Prosecution Insights
Last updated: November 04, 2026
Application No. 19/080,409

DYNAMIC RESOURCE ALLOCATION OF LARGE LANGUAGE MODEL DEPLOYMENTS FOR CONVERSATIONAL INTERFACE

Non-Final OA §103
Filed
Mar 14, 2025
Priority
May 23, 2024 — continuation of 12/254,279
Examiner
COLUCCI, MICHAEL C
Art Unit
2655
Tech Center
2600 — Communications
Assignee
Honesty Innovations Holdings LLC
OA Round
1 (Non-Final)
76%
Grant Probability
Favorable
1-2
OA Rounds
1y 6m
Est. Remaining
91%
With Interview

Examiner Intelligence

Grants 76% — above average
76%
Career Allowance Rate
775 granted / 1020 resolved
+14.0% vs TC avg
Strong +15% interview lift
Without
With
+15.2%
Interview Lift
resolved cases with interview
Typical timeline
3y 1m
Avg Prosecution
25 currently pending
Career history
1068
Total Applications
across all art units

Statute-Specific Performance

§101
13.9%
-26.1% vs TC avg
§103
61.3%
+21.3% vs TC avg
§102
8.7%
-31.3% vs TC avg
§112
4.8%
-35.2% vs TC avg
Black line = Tech Center average estimate • Based on career data from 1020 resolved cases

Office Action

§103
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 . DETAILED ACTION Double Patenting The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory obviousness-type double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); and In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969). A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on a nonstatutory double patenting ground provided the conflicting application or patent either is shown to be commonly owned with this application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. Effective January 1, 1994, a registered attorney or agent of record may sign a terminal disclaimer. A terminal disclaimer signed by the assignee must fully comply with 37 CFR 3.73(b). Claim 1 with dependent claims thereof, are rejected on the ground of nonstatutory obviousness-type double patenting as being unpatentable over claim 1 and any dependent claims thereof of U.S. Patent No. 12254279. Although the conflicting claims are not identical, they are not patentably distinct from each other because said claims of the instant application includes all of the features of said claims of U.S. Patent No. 12254279. It would have been obvious to one of ordinary skill in the art to omit the step of using a buffer window and context window amounting to a broader representation thereof, In re Karlson 136 USPQ 184 (1963): "Omission of an element and its function is an obvious expedient if the remaining elements perform the same functions as before". Present invention U.S. Patent No. 12254279 1. A dynamic conversation interface system, comprising:computing hardware, including at least one processor, data storage, and input/output facilities;wherein the computing hardware stores instructions that, when executed by the at least one processor, cause the at least one processor to implement:a plurality of instances of a large language model (LLM) engine, wherein each LLM engine instance is configured according to a respective set of system directives;an agent manager engine operative to instantiate and configure the instances of the LLM engine such that a first LLM engine instance is configured according to a first set of system directives, and a second LLM engine instance is configured according to a second set of system directives that is different from the first set,wherein the first LLM engine instance has a different functional specialization from the second LLM engine instance,wherein the first LLM engine instance and the second LLM engine instance engage in a same conversation session with a user, using the same language dialect, to perform different specializations within that conversation session; andwherein the first set of system directives include directives that determine occurrence of a defined condition for instantiating the second LLM engine instance, andwherein the agent manager engine is further operative to instantiate the second LLM engine instance in response to the occurrence of the defined condition. 2. The system of claim 1, wherein the first instance of the LLM engine and the second instance of the LLM engine are respectively associated with different client entities of the dynamic conversation interface system. 3. The system of claim 2, wherein the first instance of the LLM engine and the second instance of the LLM engine are informationally isolated from one another such that information provided by the user to the first LLM engine instance is not accessible by the second instance of the LLM engine. 4. The system of claim 1, wherein each LLM engine instance comprises:a buffer memory that is operative to temporarily store recent history of a current conversation in which the LLM engine instance is engaged; anda context window that stores a selected subset of information from the buffer memory which represents context of a defined recent portion of the current conversation. 5. The system of claim 4, wherein each LLM engine instance is configured, via corresponding system directives, to perform optimization of the context window, wherein the optimization includes at least one operation type from among: removal of certain content, compression of messages, directives, or instructions, condensing of stored information, hierarchical organization of stored content. 