DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment
The Amendment filed on 03/30/2026 has been entered. Claims 1-20 remain pending in this application.
Response to Arguments
Applicant’s arguments filed on 03/30/2026 have been fully considered but are not persuasive.
With respect to the 35 U.S.C. 101 abstract idea rejection, on pages 7-11, the Applicant asserts that the elements of the claim integrate the claim into a practical application because the claim improves the technical field of process automation by allowing intelligent content generation based on generative artificial intelligence. The Applicant cites their specification for showing these improvements, namely that the disclosed system improves upon these conventional approaches by providing a platform (e.g., intelligent content generation computing platform 100) that “generate[s] a template (e.g., a task template comprising definitions of tasks having a particular order) for automation of process steps that may be used by automation solutions” (Specification para [0032]). The Applicant goes on to state, using para [0044] from their Specification, that the process of process automation is made more efficient overall. The Applicant also asserts that the improvement is reflected in the claims themselves. They also assert that none of the limitations listed in the independent claims are directed to mere mental processes, even under their broadest reasonable interpretation, as these are inherently technical concepts that require a data processor for implementation. The Applicant also cites the August 4th, 2025 USPTO Memorandum.
The Examiner respectfully disagrees. The original claims, and the claims as amended, are merely utilizing computer devices, in this specific case “a computing platform comprising one or more computing devices coupled to a database and in communication with a large language model via a network”, “the large language model”, and “a backend system”, as tools to perform a method which is directed to an abstract idea. The claim, under its broadest reasonable interpretation, recites a system for transmitting, analyzing, altering, and validating data (e.g., domain model data, task data). This is an abstract idea in the form of certain methods of organizing human activity (i.e. mental processes such as observation, evaluation, judgement, and opinion). The steps of exporting and processing the domain model data, modifying that data, and validating that data could be performed by a human using pen and paper or by purely mental reasoning, save for the recitation of generic computing components. Further, the claims do not integrate the judicial exception into a practical application. The recitation of “a computing platform comprising one or more computing devices coupled to a database and in communication with a large language model via a network”, “the large language model”, and “a backend system” are generic instructions to perform the abstract idea on a computer or using computer devices and does not impose a meaningful limit on the judicial exception. The “a computing platform comprising one or more computing devices coupled to a database and in communication with a large language model via a network”, “the large language model”, and “a backend system” are recited at such high-levels of generality and are used merely as tools to perform the abstract idea faster or more efficiently. There is no reasonable improvement to the functioning of the data transmission, data analyzation, data alteration, data validation, the computing platform itself, the large language model itself, the backend system itself, nor to any other technology or technical field. The claims do not include any additional elements that amount to significantly more that the judicial exception. The claims, as written and amended, do not include more than mere instructions to perform the abstract method using generic computer components. Hence, Applicant’s arguments are not persuasive.
With respect to the 35 U.S.C. 103 rejection, on pages 11-14, of claims 1-20 under Carr et al. (US Patent No. 10,402,380), hereinafter referred to as Carr, in view of Zhang et al. (US Patent Application Publication No. 2025/0190449), hereinafter referred to as Zhang, the Applicant asserts that neither Carr nor Zhang disclose or render obvious the limitations of claim 1, specifically “in response to performing the content validation and the schema validation, correcting invalid tasks, wherein the correcting is repeated and performed recursively by the computing platform until the modified task template enriched with the data from the backend system is validated”. The Applicant asserts that since a user, per Carr Fig. 4, is performing the steps of the process, that then the limitations are not being performed “by a computing platform comprising one or more computing devices couple to a database and in communication with a large language model via a network”, and therefore are also not being repeated and performed recursively in an automated fashion, by a computing platform.
The Examiner respectfully disagrees. In response to the argument that Carr does not disclose “in response to performing the content validation and the schema validation, correcting invalid tasks, wherein the correcting is repeated and performed recursively by the computing platform until the modified task template enriched with the data from the backend system is validated”, Carr Fig. 4 reference character 420 shows moving back to reference character 414 in rules-creation process, or correcting invalid tasks. This process is shown to be recursive, per reference character 420 moving back to reference character 414. The added limitation of this being performed “by a computing platform comprising one or more computing devices couple to a database and in communication with a large language model via a network” does not prevent this limitation from being performed by a human, or a user, utilizing said system. The system in this case and limitation is merely used as a tool by a user to perform this task correction. Also, the assertion that because the process is being performed by a user, i.e. in a manual fashion, it is therefore not being performed recursively, is incorrect, and the claim that it need be automatic is moot. The limitations mention nothing about this process being performed automatically, and manual processes can be recursive. Hence, the Applicant’s arguments are not persuasive.
