CTNF 18/899,048 CTNF 97705 DETAILED ACTION Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. This communication is in response to the Application No. 18/899,048 filed 09/27/2024. Claims 1-20 are pending. Information Disclosure Statement The information disclosure statement(s) (IDS) submitted on 09/27/2024 has been entered and considered. Initialed copies of the PTO-1449 by the examiner are attached. Specification 07-29 AIA The disclosure is objected to because of the following informalities: At lines 4-5 of paragraph [0018] should recite, in part, “the generated fields may be generated using large language models, by functions, or retrieved from a source in some examples” to avoid typographical and/or clarity issues . Appropriate correction is required. 07-30-03-h AIA Claim Interpretation 07-30-03 AIA 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. 07-30-05 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. Claims 19 and 20 recite limitations that use words like “means” (or “step”) or similar terms with functional language and do invoke 35 U.S.C. 112(f): Claim 19; recites the limitation, “a field generator configured to … , ”. Claim 19; recites the limitation, “a smart checking engine configured to … , ”. Claim 19; recites the limitation, “a special field generator configured to … , ”. Claim 19; recites the limitation, “a filler engine configured to … , ”. Claim 20; recites the limitation, “a model configured to … , ”. 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. After a careful analysis, as disclosed above, and a careful review of the specification the following limitations in claims 19 and 20 : “field generator” (Fig. 4, #406; PGPUB Paragraph [0042]- “The field generator 406 may use open-source libraries to generate values for a variety of different fields. The field generator 406 may specify features for the various field types. For example, the field generator 406 may specify features such as minimum and maximum length of strings, regular expression patterns, dictionaries, and the like. For instance, a purchase order number may follow a particular regular expression. States and countries may have or be associated with a fixed set of possible values” wherein the field generator is part of a document generation engine, paragraph [0047]- “The document generation engine 404 may implement a method for intelligently filling out document templates of documents based on LLM”. thus, have sufficient structure or material wherein is any kind of LLM ). “smart checking engine” (Fig. 4, #410; PGPUB Paragraph [0043]- “The smart checking engine 410 is configured to fill checkbox field values. In one example, a probability distribution for each type of checkbox field in the document template may be determined or used. The type of ticker character (e.g., an “x” or a checkmark (“ ✓ ”) and its positioning are also taken or selected from a set of font types and sizes. The positioning of the ticker character is also done using the probabilistic positioner.” wherein the smart checking engine is part of a document generation engine, paragraph [0047]- “The document generation engine 404 may implement a method for intelligently filling out document templates of documents based on LLM”. thus, have sufficient structure or material wherein is any kind of LLM ). “Special field generator” (Fig. 4, #408; PGPUB Paragraph [0044]- “The special field generator 408 is configured for handling relational fields such as tables. One example of relational fields is the delivery items in a bill of lading document. The special field generator 408 may use a large language model to generate constrained tuples of relational field values. For instance, in the context of a bill of lading document, the large language model may be configured to generate item types and constrain the item types to be in a reasonable real-world range of values (e.g., weight, number, size). The large language model may also classify the item type as hazardous or not (HM for Hazard Material). As part of the tuple, numerical quantities such as number of units of a given item may be included. Additionally, as part of the last item in a table, a totalization field may be included. In this case, all constrained tuples generated by the LLM are selected and, for each numerical quantity, the total is calculated, so that the totalization field value can be filled out correctly. Like other fields, the special field generator may vary font type and size and may use and the probabilistic positioner when filling the relational field.”. thus, have sufficient structure or material wherein is any kind of LLM ). “Filler engine” (Fig. 4, #412; PGPUB Paragraph [0045]- “The filler engine 412 is configured to collect all the data collected from the field generator 406, the smart checking engine 410, and the special field generator 408 and fill an instance of the document template 402 with the data or values” wherein the filler engine is part of a document generation engine, paragraph [0047]- “The document generation engine 404 may implement a method for intelligently filling out document templates of documents based on LLM”. thus, have sufficient structure or material wherein is any kind of LLM ). “model” (Fig. 5, #512, PGPUB Paragraph [0048]-[0049]- “FIG. 5 discloses aspects of operating a model trained on synthetic data for document understanding. FIG. 5 illustrates a model 512 that includes an encoder 514 and a decoder 514. The model 512 is trained using large amounts of synthetic labeled documents and is configured to recover/extract information based on an input that includes an image 502 and/or a prompt 504. The input image 502 may be an image of a document such as a bill of lading. The model 512 is a multi-task multimodal large language model in one example and is configured to respond to different promptings for an input image 502. In this example, the model 512 is configured to response to a classification prompt 506, a question (e.g., open ended question) prompt 508, and a parsing prompt 510. In other words, the model 512 may perform multiple tasks (3 in this example). Further, for the model 512 to operate efficiently with respect to a new set of documents, the model 512 may be fine-tuned using data from that document type. Thus, synthetic documents may be generated from a document template for that type” . thus, have sufficient structure or material wherein is any kind of multi-task multimodal large language model ). 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 § 101 07-04-01 AIA 07-04 35 U.S.C. 101 reads as follows: Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title. Claim(s) 1-18 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., law of nature, a natural phenomenon, or an abstract idea) without significantly more. Regarding independent claim 1 and its dependent claim(s) 2-9: Step 1 analysis: Claim 1 is directed to a method which is a process that falls within one of the four statutory categories. Step 2A prong 1 analysis : Claim 1 recites, in part: “ (b) determining values for each of the fields in the document template; (c) filling the fields in the document template with the determined values to generate a filled document template; and (d) generating a synthetic document from the filled document template, wherein the synthetic document includes an image of the filled document template and a label that includes ground truth for each of the filled fields ” The limitations as shown above, as drafted, are processes that, under the broadest reasonable interpretation, cover the performance of the limitations in the mind which fall within the “Mental Process” grouping of abstract ideas. The limitations of: “ determining values for each of the fields in the document template... filling the fields in the document template with the determined values to generate a filled document template... generating a synthetic document from the filled document template, wherein the synthetic document includes an image of the filled document template and a label that includes ground truth for each of the filled fields ” recite steps that the human mind can perform through observation and evaluation, such as the human mind can determine the type of document template, such as a purchase order, and fill in specific values for a type of product, quantity and price, thereby