CTNF 18/961,104 CTNF 88810 Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. DETAIL ACTION Information Disclosure Statement 06-52 The information disclosure statement (IDS) was submitted on 11/26/2024 and 3/5/2026. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner. Claim Rejections - 35 USC § 101 07-04-01 AIA 07-04 35 U.S.C. 101 reads as follows: Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title. Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claimed invention is directed to non-statutory subject matter because the claim(s) as a whole, considering all claim elements both individually and in combination, do not amount to significantly more than an abstract idea. As summarized in the 2019 Revised Patent Subject Matter Eligibility Guidance , examiners must perform a Two-Part Analysis for Judicial Exceptions. Step 1 In Step 1, it must be determined whether the claimed invention is directed to a process, machine, manufacture or composition of matter. The instant invention encompasses three sets of claims: a system in claims 1-11 (i.e., a manufacture), a method in claims 12 (i.e., a process) and a system in claims 13-20 (i.e., a manufacture). All claims are directed to one of the four statutory categories and meet the requirements of step 1. Step 2A Prong One The claimed invention is directed to an abstract idea without significant more. The instant invention is broadly directed to “generating a response by a large language model based on a request applied by a user”. Claim 1 recites the following (with emphasis added): Claim 1: A multi-agent large language model (LLM) system comprising: multiple non-generative executive LLM agents each trained on a different set of technical information limited to maintenance information of a powered system; and a generative orchestration LLM agent coupled with the executive LLM agents, the orchestration LLM agent configured to receive a maintenance inquiry related to the powered system from personnel, assign one or more of the executive LLM agents to examine the maintenance inquiry based on which of the different sets of the technical information that the executive LLM agents were trained , the one or more of the executive LLM agents configured to examine the set of the technical information used to train the respective one or more of the executive LLM agents for relevant information to be output responsive to the maintenance inquiry and to provide the relevant information to the orchestration LLM agent, the orchestration LLM configured to present the relevant information from the one or more of the executive LLM agents to the personnel for maintenance of the powered system The bold portions of claim 1 encompass the abstract idea, which is also encompassed by the dependent claims 2-11, and substantially also encompassed by claims 12 and 13-20. Claims 1, 12, and 13 recite the steps to generate a content to a user interface by a natural language model including a natural language processing. These limitations, when given their broadest reasonable interpretation, are directed to certain performing of organizing human activity and mental processes, which is abstract idea. Prong Two This judicial exception is not integrated into a practical application because mere instruction to implement on computers (i.e. storage medium or processors in claim 2) or a computer model (language model here in claim 1), or merely using computers as a tool to perform the abstract idea, adding insignificant extra solution activity, and/or generally linking the use of the abstract idea to a technological environment for field of use is not considered integration into a practical application. Claim 1 recites using natural language prompt to generate output data of the trained large language model. Using input data to a trained machine-learning or large language model is a generic feature of natural language process, which does not represent a technological improvement. The using of the computer and natural language process does not add improvement to the functioning of a computer or to any other technology field, which failed to enable the abstract idea to integrate into a practical application. The claims are drafted in a result-oriented fashion, without the requisite specificity needed to provide a nonabstract technological solution. The computing system and large language models are directed to the components of a system amount to merely field of use type limitations and/or extra solution activity to implement the abstract idea as presented. Step 2B Step 2B in the analysis requires us to determine whether the claims do significantly more than simply describe that abstract method. Mayo, 132 S. Ct. at 1297. We must examine the limitations of the claims to determine whether the claims contain an "inventive concept" to "transform" the claimed abstract idea into patent-eligible subject matter. Alice, 134 S. Ct. at 2357 (quoting Mayo, 132 S. Ct. at 1294, 1298). The transformation of an abstract idea into patent-eligible subject matter "requires 'more than simply stat[ing] the [abstract idea] while adding the words 'apply it."' Id. (quoting Mayo , 132 