6. The system of claim 4, wherein each LLM engine instance is configured, via corresponding system directives, to perform optimization of the context window, wherein the optimization includes application of a memory management algorithm that is based on the Ebbinghaus Forgetting Curve. 7. The system of claim 4, wherein each LLM engine instance is configured, via corresponding system directives, to perform optimization of the context window, wherein the optimization includes application of a position-interpolation (PI) algorithm that is operative to extend a size of the context window. 8. The system of claim 4, wherein each LLM engine instance comprises multiple parallel context windows corresponding to respective threads of the conversation. 9. The system of claim 4, wherein each LLM engine instance is operative to dynamically adjust the size of the context window. 10. The system of claim 4, further comprising:a context window optimization engine operative to direct each LLM instance to preferentially focus on certain aspects of the conversation. 11. The system of claim 4, wherein the agent manager engine is further operative to pass at least a portion of the context window information of the first LLM instance to the second LLM instance in response to instantiation of the second LLM instance. 12. The system of claim 11, wherein the agent manager engine is further operative to process information of the context window of the first LLM instance to clear or anonymize personal information pertaining to the user before the context window information is passed to the second LLM instance. 13. The system of claim 12, wherein the agent manager engine is further operative to process information of the context window of the first LLM instance to such that non-personal information of the context window of the first LLM instance is kept in the context window information to be passed to the second LLM instance, wherein the non-personal information includes expressed objectives, expressed concerns, information indicative of a tone of the conversation, an assessed emotional state of the user, a type of language dialect or terminology employed by the user, or any combination thereof. 14. The system of claim 1, wherein the first set of system directives define attributes of an agent of a first customer service organization. 15. The system of claim 14, wherein the first customer service organization is a governmental agency. 16. The system of claim 14, wherein the first customer service organization is an agency that provides social-services benefits information to its customers, and wherein the first set of system directives and the second set of system directives define different sets of information pertaining to the social-service benefits information. 17. The system of claim 14, wherein the second set of system directives define attributes of an agent of a second customer service organization which is distinct from the first customer service organization. 18. The system of claim 17, wherein the second customer service organization is a non- governmental customer service organization. 19. The system of claim 14, wherein the first set of system directives defines criteria for determining whether the user is qualified for a product of the first customer service organization. 20. The system of claim 19, wherein at least one of the first set of system directives defines a set of operations to be executed by the system in response to a determination that the user is not qualified for the product, wherein the set of operations includes causing the system to communicatively connect the user with a different customer service organization during the same conversation session, wherein the different customer service organization provides a different product. 1. (Currently Amended) A dynamic conversation interface system, comprising: computing hardware, including at least one processor, data storage, and input/output facilities; wherein the computing hardware stores instructions that, when executed by the at least one processor, cause the at least one processor to implement: a plurality of instances of a large language model (LLM) engine, wherein each LLM engine instance is configured according to a respective set of system directives; an agent manager engine operative to instantiate and configure the instances of the LLM engine such that a first LLM engine instance is configured according to a first set of system directives, and a second LLM engine instance is configured according to a second set of system directives that is different from the first set, wherein the first LLM engine instance has a different functional specialization from the second LLM engine instance, wherein the first LLM engine instance and the second LLM engine instance engage in a same conversation session with a user to perform different specializations within that conversation session; and wherein the first set of system directives include directives that determine occurrence of a defined condition for instantiating the second LLM engine instance, and wherein the agent manager engine is further operative to instantiate the second LLM engine instance in response to the occurrence of the defined condition; and wherein each LLM engine instance comprises: a buffer memory that is operative to temporarily store recent history of a current conversation in which the LLM engine instance is engaged; and a context window that stores a selected subset of information from the buffer memory which represents context of a defined recent portion of the current conversation;. 