DETAILED ACTION
Notice of Pre-AIA or AIA Status
[1] The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Notice to Applicant
[2] This communication is in response to the amendment filed 7 January 2026. Claims 1 and 12 have been amended. Claims 1-20 are pending.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
[3] Claim(s) 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ngiam et al. (United States Patent Application Publication No. 2025/0045027 hereinafter ‘Ngiam’) in view of Chakhvadze et al. (United States Patent Application Publication No. 2025/0045025 hereinafter ‘Chakhvadze’) and further in view of Tunstall-Pedoe et al. (United States Patent Application Publication No. 2023/0274089 hereinafter ‘Tunstall-Pedoe’)
With respect to (currently amended) claim 1, Ngiam discloses a system comprising: a computer that includes a processor and a memory, the memory including instructions executable by the processor to: determine when a natural language requirement statement includes an atomic statement using a large language model (LLM) neural network based on a first prompt statement that includes a first request to label the natural language requirement statement, a description of a requirements language, and the natural language requirement statement (Ngiam et al.; paragraphs [0029] [0010]-[0111] [0323]-[0325]; See at least first LLM prompt including natural language text describing sequence of operations to be translated into executable code. See further analysis and criteria for determining atomic and non-atomic operations from the natural language description); when the LLM determines that the natural language requirement statement is atomic, translate the natural language requirement statement into the requirements language using the LLM based on a second prompt statement that includes a second request to translate the natural language requirement into the requirements language, the natural language requirement statement, and the description of the requirements language (Ngiam et al.; paragraphs [0029] [0115] [0324][0325] [0335] [0344]]; See at least second LLM prompt to create code including atomic statements and decomposed complex statements and further specifying code instructions that are permitted), wherein second output from the LLM includes an atomic requirements language statement (Ngiam et al.; paragraphs [0325]-[0328] [0335]-[0336]; See at least output code based on atomic statements); and output the atomic requirements language statement (Ngiam et al.; paragraphs [0325]-[0328] [0335]-[0336]; See at least output code based on atomic statements).
While Ngiam discloses determining whether text input statements are atomic or non-atomic and initiating a decomposition of complex operations into atomic sub-operations prior to code translation, Ngiam fails to state that an explanation statement indicating reasons a statement is not atomic is provided or further included or applied during the subsequent decomposition of non-atomic statements into atomic, i.e., singularly coded, atomic sub-operations.
However, as evidenced by Chakhvadze, it well-known in the art to generate an embedded hint by an LLM receiving a prompt in response to a determination that an input statement is not atomic and to further include the hint in a second prompt to direct code translation by an LLM (Chakhvadze et al.; paragraphs [0021] [0027]; See at least generation of an embedded hint in response to determination that an input request statement is not atomic. See further inclusion of the hint in follow up prompts to translate text input into executable code. The embedded hint is reasonably a form of explanation).
Claim 1 has been amended with respect to the subject “requirements language” to further specify “…wherein the requirements language is defined by a formal grammar…”.
With respect to this element, as noted above, Ngiam discloses determining whether text input statements are atomic or non-atomic and initiating a decomposition (i.e., refactoring) of complex operations into atomic sub-operations prior to code translation. While the output language of Ngiam is a structured language, i.e., a computer programming language, Ngiam fails to specify that the structured output language is defined by a formal grammar. Chakhvadze fails to remedy the deficiencies of Ngiam.
However, as evidenced by Tunstall-Pedoe, it is well-known to define an output requirements language by a formal grammar. Specifically, Tunstall-Pedoe discloses construction of input statements to an LLM to generate atomic output statements in a universal language, wherein the universal language is constructed using a formal grammar (Tunstall-Pedoe et al.; paragraphs [0023]-[0025] [0232]-[0236]; See at least prompt inputs and translation to UL atomic/complete UL statements. See further UL outputs defined by a specified grammar).
