DETAILED ACTION
Claims 1-20 are pending in this application.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 06/14/2023 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitations are:
Data processing system in claims 11 and 12.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
4. Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Odate (US 20190286692 A1) in view of Wheaton (US 20220392047 A1).
Regarding claim 1 Odate discloses; A method, in a data processing system, for automated document image annotation and data extraction, the method comprising:
processing a received document image to identify a document type of the received document image (Odate, [0050] a scanned image of the document is received by the application);
retrieving a corresponding document template data structure for the identified document type of the received document image from a document template repository having document templates for a plurality of document types (Odate [0086]-[0088] the system stores templates based on the document format (multiple templates associated with multiple identified types/formats of documents), where [0118] the document undergoes a recognition process, and [0119] the document read result is scored against each template option and [0124] then a template is selected from the plurality of templates based on the scored document attributes, where each template corresponds to a different document format/type),
PNG
media_image1.png
284
354
media_image1.png
Greyscale
(Odate, [0086]-[0088])
PNG
media_image2.png
238
348
media_image2.png
Greyscale
(Odate, [0118]-[0119])
PNG
media_image3.png
144
348
media_image3.png
Greyscale
(Odate, [0124])
wherein each template comprises key point location data and annotation location data for documents of the identified document type (Odate, [0085]-[0089] Figure 4 shows an example of the template information for multiple document types, where the template comprises attribute names corresponding to text information and position information for these attributes (annotation location data),[0098]- [0099] the system also extracts feature cluster information with feature point information on the document (key point location data));
PNG
media_image4.png
262
358
media_image4.png
Greyscale
(Odate, [0097]-[0100])
PNG
media_image5.png
486
788
media_image5.png
Greyscale
(Odate, Figure 4)
matching first key points of the received document image with second key points of the corresponding document template data structure (Odate, [0089] position information for the attributes and features of the received document are generated, [0122] the positions of the attributes/features of the document (first key points) and the positions of the attributes of the template are compared to determine a position score or deviation score between the two to determine if the template, [0181]-[0182] the determination module searches the template for cluster information, which contains attribute position information (key points on the document) and matches these with features and clusters of the template (key point locations on the template));
PNG
media_image6.png
84
280
media_image6.png
Greyscale
PNG
media_image7.png
86
282
media_image7.png
Greyscale
(Odate, [0089])
PNG
media_image8.png
54
278
media_image8.png
Greyscale
PNG
media_image9.png
116
282
media_image9.png
Greyscale
(Odate, [0122])
PNG
media_image10.png
278
280
media_image10.png
Greyscale
(Odate, [0181]-[0183])
generating a mapping data structure, based on the matching of the first key points with the second key points, to map locations of the document template data structure to locations of the received document image (Odate, [0182] the template cluster information (contains key point information) is matched to the target document’s format, [0183]the positions of features of the document are scored based on their distances/match to the features of the corresponding template);
[applying, based on the mapping data structure, a perspective transformation to first annotation locations specified in the document template data structure to generate second annotation locations corresponding to locations in the received document image;
and performing a data extraction operation on data associated with the second annotation locations based on the annotations corresponding to the second annotation locations.]
Odate does not teach; applying, based on the mapping data structure, a perspective transformation to first annotation locations specified in the document template data structure to generate second annotation locations corresponding to locations in the received document image;
and performing a data extraction operation on data associated with the second annotation locations based on the annotations corresponding to the second annotation locations.
However, in the same field of endeavor, Wheaton teaches; applying, based on the mapping data structure, a perspective transformation to first annotation locations specified in the document template data structure to generate second annotation locations corresponding to locations in the received document image (Wheaton, [0348] if the template is matched to the document, the template annotation regions (first annotation locations) maybe used to annotate the document (second annotations/annotation locations), in some embodiments a liner regression may be used to match the templates to the documents via rotations, stretches and compressions);
and performing a data extraction operation on data associated with the second annotation locations based on the annotations corresponding to the second annotation locations (Wheaton, [0348] metadata identifiers are extracted from the corresponding annotation locations generated in the document image).