Claim Rejections - 35 USC § 101
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) 1-20 rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. Independent claims 1, 8, and 15 recite “exporting, by a computing platform comprising one or more computing devices couple to a database and in communication with a large language model via a network a domain mode”, “providing, by the computing platform and to the large language model, a prompt and a context window”, “modifying, using the large language model, a task template”, “enriching, by the computing platform, the modified task template”, “performing, by the computing platform, content validation”, “performing, by the computing platform, schema validation”, “correcting invalid tasks”, and “applying, by the computing platform, changes to the domain model”. These limitations, as drafted, are a process that, under a broadest reasonable interpretation, covers the abstract idea of “mental processes” because they cover concepts performed in the human mind, including observation, evaluation, judgement, and opinion. See MPEP 2106.04(a)(2). That is, other than reciting “by a computing platform comprising one or more computing devices coupled to a database and in communication with a large language model via a network”, “by the large language model”, “by the computing platform”, “a backend system”, and “using the large language model”, nothing in the claimed elements preclude the steps from practically being performed by a person using generic computer components to alter a domain model.
This judicial exception is not integrated into a practical application because the additional elements “by a computing platform comprising one or more computing devices coupled to a database and in communication with a large language model via a network”, “by the large language model”, “by the computing platform”, and “using the large language model” are all recited at a high-level of generality. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Thus, the claims as a whole are directed to an abstract idea (Step 2A, prong two).
Claims 1, 8, and 15 do not include any additional elements that are sufficient to amount to significantly more than the judicial exception because, as discussed above with respect to integration of the abstract idea into a practical applications, the additional elements of “by a computing platform comprising one or more computing devices coupled to a database and in communication with a large language model via a network”, “by the large language model”, “by the computing platform”, and “using the large language model” amount to no more than mere instructions to apply the exception using generic computer components. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept (Step 2B).
Dependent claims 2-7, 9-14, and 16-20 are directed to attributes of exporting the domain model, the task template, the prompt, and validation. That is, nothing in the claimed elements preclude the steps from practically being performed by a person using generic computer components to alter a domain model. No additional elements are present. Thus, the claims as a whole are directed to an abstract idea.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Carr et al. (US Patent No. 10,402,380), hereinafter referred to as Carr, in view of Zhang et al. (US Patent Application Publication No. 2025/0190449), hereinafter referred to as Zhang.
Regarding claim 1, Carr discloses a system, comprising: at least one processor; and at least one memory storing instructions, which when executed by the at least one processor, result in operations comprising (Carr col. 2 lines 37-53):
a domain model for processing (Carr col. 3 lines 46-56, the domain model being structured into tasks according to a defined schema ("ANSI X12 represents a standard data interchange format across industries," Carr col. 1 lines 34-35),
modifying a task template associated with the task (Carr Fig. 4 reference characters 414, 416, and 418);
enriching by the computing platform, the modified task template with data from a backend system in communication with the computing platform via the network (Carr col. 13 lines 12-16);
performing, by the computing platform, content validation on content of the modified task template enriched with the data from the backend system (Carr Fig. 4 reference character 420);
performing, by the computing platform, schema validation for validating the modified task template enriched with the data from the backend system against the defined schema (Carr Fig. 4 reference character 420);
in response to performing the content validation and the schema validation, correcting invalid tasks, wherein the correcting is repeated and performed recursively by the computing platform until the modified task template enriched with the data from the backend system is validated (Carr Fig. 4 reference character 420 shows moving back to reference character 414, i.e. showing recursive validation);
and applying, by the computing platform, changes to the domain model (Carr Fig. 4 reference characters 422 and 424).
However, Carr fails to disclose exporting, by a computing platform comprising one or more computing devices couple to a database and in communication with a large language model via a network a domain model for processing by the large language model, wherein exporting the domain model comprises generating a text file comprising code that represents structured data; providing, by the computing platform and to the large language model, a prompt and a context window associated with a task of the domain model; modifying, using the large language model.
Zhang teaches a method for generative artificial intelligence assisted analytics of structured data.
Zhang teaches exporting, by a computing platform comprising one or more computing devices couple to a database and in communication with a large language model via a network a domain model ("the structured data set 154 may include numerical data, text data,..., In some implementations, the structured data set 154 includes a plurality of tables, and each table of the plurality of tables is organized according to one of a plurality of table types that each have associated fields, and such organization may be indicated by one or more data schemas," Zhang para [0030] and Zhang Fig. 1 shows system 100 that has computing device 102, user device 150, memory 106, generative AI agents 126, generative AI models 128, AI model(s) 125, and network(s) 140) for processing by the large language model (Zhang Fig. 9), wherein exporting the domain model comprises generating a text file comprising code that represents structured data ("For example, the structured data set 154 may include numerical data, text data, Boolean data, string data, binary data, other types of data, or a combination thereof," Zhang para [0030]);
providing, by the computing platform and to the large language model, a prompt and a context window associated with a task of the domain model ("If at least one of the entities are not present in the user prompt, the process flow 600 proceeds from 612 to 616, and a contextual phrase is added to the user prompt to update the user prompt," Zhang para [0075]);
modifying, using the large language model (Zhang Fig. 9).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Carr’s method of transforming the schema of a domain task by including Zhang’s teaching of utilizing a large language model to analyze and modify structured data. Using a large language model to modify a domain model/task would boost efficiency and accuracy of shifting between different domains and different tasks. It would allow for the automation of domain/task shifting while lessening the time and cost it would take for humans to accomplish the same.
