, DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment
In response to the office action from 10/7/2025, the applicant has submitted an amendment, filed 1/7/2026, amending claims 1, 2, 4, 7-10, 12, 15-18 and 20, cancelling claims 3, 11 and 19, adding claims 21-23, while arguing to traverse prior art and 101 rejections. Applicant’s arguments have been fully considered but are moot with respect to new grounds of rejections further in view of XUE HAOYUAN et al. (CN 10767777A), Glomann (US 2007/0198461), Rakhmetova et al. (NPL) and for the reasons explained in the response to arguments.
Response to Arguments
Page 8 the first paragraph provides a broad overview of the latest amendments.
Following a broad over view of the latest amendments on page 8 the first paragraph, and the interview of 12/5/2025 in paragraph 2, a copy of the first claim is presented on page 8, and pages 9 and 10 have specifically focused on how the latest amendments have resulted in “improvements”: i.e., page 9 paragraph 3 lines 3-4: “Claim 1 is not directed to an abstract concept, but rather a specific improvement in computer-based diagram generation using a novel multimodal model execution” “unstructured textual input is converted into a structured Unified Modeling Language (UML) diagram …”; page 9 paragraph 5 lines 3-4: “The claimed sequence of steps improves the computer’s ability to convert natural language into consistent, accurate architecture diagrams by introducing a structured intermediate representation”; page 10 the second paragraph: “The instant two-stage multimodal process constitutes a technical improvement to computer functionality in transforming unstructured data into a structured model and then into a graphical representation using a model driven layout engine”; page 11 the first paragraph lines 3-4: “The instant solution improves modeling capabilities, reduced ambiguity, and produces more accurate machine-generated diagrams”.
Unfortunately, none of these arguments address why the quoted steps, e.g. conversion or transformation of unstructured to structured data, could result in “increased flexibility, faster search times, and smaller memory requirements” (Enfish memorandum of 5/19/2016), and/or “improve computer-related technology by allowing computer performance of a function not previously performable by a computer” (MCRO memorandum of 11/2/2016). The use of “UML” amounts to nothing more than using a well known additional element, that the instant application had not invented, and furthermore the amended limitations did not result in any “improvements” (as outlined above) in its functionality.
On page 11 the second paragraph quoting “Ex Parte Desjardins”, it is asserted that it was determined that case became patentable because of “plurality of parameters to optimize performance of the machine learning model”. In trying to draw a parallel to the instant application use of “generative AI”, on page 11 the last paragraph it is asserted: “Claim 1 captures a specific improvement in how a generative AI model operates by defining a two-modality processing framework that enhances the model’s ability to interpret and synthesize software-architecture information”.
Respectfully the only way this analogy would have been valid would have been if the “defining a two-modality processing” here could have been shown to “optimize performance” of the “generative AI model”, which certainly the presented arguments have neither demonstrate and nor render plausible.
Page 12 the section before last discusses the previous 112(b) rejections.
Due to the latest amendments the said rejections are overcome.
The remainder of arguments on pages 12-14 discuss why the prior arts of record and in particular Reddy et al. fail to teach the latest amendments.
Since entirely new references are used to address the latest amendments, please visit the new office action for further details.
Finally, as one last remark, respectfully it appears somehow the applicant or his representative had not noticed there was also a non-transitory 101 rejection for the claims 17-20, as they had not addressed it.
Claim Rejections - 35 USC § 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 1-2, 4-10, 12-18, 20-23 stand rejected:
Claims 1, 9, and 17 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claims recite an interactive “user” “apparatus” system in which the “user” is primarily interested in obtaining “software architecture” information about numerous different softwares. The system though enables a user to make his requests by providing him with “prompts” on a “display” which thus helps the “user” significantly; e.g. see Fig. 4: “provide a description of the software architecture”; e.g., “architecture” of softwares “email” and/or “database” (Spec. ¶ 0001). The agent receiving this request delegates it to a “generate artificial intelligence” (“GenAI”, which could be a “multimodal large language model” (Sp. ¶ 0046) and/or a “transformer neural network” (Sp. ¶ 0036)). The results are either sent as “text-based” “response” and/or as “diagrams” (claims 2-3). Before sending the “response” as “diagrams”, they are converted using a “unified markup language (UML)” to a “UML diagram” “that includes text and graphics of components of the software architecture”, and/or a “diagram” in which “text” and “graphics” are merged together in a structed format.
As an initial matter, these quoted teachings do not provide any details on operations pertaining to the “GenAI”, e.g., on how the “GenAI” obtains the “software architecture” and/or how it is trained about it and also anything about the “text-based response” that is sent to the “user”. As regards to conversion of data associated with the “software architecture” to a “UML” “Diagram”, the “unified markup language (UML)” is a very well known additional element, that was not invented in the instant application and the amended limitations do not indicate they cause any “increased flexibility, faster search times, and smaller memory requirements” for either the “processor” (claims 1 and 17), and/or the operation of the “GenAI” (claims 1, 9 and 17).