It would have been obvious to one of ordinary skill in the art at the time the invention was made to have modified the decomposition of non-atomic statements into atomic statements responsive to a determination that an input statement is non-atomic of Ngiam by further including utilizing a neural network LLM for the generation of an embedded hint/explanation to guide decomposition/refactoring of the input in response to a determination that an input request statement is not atomic as taught by Chakhvadze. The instant invention is directed to a system and method for translation of natural language inputs/process descriptions into executable systems engineering languages. As Ngiam disclose the use of decomposition of non-atomic statements into atomic statements responsive to a determination that an input statement is non-atomic in the context of a system and method for translation of natural language inputs/process descriptions into executable systems engineering languages and Chakhvadze similarly discloses the utility of a neural network LLM for the generation of an embedded hint/explanation to guide decomposition/refactoring of the input in response to a determination that an input request statement is not atomic in the context of a system and method for translation of natural language inputs/process descriptions into executable systems engineering languages, the teachings are reasonably considered to have been derived from analogous references and applied in the manner disclosed by the respective references. Accordingly, one of ordinary skill in the art would have been motivated to make the noted combination/modification as rationalized by combining prior art elements accordingly to known methods to yield the predictable results of managing complexity and improving ease of use in generating machine-executable language from general descriptions of a system process.
Regarding the combination that includes Tunstall-Pedoe, it would have been obvious to one of ordinary skill in the art at the time the invention was made to have modified the decomposition of non-atomic statements into atomic statements responsive to a determination that an input statement is non-atomic of Ngiam by further requiring the output language to generate atomic language statements defined by specified rules or a formal applied grammar as taught by Tunstall-Pedoe. The instant invention is directed to a system and method for translation of natural language inputs/process descriptions into executable systems engineering languages. As Ngiam disclose the use of decomposition of non-atomic statements into atomic statements in the context of a system and method for translation of natural language inputs/process descriptions into executable systems engineering languages and Tunstall-Pedoe similarly discloses the utility of requiring the output language to generate atomic language statements defined by specified rules or a formal applied grammar in the context of a system and method for translation of natural language inputs/process descriptions into executable systems engineering languages, the teachings are reasonably considered to have been derived from analogous references and applied in the manner disclosed by the respective references. Accordingly, one of ordinary skill in the art would have been motivated to make the noted combination/modification as rationalized by combining prior art elements accordingly to known methods to yield the predictable results of managing complexity and improving ease of use in generating universal machine-executable language by applying defined grammar to the output language to ensure consistency of functions derived from general descriptions of a system process.
With respect to claim 2, Ngiam discloses a system the instructions including further instructions to: when the first output indicates that the natural language requirement statement is not atomic, use the LLM to refactor the natural language requirement statement into a refactored natural language requirement statement (Ngiam et al.; paragraphs [0029] [0115] [0324][0325] [0335] [0344]]; See at least second LLM prompt to create code including atomic statements and decomposed complex statements and further specifying code instructions that are permitted) based on a third prompt statement that includes a third request to refactor the natural language requirement statement, the description of the requirements language, and the natural language requirement statement and wherein third output from the LLM includes the refactored natural language requirement including one or more atomic requirements language statements (Ngiam et al.; paragraphs [0325]-[0328] [0335]-[0336]; See at least output code based on atomic statements derived from decomposition, i.e., “refactoring” of complex statement); and translate the one or more natural language requirements statements included in the refactored natural language statement into one or more atomic requirements language statements using the LLM based on a fourth prompt that includes a fourth request to translate the one or more natural language requirement statements included in the refactored natural language statements into the requirements language and the description of the requirements language wherein fourth output from the LLM includes the one or more atomic requirements language statements (Ngiam et al.; paragraphs [0029] [0115] [0324][0325] [0335] [0344]]; See at least second LLM prompt to create code including atomic statements and decomposed complex statements and further specifying code instructions that are permitted); and output the one or more atomic requirements language statements (Ngiam et al.; paragraphs [0325]-[0328] [0335]-[0336]; See at least output code based on atomic statements. NOTE: the second prompt of Ngiam includes revision of the initial prompt to further include the decomposed complex statement(s). The iterative prompts are reasonably “third” and “fourth” prompts to the LLM as the input statement are iterative decomposed/refactored).
