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 .
Status of Claims
Claims 1-20 are pending.
Response to Arguments
Applicant’s arguments, see p. 10, filed 2/3/26, with respect to claims 10 and 17 have been fully considered and are persuasive. The claim objections of 11/3/25 have been withdrawn.
Applicant’s arguments, see p. 11, filed 2/3/26, with respect to the specification have been fully considered and are persuasive. The specification objections of 11/3/25 have been withdrawn.
Applicant’s arguments, see p. 11, filed 2/3/26, with respect to the drawings have been fully considered and are persuasive. The drawing objections of 11/3/25 have been withdrawn.
Applicant’s arguments, see p. 11, filed 2/3/26, with respect to claims 3, 10, and 17 have been fully considered and are persuasive. The 35 U.S.C. 112(b) rejections of 11/3/25 have been withdrawn.
Applicant’s arguments, see p. 12, filed 2/3/26, with respect to claims 6, 13, and 14-20 have been fully considered and are persuasive. The 35 U.S.C. 101 rejections of 11/3/25 have been withdrawn.
Applicant's arguments filed 2/3/26 with respect to the 35 U.S.C. 103 rejections have been fully considered but they are not persuasive.
First, Applicant argues, in p. 13-14 of the remarks filed 2/3/26, that the prior art of record Balakrishnan does not expressly disclose the following limitations in claim 1: “based on the similarity score, performing, by the business verification service: a symbol recognition evaluation using a second machine learning model to generate a symbol recognition score; and an optical character recognition (OCR) evaluation to generate an OCR validation.” The Examiner respectfully disagrees. Balakrishnan teaches performing “fraud detection checks to identify possible tampering or alteration of a document” (Para. [0112]) in which “each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document” (Para. [0272]). Balakrishnan also teaches “generating a score, metric or other form of evaluation (such as a heat map) to indicate a level of confidence or accuracy in the authentication or verification of one or more attributes, data or content of the subject document” (Para. [0116]), detecting and verifying objects such as holograms, watermarks, logos etc. against official versions of the same (i.e., certain ID cards and passports have holograms of the faces as a redundancy factor, and these can be checked for similarity against the face photo in a document) (Para. [0266]). Balakrishnan also teaches that methods may be embodied in the form of a trained neural network and CNNs and other machine learning models are used in several parts of the document authentication and verification processes (Paras. [0375-0394]). The Examiner interprets detecting and verifying objects such as holograms, watermarks, and logos, and the score associated with fraud detection of attributes as the symbol recognition score. Additionally, Balakrishnan teaches an OCR evaluation to generate an OCR validation (Para. [0156]: a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Paras. [0162]-[0163]: usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable).
Second, in response to applicant's argument that the references fail to show certain features of the invention, it is noted that the features upon which applicant relies (i.e., the final validity determination is based on the symbol recognition score and the OCR validation) are not recited in the rejected claim(s). Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993). The independent claims recite generating/determining a symbol recognition score, generating/determining an OCR validation, and determining the validity of the license/status of the document based on the symbol recognition score or the OCR validation. Therefore, the claims do not recite that the symbol recognition score is combined with OCR validation to determine document validity.
Examiner’s Note
The claims recite limitations that are claimed in the alternative (i.e., “or”). The Examiner has specified in the claim mapping which limitations have been considered.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 8/12/26 was filed after the mailing date of the Non-Final Office Action on 11/3/25. The submission 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
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 6-8, 13-15, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Balakrishnan et al. (US 2021/0124919 A1; hereinafter “Balakrishnan”).
Regarding claim 6, Balakrishnan teaches, A method comprising (Balakrishnan, Para. [0007]: method for authentication/verification of identification and other documents; Balakrishnan, Para. [0033] and Fig. 4: computer device or system implementing the method):
receiving, at a verification service of a service provider network, an image of a document, wherein the document has a purported document type (Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan, Para. [0010]: “receive an image of a subject document”; Balakrishnan: As shown in Para. [0063], an image is obtained and includes features such as a logo, photo, hologram, and one or more data fields; Balakrishnan, Fig. 1(a); Balakrishnan: As shown in Paras. [0322]-[0324], there is an application service provider (ASP) hosted business service system and users may access the documents using any suitable client, such as computers and smartphones);
evaluating, by the verification service using a first machine learning model, similarity of the image of the document with respect to a database of known valid documents to determine a similarity score, wherein the known valid documents are with respect to the purported document type (Balakrishnan: As shown in Paras. [0121]-[0128], attributes in the document are extracted and compared against attributes of templates, and a score is generated to determine whether the document belongs to the class/document type represented by a given template; Balakrishnan, As shown in Paras. [0375]-[0394]: methods may be embodied in the form of a trained neural network and CNNs and other machine learning models are used in several parts of the document authentication and verification processes);
based at least in part on the similarity score, performing, by the verification service (Balakrishnan: As shown in Paras. [0121]-[0128], attributes in the document are extracted and compared against attributes of templates, and a score is generated to determine whether the document belongs to the class/document type represented by a given template):
a symbol recognition evaluation using a second machine learning model to determine a symbol recognition score (Balakrishnan, Paras. [0082]-[0084]; Balakrishnan, Para. [0112]: “fraud detection checks to identify possible tampering or alteration of a document”; Balakrishnan, Para. [0116]: “Generating a score, metric or other form of evaluation (such as a heat map) to indicate a level of confidence or accuracy in the authentication or verification of one or more attributes, data or content of the subject document”; Balakrishnan, Para. [0135]; Balakrishnan, Para. [0263]; Balakrishnan, Para. [0266]: “Holograms and logos: objects such as holograms, watermarks, logos etc. can be detected and verified against official versions of the same. Certain ID cards and passports have holograms of the faces as a redundancy factor-these can be checked for similarity against the face photo in a document”; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”; Balakrishnan: As shown in Paras. [0375-0394]: methods may be embodied in the form of a trained neural network and CNNs and other machine learning models are used in several parts of the document authentication and verification processes);
and an optical character recognition (OCR) evaluation to determine an OCR validation (Balakrishnan: As shown in Para. [0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable);
and based at least in part on at least one of the symbol recognition score or the OCR validation (Balakrishnan, Paras. [0082]-[0084]; Balakrishnan, Para. [0112]: “fraud detection checks to identify possible tampering or alteration of a document”; Balakrishnan, Para. [0116]: “Generating a score, metric or other form of evaluation (such as a heat map) to indicate a level of confidence or accuracy in the authentication or verification of one or more attributes, data or content of the subject document”; Balakrishnan, Para. [0135]; Balakrishnan, Para. [0263]; Balakrishnan, Para. [0266]: “Holograms and logos: objects such as holograms, watermarks, logos etc. can be detected and verified against official versions of the same. Certain ID cards and passports have holograms of the faces as a redundancy factor-these can be checked for similarity against the face photo in a document”; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”; Balakrishnan: As shown in Paras. [0375-0394]: methods may be embodied in the form of a trained neural network and CNNs and other machine learning models are used in several parts of the document authentication and verification processes; Balakrishnan: As shown in Para. [0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable), determining, by the verification service, a status of the document with respect to the purported document type (Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered; Note: the Examiner interprets indication of potential fraud/validity as the document/license status).
