducting optical character recognition (OCR) on the document to extract text content ([0034], The document being examined (referred to as the subject document herein) for authenticity is provided as an image. The image may be obtained by one or more of a photograph, a scan, OCR, or other suitable process.);
detecting a visual feature present on the document (fig. 1a, detect logo/faces/hologram);
detecting a document shape ([0036], detect logo, a hologram etc.);
detecting a shape of the document (fig. 1c, step 133, where the invariable attributes may include labels, titles, headers, field names, logos, holograms, seals, or similar features that can be recognized with confidence even if an image is skewed or distorted,);
identifying a document candidate based on at least one of (a) the text content (fig. 1c, steps 134-135, then generating a decision as to which template or templates are most likely to represent the subject document) and
(b) the visual feature, wherein the document candidate has an expected document shape (fig. 2C, accuracy heatmap, [0019], Figure 2(c) is a diagram illustrating an example of a "hear map representing a confidence level in the accuracy of extracted document attributes, and which provides a visual indication of the verification accuracy of regions of a document subjected to processing by an embodiment of the system and methods described herein); determining that the shape of the document matches the expected document shape (fig. 1(c) step 140); and
classifying the document with verification that classification is correct ([0037], Figure 1(b) is a flowchart or flow diagram illustrating an example process, operation, method, or function 120 for authenticating/verifying a document. Access Set of Document Templates and Data Describing Invariable Attributes Associated with Each Template; and Determine Most Likely Document Templates that "Match" Subject Document Based on Invariable Attributes; Fig. 1B).
The motivation for the combination is that Gogel and Vasanth are in the same field of endeavor, namely a document type classification.
Therefore, the Applicant's claimed invention would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Gogel to conducting optical character recognition (OCR) on the document to extract text content;
detecting a visual feature present on the document;
detecting a document shape; detecting a shape of the document;
identifying a document candidate based on at least one of (a) the text content and
(b) the visual feature, wherein the document candidate has an expected document shape; determining that the shape of the document matches the expected document shape; and
classifying the document with verification that classification is correct as taught by Vasanth. The motivation/suggestion would have been to further enhance/improve the document type classification since doing so will allow for authentication/verification of the uploaded document.
Regarding claim 15, Gogel and Vasanth teach: The method of claim 14, further comprising the step of training the AI system to determine whether the shape of the document matches the expected document shape by using a training set comprising documents having known document shapes (Vansanth, [0068]).
Regarding claim 16, Gogel and Vasanth teach: The method of claim 14, further comprising the step of detecting, by the AI system, a first filetype and, based on the first filetype, determining whether to convert the file to a second filetype (Vansanth, [0048], As mentioned, as part of the document authentication/verification processing, a transformation or transformations may be applied, where the transformation may be used to convert the original image of the subject document into a standard format so that it is easier and more accurately represented for further processing).
Regarding claim 17, Gogel and Vasanth teach: The method of claim 14, further comprising the step of making available, by the AI system to a user device, at least a portion of the barcode data after the document has been classified and verified (Gogel, Col. 8, lines 15-35).
Regarding claim 18, Gogel and Vasanth teach: The method of claim 14, further comprising the step of making available, by the AI system to a user device, at least a portion of the barcode data, at least a portion of the text content, and the document type (Gogel, Col. 19, lines 25-50).
Regarding claim 19, Gogel and Vasanth teach: The method of claim 14, wherein the step of detecting the visual feature relies on the AI system being trained to detect visual features using a training set of document having known visual features (Vasanth, fig. 2C, accuracy heatmap, [0019], Figure 2(c) is a diagram illustrating an example of a "hear map representing a confidence level in the accuracy of extracted document attributes, and which provides a visual indication of the verification accuracy of regions of a document subjected to processing by an embodiment of the system and methods described herein).
Regarding claim 20, Gogel and Vasanth teach: The method of claim 14, further comprising the step of detecting and decoding a machine-readable zone (Gogel, Col. 13, lines 4-25, Once captured, one or more images can be processed to generate image data. The image data can be analyzed, using image processing techniques incorporating AI software and/or hardware algorithmic technology, to determine the QR code or other embedded identification data. In some embodiments, the images and image data can be processed, such as using the mobile device 202 or the online resource provider 212, to identify or classify one or more of the images).
Claims 6-13 are rejected under 35 U.S.C. 103 as being unpatentable over Gogel (US 12462063) in view of Rodriguez (US 11755757).
