CTNF 18/788,658 CTNF 84417 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. Claims 1-20 have been examined and are pending. Claim Objections Claim 2 is objected to because it includes “the operation comprise” which should be amended to --the operation comprises-- . Claims 3, 10 and 17 are objected to because they are missing an or before the last limitation. Appropriate correction is required. 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. Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. Claims 1-20 are directed to one of the eligible categories of subject matter. With respect to independent claims 1, 8, 15 the generating, determined cover performance of the limitations manually and/or in the mind (mental processes abstract idea). The accessing, receiving, inputting limitations are recited at a high level of generality and do not add meaningful limitations to the abstract idea; these limitations are directed to insignificant extra solution activities. The claims as a whole merely describe how to generally “apply” the exception in a computer environment using generic computer functions or components. Even when viewed in combination, 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. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claims are not patent eligible. With respect to dependent claims 2, 4, 5, 6, 7, 9, 11, 12, 13, 14, 16, 18, 19, 20 the generating, detecting, identifying, re-applying, applying cover performance of the limitations manually and/or in the mind (mental processes abstract idea). No additional elements are recited and so the claims do not provide a practical application and are not considered to be significantly more. The claims are not eligible. With respect to dependent claims 3, 10, 17 presenting are recited at a high level of generality and do not add meaningful limitations to the abstract idea. The claims as a whole merely describe how to generally “apply” the exception in a computer environment using generic computer functions or components. Even when viewed in combination, 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. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claims are not patent eligible. 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. 07-23-aia AIA The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows: 1. Determining the scope and contents of the prior art. 2. Ascertaining the differences between the prior art and the claims at issue. 3. Resolving the level of ordinary skill in the pertinent art. 4. Considering objective evidence present in the application indicating obviousness or nonobviousness. 07-20-02-aia AIA This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention. 07-21-aia AIA Claim s 1-2, 6- 9, 13-16, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Vadaparty et al., Patent No.: US 12360791 B1, hereinafter Vadaparty in view of Pimparkhede et al., DocCGen: Document-based Controlled Code Generation , hereinafter Pimparkhede . As per claim 1, Vadaparty discloses One or more non-transitory computer readable media comprising instructions which, when executed by one or more hardware processors, cause performance of operations comprising: accessing […] pseudocode constructs […and…] proprietary software code constructs ( Vadaparty , at least c. 6, l. 65 to c. 7, l. 15 and c. 10, ll. 1-12, 45-60 disclose artifacts file, the validated English language description that is an intermediate input from which proprietary code is generated, “domain specific metadata about the enterprise computer system” and metadata about “the orchestrated steps”, “the formatting of the data messages that it sends and receives”, etc. - all of which encompass generating enterprise specific proprietary software code constructs using intermediate human language description / pseudocode . Claim interpretation note: par. 42 of the instant specification expressly defines pseudocode: “As referred to herein, pseudocode is a high-level description of a computer algorithm that uses natural language to outline the steps of the algorithm. The pseudocode is not tied to any specific programming language syntax.”). Vadaparty does not explicitly disclose a first mapping of one to the other. However, Pimparkhede discloses this as a “structured schema” that “stores the list of valid keywords for every field and the inter-field dependency information,” and a “template” that “encodes the structure of the code snippet” and is “used to guide the model during decoding.” See Pimparkhede , section 3.1 Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of the cited references because Pimparkhede would have allowed Vadaparty to structure its domain specific metadata as schema/template rules that constrain the LLM to generate valid enterprise specific code constructs. This improves accuracy and helps prevent invalid code from being generated. receiving a request to generate a first set of proprietary software code based on a first set of pseudocode (see Vadaparty at least c. 22, l. 55 to c. 7, l. 25 which discloses receiving prompts/requests for an LLM to generate enterprise target language code based on a human language description) ; based on the request, generating a set of instructions for a trained large language model (LLM) to generate a first set of proprietary software code based on (a) the first set of pseudocode and (b) the first mapping of pseudocode constructs to proprietary software code constructs (see Vadaparty as cited above including c. 10, ll. 17-35 and c. 11, ll. 1-23 which disclose generating prompts/instructions for an LLM based on both the human language description and enterprise metadata, and