Balakrishnan discloses and teaches the above limitations in different embodiments. It would have been obvious, before the effective filing date of the claimed invention, to one of ordinary skill in the art to combine the embodiments for receiving an image of a document, evaluating the similarity of the image document, performing OCR, and determining the status of the document since the embodiments are directed toward more efficiently and accurately authenticating and verify documents (Balakrishnan, Para. [0005]) and different arrangements and sub-combinations of components/embodiments may be employed (Balakrishnan, Para. [0466]). Therefore, one of ordinary skill in the art would be capable to have combined the embodiments as claimed by known methods, and that in combination, each element merely performs the same function as it does separately. It is for at least the aforementioned reasons that the Examiner has reached a conclusion of obviousness with respect to claim 6.
Regarding claim 7, Balakrishnan teaches the limitations as explained above in claim 6.
Balakrishnan further teaches, The method of claim 6 (see claim 6 above), further comprising: determining that the similarity score meets or exceeds a first threshold (Balakrishnan, Para. [0072]; Balakrishnan, Paras. [0102]-[0105]: a score is generated as a measure of the match of closeness of a match to a template and it is determined whether the score satisfies a threshold value);
performing the symbol recognition evaluation using the second machine learning model (Balakrishnan, Para. [0072]; Balakrishnan, Paras. [0102]-[0105]: a score is generated as a measure of the match of closeness of a match to a template and it is determined whether the score satisfies a threshold value; Balakrishnan, Para. [0135]: “After the subject document has been associated with a template with a sufficient degree of confidence, other aspects of the subject document may be identified/extracted and subject to verification…Additional verification processes, including fraud checks (169) and/or font verification may be performed to further authenticate the subject document and the information it contains”; Balakrishnan, Para. [0157]; Balakrishnan: As shown in Paras. [0247]-[0248], a score is generated which consists of matching attributes detected by a probability P above a threshold value T ; Balakrishnan, Para. [0263]; Balakrishnan, Para. [0266]: “Holograms and logos: objects such as holograms, watermarks, logos etc. can be detected and verified against official versions of the same. Certain ID cards and passports have holograms of the faces as a redundancy factor-these can be checked for similarity against the face photo in a document”; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”; Balakrishnan: As shown in Paras. [0375]-[0394]: methods may be embodied in the form of a trained neural network and CNNs and other machine learning models are used in several parts of the document authentication and verification processes);
determining that the symbol recognition score meets or exceeds a second threshold (Balakrishnan, Para. [0157]; Balakrishnan: As shown in Paras. [0247]-[0248], a score is generated which consists of matching attributes detected by a probability P above a threshold value T ; Balakrishnan, Para. [0263]; Balakrishnan, Para. [0266]: “Holograms and logos: objects such as holograms, watermarks, logos etc. can be detected and verified against official versions of the same. Certain ID cards and passports have holograms of the faces as a redundancy factor-these can be checked for similarity against the face photo in a document…”; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”);
performing the OCR evaluation (Balakrishnan, Para. [0247]; Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan: As shown in Para. [0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”);
determining that the OCR validation meets or exceeds a third threshold (Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan: As shown in Para. [0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable);
and determining that the status of the document is valid with respect to the purported document type (Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered; Note: the Examiner interprets indication of potential fraud/validity as the document/license status).
Regarding claim 8, Balakrishnan teaches the limitations as explained above in claim 7.
Balakrishnan further teaches, The method of claim 7 (see claim 7 above), wherein the document relates to an account at the service provider network and further comprising (Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0322]-[0324], there is an application service provider (ASP) hosted business service system and users may access the documents using any suitable client, such as computers and smartphones):
based at least in part on the status of the document being valid with respect to the purported document type (Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan, As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered), automatically populating a template for the account with information from the document (Balakrishnan: Paras. [0012]-[0020] describe the template identification process, including comparison of attributes/matching, and accessing data associated with the identified template; Balakrishnan: As shown in Para. [0276]-[0277], a template can be created, and the template creation process can be automated; Balakrishnan: As shown in Paras. [0322]-[0324], there is an application service provider (ASP) hosted business service system and users may access the documents using any suitable client, such as computers and smartphones).
Regarding claim 13, Balakrishnan teaches the limitations as explained above in claim 6.
Balakrishnan further teaches, The method of claim 6 (see claim 6 above), wherein the purported document type comprises one of a passport, a driver's license, an identification card, or a tax document (Balakrishnan, Para. [0007]: “Such documents may include identity cards, driver's licenses, passports, documents being used to show a proof of registration or certification, voter ballots, data entry forms, etc.”).
Regarding claim 14, Balakrishnan teaches, One or more non-transitory computer-readable media storing computer-executable instructions that, when executed, cause one or more processors to perform operations comprising (Balakrishnan, Para. [0375]: instructions may be stored in a non-transitory computer-readable medium and executed by a processor):
receiving, at a verification service of a service provider network, an image of a document, wherein the document has a purported document type (Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan, Para. [0010]: “receive an image of a subject document”; Balakrishnan: As shown in Para. [0063], an image is obtained and includes features such as a logo, photo, hologram, and one or more data fields; Balakrishnan, Fig. 1(a); Balakrishnan: As shown in Paras. [0322]-[0324], there is an application service provider (ASP) hosted business service system and users may access the documents using any suitable client, such as computers and smartphones);
evaluating, by the verification service using a first machine learning model, similarity of the image of the document with respect to a database of known valid documents to determine a similarity score, wherein the known valid documents are with respect to the purported document type (Balakrishnan: As shown in Paras. [0121]-[0128], attributes in the document are extracted and compared against attributes of templates, and a score is generated to determine whether the document belongs to the class/document type represented by a given template; Balakrishnan: As shown in Paras. [0375]-[0394]: methods may be embodied in the form of a trained neural network and CNNs and other machine learning models are used in several parts of the document authentication and verification processes);
based at least in part on the similarity score, performing, by the verification service (Balakrishnan: As shown in Paras. [0121]-[0128], attributes in the document are extracted and compared against attributes of templates, and a score is generated to determine whether the document belongs to the class/document type represented by a given template):
a symbol recognition evaluation using a second machine learning model to determine a symbol recognition score (Balakrishnan, Paras. [0082]-[0084]; Balakrishnan, Para. [0112]: “fraud detection checks to identify possible tampering or alteration of a document”; Balakrishnan, Para. [0116]: “Generating a score, metric or other form of evaluation (such as a heat map) to indicate a level of confidence or accuracy in the authentication or verification of one or more attributes, data or content of the subject document”; Balakrishnan, Para. [0135]; Balakrishnan, Para. [0263]; Balakrishnan, Para. [0266]: “Holograms and logos: objects such as holograms, watermarks, logos etc. can be detected and verified against official versions of the same. Certain ID cards and passports have holograms of the faces as a redundancy factor-these can be checked for similarity against the face photo in a document”; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”; Balakrishnan: As shown in Paras. [0375-0394]: methods may be embodied in the form of a trained neural network and CNNs and other machine learning models are used in several parts of the document authentication and verification processes);
and an optical character recognition (OCR) evaluation to determine an OCR validation (Balakrishnan: As shown in Para. [0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable);
and based at least in part on at least one of the symbol recognition score or the OCR validation (Balakrishnan, Paras. [0082]-[0084]; Balakrishnan, Para. [0112]: “fraud detection checks to identify possible tampering or alteration of a document”; Balakrishnan, Para. [0116]: “Generating a score, metric or other form of evaluation (such as a heat map) to indicate a level of confidence or accuracy in the authentication or verification of one or more attributes, data or content of the subject document”; Balakrishnan, Para. [0135]; Balakrishnan, Para. [0263]; Balakrishnan, Para. [0266]: “Holograms and logos: objects such as holograms, watermarks, logos etc. can be detected and verified against official versions of the same. Certain ID cards and passports have holograms of the faces as a redundancy factor-these can be checked for similarity against the face photo in a document”; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”; Balakrishnan: As shown in Paras. [0375-0394]: methods may be embodied in the form of a trained neural network and CNNs and other machine learning models are used in several parts of the document authentication and verification processes; Balakrishnan: As shown in Para. [0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable), determining, by the verification service, a status of the document with respect to the purported document type (Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered; Note: the Examiner interprets indication of potential fraud/validity as the document/license status).