The combination of Odate and Wheaton would have been obvious to one of ordinary skill in the art prior to the effective filing date of the presently claimed invention. The motivation for the combination lies in that the annotation rectification method of Wheaton would allow the method of Odate to extract information from documents even when the document is rotated or skewed. (Wheaton, [0340]- [0348])
Regarding claim 2 the combination of Odate and Wheaton teaches; The method of claim 1, further comprising: training, via a machine learning process based on a plurality of training document images (Wheaton, [0290]-[0292] the machine learning model is trained using training data, where the training data may be text or images which would include document images),
a document classification computer model to classify document images into the plurality of document types (Wheaton, [0022] word tokens for each document are identified and then the tokens are compared to token lists for a collection of known document templates for known document types to identify the group it belongs to and match it with a template [0316] common words for each document type may be determined, such that the common words for each document type would be used to classify the document), and thereby generate a trained document classification computer model (Wheaton, [0290]-[0292] the machine learning model is trained using training data, where the training data may be text or images which would include document images);
and generating, for each document type in the plurality of document types, at least one document template data structure specifying key points and annotation locations for document images having the document type (Odate, [0067]-[0068] a template is generated corresponding to a document format, where the document is classified and then a template is generated, [0071] the templates include position information for character strings in the document formats, as well as [0072]-[0073] cluster information which has key points on the document in it),
wherein processing the received document image comprises processing the received document image by the trained document classification computer model to identify the identified document type (Wheaton, [0010] the system may use multiple ML models to process and annotate the document images [0022] word tokens for each document are identified and then the tokens are compared to token lists for a collection of known document templates for known document types to identify the group it belongs to and match it with a template [0316] common words for each document type may be determined, such that the common words for each document type would be used to classify the document).
The combination of Odate and Wheaton would have been obvious to one of ordinary skill in the art prior to the effective filing date of the presently claimed invention. The motivation to add the machine learning model and training method of Wheaton lies in that the use of machine learning to complete the document classification and template generation would reduce the need to for manual review and increase the efficiency of classification. (Wheaton, [0177]-[0179] and [0316])
Regarding claim 3 the combination of Odate and Wheaton teaches; The method of claim 2, wherein generating at least one document template data structure comprises generating the at least one document template data structure based on a combination of key points and annotation locations for training document images in the plurality of training document images having the document type (Wheaton, [0022] the system has generated templates for each clustered type of documents where the templates have word tokens corresponding to word locations (annotation locations) and document structure locations and distances (key point locations), where [0010] the system may use multiple ML models to process and annotate the document images from templates, indicating the templates correspond to the training image/images).
The combination of Odate and Wheaton would have been obvious to one of ordinary skill in the art prior to the effective filing date of the presently claimed invention. The motivation to add the machine learning model and training method of Wheaton lies in that the use of machine learning to complete the document classification and template generation would reduce the need to for manual review and increase the efficiency of classification. (Wheaton, [0177]-[0179] and [0316])
Regarding claim 4 the combination of Odate and Wheaton teaches; The method of claim 2, wherein the training of the document classification computer model comprises (Wheaton, [0290]-[0292] the machine learning model is trained using training data, where the training data may be text or images which would include document images):
executing a feature extraction operation on each training document image in the plurality of training document images to generate at least one of image features or text features of the training document image (Wheaton, [0022] word tokens for each document are identified and then the tokens are compared to token lists for a collection of known document templates for known document types to identify the group it belongs to and match it with a template, where [0010] the system may use multiple ML models to process and annotate the document images from templates, indicating the features and images correspond to the training image/images, [0290]-[0292] the machine learning model is trained using training data, where the training data may be previously disclosed input text or images which would include document images);
processing, by the document classification computer model, the image features or text features of the training document image to generate a predicted classification of the training document image (Wheaton, [0022] word tokens for each document are identified and then the tokens are compared to token lists for a collection of known document templates for known document types to identify the group it belongs to and match it with a template [0316] common words for each document type may be determined, such that the common words for each document type would be used to classify the document, where [0010] the system may use multiple ML models to process and annotate the document images from templates, indicating the features and images correspond to the training image/images, [0290]-[0292] the machine learning model is trained using training data, where the training data may be previously disclosed input text or images which would include document images);
comparing the predicted classification of the training document image to a ground truth classification of the training document image (Wheaton, [0290]-[0293] the machine learning model is trained using training data, where the training data may be previously disclosed input text or images which would include document images, where the input data is split into training and validation sets, where each input is correlated with a desired output, indicating a ground truth comparison);
and modifying an operational parameter of the document classification computer model to reduce a difference between the predicted classification and the ground truth classification (Wheaton, [0299] during training weights of the network may be adjusted to reduce the difference between the actual output (predicted classification) and the desired output (ground truth)).