With respect to the recitation of “explanation statement”, as noted above, Ngiam discloses determining whether text input statements are atomic or non-atomic and initiating a decomposition of complex operations into atomic sub-operations prior to code translation, Ngiam fails to state that an explanation statement indicating reasons a statement is not atomic is provided or further included or applied during the subsequent decomposition of non-atomic statements into atomic, i.e., singularly coded, atomic sub-operations.
However, as evidenced by Chakhvadze, it well-known in the art to generate an embedded hint by an LLM receiving a prompt in response to a determination that an input statement is not atomic and to further include the hint in a second prompt to direct code translation by an LLM (Chakhvadze et al.; paragraphs [0021] [0027]; See at least generation of an embedded hint in response to determination that an input request statement is not atomic. See further inclusion of the hint in follow up prompts to translate text input into executable code. The embedded hint is reasonably a form of explanation).
Regarding claim 2, the conclusions of obviousness and rationale to modify as established for claim 1 above are applicable to claim 2 and are hereby incorporated by reference.
With respect to claim 3, Ngiam discloses a system wherein the natural language requirement statement is atomic when the natural language requirement statement describes one or more of a single function, a single feature, a single need, a single specification, or a single capability of a manufactured product (Ngiam et al.; paragraphs [0078] [0325]; See at least atomic vs non-atomic operations where atomic operations can be directly applied to create and execute a code segment, i.e., a single feature or function of the generated code product).
With respect to claim 4, Ngiam discloses a system wherein the requirements language is a language for writing requirements for systems engineering that includes the atomic requirements language statements (Ngiam et al.; paragraphs [0323]-[0330]; See at least atomic statements directly executed by creating code from natural language input. See further complex non-atomic operations decomposed into atomic operations).
With respect to claim 5, Ngiam discloses a system wherein the atomic requirements language statements include SHALL statements, WHEN statements, IF-THEN statements, WHILE statements, and WHERE statements (Ngiam et al.; paragraphs [0078] [0323]-[0325]; See at least definition of atomic statement including any statement that can be directly translated into executable code, i.e., reasonably inclusive of the above listed statements).
With respect to claim 6, Ngiam discloses a system wherein the atomic requirements language statements include combinations of one or more atomic requirements language statements (Ngiam et al.; paragraphs [0323]-[0330]; See at least complex non-atomic operations decomposed into atomic operations).
With respect to claim 7, Ngiam discloses a system wherein the LLM is as inputs natural language requirements statements and outputs natural language statements or the atomic requirements language statements (Ngiam et al.; paragraphs [0029] [0010]-[0111] [0323]-[0325]; See at least first LLM prompt including natural language text describing sequence of operations to be translated into executable code).
However, as evidenced by Chakhvadze, it well-known in the art to utilize neural network to embody a large language artificial intelligence model (Chakhvadze et al.; paragraph [0039]; See at least large language model embodied by an artificial neural network).
Regarding claim 7, the conclusions of obviousness and rationale to modify as established for claim 1 above are applicable to claim 7 and are hereby incorporated by reference.
With respect to claim 8, Ngiam discloses a system wherein the first prompt and the second prompt include conditional chaining (Ngiam et al.; paragraphs [0112] [0116] and Tables 3 and 4; See at least conditional statements).
With respect to claim 9, Ngiam discloses a system wherein the second prompt includes requirements language rules (Ngiam et al.; paragraphs [0029] [0010]-[0111] [0323]-[0325]; See at least first LLM prompt including natural language text describing sequence of operations to be translated into executable code. See further analysis and criteria for determining atomic and non-atomic operations from the natural language description).
With respect to the recitation of “explanation statement”, as noted above, Ngiam discloses determining whether text input statements are atomic or non-atomic and initiating a decomposition of complex operations into atomic sub-operations prior to code translation, Ngiam fails to state that an explanation statement indicating reasons a statement is not atomic is provided or further included or applied during the subsequent decomposition of non-atomic statements into atomic, i.e., singularly coded, atomic sub-operations.
