DETAILED ACTION
This is the initial Office action based on the application filed on October 9, 2024.
Claims 1-20 are pending.
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 .
Internet Communications
Without a written authorization for Internet communications by the Applicant in place, the USPTO cannot communicate with the Applicant via email and will not respond via email to any Internet correspondence which contains information subject to the confidentiality requirement as set forth in 35 U.S.C. § 122, such as claimed subject matter in an interview agenda or proposed claim amendments for an Examiner’s Amendment.
Therefore, in the interest of facilitating compact prosecution, the Examiner kindly asks the Applicant to authorize Internet communications with the USPTO by using Form PTO/SB/439 (available at https://www.uspto.gov/patents/apply/forms). The form may be submitted via the USPTO patent electronic filing system (Patent Center) using the document description “Internet Communications Authorized” to facilitate processing. The written authorization for Internet communications must be submitted on a separate paper to be entitled to acceptance in accordance with 37 CFR § 1.4(c). The separate paper will facilitate processing and avoid confusion. The written authorization for Internet communications may not be submitted via an email. See MPEP § 502.03(II).
Claim Interpretation
During patent examination, the pending claims must be “given their broadest reasonable interpretation consistent with the specification.” See MPEP § 2111. Under a broadest reasonable interpretation (BRI), words of the claim must be given their plain meaning, unless such meaning is inconsistent with the specification. The plain meaning of a term means the ordinary and customary meaning given to the term by those of ordinary skill in the art at the relevant time. The ordinary and customary meaning of a term may be evidenced by a variety of sources, including the words of the claims themselves, the specification, the drawings, and the prior art. See MPEP § 2111.01(I).
Applicant is entitled to be their own lexicographer and may rebut the presumption that claim terms are to be given their ordinary and customary meaning by clearly setting forth a definition of the term that is different from its ordinary and customary meaning(s) in the specification at the relevant time. Where an explicit definition is provided by the Applicant for a term, that definition will control interpretation of the term as it is used in the claim. See MPEP § 2111.01(IV)(A). Any such lexicographic definition for a term will be expressly noted by the Examiner in the prior art rejections of the claims.
Claim Mapping
For clarity of the prosecution history record, the Examiner has provided annotations in the prior art rejections of the claims to aid the Applicant in understanding the Examiner’s interpretations of the claimed invention and the prior art, such as emphasizing notable and relevant portions of the prior art citations, using item-to-item matching to the prior art citations, pairing exact claim language to particular language used in the prior art citations, and/or clearly explaining the Examiner’s interpretation as to how a prior art citation maps to the claim language, especially when there is no one-to-one matching of terms. Furthermore, the annotations are provided in the prior art rejections of the claims at the Examiner’s discretion where the Examiner deemed to be appropriate and necessary.
Claim Objections
Claims 4 and 15 are objected to because of the following informalities:
Claims 4 and 15 recite “(SSD).” It should read -- (SDD) --.
Appropriate correction is required.
Claim Rejections - 35 U.S.C. § 112
The following is a quotation of 35 U.S.C. § 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
Claims 15, 19, and 20 are rejected under 35 U.S.C. § 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention.
Claim 15 recites the limitation “the software platform” at lines 3 and 4. There is insufficient antecedent basis for this limitation in the claim. In the interest of compact prosecution, the Examiner subsequently interprets this limitation as reading “the computing platform” for the purpose of further examination.
Claim 19 recites the limitation “the code package” at line 16. There is insufficient antecedent basis for this limitation in the claim. In the interest of compact prosecution, the Examiner subsequently interprets this limitation as reading “a code package” for the purpose of further examination.
Claim 20 depends on Claim 19. Therefore, Claim 20 suffers the same deficiency as Claim 19.
Claim Rejections - 35 U.S.C. § 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.
Claims 1-6 and 8-20 are rejected under 35 U.S.C. § 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Claim Interpretation: It is essential that the broadest reasonable interpretation (BRI) of a claim as a whole be established prior to examining the claim for eligibility. Under the BRI, the limitations of Claim 1 are presumed to have their plain meaning consistent with the specification as it would be interpreted by one of ordinary skill in the art. See MPEP § 2111.
The BRI of Claim 1 is a system for receiving a request associated with integrating a software platform of a merchant with a computing service associated with a service provider, wherein the request comprises a payload associated with the software platform; determining a large language model (LLM) prompt for an LLM configured to generate new code integrations with at least the computing service based on LLM training data associated with available code integrations for at least the computing service; prompting the LLM to create a new code integration based on the LLM prompt and the payload; receiving the new code integration for the software platform from the LLM, wherein the new code integration comprises a code package of new code generated by the LLM for one or more uses of the computing service of the service provider via the software platform of the merchant; and loading the code package for the new code integration to a selected computing system designated by the merchant.
Step 1: This part of the eligibility analysis evaluates whether the claim falls within any statutory category. See MPEP § 2106.03. Claim 1 is directed to a system, which is a machine, and falls within one of the statutory categories of invention. (Step 1: YES).
Step 2A, Prong One: This part of the eligibility analysis evaluates whether the claim recites a judicial exception. As explained in MPEP § 2106.04(II), a claim “recites” a judicial exception when the judicial exception is “set forth” or “described” in the claim.
Claim 1 recites the limitation:
(a) determining a large language model (LLM) prompt for an LLM configured to generate new code integrations with at least the computing service based on LLM training data associated with available code integrations for at least the computing service.
The recited step, under the BRI, covers performance of the step in the human mind alone or with the aid of pen and paper. That is, other than reciting:
(1) a non-transitory memory; and
(2) one or more hardware processors coupled to the non-transitory memory and configured to execute instructions to cause the system to.
Nothing in the claim precludes the step from practically being performed in the human mind alone using observation, evaluation, judgment, and opinion or with the aid of pen and paper. For example, the limitation (a) in the context of the claim encompasses a human evaluating an LLM in the human mind alone using observation, evaluation, judgment, and opinion or with the aid of pen and paper to determine an LLM prompt. See MPEP § 2106.04(a)(2)(III).
If a claim limitation, under its BRI, covers a practical performance in the human mind alone or with the aid of pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea. (Step 2A, Prong One: YES).
Step 2A, Prong Two: This part of the eligibility analysis evaluates whether the claim as a whole integrates the recited judicial exception into a practical application of the judicial exception or whether the claim is “directed to” the judicial exception. This evaluation is performed by (1) identifying whether there are any additional elements recited in the claim beyond the judicial exception, and (2) evaluating those additional elements individually and in combination to determine whether the claim as a whole integrates the judicial exception into a practical application. See MPEP § 2106.04(d).
This judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements:
(1) a non-transitory memory; and
(2) one or more hardware processors coupled to the non-transitory memory and configured to execute instructions to cause the system to.
The additional elements (1) and (2) are recited at a high level of generality such that they amount to no more than mere instructions to apply the judicial exception using generic computer components. The non-transitory memory and hardware processors are used as a tool to perform the various steps of the claim. See MPEP § 2106.05(f).
Also, the claim recites the additional elements:
(3) prompting the LLM to create a new code integration based on the LLM prompt and the payload; and
(4) loading the code package for the new code integration to a selected computing system designated by the merchant.
The additional elements (3) and (4) fail to meaningfully limit the claim because they do not require any particular application of the judicial exception and are, at best, the equivalent of merely adding the words “apply it” (or an equivalent) to the judicial exception. See MPEP § 2106.05(f). The additional elements recite only the ideas of prompting an LLM and loading a code package without details on how they are accomplished. The claim omits any details as to how prompting the LLM and loading the code package solve a technical problem, and instead recites only the idea of a solution or outcome. Therefore, the additional elements attempt to cover any solutions to the identified problems of prompting the LLM and loading the code package with no restriction on how they are accomplished and no description of the mechanism for accomplishing them, and do not integrate the judicial exception into a practical application because this type of recitation is equivalent to the words “apply it.”
Also, the claim recites the additional elements:
(5) receiving a request associated with integrating a software platform of a merchant with a computing service associated with a service provider, wherein the request comprises a payload associated with the software platform; and
(6) receiving the new code integration for the software platform from the LLM, wherein the new code integration comprises a code package of new code generated by the LLM for one or more uses of the computing service of the service provider via the software platform of the merchant.
The additional elements (5) and (6) are mere data gathering recited at a high level of generality and thus, are an insignificant extra-solution activity. See MPEP § 2106.05(g). Furthermore, all uses of the judicial exception require such data gathering, and, as such, the additional elements do not impose any meaningful limits on the claim. The additional elements amount to necessary data gathering. See MPEP § 2106.05(g).
Accordingly, even when viewed in combination, the additional elements do not integrate the recited judicial exception into a practical application because they do not impose any meaningful limits on practicing the judicial exception. (Step 2A, Prong Two: NO). The claim is directed to an abstract idea. (Step 2A: YES).
Step 2B: This part of the eligibility analysis evaluates whether the claim as a whole amounts to significantly more than the recited judicial exception, i.e., whether any additional element, or combination of additional elements, adds an inventive concept to the claim. See MPEP § 2106.05.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements when considered both individually and as a combination do not amount to significantly more than the judicial exception. As discussed above with respect to integration of the judicial exception into a practical application, the claim recites the additional elements:
(1) a non-transitory memory; and
(2) one or more hardware processors coupled to the non-transitory memory and configured to execute instructions to cause the system to.
The additional elements (1) and (2) amount to no more than mere instructions to apply the judicial exception using generic computer components. The analysis under Step 2A, Prong Two is carried through to Step 2B. The use of a computer or other machinery in its ordinary capacity does not integrate a judicial exception into a practical application or provide significantly more.
Also, the claim recites the additional elements:
(3) prompting the LLM to create a new code integration based on the LLM prompt and the payload; and
(4) loading the code package for the new code integration to a selected computing system designated by the merchant.
The additional elements (3) and (4) do not require any particular application of the judicial exception and are, at best, the equivalent of merely adding the words “apply it” (or an equivalent) to the judicial exception. The analysis under Step 2A, Prong Two is carried through to Step 2B. Therefore, the additional elements attempt to cover any solutions to the identified problems of prompting the LLM and loading the code package with no restriction on how they are accomplished and no description of the mechanism for accomplishing them, and do not provide significantly more because this type of recitation is equivalent to the words “apply it.”
Also, the claim recites the additional elements:
(5) receiving a request associated with integrating a software platform of a merchant with a computing service associated with a service provider, wherein the request comprises a payload associated with the software platform; and
(6) receiving the new code integration for the software platform from the LLM, wherein the new code integration comprises a code package of new code generated by the LLM for one or more uses of the computing service of the service provider via the software platform of the merchant.
The additional elements (5) and (6) simply append a well-understood, routine, and conventional activity previously known to the industry, specified at a high level of generality, to the judicial exception and thus, are not indicative of an inventive concept. MPEP § 2106.05(d)(II) expressly states that the courts have recognized the computer function of receiving or transmitting data over a network, e.g., using the Internet to gather data as a well‐understood, routine, and conventional computer function when it is claimed in a merely generic manner (e.g., at a high level of generality) or as an insignificant extra-solution activity. Thus, a person of ordinary skill in the art would readily comprehend that it is well-understood, routine, and conventional in the computing art to receive a request/new code integration. Therefore, the limitations remain an insignificant extra-solution activity even upon reconsideration and do not amount to significantly more.
Thus, taken alone, the additional elements do not amount to significantly more than the above-identified judicial exception (the abstract idea). Looking at the additional elements as a combination adds nothing that is not already present when looking at the additional elements taken individually. Even when considered in combination, the additional elements represent mere instructions to apply a judicial exception using generic computer components, only the idea of a solution or outcome, and an insignificant extra-solution activity, and therefore do not provide an inventive concept. (Step 2B: NO). The claim is not patent eligible.