S. Ct. at 1294) (alterations in original). "A claim that recites an abstract idea must include 'additional features' to ensure 'that the [claim] is more than a drafting effort designed to monopolize the [abstract idea].'" Id. (quoting Mayo , 132 S. Ct. at 1297) (alterations in original). Those "additional features" must be more than "well-understood, routine, conventional activity." Mayo , 132 S. Ct. at 1298. The present claims include the additional elements other than the abstract idea which include a processor, storage medium, language model and client device with user interface (in claim 1 and 2). These additional elements are merely conventional computer and computer model. Any potentially technical aspects of the claims are well-known generic computer components performing conventional functions (e.g., a processor performing a mental process). The present claims have been analyzed both individually and in combination and, the instant claims do not provide any improvement of the functioning of the computer or improvement to computer technology or any other technical field. There do not appear to be any meaningful limitations other than those that are well-understood, routine and conventional in the field. Thus, the present claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. Thus, the claims 1-11 are not patent eligible. Claims 12 and method claim 13-20 recite similar limitations of claims 1-11, thus are abstract idea and not patent eligible. Claim Rejections - 35 USC § 112 07-30-02 AIA 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. The following is a quotation of 35 U.S.C. 112 (pre-AIA), second paragraph: The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention. Claim 1-4, 6-10 and 12-20 recite the limitation “the executive LLM agents” or “the non-executive LLM agents”. There is insufficient antecedent basis for this limitation in the claim. Claim 1-2, 6, 10-14 and 20 recite the limitation “the orchestration LLM agents”. There is insufficient antecedent basis for this limitation in the claim Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status. 07-20-aia AIA The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action: A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made. 07-21-aia AIA Claim (s) 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Siebel et al (US 20240370709 A1) in view of WANG et al (CN 118886491 A) . Regarding claim 1, Siebel discloses a multi-agent large language model (LLM) system [e.g. FIG. 1, 5, 7; multiple agents with language model] comprising: multiple non-generative executive LLM agents [e.g. FIG. 8 and 10; non-generative machine learning model] each trained on a different set of technical information [e.g. FIG. 9; [0171]; large language model trained on aerospace or defense data set]; and a generative orchestration LLM agent [FIG. 9 and 13; 904; orchestrator module] coupled with the executive LLM agents, the orchestration LLM agent configured to receive an inquiry related to from personnel [e.g. FIG. 13; receiving a question from a user], assign one or more of the executive LLM agents to examine the inquiry based on which of the different sets of the technical information that the executive LLM agents were trained [e.g. FIG. 9; [0111]; 904 and 906; orchestrator selects appropriate agents for handling queries and other inputs], the one or more of the executive LLM agents configured to examine the set of the technical information used to train the respective one or more of the executive LLM agents for relevant information [e.g. FIG. 13; generating answer to the question using related information] to be output responsive to the maintenance inquiry and to provide the relevant information to the orchestration LLM agent, the orchestration LLM configured to present the relevant information from the one or more of the executive LLM agents to the personnel [e.g. 1312; displaying the answer via user interface]. it is noted that Siebel differs to the present invention in that Siebel fails to explicitly disclose the detail of the technical information. However, WANG teaches the well-known concept of multiple LLM agents trained on a different set of technical information limited to maintenance information of a powered system [e.g. FIG. 1-2; fine tuning the large model by extracting plane system knowledge text data for airplane maintenance; the large language model performing pre-training on a large amount of text data; page 8; the text data may include the airplane engine bleed air system as an example, e.g. "control", " battery ", "location", "function"]; and present the relevant information from the one or more of the executive LLM agents to the personnel for maintenance of the powered system [e.g. generating output file in CVS format by large language model for aircraft maintenance and inspection]. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the large language model system disclosed by Siebel to exploit the well-known applying large language mode for airplane power system maintenance technique taught by WANG as above, in order to provide optimized airplane maintenance flow [See Wang; page 6]. Regarding claim 2, Siebel and WANG further disclose each of the executive LLM agents and the orchestration LLM agent comprises an application specific integrated circuit (ASIC) for an artificial neural network (ANN) [e.g. Siebel: FIG. 9; artificial neural networks] of the respective generative or non-executive LLM agent [e.g. Siebel: FIG. 17; [0248]; ASIC] , each of the ASICs of the respective generative or non-executive LLM agent comprising neurons organized in an array with each of the neurons having a register, a microprocessor, and at least an input, each of the ASICs also including synaptic circuits each having a memory for storing a synaptic weight, the neurons connected with each other via the synaptic circuits [e.g. Siebel: FIG. 17; [0248]; FPGA; neuromorphic chips]. Regarding claim 3, Siebel and WANG further disclose the non-executive LLM agent is configured to select the one or more of the executive LLM agents for assignment to examine the maintenance inquiry using a knowledge graph model [e.g. Siebel: visual models] and based on which of the different sets of the technical information that the executive LLM agents were trained [e.g. Siebel: FIG. 7 and 9; WANG: FIG.1-2]. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the large language model system disclosed by Siebel to exploit the well-known applying large language mode for airplane power system maintenance technique taught by WANG as above, in order to provide optimized airplane maintenance flow [See Wang; page 6]. Regarding claim 4, Siebel and WANG further disclose the one or more of the executive LLM agents that are assigned to examine the maintenance inquiry are configured to use a powered-system-specific-language model to examine one or more of the sets of the technical information [e.g. WANG: FIG. 1-2; fine tuning the large model by extracting plane system knowledge text data for airplane maintenance; the large language model performing pre-training on a large amount of text data; page 8; the text data may include the airplane engine bleed air system as an example, e.g. "control", " battery ", "location", "function"] used to train the one or more of the executive LLM agents to reduce hallucinatory [e.g. Siebel: FIG. 2-3; anti- hallucination] responses to the maintenance inquiry relative to the one or more of the executive LLM agents examining the one or more of the sets of the technical information using a model other than the powered-system-specific-language model [e.g. Siebel: FIG. 7 and 9; WANG FIG. 1-2]. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the large language model system disclosed by Siebel to exploit the well-known applying large language mode for airplane power system maintenance technique taught by WANG as above, in order to provide optimized airplane maintenance flow [See Wang; page 6]. Regarding claim 5, Siebel and WANG further disclose the powered-system-specific-language model includes only the technical information about the powered system [e.g. WANG: FIG. 1-2]. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the large language model system disclosed by Siebel to exploit the well-known applying large language mode for airplane power system maintenance technique taught by WANG as above, in order to provide optimized airplane maintenance flow [See Wang; page 6]. Regarding claim 6, Siebel and WANG further disclose the one or more of the executive LLM agents that are assigned to examine the maintenance inquiry are configured to generate the relevant information that is output to the orchestration LLM agent for responding to the maintenance inquiry [e.g. Siebel: FIG. 7 and 9; WANG FIG. 1-2]. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the large language model system disclosed by Siebel to exploit the well-known applying large language mode for airplane power system maintenance technique taught by WANG as above, in order to provide optimized airplane maintenance flow [See Wang; page 6]. Regarding claim 7, Siebel and WANG further disclose the executive LLM agents are configured to classify the maintenance inquiry based on one or more of a component classifier [e.g. WANG: FIG. 1-2; fine tuning the large model by extracting plane system knowledge text data for airplane maintenance; the large language model performing pre-training on a large amount of text data; page 8; the text data may include the airplane engine bleed air system as an example, e.g. "control", " battery ", "location", "function"], a condition classifier, or an action classifier for outputting the relevant information to the non-executive LLM agent [e.g. Siebel: FIG. 7 and 9; answer; WANG: FIG.1-2; output file]. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the large language model system disclosed by Siebel to exploit the well-known applying large language mode for airplane power system maintenance technique taught by WANG as above, in order to provide optimized airplane maintenance flow [See Wang; page 6]. Regarding claim 8, Siebel and WANG further disclose at least one of the executive LLM agents is trained on maintenance logbook data [e.g. WANG: input file] for one or more of the powered system or another powered system [e.g. Siebel: FIG. 7 and 9; WANG FIG. 1-2]. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the large language model system disclosed by Siebel to exploit the well-known applying large language mode for airplane power system maintenance technique taught by WANG as above, in order to provide optimized airplane maintenance flow [See Wang; page 6]. Regarding claim 9, Siebel and WANG further disclose the executive LLM agents are trained on the technical information limited to aircraft as the powered system [e.g. WANG: FIG. 1-2; maintenance and inspection for airplane]. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the large language model system disclosed by Siebel to exploit the well-known applying large language mode for airplane power system maintenance technique taught by WANG as above, in order to provide optimized airplane maintenance flow [See Wang; page 6]. Regarding claim 10, Siebel and WANG further disclose the executive LLM agents are modular and the orchestration LLM agent is configured to one or more of add one or more additional executive LLM agents to the multi-agent LLM system or replace at least one of the executive LLM agents with another executive LLM agent [e.g. Siebel: FIG. 7-9]. Regarding claim 11, Siebel and WANG further disclose orchestration LLM is configured to present the relevant information in a consistent format for many different inquiries [e.g. Siebel: FIG. 7 and 9; [01666-0167]; a format more consistent with a final answer; WANG FIG. 1-2; e.g. output with CSV format file]. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the large language model system disclosed by Siebel to exploit the well-known applying large language mode for airplane power system maintenance technique taught by WANG as above, in order to provide optimized airplane maintenance flow [See Wang; page 6]. Regarding claim 12, this is a method that includes same limitation as in claim 1 above, the rejection of which are incorporated herein. Regarding claim 13-17 and 20, this is a non-transitory computer-readable storage medium that includes same limitation as in claim 1-3, 6-7 and 20 above, the rejection of which are incorporated herein. Furthermore, Siebel and WANG disclose the one or more of the executive LLM agents configured to utilize aviation-domain-specific-language models (ADLMs) to identify relevant information to be output responsive to the maintenance inquiry [e.g. Siebel: FIG. 9; [0171]; large language model trained on aerospace or defense data set; WANG: FIG. 1-2] Regarding claim 18, Siebel and WANG further disclose the one or more of the executive LLM agents are configured to output the relevant information based on the one or more of the component classifier that identifies an aircraft component that is a subject of or related to the maintenance inquiry, the condition classifier that identifies a condition of the aircraft component [e.g. Siebel: FIG. 7 and 9; WANG: FIG. 1-2; fine tuning the large model by extracting plane system knowledge text data for airplane maintenance; the large language model performing pre-training on a large amount of text data; page 8; the text data may include the airplane engine bleed air system as an example, e.g. "control", " battery ", "location", "function"], or the action classifier that identifies a responsive action to take with respect to the aircraft component [e.g. WANG: output file for maintenance or inspection of the airplane]. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the large language model system disclosed by Siebel to exploit the well-known applying large language mode for airplane power system maintenance technique taught by WANG as above, in order to provide optimized airplane maintenance flow [See Wang; page 6]. Regarding claim 19, this is a non-transitory computer-readable storage medium that includes same limitation as in claim 7 and 8 together above, the rejection of which are incorporated herein . Conclusion 07-96 AIA The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Karri et al (US 20250077559 A1). KHAIRNAR et al (US 20250356357 A1). Any inquiry concerning this communication or earlier communications from the examiner should be directed to ZHUBING REN whose telephone number is (571)272-2788. The examiner can normally be reached Monday-Friday 9am-5pm. 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, Richemond Dorvil can be reached at 571-272-7602. 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. /ZHUBING REN/ Primary Examiner, Art Unit 2658 Application/Control Number: 18/961,104 Page 2 Art Unit: 2658 Application/Control Number: 18/961,104 Page 3 Art Unit: 2658 Application/Control Number: 18/961,104 Page 4 Art Unit: 2658 Application/Control Number: 18/961,104 Page 5 Art Unit: 2658 Application/Control Number: 18/961,104 Page 6 Art Unit: 2658 Application/Control Number: 18/961,104 Page 7 Art Unit: 2658 Application/Control Number: 18/961,104 Page 8 Art Unit: 2658 Application/Control Number: 18/961,104 Page 9 Art Unit: 2658 Application/Control Number: 18/961,104 Page 10 Art Unit: 2658 Application/Control Number: 18/961,104 Page 11 Art Unit: 2658
Prosecution Insights