CTNF 18/953,029 CTNF 99360 DETAILED ACTION This communication is in response to the Application filed on 11/19/2024 . Claims 1-24 are pending and have been examined. Claims 1 and 13 are independent. This Application was published as U.S. Pub No. 2025/0201241. 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. Information Disclosure Statement 06-52 The information disclosure statement (IDS) submitted on 03/10/2025 was filed. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner. Priority Applicant’s claims for benefit of a provisional application 63/611,386 submitted on 12/18/2023 is acknowledged. 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 1-24 are rejected under 35 U.S.C. 101 because the claimed invention is directed to abstract idea without significantly more. Regarding Claims 1 and 13, Claims 1 and 13 recite a method and system, which falls under the statutory category of process and machine , respectively (Step 1: Yes) . Claims recite limitations “(a) receiving a natural language query…”, “(b) receiving a prompt composition…”, “(c) structuring a conciseness prompt by concatenating…”, “(d) processing, using the assistant LLM, the conciseness prompt…”, and “(e) providing, for output from a user device, the concise response…”. Except for the recitation of data processing hardware, an assistant large language model (LLM), and a user device, limitations (c) and (d) are concepts, which can be performed in the human mind through observation, evaluation, or judgement, or by a human using a pen and paper. The claims, under their broadest reasonable interpretation, cover the concept of a customer service agent receiving customer’s call asking for information regarding the product, referring to the response protocol (rule or style format) on how to effectively answer customer’s questions, combining the context of customer’s query with answering protocol, and coming up with the appropriate answer and providing the answer to the customer (see MPEP 2106.04(a)(2) III. Under its broadest reasonable interpretation when read in light of the specification, the actions recited in limitations (c) and (d) encompass mental processes practically performed in the human mind. According, the claim recites an abstract idea (Step 2A, Prong one). The judicial exception is not integrated into a practical application. In particular, limitations recite an additional elements of data processing hardware, an assistant large language model (LLM), and a user device but they are recited at a high level of generality (i.e., models or modules, combination of hardware and software are a generic computing device and generic computer components performing a generic computer functions such as processing and storing data from given input) such that it amounts to no more than mere instructions to apply to the exception using a generic computer component. The claim recites the following additional limitations (a), (b), and (e). The additional limitations are recited at a high level of generality, and amounts to mere data gathering and output, which is a form of insignificant extra-solution activity. Each of the additional limitations is no more than mere instructions to apply the exception using a generic computer component. Accordingly, the additional element(s) do(es) not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea and the claim is therefore directed to the judicial exception. (Step 2A: YES). The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because they do not include subject matter that could not be performed by a human, as discussed above with respect to integration of the abstract idea into a practical application, the additional element of using the generic computing elements to perform the claimed elements amounts 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. As noted previously, the claim as a whole merely describes how to generally linking the use of the aforementioned concept to a particular technological environment or field of use. Thus, even when viewed as a whole, nothing in the claim adds significantly more (i.e., an inventive concept) to the abstract idea. The claim is not patent eligible. (Step 2B: NO). Regarding Dependent Claims 2-12 and 14-24, Claims 2-12 and 14-24 are dependent on supra claims and includes all the limitations of the claims and further limits the elements of Claims 1 and 13 . Therefore, the dependent claim(s) recite(s) the same abstract idea. The claim recites the additional limitations of “receiving audio data…”, “performing speech recognition on the audio data…”, and in Claims 2 and 14, “pre-fixing the prompt composition to the textual representation…” in claims 3 and 15, “…add a suffix to a concise response generated by the LLM…” in claims 5 and 17, “…determining that the initial LLM response generated by the assistant LLM satisfies the threshold parameter…”, “…providing, as feedback to the assistant LLM, a calibration phrase…“ and “…processing, using the assistant LLM, … to shorten and/or summarize the initial LLM response into the concise response” in claims 11 and 23, which are no more than mere instructions to apply the exception using a generic computer component, generally linking the use of the judicial exception to a particular technological environment or field of use, insignificant extra-solution activity, or that are well understood, routine and conventional activities previously known to the industry. No additional elements beyond the use of generic computing elements are claimed, therefore the judicial exception is not integrated into a practical application nor are the claim elements sufficient to amount to significantly more than the judicial exception. Therefore, claims are not patent eligible. Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status. 07-20-aia AIA The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action: A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made. 07-21-aia AIA Claim s 1-24 are rejected under 35 U.S.C. 103 as being unpatentable over ASI et al., (US Pub No. 2024/0346232, hereinafter , ASI) in view of Sengupta et al., (US Pat No.12602548 , hereinafter, Sengupta) further in view of Liu et al., ("Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing." ACM computing surveys 55.9 (2023): 1-35, hereinafter, Liu) . Regarding Claim 1, ASI discloses a computer-implemented method executing on data processing hardware that causes the data processing hardware to perform operations (ASI, par [004], " …dynamically generating a language model prompt using the topic-specific data and the summary; and generating an output text using a language model and the language model prompt... ") comprising: receiving a natural language query from a user that solicits a response from an assistant large language model (LLM) (ASI, Fig.1, par [020], " …architecture 100 is used to generate an email message 134 summarizing the conversation, as captured in audio data 104... "; par [021], " …An automatic speech recognition (ASR) module 110 generates a transcript 112 of audio data 104... "; par [024], " …Language model 124 may be an LLM, and in some examples comprises GPT-3, GPT-4, chatGPT, or an equivalent. "; i.e., chatGPT is an exemplary agentic LLM. ); receiving a prompt composition comprising an instruction parameter that specifies a task for the assistant LLM to respond to user queries concisely (ASI, Fig.4, paras [031-033], " …Dynamic prompt generator 400 has scenario-specific behavior 410, such as logic and heuristics, to generate custom language model prompt 122... "; See also Fig.5A-5B as examples of input, language model prompt 122 for a two-participant conversation ); processing, using the assistant LLM, the conciseness prompt to generate a concise response to the natural language query (Asi, Fig.1,6C-7, par [024], " …Language model 124 produces an output text 130... "; par [045], " …FIG. 6C shows a textual passage 650, which may be a version of output text 130... "; par [051], " …Operation 718 generates output text 130 using language model 124 and language model prompt 122... "); and providing, for output from a user device, the concise response to the natural language query (ASI, Figs.1, 7-8, par [024], " …Language model 124 produces an output text 130, which may be sent automatically as email message 134...Operation 722 transmits output text 130 across computer network 140 as email message 134... "). Asi discloses examples of a text passage 620 (e.g., language model prompt) and a set of language model directives to guide language model 124 (e.g., custom prompt 646) to generate the output text (ASI, Fig. 6B, paras [042-044]), but does not explicitly discloses the limitation, "structuring a conciseness prompt by concatenating the prompt composition to the natural language query." Liu, in the analogous field of endeavor, discloses structuring a conciseness prompt by concatenating the prompt composition to the natural language query (Liu, Fig.1, 3 Prompt Template Engineering, 3.3.2 Continuous Prompts " …C1: Prefix Tuning. Prefix Tuning [71] is a method that prepends a sequence of continuous task-specific vectors to the input, while keeping the LM parameters frozen... "); Therefore, it would have been obvious to one of ordinary skill in the art, before effective filing date of the claimed invention, to have modified a dynamic generation of a language model prompt of Asi with the prompt template engineering (e.g., prefix tuning) of Liu with a reasonable expectation of success to allows the language model to be pre-trained on massive amounts of raw text, and by defining a new prompting function the model is able to perform few-shot or even zero-shot learning, adapting to new scenarios with few or no labeled data (Liu, Abstract) . ASI and Liu in combination discloses the dynamic generation of a language model using the captured audio data and output text using LLM and prefix tuning by prepending a sequence of continuous task-specific vectors to the input, but does not explicitly