Therefore, under the broadest reasonable interpretation, the claims cover performance of their limitations in the mind but for the recitation of generic computer component of “processor” and the “GenAI” and/or “UML” softwares. For example, but for the recitation of “processor” (claims 1, 17) and “GenAI” and “UML” (claims 1, 9 and 17), in the simplest scenario, I (a user) could ask another person if he possesses a book and/or manual about a certain software in response to the person providing a solicitation board about certain software information he has in his disposal (e.g., something like going to a computer store (e.g. “Comp USA”) and interacting with a store employee). The person can in turn provide me with a copy of a book and/or manuals and/or even cd about the said software which has pictures of the software architecture, and/or provide specific graphs and their associated text into slides highlighting specifica features. And/or even use the internet to make such a request, by responding to some of the solicitations that come online. The person can also learn (gets trained) in time about each software architecture in response to frequent visitation of its associated manuals. This makes the function of the “processor”, “GenAI” and “UML” as additional elements. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components and/or software programs, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claims recite an abstract idea.
The judicial exception is not integrated into a practical application. The claims 1 and 17 only recite one additional element, i.e., the “processor” to be responsible for the “train”, “display”, “receive”, “generate” and “convert” steps. Therefore the “processor” is recited at a high-level of generality to carry out all the claimed steps. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed therefore to an abstract idea. Furthermore “GenAI” according to Spec. ¶ 0046 “may be a multi-modal large language model (LLM)”, and/or a “transformer neural network” (Spec. ¶ 0036), and/or ¶ 0115: “A module may also be at least partially implemented in software for execution by various types of processors”, and/or ¶ 0086 S2: “wherein the UML diagram may include both text and graphics that describe the plurality of different architecture diagrams of the software architecture”. These are all well known software and hardware, and the claims not only are silent on how they are used and/or trained, but also do not provide any details on how they might have been modified to carry out the claimed limitations.
Therefore, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a “processor” to do all the claim steps pertaining to “train”, “display”, “receive”, “generate” amount to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claims are therefore not patent eligible.
Regarding claims 2, 10, 6, 14, 18 the person once determined the requested software architecture manual or book, can turn to a specific page associated with the said architecture and display to the user.
Regarding claims 4, 12, 20 the person once determined the requested software architecture manual or book, can show any page with diagrams as well as any page with textual descriptions in response to a specific prompt solicitation by the person.
Regarding claims 5, 13 appears to provide some information about how “GenAI” may be “executed” on “blueprints of the software architecture and descriptions of the software architecture”. Unfortunately, no specific details of the blueprint and its training is provided to assess how the model may be trained. Therefore it cannot be assessed if the method in the claim results in “increased flexibility, faster search times, and smaller memory requirements” of the “GenAI model” (Enfish memorandum of 5/19/2016)
Regarding claims 7, 15, it is quite reasonable the user asks for more information (provides feedback) in response to the person providing any information.
Regarding claims 8, 16 the user could be provided information pertaining to runtime associated with a software from the person who could point out an associated manual of the software which typically possess that information.
Regarding claim 21, displaying boxes around information intended to be emphasized requires the ability to draw lines including arrows by the person making presentation of the catalog to the user.
Regarding claim 22, in presenting one of the catalog’s pictures can be made to adjust direction of eye of the user (i.e., a view associated with the user) by simple rotation which can be done by the person provided he has no physical disabilities.
Regarding claim 23, conversion from UML to JSON, is using two well known additional elements and since nothing in the claim limitation requires any reverse impact on e.g. the JSON, therefore it cannot be used to assess if it helps with “increased flexibility, faster search times, and smaller memory requirements” for the “JSON” (Enfish memorandum of 5/19/2016)
Claims 17-20 recite an embodiment of the applicants' invention directed towards a computer readable medium storing a program. It is noted, however, the recitation of the medium in the specification is not exclusory with respect to non-statutory medium types as no specific and limiting definition of “computer readable medium” is provided. Thus, under the broadest reasonable interpretation, the full claim scope of "computer readable medium" would include non-statutory mediums such as carrier waves.
As per the recent USPTO notice signed by director David Kappos on 1/26/2010: “The United States Patent and Trademark Office (USPTO) is obliged to give claims their broadest reasonable interpretation consistent with the specification during proceedings before the USPTO. See In re Zletz, 893 F.2d 319(Fed. Cir. 1989) (during patent examination the pending claims must be interpreted as broadly as their terms reasonably allow). The broadest reasonable interpretation of a claim drawn to a computer readable medium (also called machine readable medium and other such variations) typically covers forms of non-transitory tangible media and transitory propagating signals per se in view of the ordinary and customary meaning of computer readable media, particularly when the specification is silent. See MPEP 2111.01. When the broadest reasonable interpretation of a claim covers a signal per se, the claim must be rejected under 35 U.S.C. 101 as covering non-statutory subject matter. See In re Nuijten, 500 F.3d 1346, 1356-57 (Fed. Cir. 2007) (transitory embodiments are not directed to statutory subject matter) and Interim Examination Instructions for Evaluating Subject Matter Eligibility Under 35 U.S.C.j101, Aug. 24,2009; p. 2.”
