DETAILED ACTION
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 07/07/2026 has been entered.
This communication is in response to the Amendments and Arguments filed on 07/07/2026.
Claims 1, 3-9, 11-17, 19, and 20 are pending and have been examined.
All previous objections/rejections not mentioned in this Office Action have been withdrawn by the examiner.
Notice of Pre-AIA or AIA Status
The present application is being examined under the pre-AIA first to invent provisions.
Response to Arguments
Regarding the rejection under 101, the Examiner notes that the rejection has been withdrawn. The claims now recite compilation and execution of the generated server files. When considered as a whole, the claims no longer fall under the –Mental Processes-- grouping of abstract ideas, and are patent eligible.
Applicant’s arguments with respect to claim(s) 1, 9, and 17 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. Please see the updated mappings below citing Stephens and Stephens 2 for further detail.
Claim Objections
Claims 3, 11, and 19 are objected to because of the following informalities: the claims recite “a schema file” and “a service file”. The Examiner suggests amending the claim(s) to recite –the schema file—and –the service file--, respectively, in order to maintain clear antecedent basis. Appropriate correction is required.
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.
Claim(s) 1, 3, 5-7, 9, 11, 13-15, 17, and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Jiang et al. (‘Discovering the Syntax and Strategies of Natural Language Programming with Generative Language Models’, ACM, 2022), hereinafter Jiang, in view of Stephens (U.S. PG Pub No. 2024/0354070, with support in provisional application No. 63/ 496,818), hereinafter Stephens, and further in view of Stephens et al. (U.S. PG Pub No. 2024/0354065, with support in provisional application No. 63/496,848), hereinafter Stephens 2.
Regarding claims 1, 9, and 17, Jiang teaches
(claim 1) A system comprising (a code synthesis tool enabling user input Fig.1,(Abstract, Intro)):
(claim 1) a generative artificial intelligence (GAI) model (natural language code synthesis tool using a large generative language model, i.e. generative artificial intelligence (GAI) model (Abstract));
(claim 1) a framework server configured to perform operations comprising (human computer interactions and computing, i.e. framework server configured to perform Fig. 1,(CCS concepts, Abstract, Intro)):
(claim 9) A method comprising (a code synthesis tool enabling user input Fig.1,(Abstract, Intro)):
(claim 17) …instructions which, when executed by one or more processors, cause the one or more processors to perform operations comprising (human computer interactions and computing, i.e. one or more processors…to perform operations, where the natural language code synthesis tool includes models and task-specific prompts, i.e. instructions, Fig. 1,(CCS concepts, Abstract, Intro, Sec. 3.1 and 3.2)):
receiving, from a framework client, a text-based prompt describing one or more services (the user can input into an interface, i.e. from a framework client, a text input for a prompt in a natural language format, i.e. receiving…a text-based prompt describing, as a description of a request for code, such as making a button or creating a flashcard app, i.e. describing one or more services Fig. 1,(Abstract, Intro));
creating a server generation request comprising the text-based prompt and a first pre-designed system message (when a tag is detected related to the input, i.e. comprising the text-based prompt, the input is incorporated into a task-specific prompt with examples is automatically loaded, i.e. a first pre-designed system message, and the prompt is loaded as input into the generative language model to execute the task, such as generating code, i.e. creating a server generation request Fig. 1,(Intro, Sec. 3.1 and 3.2, Appendix A and B));
feeding the server generation request to the GAI model to generate one or more server files …being …executable in the framework server, …(the task-specific prompt with incorporated user input, i.e. server generation request, fed into the generative language model, i.e. feeding…to the GAI model, to output code such as HTML or JavaScript and/or subtask suggestions, i.e. generate one or more server files, for a request such as making a To-Do app or a flashcard app, where the code result can be demonstrated, such as displaying the “Submit” button coded for in HTML, i.e. a software-based server service the one or more server files being…executable in the framework server Fig. 1,(Intro, Sec. 3.1 and 3.2, Appendix A and B)).
While Jiang provides generating code for apps from natural language using an LLM, Jiang does not specifically teach the declarative-based data model definition, where the server files comprise a schema and service file in a declarative model definition language defining the data model definition without describing its control flow, and thus does not teach
generate one or more server files specifying a declarative-based data model definition for a software-based server service, the one or more server files comprising a schema file and a service file in a declarative model definition language and being compilable and executable in the framework server, wherein a declarative model definition language is a language that defines the data model definition without describing its control flow;
compiling the one or more server files;
storing the one or more server files in the server repository; and
executing the one or more server files in the framework server to handle one or more requests for the software-based server service.