The combination of Odate and Wheaton would have been obvious to one of ordinary skill in the art prior to the effective filing date of the presently claimed invention. The motivation to add the machine learning model and training method of Wheaton lies in that the use of machine learning to complete the document classification and template generation would reduce the need to for manual review and increase the efficiency of classification. (Wheaton, [0177]-[0179], [0290]-[0300], and [0316])
Regarding claim 5 the combination of Odate and Wheaton teaches; The method of claim 1, wherein the mapping data structure is a homography transformation matrix specifying an isomorphism of projective spaces, wherein the homography transformation matrix, when applied to coordinates of the first annotation locations, generates the second annotation locations (Wheaton, [0174] linear regression is used to find the terms to rotate, scale and adjust the template to the input image to produce an updated annotations for the annotated image, given that linear regression is being used to generate translated/adjusted coordinates of the annotations, it would generate a transformation matrix for this application).
The combination of Odate and Wheaton would have been obvious to one of ordinary skill in the art prior to the effective filing date of the presently claimed invention. The motivation for the combination lies in that the alignment adjustment of Wheaton allows for correction and alignment of document images which may have been scanned in at an angle such that the template may still be used. (Wheaton, [0174])
Regarding claim 6 the combination of Odate and Wheaton teaches; The method of claim 1, wherein the data extraction operation comprises at least one of an optical character reading operation on text content of a second annotation location, or an image extraction algorithm on non-text content of a second annotation location (Odate, [0121]-[0122] OCR and position information is extracted from the attributes/annotations of the document).
Regarding claim 7 the combination of Odate and Wheaton teaches; The method of claim 1, wherein performing the data extraction operation on the data associated with the second annotation locations further comprising storing the extracted data in a persistent storage and accessing the extracted data by a downstream automated document processing computing tool to perform an automated document processing operation (Odate, [0137] extracted OCR data and image extraction data is accessed and used in multiple other processes, [0059]-[0061] processors and other storage devices execute the programs and store the images and image data).
Regarding claim 8 the combination of Odate and Wheaton teaches; The method of claim 1, wherein retrieving a corresponding document template data structure for the identified document type of the received document image from a document template repository comprises (Odate, [0092]-[0093] the template is matched to the format of the document (document type)):
retrieving a set of document template data structures associated with the identified document type (Odate, [0108] a template is indicated as corresponding to document format/type, the management system manages the templates and the clusters of documents it corresponds to);
and identifying a closest matching document template data structure from the set of document template data structures (Odate, [0124] a template suited for generating a document read summary is selected based upon a comparison of the document and multiple stored templates, the closest match is selected), wherein the closest matching document template data structure is retrieved as the corresponding document template data structure (Odate, [0139] the template is a data structure with attributes which correspond to extract attributes from the document, which are all data structures).
Regarding claim 9 the combination of Odate and Wheaton teaches; The method of claim 8, wherein the closest matching document template data structure is identified by at least one of matching randomly selected key points of the received document image with key points specified in the document template data structures of the set of document template data structures, or performing a vector comparison of a feature vector of the received document image with a feature vector associated with the document template data structures of the set of document template data structures (Odate, [0124] a template suited for generating a document read summary is selected based upon a comparison of the document and multiple stored templates, the closest match is selected, the comparison consists of attributes (key points) of the template being compared with the document to determine a distance between the two to match the templates).
Regarding claim 10 the combination of Odate and Wheaton teaches; The method of claim 1, wherein the received document image comprises at least one geometric or image quality imperfection that causes annotation locations in data structures for the identified document type to not be aligned with corresponding locations of the received document image (Wheaton, [0174] the input image may need to be aligned or have its alignment corrected to match to the template using linear regression, which is being interpreted as a geometric imperfection).