Claims 2-6, 8, and 9 are dependent on Claim 1, but do not add any feature or subject matter that would solve the judicial exception deficiencies of Claim 1.
Claims 2-6, 8, and 9 are as follows:
Claim 2 recites the limitation(s):
(a) wherein the request comprises an update of existing code with a set of legacy application programming interfaces (APIs) previously used with the computing service to the new code for a set of current APIs for the computing service.
<<>> + <<>> + <<>> • × • <<>> + <<>> + <<>>
Claim 3 recites the limitation(s):
(a) wherein the existing code comprises source code currently used by the software platform, wherein the payload comprises one or more code packages for the source code, and wherein the set of current APIs include one or more representational state transfer (REST) APIs.
<<>> + <<>> + <<>> • × • <<>> + <<>> + <<>>
Claim 4 recites the limitation(s):
(a) determine a software design document (SSD) for the software platform, wherein the prompting is further based on the SSD.
<<>> + <<>> + <<>> • × • <<>> + <<>> + <<>>
Claim 5 recites the limitation(s):
(a) wherein the LLM prompt comprises a plurality of LLM prompts, and wherein prompting the LLM is further based on each of the plurality of LLM prompts and a corresponding portion of the payload.
<<>> + <<>> + <<>> • × • <<>> + <<>> + <<>>
Claim 6 recites the limitation(s):
(a) wherein prompting the LLM uses an orchestration layer of the system to prompt the LLM using each of the plurality of LLM prompts and the corresponding portion of the payload, and wherein the plurality of LLM prompts are associated with generating the new code for at least one of an authentication process, backend code, a backend API layer, a user interface, one or more user interface elements, or one or more application dependencies.
<<>> + <<>> + <<>> • × • <<>> + <<>> + <<>>
Claim 8 recites the limitation(s):
(a) wherein loading the code package comprises pushing the code package to the selected computing system designated by the merchant, and wherein the selected computing system comprises one of a test computing environment, a production computing environment, or a code repository platform.
<<>> + <<>> + <<>> • × • <<>> + <<>> + <<>>
Claim 9 recites the limitation(s):
(a) wherein prompting the LLM is further based on sample code for at least one of the available code integrations.
Claim 4 recites further mental steps which can be practically performed in the human mind alone using observation, evaluation, judgment, and opinion or with the aid of pen and paper and thus, fail to make the claim any less abstract under Step 2A, Prong One (see MPEP § 2106.04(a)(2)(III)).
Claims 6 and 8 recite further additional elements that do not integrate the judicial exception into a practical application of the judicial exception because they do not require any particular application of the judicial exception and are, at best, the equivalent of merely adding the words “apply it” (or an equivalent) to the judicial exception under Step 2A, Prong Two (see MPEP § 2106.05(f)) and thus, are also not significantly more than the abstract idea under Step 2B.
Claims 2, 3, 5, and 9 recite further additional elements that do not integrate the judicial exception into a practical application of the judicial exception because they merely indicate a field of use or technological environment in which the judicial exception is performed and thus, fail to add an inventive concept to the claims under Step 2A, Prong Two (see MPEP § 2106.05(h)) and thus, are also not significantly more than the abstract idea under Step 2B.
Thus, Claims 2-6, 8, and 9 do not add any steps or additional elements, when considered both individually and as a combination, that would convert Claim 1 into patent-eligible subject matter.
Therefore, Claims 1-6, 8, and 9 are not drawn to patent-eligible subject matter as they are directed to an abstract idea without significantly more.
<<>> • × • <<>> • × • <<>> • × • <<>> • + • <<>> • × • <<>> • × • <<>> • × • <<>>
Claim Interpretation: It is essential that the broadest reasonable interpretation (BRI) of a claim as a whole be established prior to examining the claim for eligibility. Under the BRI, the limitations of Claim 10 are presumed to have their plain meaning consistent with the specification as it would be interpreted by one of ordinary skill in the art. See MPEP § 2111.
The BRI of Claim 10 is a method for determining that a code integration with a computing service provided by a service provider is available for a computing platform; determining a payload usable when prompting a large language model (LLM) for an automated generation of the code integration, wherein the LLM is configured to generate new code integrations with at least the computing service based on LLM training data associated with available code integrations for at least the computing service; identifying an LLM prompt associated with the code integration and the LLM; prompting the LLM based on the LLM prompt and the payload; receiving, based on the prompting, a new code integration for the computing platform from the LLM, wherein the new code integration comprises a code package of new code for one or more uses of the computing service of the service provider via the computing platform; and outputting the new code integration via a code integration deployment process for the code integration of the computing platform with the computing service.
Step 1: This part of the eligibility analysis evaluates whether the claim falls within any statutory category. See MPEP § 2106.03. Claim 10 is directed to a method, which is a process (a series of steps or acts), and falls within one of the statutory categories of invention. (Step 1: YES).
Step 2A, Prong One: This part of the eligibility analysis evaluates whether the claim recites a judicial exception. As explained in MPEP § 2106.04(II), a claim “recites” a judicial exception when the judicial exception is “set forth” or “described” in the claim.
Claim 10 recites the limitations:
(a) determining that a code integration with a computing service provided by a service provider is available for a computing platform;
(b) determining a payload usable when prompting a large language model (LLM) for an automated generation of the code integration; and
(c) identifying an LLM prompt associated with the code integration and the LLM.
These recited steps, under the BRI, cover performance of the steps in the human mind alone or with the aid of pen and paper. That is, nothing in the claim precludes the steps from practically being performed in the human mind alone using observation, evaluation, judgment, and opinion or with the aid of pen and paper. For example, the limitation (a) in the context of the claim encompasses a human evaluating a computing service in the human mind alone using observation, evaluation, judgment, and opinion or with the aid of pen and paper to determine a code integration. And the limitation (b) in the context of the claim encompasses a human evaluating the code integration in the human mind alone using observation, evaluation, judgment, and opinion or with the aid of pen and paper to determine a payload. And the limitation (c) in the context of the claim encompasses a human evaluating the code integration in the human mind alone using observation, evaluation, judgment, and opinion or with the aid of pen and paper to identify an LLM prompt. See MPEP § 2106.04(a)(2)(III).
If a claim limitation, under its BRI, covers a practical performance in the human mind alone or with the aid of pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea. (Step 2A, Prong One: YES).
Step 2A, Prong Two: This part of the eligibility analysis evaluates whether the claim as a whole integrates the recited judicial exception into a practical application of the judicial exception or whether the claim is “directed to” the judicial exception. This evaluation is performed by (1) identifying whether there are any additional elements recited in the claim beyond the judicial exception, and (2) evaluating those additional elements individually and in combination to determine whether the claim as a whole integrates the judicial exception into a practical application. See MPEP § 2106.04(d).
This judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements:
(1) wherein the LLM is configured to generate new code integrations with at least the computing service based on LLM training data associated with available code integrations for at least the computing service; and
(2) prompting the LLM based on the LLM prompt and the payload.
The additional elements (1) and (2) fail to meaningfully limit the claim because they do not require any particular application of the judicial exception and are, at best, the equivalent of merely adding the words “apply it” (or an equivalent) to the judicial exception. See MPEP § 2106.05(f). The additional elements recite only the ideas of generating new code integrations using an LLM and prompting the LLM without details on how they are accomplished. The claim omits any details as to how generating new code integrations using the LLM and prompting the LLM solve a technical problem, and instead recites only the idea of a solution or outcome. Therefore, the additional elements attempt to cover any solutions to the identified problems of generating new code integrations using the LLM and prompting the LLM with no restriction on how they are accomplished and no description of the mechanism for accomplishing them, and do not integrate the judicial exception into a practical application because this type of recitation is equivalent to the words “apply it.”
Also, the claim recites the additional elements:
(3) receiving, based on the prompting, a new code integration for the computing platform from the LLM, wherein the new code integration comprises a code package of new code for one or more uses of the computing service of the service provider via the computing platform; and
(4) outputting the new code integration via a code integration deployment process for the code integration of the computing platform with the computing service.
The additional elements (3) and (4) are mere data gathering/outputting recited at a high level of generality and thus, are insignificant extra-solution activities. See MPEP § 2106.05(g). Furthermore, all uses of the judicial exception require such data gathering/outputting, and, as such, the additional elements do not impose any meaningful limits on the claim. The additional elements amount to necessary data gathering/outputting. See MPEP § 2106.05(g).
Accordingly, even when viewed in combination, the additional elements do not integrate the recited judicial exception into a practical application because they do not impose any meaningful limits on practicing the judicial exception. (Step 2A, Prong Two: NO). The claim is directed to an abstract idea. (Step 2A: YES).
Step 2B: This part of the eligibility analysis evaluates whether the claim as a whole amounts to significantly more than the recited judicial exception, i.e., whether any additional element, or combination of additional elements, adds an inventive concept to the claim. See MPEP § 2106.05.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements when considered both individually and as a combination do not amount to significantly more than the judicial exception. As discussed above with respect to integration of the judicial exception into a practical application, the claim recites the additional elements:
(1) wherein the LLM is configured to generate new code integrations with at least the computing service based on LLM training data associated with available code integrations for at least the computing service; and
(2) prompting the LLM based on the LLM prompt and the payload.
The additional elements (1) and (2) do not require any particular application of the judicial exception and are, at best, the equivalent of merely adding the words “apply it” (or an equivalent) to the judicial exception. The analysis under Step 2A, Prong Two is carried through to Step 2B. Therefore, the additional elements attempt to cover any solutions to the identified problems of generating new code integrations using the LLM and prompting the LLM with no restriction on how they are accomplished and no description of the mechanism for accomplishing them, and do not provide significantly more because this type of recitation is equivalent to the words “apply it.”
Also, the claim recites the additional elements:
(3) receiving, based on the prompting, a new code integration for the computing platform from the LLM, wherein the new code integration comprises a code package of new code for one or more uses of the computing service of the service provider via the computing platform; and
(4) outputting the new code integration via a code integration deployment process for the code integration of the computing platform with the computing service.
The additional elements (3) and (4) simply append well-understood, routine, and conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception and thus, are not indicative of an inventive concept. MPEP § 2106.05(d)(II) expressly states that the courts have recognized the computer functions of receiving or transmitting data over a network, e.g., using the Internet to gather data and presenting offers and gathering statistics as well‐understood, routine, and conventional computer functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activities. Thus, a person of ordinary skill in the art would readily comprehend that it is well-understood, routine, and conventional in the computing art to receive and output a new code integration. Therefore, the limitations remain insignificant extra-solution activities even upon reconsideration and do not amount to significantly more.
Thus, taken alone, the additional elements do not amount to significantly more than the above-identified judicial exception (the abstract idea). Looking at the additional elements as a combination adds nothing that is not already present when looking at the additional elements taken individually. Even when considered in combination, the additional elements represent only the idea of a solution or outcome and insignificant extra-solution activities, and therefore do not provide an inventive concept. (Step 2B: NO). The claim is not patent eligible.
Claims 11-18 are dependent on Claim 10, but do not add any feature or subject matter that would solve the judicial exception deficiencies of Claim 10.
Claims 11-18 are as follows:
Claim 11 recites the limitation(s):
(a) wherein the LLM has a token limit corresponding to a data restriction for the prompting the LLM, and wherein the prompting the LLM is performed based on the token limit.
<<>> + <<>> + <<>> • × • <<>> + <<>> + <<>>
Claim 12 recites the limitation(s):
(a) wherein the prompting the LLM comprises prompting the LLM in parts based on a plurality of calls executed to the LLM to adhere to the token limit.
<<>> + <<>> + <<>> • × • <<>> + <<>> + <<>>
Claim 13 recites the limitation(s):
(a) wherein the prompting the LLM in parts uses different portions of the payload for each of the plurality of calls.