generating a synthetic document with fake values. Such document may be compared to a real purchase order to obtain labels of where the fake values were inputted to fit a description (e.g., a quantity, product, price, etc.) and deem it as ground truth via observation and evaluation. Accordingly, the claim recites an abstract idea. Step 2A prong 2 analysis: this judicial exception is not integrated into a practical application. In particular, the claim recites the following element(s) – “(a) selecting a document template, wherein the document template is associated with fields and positions of the fields within the document template” The steps of “selecting a document template” merely constitute pre-solution activities involving data gathering such as acquiring data, and thus are insignificant extra-solution activities. In view of the foregoing, the additional elements do not integrate the abstract idea into a practical application. Step 2B analysis: there are no additional elements that amount to significantly more than the judicial exception. Moreover, the additional element(s) as mentioned above do not amount to significantly more for the claim as a whole. Please see MPEP §2106.05. The claim is directed to an abstract idea. For all the foregoing reasons, claim 1 does not comply with the requirements of 35 USC 101. Dependent claims 2-9 do not provide elements and/or limitations that overcome the deficiencies of the independent claim. Specifically: Claims 2 and 3 recite limitations in the form of additional elements involving data gathering. Such limitations include “wherein the document template is selected from a library of document templates” and “wherein the fields include simple fields, checkbox fields, and/or relational fields” which recite insignificant extra-solution activity. Claims 4-6 do not provide elements and/or limitations that overcome the deficiencies of the independent claim. Specifically: Claim 4 recites, in part, “determining positions of each of the fields in the document template” which recites a mental process. For example, the human mind may determine positions field texts within a document using observation and evaluation. Claim 5 recites, in part, “performing (b), (c), and (d) n times for each of a plurality of document templates to generate synthetic documents for each of the plurality of document templates, wherein a font type and a font size are varied among the synthetic documents” which recites a mental process. For example, a human mind can generate fake values for a plurality of documents using a pen and paper and vary their font types and font sizes to obtain more document templates, each filled with their corresponding values for each field using observation and evaluation. Claim 6 recites, in part, “varying a position of the determined values within the corresponding fields based on a probabilistic positioner” which similarly recites a mental process as described in claim 5, with a variety of field positions. The additional element included in the claim is that of a probabilistic positioner, however, does not expressly state any details on the function of such term. Therefore, the plain meaning of probabilistic positioner is that of a human mind varying positions of values within the fields of a document based on guessing, through observation and evaluation, to change the position of field values. Claims 7-9 do not provide elements and/or limitations that overcome the deficiencies of the independent claim. Specifically: Claim 7 recites, in part, “generating values for the relational fields using a large language model, wherein the values for the relational fields are constrained to real-world ranges”. The claim recites generating values for the relational fields using a large langue model but the claim does not provide any details about how the large langue model operates as it only states the outcome. The claim simply uses a generic LLM to perform the abstract idea, that is, the LLM provides nothing more than mere instructions to implement an abstract idea on a generic computer. The plain meaning of “generating” encompasses mental observations or evaluations, e.g., a human mind can generate item quantities and prices based on real world ranges such that the ranges do not seem fake. Claim 8 recites, in part, “determining totals for numerical quantities in the relational fields” which recites a mental process. For example, a human mind can generate fake values and total them for a plurality of documents using a pen and paper, each filled with corresponding item values for each field using observation and evaluation. Claim 9 recites, in part, “training a model using the synthetic documents” which recites a model as an additional element. However, such model is not defined and therefore can encompass any processor using a generic computer. Similarly, the training of a model does not integrate the abstract idea into a practical application because the claim does not limit what encompasses such model. Independent claim 10 and its dependent claims 11-18: Independent claim 10 recites similar limitations as described in claim 1 and does not comply with the requirements of 35 USC 101. More specifically: Step 1 analysis: Claim 10 is directed to a non-transitory storage medium containing instructions for performing operations which is a manufacture that falls within one of the four statutory categories. Step 2A prong 1 analysis : Claim 10 recites, in part: “ (b) determining values for each of the fields in the document template; (c) filling the fields in the document template with the determined values to generate a filled document template; and (d) generating a synthetic document from the filled document template, wherein the synthetic document includes an image of the filled document template and a label that includes ground truth for each of the filled fields ” The limitations as shown above, as drafted, are processes that, under the broadest reasonable interpretation, cover the performance of the limitations in the mind which fall within the “Mental Process” grouping of abstract ideas. The limitations of: “ determining values for each of the fields in the document template... filling the fields in the document template with the determined values to generate a filled document template... generating a synthetic document from the filled document template, wherein the synthetic document includes an image of the filled document template and a label that includes ground truth for each of the filled fields ” recite steps that the human mind can perform through observation and evaluation, such as the human mind can determine the type of document template, such as a purchase order, and fill in specific values for a type of product, quantity and price, thereby generating a synthetic document with fake values. Such document may be compared to a real purchase order to obtain labels of where the fake values were inputted to fit a description (e.g., a quantity, product, price, etc.) and deem it as ground truth via observation and evaluation. Accordingly, the claim recites an abstract idea. Step 2A prong 2 analysis: this judicial exception is not integrated into a practical application. In particular, the claim recites the following element(s) – “(a) selecting a document template, wherein the document template is associated with fields and positions of the fields within the document template” “hardware processors” The steps of “selecting a document template” merely constitute pre-solution activities involving data gathering such as acquiring data, and thus are insignificant extra-solution activities. Similarly, limitation of “hardware processors” are recited as being performed by generic computer components at a high level of generality and amount to no more than instructions to apply the exception using a generic computer. In view of the foregoing, the additional elements do not integrate the abstract idea into a practical application. Step 2B analysis: there are no additional elements that amount to significantly more than the judicial exception. Moreover, the additional element(s) as mentioned above do not amount to significantly more for the claim as a whole. Please see MPEP §2106.05. The claim is directed to an abstract idea. For all the foregoing reasons, claim 10 does not comply with