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
Claim Objections
Claim 33 is objected to because of the following informalities:
“generating the plurality of first output information in parallel “
“the plurality” lacks antecedent support but is functionally sound and definite. Appropriate correction is required.
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 quality from an LLM by combining both RAG and LLM supported by the specification, and reflected by the claims e.g. in spec: 0141.
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 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 21-40 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 20250103592 A1 Niu; Tong et al. (hereinafter Niu) in view of US 20210295822 A1 Tomkins; Adam et al. (hereinafter Tomkins).
Re claim 21, Niu teaches
21. (New) A processing method, comprising: (fig. 3a)
receiving, from a client terminal, an input of a question from a user; (as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082)
generating, based on the question, first output information using a large language model; (as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060)
generating, based on the first output information, second output information using the large language model; and (as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060)
However, while Niu teaches displaying answers and iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis, it fails to teach:
transmitting the first output information to a client terminal for causing first summary information to be displayed on the display of the client terminal; and (Tomkins dual display of answers/summaries 0026, 0230, 0238, with fig. 15 and also in technical format e.g. node/tree as in fig. 22 with 0354)
transmitting the second output information to a client terminal for causing second summary information to be displayed on the display of the client terminal. (Tomkins dual display of answers/summaries 0026, 0230, 0238, with fig. 15 and also in technical format e.g. node/tree as in fig. 22 with 0354)
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 Niu to incorporate the above claim limitations as taught by Tomkins to allow for combining prior art elements according to known methods to yield predictable results such as providing the option for the user to choose their own answer which forces reinforcement learning via user interaction or feedback i.e. input, fetches real-time, verified data from specific nodes in your knowledge tree, ensuring both generated answers are grounded in fact rather than LLM hallucinations, thus tailoring the information to different user personas simultaneously via A/B Testing in Real Time in which user selections act as high-quality training data, mapping messy natural language queries to specific, rigid nodal structures or API endpoints.
Re claim 35, this claim has been rejected for teaching a broader, or narrower claim based on general inclusion of hardware alone (e.g. processor, memory, instructions), representation of claim 1 omitting/including hardware for instance, otherwise amounting to a virtually identical scope
For instance, see fig. 3a which contains the hardware/software necessary.
Re claim 38, this claim has been rejected for teaching a broader, or narrower claim based on general inclusion of hardware alone (e.g. processor, memory, instructions), representation of claim 1 omitting/including hardware for instance, otherwise amounting to a virtually identical scope
For instance, see fig. 3a which contains the hardware/software necessary.
Re claims 22, 36, and 39, Niu teaches
22. (New) The processing method according to claim 21, further comprising:
retrieving related information based on the question; and (as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060… iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis 0026-0029 RAG model as an augmented language model per se, nodes and layers fig. 3b with 0039 and utilizing historical data 0023, 0056, 0061)
wherein the first output information is generated based on the question and the related information. (as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060… iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis 0026-0029 RAG model as an augmented language model per se, nodes and layers fig. 3b with 0039 and utilizing historical data 0023, 0056, 0061)
Re claims 23, 37, and 40, Niu teaches
23. (New) The processing method according to claim 21, further comprising:
repeatedly generating, based on previously generated output information, further output information using the large language model. (iterative approach as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060… iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis 0026-0029 RAG model as an augmented language model per se, nodes and layers fig. 3b with 0039 and utilizing historical data 0023, 0056, 0061)
Re claim 24, while Niu teaches displaying answers and iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis, it fails to teach:
24. (New) The processing method according to claim 21, further comprising:
accepting an input of an analysis perspective from a user; and (Tomkins dual display of answers/summaries 0026, 0230, 0238, with fig. 15 and also in technical format e.g. node/tree as in fig. 22 with 0354)
wherein the first output information is generated based on the question and the analysis perspective. (Tomkins dual display of answers/summaries 0026, 0230, 0238, with fig. 15 and also in technical format e.g. node/tree as in fig. 22 with 0354)
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 Niu to incorporate the above claim limitations as taught by Tomkins to allow for combining prior art elements according to known methods to yield predictable results such as providing the option for the user to choose their own answer which forces reinforcement learning via user interaction or feedback i.e. input, fetches real-time, verified data from specific nodes in your knowledge tree, ensuring both generated answers are grounded in fact rather than LLM hallucinations, thus tailoring the information to different user personas simultaneously via A/B Testing in Real Time in which user selections act as high-quality training data, mapping messy natural language queries to specific, rigid nodal structures or API endpoints.