<<>> + <<>> + <<>> • × • <<>> + <<>> + <<>>
Claim 14 recites the limitation(s):
(a) wherein the prompting in parts is performed based on different code sections for generation by the LLM for the new code.
<<>> + <<>> + <<>> • × • <<>> + <<>> + <<>>
Claim 15 recites the limitation(s):
(a) wherein the payload comprises at least one of a legacy code integration of the computing service with the computing platform, a software design document (SSD) for the software platform, or one or more response payloads of API calls from the software platform.
<<>> + <<>> + <<>> • × • <<>> + <<>> + <<>>
Claim 16 recites the limitation(s):
(a) wherein the new code implements the computing service externally on the computing platform and causes calls to be executed to the service provider for the computing service.
<<>> + <<>> + <<>> • × • <<>> + <<>> + <<>>
Claim 17 recites the limitation(s):
(a) wherein outputting the new code integration comprises storing the new code with a code repository platform accessible by a plurality of users, and wherein the new code is testable and reviewable on the code repository platform.
<<>> + <<>> + <<>> • × • <<>> + <<>> + <<>>
Claim 18 recites the limitation(s):
(a) wherein the prompting the LLM is further based on sample code previously used by at least one of the available code integrations.
Claims 11-14, 16, and 18 recite further additional elements that do not integrate the judicial exception into a practical application of the judicial exception because they do not require any particular application of the judicial exception and are, at best, the equivalent of merely adding the words “apply it” (or an equivalent) to the judicial exception under Step 2A, Prong Two (see MPEP § 2106.05(f)) and thus, are also not significantly more than the abstract idea under Step 2B.
Claim 17 recites further additional elements that do not integrate the judicial exception into a practical application of the judicial exception because they are mere data gathering/transmitting/outputting recited at a high level of generality and thus, are insignificant extra-solution activities under Step 2A, Prong Two (see MPEP § 2106.05(g)) and thus, are also not significantly more than the abstract idea under Step 2B.
Claim 15 recites further additional elements that do not integrate the judicial exception into a practical application of the judicial exception because they merely indicate a field of use or technological environment in which the judicial exception is performed and thus, fail to add an inventive concept to the claims under Step 2A, Prong Two (see MPEP § 2106.05(h)) and thus, are also not significantly more than the abstract idea under Step 2B.
Thus, Claims 11-18 do not add any steps or additional elements, when considered both individually and as a combination, that would convert Claim 10 into patent-eligible subject matter.
Therefore, Claims 10-18 are not drawn to patent-eligible subject matter as they are directed to an abstract idea without significantly more.
<<>> • × • <<>> • × • <<>> • × • <<>> • + • <<>> • × • <<>> • × • <<>> • × • <<>>
Claim Interpretation: It is essential that the broadest reasonable interpretation (BRI) of a claim as a whole be established prior to examining the claim for eligibility. Under the BRI, the limitations of Claim 19 are presumed to have their plain meaning consistent with the specification as it would be interpreted by one of ordinary skill in the art. See MPEP § 2111.
The BRI of Claim 19 is a non-transitory machine-readable medium for receiving a request for a use of a computing service of a service provider with a software platform of a merchant, wherein the request comprises computing code data associated with the software platform; determining at least one large language model (LLM) prompt for an LLM configured to generate a new code integration of the computing service with different software platforms based on LLM training data associated with integrating code for the computing service with the different software platforms; prompting the LLM based on the at least one LLM prompt and the computing code data; receiving the new code integration for the software platform from the LLM, wherein the new code integration comprises new code generated by the LLM for the use of the computing service of the service provider via the software platform of the merchant; and communicating the code package to the merchant.
Step 1: This part of the eligibility analysis evaluates whether the claim falls within any statutory category. See MPEP § 2106.03. Claim 19 is directed to a non-transitory machine-readable medium, which is an article of manufacture, and falls within one of the statutory categories of invention. (Step 1: YES).
Step 2A, Prong One: This part of the eligibility analysis evaluates whether the claim recites a judicial exception. As explained in MPEP § 2106.04(II), a claim “recites” a judicial exception when the judicial exception is “set forth” or “described” in the claim.
Claim 19 recites the limitation:
(a) determining at least one large language model (LLM) prompt for an LLM configured to generate a new code integration of the computing service with different software platforms based on LLM training data associated with integrating code for the computing service with the different software platforms.
The recited step, under the BRI, covers performance of the step in the human mind alone or with the aid of pen and paper. That is, other than reciting:
(1) [a] non-transitory machine-readable medium having stored thereon machine-readable instructions executable to cause a machine to perform operations comprising.
Nothing in the claim precludes the step from practically being performed in the human mind alone using observation, evaluation, judgment, and opinion or with the aid of pen and paper. For example, the limitation (a) in the context of the claim encompasses a human evaluating an LLM in the human mind alone using observation, evaluation, judgment, and opinion or with the aid of pen and paper to determine at least one LLM prompt. See MPEP § 2106.04(a)(2)(III).
If a claim limitation, under its BRI, covers a practical performance in the human mind alone or with the aid of pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea. (Step 2A, Prong One: YES).
Step 2A, Prong Two: This part of the eligibility analysis evaluates whether the claim as a whole integrates the recited judicial exception into a practical application of the judicial exception or whether the claim is “directed to” the judicial exception. This evaluation is performed by (1) identifying whether there are any additional elements recited in the claim beyond the judicial exception, and (2) evaluating those additional elements individually and in combination to determine whether the claim as a whole integrates the judicial exception into a practical application. See MPEP § 2106.04(d).
This judicial exception is not integrated into a practical application. In particular, the claim recites the additional element:
(1) [a] non-transitory machine-readable medium having stored thereon machine-readable instructions executable to cause a machine to perform operations comprising.
The additional element (1) is recited at a high level of generality such that it amounts to no more than mere instructions to apply the judicial exception using generic computer components. The non-transitory machine-readable medium and machine are used as a tool to perform the various steps of the claim. See MPEP § 2106.05(f).
Also, the claim recites the additional element:
(2) prompting the LLM based on the at least one LLM prompt and the computing code data.
The additional element (2) fails to meaningfully limit the claim because it does not require any particular application of the judicial exception and is, at best, the equivalent of merely adding the words “apply it” (or an equivalent) to the judicial exception. See MPEP § 2106.05(f). The additional element recites only the idea of prompting an LLM without details on how it is accomplished. The claim omits any details as to how prompting the LLM solves a technical problem, and instead recites only the idea of a solution or outcome. Therefore, the additional element attempts to cover any solutions to the identified problem of prompting the LLM with no restriction on how it is accomplished and no description of the mechanism for accomplishing it, and does not integrate the judicial exception into a practical application because this type of recitation is equivalent to the words “apply it.”
Also, the claim recites the additional elements:
(3) receiving a request for a use of a computing service of a service provider with a software platform of a merchant, wherein the request comprises computing code data associated with the software platform;
(4) receiving the new code integration for the software platform from the LLM, wherein the new code integration comprises new code generated by the LLM for the use of the computing service of the service provider via the software platform of the merchant; and
(5) communicating the code package to the merchant.
The additional elements (3) to (5) are mere data gathering/transmitting recited at a high level of generality and thus, are insignificant extra-solution activities. See MPEP § 2106.05(g). Furthermore, all uses of the judicial exception require such data gathering/transmitting, and, as such, the additional elements do not impose any meaningful limits on the claim. The additional elements amount to necessary data gathering/transmitting. See MPEP § 2106.05(g).
Accordingly, even when viewed in combination, the additional elements do not integrate the recited judicial exception into a practical application because they do not impose any meaningful limits on practicing the judicial exception. (Step 2A, Prong Two: NO). The claim is directed to an abstract idea. (Step 2A: YES).
Step 2B: This part of the eligibility analysis evaluates whether the claim as a whole amounts to significantly more than the recited judicial exception, i.e., whether any additional element, or combination of additional elements, adds an inventive concept to the claim. See MPEP § 2106.05.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements when considered both individually and as a combination do not amount to significantly more than the judicial exception. As discussed above with respect to integration of the judicial exception into a practical application, the claim recites the additional element:
(1) [a] non-transitory machine-readable medium having stored thereon machine-readable instructions executable to cause a machine to perform operations comprising.
The additional element (1) amounts to no more than mere instructions to apply the judicial exception using generic computer components. The analysis under Step 2A, Prong Two is carried through to Step 2B. The use of a computer or other machinery in its ordinary capacity does not integrate a judicial exception into a practical application or provide significantly more.
Also, the claim recites the additional element:
(2) prompting the LLM based on the at least one LLM prompt and the computing code data.
The additional element (2) does not require any particular application of the judicial exception and is, at best, the equivalent of merely adding the words “apply it” (or an equivalent) to the judicial exception. The analysis under Step 2A, Prong Two is carried through to Step 2B. Therefore, the additional element attempts to cover any solutions to the identified problem of prompting the LLM with no restriction on how it is accomplished and no description of the mechanism for accomplishing it, and does not provide significantly more because this type of recitation is equivalent to the words “apply it.”
Also, the claim recites the additional elements:
(3) receiving a request for a use of a computing service of a service provider with a software platform of a merchant, wherein the request comprises computing code data associated with the software platform;
(4) receiving the new code integration for the software platform from the LLM, wherein the new code integration comprises new code generated by the LLM for the use of the computing service of the service provider via the software platform of the merchant; and
(5) communicating the code package to the merchant.
The additional elements (3) to (5) simply append well-understood, routine, and conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception and thus, are not indicative of an inventive concept. MPEP § 2106.05(d)(II) expressly states that the courts have recognized the computer function of receiving or transmitting data over a network, e.g., using the Internet to gather data as a well‐understood, routine, and conventional computer function when it is claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activities. Thus, a person of ordinary skill in the art would readily comprehend that it is well-understood, routine, and conventional in the computing art to receive a request/new code integration and communicate a code package. Therefore, the limitations remain insignificant extra-solution activities even upon reconsideration and do not amount to significantly more.
Thus, taken alone, the additional elements do not amount to significantly more than the above-identified judicial exception (the abstract idea). Looking at the additional elements as a combination adds nothing that is not already present when looking at the additional elements taken individually. Even when considered in combination, the additional elements represent mere instructions to apply a judicial exception using generic computer components, only the idea of a solution or outcome, and insignificant extra-solution activities, and therefore do not provide an inventive concept. (Step 2B: NO). The claim is not patent eligible.
Claim 20 is dependent on Claim 19, but does not add any feature or subject matter that would solve the judicial exception deficiencies of Claim 19.
Claim 20 is as follows:
Claim 20 recites the limitation(s):
(a) wherein the at least one LLM prompt is associated with a plurality of computing code tokens generated based on a maximum data size for LLM tokens processable by the LLM, and wherein the plurality of computing code tokens correspond to different code portions of the new code integration and corresponding data portions of the computing code data.
Claim 20 recites further additional elements that do not integrate the judicial exception into a practical application of the judicial exception because they merely indicate a field of use or technological environment in which the judicial exception is performed and thus, fail to add an inventive concept to the claims under Step 2A, Prong Two (see MPEP § 2106.05(h)) and thus, are also not significantly more than the abstract idea under Step 2B.
Thus, Claim 20 does not add any steps or additional elements, when considered both individually and as a combination, that would convert Claim 19 into patent-eligible subject matter.
Therefore, Claims 19 and 20 are not drawn to patent-eligible subject matter as they are directed to an abstract idea without significantly more.
Claim Rejections - 35 U.S.C. § 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 1, 4, 5, 7, and 19 are rejected under 35 U.S.C. § 103 as being unpatentable over US 2026/0086775 (hereinafter “Li”) in view of US 2015/0142640 (hereinafter “Kneen”) and US 2024/0419917 (hereinafter “Clement”).