the requirements of 35 USC 101. Dependent claims 11-18 do not provide elements and/or limitations that overcome the deficiencies of the independent claim. Specifically, these claims recite identical limitations as previously discussed in claims 2-9 above and therefore are not eligible under 101 analysis. Independent claim 19 and its dependent claim 20: Step 1 analysis: Claim 19 is directed to a computer system which is a machine that falls within one of the four statutory categories. Step 2A prong 1 analysis: the claim does not recite any judicial exceptions. For instance, the claim does not recite a mental process because the claim, under its broadest reasonable interpretation, does not cover the performance in the mind but for the recitation of generic computer components. For example, “generating” step now requires the use of a large langue models. In particular, the claim and its ordered combination of steps of generating values, filling out checkbox fields, generating relational field values, and generating a filled document template to produce synthetic documents reflects an improved technicality of generating synthetically filled documents. Accordingly, the claim is directed to an improvement of generating synthetic documents. Therefore, Claim 19 and its dependent claim 20 are eligible under 101 analysis. Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 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. 07-20-aia AIA 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. 07-21-aia AIA Claim (s) 1-5 and 10-14 are rejected under 35 U.S.C. 103 as being unpatentable over Srivastava et al. (US 11087081 B1, hereinafter referred to as “Srivastava”) in view of Dong et al. (CN 108595398 A, hereinafter referred to as “Dong”) . Regarding claim 1, Srivastava teaches a method comprising: wherein the document template is associated with fields and positions of the fields within the document template (“General categories of document elements that may be extracted from real-world documents 10A and represented by element templates 22 in the repository 170 may include one or more of, but are not limited to, text elements (numeric symbols, letters, punctuation symbols, short words, long words, regular words, hyphenated words, etc.), key-value elements (single key-single value elements, single key-multiple value elements, key-clickable value elements (for example, checkboxes), etc.), tables, columns, headers, footers, sections (e.g., text sections), or in general any category of element that may be found in real-world documents 10A. Multiple types of element templates 22 may be generated for a category of document element, each type of element template 22 representing a different style, form, and/or size for an element in that category. The element templates 22 may be tagged with identifiers” Srivastava, Col 4 ln 1-16; wherein the document elements are that of fields where the locations are known, “an annotation document may include information describing the element template 22 type, location, size, style, and content of the elements” Srivastava, Col 5 ln 14-16) ; (b) determining values for each of the fields in the document template (“a configuration for synthetic documents is derived from real-world documents. The configuration may specify which elements should be present in the synthetic documents (key-value pairs, tables, text, etc.). The configuration may also specify whether or not the layout of the elements is to be structured (e.g., number of rows and columns), and which styles the elements should adhere to” Srivastava, Col 6 ln 6-14) ; (c) filling the fields in the document template with the determined values to generate a filled document template (“The configuration may specify which elements should be present in the synthetic documents (key-value pairs, tables, text, etc.). The configuration may also specify whether or not the layout of the elements is to be structured (e.g., number of rows and columns), and which styles the elements should adhere to... element template types, styles, and layouts for the synthetic documents are determined for the configuration. In some embodiments, a controller receives the configuration that was derived from real-world documents at 200, analyzes the configuration according to a set of rules to determine which types of element templates should be used to generate the synthetic documents, and generates a configuration file (e.g., a JSON file) that indicates the types of element templates and weights for the different types of element templates based on the received configuration” Srivastava, Col 6 ln 10-27) ; and (d) generating a synthetic document from the filled document template, wherein the synthetic document includes an image of the filled document template and a label that includes ground truth for each of the filled fields (“synthetic documents and corresponding annotation documents are generated based on the configuration” Srivastava, Col 6 ln 33-34; wherein the annotation documents correspond to ground truth; Additionally, the synthetic document is an image “an image or screenshot of the rendered markup language document may be captured to generate the synthetic document” Srivastava, Col 7 ln 22-24) . Srivastava fails to explicitly teach (a) selecting a document template. However, Dong teaches (a) selecting a document template (“select the corresponding template in the template database” Dong, top of pg. 3). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Srivastava of having a method wherein the document template is associated with fields and positions of the fields within the document template; determining values for each of the fields in the document template; filling the fields in the document template with the determined values to generate a filled document template; and generating a synthetic document from the filled document template, wherein the synthetic document includes an image of the filled document template and a label that includes ground truth for each of the filled fields with the teachings of Dong of having selecting a document template. Wherein having Srivastava method of generating a synthetic document having selecting a document template. The motivation behind the modification would have been to obtain a method of generating synthetic documents that improves classification of real-world documents such as forms, receipts, and dense text documents using machine learning models, since Srivastava and Dong relate to using document template generation. Wherein Srivastava element templates are extracted from real-world documents and stored in an element template repository, while Dong is for facilitating the calling and modifications of template documents having certain document structures. Please see Srivastava et al. (US 11087081 B1), Col 3 ln 54-58 and Dong et al. (CN 108595398 A), top of page 3. Regarding claim 2, Srivastava in view of Dong teach the method of claim 1, Srivastava fails to explicitly teach wherein the document template is selected from a library of document templates. However, Dong teaches wherein the document template is selected from a library of document templates (“select the corresponding template in the template database” Dong, top of pg. 3) . Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Srivastava of having a method wherein the document template is associated with fields and positions of the fields within the document template; determining values for each of the fields in the document template; filling the fields in the document template with the determined values to generate a filled document template; and generating a synthetic document from the filled document template, wherein the synthetic document includes an image of the filled document template and a label that includes ground truth for each of the filled fields with the teachings of Dong of having wherein the document template is selected from a library of document templates. Wherein having Srivastava method of generating a synthetic document wherein the document template is selected from a library of document templates. The motivation behind the modification would have been to obtain a method of generating synthetic documents that improves classification of real-world documents such as forms, receipts, and dense text documents using machine learning models, since Srivastava and Dong relate to using document template generation. Wherein Srivastava element templates are extracted from real-world documents and stored in an element template repository, while Dong is for facilitating the calling and modifications of template documents having certain document structures. Please see Srivastava et al. (US 11087081 B1), Col 3 ln 54-58 and Dong et al. (CN 108595398 A), top of page 3. Regarding claim 3, Srivastava in view of Dong teach the method of claim 1, Srivastava further teaches wherein the fields include simple fields, checkbox fields, and/or relational fields (“element templates 22 in the repository 170 may include one or more of, but are not limited to, text elements (numeric symbols, letters, punctuation symbols, short words, long words, regular words, hyphenated words, etc.), key-value elements (single key-single value elements, single key-multiple value elements, key-clickable value elements (for example, checkboxes), etc.), tables, columns, headers, footers, sections (e.g., text sections), or in general any category of element that may be found in real-world documents 10A” Srivastava, Col 4 ln 3-11) . Regarding claim 4, Srivastava in view of Dong teach the method of claim 3, Srivastava further teaches further comprising determining positions of each of the fields in the document template (“an annotation document may include information describing the element template 22 type, location, size, style, and content of the elements” Srivastava, Col 5 ln 14-16). Regarding claim 5, Srivastava in view of Dong teach the method of claim 4, Srivastava further teaches further comprising performing (b), (c), and (d) n times for each of a plurality of document templates to generate synthetic documents for each of the plurality of document templates (“new configurations can be generated to generate additional synthetic training data that includes new synthetic and annotation documents to further train the model 932 on the features or elements of real-world documents where the model underperforms. This process can be repeated to fine tune the machine learning model 932 to perform better when analyzing real-world documents” Srivastava, Col 13 ln 8-15) , wherein a font type and a font size are varied among the synthetic documents (“Content, size, style, and location of the element templates in the markup language documents may be randomized to provide diversity in the synthetic documents. As indicated at 224, a synthetic document and an annotation document are generated from the markup language document... multiple instances of element 220 may be used to generate multiple, diverse synthetic documents and corresponding annotation documents” Srivastava, Col 7 ln 8-19; wherein the element size and style indicate a type of font size and type “annotation document 700 includes a list of words that appear in the respective synthetic document... For words 1 and 2 of type text, the style of the word (font size, type, and color) are provided” Srivastava, Col 10 ln 46-54) . Regarding claim 10, Srivastava teaches a non-transitory storage medium having stored therein instructions that are executable by one or more hardware processors to perform operations comprising (non-transitory storage medium, Srivastava Col 20 ln 44; one or more processors, Srivastava Col 19 ln 38) : wherein the document template is associated with fields and positions of the fields within the document template (“General categories of document elements that may be extracted from real-world documents 10A and represented by element templates 22 in the repository 170 may include one or more of, but are not limited to, text elements (numeric symbols, letters, punctuation symbols, short words, long words, regular words, hyphenated words, etc.), key-value elements (single key-single value elements, single key-multiple value elements, key-clickable value elements (for example, checkboxes), etc.), tables, columns, headers, footers, sections (e.g., text sections), or in general any category of element that may be found in real-world documents 10A. Multiple types of element templates 22 may be generated for a category of document element, each type of element template 22 representing a different style, form, and/or size for an element in that category. The element templates 22 may be tagged with identifiers” Srivastava, Col 4 ln 1-16; wherein the document elements are that of fields where the locations are known, “an annotation document may include information describing the element template 22 type, location, size, style, and content of the elements” Srivastava, Col 5 ln 14-16) ; (b) determining values for each of the fields in the document template (“a configuration for synthetic documents is derived from real-world documents. The configuration may specify which elements should be present in the synthetic documents (key-value pairs, tables, text, etc.). The configuration may also specify whether or not the layout of the elements is to be structured (e.g., number of rows and columns), and which styles the elements should adhere to” Srivastava, Col 6 ln 6-14) ; (c) filling the fields in the document template with the determined values to generate a filled document template (“The configuration may specify which elements should be present in the synthetic documents (key-value pairs, tables, text, etc.). The configuration may also specify whether or not the layout of the elements is to be structured (e.g., number of rows and columns), and which styles the elements should adhere to... element template types, styles, and layouts for the synthetic documents are determined for the configuration. In some embodiments, a controller receives the configuration that was derived from real-world documents at 200, analyzes the configuration according to a set of rules to determine which types of element templates should be used to generate the synthetic documents, and generates a configuration file (e.g., a JSON file) that indicates the types of element templates and weights for the different types of element templates based on the received configuration” Srivastava, Col 6 ln 10-27) ; and (d) generating a synthetic document from the filled document template, wherein the synthetic document includes an image of the filled document template and a label that includes ground truth for each of the filled fields (“synthetic documents and corresponding annotation documents are generated based on the configuration” Srivastava, Col 6 ln 33-34; wherein the annotation documents correspond to ground truth; Additionally, the synthetic document is an image “an image or screenshot of the rendered markup language document may be captured to generate the synthetic document” Srivastava, Col 7 ln 22-24) . Srivastava fails to explicitly teach (a) selecting a document template. However, Dong teaches (a) selecting a document template (“select the corresponding template in the template database” Dong, top of pg. 3). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Srivastava of having a method wherein the document template is associated with fields and positions of the fields within the document template; determining values for each of the fields in the document template; filling the fields in the document template with the determined values to generate a filled document template; and generating a synthetic document from the filled document template, wherein the synthetic document includes an image of the filled document template and a label that includes ground truth for each of the filled fields with the teachings of Dong of having selecting a document template. Wherein having Srivastava method of generating a synthetic document having selecting a document template. The motivation behind the modification would have been to obtain a method of generating synthetic documents that improves classification of real-world documents such as forms, receipts, and dense text documents using machine learning models, since Srivastava and Dong relate to using document template generation. Wherein Srivastava element templates are extracted from real-world documents and stored in an element template repository, while Dong is for facilitating the calling and modifications of template documents having certain document structures. Please see Srivastava et al. (US 11087081 B1), Col 3 ln 54-58 and Dong et al. (CN 108595398 A), top of page 3. Regarding claim 11, Srivastava in view of Dong teach the non-transitory storage medium of claim 10, Srivastava fails to explicitly teach wherein the document template is selected from a library of document templates. However, Dong teaches wherein the document template is selected from a library of document templates (“select the corresponding template in the template database” Dong, top of pg. 3) . Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Srivastava of having a method wherein the document template is associated with fields and positions of the fields within the document template; determining values for each of the fields in the document template; filling the fields in the document template with the determined values to generate a filled document template; and generating a synthetic document from the filled document template, wherein the synthetic document includes an image of the filled document template and a label that includes ground truth for each of the filled fields with the teachings of Dong of having wherein the document template is selected from a library of document templates. Wherein having Srivastava method of generating a synthetic document wherein the document template is selected from a library of document templates. The motivation behind the modification would have been to obtain a method of generating synthetic documents that improves classification of real-world documents such as forms, receipts, and dense text documents using machine learning models, since Srivastava and Dong relate to using document template generation. Wherein Srivastava element templates are extracted from real-world documents and stored in an element template repository, while Dong is for facilitating the calling and modifications of template documents having certain document structures. Please see Srivastava et al. (US 11087081 B1), Col 3 ln 54-58 and Dong et al. (CN 108595398 A), top of page 3. Regarding claim 12, Srivastava in view of Dong teach the non-transitory storage medium of claim 10, Srivastava further teaches wherein the fields include simple fields, checkbox fields, and/or relational fields (“element templates 22 in the repository 170 may include one or more of, but are not limited to, text elements (numeric symbols, letters, punctuation symbols, short words, long words, regular words, hyphenated words, etc.), key-value elements (single key-single value elements, single key-multiple value elements, key-clickable value elements (for example, checkboxes), etc.), tables, columns, headers, footers, sections (e.g., text sections), or in general any category of element that may be found in real-world documents 10A” Srivastava, Col 4 ln 3-11) . Regarding claim 13, Srivastava in view of Dong teach the non-transitory storage medium of claim 12, Srivastava further teaches further comprising determining positions of each of the fields in the document template (“an annotation document may include information describing the element template 22 type, location, size, style, and content of the elements” Srivastava, Col 5 ln 14-16). Regarding claim 14, Srivastava in view of Dong teach the non-transitory storage medium of claim 13, Srivastava further teaches further comprising performing (b), (c), and (d) n times for each of a plurality of document templates to generate synthetic documents for each of the plurality of document templates (“new configurations can be generated to generate additional synthetic training data that includes new synthetic and annotation documents to further train the model 932 on the features or elements of real-world documents where the model underperforms. This process can be repeated to fine tune the machine learning model 932 to perform better when analyzing real-world documents” Srivastava, Col 13 ln 8-15) , wherein a font type and a font size are varied among the synthetic documents (“Content, size, style, and location of the element templates in the markup language documents may be randomized to provide diversity in the synthetic documents. As indicated at 224, a synthetic document and an annotation document are generated from the markup language document... multiple instances of element 220 may be used to generate multiple, diverse synthetic documents and corresponding annotation documents” Srivastava, Col 7 ln 8-19; wherein the element size and style indicate a type of font size and type “annotation document 700 includes a list of words that appear in the respective synthetic document... For words 1 and 2 of type text, the style of the word (font size, type, and color) are provided” Srivastava, Col 10 ln 46-54) . 07-21-aia AIA Claim (s) 6, 7, 9, 15, 16 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Srivastava et al. in view of Dong et al. and in further view of Jayaram et al. (US 20250371262 A1, hereinafter referred to as “Jayaram”) . Regarding claim 6, Srivastava in view of Dong teach the method of claim 5, Srivastava in view of Dong fail to explicitly teach further comprising varying a position of the determined values within the corresponding fields based on a probabilistic positioner. However, Jayaram teaches further comprising varying a position of the determined values within the corresponding fields based on a probabilistic positioner (“the one or more adjustments can optionally include adjustment of the field coordinates of one or more of the translated fields at 310. For example, to introduce variety into the training dataset, the ML model may slightly vary the position a given translated field relative to the position of the corresponding field in the master document. Different variations may be used for different fake documents within the training dataset. For example, if the field coordinates of a given translated field are [x, y, h, w], one fake document may have the adjusted field coordinates [x+1, y, h, w] for that translated field, whereas another fake document may have the adjusted field coordinates [x+1, y−1, h, w] for that translated field, etc.” Jayaram, [0058]) . Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Srivastava in view of Dong of having a method wherein the document template is associated with fields and positions of the fields within the document template; determining values for each of the fields in the document template; filling the fields in the document template with the determined values to generate a filled document template; and generating a synthetic document from the filled document template, wherein the synthetic document includes an image of the filled document template and a label that includes ground truth for each of the filled fields with the teachings of Jayaram of having varying a position of the determined values within the corresponding fields based on a probabilistic positioner. Wherein having Srivastava method of generating a synthetic document varying a position of the determined values within the corresponding fields based on a probabilistic positioner. The motivation behind the modification would have been to obtain a method of generating synthetic documents that improves classification of real-world documents such as forms, receipts, and dense text documents using machine learning models, since Srivastava and Jayaram relate to extracting document information. Wherein Srivastava element templates are extracted from real-world documents and stored in an element template repository and generate additional synthetic training data, while Jayaram is for extracting document information given a document type to serve for data augmentation. Please see Srivastava et al. (US 11087081 B1), Col 3 ln 54-58, ln 24-26 and Jayaram et al. (US 20250371262 A1), paragraph [0016]. Regarding claim 7, Srivastava in view of Dong and in further view of Jayaram teach the method of claim 6, Srivastava in view of Dong fail to explicitly teach further comprising generating values for the relational fields using a large language model, wherein the values for the relational fields are constrained to real-world ranges. However, Jayaram teaches further comprising generating values for the relational fields using a large language model (“The example fake document 412 generated by the LLM 410 is similar to master document 402... For example, the values of the documentNumber and documentDate header fields in the fake document 412 (i.e., the fields with the values “N° DE FACTURE: #567ABC” and “DATE DE FACTURE: Jan. 14, 2024”) have been slightly modified relative to the values of the corresponding documentNumber and documentDate header fields in the master document 402 (i.e., the fields in the master document 402 with the values “INVOICE NO: #123XYZ” and “INVOICE DATE: Jan. 2, 2024”)... the string “#123XYZ” has been modified to “#567ABC” and the date “Jan. 2, 2024” has been modified to “Jan. 14, 2024”” Jayaram, [0066]; wherein the fake values are in relational fields, such as a table form, from a large language model; See Fig. 4, part No. 412) , wherein the values for the relational fields are constrained to real-world ranges (“the values of the partNo, description, qty, eachPrice, and total line item fields in fake document 412 have each been modified relative to the corresponding line item field in master document 402” Jayaram, [0067]; wherein each fake value contains real world ranges such that the data may be used for generating a training dataset, see Jayaram, [0068]; additionally, the fake values correspond to real-world ranges such that part numbers and quantity for each part remains relevant, see [0066]) . Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Srivastava in view of Dong of having a method wherein the document template is associated with fields and positions of the fields within the document template; determining values for each of the fields in the document template; filling the fields in the document template with the determined values to generate a filled document template; and generating a synthetic document from the filled document template, wherein the synthetic document includes an image of the filled document template and a label that includes ground truth for each of the filled fields with the teachings of Jayaram of having further comprising generating values for the relational fields using a large language model, wherein the values for the relational fields are constrained to real-world ranges. Wherein having Srivastava method of generating a synthetic document further comprising generating values for the relational fields using a large language model, wherein the values for the relational fields are constrained to real-world ranges. The motivation behind the modification would have been to obtain a method of generating synthetic documents that improves classification of real-world documents such as forms, receipts, and dense text documents using machine learning models, since Srivastava and Jayaram relate to extracting document information. Wherein Srivastava element templates are extracted from real-world documents and stored in an element template repository and generate additional synthetic training data, while Jayaram is for extracting document information given a document type to serve for data augmentation. Please see Srivastava et al. (US 11087081 B1), Col 3 ln 54-58, ln 24-26 and Jayaram et al. (US 20250371262 A1), paragraph [0016]. Regarding 9 , Srivastava in view of Dong and in further view of Jayaram teach the method of claim 7, Srivastava further teaches further comprising training a model using the synthetic documents (“the synthetic 132 and annotation 142 documents may be input to a machine learning model 180 (e.g., a neural network) as training data” Srivastava, Col 5 ln 29-31) . Regarding claim 15, Srivastava in view of Dong teach the non-transitory storage medium of claim 14, Srivastava in view of Dong fail to explicitly teach further comprising varying a position of the determined values within the corresponding fields based on a probabilistic positioner. However, Jayaram teaches further comprising varying a position of the determined values within the corresponding fields based on a probabilistic positioner (“the one or more adjustments can optionally include adjustment of the field coordinates of one or more of the translated fields at 310. For example, to introduce variety into the training dataset, the ML model may slightly vary the position a given translated field relative to the position of the corresponding field in the master document. Different variations may be used for different fake documents within the training dataset. For example, if the field coordinates of a given translated field are [x, y, h, w], one fake document may have the adjusted field coordinates [x+1, y, h, w] for that translated field, whereas another fake document may have the adjusted field coordinates [x+1, y−1, h, w] for that translated field, etc.” Jayaram, [0058]) . Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Srivastava in view of Dong of having a method wherein the document template is associated with fields and positions of the fields within the document template; determining values for each of the fields in the document template; filling the fields in the document template with the determined values to generate a filled document template; and generating a synthetic document from the filled document template, wherein the synthetic document includes an image of the filled document template and a label that includes ground truth for each of the filled fields with the teachings of Jayaram of having varying a position of the determined values within the corresponding fields based on a probabilistic positioner. Wherein having Srivastava method of generating a synthetic document varying a position of the determined values within the corresponding fields based on a probabilistic positioner. The motivation behind the modification would have been to obtain a method of generating synthetic documents that improves classification of real-world documents such as forms, receipts, and dense text documents using machine learning models, since Srivastava and Jayaram relate to extracting document information. Wherein Srivastava element templates are extracted from real-world documents and stored in an element template repository and generate additional synthetic training data, while Jayaram is for extracting document information given a document type to serve for data augmentation. Please see Srivastava et al. (US 11087081 B1), Col 3 ln 54-58, ln 24-26 and Jayaram et al. (US 20250371262 A1), paragraph [0016]. Regarding claim 16, Srivastava in view of Dong and in further view of Jayaram teach the non-transitory storage medium of claim 15, Srivastava in view of Dong fail to explicitly teach further comprising generating values for the relational fields using a large language model, wherein the values for the relational fields are constrained to real-world ranges. However, Jayaram teaches further comprising generating values for the relational fields using a large language model (“The example fake document 412 generated by the LLM 410 is similar to master document 402... For example, the values of the documentNumber and documentDate header fields in the fake document 412 (i.e., the fields with the values “N° DE FACTURE: #567ABC” and “DATE DE FACTURE: Jan. 14, 2024”) have been slightly modified relative to the values of the corresponding documentNumber and documentDate header fields in the master document 402 (i.e., the fields in the master document 402 with the values “INVOICE NO: #123XYZ” and “INVOICE DATE: Jan. 2, 2024”)... the string “#123XYZ” has been modified to “#567ABC” and the date “Jan. 2, 2024” has been modified to “Jan. 14, 2024”” Jayaram, [0066]; wherein the fake values are in relational fields, such as a table form, from a large language model; See Fig. 4, part No. 412) , wherein the values for the relational fields are constrained to real-world ranges (“the values of the partNo, description, qty, eachPrice, and total line item fields in fake document 412 have each been modified relative to the corresponding line item field in master document 402” Jayaram, [0067]; wherein each fake value contains real world ranges such that the data may be used for generating a training dataset, see Jayaram, [0068]; additionally, the fake values correspond to real-world ranges such that part numbers and quantity for each part remains relevant, see [0066]) . Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Srivastava in view of Dong of having a method wherein the document template is associated with fields and positions of the fields within the document template; determining values for each of the fields in the document template; filling the fields in the document template with the determined values to generate a filled document template; and generating a synthetic document from the filled document template, wherein the synthetic document includes an image of the filled document template and a label that includes ground truth for each of the filled fields with the teachings of Jayaram of having further comprising generating values for the relational fields using a large language model, wherein the values for the relational fields are constrained to real-world ranges. Wherein having Srivastava method of generating a synthetic document further comprising generating values for the relational fields using a large language model, wherein the values for the relational fields are constrained to real-world ranges. The motivation behind the modification would have been to obtain a method of generating synthetic documents that improves classification of real-world documents such as forms, receipts, and dense text documents using machine learning models, since Srivastava and Jayaram relate to extracting document information. Wherein Srivastava element templates are extracted from real-world documents and stored in an element template repository and generate additional synthetic training data, while Jayaram is for extracting document information given a document type to serve for data augmentation. Please see Srivastava et al. (US 11087081 B1), Col 3 ln 54-58, ln 24-26 and Jayaram et al. (US 20250371262 A1), paragraph [0016]. Regarding 18 , Srivastava in view of Dong and in further view of Jayaram teach the non-transitory storage medium of claim 16, Srivastava further teaches further comprising training a model using the synthetic documents (“the synthetic 132 and annotation 142 documents may be input to a machine learning model 180 (e.g., a neural network) as training data” Srivastava, Col 5 ln 29-31) . 07-21-aia AIA Claim (s) 8 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Srivastava et al. in view of Dong et al. in view of Jayaram et al. and in further view of Hu et al. (US 20240177511 A1, hereinafter referred to as “Hu”) . Regarding claim 8 , Srivastava in view of Dong and in further view of Jayaram teach the method of claim 7, Srivastava in view of Dong and in further view of Jayaram fail to explicitly teach further comprising determining totals for numerical quantities in the relational fields. However, Hu teaches further comprising determining totals for numerical quantities in the relational fields (“equal amounts of diverse synthetic data may be obtained for each of the first to eighth keys 452, 456, 458, 460, 462, 464, 466, and 468” Hu, [0139]; wherein the eighth key may correspond to total price of items (e.g., indicating a relation of item, quantity and price), see “An eighth key 468 (“Item TotalPrice_1”) identifies a total price of the items purchased” Hu, [0132]-[0135]) . Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Srivastava in view of Dong and in further view of Jayaram of having a method wherein the document template is associated with fields and positions of the fields within the document template; determining values for each of the fields in the document template; filling the fields in the document template with the determined values to generate a filled document template; and generating a synthetic document from the filled document template, wherein the synthetic document includes an image of the filled document template and a label that includes ground truth for each of the filled fields with the teachings of Hu of having further comprising determining totals for numerical quantities in the relational fields. Wherein having Srivastava method of generating a synthetic document further comprising determining totals for numerical quantities in the relational fields. The motivation behind the modification would have been to obtain a method of generating synthetic documents that improves classification of real-world documents such as forms, receipts, and dense text documents using machine learning models, since Srivastava and Hu relate to generating synthetic document training data. Wherein Srivastava element templates are extracted from real-world documents and stored in an element template repository and generate additional synthetic training data, while Hu is for generating training data which contains synthetic text content that can be used for training machine learning models capable of processing document images. Please see Srivastava et al. (US 11087081 B1), Col 3 ln 54-58, ln 24-26 and Hu et al. (US 20240177511 A1), paragraph [0006]. Regarding claim 17 , Srivastava in view of Dong and in further view of Jayaram teach the non-transitory storage medium of claim 16, Srivastava in view of Dong and in further view of Jayaram fail to explicitly teach further comprising determining totals for numerical quantities in the relational fields. However, Hu teaches further comprising determining totals for numerical quantities in the relational fields (“equal amounts of diverse synthetic data may be obtained for each of the first to eighth keys 452, 456, 458, 460, 462, 464, 466, and 468” Hu, [0139]; wherein the eighth key may correspond to total price of items (e.g., indicating a relation of item, quantity and price), see “An eighth key 468 (“Item TotalPrice_1”) identifies a total price of the items purchased” Hu, [0132]-[0135]) . Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Srivastava in view of Dong and in further view of Jayaram of having a method wherein the document template is associated with fields and positions of the fields within the document template; determining values for each of the fields in the document template; filling the fields in the document template with the determined values to generate a filled document template; and generating a synthetic document from the filled document template, wherein the synthetic document includes an image of the filled document template and a label that includes ground truth for each of the filled fields with the teachings of Hu of having further comprising determining totals for numerical quantities in the relational fields. Wherein having Srivastava method of generating a synthetic document further comprising determining totals for numerical quantities in the relational fields. The motivation behind the modification would have been to obtain a method of generating synthetic documents that improves classification of real-world documents such as forms, receipts, and dense text documents using machine learning models, since Srivastava and Hu relate to generating synthetic document training data. Wherein Srivastava element templates are extracted from real-world documents and stored in an element template repository and generate additional synthetic training data, while Hu is for generating training data which contains synthetic text content that can be used for training machine learning models capable of processing document images. Please see Srivastava et al. (US 11087081 B1), Col 3 ln 54-58, ln 24-26 and Hu et al. (US 20240177511 A1), paragraph [0006] . Allowable Subject Matter 12-151-07 AIA 07-97 12-51-07 Claim 19 and its dependent 20 are allowed. 