The scope of “computer-readable storage medium” therefore includes signal-based mediums. A signal does not fall within one of the four statutory categories of invention (i.e., process, machine, manufacture, or composition of matter) because it is an ephemeral, transient signal and thus is non-statutory. Since the scope of “computer readable medium" includes these non-statutory instances, claims 17-20 are directed to non-statutory subject matter.
The examiner suggests replacing the phrase “computer readable medium” to “non-transitory computer readable medium”, which would exclude signal type embodiment and thereby overcome the 35 U.S.C. 101 rejection of the said claim.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 7, and 15 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention. Nowhere in the disclosure one finds any teaching either inherently and/or expressly pertaining to an “AI agent” let alone performing “an action based on the architecture diagram” by the said “AI agent”.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-2, 4-10, 12-18, 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Reddy et al. (US 2025/0045530) in view of Zhang (US Patent 11,385,892), and Das et al. (US 2024/0176808), and further in view of XUE HAOYUAN et al. (CN 107678777).
Regarding claim 1, Reddy et al. do teach an apparatus comprising: a processor (¶ 0117 sentence 1: “The various operations of example methods described herein may be performed, at least partially, by one or more processors that are temporarily configured (e.g., by software) or permanently configured to perform the relevant operations.”, wherein the associated “methods” are carried out by a “client device” (an apparatus (Fig. 10)))
configured to:
train a generative artificial intelligence (GenAI) model based on
display prompts on a user interface (¶ 0037 sentence 1: “a prompt received via the user interface” (a displayed prompt on a user interface); step “1010” in Fig. 10: “RECEIVE PROMPT FROM CLIENT DEVICE”); ¶0030 sentence 2: “generated by the user interface module 240, transmitted to a client device 160 by the communication module 210, and rendered on a display device of the client device 160” (all interface generated material is displayed); ¶ 0031: “Prompts” (plurality of prompts) “may be stored and accessed by the storage module 250”),
receive responses associated with the software 0063 sentence 2: “use an LLM to answer questions about different software products” (receive an “answer” (one or more natural language responses associated with the software) in response to a “question” (a natural language query and/or response) from a “user”); i.e., see ¶ 0074 sentence 2: “For example, after the response is provided to the client device in operation 1070, the user may be asked, “Does this answer your question?””)) ,
and display [response] via the user interface (step “1070”: “PROVIDE THE RESPONSE TO THE CLIENT DEVICE” (¶ 0066 last sentence: “responsive text” (the text based response) “is presented to the user via the chat interface” (is displayed via the user interface)).
Reddy et al. do not specifically disclose:
Train a generative artificial intelligence (GenAI) model based on architecture diagrams of a software architecture,
Receive responses associated with the software architecture in response to the prompts.
Zhang does teach:
Receive responses associated with the software architecture in response to the prompts (Abstract last 7 lines: “API” “enables users” “to request” (a prompt to a user to request in natural language) “software application architecture” (information about a software architecture); Col. 12 lines 30+: “query the software architecture data models to identify” “software architectures” (receive responses in response to e.g., the “request” or “query” (prompt) associated with a software architecture); Col. 13 lines 24+: “once a recommended software architecture is identified” “assessment service 124 causes display of a graphical user interface (GUI) including indication of the recommended software application architecture” “For example” “displays the recommendation” (in natural language)).
It would have therefore been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the functionality of the “API” of Zhang into the “API” of Reddy et al. would enable the combined systems and their associated methods to perform in combination as they do separately and to further enable Reddy et al. to “query the data models to determine whether the amount of memory” “is suitable for one or more [software] architectures” as disclosed in Zhang Col. 12 line 33+.
Reddy et al. in view of Zhang do not specifically disclose:
Train a generative artificial intelligence (GenAI) model based on architecture diagrams of a software architecture.
Das et al. do teach:
Train a generative artificial intelligence (GenAI) model based on architecture diagrams of a software architecture (¶ 0097 sentence 2: “a machine learning model” (an artificial intelligence model) “may be trained” (is trained) “by calculating weights according to a neural network” (based on a software) “architecture” (architecture (e.g. its associated diagrams)).
It would have therefore been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate “weight[ing]” “neural network [software] architecture” of Das et al. into the overall “software architecture” “recommendations” of Zhang in Reddy et al. in view of Zhang would enable the combined systems and their associated methods to perform in combination as they do separately and to further enable Reddy et al. in view of Zhang to “infer or predict information using resources” (regarding software architecture) as disclosed in Das et al. ¶ 0097 last sentence.