Balakrishnan discloses and teaches the above limitations in different embodiments. It would have been obvious, before the effective filing date of the claimed invention, to one of ordinary skill in the art to combine the embodiments for receiving an image of a document, evaluating the similarity of the image document, performing OCR, and determining the status of the document since the embodiments are directed toward more efficiently and accurately authenticating and verify documents (Balakrishnan, Para. [0005]) and different arrangements and sub-combinations of components/embodiments may be employed (Balakrishnan, Para. [0466]). Therefore, one of ordinary skill in the art would be capable to have combined the embodiments as claimed by known methods, and that in combination, each element merely performs the same function as it does separately. It is for at least the aforementioned reasons that the Examiner has reached a conclusion of obviousness with respect to claim 14.
Regarding claim 15, Balakrishnan teaches the limitations as explained above in claim 14.
Balakrishnan further teaches, The one or more non-transitory computer-readable media of claim 14 (see claim 14 above), wherein the operations further comprise:
determining that the similarity score meets or exceeds a first threshold (Balakrishnan, Paras. [0102]-[0105]: a score is generated as a measure of the match of closeness of a match to a template and it is determined whether the score satisfies a threshold value);
performing the symbol recognition evaluation using the second machine learning model (Balakrishnan, Para. [0072]; Balakrishnan, Paras. [0102]-[0105]: a score is generated as a measure of the match of closeness of a match to a template and it is determined whether the score satisfies a threshold value; Balakrishnan, Para. [0135]: “After the subject document has been associated with a template with a sufficient degree of confidence, other aspects of the subject document may be identified/extracted and subject to verification…Additional verification processes, including fraud checks (169) and/or font verification may be performed to further authenticate the subject document and the information it contains”; Balakrishnan, Para. [0157]; Balakrishnan: As shown in Paras. [0247]-[0248], a score is generated which consists of matching attributes detected by a probability P above a threshold value T ; Balakrishnan, Para. [0263]; Balakrishnan, Para. [0266]: “Holograms and logos: objects such as holograms, watermarks, logos etc. can be detected and verified against official versions of the same. Certain ID cards and passports have holograms of the faces as a redundancy factor-these can be checked for similarity against the face photo in a document”; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”; Balakrishnan: As shown in Paras. [0375]-[0394]: methods may be embodied in the form of a trained neural network and CNNs and other machine learning models are used in several parts of the document authentication and verification processes);
determining that the symbol recognition score meets or exceeds a second threshold (Balakrishnan, Para. [0157]; Balakrishnan: As shown in Paras. [0247]-[0248], a score is generated which consists of matching attributes detected by a probability P above a threshold value T ; Balakrishnan, Para. [0263]; Balakrishnan, Para. [0266]: “Holograms and logos: objects such as holograms, watermarks, logos etc. can be detected and verified against official versions of the same. Certain ID cards and passports have holograms of the faces as a redundancy factor-these can be checked for similarity against the face photo in a document…”; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”);
performing the OCR evaluation (Balakrishnan, Para. [0247]; Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan: As shown in Para. [0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”);
determining that the OCR validation meets or exceeds a third threshold (Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan: As shown in Para. [0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable);
and determining that the status of the document is valid with respect to the purported document type (Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered; Note: the Examiner interprets indication of potential fraud/validity as the document/license status).
Regarding claim 20, Balakrishnan teaches the limitations as explained above in claim 14.
Balakrishnan further teaches, The one or more non-transitory computer-readable media of claim 14 (see claim 14 above), wherein the purported document type comprises one of a passport, a driver's license, an identification card, or a tax document (Balakrishnan, Para. [0007]: “Such documents may include identity cards, driver's licenses, passports, documents being used to show a proof of registration or certification, voter ballots, data entry forms, etc.”).
Claims 1-2, 4, 9, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Balakrishnan et al. (US 2021/0124919 A1; hereinafter “Balakrishnan”) in view of Wang (CN 108053545A, see previously provided machine translation).