EXAMINER’S REMARKS
In order for a reference to be proper for use in an obviousness rejection under 35 U.S.C. § 103, the reference must be analogous art to the claimed invention. In re Bigio, 381 F.3d 1320, 1325, 72 USPQ2d 1209, 1212 (Fed. Cir. 2004). A reference is analogous art to the claimed invention if: (1) the reference is from the same field of endeavor as the claimed invention (even if it addresses a different problem); or (2) the reference is reasonably pertinent to the problem faced by the inventor (even if it is not in the same field of endeavor as the claimed invention). See MPEP § 2141.01(a)(I).
Note that the claimed invention is generally directed to automated code generation using large language models (LLMs) for software platform integrations with computing services (specification, paragraph [0009]). As for the “same field of endeavor” test, Li is generally directed to an extensibility and code generation system leveraging LLM capabilities (Abstract). As for the “reasonably pertinent” test, Kneen is generally directed to retrieving and displaying merchant payment preferences to a user (Abstract). And Clement is generally directed to automating prompts to a large language model to perform a specified software engineering task (Abstract). Thus, Li, Kneen, and Clement are all analogous art to the claimed invention (even if they address different problems or are not in the same field of endeavor as the claimed invention).
As per Claim 1, Li discloses:
A system (Figure 4) comprising:
a non-transitory memory (Figure 4: 408); and
one or more hardware processors (Figure 4: 404) coupled to the non-transitory memory and configured to execute instructions to cause the system to:
receive a request associated with integrating a software platform of a […] computing service […] (paragraph [0014], “[…] the user 110 may submit an update request 116 via a chatbot 118 (or chatbot interface) [receive a request associated with integrating a software platform of a […] computing service {…}].”; paragraph [0018], “CGS 102, which may include chatbot 118, may interpret or translate the update request 116 into one more technical commands and perform all the technical operations required to update application 108 in accordance with the update request 116 (emphasis added).”; paragraph [0066], “Computer system 400 may be a client or server, accessing or hosting any applications and/or data through any delivery paradigm, including but not limited to remote or distributed cloud computing solutions; local or on-premises software (‘on-premise’ cloud-based solutions); ‘as a service’ models (e.g., content as a service (CaaS), digital content as a service (DCaaS), software as a service (SaaS), managed software as a service (MSaaS), platform as a service (PaaS), desktop as a service (DaaS), framework as a service (FaaS), backend as a service (BaaS), mobile backend as a service (MBaaS), infrastructure as a service (IaaS), etc.); and/or a hybrid model including any combination of the foregoing examples or other services or delivery paradigms [a software platform of a {…} computing service {…}].”);
determine a large language model (LLM) prompt for an LLM configured to generate new code integrations with at least the computing service based on LLM training data associated with available code integrations for at least the computing service (paragraph [0027], “[…] LLM 104 may be specifically trained on a specification 128. Specification 128 may include a set of guidelines that were used to generate or code application 108, and may include references to metadata 130 of application 108. Specification 128 may include a template, library, or set of rules or configurations used to generate one or more applications 108. For example, even though only a single application 108 is illustrated, in some embodiments, there may be a suite of applications which are all developed in accordance with specification 128. Specification 128 may include a naming convention, library locations, etc. LLM 104 may be specifically trained with specification 128, such that LLM 104 is able to understand application 108 through metadata 130 and generate new code 106 in accordance with specification 128 for application 108, that can be integrated into source code 112, written in the same programing language as source code 112, or a compatible programming language (emphasis added).”; paragraph [0029], “Code prompt 126 may be a prompt generated to request new code 106 from LLM 104, corresponding to update request 116. In some embodiments, prompt generator 124 may provide the update request 116 and/or the name of the application 108 as input for the code prompt 126, and request new code 106 as output from the LLM 104. The new code 106 may include any revisions to be added to source code 112. In some embodiments, the new code 106 may include deleting or modifying existing source code 112 (emphasis added).”);
prompt the LLM to create a new code integration based on the LLM prompt and the payload (paragraph [0045], “Upon receiving confirmation, CGS 102 may generate a code prompt 126 and receive new code 106 from an LLM 104, trained to generate code for application 108 in accordance with specification 128. As illustrated in section 232, CGS 102 may provide the new code 106 to the user 110 to review/confirm. In some embodiments, the new code 106 may include some portions or copies of the pre-existing source code 112 (emphasis added).”);
EXAMINER’S REMARKS
Note that the Applicant’s specification expressly states that “[t]he payload may include such source code, as well as SDDs, source code files, source code change logs and/or informational logs, sample code and/or code snippets, desired code formats and/or code specifications or configurations, API specifications and/or call structures or requirements, legacy code integrations and/or legacy code, and the like” (paragraph [00078], emphasis added). Thus, under the broadest reasonable interpretation (BRI), the plain meaning of the limitation “payload” includes source code, which is consistent with the specification. Therefore, the limitation “payload,” given its plain meaning consistent with the specification, is mapped to Li’s source code. See MPEP § 2173.01(I).
receive the new code integration for the software platform from the LLM, wherein the new code integration comprises a code package of new code generated by the LLM […] (paragraph [0052], “In 340, new code corresponding to the update is generated. For example, a prompt generator 124 may generate a code prompt 126 to generate new code 106 corresponding to update request 116. The new code 106 may be in the same programming language, or a compatible programming language, as source code 112 (emphasis added).”; paragraph [0053], “In 350, the new code is provided for display via the user interface. For example, CGS 102 may receive new code 106 from LLM 104. CGS 102 may then format for display, via a chatbot (window) 118 the new code 106 for user review/approval/modification. In some embodiments, CGS 102 may generate a modifiable file with new code 106 [a code package of new code generated by the LLM], such that user 110 may modify (134) the new code 106 in a code preview 132 window. The user 110 may then approve the new code 106 (emphasis added).”); and
EXAMINER’S REMARKS
Note that the Applicant’s specification expressly states that “[…]migration assistant service 202 may combine, stitch together, or otherwise package each code section into a single code package or file that may be executable and/or utilized to integrate code and/or upgrade/migrate existing code for computing service usage on a merchant platform” (paragraph [00075], emphasis added). Thus, under the broadest reasonable interpretation (BRI), the plain meaning of the limitation “code package” includes code file, which is consistent with the specification. Therefore, the limitation “code package,” given its plain meaning consistent with the specification, is mapped to Li’s modifiable file with new code. See MPEP § 2173.01(I).
load the code package for the new code integration to a […] computing system […] (paragraph [0054], “In 360, the new code, corresponding to the update, is integrated into the application. For example, prompt generator 124 may generate a finalize prompt 142 which may cause LLM 104 to integrate the new code 106 into source code 112 [load the code package for the new code integration to a {…} computing system {…}].”).
Li does not explicitly disclose:
[…] a merchant with a computing service associated with a service provider;
[…] one or more uses of the computing service of the service provider via the software platform of the merchant; and
[…] a selected computing system designated by the merchant.
However, Kneen discloses:
[…] a merchant with a computing service associated with a service provider (paragraph [0021], “The merchant payee device 130, in various embodiments, may be implemented using any appropriate combination of hardware and/or software configured for wired and/or wireless communication over the network 160 (emphasis added).”; paragraph [0029], “The service provider may be, for example, PayPal®, Inc. of San Jose, CA, which assists in the making of payments from the user 102 to the merchant by transferring funds from the user account to a merchant account.”);
[…] one or more uses of the computing service of the service provider via the software platform of the merchant (paragraph [0021], “The merchant payee device 130, in various embodiments, may be implemented using any appropriate combination of hardware and/or software configured for wired and/or wireless communication over the network 160 (emphasis added).”; paragraph [0029], “The service provider may be, for example, PayPal®, Inc. of San Jose, CA, which assists in the making of payments from the user 102 to the merchant by transferring funds from the user account to a merchant account (emphasis added).”); and
[…] a selected computing system designated by the merchant (paragraph [0021], “The merchant payee device 130, in various embodiments, may be implemented using any appropriate combination of hardware and/or software configured for wired and/or wireless communication over the network 160 (emphasis added).”; paragraph [0034], “At step 206, the user 102 selects a merchant, and may check-in or register with the merchant on the mobile device 120. Once the user 102 inputs a selection, at step 208, the service provider server 180 automatically generates and displays payment methods or options acceptable by the selected merchant (emphasis added).”).
As pointed out hereinabove, Li and Kneen are both analogous art to the claimed invention. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Kneen into the teaching of Li to include “[…] a merchant with a computing service associated with a service provider; […] one or more uses of the computing service of the service provider via the software platform of the merchant; and […] a selected computing system designated by the merchant.” The modification would be obvious because one of ordinary skill in the art would be motivated to provide modifications to a software platform of an on-line or mobile payment service provider such as, for example, PayPal®, Inc. of San Jose, Calif (Kneen, paragraph [0004]).
The combination of Li and Kneen does not explicitly disclose:
wherein the request comprises a payload associated with the software platform.
However, Clement discloses:
wherein the request comprises a payload associated with the software platform (paragraph [0024], “A request may include a query, a context, and/or an intent 112. The query is a request for an action, the context is the subject of the action, such as source code, code diff hunks, or a URL, and the intent specifies the software engineering task related to the action (emphasis added).”).
EXAMINER’S REMARKS
Note that the Applicant’s specification expressly states that “[t]he payload may include such source code, as well as SDDs, source code files, source code change logs and/or informational logs, sample code and/or code snippets, desired code formats and/or code specifications or configurations, API specifications and/or call structures or requirements, legacy code integrations and/or legacy code, and the like” (paragraph [00078], emphasis added). Thus, under the broadest reasonable interpretation (BRI), the plain meaning of the limitation “payload” includes source code, which is consistent with the specification. Therefore, the limitation “payload,” given its plain meaning consistent with the specification, is mapped to Clement’s source code. See MPEP § 2173.01(I).
As pointed out hereinabove, Clement is an analogous art to the claimed invention. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Clement into the combined teachings of Li and Kneen to include “wherein the request comprises a payload associated with the software platform.” The modification would be obvious because one of ordinary skill in the art would be motivated to create a custom prompt for a large language model to perform a specific software engineering task and generate a response (Clement, paragraph [0022]).
As per Claim 4, the rejection of Claim 1 is incorporated; and Li further discloses:
determine a software design document (SSD) for the software platform (paragraph [0027], “[…] LLM 104 may be specifically trained on a specification 128. Specification 128 may include a set of guidelines that were used to generate or code application 108, and may include references to metadata 130 of application 108. Specification 128 may include a template, library, or set of rules or configurations used to generate one or more applications 108. For example, even though only a single application 108 is illustrated, in some embodiments, there may be a suite of applications which are all developed in accordance with specification 128. Specification 128 may include a naming convention, library locations, etc. LLM 104 may be specifically trained with specification 128, such that LLM 104 is able to understand application 108 through metadata 130 and generate new code 106 in accordance with specification 128 for application 108, that can be integrated into source code 112, written in the same programing language as source code 112, or a compatible programming language.”),
wherein the prompting is further based on the SSD (paragraph [0045], “Upon receiving confirmation, CGS 102 may generate a code prompt 126 and receive new code 106 from an LLM 104, trained to generate code for application 108 in accordance with specification 128.”).
As per Claim 5, the rejection of Claim 1 is incorporated; and Li further discloses:
wherein the LLM prompt comprises a plurality of LLM prompts (paragraph [0026], “Upon receiving update request 116, or a confirmation of the request 116, a prompt generator 124 may generate one or more prompts for LLM 104 to perform some functionality or generate a response. A prompt may include one or more lines of text organized across one or more documents that is particularly formatted to by understandable by a large language model (LLM) 104.”).