2. (Original) The system of claim 1, wherein the first instance of the LLM engine and the second instance of the LLM engine are respectively associated with different client entities of the dynamic conversation interface system. 3. (Original) The system of claim 2, wherein the first instance of the LLM engine and the second instance of the LLM engine are informationally isolated from one another such that information provided by the user to the first LLM engine instance is not accessible by the second instance of the LLM engine. 4. (Cancelled). 5. (Currently Amended) The system of claim [[4]]1, wherein each LLM engine instance is configured, via corresponding system directives, to perform optimization of the context window, wherein the optimization includes at least one operation type from among: removal of certain content, compression of messages, directives, or instructions, condensing of stored information, hierarchical organization of stored content. 6. (Currently Amended) The system of claim [[4]]1, wherein each LLM engine instance is configured, via corresponding system directives, to perform optimization of the context window, wherein the optimization includes application of a memory management algorithm that is based on the Ebbinghaus Forgetting Curve. 7. (Currently Amended) The system of claim [[4]]1, wherein each LLM engine instance is configured, via corresponding system directives, to perform optimization of the context window, wherein the optimization includes application of a position-interpolation (PI) algorithm that is operative to extend a size of the context window. 8. (Currently Amended) The system of claim [[4]]1, wherein each LLM engine instance comprises multiple parallel context windows corresponding to respective threads of the conversation. 9. (Currently Amended) The system of claim [[4]]1, wherein each LLM engine instance is operative to dynamically adjust the size of the context window. 10. (Currently Amended) The system of claim [[4]]1, further comprising: a context window optimization engine operative to direct each LLM instance to preferentially focus on certain aspects of the conversation. 11. (Currently Amended) The system of claim [[4]]1, wherein the agent manager engine is further operative to pass at least a portion of the context window information of the first LLM instance to the second LLM instance in response to instantiation of the second LLM instance. 12. (Original) The system of claim 11, wherein the agent manager engine is further operative to process information of the context window of the first LLM instance to clear or anonymize personal information pertaining to the user before the context window information is passed to the second LLM instance. 13. (Original) The system of claim 12, wherein the agent manager engine is further operative to process information of the context window of the first LLM instance to such that non-personal information of the context window of the first LLM instance is kept in the context window information to be passed to the second LLM instance, wherein the non-personal information includes expressed objectives, expressed concerns, information indicative of a tone of the conversation, an assessed emotional state of the user, a type of language dialect or terminology employed by the user, or any combination thereof. 14. (Original) The system of claim 1, wherein the first set of system directives define attributes of an agent of a first customer service organization. 15. (Original) The system of claim 14, wherein the first customer service organization is a governmental agency. 16. (Original) The system of claim 14, wherein the first customer service organization is an agency that provides social-services benefits information to its customers, and wherein the first set of system directives and the second set of system directives define different sets of information pertaining to the social-service benefits information. 17. (Original) The system of claim 14, wherein the second set of system directives define attributes of an agent of a second customer service organization which is distinct from the first customer service organization. 18. (Original) The system of claim 17, wherein the second customer service organization is a non-governmental customer service organization. 19. (Original) The system of claim 14, wherein the first set of system directives defines criteria for determining whether the user is qualified for a product of the first customer service organization. 