that the prompts include a target programming language, enterprise system architecture and domain specific metadata, and that “based on the prompts 47, 48, as well as the description 12, the LLM could generate a new code file 51 in the target programming language”. See Pimparkhede as cited above and abstract, section 3.2 which include that DocGen first retrieves documentation and then “utilizes schema rules extracted from the documentation of these libraries to constrain the decoding” and “fetch the initial templates of every retrieved library stored offline… the model is constrained to follow one of the k code templates.”) ; and inputting the set of instructions to the trained LLM to generate the first set of proprietary software code, wherein the proprietary software code constructs are determined by the trained LLM based on the first mapping of pseudocode constructs to proprietary software code constructs (see Vadaparty as cited above including c. 5, ll. 3-6 include “The API gateway 19 can route the user's inputs/prompts to the LLM 14”; see also claim 1 of Vadaparty which includes “generating, by the LLM, based on the legacy software program and the prompting, the software program code in the target programming language, wherein the program code in the target programming language is based on the output file” and note that the output file “captures business rules of the legacy software program based on the description”. Also, see Pimparkhede as cited above and fig. 2 and section 3.1 “The model is guided to follow one of the templates during decoding” and “the model generates the variable part adhering to the library schema… Structured schema and template together represent the grammar of the library in the format, which can be easily used to guide the decoding. ”). As per claim 2, Vadaparty in view of Pimparkhede discloses The non-transitory computer readable media of Claim 1, wherein the set of instructions further comprises an instruction to the LLM to refrain from guessing, and wherein the operation comprise: based on the instruction to refrain from guessing, generating, by the LLM, the first set of proprietary software code including an indication of uncertainty corresponding to at least one software code construct (see Vadaparty as cited in the rejection of claim 1 for prompts/instructions to an LLM for enterprise code generation and see Pimparkhede section 3.4 says “decoding is constrained to follow that template from left to right while adhering to the grammar of the corresponding library” and that “the model is constrained to select the valid keywords” wherein any generated construct that is not a valid schema/template as an indication of uncertainty). As per claim 6, Vadaparty in view of Pimparkhede discloses The non-transitory computer readable media of Claim 1, wherein the request comprises a first set of human-understandable requirements, wherein the operations further comprise: applying the LLM to the first set of human-understandable requirements to generate a first set of non-proprietary software code (see Vadaparty c. 4, l. 60 to c. 5, l. 5) ; and applying the LLM to the first set of non-proprietary software code to generate the first set of pseudocode based on the first set of non-proprietary software code (see Vadaparty at least c. 10, ll. 17-35 and c. 11, ll. 1-23 and c. 22, l. 55 to c. 7, l. 25) . As per claim 7, Vadaparty in view of Pimparkhede discloses The non-transitory computer readable media of Claim 6, wherein the operations further comprise: determining the request is associated with a first set of proprietary code requirements (see Vadaparty c. 23, ll. 15-20 ) ; wherein accessing the first mapping of pseudocode constructs to proprietary software code constructs is performed based on determining the first mapping corresponds to the first set of proprietary code requirements (see Pimparkhede , claim 1 “second prompting, by the user device, the LLM to generate an output file that captures business rules of the legacy software program based on the description” and Pimparkhede as cited in the rejection of claim 1). As per claims 8, 9, 13, 14, 15, 16, and 20 they are analogous to claims above and thus likewise rejected . 07-21-aia AIA Claim s 3-5, 10-12 and 17-19 are rejected under 35 U.S.C. 103 as being unpatentable over Vadaparty in view of Pimparkhede and further in view of Hawes et al., Pub. No.: US 20240403290 A1, hereinafter Hawes . As per claim 3, Vadaparty in view of Pimparkhede discloses The non-transitory computer readable media of Claim 2. The combination does not disclose but Hawes discloses wherein the indication of uncertainty includes at least one of: including in the first set of proprietary software code a first pseudocode construct; presenting one or more confidence level values corresponding to one or more software code constructs included in the first set of proprietary software code; presenting one or more express statements of uncertainty corresponding to the one or more software code constructs included in the first set of proprietary software code ( Hawes , par. 70 and claim 18 include at least “an indication of a mistake in the first response to the prompt” and “wherein the mistake comprises at least one of: a hallucination, a reference to a tool that does not exist, a reference to incorrect name of tool, a reference to a different tool than an instructed computer-based tool from the prompt, a response not conforming to the format, a response that includes an unrecognized word, or a response using a syntax different from instructed by the prompt.”). Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of the cited references because Hawes would have allowed the combination to clearly identify LLM output problems instead of generating and using invalid code. This would improve reliability and integrity of the generated code. As per claim 4, Vadaparty in view of Pimparkhede discloses The non-transitory computer readable media of Claim 2. The combination does not disclose but Hawes discloses wherein the operations further comprise: detecting in the first set of proprietary software code a first indication of uncertainty associated with a first software code construct (see Vadaparty in view of Pimparkhede as cited in claims 1 and 2; see Hawes , par. 70 and claim 18 include at least “an indication of a mistake in the first response to the prompt” and “wherein the mistake comprises at least one of: a hallucination, a reference to a tool that does not exist, a reference to incorrect name of tool, a reference to a different tool than an instructed computer-based tool from the prompt, a response not conforming to the format, a response that includes an unrecognized word, or a response using a syntax different from instructed by the prompt.”). identifying a second proprietary software code construct corresponding to the first software code construct ( Pimparkhede section 3.4 says that “the model is constrained to select the valid keywords” which discloses selecting a valid replacement construct from a defined set, to replace an invalid one); generating a second mapping at least by: updating the first mapping to map the second proprietary software code construct to the first software code construct ( Hawes , pars. 113, 119 “update, based on the mistake, the format of the target computer language; and generate an indication of the updated format of the target computer language” and claim 20 says “updating an acceptable grammar of the format of the target language, or updating a list of acceptable terms for a command”); and re-applying the LLM to the set of pseudocode and the second mapping to generate a second set of proprietary software code, wherein the second set of proprietary software code includes the second proprietary software code construct (see rejection of above limitations). Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of the cited references because Hawes would have allowed the combination to clearly identify LLM output problems instead of generating and using invalid code. This would improve reliability and integrity of the generated code. As per claim 5, Vadaparty in view of Pimparkhede discloses The non-transitory computer readable media of claim 2, wherein generating the first set of proprietary software code including the indication of uncertainty comprises: determining, by the LLM, that a first certainty level corresponding to a first set of software code constructs meets a threshold certainty level (see rejection of above and note that in Pimparkhede , section 3.4, determining that a generated construct satisfies the required schema/template corresponds to determining that the construct meets the required certainty or validity threshold) ; based on determining the first certainty level meets the threshold certainty level: including the first set of software code constructs in the proprietary software code ( Pimparkhede , section 6 includes “following the grammar template ensures that subcommand is generated from valid strings enclosed in <>”); The combination does not disclose but Hawes discloses determining, by the LLM, that a second certainty level corresponding to a second set of software code constructs does not meet the threshold certainty level ( Hawes discloses that the system may “determine and/or receive an indication of a mistake in the first response to the prompt” and Pimparkhede , section 6 includes “Constraining the model to follow schema rules during decoding restricts the generation of invalid keywords”); and based on determining the second certainty level does not meet the threshold certainty level: including a first set of pseudocode constructs, corresponding to the second set of software code constructs, in the proprietary software code (see rejection of above limitations) . Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of the cited references because Hawes would have allowed the combination to clearly identify LLM output problems instead of generating and using invalid code. This would improve reliability and integrity of the generated code. As per claims 10-12 and 17-19 they are analogous to claims above and thus likewise rejected. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to SYED HASAN whose telephone number is (571)270-5008. The examiner can normally be reached M-F 8am - 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, Boris Gorney can be reached at (571)270-5626. 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. /SYED H HASAN/Primary Examiner, Art Unit 2154 Application/Control Number: 18/788,658 Page 2 Art Unit: 2154 Application/Control Number: 18/788,658 Page 3 Art Unit: 2154 Application/Control Number: 18/788,658 Page 4 Art Unit: 2154 Application/Control Number: 18/788,658 Page 5 Art Unit: 2154 Application/Control Number: 18/788,658 Page 6 Art Unit: 2154 Application/Control Number: 18/788,658 Page 7 Art Unit: 2154 Application/Control Number: 18/788,658 Page 8 Art Unit: 2154 Application/Control Number: 18/788,658 Page 9 Art Unit: 2154 Application/Control Number: 18/788,658 Page 10 Art Unit: 2154 Application/Control Number: 18/788,658 Page 11 Art Unit: 2154 Application/Control Number: 18/788,658 Page 12 Art Unit: 2154 Application/Control Number: 18/788,658 Page 13 Art Unit: 2154
Prosecution Insights