Reddy et al. in view of Zhang and Das et al. do not specifically disclose:
Generate a unified markup language (UML) diagram that includes text and graphics of components of the software architecture based on execution of a first modality of the GenAI model on the prompts associated with the software architecture;
Convert the UML diagram into an architecture diagram of the components of the software architecture based on execution of a second modality of the GenAI model.
XUE HAOYUAN et al. do teach:
Generate a unified markup language (UML) diagram that includes text and graphics of components of the software architecture based on execution of a first modality of the GenAI model on the prompts associated with the software architecture (Abstract lines 6+: “converting” (generating) “the text between the front label and the back label in the software document” (using a software architecture) “into the UML graph” (a unified markup language (UML) diagram that includes graphics) “and converting the software document into preview text” (and text in a first modality focused on the UML generation) and these follow “receiving” (a prompt) “the software document” (associated with the software architecture) “edited by the user” (Abstract lines 2-3));
Convert the UML diagram into an architecture diagram of the components of the software architecture based on execution of a second modality of the GenAI model (Abstract lines 8+: “and inserting the UML graph” (and converting the UML diagram in a second modality based on merging the “text” and the “graph” in the software architecture diagram) “into the preview text” “according to the positions of the front label and/or the back label”);
And display the architecture diagram via the user interface (¶ 0042: “The system interface” (a user interface tailored to) “includes a preview window for displaying” (display) “the software documents” (e.g., the software architecture UML diagram) “edited by the user”).
It would have therefore been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the conversion of “software document” “into [a] UML” of XUE HAOYUAN et al. into “software application architecture” of Zhang in Reddy et al. in view of Zhang and Das et al., would enable the combined systems and their associated methods to perform in combination as they do separately and to further enable to “preserv[e]” (i.e. store) “modification[s]” “when UML drawing files within software documentation are modified or replaced” as disclosed in XUE HAOYUAN et al. ¶ 0033 paragraph 4.
Regarding claim 2, Reddy et al. do not specifically disclose the apparatus of claim 1, wherein the processor is configured to generate a text-based response based on execution of the first modality of the GenAI model, and display the diagram with the text-based response via the user interface.
Zhang does teach the apparatus of claim 1, wherein the processor is configured to generate a text-based response , and display the diagram with the text-based response via the user interface (Col. 13 lines 24+: “once a recommended software architecture is identified” “assessment service 124 causes display of a graphical user interface (GUI) including indication of the recommended software application architecture” “For example” “displays the recommendation” (display a text-based response via the “GUI” (graphical user interface) of diagrams because according to Col. 13 lines 33-35: “the GUI generated” “includes a diagram”)).
For obviousness to combine Reddy et al. and Zhang see claim 1.
Reddy et al. in view of Zhang and Das et al. do not specifically disclose generate a text-based response based on execution of the first modality of the GenAI model.
XUE HAOYUAN et al. do teach generate a text-based response based on execution of the first modality of the GenAI model (Abstract lines 6+: “converting” (generating) “the text between the front label and the back label in the software document” (using a software architecture) “into the UML graph” (a unified markup language (UML) diagram that includes graphics) “and converting the software document into preview text” (and text in a first modality focused on the UML generation)).
For obviousness to combine Reddy et al. in view of Zhang and Das et al. and XUE HAOYUAN et al. see claim 1.
Regarding claim 4, Reddy et al. do teach the apparatus of claim 1, wherein the processor is configured to receive a question about the software
Reddy et al. do not specifically disclose answering questions about software architecture.
Zhang do teach answering questions about software architecture (Abstract last 7 lines: “API” “enables users” “to request” (questions) “software application architecture” (about a software architecture); Col. 13 lines 24+: “once a recommended software architecture is identified” “assessment service 124 causes display of a graphical user interface (GUI) including indication of the recommended software application architecture” “For example” “displays the recommendation” (answers are provided)).
For obviousness to combine Reddy et al. and Zhang see claim 1.
Regarding claim 5, Reddy et al. in view of Zhang do not specifically disclose the apparatus of claim 1, wherein the processor is configured to train the GenAI model based on execution of the GenAI model on blueprints of the software architecture and descriptions of the software architecture.
Das et al. do teach the apparatus of claim 1, wherein the processor is configured to train the GenAI model based on execution of the GenAI model on blueprints of the software architecture and descriptions of the software architecture (¶ 0097 sentence 2: “a machine learning model” (the GenAI) “may be trained” (is trained) “by calculating weights according to a neural network” (based on a software) “architecture” (blueprint), wherein the said “weights” calculation require descriptions of the “neural network architecture” (software architecture)).
For obviousness to combine Reddy et al. in view of Zhang and Das et al. see claim 1.
Regarding claim 6, Reddy et al. do not specifically disclose the apparatus of claim 5, wherein the processor is configured to receive a request for a view of the software architecture, generate a diagram of the view of the software architecture, and display the diagram of the view via the user interface.