The combination of Odate and Wheaton would have been obvious to one of ordinary skill in the art prior to the effective filing date of the presently claimed invention. The motivation for the combination lies in that the alignment adjustment of Wheaton allows for correction and alignment of document images which may have been scanned in at an angle such that the template may still be used. (Wheaton, [0174])
Regarding claim 11 the combination of Odate and Wheaton teaches; A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a data processing system, causes the data processing system to (Odate, [0057] the system has a processor connected to a storage device to execute the program):
process a received document image to identify a document type of the received document image (Odate, [0050] a scanned image of the document is received by the application);
retrieve a corresponding document template data structure for the identified document type of the received document image from a document template repository having document templates for a plurality of document types (Odate [0086]-[0088] the system stores templates based on the document format (multiple templates associated with multiple identified types/formats of documents), where [0118] the document undergoes a recognition process, and [0119] the document read result is scored against each template option and [0124] then a template is selected from the plurality of templates based on the scored document attributes, where each template corresponds to a different document format/type),
wherein each template comprises key point location data and annotation location data for documents of the identified document type (Odate, [0085]-[0089] Figure 4 shows an example of the template information for multiple document types, where the template comprises attribute names corresponding to text information and position information for these attributes (annotation location data),[0098]- [0099] the system also extracts feature cluster information with feature point information on the document (key point location data));
match first key points of the received document image with second key points of the corresponding document template data structure(Odate, [0089] position information for the attributes and features of the received document are generated, [0122] the positions of the attributes/features of the document (first key points) and the positions of the attributes of the template are compared to determine a position score or deviation score between the two to determine if the template, [0181]-[0182] the determination module searches the template for cluster information, which contains attribute position information (key points on the document) and matches these with features and clusters of the template (key point locations on the template));
generate a mapping data structure, based on the matching of the first key points with the second key points, to map locations of the document template data structure to locations of the received document image (Odate, [0182] the template cluster information (contains key point information) is matched to the target document’s format, [0183]the positions of features of the document are scored based on their distances/match to the features of the corresponding template);
apply, based on the mapping data structure, a perspective transformation to first annotation locations specified in the document template data structure to generate second annotation locations corresponding to locations in the received document image (Wheaton, [0348] if the template is matched to the document, the template annotation regions (first annotation locations) maybe used to annotate the document (second annotations/annotation locations), in some embodiments a liner regression may be used to match the templates to the documents via rotations, stretches and compressions);
and perform a data extraction operation on data associated with the second annotation locations based on the annotations corresponding to the second annotation locations (Wheaton, [0348] metadata identifiers are extracted from the corresponding annotation locations generated in the document image.
The combination of Odate and Wheaton would have been obvious to one of ordinary skill in the art prior to the effective filing date of the presently claimed invention. The motivation for the combination lies in that the annotation rectification method of Wheaton would allow the method of Odate to extract information from documents even when the document is rotated or skewed. (Wheaton, [0340]- [0348])
Regarding claim 12 the combination of Odate and Wheaton teaches; The computer program product of claim 11, wherein the computer readable program further causes the data processing system to (Odate, [0057] the system has a processor connected to a storage device to execute the program): train, via a machine learning process based on a plurality of training document images (Wheaton, [0290]-[0292] the machine learning model is trained using training data, where the training data may be text or images which would include document images),
(Wheaton, [0022] word tokens for each document are identified and then the tokens are compared to token lists for a collection of known document templates for known document types to identify the group it belongs to and match it with a template [0316] common words for each document type may be determined, such that the common words for each document type would be used to classify the document), and thereby generate a trained document classification computer model (Wheaton, [0290]-[0292] the machine learning model is trained using training data, where the training data may be text or images which would include document images);
and generate, for each document type in the plurality of document types, at least one document template data structure specifying key points and annotation locations for document images having the document type (Odate, [0067]-[0068] a template is generated corresponding to a document format, where the document is classified and then a template is generated, [0071] the templates include position information for character strings in the document formats, as well as [0072]-[0073] cluster information which has key points on the document in it),
wherein processing the received document image comprises processing the received document image by the trained document classification computer model to identify the identified document type (Wheaton, [0010] the system may use multiple ML models to process and annotate the document images [0022] word tokens for each document are identified and then the tokens are compared to token lists for a collection of known document templates for known document types to identify the group it belongs to and match it with a template [0316] common words for each document type may be determined, such that the common words for each document type would be used to classify the document).
The combination of Odate and Wheaton would have been obvious to one of ordinary skill in the art prior to the effective filing date of the presently claimed invention. The motivation to add the machine learning model and training method of Wheaton lies in that the use of machine learning to complete the document classification and template generation would reduce the need to for manual review and increase the efficiency of classification. (Wheaton, [0177]-[0179] and [0316])
Regarding claim 13 the combination of Odate and Wheaton teaches; The computer program product of claim 12, wherein generating at least one document template data structure comprises generating the at least one document template data structure based on a combination of key points and annotation locations for training document images in the plurality of training document images having the document type (Wheaton, [0022] the system has generated templates for each clustered type of documents where the templates have word tokens corresponding to word locations (annotation locations) and document structure locations and distances (key point locations), where [0010] the system may use multiple ML models to process and annotate the document images from templates, indicating the templates correspond to the training image/images).