Regarding claim 1, Balakrishnan teaches, A computer-implemented method comprising (Balakrishnan, Para. [0007]: method for authentication/verification of identification and other documents; Balakrishnan, Para. [0033] and Fig. 4: computer device or system implementing the method):
receiving, from a user device and at a business verification service of a service provider network, user credentials for an account at the service provider network (Balakrishnan, Para. [0167]: “An administrative console may allow users to securely access the underlying request and response data, manage accounts and access, and in some cases, modify the processing workflow or configuration”; Balakrishnan, Para. [0321]: there is delivery of business-related or other applications and services to multiple accounts/users, and document authentication and verifications services coupled with confirming the validity of the information in the document or the identity of a person presenting an identification document; Balakrishnan: As shown in Paras. [0322-0324], there is an application service provider (ASP) hosted business service system and users may access the documents using any suitable client, such as computers and smartphones; Balakrishnan: As shown in Paras. [0325]-[0327], account management services include a process/service to authenticate a user wishing to submit a document for evaluation; Balakrishnan, Fig. 5; Note: the Examiner interprets the identity of the user to authenticate/access the account as user credentials);
receiving, at the business verification service, an electronic image of a (Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan, Para. [0010]: “receive an image of a subject document”; Balakrishnan: As shown in Para. [0063], an image is obtained and includes features such as a logo, photo, hologram, and one or more data fields; Balakrishnan, Fig. 1(a));
pre-processing, by the business verification service, the electronic image of the Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan, Paras. [0224]-[0226]: pre-processing on the subject documents may include sharpness);
evaluating, by the business verification service using a first machine learning model, similarity of the electronic image of the Balakrishnan: As shown in Paras. [0121]-[0128], attributes in the document are extracted and compared against attributes of templates, and a score is generated to determine whether the document belongs to the class/document type represented by a given template; Balakrishnan: As shown in Paras. [0375]-[0394]: methods may be embodied in the form of a trained neural network and CNNs and other machine learning models are used in several parts of the document authentication and verification processes);
based on the similarity score, performing, by the business verification service (Balakrishnan: As shown in Paras. [0121]-[0128], attributes in the document are extracted and compared against attributes of templates, and a score is generated to determine whether the document belongs to the class/document type represented by a given template):
a symbol recognition evaluation using a second machine learning model to generate a symbol recognition score (Balakrishnan, Paras. [0082]-[0084]; Balakrishnan, Para. [0112]: “fraud detection checks to identify possible tampering or alteration of a document”; Balakrishnan, Para. [0116]: “Generating a score, metric or other form of evaluation (such as a heat map) to indicate a level of confidence or accuracy in the authentication or verification of one or more attributes, data or content of the subject document”; Balakrishnan, Para. [0135]; Balakrishnan, Para. [0263]; Balakrishnan, Para. [0266]: “Holograms and logos: objects such as holograms, watermarks, logos etc. can be detected and verified against official versions of the same. Certain ID cards and passports have holograms of the faces as a redundancy factor-these can be checked for similarity against the face photo in a document”; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”; Balakrishnan: As shown in Paras. [0375]-[0394]: methods may be embodied in the form of a trained neural network and CNNs and other machine learning models are used in several parts of the document authentication and verification processes);
and an optical character recognition (OCR) evaluation to generate an OCR validation (Balakrishnan: As shown in [Para. 0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable);
and based on at least one of the symbol recognition score or the OCR validation (Balakrishnan, Paras. [0082]-[0084]; Balakrishnan, Para. [0112]: “fraud detection checks to identify possible tampering or alteration of a document”; Balakrishnan, Para. [0116]: “Generating a score, metric or other form of evaluation (such as a heat map) to indicate a level of confidence or accuracy in the authentication or verification of one or more attributes, data or content of the subject document”; Balakrishnan, Para. [0135]; Balakrishnan, Para. [0263]; Balakrishnan, Para. [0266]: “Holograms and logos: objects such as holograms, watermarks, logos etc. can be detected and verified against official versions of the same. Certain ID cards and passports have holograms of the faces as a redundancy factor-these can be checked for similarity against the face photo in a document”; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”; Balakrishnan: As shown in Paras. [0375]-[0394]: methods may be embodied in the form of a trained neural network and CNNs and other machine learning models are used in several parts of the document authentication and verification processes; Balakrishnan: As shown in Para. [0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable), determining, by the business verification service, that (i) the Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered; Note: the Examiner selected limitation (i). The Examiner interprets indication of potential fraud as the document/license being non-likely valid. The Examiner also interprets the information in the license, etc. being determined as valid as the license being valid).
Balakrishnan does not expressly disclose the following limitation: business license; business licenses.
However, Wang teaches, business license (Wang, Para. [0035]: documents include business licenses; Wang, Paras. [0046]-[0047]);
business licenses (Wang, Para. [0035]: documents include business licenses; Wang, Paras. [0046]-[0047]).
It would have been obvious, before the effective filing date of the claim invention, to one of ordinary skill in the art to combine licenses being business licenses as taught by Wang with the verification/authentication of Balakrishnan in order to increase the accuracy rate of verification and lower labor cost of verification (Wang, Abstract). Therefore, one of ordinary skill in the art would be capable to have combined the elements as claimed by known methods, and that in combination, each element merely performs the same function as it does separately. It is for at least the aforementioned that the Examiner has reached a conclusion of obviousness with respect to claim 1.
Regarding claim 2, the combination of Balakrishnan and Wang teaches the limitations as explained above in claim 1.
The combination of Balakrishnan and Wang further teaches, The computer-implemented method of claim 1 (see claim 1 above), further comprising: determining that the similarity score meets or exceeds a first threshold value (Balakrishnan, Para. [0072]; Balakrishnan, Paras. [0102]-[0105]: a score is generated as a measure of the match of closeness of a match to a template and it is determined whether the score satisfies a threshold value);
performing, based on the similarity score meeting or exceeding the first threshold value, the symbol recognition evaluation using the second machine learning model (Balakrishnan, Para. [0072]; Balakrishnan, Paras. [0102]-[0105]: a score is generated as a measure of the match of closeness of a match to a template and it is determined whether the score satisfies a threshold value; Balakrishnan, Para. [0135]: “After the subject document has been associated with a template with a sufficient degree of confidence, other aspects of the subject document may be identified/extracted and subject to verification…Additional verification processes, including fraud checks (169) and/or font verification may be performed to further authenticate the subject document and the information it contains”; Balakrishnan, Para. [0157]; Balakrishnan: As shown in Paras. [0247]-[0248], a score is generated which consists of matching attributes detected by a probability P above a threshold value T ; Balakrishnan, Para. [0263]; Balakrishnan, Para. [0266]: “Holograms and logos: objects such as holograms, watermarks, logos etc. can be detected and verified against official versions of the same. Certain ID cards and passports have holograms of the faces as a redundancy factor-these can be checked for similarity against the face photo in a document”; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”; Balakrishnan: As shown in Paras. [0375]-[0394]: methods may be embodied in the form of a trained neural network and CNNs and other machine learning models are used in several parts of the document authentication and verification processes);
determining that the symbol recognition score meets or exceeds a second threshold value (Balakrishnan, Para. [0157]; Balakrishnan: As shown in Paras. [0247]-[0248], a score is generated which consists of matching attributes detected by a probability P above a threshold value T ; Balakrishnan, Para. [0263]; Balakrishnan, Para. [0266]: “Holograms and logos: objects such as holograms, watermarks, logos etc. can be detected and verified against official versions of the same. Certain ID cards and passports have holograms of the faces as a redundancy factor-these can be checked for similarity against the face photo in a document…”; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”);
performing, based on the symbol recognition score meeting or exceeding the second threshold value, the OCR evaluation (Balakrishnan, Para. [0247]; Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan: As shown in Para. [0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”);
determining that the OCR validation meets or exceeds a third threshold value (Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan: As shown in Para. [0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable);
and determining, based on the OCR validation meeting or exceeding the third threshold value, that the business license is the valid business license (Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan, Para. 0007: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered; Note: the Examiner interprets the information in the license, etc. being determined as valid as the license being valid; Wang, Para. [0035]: documents include business licenses; Wang, Paras. [0046]-[0047]).
The proposed combination as well as the motivation for combining the Balakrishnan and Wang references presented in the rejection of claim 1 apply to claim 2 and are incorporated herein by reference. Thus, the method recited in claim 2 is met by Balakrishnan and Wang.
Regarding claim 4, the combination of Balakrishnan and Wang teaches the limitations as explained above in claim 1.