Stephens, however, teaches generate one or more server files specifying a declarative-based data model definition for a software-based server service, the one or more server files comprising a schema file and a service file in a declarative model definition language and being compilable and executable in the framework server, wherein a declarative model definition language is a language that defines the data model definition without describing its control flow (the machine learning model can generate an application definition that is inserted into a declarative model associated with the software application, i.e. generate one or more server files specifying a declarative-based data model definition for a software-based server service, where the declarative model includes a data schema and the application definition, i.e. one or more server files comprising a schema file and a service file in a declarative model definition language, and the declarative model describes what the software application should do without specifying how it should do it, i.e. a declarative model definition language is a language that defines the data model definition without describing its control flow, and where code that can be compiled and executed is generated from the declarative model, i.e. being compilable and executable in the framework server, and where the target deployment of the application is a server, i.e. server files…framework server [0026],[0029],[0047-8],[0064](see provisional [0025],[0028][0046-7],[0063]));
compiling the one or more server files (code is generated from the declarative model and compiled [0026],[0029],[0047-8],[0064](see provisional [0025],[0028][0046-7],[0063]));
storing the one or more server files in the server repository (the server computing system can store some or all of an application development platform, where the declarative model is part of the platform [0047-8],[0093](see provisional [0046-7],[0092])); and
executing the one or more server files in the framework server to handle one or more requests for the software-based server service (the application code generated from the declarative model is executed, i.e. executing the one or more server files in the framework server, where the application performs different tasks in response to a user query, i.e. handle one or more requests for the software-based server service [0026],[0029],[0047-8],[0060-1],[0072](see provisional [0025],[0028][0046-7],[0059-60],[0071])).
Jiang and Stephens are analogous art because they are from a similar field of endeavor in generating code from natural language inputs. Thus, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the generating code for apps from natural language using an LLM teachings of Jiang with the machine learning model generating application definitions for a declarative model as taught by Stephens. It would have been obvious to combine the references to enable more efficient development, execution, and maintenance of applications (Stephens [0029](pro [0028])).
While Jiang in view of Stephens provides a declarative model with application definitions generated by a machine learning model, Jiang in view of Stephens does not specifically teach the machine learning model also generates the schema file, and thus does not teach
generate one or more server files specifying a declarative-based data model definition for a software-based server service, the one or more server files comprising a schema file … in a declarative model definition language.
Stephens 2, however, teaches generate one or more server files specifying a declarative-based data model definition for a software-based server service, the one or more server files comprising a schema file … in a declarative model definition language (the application development platform can process the natural language description with a machine learned language model to generate a data schema for the software application, which can be inserted into a declarative model [0023],[0025],[0045-7](see provisional [0022],[0024],[0044-6])).
Jiang, Stephens, and Stephens 2, are analogous art because they are from a similar field of endeavor in generating code from natural language inputs. Thus, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the declarative model with application definitions generated by a machine learning model teachings of Jiang, as modified by Stephens with the machine learning model generating the data schema as taught by Stephens 2. It would have been obvious to combine the references to enable users to develop software applications using low-code or no-code tools (Stephens 2 [0020](pro [0019])).
Regarding claims 3, 11, and 19, Jiang in view of Stephens and Stephens 2 teaches claims 1, 9, and 17, and Stephens further teaches
the one or more server files include a schema file and a service file (the declarative model, i.e. server files, includes a data schema, i.e. schema file, and the application definition, i.e. service file [0047-8](pro [0046-7]).
Where the motivation to combine is the same as previously presented.
Regarding claims 5 and 13, Jiang in view of Stephens and Stephens 2 teaches claims 1 and 13, and Jiang further teaches
creating a data generation request comprising one or more statements generated from the one or more server files and a second pre-designed system message (the user can input a text input for a prompt in a natural language format, such as a step from a suggestion for how to create an app from suggestions provided in response to a previous prompt, as a description of a request for code, i.e. one or more statements generated from the one or more server files, and when a tag is detected related to the input, the input is incorporated into a task-specific prompt with examples is automatically loaded, such how to fix the code, output code in a different language, or provide further suggestions for sub-tasks, i.e. a second pre-designed system message, and the prompt is loaded as input into the generative language model to execute the task, i.e. creating a data generation request Fig. 1,(Intro, Sec. 3.1 and 3.2, Appendix A and B));
feeding the data generation request to the GAI model to generate one or more server data files (the task-specific prompt with incorporated user input, i.e. server generation request, fed into the generative language model, i.e. feeding…to the GAI model, to output code and/or subtask suggestions, i.e. generate one or more server data files, for a request such as making a To-Do app or a flashcard app Fig. 1,(Intro, Sec. 3.1 and 3.2, Appendix A and B)).