The combination of Odate and Wheaton would have been obvious to one of ordinary skill in the art prior to the effective filing date of the presently claimed invention. The motivation to add the machine learning model and training method of Wheaton lies in that the use of machine learning to complete the document classification and template generation would reduce the need to for manual review and increase the efficiency of classification. (Wheaton, [0177]-[0179] and [0316])
Regarding claim 14 the combination of Odate and Wheaton teaches; The computer program product of claim 12, wherein the training of the document classification computer model comprises (Wheaton, [0290]-[0292] the machine learning model is trained using training data, where the training data may be text or images which would include document images):
executing a feature extraction operation on each training document image in the plurality of training document images to generate at least one of image features or text features of the training document image (Wheaton, [0022] word tokens for each document are identified and then the tokens are compared to token lists for a collection of known document templates for known document types to identify the group it belongs to and match it with a template, where [0010] the system may use multiple ML models to process and annotate the document images from templates, indicating the features and images correspond to the training image/images, [0290]-[0292] the machine learning model is trained using training data, where the training data may be previously disclosed input text or images which would include document images);
processing, by the document classification computer model, the image features or text features of the training document image to generate a predicted classification of the training document image (Wheaton, [0022] word tokens for each document are identified and then the tokens are compared to token lists for a collection of known document templates for known document types to identify the group it belongs to and match it with a template [0316] common words for each document type may be determined, such that the common words for each document type would be used to classify the document, where [0010] the system may use multiple ML models to process and annotate the document images from templates, indicating the features and images correspond to the training image/images, [0290]-[0292] the machine learning model is trained using training data, where the training data may be previously disclosed input text or images which would include document images);
comparing the predicted classification of the training document image to a ground truth classification of the training document image (Wheaton, [0290]-[0293] the machine learning model is trained using training data, where the training data may be previously disclosed input text or images which would include document images, where the input data is split into training and validation sets, where each input is correlated with a desired output, indicating a ground truth comparison);
and modifying an operational parameter of the document classification computer model to reduce a difference between the predicted classification and the ground truth classification (Wheaton, [0299] during training weights of the network may be adjusted to reduce the difference between the actual output (predicted classification) and the desired output (ground truth)).
The combination of Odate and Wheaton would have been obvious to one of ordinary skill in the art prior to the effective filing date of the presently claimed invention. The motivation to add the machine learning model and training method of Wheaton lies in that the use of machine learning to complete the document classification and template generation would reduce the need to for manual review and increase the efficiency of classification. (Wheaton, [0177]-[0179], [0290]-[0300], and [0316])
Regarding claim 15 the combination of Odate and Wheaton teaches; The computer program product of claim 11, wherein the mapping data structure is a homography transformation matrix specifying an isomorphism of projective spaces, wherein the homography transformation matrix, when applied to coordinates of the first annotation locations, generates the second annotation locations (Wheaton, [0174] linear regression is used to find the terms to rotate, scale and adjust the template to the input image to produce an updated annotations for the annotated image, given that linear regression is being used to generate translated/adjusted coordinates of the annotations, it would generate a transformation matrix for this application).
The combination of Odate and Wheaton would have been obvious to one of ordinary skill in the art prior to the effective filing date of the presently claimed invention. The motivation for the combination lies in that the alignment adjustment of Wheaton allows for correction and alignment of document images which may have been scanned in at an angle such that the template may still be used. (Wheaton, [0174])
Regarding claim 16 the combination of Odate and Wheaton teaches; The computer program product of claim 11, wherein the data extraction operation comprises at least one of an optical character reading operation on text content of a second annotation location, or an image extraction algorithm on non-text content of a second annotation location (Odate, [0121]-[0122] OCR and position information is extracted from the attributes/annotations of the document).
Regarding claim 17 the combination of Odate and Wheaton teaches; The computer program product of claim 11, wherein performing the data extraction operation on the data associated with the second annotation locations further comprising storing the extracted data in a persistent storage and accessing the extracted data by a downstream automated document processing computing tool to perform an automated document processing operation (Odate, [0137] extracted OCR data and image extraction data is accessed and used in multiple other processes, [0059]-[0061] processors and other storage devices execute the programs and store the images and image data).