20. (Original) The system of claim 19, wherein at least one of the first set of system directives defines a set of operations to be executed by the system in response to a determination that the user is not qualified for the product, wherein the set of operations includes causing the system to communicatively connect the user with a different customer service organization during the same conversation session, wherein the different customer service organization provides a different product. Note: The claims are not directed towards patent ineligible subject matter under 35 U.S.C. 101 Step 1: IS THE CLAIM DIRECTED TO A PROCESS, MACHINE, MANUFACTURE OR COMPOSITION OF MATTER? Yes Step 2A.1: IS THE CLAIM DIRECTED TO A LAW OF NATURE, A NATURAL PHENOMENON (PRODUCT OF NATURE) OR AN ABSTRACT IDEA? No Step 2A.2: DOES THE CLAIM RECITE ADDITIONAL ELEMENTS THAT INTEGRATE THE JUDICIAL EXCEPTION INTO A PRACTICAL APPLICATION? Yes, if the claims are alternatively construed to be abstract in step 2A1. The claims seek to improve multiple LLM instances within a dynamically-variable system architecture supported by the specification, and reflected by the claims. In other words, the claims enable the invention to improve the system's performance over a single LLM instance that is trained for the entire conversation flow, ensuring that the conversation stays focused and relevant, and portions of the process optimized to improve its efficiency and effectiveness. Supported by the following: In Finjan Inc. v. Blue Coat Systems, Inc., 879 F.3d 1299, 125 USPQ2d 1282 (Fed. Cir. 2018), the claimed invention was a method of virus scanning that scans an application program, generates a security profile identifying any potentially suspicious code in the program, and links the security profile to the application program. 879 F.3d at 1303-04, 125 USPQ2d at 1285-86. The Federal Circuit noted that the recited virus screening was an abstract idea, and that merely performing virus screening on a computer does not render the claim eligible. 879 F.3d at 1304, 125 USPQ2d at 1286. The court then continued with its analysis under part one of the Alice/Mayo test by reviewing the patent’s specification, which described the claimed security profile as identifying both hostile and potentially hostile operations. The court noted that the security profile thus enables the invention to protect the user against both previously unknown viruses and “obfuscated code,” as compared to traditional virus scanning, which only recognized the presence of previously-identified viruses. The security profile also enables more flexible virus filtering and greater user customization. 879 F.3d at 1304, 125 USPQ2d at 1286. The court identified these benefits as improving computer functionality, and verified that the claims recite additional elements (e.g., specific steps of using the security profile in a particular way) that reflect this improvement. Accordingly, the court held the claims eligible as not being directed to the recited abstract idea. 879 F.3d at 1304-05, 125 USPQ2d at 1286-87. This analysis is equivalent to the Office’s analysis of determining that the additional elements integrate the judicial exception into a practical application at Step 2A Prong Two, and thus that the claims were not directed to the judicial exception (Step 2A: NO). Examples of claims that improve technology and are not directed to a judicial exception include: Enfish, LLC v. Microsoft Corp., 822 F.3d 1327, 1339, 118 USPQ2d 1684, 1691-92 (Fed. Cir. 2016) (claims to a self-referential table for a computer database were directed to an improvement in computer capabilities and not directed to an abstract idea); McRO, Inc. v. Bandai Namco Games Am. Inc., 837 F.3d 1299, 1315, 120 USPQ2d 1091, 1102-03 (Fed. Cir. 2016) (claims to automatic lip synchronization and facial expression animation were directed to an improvement in computer-related technology and not directed to an abstract idea); Visual Memory LLC v. NVIDIA Corp., 867 F.3d 1253,1259-60, 123 USPQ2d 1712, 1717 (Fed. Cir. 2017) (claims to an enhanced computer memory system were directed to an improvement in computer capabilities and not an abstract idea); Finjan Inc. v. Blue Coat Systems, Inc., 879 F.3d 1299, 125 USPQ2d 1282 (Fed. Cir. 2018) (claims to virus scanning were found to be an improvement in computer technology and not directed to an abstract idea); SRI Int’l, Inc. v. Cisco Systems, Inc., 930 F.3d 1295, 1303 (Fed. Cir. 2019) (claims to detecting suspicious activity by using network monitors and analyzing network packets were found to be an improvement in computer network technology and not directed to an abstract idea). Additional examples are provided in MPEP § 2106.05(a). Regarding the December 5th 2025 Memo in light of September 26, 2025 Appeals Review Panel Decision in Ex parte Desjardins, Appeal 2024-000567 for Application 16/319,040, in deciding if a recited abstract idea does or does not direct the entire claim to an abstract idea, when a claim is considered as a whole: Paragraph 21 of the Specification, which the Appellant cites, identifies improvements in training the machine learning model itself. Of course, such an assertion in the Specification alone is insufficient to support a patent eligibility determination, absent a subsequent determination that the claim itself reflects the disclosed improvement. See MPEP § 2106.05(a) (citing Intellectual Ventures I LLC v. Symantec Corp., 838 F.3d 1307, 1316 (Fed. Cir. 2016)). Here, however, we are persuaded that the claims reflect such an improvement. For example, one improvement identified in the 8 Appeal2024-000567 Application 16/319,040 Specification is to "effectively learn new tasks in succession whilst protecting knowledge about previous tasks." Spec. ,r 21. The Specification also recites that the claimed improvement allows artificial intelligence (AI) systems to "us[e] less of their storage capacity" and enables "reduced system complexity." Id. When evaluating the claim as a whole, we discern at least the following limitation of independent claim 1 that reflects the improvement: "adjust the first values of the plurality of parameters to optimize