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 .
This office action is in response to applicant’s response (dated 05/06/2026) to a restriction request. Applicant elected group 1 (claims 1-16) for examination.
Per claim 9, “one or more computing devices” is interpreted as hardware devices with processors and memory, as shown as in applicant specification (Fig. 5A).
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-5, 8 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Nikumb et al. (US PGPUB 2021/0397418) hereinafter Nikumb.
Per claim 1, Nikumb discloses a method comprising: obtaining, by a computing system comprising one or more computing devices, a natural language description of a software application; (paragraph [0020]; receiving one or more requirement documents for processing with a natural language model); processing, by the computing system, the natural language description with a machine-learned language model to generate, as an output of the machine-learned language model, an application definition for the software application; and inserting, by the computing system, the application definition generated by the machine-learned language model into a declarative model associated with the software application (claim 1; paragraphs [0020]-[0022][0050]; based on the requirement documents, generating a structure data XML file (application definition) that includes entity data and the intent classification, which include information indicating a type of the application, a purpose of the application, a context in which the application is to be used, and the like; the entity data and the intent classification is used to generate an application architecture (declarative model) associated with the application).
Per claim 2, Nikumb further discloses generating, by a code generation system of the computing system, a set of application code for the software application based on the declarative model that includes the application definition (claim 1; generating application code for the application based the entity data, the intent classification data).
Per claim 3, Nikumb further discloses wherein the application definition generated by the machine-learned language model comprises descriptions of one or more user interface elements of the software application (claim 1; based on the user input data to identify user interface (UI) objects).
Per claim 4, Nikumb further discloses wherein the application definition generated by the machine-learned language model comprises a workflow or process model (claim 1; based on the user input document to generate an API response model).
Per claim 5, Nikumb further discloses wherein the application definition generated by the machine-learned language model comprises a security model (claim 1; paragraph [0038]; based on the user input document to generate a response API model and a request API model, which includes how to access a resource and the allowed interactions (e.g., GET, POST, DELETE) with the resource (security rules)).
Per claim 8, Nikumb further discloses wherein the natural language description comprises a textual description contained in a dialog between a user and a chatbot (claim 1; paragraph [0011]; application generation system may interact with a user via a chatbot to obtain, from the user, user input data).
Claims 9-13 and 16 are rejected under similar rationales as claims 1-5, 8.
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.
Claims 6-7, 14-15 are rejected under 35 U.S.C. 103 as being unpatentable over Nikumb, in view of Beauchamp (US PGPUB 2024/0256762).
Per claim 6, Nikumb does not explicitly teach obtaining, by the computing system, a second natural language description of the software application, wherein the second natural language description specifies one or more requested changes to the software application; processing, by the computing system, the second natural language description with the machine-learned language model to generate, as an output of the machine-learned language model, an updated application definition for the software application; and inserting, by the computing system, the updated application definition generated by the machine-learned language model into the declarative model associated with the software application. However, Beauchamp in view of Nikumb suggests the above (Beauchamp, claim 1; receive a text editing instruction (second natural language description requesting changes), processing by a LLM a prompt containing the text editing instruction, outputting a revised block of text (updated application definition)); Nikumb further discloses (claim 1; generating a structure data XML file (application definition) that includes entity data; the entity data is used to generate an application architecture (declarative model) associated with the application; paragraph [0046]; user can input data to modify the application). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Nikumb and Beauchamp to allow user to enter modification request to the LLM to revise the application definition to implement a revised declarative model, this would give the user the flexibility to continuously enhance the application.
Per claim 7, Beauchamp further suggests wherein processing, by the computing system, the second natural language description with the machine-learned language model comprises: concatenating, by the computing system, the application definition with the second natural language description to generate a concatenated input; and processing, by the computing system, the concatenated input with the machine-learned language model to generate, as the output of the machine-learned language model, the updated application definition for the software application (claim 1; receive a text editing instruction (second natural language description requesting changes), processing by a LLM a prompt containing text-editing instruction inserted into an existing block of text (concatenating the application definition with the second natural language description to generate a concatenated input), outputting a revised block of text (updated application definition)).
Claims 14-15 are rejected under similar rationales as claims 6-7.
Response to Arguments
In the response filed on 05/06/2026, applicant argued that the restriction request was not proper. Applicant stated “Specifically, Applicant traverses the restriction requirement in view of MPEP § 803 because the claims are sufficiently related such that examining them together imposes no serious burden on the examiner”. The examiner respectfully disagrees. As stated in the restriction request (dated 03/06/2026), claims 1-16 and claims 17-20 are two inventions shown on different figures, and they belong to two different classifications. Claims 1-16 are related to using a machine learning language model to generate code. Claims 17-20 are related to evaluating, training and tuning a machine learning language model. Thus, claims 1-16 and claims 17-20 are different inventions that require different search focuses. Therefore, the examiner believes the restriction request was proper.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HANG PAN whose telephone number is (571)270-7667. The examiner can normally be reached 9 AM to 5 PM.
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, Chat Do can be reached at 571-272-3721. 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.
/HANG PAN/Primary Examiner, Art Unit 2193
Prosecution Insights