The combination of Li and Kneen does not explicitly disclose:
wherein prompting the LLM is further based on each of the plurality of LLM prompts and a corresponding portion of the payload.
However, Clement discloses:
wherein prompting the LLM is further based on each of the plurality of LLM prompts and a corresponding portion of the payload (paragraph [0021], “The system includes a customized prompt generation service 102 that interacts with a large language model 104A-104N (‘104’) of a model hosting service 106 to perform a specific software engineering task.”; paragraph [0030], “The code review prompt service 118 utilizes a code quality model 122 to determine whether a code review is needed.”; paragraph [0031], “The code search prompt service 124 searches for source code satisfying a query. The large language model does not have access to perform the search in the client’s codebase or repository.”; paragraph [0032], “The vulnerability repair prompt service 128 determines whether or not a source code snippet contains a software vulnerability.”).
As pointed out hereinabove, Clement is an analogous art to the claimed invention. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Clement into the combined teachings of Li and Kneen to include “wherein prompting the LLM is further based on each of the plurality of LLM prompts and a corresponding portion of the payload.” The modification would be obvious because one of ordinary skill in the art would be motivated to create a custom prompt for a large language model to perform a specific software engineering task and generate a response (Clement, paragraph [0022]).
As per Claim 7, the rejection of Claim 1 is incorporated; and Li further discloses:
wherein the new code, when executed, integrates the computing service on […] (paragraph [0054], “In 360, the new code, corresponding to the update, is integrated into the application. For example, prompt generator 124 may generate a finalize prompt 142 which may cause LLM 104 to integrate the new code 106 into source code 112.”).
The combination of Li and Clement does not explicitly disclose:
[…] the software platform of the merchant for use by one or more users via a website or an application of the merchant, and wherein the computing service comprises at least one of a user authentication service, a transaction processing service, or a digital account service.
However, Kneen discloses:
[…] the software platform of the merchant for use by one or more users via a website or an application of the merchant (paragraph [0014], “The mobile device 120, in one embodiment, may be utilized by the user 102 to interact with the service provider server 180, over the network 160. For example, the user 102 may log in to a mobile application run by the service provider via the mobile device 120.”; paragraph [0029], “The service provider may be, for example, PayPal®, Inc. of San Jose, CA, which assists in the making of payments from the user 102 to the merchant by transferring funds from the user account to a merchant account.”), and wherein the computing service comprises at least one of a user authentication service, a transaction processing service, or a digital account service (paragraph [0016], “The mobile device 120, in one embodiment, includes a user interface application 122, which may be utilized by the user 102 to conduct transactions (e.g., shopping, purchasing, bidding, transferring, etc.) with the service provider server 180 over the network 160.”).
As pointed out hereinabove, Kneen is an analogous art to the claimed invention. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Kneen into the combined teachings of Li and Clement to include “ […] the software platform of the merchant for use by one or more users via a website or an application of the merchant, and wherein the computing service comprises at least one of a user authentication service, a transaction processing service, or a digital account service.” The modification would be obvious because one of ordinary skill in the art would be motivated to provide modifications to a software platform of an on-line or mobile payment service provider such as, for example, PayPal®, Inc. of San Jose, Calif (Kneen, paragraph [0004]).
As per Claim 19, Li discloses:
A non-transitory machine-readable medium (Figure 4: 414) having stored thereon machine- readable instructions executable to cause a machine to perform operations comprising:
receiving a request for a use of a computing service of a […] software platform […] (paragraph [0014], “[…] the user 110 may submit an update request 116 via a chatbot 118 (or chatbot interface) [receiving a request for a use of a computing service of a {…} software platform {…}].”; paragraph [0018], “CGS 102, which may include chatbot 118, may interpret or translate the update request 116 into one more technical commands and perform all the technical operations required to update application 108 in accordance with the update request 116 (emphasis added).”; paragraph [0066], “Computer system 400 may be a client or server, accessing or hosting any applications and/or data through any delivery paradigm, including but not limited to remote or distributed cloud computing solutions; local or on-premises software (‘on-premise’ cloud-based solutions); ‘as a service’ models (e.g., content as a service (CaaS), digital content as a service (DCaaS), software as a service (SaaS), managed software as a service (MSaaS), platform as a service (PaaS), desktop as a service (DaaS), framework as a service (FaaS), backend as a service (BaaS), mobile backend as a service (MBaaS), infrastructure as a service (IaaS), etc.); and/or a hybrid model including any combination of the foregoing examples or other services or delivery paradigms [a use of a computing service of a {…} software platform {…}].”);
determining at least one large language model (LLM) prompt for an LLM configured to generate a new code integration of the computing service with different software platforms based on LLM training data associated with integrating code for the computing service with the different software platforms (paragraph [0027], “[…] LLM 104 may be specifically trained on a specification 128. Specification 128 may include a set of guidelines that were used to generate or code application 108, and may include references to metadata 130 of application 108. Specification 128 may include a template, library, or set of rules or configurations used to generate one or more applications 108. For example, even though only a single application 108 is illustrated, in some embodiments, there may be a suite of applications which are all developed in accordance with specification 128. Specification 128 may include a naming convention, library locations, etc. LLM 104 may be specifically trained with specification 128, such that LLM 104 is able to understand application 108 through metadata 130 and generate new code 106 in accordance with specification 128 for application 108, that can be integrated into source code 112, written in the same programing language as source code 112, or a compatible programming language (emphasis added).”; paragraph [0029], “Code prompt 126 may be a prompt generated to request new code 106 from LLM 104, corresponding to update request 116. In some embodiments, prompt generator 124 may provide the update request 116 and/or the name of the application 108 as input for the code prompt 126, and request new code 106 as output from the LLM 104. The new code 106 may include any revisions to be added to source code 112. In some embodiments, the new code 106 may include deleting or modifying existing source code 112 (emphasis added).”);
prompting the LLM based on the at least one LLM prompt and the computing code data (paragraph [0045], “Upon receiving confirmation, CGS 102 may generate a code prompt 126 and receive new code 106 from an LLM 104, trained to generate code for application 108 in accordance with specification 128. As illustrated in section 232, CGS 102 may provide the new code 106 to the user 110 to review/confirm. In some embodiments, the new code 106 may include some portions or copies of the pre-existing source code 112 (emphasis added).”);
receiving the new code integration for the software platform from the LLM, wherein the new code integration comprises new code generated by the LLM […] (paragraph [0052], “In 340, new code corresponding to the update is generated. For example, a prompt generator 124 may generate a code prompt 126 to generate new code 106 corresponding to update request 116. The new code 106 may be in the same programming language, or a compatible programming language, as source code 112 (emphasis added).”; paragraph [0053], “In 350, the new code is provided for display via the user interface. For example, CGS 102 may receive new code 106 from LLM 104. CGS 102 may then format for display, via a chatbot (window) 118 the new code 106 for user review/approval/modification. In some embodiments, CGS 102 may generate a modifiable file with new code 106, such that user 110 may modify (134) the new code 106 in a code preview 132 window. The user 110 may then approve the new code 106 (emphasis added).”); and
communicating the code package to the [software platform] (paragraph [0012], “CGS 102 may allow the user 110 to leverage the coding capabilities of an LLM 104 to perform the code changes, and allow the user 110 to test the updated code, and deploy the update to the application 108 [communicating the code package to the {software platform}].”; paragraph [0053], “In 350, the new code is provided for display via the user interface. For example, CGS 102 may receive new code 106 from LLM 104. CGS 102 may then format for display, via a chatbot (window) 118 the new code 106 for user review/approval/modification. In some embodiments, CGS 102 may generate a modifiable file with new code 106 [the code package], such that user 110 may modify (134) the new code 106 in a code preview 132 window. The user 110 may then approve the new code 106.”).
EXAMINER’S REMARKS
Note that the Applicant’s specification expressly states that “[…]migration assistant service 202 may combine, stitch together, or otherwise package each code section into a single code package or file that may be executable and/or utilized to integrate code and/or upgrade/migrate existing code for computing service usage on a merchant platform” (paragraph [00075], emphasis added). Thus, under the broadest reasonable interpretation (BRI), the plain meaning of the limitation “code package” includes code file, which is consistent with the specification. Therefore, the limitation “code package,” given its plain meaning consistent with the specification, is mapped to Li’s modifiable file with new code. See MPEP § 2173.01(I).
Li does not explicitly disclose:
[…] a computing service of a service provider with a software platform of a merchant; and
[…] the use of the computing service of the service provider via the software platform of the merchant.
However, Kneen discloses:
[…] a computing service of a service provider with a software platform of a merchant (paragraph [0021], “The merchant payee device 130, in various embodiments, may be implemented using any appropriate combination of hardware and/or software configured for wired and/or wireless communication over the network 160 (emphasis added).”; paragraph [0029], “The service provider may be, for example, PayPal®, Inc. of San Jose, CA, which assists in the making of payments from the user 102 to the merchant by transferring funds from the user account to a merchant account.”); and
[…] the use of the computing service of the service provider via the software platform of the merchant (paragraph [0021], “The merchant payee device 130, in various embodiments, may be implemented using any appropriate combination of hardware and/or software configured for wired and/or wireless communication over the network 160 (emphasis added).”; paragraph [0029], “The service provider may be, for example, PayPal®, Inc. of San Jose, CA, which assists in the making of payments from the user 102 to the merchant by transferring funds from the user account to a merchant account (emphasis added).”).
As pointed out hereinabove, Li and Kneen are both analogous art to the claimed invention. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Kneen into the teaching of Li to include “[…] a computing service of a service provider with a software platform of a merchant; and […] the use of the computing service of the service provider via the software platform of the merchant.” The modification would be obvious because one of ordinary skill in the art would be motivated to provide modifications to a software platform of an on-line or mobile payment service provider such as, for example, PayPal®, Inc. of San Jose, Calif (Kneen, paragraph [0004]).
The combination of Li and Kneen does not explicitly disclose:
wherein the request comprises computing code data associated with the software platform.
However, Clement discloses:
wherein the request comprises computing code data associated with the software platform (paragraph [0024], “A request may include a query, a context, and/or an intent 112. The query is a request for an action, the context is the subject of the action, such as source code, code diff hunks, or a URL, and the intent specifies the software engineering task related to the action (emphasis added).”).
As pointed out hereinabove, Clement is an analogous art to the claimed invention. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Clement into the combined teachings of Li and Kneen to include “wherein the request comprises computing code data associated with the software platform.” The modification would be obvious because one of ordinary skill in the art would be motivated to create a custom prompt for a large language model to perform a specific software engineering task and generate a response (Clement, paragraph [0022]).
Claims 2 and 3 are rejected under 35 U.S.C. § 103 as being unpatentable over Li in view of Kneen and Clement as applied to Claim 1 above, and further in view of US 2024/0078140 (hereinafter “Srivastava”) (cited in the IDS submitted on 01/09/2026).
EXAMINER’S REMARKS
In order for a reference to be proper for use in an obviousness rejection under 35 U.S.C. § 103, the reference must be analogous art to the claimed invention. In re Bigio, 381 F.3d 1320, 1325, 72 USPQ2d 1209, 1212 (Fed. Cir. 2004). A reference is analogous art to the claimed invention if: (1) the reference is from the same field of endeavor as the claimed invention (even if it addresses a different problem); or (2) the reference is reasonably pertinent to the problem faced by the inventor (even if it is not in the same field of endeavor as the claimed invention). See MPEP § 2141.01(a)(I).
Note that the claimed invention is generally directed to automated code generation using large language models (LLMs) for software platform integrations with computing services (specification, paragraph [0009]). As for the “reasonably pertinent” test, Srivastava is generally directed to the use of legacy APIs in the cloud environment (specification, paragraph [0004]). Thus, Srivastava is an analogous art to the claimed invention (even if it is not in the same field of endeavor as the claimed invention).