However, as evidenced by Chakhvadze, it well-known in the art to generate an embedded hint by an LLM receiving a prompt in response to a determination that an input statement is not atomic and to further include the hint in a second prompt to direct code translation by an LLM (Chakhvadze et al.; paragraphs [0021] [0027]; See at least generation of an embedded hint in response to determination that an input request statement is not atomic. See further inclusion of the hint in follow up prompts to translate text input into executable code. The embedded hint is reasonably a form of explanation).
Regarding claim 9, the conclusions of obviousness and rationale to modify as established for claim 1 above are applicable to claim 9 and are hereby incorporated by reference.
With respect to claim 10, Ngiam discloses a system wherein first prompt and the second prompt include one or more of an instruction, context data, an output indicator, and input data (Ngiam et al.; paragraphs [0029] [0343]-[0345]; See at least first prompt including text describing a sequence of operations to be translated. See second prompt including instruction to create code, i.e., translate text input/plan into code language, i.e., requirement language).
With respect to claim 11, Ngiam discloses a system wherein context data includes background data to guide the LLM in performing a processing task included in the instruction (Ngiam et al.; paragraphs [0029] [0343]-[0345]; See at least first prompt including text describing a sequence of operations to be translated. See second prompt including instruction to create code, i.e., translate text input/plan into code language, i.e., requirements language).
[4] Claims 12-20 substantially repeat the subject matter addressed above with respect to claims 1-11 as directed to performed method/process. With respect to these elements, Ngiam discloses performance of the method/process steps employing the enabling systems and executable instructions. Accordingly, claims 12-20 are rejected under the applied teachings, conclusions obviousness, and rationale to modify as discussed above with respect to claims 1-11.
Response to Remarks/Amendment
[5] Applicant's remarks filed 7 January 2026 have been fully considered and are addressed as follows:
[i] Applicant’s remarks directed to previous rejection(s) of claim(s) 1-20 under 35 U.S.C. 103(a) as being unpatentable as set forth in the previous Office Action mailed 7 October 2025 have been fully considered and are convincing in light of the present amendments to the pending claims. The previous rejection of pending claims 1-20 under 35 U.S.C. 103 has/have been overcome by the amendments to the pending claims and is/are withdrawn.
[ii] Applicant’s remarks directed to previous rejection(s) of claim(s) 1-20 under 35 U.S.C. 103 as being unpatentable as set forth in the previous Office Action mailed 7 October 2025 have been fully considered and are moot in light of newly added grounds of rejection responsive to the amendments to the subject claims. See revised rejection under 35 U.S.C. 103 presented above.
Conclusion
[6] The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Cited NON-PATENT Literature:
White et al., A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT, 2023-02-21, Department of Computer Science, Vanderbilt University: Relevant Teachings: White discloses a system/method that provides a catalog and functions to generate catalogs of conversation prompts for LLMs. The publication establishes that prompt engineering to create novel interactions with existing LLMs as common practice in the art.
Cited PATENT Literature:
Mishra et al., IMPLICIT PROMPT REWRIWTING, United States Patent Application Publication No. 2025/0259020, paragraphs [0035]-[0040]: Relevant Teachings: Mishra discloses a system/method that includes steps/functions to prompt engineer input statements to optimize outputs of LLMs.
Kusch, SYSTEMS AND METHODS APPLYING LARGE LANGUAGE MODELS TO CONTRACT PRIORITIZATION, United States Patent Application Publication No. 2024/0420262, paragraphs [0026]-[0028]: Relevant Teachings: Kusch discloses a system/method that includes steps/functions in which input statements to a first LLM are parsed to generate inputs for second LLM which generates statements in a contractually compliant language.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 ROBERT D RINES whose telephone number is (571)272-5585. The examiner can normally be reached M-F 9am - 5pm.
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, Beth V Boswell can be reached at 571-272-6737. 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.
/ROBERT D RINES/Primary Examiner, Art Unit 3625
Prosecution Insights