Zhang do teach the apparatus of claim 5, wherein the processor is configured to receive a request for a view of the software architecture, generate a diagram of the view of the software architecture, and display the diagram of the view via the user interface (Abstract last 7 lines: “API” “enables users” “to request” (request) “software application architecture” (to view a software architecture); i.e., Col. 13 lines 24+: “once a recommended software architecture is identified” “assessment service 124” (a processor) “causes display” (to help viewing) “of a graphical user interface (GUI)” (using a user interface) “including indication of the recommended software application architecture” “For example” “displays” (generates a “diagram” of the software architecture for the view because Col. 13 lines 34-35: “the GUI generated” “includes a diagram”)“the recommendation”).
For obviousness to combine Reddy et al. and Zhang see claim 1.
Regarding claim 7, Reddy et al. do teach the apparatus of claim 1, wherein the processor is further configured to receive feedback about the text-based response and retrain the GenAI model based on the text-based response and the feedback to the text-based response (¶ 0066 last sentence: “responsive text” (the text based response) “is presented to the user via the chat interface” (is displayed via the user interface), and afterwards according to ¶ 0074 sentence 2+: “after the response is provided” “If the user responds” (a user feedback is provided) “in affirmative” “The completed interaction may be added” “for future LLM instances, reinforcing” (retraining) “the training of the LLM” (the generative artificial intelligence)).
Reddy et al. in view of Zhang and Das et al. do not specifically disclose:
A text-based response to correspond to an architecture diagram.
XUE HAOYUAN et al. do teach generate a text-based response to correspond to an “architecture diagram” (Abstract lines 6+: “converting” (generating) “the text” (a text based response) “between the front label and the back label in the software document” (based on a software architecture) “into the UML graph” (diagram) “and converting the software document into preview text”).
For obviousness to combine Reddy et al. in view of Zhang and Das et al. and XUE HAOYUAN et al. see claim 1.
Regarding claim 8, Reddy et al. do not specifically disclose the apparatus of claim 1, wherein the processor is further configured to receive runtime data from the software architecture, and generate the architecture diagram based on execution of the GenAI model the runtime data.
Zhang does teach
the apparatus of claim 1, wherein the processor is further configured to receive runtime data from the software architecture, and generate the architecture diagram based on execution of the GenAI model on the runtime data (Col. 12 lines 29-33 and 41-42 respectively: “the assessment service 124 may query the software architecture data models to identify (or rule out) software architectures that support the use of the identified language” “based on features and constraints defined for each architecture” e.g., Col. 6 lines 28-30: “software” “includes everything needed to run an application process” e.g. “runtime” (the runtime associated with a software architecture for running an ”application” to be provided by the software architecture to the “assessment service 124” (a processor) to help it in assessing its generation which could involve an architecture diagram)).
It would have therefore been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the functionality of Zhang pertaining to the ability to “query” “software” for important “runtime” information into the “API” of Reddy et al. would enable the combined systems and their associated methods to perform in combination as they do separately and to further enable Reddy et al. to include “runtime” information pertaining to specific “applications” for a “software” as an important “assessment” feature of the “software” to a “user” interested in the “software” as disclosed in Zhang Col. 12 lines 29-33 and Col. 6 lines 28-30.
Regarding claim 9, Reddy et al. do teach a method (Title, Abstract; e.g. ¶ 0117 sentence 1: “The various operations of example methods described herein may be performed, at least partially, by one or more processors that are temporarily configured (e.g., by software) or permanently configured to perform the relevant operations.”, wherein the associated “methods” are carried out by a “client device” (an apparatus and its associated method (Fig. 10)))
comprising:
training a generative artificial intelligence (GenAI) model based on¶ 0074 sentence 2+: “after the response is provided” “If the user responds in affirmative” (based on the software description)“The completed interaction may be added” “for future LLM instances, reinforcing the training of the LLM” (a generative artificial intelligence is trained)),
displaying prompts on a user interface (¶ 0037 sentence 1: “a prompt received via the user interface” (a displayed prompt on a user interface); step “1010” in Fig. 10: “RECEIVE PROMPT FROM CLIENT DEVICE”); ¶0030 sentence 2: “generated by the user interface module 240, transmitted to a client device 160 by the communication module 210, and rendered on a display device of the client device 160” (all interface generated material is displayed); ¶ 0031: “Prompts” (plurality of prompts) “may be stored and accessed by the storage module 250”),
receiving responses associated with the software
and displaying response via the user interface (step “1070”: “PROVIDE THE RESPONSE TO THE CLIENT DEVICE” (¶ 0066 last sentence: “responsive text” (the text based response) “is presented to the user via the chat interface” (is displayed via the user interface)).
Reddy et al. do not specifically disclose:
Training a generative artificial intelligence (GenAI) model based on architecture diagrams of a software architecture,
Receiving one or more natural language responses associated with the software architecture in response to the one or more prompts.