13-03-01 AIA The following is a statement of reasons for the indication of allowable subject matter: Regarding claim 19 , Srivastava teaches a computing system comprising a processor and configured to generate synthetic documents that each include an image of a document and a corresponding label (“Various embodiments of methods and apparatus for generating configuration-controlled synthetic documents for training machine learning models such as neural networks are described. A document analysis service or system may analyze real-world documents such as forms, receipts, and dense text documents using machine learning models (e.g., neural networks) to generate digital and semantic information for the documents” Srivastava Col 2, ln 17-14; see additionally, “The configuration allows for the extraction of defining elements and features (style, layout, element composition, content, etc.) from real-world forms and replicating the elements and features in synthetic documents with the required diversity. From the configuration, the system can generate a large number of synthetic documents and corresponding annotation documents in a short period of time” Srivastava, Col 3 ln 8-16) , the computing system comprising a document generation engine that includes: a field generator configured to generate values for fields of a document template using source, functions (“The configuration may specify which elements should be present in the synthetic documents (key-value pairs, tables, text, etc.). The configuration may also specify whether or not the layout of the elements is to be structured (e.g., number of rows and columns), and which styles the elements should adhere to... element template types, styles, and layouts for the synthetic documents are determined for the configuration. In some embodiments, a controller receives the configuration that was derived from real-world documents at 200, analyzes the configuration according to a set of rules to determine which types of element templates should be used to generate the synthetic documents, and generates a configuration file (e.g., a JSON file) that indicates the types of element templates and weights for the different types of element templates based on the received configuration” Srivastava, Col 6 ln 10-27) , and/or large language models, wherein the field generator varies font type, font size and positions of the values when the values are inserted into the fields (“Content, size, style, and location of the element templates in the markup language documents may be randomized to provide diversity in the synthetic documents. As indicated at 224, a synthetic document and an annotation document are generated from the markup language document... multiple instances of element 220 may be used to generate multiple, diverse synthetic documents and corresponding annotation documents” Srivastava, Col 7 ln 8-19; wherein the element size and style indicate a type of font size and type “annotation document 700 includes a list of words that appear in the respective synthetic document... For words 1 and 2 of type text, the style of the word (font size, type, and color) are provided” Srivastava, Col 10 ln 46-54) , wherein the document template defines the fields and positions of the fields (“an annotation document may include information describing the element template 22 type, location, size, style, and content of the elements” Srivastava, Col 5 ln 14-16) , the fields including simple fields, checkbox fields, and relational fields (“element templates 22 in the repository 170 may include one or more of, but are not limited to, text elements (numeric symbols, letters, punctuation symbols, short words, long words, regular words, hyphenated words, etc.), key-value elements (single key-single value elements, single key-multiple value elements, key-clickable value elements (for example, checkboxes), etc.), tables, columns, headers, footers, sections (e.g., text sections), or in general any category of element that may be found in real-world documents 10A” Srivastava, Col 4 ln 3-11) ; a smart checking engine configured to fill out the checkbox fields using a probability distribution (“The configuration may specify which elements should be present in the synthetic documents (key-value pairs, tables, text, etc.). The configuration may also specify whether or not the layout of the elements is to be structured (e.g., number of rows and columns), and which styles the elements should adhere to. In addition, a weight may be specified for each element to attain a weighted probabilistic distribution of elements in the synthetic documents” Srivastava, Col 6 ln 8-16) , wherein a ticker character for filling the checkbox fields is varied in font type, font size and position within the checkbox fields (“element templates 22 in the repository 170 may include one or more of, but are not limited to, text elements (numeric symbols, letters, punctuation symbols, short words, long words, regular words, hyphenated words, etc.), key-value elements (single key-single value elements, single key-multiple value elements, key-clickable value elements (for example, checkboxes), etc.), tables, columns, headers, footers, sections (e.g., text sections), or in general any category of element that may be found in real-world documents 10A” Srivastava, Col 4 ln 3-11) ; wherein the document generation engine outputs the synthetic documents (“a synthetic document generation method and system are described that provide a configuration-driven approach that addresses these problems with conventional methods. The synthetic document generation system takes a configuration (e.g., a JSON (JavaScript Object Notation) file) specifying which elements must be present in a form or document (key-value pairs, tables, checkboxes, text, etc.). The configuration may also specify whether or not the layout of the elements is structured (number of rows and columns), and which styles the elements should adhere to” Srivastava, Col 2-3 ln 61-3; wherein “the system can generate a large number of synthetic documents and corresponding annotation documents in a short period of time” Srivastava, Col 3 ln 14-16) . However, Jayaram fails to explicitly teach a special field generator configured to generate relational field values for the relational fields using a large language model, wherein the relational field values are constrained tuples according to real-world ranges; a filler engine configured to collect data generated by the field generator, the smart checking engine, and the special field generate to fill an instance of the document template. The references stated above and in the conclusion section neither alone, nor in combination teach or suggest the uniquely combined elements and method steps in the order of the named computing system comprising a processor and configured to generate synthetic documents that each include an image of a document and a corresponding label, the computing system comprising a document generation engine that includes, wherein a special field generator configured to generate relational field values for the relational fields using a large language model, wherein the relational field values are constrained tuples according to real-world ranges; a filler engine configured to collect data generated by the field generator, the smart checking engine, and the special field generate to fill an instance of the document template, nor the motivation to do so . Conclusion 07-96 AIA The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Streltsov et al. (US 20230334309 A1) – generates synthetic training data from an original unstructured electronic document and may be used to train a deep learning model to extract data from the original electronic document. Kaynig-Fittkau et al. (US 20210158093 A1) – generates diverse and realistic synthetic documents using deep learning comprising page elements that comply with layout parameters and insert synthetic content into the corresponding page elements to generate synthetic documents. Goodsitt et al. (US 10482174 B1) – generates synthetic documents with synthetic data from a plurality of documents by determining features on a plurality of documents; generate a distribution of values for a corresponding pixel in the individual documents of plurality of documents; determine, based on the distributions, one or more common features of the plurality of documents; determine, based on the comparison, one or more input fields; generate a template including the one or more common features and the one or more input fields; and input synthetic data into the one or more input fields of the template thereby generating a plurality of synthetic documents. Inquiries Any inquiry concerning this communication or earlier communications from the examiner should be directed to EMMANUEL SILVA-AVINA whose telephone number is (571)270-0729. The examiner can normally be reached Monday - Friday 11 AM - 8 PM EST. 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, Chineyere Wills-Burns can be reached at (571) 272-9752. 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. /EMMANUEL SILVA-AVINA/Examiner, Art Unit 2673 /CHINEYERE WILLS-BURNS/Supervisory Patent Examiner, Art Unit 2673 Application/Control Number: 18/899,048 Page 2 Art Unit: 2673 Application/Control Number: 18/899,048 Page 3 Art Unit: 2673 Application/Control Number: 18/899,048 Page 4 Art Unit: 2673
Prosecution Insights