As per Claim 2, the rejection of Claim 1 is incorporated; and the combination of Li, Kneen, and Clement does not explicitly disclose:
wherein the request comprises an update of existing code with a set of legacy application programming interfaces (APIs) previously used with the computing service to the new code for a set of current APIs for the computing service.
However, Srivastava discloses:
wherein the request comprises an update of existing code with a set of legacy application programming interfaces (APIs) previously used with the computing service to the new code for a set of current APIs for the computing service (paragraph [0021], “While the new applications and APIs are helpful, users may want to update/modernize their existing legacy APIs to be used in the cloud platform.”; paragraph [0038], “With every new release or every new version, the API mapping table 142 may be populated with the updated APIs that are being released for that particular version/release and are mapped to the legacy API that was previously provided.”; paragraph [0049], “In a case the new updated API has been published, the process may return to S216, and the API mapping table may be updated with the newly created updated API mapped to an existing legacy API.”).
As pointed out hereinabove, Srivastava is an analogous art to the claimed invention. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Srivastava into the combined teachings of Li, Kneen, and Clement to include “wherein the request comprises an update of existing code with a set of legacy application programming interfaces (APIs) previously used with the computing service to the new code for a set of current APIs for the computing service.” The modification would be obvious because one of ordinary skill in the art would be motivated to update/modernize existing legacy APIs to be used in a cloud platform (Srivastava, paragraph [0021]).
As per Claim 3, the rejection of Claim 2 is incorporated; and Li further discloses:
wherein the existing code comprises source code currently used by the software platform (paragraph [0015], “Application 108 may include any computer program, application, web application, or app, that includes source code 112 that can be updated to modify the functionality of application 108. Source code 112 may include any computing code written across one or more computing or programming languages which is used to execute application 108 (which may be done after compiling the source code 112).”; paragraph [0029], “[…] the new code 106 may include deleting or modifying existing source code 112.”).
The combination of Li and Kneen does not explicitly disclose:
wherein the payload comprises one or more code packages for the source code.
However, Clement discloses:
wherein the payload comprises one or more code packages for the source code (paragraph [0021], “The custom data includes source code artifacts such as code segments from code files (script files, source code, build files, etc.), unit tests, code changes (code diff hunks), code reviews, repaired code, etc.”; paragraph [0024], “A request may include a query, a context, and/or an intent 112. The query is a request for an action, the context is the subject of the action, such as source code, code diff hunks, or a URL, and the intent specifies the software engineering task related to the action.”).
As pointed out hereinabove, Clement is an analogous art to the claimed invention. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Clement into the combined teachings of Li and Kneen to include “wherein the payload comprises one or more code packages for the source code.” The modification would be obvious because one of ordinary skill in the art would be motivated to create a custom prompt for a large language model to perform a specific software engineering task and generate a response (Clement, paragraph [0022]).
The combination of Li, Kneen, and Clement does not explicitly disclose:
wherein the set of current APIs include one or more representational state transfer (REST) APIs.
However, Srivastava discloses:
wherein the set of current APIs include one or more representational state transfer (REST) APIs (paragraph [0020], “Any development on ABAP on BTP may use an ABAP RESTful Application Programming Model (RAP). RAP is a development paradigm/framework that may support the efficient development of cloud-ready applications, new APIs (which may be referred to as a ‘RAP API’), as well as the extension of standard APIs and applications to the cloud environment.”).
As pointed out hereinabove, Srivastava is an analogous art to the claimed invention. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Srivastava into the combined teachings of Li, Kneen, and Clement to include “wherein the set of current APIs include one or more representational state transfer (REST) APIs.” The modification would be obvious because one of ordinary skill in the art would be motivated to update/modernize existing legacy APIs to be used in a cloud platform (Srivastava, paragraph [0021]).
Claim 6 is rejected under 35 U.S.C. § 103 as being unpatentable over Li in view of Kneen and Clement as applied to Claim 5 above, and further in view of US 2025/0378322 (hereinafter “Ramakrishnan”).
EXAMINER’S REMARKS
In order for a reference to be proper for use in an obviousness rejection under 35 U.S.C. § 103, the reference must be analogous art to the claimed invention. In re Bigio, 381 F.3d 1320, 1325, 72 USPQ2d 1209, 1212 (Fed. Cir. 2004). A reference is analogous art to the claimed invention if: (1) the reference is from the same field of endeavor as the claimed invention (even if it addresses a different problem); or (2) the reference is reasonably pertinent to the problem faced by the inventor (even if it is not in the same field of endeavor as the claimed invention). See MPEP § 2141.01(a)(I).
Note that the claimed invention is generally directed to automated code generation using large language models (LLMs) for software platform integrations with computing services (specification, paragraph [0009]). As for the “reasonably pertinent” test, Ramakrishnan is generally directed to context recommendation in information processing systems (specification, paragraph [0002]). Thus, Ramakrishnan is an analogous art to the claimed invention (even if it is not in the same field of endeavor as the claimed invention).
As per Claim 6, the rejection of Claim 5 is incorporated; and Li further discloses:
wherein the plurality of LLM prompts are associated with generating the new code for at least one of an authentication process, backend code, a backend API layer, a user interface, one or more user interface elements, or one or more application dependencies (paragraph [0045], “Upon receiving confirmation, CGS 102 may generate a code prompt 126 and receive new code 106 from an LLM 104, trained to generate code for application 108 in accordance with specification 128. As illustrated in section 232, CGS 102 may provide the new code 106 to the user 110 to review/confirm. In some embodiments, the new code 106 may include some portions or copies of the pre-existing source code 112.”; paragraph [0066], “Computer system 400 may be a client or server, accessing or hosting any applications and/or data through any delivery paradigm, including but not limited to remote or distributed cloud computing solutions; local or on-premises software (‘on-premise’ cloud-based solutions); ‘as a service’ models (e.g., content as a service (CaaS), digital content as a service (DCaaS), software as a service (SaaS), managed software as a service (MSaaS), platform as a service (PaaS), desktop as a service (DaaS), framework as a service (FaaS), backend as a service (BaaS), mobile backend as a service (MBaaS), infrastructure as a service (IaaS), etc.); and/or a hybrid model including any combination of the foregoing examples or other services or delivery paradigms.”).
The combination of Li, Kneen, and Clement does not explicitly disclose:
wherein prompting the LLM uses an orchestration layer of the system to prompt the LLM using each of the plurality of LLM prompts and the corresponding portion of the payload.
However, Ramakrishnan discloses:
wherein prompting the LLM uses an orchestration layer of the system to prompt the LLM using each of the plurality of LLM prompts and the corresponding portion of the payload (paragraph [0046], “The orchestration layers 133 build the LLM prompts. In more detail, with the relevant context for the question being retrieved, the next step involves integrating this retrieved information into a prompt for the LLM 134.”; paragraph [0047], “The orchestration layers 133 are used to call the LLMs 134. In more detail, a constructed prompt is fed to an LLM 134, which generates a response.”; paragraph [0061], “Pseudocode 701 for common embedding of an LLM request and PCA to reduce dimensionality of the request vector is shown in FIG. 7A.”).
As pointed out hereinabove, Ramakrishnan is an analogous art to the claimed invention. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Ramakrishnan into the combined teachings of Li, Kneen, and Clement to include “wherein prompting the LLM uses an orchestration layer of the system to prompt the LLM using each of the plurality of LLM prompts and the corresponding portion of the payload.” The modification would be obvious because one of ordinary skill in the art would be motivated to generate a prompt for a request and respond to the request, and implement necessary interfaces (e.g., APIs) and commands to interface with orchestration layers and LLMs (Ramakrishnan, paragraph [0052]).
Claim 8 is rejected under 35 U.S.C. § 103 as being unpatentable over Li in view of Kneen and Clement as applied to Claim 1 above, and further in view of US 2016/0103667 (hereinafter “Chen”).
EXAMINER’S REMARKS
In order for a reference to be proper for use in an obviousness rejection under 35 U.S.C. § 103, the reference must be analogous art to the claimed invention. In re Bigio, 381 F.3d 1320, 1325, 72 USPQ2d 1209, 1212 (Fed. Cir. 2004). A reference is analogous art to the claimed invention if: (1) the reference is from the same field of endeavor as the claimed invention (even if it addresses a different problem); or (2) the reference is reasonably pertinent to the problem faced by the inventor (even if it is not in the same field of endeavor as the claimed invention). See MPEP § 2141.01(a)(I).
Note that the claimed invention is generally directed to automated code generation using large language models (LLMs) for software platform integrations with computing services (specification, paragraph [0009]). As for the “reasonably pertinent” test, Chen is generally directed to creating a deployment package for deploying an application (Abstract). Thus, Chen is an analogous art to the claimed invention (even if it is not in the same field of endeavor as the claimed invention).
As per Claim 8, the rejection of Claim 1 is incorporated; and the combination of Li, Kneen, and Clement discloses “the merchant,” but the combination of Li, Kneen, and Clement does not explicitly disclose:
wherein loading the code package comprises pushing the code package to the selected computing system designated by the merchant, and wherein the selected computing system comprises one of a test computing environment, a production computing environment, or a code repository platform.
However, Chen discloses:
wherein loading the code package comprises pushing the code package to the selected computing system designated by the [user], and wherein the selected computing system comprises one of a test computing environment, a production computing environment, or a code repository platform (paragraph [0016], “When an administrator deploys the application entity, the administrator can specify the target environment. This causes an appropriate configuration file to be selected for the target environment.”; paragraph [0028], “The deployable application entity 118 and the transformed configuration datasets 120-1 through 120-n are assembled into a deployment package 122.”; paragraph [0031], “[…] assuming that the target environment 134 is a production environment, and the administrator 128 enters one or more commands 130 indicating that the target environment is a production environment, the configuration dataset 120-3 (see FIG. 1) will be selected from the deployment package 122.”; paragraph [0053], “The method 400 further includes based on the command, selecting one of the configuration datasets and deploying the selected configuration dataset along with the application entity to the target environment (act 408).”).
As pointed out hereinabove, Chen is an analogous art to the claimed invention. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Chen into the combined teachings of Li, Kneen, and Clement to include “wherein loading the code package comprises pushing the code package to the selected computing system designated by the merchant, and wherein the selected computing system comprises one of a test computing environment, a production computing environment, or a code repository platform.” The modification would be obvious because one of ordinary skill in the art would be motivated to deploy a deployment package to a target environment specified by a merchant (Chen, paragraph [0016]).
Claim 9 is rejected under 35 U.S.C. § 103 as being unpatentable over Li in view of Kneen and Clement as applied to Claim 1 above, and further in view of US 2025/0094138 (hereinafter “Hu”).
EXAMINER’S REMARKS
In order for a reference to be proper for use in an obviousness rejection under 35 U.S.C. § 103, the reference must be analogous art to the claimed invention. In re Bigio, 381 F.3d 1320, 1325, 72 USPQ2d 1209, 1212 (Fed. Cir. 2004). A reference is analogous art to the claimed invention if: (1) the reference is from the same field of endeavor as the claimed invention (even if it addresses a different problem); or (2) the reference is reasonably pertinent to the problem faced by the inventor (even if it is not in the same field of endeavor as the claimed invention). See MPEP § 2141.01(a)(I).
Note that the claimed invention is generally directed to automated code generation using large language models (LLMs) for software platform integrations with computing services (specification, paragraph [0009]). As for the “reasonably pertinent” test, Hu is generally directed to automated fine-tuning of software code generation by large language models (Abstract). Thus, Hu is an analogous art to the claimed invention (even if it is not in the same field of endeavor as the claimed invention).