The combination of Balakrishnan and Wang further teaches, The computer-implemented method of claim 1 (see claim 1 above), further comprising: determining that the similarity score is less than a first threshold value (Balakrishnan, Paras. [0252]-[0253]: the document attributes are matched to determine if there is a match to the template, and a document that scores below the threshold score may be considered to not match the template);
performing, based on the similarity score being less than the first threshold value, the OCR evaluation (Balakrishnan Paras. [0252]-[0255]: the document attributes are matched to determine if there is a match to the template, and a document that scores below the threshold score may be considered to not match the template. Template specific detections, checks, fraud checks may be done to provide additional attributes and re-score the document; Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan: As shown in Para. [0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable);
determining that the OCR validation is less than a second threshold value (Balakrishnan, Para. [0249]: OCR text has a specific threshold value to be considered accurate detection; Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered; Note: the Examiner interprets the unreliable results/score not satisfying the threshold as validation being less than a threshold);
determining, based on the OCR validation being less than the second threshold value, that the business license does not correspond to the actual business license (Note: the Examiner did not previously select the actual business license limitation and therefore this limitation is not considered);
and transmitting, to the user device, an indication that the electronic image of the business license does not correspond to the actual business license (Note: the Examiner did not previously select the actual business license limitation and therefore this limitation is not considered).
Regarding claim 9, Balakrishnan teaches the limitations as explained above in claim 8.
Balakrishnan does not expressly disclose the following limitation: wherein the document is a business license.
However, Wang teaches, wherein the document is a business license (Wang, Para. [0035]: documents include business licenses; Wang, Paras. [0046]-[0047]).
It would have been obvious, before the effective filing date of the claim invention, to one of ordinary skill in the art to combine licenses being business licenses as taught by Wang with the verification/authentication of Balakrishnan in order to increase the accuracy rate of verification and lower labor cost of verification (Wang, Abstract). Therefore, one of ordinary skill in the art would be capable to have combined the elements as claimed by known methods, and that in combination, each element merely performs the same function as it does separately. It is for at least the aforementioned that the Examiner has reached a conclusion of obviousness with respect to claim 9.
Regarding claim 16, Balakrishnan teaches the limitations as explained above in claim 14.
Balakrishnan further teaches, The one or more non-transitory computer-readable media of claim 14 (see claim 14 above), wherein the document is a Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification), wherein the Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0322]-[0324], there is an application service provider (ASP) hosted business service system and users may access the documents using any suitable client, such as computers and smartphones):
based at least in part on the status of the document being valid with respect to the purported document type (Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; As shown in Paras. 0366-0370, fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered), automatically populating a template for the account with information from the document (Balakrishnan, Paras. [0012]-[0020] describe the template identification process, including comparison of attributes/matching, and accessing data associated with the identified template; Balakrishnan: As shown in Para. [0276]-[0277], a template can be created, and the template creation process can be automated; Balakrishnan: As shown in Paras. [0322]-[0324], there is an application service provider (ASP) hosted business service system and users may access the documents using any suitable client, such as computers and smartphones).
Balakrishnan does not expressly disclose the following limitation: a business license.
However, Wang teaches, a business license (Wang, Para. [0035]: documents include business licenses; Wang, Paras. [0046]-[0047]).
It would have been obvious, before the effective filing date of the claim invention, to one of ordinary skill in the art to combine licenses being business licenses as taught by Wang with the verification/authentication of Balakrishnan in order to increase the accuracy rate of verification and lower labor cost of verification (Wang, Abstract). Therefore, one of ordinary skill in the art would be capable to have combined the elements as claimed by known methods, and that in combination, each element merely performs the same function as it does separately. It is for at least the aforementioned that the Examiner has reached a conclusion of obviousness with respect to claim 16.
Claims 3 and 5 are rejected under 35 U.S.C. 103 as being unpatentable over Balakrishnan et al. (US 2021/0124919 A1; hereinafter “Balakrishnan”) in view of Wang (CN 108053545A, see provided machine translation) and further in view of Shaevel et al. (US 2021/0233075 A1; hereinafter “Shaevel”).
Regarding claim 3, the combination of Balakrishnan and Wang teaches the limitations as explained above in claim 1.
The combination of Balakrishnan and Wang further teaches, The computer-implemented method of claim 1 (see claim 1 above), further comprising: determining that the similarity score meets or exceeds a first threshold value (Balakrishnan, Para. [0072]; Balakrishnan, Paras. [0102]-[0105]: a score is generated as a measure of the match of closeness of a match to a template and it is determined whether the score satisfies a threshold value);
performing, based on the similarity score meeting or exceeding the first threshold value, the symbol recognition evaluation using the second machine learning model (Balakrishnan, Para. [0072]; Balakrishnan, Paras. [0102]-[0105]: a score is generated as a measure of the match of closeness of a match to a template and it is determined whether the score satisfies a threshold value; Balakrishnan, Para. [0135]: “After the subject document has been associated with a template with a sufficient degree of confidence, other aspects of the subject document may be identified/extracted and subject to verification…Additional verification processes, including fraud checks (169) and/or font verification may be performed to further authenticate the subject document and the information it contains”; Balakrishnan, Para. [0157]; Balakrishnan: As shown in Paras. [0247]-[0248], a score is generated which consists of matching attributes detected by a probability P above a threshold value T ; Balakrishnan, Para. [0263]; Balakrishnan, Para. [0266]: “Holograms and logos: objects such as holograms, watermarks, logos etc. can be detected and verified against official versions of the same. Certain ID cards and passports have holograms of the faces as a redundancy factor-these can be checked for similarity against the face photo in a document”; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”; Balakrishnan: As shown in Paras. [0375]-[0394]: methods may be embodied in the form of a trained neural network and CNNs and other machine learning models are used in several parts of the document authentication and verification processes);
performing the OCR evaluation (Balakrishnan, Para. [0247]; Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan: As shown in Para. [0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”);
one of: based on a first determination that the symbol recognition score is less than a second threshold value and that the OCR validation meets or exceeds a third threshold value, determining that the business license is the likely valid business license (Balakrishnan, Para. [0248]; Balakrishnan, [0249]: OCR text has a specific threshold value to be considered accurate detection; Balakrishnan, Para. [0105]: “If the generated score does not satisfy the threshold value, then re-evaluating the subject document (rescoring) using one or more of additional invariable attributes, inspection of the subject document by a person, or use of a different methodology to determine the correct document type”; Balakrishnan, Para. [0118]; Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered; Note: the Examiner interprets the information in the license, etc. being determined as valid/sufficient as the license being valid; Wang, Para. [0035]: documents include business licenses; Wang, Paras. [0046]-[0047]);
or based on a second determination that the symbol recognition score is less than the second threshold value and that the OCR validation is less than the third threshold value, determining that the business license is the non-likely valid business license (Balakrishnan, Para. [0248]; Balakrishnan, [0249]: OCR text has a specific threshold value to be considered accurate detection; Balakrishnan, Para. [0105]: “If the generated score does not satisfy the threshold value, then re-evaluating the subject document (rescoring) using one or more of additional invariable attributes, inspection of the subject document by a person, or use of a different methodology to determine the correct document type”; Balakrishnan, Para. [0118]; Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered; Note: the Examiner interprets indication of potential fraud/the score being insufficient as the document/license being non-likely valid; Wang, Para. [0035]: documents include business licenses; Wang, Paras. [0046]-[0047]);
and transmitting, to the user device, an Balakrishnan, Para. [0139]: the further review process may include human visual inspection; Balakrishnan, Para. [0239]: attributes may be manually verified to finalize the set of document/template attributes; Balakrishnan, Para. [0240]: there are attributes considered as “further review” attributes; Balakrishnan, Para. [0322]: user may access the document processing services using computers and smartphones; Wang, Para. [0035]: documents include business licenses; Wang, Paras. [0046]-[0047]).