performance of the machine learning model on the second machine learning task while protecting performance of the machine learning model on the first machine learning task." We are persuaded that constitutes an improvement to how the machine learning model itself operates, and not, for example, the identified mathematical calculation. Under a charitable view, the overbroad reasoning of the original panel below is perhaps understandable given the confusing nature of existing § 101 jurisprudence, but troubling, because this case highlights what is at stake. Categorically excluding AI innovations from patent protection in the United States jeopardizes America's leadership in this critical emerging technology. Yet, under the panel's reasoning, many AI innovations are potentially unpatentable-even if they are adequately described and nonobvious-because the panel essentially equated any machine learning with an unpatentable "algorithm" and the remaining additional elements as "generic computer components," without adequate explanation. Dec. 24. Examiners and panels should not evaluate claims at such a high level of generality. Specifically, Ex Parte Desjardins explained the following: Enfish ranks among the Federal Circuit's leading cases on the eligibility of technological improvements. In particular, Enfish recognized that “[m]uch of the advancement made in computer technology consists of improvements to software that, by their very nature, may not be defined by particular physical features but rather by logical structures and processes.” 822 F.3d at 1339. Moreover, because “[s]oftware can make non-abstract improvements to computer technology, just as hardware improvements can,” the Federal Circuit held that the eligibility determinations should turn on whether “the claims are directed to an improvement to computer functionality versus being directed to an abstract idea.” Id. at 1336. (Desjardins, page 8). Further in Ex Parte Desjardins, Appeal No. 2024-000567 (PTAB September 26, 2025, Appeals Review Panel Decision) (precedential), the claimed invention was a method of training a machine learning model on a series of tasks. The Appeals Review Panel (ARP) overall credited benefits including reduced storage, reduced system complexity and streamlining, and preservation of performance attributes associated with earlier tasks during subsequent computational tasks as technological improvements that were disclosed in the patent application specification. Specifically, the ARP upheld the Step 2A Prong One finding that the claims recited an abstract idea (i.e., mathematical concept). In Step 2A Prong Two, the ARP then determined that the specification identified improvements as to how the machine learning model itself operates, including training a machine learning model to learn new tasks while protecting knowledge about previous tasks to overcome the problem of “catastrophic forgetting” encountered in continual learning systems. Importantly, the ARP evaluated the claims as a whole in discerning at least the limitation “adjust the first values of the plurality of parameters to optimize performance of the machine learning model on the second machine learning task while protecting performance of the machine learning model on the first machine learning task” reflected the improvement disclosed in the specification. Accordingly, the claims as a whole integrated what would otherwise be a judicial exception instead into a practical application at Step 2A Prong Two, and therefore the claims were The claim itself does not need to explicitly recite the improvement described in the specification (e.g., “thereby increasing the bandwidth of the channel”). See, e.g., Ex Parte Desjardins, Appeal No. 2024-000567 (PTAB September 26, 2025, Appeals Review Panel Decision) (precedential), in which the specification identified the improvement to machine learning technology by explaining how the machine learning model is trained to learn new tasks while protecting knowledge about previous tasks to overcome the problem of “catastrophic forgetting,” and that the claims reflected the improvement identified in the specification. Indeed, enumerated improvements identified in the Desjardins specification included disclosures of the effective learning of new tasks in succession in connection with specifically protecting knowledge concerning previously accomplished tasks; allowing the system to reduce use of storage capacity; and the enablement of reduced complexity in the system. Such improvements were tantamount to how the machine learning model itself would function in operation and therefore not subsumed in the identified mathematical calculation. Claim Interpretation The following is a quotation of 35 U.S.C. 112(f): (f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof. The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph: An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof. The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked. As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph: (A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function; (B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and (C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function. Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function. Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function. Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are: an agent manager engine Such a term on its own provides basic structure of managing agents but not with the specificity needed. For instance, an agent manager engine can manage multiple engines but lacks the specificity for different system directives and LLMs. Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof. If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. 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. Claims 1, 14, 17, and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 20200135187 A1 Chao; Pu-sen et al. (hereinafter Chao) in view of US 20230403357 A1 Ezell; Joel (hereinafter Ezell). Re claim 1, Chao teaches 1. A dynamic conversation interface system, comprising: computing hardware, including at least one processor, data storage, and input/output facilities; wherein the computing hardware stores instructions that, when executed by the at least one processor, cause the at least one processor to implement: (fig. 1 & fig. 2 hardware) a plurality of instances of a large language model (LLM) (LLM not taught by Chao) engine, wherein each LLM engine instance is configured according to a respective set of system directives; (switching models based on a trigger such as a user speaking characteristic e.g. language change from English to another language as in 0060 with 0050) an agent manager engine operative to instantiate and configure the instances of the LLM engine such that a first LLM engine instance is configured according to a first set of system directives, and a second LLM engine instance is configured according to a second set of system directives that is different from the first set, (switching from first model to another model based on a trigger such as a user speaking characteristic e.g. language change from English to another language as in 0060 with 0050, here the specialization is languages) wherein the first LLM engine instance has a different functional specialization from the second LLM engine instance, (switching from first model to another model based on a trigger such as a user speaking characteristic e.g. language change from English to another language as in 0060 with 0050, here the specialization is languages model1 = English and model2 = Chinese for example) wherein the first LLM engine instance and the second LLM engine instance engage in a same conversation session with a user to perform different specializations within that conversation session, and (switching in real-time based on a trigger such as a user speaking characteristic e.g. language change from English to another language as in 0060 with 0050, here the specialization is languages model1 = English and model2 = Chinese for example) wherein the first set of system directives include directives that determine occurrence of a defined condition for instantiating the second LLM engine instance, and wherein the agent manager engine is further operative to instantiate the second LLM engine instance in response to the occurrence of the defined condition. (if model1 = false then model2 and visa versa such that the system can handle any permutation of language changes, switching in real-time based on a trigger such as a user speaking characteristic e.g. language change from English to another language as in 0060 with 0050, here the specialization is languages model1 = English and model2 = Chinese for example) However, while Chao teaches machine learning models, it fails to teach: Large language model (LLM) (Ezell known concepts of LLM 0005 and 0172) Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chao to incorporate the above claim limitations as taught by Ezell to allow for a simple substation of LM with LLM for an expanded model as a predictable result, wherein the system of Chao is improved to be expanded to handle more data thereby allowing for faster processing and a more flexible model set. Re claim 14, while Chao switching models, it fails to teach customer service as follows: 14. The system of claim 1, wherein the first set of system directives define attributes of an agent of a first customer service organization. (Ezell subset of agents and a variety of agents ready for unique customers needs as in 0034 and 0038) Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chao to incorporate the above claim limitations as taught by Ezell to allow for a simple substation a user dialogue context to that of customer service, yielding analogous bot/agent operations with predictable results of providing answers to user inquiries, but in the context of customer service. Re claim 17, while Chao switching models, it fails to teach customer service as follows: 17. The system of claim 14, wherein the second set of system directives define attributes of an agent of a second customer service organization which is distinct from the first customer service organization. (Ezell from one or more companies depending on user needs, subset of agents and a variety of agents ready for unique customers needs as in 0034 and 0038) Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chao to incorporate the above claim limitations as taught by Ezell to allow for a simple substation a user dialogue context to that of customer service, yielding analogous bot/agent operations with predictable results of providing answers to user inquiries, but in the context of customer service. Re claim 18, while Chao switching models, it fails to teach