Regarding claim 6, Gogel teaches: A method (FIG. 2 is a block diagram of systems, devices, methods, and computer program products for authorizing access to account-based online resources using image data, according to various embodiments described herein.) of using an artificial intelligence to classify documents (Thus, the mobile device 202 can capture an image displayed in an automatic sign-in interface displayed on a television 206. Furthermore, the mobile device 202 can capture an image displayed on a form or document 208. In some embodiments, the images and image data can be processed, such as using the mobile device 202 or the online resource provider 212, to identify or classify one or more of the images.), the method comprising the steps of:
receiving, at a platform server running the AI system, a file comprising a document (Col. 13, lines 4-25, Once captured, one or more images can be processed to generate image data. The image data can be analyzed, using image processing techniques incorporating AI software and/or hardware algorithmic technology, to determine the QR code or other embedded identification data. In some embodiments, the images and image data can be processed, such as using the mobile device 202 or the online resource provider 212, to identify or classify one or more of the images);
visually identifying that a barcode is present on the document (col. 13, lines 4-25, The image data can be analyzed, using image processing techniques incorporating AI software and/or hardware algorithmic technology, to determine the QR code);
Gogel does not explicitly teach: decoding the barcode to extract barcode data; and
using the barcode data, detecting a document type and verifying the document.
However, Rodriguez teaches: decoding the barcode to extract barcode data (Col. 10, lines 51-52, Data may be extracted from the PDF417 barcode); and
using the barcode data, detecting a document type (Col. 10, lines 48-55, a class to which the identity document belongs may be determined using the extracted data.) and verifying the document (Col. 10, lines 48-66, The identified unique data may be compared against unique data of any authenticated identity document of the determined class and an authenticity score may be calculated based on the comparison. In response to determining the authenticity score satisfies a threshold score, the identity document may be determined to be authentic.).
The motivation for the combination is that Gogel and Rodriguez are in the same field of endeavor, namely a document type classification.
Therefore, the Applicant's claimed invention would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Gogel to include decoding the barcode to extract barcode data; and using the barcode data, detecting a document type and verifying the document as taught by Rodriguez. The motivation/suggestion would have been to further enhance/improve the document type classification since doing so will allow for authentication of the uploaded document.
Regarding claim 7, Gogel and Rogdriguez teach: The method of claim 6, wherein the barcode comprises a matrix type barcode (Gogel, The mobile device 202 can incorporate a camera that is able to scan an image, such as a QR code.).
Regarding claim 8, Gogel and Rogdriguez teach: The method of claim 6, wherein the barcode data comprises text information corresponding to the document type (Rogdriguez, see fig. 8, item 100, It is contemplated by the present disclosure that the unique data is unique to all the identity documents that belong to the same class).
Regarding claim 9, Gogel and Rogdriguez teach: The method of claim 6, further comprising the step of determining document validity using the barcode data (Rogdriguez, see fig. 8 and fig. 9, item 100), Additionally, or alternatively, if it is determined that the identity document does not include the unique data the identity document may be fraudulent and Col. 10, lines 48-66).
Regarding claim 10, Gogel and Rogdriguez teach: The method of claim 6, wherein the step of detecting the document type relies on the AI system being trained to detect the document type using a training set of documents having known document types (Rogdriguez, col. 15, lines 14-25, FIG. 10 is a diagram 106 illustrating an example machine learning algorithm (MLA) 108 for training an example machine learning model (MLM) for use in determining the authenticity of an identity document according to an embodiment of the present disclosure.).
Regarding claim 11, Gogel and Rogdriguez teach: The method of claim 6, wherein the step of visually identifying that a barcode is present on the document relies on the AI system being trained to identify barcodes using a training set of document having known barcodes (Rogdriguez, col. 15, lines 14-25, FIG. 10 is a diagram 106 illustrating an example machine learning algorithm (MLA) 108 for training an example machine learning model (MLM) for use in determining the authenticity of an identity document according to an embodiment of the present disclosure. And fig. 11, In step S1, the software 20b executed by the processor 18 causes the electronic device 10 to capture image data of a PDF417 barcode located on an identity document including textual data and, in step S2, to extract data from the PDF417 barcode.).
Regarding claim 12, Gogel and Rogdriguez teach: The method of claim 6, further comprising the step of making available, by the AI system to a user device (Rodgriguez, user device 10), at least a portion of the barcode data and the document type (Rogdrguez, col. 11, lines 54-66.).
Regarding claim 13, Gogel and Rogdriguez teach: The method of claim 6, further comprising the step of converting the file from a first filetype to a second filetype (Rogdriguez, col. 13, lines 29-35, Although numbers harvested from data included in the identity document are used in the above example, it is contemplated by the present disclosure that the numbers may be from any source other than the identity document and that textual data from the identity document may be converted into numerical data and used.).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ANDREW H LAM whose telephone number is (571)270-7969 and fax number is 571-270-8969. The examiner can normally be reached on 9AM-5PM.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Benny Tieu can be reached on 571-272-7490. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/ANDREW H LAM/
Primary Examiner, Art Unit 2682