Where Stephens further teaches storing the one or more server data files in a data repository (the server computing system can store some or all of an application development platform, where the declarative model is part of the platform [0047-8],[0093](see provisional [0046-7],[0092])).
And where the motivation to combine is the same as previously presented.
Regarding claims 6 and 14, Jiang in view of Stephens and Stephens 2 teaches claims 5 and 13, and Jiang further teaches
validating the one or more server files (for prompts that produce HTML, i.e. one or more server files, GenLine renders the model output in an HTML iframe, providing a way to validate the output at a glance, i.e. validating (Sec. 3.1)); and
in response to a determination that the one or more server files have failed the validation, retrying the feeding of the server generation request to the GAI model (if there are errors in the code noticed by validating the output at a glance, i.e. in response to a determination that the one or more server files have failed the validation, a prompt template for fixing errors in existing code can be sent to the LLM that incorporates user input, which can include code and natural language, i.e. retrying the feeding of the server generation request to the GAI model Fig. 1,(Intro, Sec. 3.1 and 3.2, Appendix A and B)).
Regarding claims 7 and 15, Jiang in view of Stephens and Stephens 2 teaches claims 6 and 14, and Jiang further teaches
the validating includes attempting to compile the one or more server files (for prompts that produce HTML, i.e. one or more server files, GenLine renders the model output in an HTML iframe, providing a way to validate the output at a glance, i.e. validating includes attempting to compile Fig. 1,(Sec. 3.1)).
Claim(s) 4, 12, and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Jiang, in view of Stephens, in view of Stephens 2, and further in view of Wang et al. (U.S. PG Pub No. 2022/0019932), as found in the IDS, hereinafter Wang.
Regarding claims 4, 12, and 20, Jiang in view of Stephens and Stephens 2 teaches claims 3, 11, and 19.
While Jiang in view of Stephens and Stephens 2 provides the generation of schema and service files, Jiang in view of Stephens and Stephens 2 does not specifically teach the files define an OData service, and thus does not teach
the schema file and the service file define an Open Data Protocol (OData) service.
Wang, however, teaches the schema file and the service file define an Open Data Protocol (OData) service (an EDM file is generated based on the user input and is provided in a Common Schema Definition Language, i.e. include a schema file, which is further used to generate OData service code, i.e. a service file define an OData service [0026-7],[0055]).
Jiang, Stephens, Stephens 2, and Wang, are analogous art because they are from a similar field of endeavor in developing service code in response to user input. Thus, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the generation of schema and service files teachings of Jiang, as modified by Stephens and Stephens 2, with the generation of OData service codes as taught by Wang. It would have been obvious to combine the references to automatically generate services from user text and image input using machine learning (Wang [0004-5]).
Claim(s) 8 and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Jiang, in view of Stephens, in view of Stephens 2, and further in view of Kulal et al. (‘SPoC: Search-based Pseudocode to Code’, NeurIPS 2019), hereinafter Kulal.
Regarding claims 8 and 16, Jiang in view of Stephens and Stephens 2 teaches claims 6 and 14.
While Jiang in view of Stephens and Stephens 2 provides validating the files, Jiang in view of Stephens and Stephens 2 does not specifically teach performing tests, and thus does not teach
the validating includes performing one or more tests on the one or more server files using the one or more server data files.
Kulal, however, teaches the validating includes performing one or more tests on the one or more server files using the one or more server data files (a synthesized program, i.e. one or more server files, is accepted, i.e. validating, if it successfully compiles and passes all public test cases, i.e. performing on or more tests, where the text cases are input-output sets that the program must compute correctly, i.e. one or more server data files Figs. 1 and 2,(Intro, Sec. 2)).
Jiang, Stephens, Stephens 2, and Kulal are analogous art because they are from a similar field of endeavor in developing service code in response to user input. Thus, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the validating the files teachings of Jiang, as modified by Stephens and Stephens 2, with performing tests with text cases for validation as taught by Kulal. It would have been obvious to combine the references to improve the program synthesis success rate during program validation (Kulal Abstract).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NICOLE A K SCHMIEDER whose telephone number is (571)270-1474. The examiner can normally be reached 8:00 - 5:00 M-F.
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, Pierre-Louis Desir can be reached at (571) 272-7799. 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.
/NICOLE A K SCHMIEDER/Primary Examiner, Art Unit 2659
Prosecution Insights