discloses a "conciseness" prompt regarding the length of the responses. However, Sengupta , in the analogous field of natural language processing, discloses a response generator using framework parameters with a large language model to create beams based on a prompt (Sengupta, Abstract) . Sengupta discloses the conciseness prompt to generate a concise response (Sengupta, Fig.1, col.2, lls.30-59, " ...A future constraint may be included to ensure answers are less than a threshold number of words. For example, to prevent a full list of dangerous substances, the future constraint may limit the response to a word limit of 15... "; col.5, lls.22-39, " …an alignment model response system 100 including a response generator 122...The response generator 122 may receive a prompt 102 at a large language model 104... "). Therefore, it would have been obvious to one of ordinary skill in the art, before effective filing date of the claimed invention, to have modified a dynamic generation of a language model prompt using prefix tuning of Asi in view of Liu with of a response generator using framework parameters Sengupta with a reasonable expectation of success to utilize multiple learning models and framework parameters to create and validate potential responses to aid in outputting answers that comply with a preferred set of objectives (Sengupta, col.1, ll.52 - col.2, ll.49) . Regarding Claim 2, The combination of Asi , Liu , and Sengupta discloses the method of claim 1, wherein: receiving the natural language query comprises: receiving audio data characterizing an utterance of the natural language query spoken by the user and captured by the user device (ASI, Fig.1, par [020], " …architecture 100 is used to generate an email message 134 summarizing the conversation, as captured in audio data 104... "; par [024], " …Language model 124 may be an LLM, and in some examples comprises GPT-3, GPT-4, chatGPT, or an equivalent. "; i.e., chatGPT is an exemplary agentic LLM. ); and performing speech recognition on the audio data to generate a textual representation of the natural language query spoken by the user (ASI, Fig.1, par [021], " …An automatic speech recognition (ASR) module 110 generates a transcript 112 of audio data 104... ") and structuring the conciseness prompt comprises concatenating the prompt composition to the textual representation of the natural language query (Liu, Fig.1, 3 Prompt Template Engineering, 3.3.2 Continuous Prompts " …C1: Prefix Tuning. Prefix Tuning [71] is a method that prepends a sequence of continuous task-specific vectors to the input, while keeping the LM parameters frozen... "). Regarding Claim 3, The combination of Asi , Liu , and Sengupta discloses the method of claim 2, wherein concatenating the prompt composition to the textual representation of the natural language query comprises pre-fixing the prompt composition to the textual representation of the natural language query (Liu, Fig.1, 3 Prompt Template Engineering, 3.3.2 Continuous Prompts " …C1: Prefix Tuning. Prefix Tuning [71] is a method that prepends a sequence of continuous task-specific vectors to the input, while keeping the LM parameters frozen... "). Regarding Claim 4, The combination of Asi , Liu , and Sengupta discloses the method of claim 1, wherein the instruction parameter that specifies the task for the assistant LLM to respond to user queries concisely further specifies a number of sentences for the assistant LLM to generate when responding to the user queries concisely (Sengupta, col.2, lls.6-34, " …Future constraints further aid the AI chatbot in generating correct or correctly formatted answers and may not cover all constraints for which the AI chatbot is trained…A future constraint may be included to ensure answers are less than a threshold number of words. For example, to prevent a full list of dangerous substances, the future constraint may limit the response to a word limit of 15... "). Regarding Claim 5, The combination of Asi , Liu , and Sengupta discloses the method of claim 1, wherein the instruction parameter specifies another task for the assistant LLM to add a suffix to a concise response generated by the LLM that asks the user a follow-up question related to the concise response (Sengupta, Fig.4, col.14, lls.18-42, " …At block 412, the alignment model can be used to evaluate the first beam and the second beam and the tokens within...prior to populating the first beam and the second beam with tokens, the response generator 122 may review or request review of the prompt. For example, the response generator 122 could ask follow-up questions to the customer providing the prompt... "). Regarding Claim 6, The combination of Asi , Liu , and Sengupta discloses the method of claim 1, wherein the prompt composition further comprises a constraint parameter specifying one or more constraints for concise responses generated by the assistant LLM, the one or more constraints indicating at least one of a maximum number of words or a number