Regarding claim 2, Carr, in view of Zhang, discloses all of the limitations of claim 1. However, Carr fails to disclose wherein exporting the domain model comprises exporting a portion of the domain model including a specific task and a specific field.
Zhang teaches wherein exporting the domain model comprises exporting a portion of the domain model including a specific task and a specific field ("In some implementations, the structured data set 154 includes a plurality of tables, and each table of the plurality of tables is organized according to one of a plurality of table types that each have associated fields, and such organization may be indicated by one or more data schemas," Zhang para [0030]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Carr’s method of transforming the schema of a domain task by including Zhang’s teaching of exporting the structured data with specific fields and schemas. Structured data with specific fields helps to streamline data management, analysis, and it also helps the user to understand the data and domain model better.
Regarding claim 3, Carr, in view of Zhang, discloses all of the limitations of claim 1. Carr further discloses wherein enriching the modified task template with the data from a backend system comprises merging the modified task template with user specific data that is not available to the large language model (Carr col. 13 lines 8-25).
Regarding claim 4, Carr, in view of Zhang, discloses all of the limitations of claim 1. Carr further discloses wherein the task template is written in a data interchange format storing data objects and structures ("ANSI X12 represents a standard data interchange format across industries," Carr col. 1 lines 34-35).
Regarding claim 5, Carr, in view of Zhang, discloses all of the limitations of claim 1. However, Carr fails to disclose wherein the prompt comprises a set of instructions provided to the large language model for receiving a specific response.
Zhang teaches wherein the prompt comprises a set of instructions provided to the large language model for receiving a specific response (Zhang Fig. 9 shows a prompt, prompts to LLMs inherently contain instructions).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Carr’s method of transforming the schema of a domain task by including Zhang’s teaching of including a prompt that is comprised of a set of instructions as input to a large language model. Prompts, when being used as inputs to large language models, are inherently comprised of instructional statements and/or questions. A prompt comprised of a set of instructions is inherently part of the prompt itself.
Regarding claim 6, Carr, in view of Zhang, discloses all of the limitations of claim 1. Carr further discloses further comprising, in response to performing the content validation and the schema validation: identifying one or more invalidations associated with the modified task template enriched with the data from the backend system ("This would result in a failed validation. The validation process confirms that required inputs and outputs for a node are connected properly and logically, e.g., confirms that the user did not map an element in the wrong place," Carr col. 13 lines 21-25);
and initiating a display of the one or more invalidations ("Interface 512 provides an interactive display where a user may select various nodes from Panel 502 to create and define a specific rules set," Carr col. 12 lines 41-43, inherently displays the ongoing process and thereby displays the invalidations).
Regarding claim 7, Carr, in view of Zhang, discloses all of the limitations of claim 1. However, Carr fails to disclose prior to applying changes to the domain model, requesting user input for granting or denying a change to the domain model.
Zhang discloses prior to applying changes to the domain model, requesting user input for granting or denying a change to the domain model (Zhang Fig. 12 reference characters 1118, 1120, and 1122).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Carr’s method of transforming the schema of a domain task by including Zhang’s teaching of taking in user input before applying changes to the model. User input is crucial for ensuring accuracy, relevance, and alignment with the original prompt. Users would be able to catch and correct factual errors, like hallucinations, and other errors that might not be conducive with the original prompt.
As to claims 8-14, method claims 8-14 and system claims 1-7 are related as system and method of using same, with each claimed element’s function corresponding to the system step, respectively. Accordingly, claims 8-14 are similarly rejected under the same rationale as applied above with respect to the system claims.
As to claims 15-18, computer-readable medium (CRM) claims 15-18 and system claims 1-4 are related as system and CRM of using same, with each claimed element’s function corresponding to the system step, respectively. Accordingly, claims 15-18 are similarly rejected under the same rationale as applied above with respect to the system claims.
As to claims 19-20, CRM claims 19-20 and system claims 6-7 are related as system and CRM of using same, with each claimed element’s function corresponding to the system step, respectively. Accordingly, claims 19-20 are similarly rejected under the same rationale as applied above with respect to the system claims.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ADAM MICHAEL WEAVER whose telephone number is (571)272-7062. The examiner can normally be reached Monday-Friday, 8AM-5PM 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, Richemond Dorvil can be reached at (571) 272-7602. 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.
/ADAM MICHAEL WEAVER/ Examiner, Art Unit 2658
/RICHEMOND DORVIL/ Supervisory Patent Examiner, Art Unit 2658
Prosecution Insights