Zhang does teach:
Receiving responses associated with the software architecture in response to the prompts (Abstract last 7 lines: “API” “enables users” “to request” (a prompt to a user to request in natural language) “software application architecture” (information about a software architecture); Col. 12 lines 30+: “query the software architecture data models to identify” “software architectures” (receive responses in response to e.g., the “request” or “query” (prompt) associated with a software architecture); Col. 13 lines 24+: “once a recommended software architecture is identified” “assessment service 124 causes display of a graphical user interface (GUI) including indication of the recommended software application architecture” “For example” “displays the recommendation” (in natural language)).
It would have therefore been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the functionality of the “API” of Zhang into the “API” of Reddy et al. would enable the combined systems and their associated methods to perform in combination as they do separately and to further enable Reddy et al. to “query the data models to determine whether the amount of memory” “is suitable for one or more [software] architectures” as disclosed in Zhang Col. 12 line 33+.
Reddy et al. in view of Zhang do not specifically disclose:
Training a generative artificial intelligence (GenAI) model based on architecture diagrams of a software architecture.
Das et al. do teach:
Training a generative artificial intelligence (GenAI) model based on architecture diagrams of a software architecture (¶ 0097 sentence 2: “a machine learning model” (an artificial intelligence model) “may be trained” (is trained) “by calculating weights according to a neural network” (based on a software) “architecture” (architecture (e.g. its associated diagrams)).
It would have therefore been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate “weight[ing]” “neural network [software] architecture” of Das et al. into the overall “software architecture” “recommendations” of Zhang in Reddy et al. in view of Zhang would enable the combined systems and their associated methods to perform in combination as they do separately and to further enable Reddy et al. in view of Zhang to “infer or predict information using resources” (regarding software architecture) as disclosed in Das et al. ¶ 0097 last sentence.
Reddy et al. in view of Zhang and Das et al. do not specifically disclose:
Generate a unified markup language (UML) diagram that includes text and graphics of components of the software architecture based on execution of a first modality of the GenAI model on the prompts associated with the software architecture;
Convert the UML diagram into an architecture diagram of the components of the software architecture based on execution of a second modality of the GenAI model.
XUE HAOYUAN et al. do teach:
Generating a unified markup language (UML) diagram that includes text and graphics of components of the software architecture based on execution of a first modality of the GenAI model on the prompts associated with the software architecture (Abstract lines 6+: “converting” (generating) “the text between the front label and the back label in the software document” (using a software architecture) “into the UML graph” (a unified markup language (UML) diagram that includes graphics) “and converting the software document into preview text” (and text in a first modality focused on the UML generation) and these follow “receiving” (a prompt) “the software document” (associated with the software architecture) “edited by the user” (Abstract lines 2-3));
Converting the UML diagram into an architecture diagram of the components of the software architecture based on execution of a second modality of the GenAI model (Abstract lines 8+: “and inserting the UML graph” (and converting the UML diagram in a second modality based on merging the “text” and the “graph” in the software architecture diagram) “into the preview text” “according to the positions of the front label and/or the back label”);
And display the architecture diagram via the user interface (¶ 0042: “The system interface” (a user interface tailored to) “includes a preview window for displaying” (display) “the software documents” (e.g., the software architecture UML diagram) “edited by the user”).
It would have therefore been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the conversion of “software document” “into [a] UML” of XUE HAOYUAN et al. into “software application architecture” of Zhang in Reddy et al. in view of Zhang and Das et al., would enable the combined systems and their associated methods to perform in combination as they do separately and to further enable to “preserv[e]” (i.e. store) “modification[s]” “when UML drawing files within software documentation are modified or replaced” as disclosed in XUE HAOYUAN et al. ¶ 0033 paragraph 4.
Regarding claim 10, Reddy et al. do not specifically disclose the method of claim 9, wherein the method further comprises generating a text-based response based on the execution of the first modality of the GenAI model, and displaying the text-based response via the user interface.
Zhang does teach the method of claim 9, wherein the method further comprises generating a text-based response , and displaying the text-based response via the user interface (Col. 13 lines 24+: “once a recommended software architecture is identified” “assessment service 124 causes display of a graphical user interface (GUI) including indication of the recommended software application architecture” “For example” “displays the recommendation” (display a text-based response via the “GUI” (graphical user interface) of diagrams because according to Col. 13 lines 33-35: “the GUI generated” “includes a diagram”)).
For obviousness to combine Reddy et al. and Zhang see claim 1.
Reddy et al. in view of Zhang and Das et al. do not specifically disclose generate a text-based response based on execution of the first modality of the GenAI model.
XUE HAOYUAN et al. do teach generate a text-based response based on execution of the first modality of the GenAI model (Abstract lines 6+: “converting” (generating) “the text between the front label and the back label in the software document” (using a software architecture) “into the UML graph” (a unified markup language (UML) diagram that includes graphics) “and converting the software document into preview text” (and text in a first modality focused on the UML generation)).