of sentences the concise responses should include (Sengupta, col.4, lls.5-11, " …the reward model may include multiple criteria. A first criterion may be the alignment model and a second criterion may be a constraint checker that includes one or more constraints for the potential responses…The constraints may include keyword constraints, maximum length , minimum length, desired formats, an inclusion requirement, and the like... "). Regarding Claim 7, The combination of Asi , Liu , and Sengupta discloses the method of claim 1, wherein the prompt composition further comprises one or more few-shot learning examples each depicting an exemplary query-concise response pair, each query-concise response pair providing in-context learning for enabling the assistant LLM to generalize for the task of responding to user queries concisely (Liu, Fig.2, 5 Multiple-Prompt Learning, 5.2 Prompt Augmentation" …Prompt augmentation, also sometimes called demonstration learning [32], provides a few additional answered prompts that can be used to demonstrate how the LM should provide the answer to the actual prompt instantiated with the input x...Another example of performing addition of two numbers can be found in Figure 2(b)...These few-shot demonstrations take advantage of the ability of strong language models to learn repetitive patterns [9]... "). Regarding Claim 8, The combination of Asi , Liu , and Sengupta discloses the method of claim 7, wherein at least one of the one or more few-shot learning examples comprises an exemplary initial response and a chain-of-thought reasoning for why or not the exemplary initial response is concise (Liu, Fig.2, 5 Multiple-Prompt Learning, see Figure 2 for examples of different multi-prompt learning strategies ). Regarding Claim 9, The combination of Asi , Liu , and Sengupta discloses the method of claim 1, wherein the prompt composition further comprises a format parameter that specifies how the assistant LLM should format concise responses (Sengupta, col.2, lls.1-9, " …Future constraints further aid the AI chatbot in generating correct or correctly formatted answers and may not cover all constraints for which the AI chatbot is trained. "). Regarding Claim 10, The combination of Asi , Liu , and Sengupta discloses the method of claim 1, wherein the operations further comprises enabling a threshold parameter for triggering calibration when an initial response generated by the assistant LLM is too long (Sengupta, col.3, lls.2-31, "…The learning and feedback enables the alignment model to give a numerical value to a potential answer that equates to how well the potential answer conforms with the constitutional principle...If the answer is does not meet a minimum threshold of aggregated feature score of harmlessness, the answer can be eliminated as an option for response...the large language model could then be prompted to create another potential response. The second prompt may indicate additional constraints that prevent an identical response from being created... "; Fig.4B, col.15, ll.6 - col.16, ll.3, " … a flow diagram depicting a score evaluation sub-routine 400B of the routine in FIG. 4A for selecting a beam created by the response generator 122...If the second preference score does not meet the minimum threshold value at block 432, neither beam may be selected, and the large language model may instead be prompted to generate entirely new beams with different subsets of additional tokens… "). Regarding Claim 11, The combination of Asi , Liu , and Sengupta discloses the method of claim 10, wherein processing the conciseness prompt to generate the concise response to the natural language query comprises: processing, using the assistant LLM, the conciseness prompt to generate an initial LLM response to the natural language query (Sengupta, Figs. 4A-B, col.12, ll.36 - col.16, ll.3, " …At block 410, a first beam and a second beam can be generated based on the beam size of two being established by the framework parameters 110… "); determining that the initial LLM response generated by the assistant LLM satisfies the threshold parameter (Sengupta, col.14, lls.18-67, " …At block 416, the alignment model response system 100 can perform a score evaluation sub-routine 400B as described below in FIG. 4B... "); in response to determining the initial LLM response generated by the assistant LLM satisfies the threshold parameter, providing, as feedback to the assistant LLM, a calibration phrase that indicates the initial LLM response is too long (Sengupta, col.15, lls.6-38, " …at block 432, neither beam may be selected, and the large language model may instead be prompted to generate entirely new beams with different subsets of additional tokens... "); and based on the calibration phrase provided as feedback to the assistant LLM, processing, using the assistant LLM, the conciseness prompt and the initial LLM response to cause the assistant LLM to shorten and/or summarize the initial LLM response into the concise response (Sengupta, Figs. 4A-B, col.12, ll.36 - col.16, ll.3, " …at 432, prompt the large language model to repopulate beams and return to step 410 ", " …After performing the score evaluation sub-routine 400B and selecting a beam, a response is created based on the selected beam at block 418…. "). Regarding Claim 12, The combination of Asi , Liu , and Sengupta discloses the method of claim 11, wherein the initial LLM response is hidden from the user and not saved as part of a conversation history between the user and the assistant LLM (Sengupta, Fig.4B, col.15, ll.6 - col.16, ll.3, " …if the answer does not meet a minimum threshold of aggregated feature score of harmlessness, the answer can be eliminated as an option for response… "). Claim 13 is a system claim with limitations similar to the limitations of Claim 1 and is rejected under similar rationale. Additionally, Asi discloses a system comprising: data processing hardware (Fig.9, processor(s) 914 , par [091], " …processor(s) 914 are programmed to execute computer-executable instructions for implementing aspects of the disclosure... "); and memory hardware in communication with the data processing hardware , the memory hardware storing instructions that when executed on the data processing hardware cause the data processing hardware to perform operations (Fig.9, memory 912 , par [089], " …Memory 912 is thus able to store and access data 912a and instructions 912b that are executable by processor 914 and configured to carry out the various operations disclosed herein…. ") comprising … Rationale for combination is similar to that provided for Claim 1. Claim 14 is a system claim with limitations similar to the limitations of Claim 2 and is rejected under similar rationale. Claim 15 is a system claim with limitations similar to the limitations of Claim 3 and is rejected under similar rationale. Claim 16 is a system claim with limitations similar to the limitations of Claim 4 and is rejected under similar rationale. Claim 17 is a system claim with limitations similar to the limitations of Claim 5 and is rejected under similar rationale. Claim 18 is a system claim with limitations similar to the limitations of Claim 6 and is rejected under similar rationale. Claim 19 is a system claim with limitations similar to the limitations of Claim 7 and is rejected under similar rationale. Claim 20 is a system claim with limitations similar to the limitations of Claim 8 and is rejected under similar rationale. Claim 21 is a system claim with limitations similar to the limitations of Claim 9 and is rejected under similar rationale. Claim 22 is a system claim with limitations similar to the limitations of Claim 10 and is rejected under similar rationale. Claim 23 is a system claim with limitations similar to the limitations of Claim 11 and is rejected under similar rationale. Claim 24 is a system claim with limitations similar to the limitations of Claim 12 and is rejected under similar rationale . Conclusion 07-96 AIA The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Kim et al., (US Pub No. 2026/0148112) discloses a method for providing an interactive communication agent service based on a generative artificial intelligence (AI) model. In order to construct such a chatbot ( or an interactive artificial intelligence system), a technology of "Prompt Engineering" that performs a natural language processing task by utilizing a large (or large-scale, ultra-large) language model (LLM) . Any inquiry concerning this communication or earlier communications from the examiner should be directed to JANGWOEN LEE whose telephone number is (703)756-5597. The examiner can normally be reached Monday-Friday 8:00 am - 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, 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, BHAVESH MEHTA can be reached at (571)272-7453. 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. /JANGWOEN LEE/Examiner, Art Unit 2656 /BHAVESH M MEHTA/Supervisory Patent Examiner, Art Unit 2656 Application/Control Number: 18/953,029 Page 2 Art Unit: 2656 Application/Control Number: 18/953,029 Page 4 Art Unit: 2656 Application/Control Number: 18/953,029 Page 5 Art Unit: 2656 Application/Control Number: 18/953,029 Page 6 Art Unit: 2656 Application/Control Number: 18/953,029 Page 7 Art Unit: 2656 Application/Control Number: 18/953,029 Page 8 Art Unit: 2656 Application/Control Number: 18/953,029 Page 9 Art Unit: 2656 Application/Control Number: 18/953,029 Page 10 Art Unit: 2656 Application/Control Number: 18/953,029 Page 11 Art Unit: 2656 Application/Control Number: 18/953,029 Page 12 Art Unit: 2656 Application/Control Number: 18/953,029 Page 13 Art Unit: 2656 Application/Control Number: 18/953,029 Page 14 Art Unit: 2656 Application/Control Number: 18/953,029 Page 15 Art Unit: 2656 Application/Control Number: 18/953,029 Page 16 Art Unit: 2656 Application/Control Number: 18/953,029 Page 17 Art Unit: 2656 Application/Control Number: 18/953,029 Page 18 Art Unit: 2656
Prosecution Insights