The proposed combination as well as the motivation for combining the Balakrishnan and Wang references presented in the rejection of claim 1 apply to claim 3 and are incorporated herein by reference.
The combination of Balakrishnan and Wang does not expressly disclose the following limitation: an indication.
However, Shaevel teaches, an indication (Shaevel, Para. [0043]: a user is notified to review the electronic documents).
It would have been obvious, before the effective filing date of the claim invention, to one of ordinary skill in the art to combine a user being informed/receiving an indication to review a document as taught by Shaevel with the combined verification/authentication of Balakrishnan and Wang in order to ensure accuracy and validity of transactions (Shaevel, Abstract). Therefore, one of ordinary skill in the art would be capable to have combined the elements as claimed by known methods, and that in combination, each element merely performs the same function as it does separately. It is for at least the aforementioned that the Examiner has reached a conclusion of obviousness with respect to claim 3.
Regarding claim 5, the combination of Balakrishnan and Wang teaches the limitations as explained above in claim 1.
The combination of Balakrishnan and Wang further teaches, The computer-implemented method of claim 1 (see claim 1 above), further comprising: determining that the similarity score is less than a first threshold value (Balakrishnan, Paras. [0252]-[0253]: the document attributes are matched to determine if there is a match to the template, and a document that scores below the threshold score may be considered to not match the template);
performing, based on the similarity score being less than the first threshold value, the OCR evaluation (Balakrishnan, Paras. [0252]-[0255]: the document attributes are matched to determine if there is a match to the template, and a document that scores below the threshold score may be considered to not match the template. Template specific detections, checks, fraud checks may be done to provide additional attributes and re-score the document; Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan: As shown in Para. [0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable);
determining that the OCR validation meets or exceeds a second threshold value (Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered);
determining, based on the OCR validation meeting or exceeding the second threshold value, that the business license is the likely valid business license (Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered; Note: the Examiner interprets the information in the license, etc. being determined as valid/sufficient as the license being valid; Wang, Para. [0035]: documents include business licenses; Wang, Paras. [0046]-[0047]);
and transmitting, to the user device, an Balakrishnan, Para. [0139]: the further review process may include human visual inspection; Balakrishnan, Para. [0239]: attributes may be manually verified to finalize the set of document/template attributes; Balakrishnan, Para. [0240]: there are attributes considered as “further review” attributes; Balakrishnan, Para. [0322]: user may access the document processing services using computers and smartphones; Wang, Para. [0035]: documents include business licenses; Wang, Paras. [0046]-[0047]).
The proposed combination as well as the motivation for combining the Balakrishnan and Wang references presented in the rejection of claim 1 apply to claim 5 and are incorporated herein by reference.
The combination of Balakrishnan and Wang does not expressly disclose the following limitation: an indication.
However, Shaevel teaches, an indication (Shaevel, Para. 0043: a user is notified to review the electronic documents).
It would have been obvious, before the effective filing date of the claim invention, to one of ordinary skill in the art to combine a user being informed/receiving an indication to review a document as taught by Shaevel with the combined verification/authentication of Balakrishnan and Wang in order to ensure accuracy and validity of transactions (Shaevel, Abstract). Therefore, one of ordinary skill in the art would be capable to have combined the elements as claimed by known methods, and that in combination, each element merely performs the same function as it does separately. It is for at least the aforementioned that the Examiner has reached a conclusion of obviousness with respect to claim 5.
Claims 10, 12, 17, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Balakrishnan et al. (US 2021/0124919 A1; hereinafter “Balakrishnan”) in view of Shaevel et al. (US 2021/0233075 A1; hereinafter “Shaevel”).
Regarding claim 10, Balakrishnan teaches the limitations as explained above in claim 6.
Balakrishnan further teaches, The method of claim 6 (see claim 6 above), further comprising: determining that the similarity score meets or exceeds a first threshold (Balakrishnan, Paras. [0102]-[0105]: a score is generated as a measure of the match of closeness of a match to a template and it is determined whether the score satisfies a threshold value);
performing the symbol recognition evaluation using the second machine learning model (Balakrishnan, Para. [0072]; Balakrishnan, Paras. [0102]-[0105]: a score is generated as a measure of the match of closeness of a match to a template and it is determined whether the score satisfies a threshold value; Balakrishnan, Para. [0135]: “After the subject document has been associated with a template with a sufficient degree of confidence, other aspects of the subject document may be identified/extracted and subject to verification…Additional verification processes, including fraud checks (169) and/or font verification may be performed to further authenticate the subject document and the information it contains”; Balakrishnan, Para. [0157]; Balakrishnan: As shown in Paras. [0247]-[0248], a score is generated which consists of matching attributes detected by a probability P above a threshold value T ; Balakrishnan, Para. [0263]; Balakrishnan, Para. [0266]: “Holograms and logos: objects such as holograms, watermarks, logos etc. can be detected and verified against official versions of the same. Certain ID cards and passports have holograms of the faces as a redundancy factor-these can be checked for similarity against the face photo in a document”; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”; Balakrishnan: As shown in Paras. [0375]-[0394]: methods may be embodied in the form of a trained neural network and CNNs and other machine learning models are used in several parts of the document authentication and verification processes);
performing the OCR evaluation (Balakrishnan, Para. [0247]; Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan: As shown in Para. [0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”);
one of: based at least in part on a first determination that the symbol recognition score is below a second threshold and that the OCR validation meets or exceeds a third threshold, determining that the status of the document is likely valid with respect to the purported document type (Balakrishnan, Para. [0248]; Balakrishnan, [0249]: OCR text has a specific threshold value to be considered accurate detection; Balakrishnan, Para. [0105]: “If the generated score does not satisfy the threshold value, then re-evaluating the subject document (rescoring) using one or more of additional invariable attributes, inspection of the subject document by a person, or use of a different methodology to determine the correct document type”; Balakrishnan, Para. [0118]; Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered; Note: the Examiner interprets the information in the license, etc. being determined as valid/sufficient as the license being valid);
or based at least in part on a second determination that the symbol recognition score is below the second threshold and that the OCR validation is below the third threshold, determining that the status of the document is likely non-valid with respect to the purported document type (Balakrishnan, Para. [0248]; Balakrishnan, [0249]: OCR text has a specific threshold value to be considered accurate detection; Balakrishnan, Para. [0105]: “If the generated score does not satisfy the threshold value, then re-evaluating the subject document (rescoring) using one or more of additional invariable attributes, inspection of the subject document by a person, or use of a different methodology to determine the correct document type”; Balakrishnan, Para. [0118]; Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered; Note: the Examiner interprets indication of potential fraud/the score being insufficient as the document/license being non-likely valid);
and Balakrishnan, Para. [0139]: the further review process may include human visual inspection; Balakrishnan, Para. [0239]: attributes may be manually verified to finalize the set of document/template attributes; Balakrishnan, Para. [0240]: there are attributes considered as “further review” attributes; Balakrishnan, Para. [0322]: user may access the document processing services using computers and smartphones).