As per Claim 9, the rejection of Claim 1 is incorporated; and the combination of Li, Kneen, and Clement does not explicitly disclose:
wherein prompting the LLM is further based on sample code for at least one of the available code integrations.
However, Hu discloses:
wherein prompting the LLM is further based on sample code for at least one of the available code integrations (paragraph [0025], “[…] data breaker 106 is configured to transmit or otherwise pass sample code 124 and prompt 126 to LLM fine tuner 108, where sample code 124 and prompt 126 may be used in operations to fine-tune the code generation performance of a large language model (LLM) 132 by further training.”).
As pointed out hereinabove, Hu is an analogous art to the claimed invention. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Hu into the combined teachings of Li, Kneen, and Clement to include “wherein prompting the LLM is further based on sample code for at least one of the available code integrations.” The modification would be obvious because one of ordinary skill in the art would be motivated to fine-tune code generation performance of a large language model (LLM) by further training using sample code (Hu, paragraph [0025]).
Claims 10, 15, and 16 are rejected under 35 U.S.C. § 103 as being unpatentable over US 2026/0086775 (hereinafter “Li”) in view of US 2015/0142640 (hereinafter “Kneen”).
EXAMINER’S REMARKS
In order for a reference to be proper for use in an obviousness rejection under 35 U.S.C. § 103, the reference must be analogous art to the claimed invention. In re Bigio, 381 F.3d 1320, 1325, 72 USPQ2d 1209, 1212 (Fed. Cir. 2004). A reference is analogous art to the claimed invention if: (1) the reference is from the same field of endeavor as the claimed invention (even if it addresses a different problem); or (2) the reference is reasonably pertinent to the problem faced by the inventor (even if it is not in the same field of endeavor as the claimed invention). See MPEP § 2141.01(a)(I).
Note that the claimed invention is generally directed to automated code generation using large language models (LLMs) for software platform integrations with computing services (specification, paragraph [0009]). As for the “same field of endeavor” test, Li is generally directed to an extensibility and code generation system leveraging LLM capabilities (Abstract). As for the “reasonably pertinent” test, Kneen is generally directed to retrieving and displaying merchant payment preferences to a user (Abstract). Thus, Li and Kneen are both analogous art to the claimed invention (even if they address different problems or are not in the same field of endeavor as the claimed invention).
As per Claim 10, Li discloses:
A method (paragraph [0009], “Provided herein are […] method […] for providing a customized application extensibility and code generation system leveraging large language model (LLM) capabilities.”) comprising:
determining that a code integration with a computing service […] is available for a computing platform (paragraph [0051], “In 330, the one or more data elements are provided for display via the user interface. For example, CGS 102 may generate an application snippet 120 including the data elements 114 related or that are likely to be impacted by the update request 116 [determining that a code integration with a computing service {…} is available for a computing platform].”; paragraph [0066], “Computer system 400 may be a client or server, accessing or hosting any applications and/or data through any delivery paradigm, including but not limited to remote or distributed cloud computing solutions; local or on-premises software (‘on-premise’ cloud-based solutions); ‘as a service’ models (e.g., content as a service (CaaS), digital content as a service (DCaaS), software as a service (SaaS), managed software as a service (MSaaS), platform as a service (PaaS), desktop as a service (DaaS), framework as a service (FaaS), backend as a service (BaaS), mobile backend as a service (MBaaS), infrastructure as a service (IaaS), etc.); and/or a hybrid model including any combination of the foregoing examples or other services or delivery paradigms [a computing service {…} is available for a computing platform].”);
determining a payload usable when prompting a large language model (LLM) for an automated generation of the code integration, wherein the LLM is configured to generate new code integrations with at least the computing service based on LLM training data associated with available code integrations for at least the computing service (paragraph [0027], “[…] LLM 104 may be specifically trained on a specification 128. Specification 128 may include a set of guidelines that were used to generate or code application 108, and may include references to metadata 130 of application 108. Specification 128 may include a template, library, or set of rules or configurations used to generate one or more applications 108. For example, even though only a single application 108 is illustrated, in some embodiments, there may be a suite of applications which are all developed in accordance with specification 128. Specification 128 may include a naming convention, library locations, etc. LLM 104 may be specifically trained with specification 128, such that LLM 104 is able to understand application 108 through metadata 130 and generate new code 106 in accordance with specification 128 for application 108, that can be integrated into source code 112, written in the same programing language as source code 112, or a compatible programming language (emphasis added).”; paragraph [0029], “Code prompt 126 may be a prompt generated to request new code 106 from LLM 104, corresponding to update request 116. In some embodiments, prompt generator 124 may provide the update request 116 and/or the name of the application 108 as input for the code prompt 126, and request new code 106 as output from the LLM 104. The new code 106 may include any revisions to be added to source code 112. In some embodiments, the new code 106 may include deleting or modifying existing source code 112 [determining a payload usable] (emphasis added).”);
EXAMINER’S REMARKS
Note that the Applicant’s specification expressly states that “[t]he payload may include such source code, as well as SDDs, source code files, source code change logs and/or informational logs, sample code and/or code snippets, desired code formats and/or code specifications or configurations, API specifications and/or call structures or requirements, legacy code integrations and/or legacy code, and the like” (paragraph [00078], emphasis added). Thus, under the broadest reasonable interpretation (BRI), the plain meaning of the limitation “payload” includes source code, which is consistent with the specification. Therefore, the limitation “payload,” given its plain meaning consistent with the specification, is mapped to Li’s source code. See MPEP § 2173.01(I).
identifying an LLM prompt associated with the code integration and the LLM (paragraph [0045], “Upon receiving confirmation, CGS 102 may generate a code prompt 126 and receive new code 106 from an LLM 104, trained to generate code for application 108 in accordance with specification 128 (emphasis added).”);
prompting the LLM based on the LLM prompt and the payload (paragraph [0045], “Upon receiving confirmation, CGS 102 may generate a code prompt 126 and receive new code 106 from an LLM 104, trained to generate code for application 108 in accordance with specification 128. As illustrated in section 232, CGS 102 may provide the new code 106 to the user 110 to review/confirm. In some embodiments, the new code 106 may include some portions or copies of the pre-existing source code 112 (emphasis added).”);
receiving, based on the prompting, a new code integration for the computing platform from the LLM, wherein the new code integration comprises a code package of new code […] (paragraph [0052], “In 340, new code corresponding to the update is generated. For example, a prompt generator 124 may generate a code prompt 126 to generate new code 106 corresponding to update request 116. The new code 106 may be in the same programming language, or a compatible programming language, as source code 112 (emphasis added).”; paragraph [0053], “In 350, the new code is provided for display via the user interface. For example, CGS 102 may receive new code 106 from LLM 104. CGS 102 may then format for display, via a chatbot (window) 118 the new code 106 for user review/approval/modification. In some embodiments, CGS 102 may generate a modifiable file with new code 106 [a code package of new code], such that user 110 may modify (134) the new code 106 in a code preview 132 window. The user 110 may then approve the new code 106 (emphasis added).”); and
EXAMINER’S REMARKS
Note that the Applicant’s specification expressly states that “[…]migration assistant service 202 may combine, stitch together, or otherwise package each code section into a single code package or file that may be executable and/or utilized to integrate code and/or upgrade/migrate existing code for computing service usage on a merchant platform” (paragraph [00075], emphasis added). Thus, under the broadest reasonable interpretation (BRI), the plain meaning of the limitation “code package” includes code file, which is consistent with the specification. Therefore, the limitation “code package,” given its plain meaning consistent with the specification, is mapped to Li’s modifiable file with new code. See MPEP § 2173.01(I).
outputting the new code integration via a code integration deployment process for the code integration of the computing platform with the computing service. (paragraph [0053], “In 350, the new code is provided for display via the user interface. For example, CGS 102 may receive new code 106 from LLM 104. CGS 102 may then format for display, via a chatbot (window) 118 the new code 106 for user review/approval/modification. In some embodiments, CGS 102 may generate a modifiable file with new code 106, such that user 110 may modify (134) the new code 106 in a code preview 132 window. The user 110 may then approve the new code 106 (emphasis added).”).
Li does not explicitly disclose:
[…] a computing service provided by a service provider is available for a computing platform; and
[…] one or more uses of the computing service of the service provider via the computing platform.
However, Kneen discloses:
[…] a computing service provided by a service provider is available for a computing platform (paragraph [0021], “The merchant payee device 130, in various embodiments, may be implemented using any appropriate combination of hardware and/or software configured for wired and/or wireless communication over the network 160 (emphasis added).”; paragraph [0029], “The service provider may be, for example, PayPal®, Inc. of San Jose, CA, which assists in the making of payments from the user 102 to the merchant by transferring funds from the user account to a merchant account.”); and
[…] one or more uses of the computing service of the service provider via the computing platform (paragraph [0021], “The merchant payee device 130, in various embodiments, may be implemented using any appropriate combination of hardware and/or software configured for wired and/or wireless communication over the network 160 (emphasis added).”; paragraph [0029], “The service provider may be, for example, PayPal®, Inc. of San Jose, CA, which assists in the making of payments from the user 102 to the merchant by transferring funds from the user account to a merchant account (emphasis added).”).
As pointed out hereinabove, Li and Kneen are both analogous art to the claimed invention. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Kneen into the teaching of Li to include “[…] a computing service provided by a service provider is available for a computing platform; and […] one or more uses of the computing service of the service provider via the computing platform.” The modification would be obvious because one of ordinary skill in the art would be motivated to provide modifications to a software platform of an on-line or mobile payment service provider such as, for example, PayPal®, Inc. of San Jose, Calif (Kneen, paragraph [0004]).
As per Claim 15, the rejection of Claim 10 is incorporated; and Li further discloses:
wherein the payload comprises at least one of a legacy code integration of the computing service with the computing platform, a software design document (SSD) for the software platform, or one or more response payloads of API calls from the software platform (paragraph [0029], “Code prompt 126 may be a prompt generated to request new code 106 from LLM 104, corresponding to update request 116. In some embodiments, prompt generator 124 may provide the update request 116 and/or the name of the application 108 as input for the code prompt 126, and request new code 106 as output from the LLM 104. The new code 106 may include any revisions to be added to source code 112. In some embodiments, the new code 106 may include deleting or modifying existing source code 112.”).
As per Claim 16, the rejection of Claim 10 is incorporated; and the combination of Li and Kneen discloses “the service provider for the computing service” and Li further discloses:
wherein the new code implements the computing service externally on the computing platform and causes calls to be executed to […] the computing service (paragraph [0054], “In 360, the new code, corresponding to the update, is integrated into the application.”; paragraph [0055], “In some embodiments, once the live or cloud version of the application 108 has been updated, CGS 102 may send a message to user 110 or the various tenants 146 that the application 108 has been updated with the new functionality in accordance with update request 116. The tenants 146 may then access the application 108 with the updated functionality based on new code 106.”; paragraph [0066], “Computer system 400 may be a client or server, accessing or hosting any applications and/or data through any delivery paradigm, including but not limited to remote or distributed cloud computing solutions; local or on-premises software (‘on-premise’ cloud-based solutions); ‘as a service’ models (e.g., content as a service (CaaS), digital content as a service (DCaaS), software as a service (SaaS), managed software as a service (MSaaS), platform as a service (PaaS), desktop as a service (DaaS), framework as a service (FaaS), backend as a service (BaaS), mobile backend as a service (MBaaS), infrastructure as a service (IaaS), etc.); and/or a hybrid model including any combination of the foregoing examples or other services or delivery paradigms.”).
Claims 11-14 are rejected under 35 U.S.C. § 103 as being unpatentable over Li in view of Kneen as applied to Claim 10 above, and further in view of US 2025/0005300 (hereinafter “O’Kelly”).