For obviousness to combine Reddy et al. in view of Zhang and Das et al. and XUE HAOYUAN et al. see claim 9.
Regarding claim 12, Reddy et al. do teach the method of claim 9, wherein the receiving comprises receiving a question about the software
Reddy et al. do not specifically disclose answering questions about software architecture.
Zhang do teach answering questions about software architecture (Abstract last 7 lines: “API” “enables users” “to request” (questions) “software application architecture” (about a software architecture); Col. 13 lines 24+: “once a recommended software architecture is identified” “assessment service 124 causes display of a graphical user interface (GUI) including indication of the recommended software application architecture” “For example” “displays the recommendation” (answers are provided)).
For obviousness to combine Reddy et al. and Zhang see claim 9.
Regarding claim 13, Reddy et al. in view of Zhang do not specifically disclose the method of claim 9, wherein the training comprises training the GenAI model based on execution of the GenAI model on blueprints of the software architecture and descriptions of the software architecture.
Das et al. do teach the method of claim 9, wherein the training comprises training the GenAI model based on execution of the GenAI model on blueprints of the software architecture and descriptions of the software architecture (¶ 0097 sentence 2: “a machine learning model” (the GenAI) “may be trained” (is trained) “by calculating weights according to a neural network” (based on a software) “architecture” (blueprint), wherein the said “weights” calculation require descriptions of the “neural network architecture” (software architecture)).
For obviousness to combine Reddy et al. in view of Zhang and Das et al. see claim 9.
Regarding claim 14, Reddy et al. do not specifically disclose the method of claim 13, wherein the receiving comprises receiving a request for a view of the software architecture, and the generating further comprises generating a diagram of the view of the software architecture, and displaying the diagram of the view via the user interface.
Zhang do teach the method of claim 13, wherein the receiving comprises receiving a request for a view of the software architecture, and the generating further comprises generating a diagram of the view of the software architecture and displaying the diagram of the view via the user interface (Abstract last 7 lines: “API” “enables users” “to request” (request) “software application architecture” (to view a software architecture); i.e., Col. 13 lines 24+: “once a recommended software architecture is identified” “assessment service 124” (a processor) “causes display” (to help viewing) “of a graphical user interface (GUI)” (using a user interface) “including indication of the recommended software application architecture” “For example” “displays” (generates a “diagram” of the software architecture for the view because Col. 13 lines 34-35: “the GUI generated” “includes a diagram”)“the recommendation”).
For obviousness to combine Reddy et al. and Zhang see claim 9.
Regarding claim 15, Reddy et al. do teach the method of claim 9, wherein the method further comprises receiving feedback about the text-based response and retraining the GenAI model based on the text-based response and the feedback to the text-based response (¶ 0066 last sentence: “responsive text” (the text based response) “is presented to the user via the chat interface” (is displayed via the user interface), and afterwards according to ¶ 0074 sentence 2+: “after the response is provided” “If the user responds” (a user feedback is provided) “in affirmative” “The completed interaction may be added” “for future LLM instances, reinforcing” (retraining) “the training of the LLM” (the generative artificial intelligence)).
Reddy et al. in view of Zhang and Das et al. do not specifically disclose:
A text-based response to correspond to an architecture diagram.
XUE HAOYUAN et al. do teach generate a text-based response to correspond to an “architecture diagram” (Abstract lines 6+: “converting” (generating) “the text” (a text based response) “between the front label and the back label in the software document” (based on a software architecture) “into the UML graph” (diagram) “and converting the software document into preview text”).
For obviousness to combine Reddy et al. in view of Zhang and Das et al. and XUE HAOYUAN et al. see claim 9.
Regarding claim 16, Reddy et al. do not specifically disclose the method of claim 9, wherein the generating further comprises receiving a runtime data from the software architecture, and generating the architecture diagram based on execution of the GenAI model the runtime data.
Zhang does teach
the method of claim 9, wherein the generating further comprises receiving a runtime data from the software architecture, and generating the architecture diagram based on execution of the GenAI model the runtime data (Col. 12 lines 29-33 and 41-42 respectively: “the assessment service 124 may query the software architecture data models to identify (or rule out) software architectures that support the use of the identified language” “based on features and constraints defined for each architecture” e.g., Col. 6 lines 28-30: “software” “includes everything needed to run an application process” e.g. “runtime” (the runtime associated with a software architecture for running an ”application” to be provided by the software architecture to the “assessment service 124” (a processor) to help it in assessing its generation which could involve an architecture diagram)).
It would have therefore been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the functionality of Zhang pertaining to the ability to “query” “software” for important “runtime” information into the “API” of Reddy et al. would enable the combined systems and their associated methods to perform in combination as they do separately and to further enable Reddy et al. to include “runtime” information pertaining to specific “applications” for a “software” as an important “assessment” feature of the “software” to a “user” interested in the “software” as disclosed in Zhang Col. 12 lines 29-33 and Col. 6 lines 28-30.