Balakrishnan does not expressly disclose the following limitation: informing a user.
However, Shaevel teaches, informing a user (Shaevel, Para. [0043]: a user is notified to review the electronic documents).
It would have been obvious, before the effective filing date of the claim invention, to one of ordinary skill in the art to combine a user being informed to review a document as taught by Shaevel with the verification/authentication of Balakrishnan in order to ensure accuracy and validity of transactions (Shaevel, Abstract). Therefore, one of ordinary skill in the art would be capable to have combined the elements as claimed by known methods, and that in combination, each element merely performs the same function as it does separately. It is for at least the aforementioned that the Examiner has reached a conclusion of obviousness with respect to claim 10.
Regarding claim 12, Balakrishnan teaches the limitations as explained above in claim 6.
Balakrishnan further teaches, The method of claim 6 (see claim 6 above), The method of claim 6, further comprising: determining that the similarity score is below a first threshold (Balakrishnan, Paras. [0252]-[0253]: the document attributes are matched to determine if there is a match to the template, and a document that scores below the threshold score may be considered to not match the template);
performing the OCR evaluation (Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan: As shown in Para. [0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable);
determining that the OCR validation meets or exceeds a second threshold (Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan: As shown in Para. [0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable);
determining that the status of the document is likely valid with respect to the purported document type (Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered; Note: the Examiner interprets indication of potential fraud/validity as the document/license status);
and Balakrishnan, Para. [0139]: the further review process may include human visual inspection; Balakrishnan, Para. [0239]: attributes may be manually verified to finalize the set of document/template attributes; Balakrishnan, Para. [0240]: there are attributes considered as “further review” attributes; Balakrishnan, Para. [0322]: user may access the document processing services using computers and smartphones).
Balakrishnan does not expressly disclose the following limitation: informing a user.
However, Shaevel teaches, informing a user (Shaevel, Para. [0043]: a user is notified to review the electronic documents).
It would have been obvious, before the effective filing date of the claim invention, to one of ordinary skill in the art to combine a user being informed to review a document as taught by Shaevel with the verification/authentication of Balakrishnan in order to ensure accuracy and validity of transactions (Shaevel, Abstract). Therefore, one of ordinary skill in the art would be capable to have combined the elements as claimed by known methods, and that in combination, each element merely performs the same function as it does separately. It is for at least the aforementioned that the Examiner has reached a conclusion of obviousness with respect to claim 12.
Regarding claim 17, Balakrishnan teaches, The one or more non-transitory computer-readable media of claim 14 (see claim 14 above), wherein the operations further comprise: determining that the similarity score meets or exceeds a first threshold (Balakrishnan, Paras. [0102]-[0105]: a score is generated as a measure of the match of closeness of a match to a template and it is determined whether the score satisfies a threshold value);
performing the symbol recognition evaluation using the second machine learning model (Balakrishnan, Para. [0072]; Balakrishnan, Paras. [0102]-[0105]: a score is generated as a measure of the match of closeness of a match to a template and it is determined whether the score satisfies a threshold value; Balakrishnan, Para. [0135]: “After the subject document has been associated with a template with a sufficient degree of confidence, other aspects of the subject document may be identified/extracted and subject to verification…Additional verification processes, including fraud checks (169) and/or font verification may be performed to further authenticate the subject document and the information it contains”; Balakrishnan, Para. [0157]; Balakrishnan: As shown in Paras. [0247]-[0248], a score is generated which consists of matching attributes detected by a probability P above a threshold value T ; Balakrishnan, Para. [0263]; Balakrishnan, Para. [0266]: “Holograms and logos: objects such as holograms, watermarks, logos etc. can be detected and verified against official versions of the same. Certain ID cards and passports have holograms of the faces as a redundancy factor-these can be checked for similarity against the face photo in a document”; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”; Balakrishnan: As shown in Paras. [0375]-[0394]: methods may be embodied in the form of a trained neural network and CNNs and other machine learning models are used in several parts of the document authentication and verification processes);
performing the OCR evaluation (Balakrishnan, Para. [0247]; Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan: As shown in Para. [0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable; Balakrishnan, Para. [0272]: “Each of the fraud scenarios can be associated with a score, with the scores combined to generate an overall score or evaluation for a subject document…”);
one of: based at least in part on a first determination that the symbol recognition score is below a second threshold and that the OCR validation meets or exceeds a third threshold, determining that the status of the document is likely valid with respect to the purported document type (Balakrishnan, Para. [0248]; Balakrishnan, [0249]: OCR text has a specific threshold value to be considered accurate detection; Balakrishnan, Para. [0105]: “If the generated score does not satisfy the threshold value, then re-evaluating the subject document (rescoring) using one or more of additional invariable attributes, inspection of the subject document by a person, or use of a different methodology to determine the correct document type”; Balakrishnan, Para. [0118]; Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered; Note: the Examiner interprets the information in the license, etc. being determined as valid/sufficient as the license being valid);
or based at least in part on a second determination that the symbol recognition score is below the second threshold and that the OCR validation is below the third threshold, determining that the status of the document is likely non-valid with respect to the purported document type (Balakrishnan, Para. [0248]; Balakrishnan, [0249]: OCR text has a specific threshold value to be considered accurate detection; Balakrishnan, Para. [0105]: “If the generated score does not satisfy the threshold value, then re-evaluating the subject document (rescoring) using one or more of additional invariable attributes, inspection of the subject document by a person, or use of a different methodology to determine the correct document type”; Balakrishnan, Para. [0118]; Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered; Note: the Examiner interprets indication of potential fraud/the score being insufficient as the document/license being non-likely valid);
and Balakrishnan, Para. [0139]: the further review process may include human visual inspection; Balakrishnan, Para. [0239]: attributes may be manually verified to finalize the set of document/template attributes; Balakrishnan, Para. [0240]: there are attributes considered as “further review” attributes; Balakrishnan, Para. [0322]: user may access the document processing services using computers and smartphones).
Balakrishnan does not expressly disclose the following limitation: informing a user.
However, Shaevel teaches informing a user (Shaevel, Para. [0043]: a user is notified to review the electronic documents).
It would have been obvious, before the effective filing date of the claim invention, to one of ordinary skill in the art to combine a user being informed to review a document as taught by Shaevel with the verification/authentication of Balakrishnan in order to ensure accuracy and validity of transactions (Shaevel, Abstract). Therefore, one of ordinary skill in the art would be capable to have combined the elements as claimed by known methods, and that in combination, each element merely performs the same function as it does separately. It is for at least the aforementioned that the Examiner has reached a conclusion of obviousness with respect to claim 17.
Regarding claim 19, Balakrishnan teaches the limitations as explained above in claim 14.