customer service as follows: 18. The system of claim 17, wherein the second customer service organization is a non-governmental customer service organization. (Ezell, no mention of government services… from one or more companies depending on user needs, subset of agents and a variety of agents ready for unique customers needs as in 0034 and 0038) Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chao to incorporate the above claim limitations as taught by Ezell to allow for a simple substation a user dialogue context to that of customer service, yielding analogous bot/agent operations with predictable results of providing answers to user inquiries, but in the context of customer service. Claims 2 and 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 20200135187 A1 Chao; Pu-sen et al. (hereinafter Chao) in view of US 20230403357 A1 Ezell; Joel (hereinafter Ezell) and further in view of US 20160111112 A1 Hayakawa; Shoji (hereinafter Hayakawa). Re claim 2, while Chao teaches machine learning models, it fails to teach: Large language model (LLM) (Ezell known concepts of LLM 0005 and 0172) Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chao to incorporate the above claim limitations as taught by Ezell to allow for a simple substation of LM with LLM for an expanded model as a predictable result, wherein the system of Chao is improved to be expanded to handle more data thereby allowing for faster processing and a more flexible model set. However, while Chao teaches identifying a user profile for a speaker as in 0026, implying that multiple users are possible, it fails to teach: 2. The system of claim 1, wherein the first instance of the LLM engine and the second instance of the LLM engine are respectively associated with different client entities of the dynamic conversation interface system. (Hayakawa switching models when another user is detected 0006) Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chao in view of Ezell to incorporate the above claim limitations as taught by Hayakawa to allow for a combining the prior art elements of Chao’s language trigger models with Hayakawa’s user models, as a substitution of identifying a user profile for a speaker as in 0026 of Chao, such that the combination produces predictable results where users are now expressly identified as well as their language spoken, thereby improving a switch trigger for either user or language using a user profile, which increasing processing power and reduces the need for disambiguation. Re claim 3, Chao teaches 3. The system of claim 2, wherein the first instance of the LLM engine and the second instance of the LLM engine are informationally isolated from one another such that information provided by the user to the first LLM engine instance is not accessible by the second instance of the LLM engine. (the models entire purpose is to not share data, otherwise English and Chinese would merge into an unreal language…if model1 = false then model2 and visa versa such that the system can handle any permutation of language changes, switching in real-time based on a trigger such as a user speaking characteristic e.g. language change from English to another language as in 0060 with 0050, here the specialization is languages model1 = English and model2 = Chinese for example) However, while Chao teaches machine learning models, it fails to teach: Large language model (LLM) (Ezell known concepts of LLM 0005 and 0172) Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chao to incorporate the above claim limitations as taught by Ezell to allow for a simple substation of LM with LLM for an expanded model as a predictable result, wherein the system of Chao is improved to be expanded to handle more data thereby allowing for faster processing and a more flexible model set. Claims 15, 16, 19, and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 20200135187 A1 Chao; Pu-sen et al. (hereinafter Chao) in view of US 20230403357 A1 Ezell; Joel (hereinafter Ezell) and further in view of US 20220375259 A1 Banerjee; Ashim et al. (hereinafter Banerjee). Re claim 15, the combination teaches multiple companies with a subset of agents using model switching per user, but fails to teach: 15. The system of claim 14, wherein the first customer service organization is a governmental agency. (Banerjee customer and agent interactions in a government setting 0163 and 0190). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chao in view of Ezell to incorporate the above claim limitations as taught by Banerjee to allow for simple substitution of the private company of Ezell to include a government offering analogous services to a customer such as analogous competing insurance or benefits, thereby expanding the agent subset allowing for more user options. Re claim 16, the combination teaches multiple companies with a subset of agents using model switching per user, but fails to teach: 16. The system of claim 14, wherein the first customer service organization is an agency that provides social-services benefits information to its customers, and wherein the first set of system directives and the second set of system directives define different sets of information pertaining to the social-service benefits information. (Banerjee government services encompass social services under BRI, such as any form of help precluding a narrowed claim context, or whether social service is not given a customary meaning e.g. social interaction service… customer and agent interactions in a government setting 0163 and 0190). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chao in view of Ezell to incorporate the above claim limitations as taught by Banerjee to allow for simple substitution of the private company of Ezell to include a government offering analogous services to a customer such as analogous competing insurance or benefits, thereby expanding the agent subset allowing for more user options. Re claim 19, the combination teaches multiple companies with a subset of agents using model switching per user, but fails to teach: 19. The system of claim 14, wherein the first set of system directives defines criteria for determining whether the user is qualified for a product of the first customer service organization. (Banerjee customer and agent interactions in a government setting 0163 and 0190). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chao in view of Ezell to incorporate the above claim limitations as taught by Banerjee to allow for simple substitution of the private company of Ezell to include a government offering analogous services to a customer such as analogous competing insurance or benefits, thereby expanding the agent subset allowing for more user options. Re claim 20, the combination teaches multiple companies with a subset of agents (Ezell 0034 and 0038 with products e.g. 0003) using model switching per user (Chao 0050 and 0060), but fails to teach switching for eligibility or qualification: 20. The system of claim 19, wherein at least one of the first set of system directives defines a set of operations to be executed by the system in response to a determination that the user is not qualified for the product, wherein the set of operations includes causing the system to communicatively connect the user with a different customer service organization during the same conversation session, wherein the different customer service organization provides a different product. (Banerjee customer products and eligibility provides yes/no, in which case a different agent can intervene, customer and agent interactions in a government setting 0163 and 0190). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chao in view of Ezell to incorporate the above claim limitations as taught by Banerjee to allow for simple substitution of the private company of Ezell to include a government offering analogous services to a customer such as analogous competing insurance or benefits, thereby expanding the agent subset allowing for more user options, and further for modification of the combination such that the agent subset products contains eligible versus non-eligible thereby further substituting the concept of transferring agents/bot-agents for predictable results of literal agent transfer in either government or non-government settings using the user profiles of Chao and agent subsets of Ezell. Allowable Subject Matter Claim 4 is objected to, including dependent claims 5-13 thereof, as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims. Conclusion The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. US 20240211693 A1 Mazor; Igal et al. Customer agent switch US 20200135187 A1 Chao; Pu-sen et al. Language switching mid-conversation US 20160111112 A1 Hayakawa; Shoji Speaker change detection US 20220375259 A1 Banerjee; Ashim et al. Customer service including government US 20230403357 A1 Ezell; Joel Large language models US 20240107083 A1 COPPELMANS; CAMIEL et al. Government and private agents Any inquiry concerning this communication or earlier communications from the examiner should be directed to MICHAEL COLUCCI whose telephone number is (571)270-1847. The examiner can normally be reached on M-F 9 AM - 7 PM. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Andrew Flanders can be reached at (571)272-7516. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000. /MICHAEL COLUCCI/Primary Examiner, Art Unit 2655 (571)-270-1847 Examiner FAX: (571)-270-2847 Michael.Colucci@uspto.gov
Read full office action

Prosecution Timeline

Mar 14, 2025
Application Filed
Oct 28, 2026
Non-Final Rejection mailed — §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12784743
DEEPFAKE DETECTION
2y 12m to grant Granted Nov 03, 2026
Patent 12784740
Diffusion Models for Generation of Audio Data Based on Descriptive Textual Prompts
2y 6m to grant Granted Nov 03, 2026
Patent 12749485
Device Leadership Negotiation Among Voice Interface Devices
2y 2m to grant Granted Sep 29, 2026
Patent 12749487
METHOD AND APPARATUS FOR PROVIDING VOICE RECOGNITION SERVICE
2y 2m to grant Granted Sep 29, 2026
Patent 12748934
ESTIMATION APPARATUS, LEARNING APPARATUS, ESTIMATION METHOD, LEARNING METHOD, AND PROGRAM
2y 2m to grant Granted Sep 29, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

Strategy Recommendation AI-generated — please review before filing

Get a prosecution strategy drawn from examiner precedents, rejection analysis, and claim mapping.
Typically takes 5-10 seconds — AI-generated, attorney review required before filing

Prosecution Projections

1-2
Expected OA Rounds
76%
Grant Probability
91%
With Interview (+15.2%)
3y 1m (~1y 6m remaining)
Median Time to Grant
Low
PTA Risk
Based on 1020 resolved cases by this examiner. Grant probability derived from career allowance rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month