Regarding claims 17-18 and 20, they correspond to the claims 1-2 and 4 respectively but when ported on a “computer-readable medium” and are thus rejected under similar rationale since Reddy et al. ¶ 0087 sentence 1 also teaches: “[0087] Example 9 is a non-transitory computer-readable medium that stores instructions that, when executed by one or more processors, cause the one or more processors to perform operations”.
Claim(s) 21-22 is/are rejected under 35 U.S.C. 103 as being unpatentable over Reddy et al. in view of Zhang, Das et al. and XUE HAOYUAN et al. , and further in view of Glomann (US 2007/0198461).
Regarding claim 21, Reddy et al. in view of Zhang, Das et al. and XUE HAOYUAN et al. do not specifically disclose the apparatus of claim 1, wherein the processor is configured to generate a software architecture diagram that includes a plurality of architectural components of the software architecture fitted together with boxes, lines, and arrows.
Glomann does teach the apparatus of claim 1, wherein the processor is configured to generate a software architecture diagram that includes a plurality of architectural components of the software architecture fitted together with boxes, lines, and arrows (¶ 0031 lines 1+ referring to Fig. 2: “UML” “class diagram of a software architecture” (a software architecture diagram) “that describes the structure of a system” “In this diagram, arrows” (comprising of arrows) “between class boxes” (and boxes) where the “arrow” according to ¶ 0032 S1 are “dotted-lines” (comprise of lines)).
It would have therefore been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the “UML” functions of Glomann into the “UML” of XUE HAOYUAN et al. in Reddy et al. in view of Zhang, Das et al. and XUE HAOYUAN et al. would enable the combined systems and their associated methods to perform in combination as they do separately and to further enable XUE HAOYUAN et al. in XUE HAOYUAN et al. in Reddy et al. in view of Zhang, Das et al. and XUE HAOYUAN et al. to enhance presenting its “UML graph” (software diagram or architecture) with different “resolut[ions]” as disclosed in Glomann ¶ 0009 last sentence.
Regarding claim 22, Reddy et al. in view of Zhang, Das et al. and XUE HAOYUAN et al. do not specifically disclose the apparatus of claim 1, wherein the responses comprise a plurality of different architectural views of the components of the software architecture.
Glomann does teach the apparatus of claim 1, wherein the responses comprise a plurality of different architectural views of the components of the software architecture (¶ 0009 last S: “Further embodiments of an architecture” (software architecture) “implement sub-sampling, which is selecting a lower-resolution subset of relation” (where the “relation” according to ¶ 0046 last S: “new Relation instance” “might” “present another “view”” (comprise of different views)).
For obviousness to combine Reddy et al. in view of Zhang, Das et al. and XUE HAOYUAN et al. and Glomann see claim 21.
Claim(s) 23 is/are rejected under 35 U.S.C. 103 as being unpatentable over Reddy et al. in view of Zhang, Das et al. and XUE HAOYUAN et al., and further in view of Rakhmetova et al. “Technical Report Department of Computer Science University of Verona, 2021”).
Regarding claim 23, Reddy et al. in view of Zhang, Das et al. and XUE HAOYUAN et al. do not specifically disclose the apparatus of claim 1, wherein the converting comprises converting the UML diagram into a multi-domain architecture diagram in at least one of a JavaScript Object Notation (JSON) format and eXtensible Markup Language (XML) format.
Rakhmetova et al. do teach the apparatus of claim 1, wherein the converting comprises converting the UML diagram into a multi-domain architecture diagram in at least one of a JavaScript Object Notation (JSON) format and eXtensible Markup Language (XML) format (Abstract S2: “we build an ad hoc UML-based (class) diagram” (a UML formatted diagram) “to represent the key features of the Log nested structure and generated” (converted to) “an artifact” “a template in JSON” (to a JSON format)).
It would have therefore been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the “UML” to “JSON” conversion feature of Rakhmetova et al. into the “UML” of XUE HAOYUAN et al. in Reddy et al. in view of Zhang, Das et al. and XUE HAOYUAN et al. would enable the combined systems and their associated methods to perform in combination as they do separately and to further enable XUE HAOYUAN et al. in XUE HAOYUAN et al. in Reddy et al. in view of Zhang, Das et al. and XUE HAOYUAN et al. to benefit from the feature of “JSON is simple to implement in languages without build-in JSON functionality” as disclosed in Rakhmetova et al. § 2.2 ¶ 2 lines 1-2.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to FARZAD KAZEMINEZHAD whose telephone number is (571)270-5860. The examiner can normally be reached 10:30 am to 11:30 pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Paras D. Shah can be reached at (571) 270-1650. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/Farzad Kazeminezhad/
Art Unit 2653
April 24th 2026.
Prosecution Insights