EXAMINER’S REMARKS
In order for a reference to be proper for use in an obviousness rejection under 35 U.S.C. § 103, the reference must be analogous art to the claimed invention. In re Bigio, 381 F.3d 1320, 1325, 72 USPQ2d 1209, 1212 (Fed. Cir. 2004). A reference is analogous art to the claimed invention if: (1) the reference is from the same field of endeavor as the claimed invention (even if it addresses a different problem); or (2) the reference is reasonably pertinent to the problem faced by the inventor (even if it is not in the same field of endeavor as the claimed invention). See MPEP § 2141.01(a)(I).
Note that the claimed invention is generally directed to automated code generation using large language models (LLMs) for software platform integrations with computing services (specification, paragraph [0009]). As for the “reasonably pertinent” test, O’Kelly is generally directed to the generation of novel text based on structured input documents (specification, paragraph [0028]). Thus, O’Kelly is an analogous art to the claimed invention (even if it is not in the same field of endeavor as the claimed invention).
As per Claim 11, the rejection of Claim 10 is incorporated; and the combination of Li and Kneen does not explicitly disclose:
wherein the LLM has a token limit corresponding to a data restriction for the prompting the LLM, and wherein the prompting the LLM is performed based on the token limit.
However, O’Kelly discloses:
wherein the LLM has a token limit corresponding to a data restriction for the prompting the LLM, and wherein the prompting the LLM is performed based on the token limit (paragraph [0562], “[…] the selected subset may be combined with the document structure prompt template to determine a document structure prompt that is sufficiently small so as to be completed by a large language model without exceeding a maximum token size for the large language model.”).
As pointed out hereinabove, O’Kelly is an analogous art to the claimed invention. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of O’Kelly into the combined teachings of Li and Kneen to include “wherein the LLM has a token limit corresponding to a data restriction for the prompting the LLM, and wherein the prompting the LLM is performed based on the token limit.” The modification would be obvious because one of ordinary skill in the art would be motivated to determine a prompt that is sufficiently small so as to be completed by a large language model without exceeding a maximum token size for the large language model (O’Kelly, paragraph [0562]).
As per Claim 12, the rejection of Claim 11 is incorporated; and the combination of Li and Kneen does not explicitly disclose:
wherein the prompting the LLM comprises prompting the LLM in parts based on a plurality of calls executed to the LLM to adhere to the token limit.
However, O’Kelly discloses:
wherein the prompting the LLM comprises prompting the LLM in parts based on a plurality of calls executed to the LLM to adhere to the token limit (paragraph [0044], “As another example, text chunking may reduce token overhead and hence cost expended on large language model prompts. As yet another example, text chunking may reduce calls to a large language model, increasing response speed.”).
As pointed out hereinabove, O’Kelly is an analogous art to the claimed invention. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of O’Kelly into the combined teachings of Li and Kneen to include “wherein the prompting the LLM comprises prompting the LLM in parts based on a plurality of calls executed to the LLM to adhere to the token limit.” The modification would be obvious because one of ordinary skill in the art would be motivated to determine a prompt that is sufficiently small so as to be completed by a large language model without exceeding a maximum token size for the large language model (O’Kelly, paragraph [0562]).
As per Claim 13, the rejection of Claim 12 is incorporated; and the combination of Li and Kneen does not explicitly disclose:
wherein the prompting the LLM in parts uses different portions of the payload for each of the plurality of calls.
However, O’Kelly discloses:
wherein the prompting the LLM in parts uses different portions of the payload for each of the plurality of calls (paragraph [0044], “[…] text chunking may reduce calls to a large language model, increasing response speed.”; paragraph [0048], “[…] regular expressions may be determined by providing some or all of the input text portions determined at 102 to a large language model for analysis. The text portions may be included in one or more prompts that in turn include natural language instructions to the large language model. The instructions may instruct the large language model to determine one or more natural expressions for subdividing the text into portions that correspond with structural elements of the input document.”).
As pointed out hereinabove, O’Kelly is an analogous art to the claimed invention. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of O’Kelly into the combined teachings of Li and Kneen to include “wherein the prompting the LLM in parts uses different portions of the payload for each of the plurality of calls.” The modification would be obvious because one of ordinary skill in the art would be motivated to determine a prompt that is sufficiently small so as to be completed by a large language model without exceeding a maximum token size for the large language model (O’Kelly, paragraph [0562]).
As per Claim 14, the rejection of Claim 12 is incorporated; and Li further discloses:
wherein the prompting in parts is performed based on different code sections for generation by the LLM for the new code (paragraph [0045], “Upon receiving confirmation, CGS 102 may generate a code prompt 126 and receive new code 106 from an LLM 104, trained to generate code for application 108 in accordance with specification 128. As illustrated in section 232, CGS 102 may provide the new code 106 to the user 110 to review/confirm. In some embodiments, the new code 106 may include some portions or copies of the pre-existing source code 112.”).
Claim 17 is rejected under 35 U.S.C. § 103 as being unpatentable over Li in view of Kneen as applied to Claim 10 above, and further in view of US 2023/0229435 (hereinafter “Calahan”).
EXAMINER’S REMARKS
In order for a reference to be proper for use in an obviousness rejection under 35 U.S.C. § 103, the reference must be analogous art to the claimed invention. In re Bigio, 381 F.3d 1320, 1325, 72 USPQ2d 1209, 1212 (Fed. Cir. 2004). A reference is analogous art to the claimed invention if: (1) the reference is from the same field of endeavor as the claimed invention (even if it addresses a different problem); or (2) the reference is reasonably pertinent to the problem faced by the inventor (even if it is not in the same field of endeavor as the claimed invention). See MPEP § 2141.01(a)(I).
Note that the claimed invention is generally directed to automated code generation using large language models (LLMs) for software platform integrations with computing services (specification, paragraph [0009]). As for the “reasonably pertinent” test, Calahan is generally directed to version control for source code development stored in a code repository (specification, paragraph [0001]). Thus, Calahan is an analogous art to the claimed invention (even if it is not in the same field of endeavor as the claimed invention).
As per Claim 17, the rejection of Claim 10 is incorporated; and the combination of Li and Kneen does not explicitly disclose:
wherein outputting the new code integration comprises storing the new code with a code repository platform accessible by a plurality of users, and wherein the new code is testable and reviewable on the code repository platform.
However, Calahan discloses:
wherein outputting the new code integration comprises storing the new code with a code repository platform accessible by a plurality of users (paragraph [0013], “[…] users can collaboratively code, test, and review their changes to the source code using a primary source code management system (e.g., Git, a free and open-source software project).”; paragraph [0017], “The cross support system requests a copy of the listed source code files from the secondary code management system 103 and stores them in an existing or new repository in the primary code management system 101.”), and wherein the new code is testable and reviewable on the code repository platform (paragraph [0013], “[…] users can collaboratively code, test, and review their changes to the source code using a primary source code management system (e.g., Git, a free and open-source software project).”).
As pointed out hereinabove, Calahan is an analogous art to the claimed invention. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Calahan into the combined teachings of Li and Kneen to include “wherein outputting the new code integration comprises storing the new code with a code repository platform accessible by a plurality of users, and wherein the new code is testable and reviewable on the code repository platform.” The modification would be obvious because one of ordinary skill in the art would be motivated to allow users to collaboratively code, test, and review their changes to source code using a primary source code management system (Calahan, paragraph [0013]).
Claim 18 is rejected under 35 U.S.C. § 103 as being unpatentable over Li in view of Kneen as applied to Claim 10 above, and further in view of Hu.
As per Claim 18, the rejection of Claim 10 is incorporated; and the combination of Li and Kneen does not explicitly disclose:
wherein the prompting the LLM is further based on sample code previously used by at least one of the available code integrations.
However, Hu discloses:
wherein the prompting the LLM is further based on sample code previously used by at least one of the available code integrations (paragraph [0025], “[…] data breaker 106 is configured to transmit or otherwise pass sample code 124 and prompt 126 to LLM fine tuner 108, where sample code 124 and prompt 126 may be used in operations to fine-tune the code generation performance of a large language model (LLM) 132 by further training.”).
As pointed out hereinabove, Hu is an analogous art to the claimed invention. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Hu into the combined teachings of Li and Kneen to include “wherein the prompting the LLM is further based on sample code previously used by at least one of the available code integrations.” The modification would be obvious because one of ordinary skill in the art would be motivated to fine-tune code generation performance of a large language model (LLM) by further training using sample code (Hu, paragraph [0025]).
Claim 20 is rejected under 35 U.S.C. § 103 as being unpatentable over Li in view of Kneen and Clement as applied to Claim 19 above, and further in view of O’Kelly.
As per Claim 20, the rejection of Claim 19 is incorporated; and Li discloses “a plurality of computing code,” “different code portions of the new code integration,” and “the computing code data,” but the combination of Li, Kneen, and Clement does not explicitly disclose:
wherein the at least one LLM prompt is associated with a plurality of computing code tokens generated based on a maximum data size for LLM tokens processable by the LLM, and wherein the plurality of computing code tokens correspond to different code portions of the new code integration and corresponding data portions of the computing code data.
However, O’Kelly discloses:
wherein the at least one LLM prompt is associated with a plurality of computing […] tokens generated based on a maximum data size for LLM tokens processable by the LLM (paragraph [0562], “[…] the selected subset may be combined with the document structure prompt template to determine a document structure prompt that is sufficiently small so as to be completed by a large language model without exceeding a maximum token size for the large language model.”), and wherein the plurality of computing […] tokens correspond to different […] portions of the new […] integration and corresponding data portions of the computing […] data (paragraph [0192], “[…] a document may be tokenized into words. Words may then be grouped into phrases and/or sentences based on indicators such as punctuation and semantic content. Sentences may be grouped into sections such as paragraphs or other units. Clauses may then be identified based on the structure.”).
As pointed out hereinabove, O’Kelly is an analogous art to the claimed invention. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of O’Kelly into the combined teachings of Li, Kneen, and Clement to include “wherein the at least one LLM prompt is associated with a plurality of computing code tokens generated based on a maximum data size for LLM tokens processable by the LLM, and wherein the plurality of computing code tokens correspond to different code portions of the new code integration and corresponding data portions of the computing code data.” The modification would be obvious because one of ordinary skill in the art would be motivated to determine a prompt that is sufficiently small so as to be completed by a large language model without exceeding a maximum token size for the large language model (O’Kelly, paragraph [0562]).
Pertinent Prior Art
The prior art made of record and not relied upon is considered pertinent to the Applicant’s disclosure. They are as follows:
US 2025/0045027 (hereinafter “Ngiam”) discloses implementing a tool that generates and executes the code in a controlled environment to satisfy user requests entered as text prompts.
<<>> + <<>> + <<>> • × • <<>> + <<>> + <<>>
US 2025/0111036 (hereinafter “Ngiam”) discloses managing access to external resources while executing code.
<<>> + <<>> + <<>> • × • <<>> + <<>> + <<>>
US 2025/0306918 (hereinafter “Hays”) discloses recursively rectifying source code issues using artificial intelligence.
<<>> + <<>> + <<>> • × • <<>> + <<>> + <<>>
US 12,277,409 (hereinafter “Leeman-Munk”) discloses training a code generation model for low-resource languages based in part on generated/synthetic training data.
Conclusion
Any inquiry concerning this communication or earlier communications from the Examiner should be directed to Qing Chen whose telephone number is 571-270-1071. The Examiner can normally be reached on Monday through Friday from 9:00 AM to 5:00 PM ET.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, the Applicant is encouraged to use the USPTO Automated Interview Request (AIR) at https://www.uspto.gov/ interviewpractice.
If attempts to reach the Examiner by telephone are unsuccessful, the Examiner’s supervisor, Wei Mui, can be reached at 571-272-3708. 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 more 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.
/Qing Chen/
Primary Examiner, Art Unit 2191
Prosecution Insights