Regarding claim 18 the combination of Odate and Wheaton teaches; The computer program product of claim 11, wherein retrieving a corresponding document template data structure for the identified document type of the received document image from a document template repository comprises (Odate, [0092]-[0093] the template is matched to the format of the document (document type)):
retrieving a set of document template data structures associated with the identified document type (Odate, [0108] a template is indicated as corresponding to document format/type, the management system manages the templates and the clusters of documents it corresponds to);
and identifying a closest matching document template data structure from the set of document template data structures (Odate, [0124] a template suited for generating a document read summary is selected based upon a comparison of the document and multiple stored templates, the closest match is selected), wherein the closest matching document template data structure is retrieved as the corresponding document template data structure (Odate, [0139] the template is a data structure with attributes which correspond to extract attributes from the document, which are all data structures).
Regarding claim 19 the combination of Odate and Wheaton teaches; The computer program product of claim 18, wherein the closest matching document template data structure is identified by at least one of matching randomly selected key points of the received document image with key points specified in the document template data structures of the set of document template data structures, or performing a vector comparison of a feature vector of the received document image with a feature vector associated with the document template data structures of the set of document template data structures (Odate, [0124] a template suited for generating a document read summary is selected based upon a comparison of the document and multiple stored templates, the closest match is selected, the comparison consists of attributes (key points) of the template being compared with the document to determine a distance between the two to match the templates).
Regarding claim 20 the combination of Odate and Wheaton teaches; An apparatus comprising: at least one processor (Odate, [0057] the system has a processor connected to a storage device to execute the program);
and at least one memory coupled to the at least one processor, wherein the at least one memory comprises instructions which, when executed by the at least one processor, cause the at least one processor to (Odate, [0057] the system has a processor connected to a storage device to execute the program):
process a received document image to identify a document type of the received document image (Odate, [0050] a scanned image of the document is received by the application);
retrieve a corresponding document template data structure for the identified document type of the received document image from a document template repository having document templates for a plurality of document types (Odate [0086]-[0088] the system stores templates based on the document format (multiple templates associated with multiple identified types/formats of documents), where [0118] the document undergoes a recognition process, and [0119] the document read result is scored against each template option and [0124] then a template is selected from the plurality of templates based on the scored document attributes, where each template corresponds to a different document format/type),
wherein each template comprises key point location data and annotation location data for documents of the identified document type (Odate, [0085]-[0089] Figure 4 shows an example of the template information for multiple document types, where the template comprises attribute names corresponding to text information and position information for these attributes (annotation location data),[0098]- [0099] the system also extracts feature cluster information with feature point information on the document (key point location data));
match first key points of the received document image with second key points of the corresponding document template data structure(Odate, [0089] position information for the attributes and features of the received document are generated, [0122] the positions of the attributes/features of the document (first key points) and the positions of the attributes of the template are compared to determine a position score or deviation score between the two to determine if the template, [0181]-[0182] the determination module searches the template for cluster information, which contains attribute position information (key points on the document) and matches these with features and clusters of the template (key point locations on the template));
generate a mapping data structure, based on the matching of the first key points with the second key points, to map locations of the document template data structure to locations of the received document image (Odate, [0182] the template cluster information (contains key point information) is matched to the target document’s format, [0183]the positions of features of the document are scored based on their distances/match to the features of the corresponding template);
apply, based on the mapping data structure, a perspective transformation to first annotation locations specified in the document template data structure to generate second annotation locations corresponding to locations in the received document image (Wheaton, [0348] if the template is matched to the document, the template annotation regions (first annotation locations) maybe used to annotate the document (second annotations/annotation locations), in some embodiments a liner regression may be used to match the templates to the documents via rotations, stretches and compressions);
and perform a data extraction operation on data associated with the second annotation locations based on the annotations corresponding to the second annotation locations (Wheaton, [0348] metadata identifiers are extracted from the corresponding annotation locations generated in the document image.
The combination of Odate and Wheaton would have been obvious to one of ordinary skill in the art prior to the effective filing date of the presently claimed invention. The motivation for the combination lies in that the annotation rectification method of Wheaton would allow the method of Odate to extract information from documents even when the document is rotated or skewed. (Wheaton, [0340]- [0348])
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Semenov, US (20240169752 A1), which is pertinent to claims 1-20 and teaches a method of matching known key point within a document to extract information.
Aschel, US (11257006 B1), which is pertinent to claims 1-20 and teaches a method of rectifying annotations to a document scan from a template, such that the annotations are oriented correctly on the document image regardless of scan angle.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JORDAN M ELLIOTT whose telephone number is (703)756-5463. The examiner can normally be reached M-F 8AM-5PM ET.
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.
/J.M.E./Examiner, Art Unit 2666
/EMILY C TERRELL/Supervisory Patent Examiner, Art Unit 2666
Prosecution Insights