Balakrishnan further teaches, The one or more non-transitory computer readable media of claim 14 (see claim 14 above), wherein the operations further comprise: determining that the similarity score is below a first threshold (Balakrishnan, Paras. [0252]-[0253]: the document attributes are matched to determine if there is a match to the template, and a document that scores below the threshold score may be considered to not match the template);
performing the OCR evaluation (Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan: As shown in Para. [0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable);
determining that the OCR validation meets or exceeds a second threshold (Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan: As shown in Para. [0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable);
determining that the status of the document is likely valid with respect to the purported document type (Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered; Note: the Examiner interprets indication of potential fraud/validity as the document/license status);
and Balakrishnan, Para. [0139]: the further review process may include human visual inspection; Balakrishnan, Para. [0239]: attributes may be manually verified to finalize the set of document/template attributes; Balakrishnan, Para. [0240]: there are attributes considered as “further review” attributes; Balakrishnan, Para. [0322]: user may access the document processing services using computers and smartphones).
Balakrishnan does not expressly disclose the following limitation: informing a user.
However, Shaevel teaches, informing a user (Shaevel, Para. [0043]: a user is notified to review the electronic documents).
It would have been obvious, before the effective filing date of the claim invention, to one of ordinary skill in the art to combine a user being informed to review a document as taught by Shaevel with the verification/authentication of Balakrishnan in order to ensure accuracy and validity of transactions (Shaevel, Abstract). Therefore, one of ordinary skill in the art would be capable to have combined the elements as claimed by known methods, and that in combination, each element merely performs the same function as it does separately. It is for at least the aforementioned that the Examiner has reached a conclusion of obviousness with respect to claim 19.
Claims 11 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Balakrishnan et al. (US 2021/0124919 A1; hereinafter “Balakrishnan”) in view of Sakuma (JP 2019057083A, see previously provided machine translation).
Regarding claim 11, Balakrishnan teaches the limitations as explained above in claim 6.
Balakrishnan further teaches, The method of claim 6 (see claim 6 above), further comprising: determining that the similarity score is below a first threshold (Balakrishnan, Paras. [0252]-[0253]: the document attributes are matched to determine if there is a match to the template, and a document that scores below the threshold score may be considered to not match the template);
performing the OCR evaluation (Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan: As shown in Para. [0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable);
determining that the OCR validation is below a second threshold (Balakrishnan, Para. [0249]: OCR text has a specific threshold value to be considered accurate detection; Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered; Note: the Examiner interprets the unreliable results/score not satisfying the threshold as validation being less than a threshold);
determining that the status of the document is non-valid with respect to the purported document type (Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered; Note: the Examiner interprets indication of potential fraud/the score being insufficient as the document/license being non-valid);
and Balakrishnan: As shown in Para. 0272, fraud attempts or a fake document may cause rejection of the document; Balakrishnan: As shown in Paras. 0311, the fraud detection process includes rejecting the document if unable to be verified or authenticated due to the score not satisfying the threshold; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered).
Balakrishnan does not expressly disclose the following limitation: informing a user.
However, Sakuma teaches, informing a user (Sakuma, Para. [0021]: if the electronic certificate is invalid, then the financial institution server transmits the defect notification data to the customer terminal; Sakuma, Para. [0031]).
It would have been obvious, before the effective filing date of the claim invention, to one of ordinary skill in the art to combine a user being informed/notified that a document is invalid as taught by Sakuma with the verification/authentication of Balakrishnan in order to perform personal identification by an electronic signature and immediately notify a customer when opening an account (Sakuma, Para. [0001]). Therefore, one of ordinary skill in the art would be capable to have combined the elements as claimed by known methods, and that in combination, each element merely performs the same function as it does separately. It is for at least the aforementioned that the Examiner has reached a conclusion of obviousness with respect to claim 11.
Regarding claim 18, Balakrishnan teaches the limitations as explained above in claim 14.
Balakrishnan further teaches, The one or more non-transitory computer-readable media of claim 14 (see claim 14 above), wherein the operations further comprise: determining that the similarity score is below a first threshold (Balakrishnan, Paras. [0252]-[0253]: the document attributes are matched to determine if there is a match to the template, and a document that scores below the threshold score may be considered to not match the template);
performing the OCR evaluation (Balakrishnan, Paras. [0248]-[0249]: matching attributes are detected by a probability P above a certain threshold value T, and OCR text has a specific threshold value to be considered accurate detection; Balakrishnan: As shown in Para. [0156], a set of documents believed to be the same type of category are selected and the OCR results and search process are used to fit a set of passible fonts to each attribute; Balakrishnan: As shown in Para. [0162]-[0163], usable attribute values are extracted from OCR processing and it is also detected if OCR results are unreliable);
determining that the OCR validation is below a second threshold (Balakrishnan, Para. [0249]: OCR text has a specific threshold value to be considered accurate detection; Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered; Note: the Examiner interprets the unreliable results/score not satisfying the threshold as validation being less than a threshold);
determining that the status of the document is non-valid with respect to the purported document type (Balakrishnan, Para. [0007]: documents authenticated/verified include licenses and proof or registration or certification; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered; Note: the Examiner interprets indication of potential fraud/the score being insufficient as the document/license being non-valid);
and ; Balakrishnan: As shown in Para. [0272], fraud attempts or a fake document may cause rejection of the document; Balakrishnan: As shown in Paras. [0311], the fraud detection process includes rejecting the document if unable to be verified or authenticated due to the score not satisfying the threshold; Balakrishnan: As shown in Paras. [0162]-[0165], usable attribute values are extracted from OCR processing of document images, OCR results that are unreliable are detected, and potential fraud is indicated by ensuring the correct appearance of attribute values; Balakrishnan: As shown in Paras. [0366]-[0370], fraud detection is performed in which information is confirmed/validated. If the score doesn’t satisfy the threshold, then it is rejected; Balakrishnan: As shown in Fig. 1(c), steps 144-147, fraud detection is performed. If the score is sufficient, then the document is accepted and the information it contains is valid. If the score is insufficient, then other attributes are considered).
Balakrishnan does not expressly disclose the following limitation: informing a user.
However, Sakuma teaches, informing a user (Sakuma, Para. [0021]: if the electronic certificate is invalid, then the financial institution server transmits the defect notification data to the customer terminal; Sakuma, Para. [0031]).
It would have been obvious, before the effective filing date of the claim invention, to one of ordinary skill in the art to combine a user being informed/notified that a document is invalid as taught by Sakuma with the verification/authentication of Balakrishnan in order to perform personal identification by an electronic signature and immediately notify a customer when opening an account (Sakuma, Para. [0001]). Therefore, one of ordinary skill in the art would be capable to have combined the elements as claimed by known methods, and that in combination, each element merely performs the same function as it does separately. It is for at least the aforementioned that the Examiner has reached a conclusion of obviousness with respect to claim 18.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Mohiuddin Khan et al. (US 2019/0303447 A1)
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Daniella M. DiGuglielmo whose telephone number is (571)272-0183. The examiner can normally be reached Monday - Friday 8:00 AM - 4:00 PM.
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, Emily Terrell can be reached at (571)270-3717. 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.
/Daniella M. DiGuglielmo/Examiner, Art Unit 2666
/EMILY C TERRELL/Supervisory Patent Examiner, Art Unit 2666
Prosecution Insights