Re claim 25, Niu teaches
25. (New) The processing method according to claim 21, wherein generating the first output information comprises:
generating a prompt based on the question; (internal prompt splitting the query, as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060… iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis 0026-0029 RAG model as an augmented language model per se, nodes and layers fig. 3b with 0039 and utilizing historical data 0023, 0056, 0061)
inputting the prompt to the large language model; and (as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060… iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis 0026-0029 RAG model as an augmented language model per se, nodes and layers fig. 3b with 0039 and utilizing historical data 0023, 0056, 0061)
generating the first output information using the large language model. (as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060… iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis 0026-0029 RAG model as an augmented language model per se, nodes and layers fig. 3b with 0039 and utilizing historical data 0023, 0056, 0061)
Re claim 26, Niu teaches
26. (New) The processing method according to claim 22, wherein the related information is retrieved using a web retrieval engine. (web retrival 0017, as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060… iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis 0026-0029 RAG model as an augmented language model per se, nodes and layers fig. 3b with 0039 and utilizing historical data 0023, 0056, 0061)
Re claim 27, Niu teaches
27. (New) The processing method according to claim 22, wherein retrieving the related information comprises:
generating a search query based on the question; (searching the web for instance 0017, as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060… iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis 0026-0029 RAG model as an augmented language model per se, nodes and layers fig. 3b with 0039 and utilizing historical data 0023, 0056, 0061)
inputting the search query to a retrieval model; and (a RAG model for instance, as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060… iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis 0026-0029 RAG model as an augmented language model per se, nodes and layers fig. 3b with 0039 and utilizing historical data 0023, 0056, 0061)
retrieving the related information using the retrieval model. (a RAG model for instance, as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060… iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis 0026-0029 RAG model as an augmented language model per se, nodes and layers fig. 3b with 0039 and utilizing historical data 0023, 0056, 0061)
Re claim 28, Niu teaches
28. (New) The processing method according to claim 21, further comprising:
generating, based on n-th output information, (n+1)-th output information using the large language model, wherein n is an integer greater than or equal to 1. (any number of iterations, two for instance is shown as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060… iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis 0026-0029 RAG model as an augmented language model per se, nodes and layers fig. 3b with 0039 and utilizing historical data 0023, 0056, 0061)
Re claim 29, Niu teaches
29. (New) The processing method according to claim 21, wherein generating the first output information comprises:
retrieving first related information based on the question; (as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060… iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis 0026-0029 RAG model as an augmented language model per se, nodes and layers fig. 3b with 0039 and utilizing historical data 0023, 0056, 0061)
converting the question into a vector representation; (vectorized e.g. 0026-0029… as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060… iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis 0026-0029 RAG model as an augmented language model per se, nodes and layers fig. 3b with 0039 and utilizing historical data 0023, 0056, 0061)
identifying second related information based on the vector representation and the related information; and (iterative, as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060… iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis 0026-0029 RAG model as an augmented language model per se, nodes and layers fig. 3b with 0039 and utilizing historical data 0023, 0056, 0061)
generating, based on the second related information, the first output information using the large language model. (final output based on several stage query breakdown, as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060… iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis 0026-0029 RAG model as an augmented language model per se, nodes and layers fig. 3b with 0039 and utilizing historical data 0023, 0056, 0061)
Re claim 30, while Niu teaches displaying answers and iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis, it fails to teach:
30. (New) The processing method according to claim 21, wherein the first summary information is displayed as a first node, the first node comprising a first display area for presenting content based on the first output information, (Tomkins dual display of answers/summaries 0026, 0230, 0238, with fig. 15 and also in technical format e.g. node/tree as in fig. 22 with 0354)
wherein the second summary information is displayed as a second node, the second node comprising a second display area for presenting content based on the second output information, and (Tomkins dual display of answers/summaries 0026, 0230, 0238, with fig. 15 and also in technical format e.g. node/tree as in fig. 22 with 0354)
wherein the second node is displayed on the display of the client terminal connected to the first node. (Tomkins dual display of answers/summaries 0026, 0230, 0238, with fig. 15 and also in technical format e.g. node/tree as in fig. 22 with 0354)
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 Niu to incorporate the above claim limitations as taught by Tomkins to allow for combining prior art elements according to known methods to yield predictable results such as providing the option for the user to choose their own answer which forces reinforcement learning via user interaction or feedback i.e. input, fetches real-time, verified data from specific nodes in your knowledge tree, ensuring both generated answers are grounded in fact rather than LLM hallucinations, thus tailoring the information to different user personas simultaneously via A/B Testing in Real Time in which user selections act as high-quality training data, mapping messy natural language queries to specific, rigid nodal structures or API endpoints.
Re claim 31, Niu teaches
31. (New) The processing method according to claim 22, further comprising:
retrieving related information based on the first output information; (as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060… iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis 0026-0029 RAG model as an augmented language model per se, nodes and layers fig. 3b with 0039 and utilizing historical data 0023, 0056, 0061)
generating, based on the related information, the second output information using the large language model; and (iterative back into LLM, as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060… iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis 0026-0029 RAG model as an augmented language model per se, nodes and layers fig. 3b with 0039 and utilizing historical data 0023, 0056, 0061)
transmitting each output information in association with the related information used to generate the output information. (as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060… iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis 0026-0029 RAG model as an augmented language model per se, nodes and layers fig. 3b with 0039 and utilizing historical data 0023, 0056, 0061)
Re claim 32, while Niu teaches displaying answers and iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis, it fails to teach:
32. (New) The processing method according to claim 23, further comprising:
transmitting the output information to the client terminal for causing a plurality of pieces of summary information to be displayed in a form of a tree structure on the display of the client terminal, (Tomkins dual display of answers/summaries 0026, 0230, 0238, with fig. 15 and also in technical format e.g. node/tree as in fig. 22 with 0354)
wherein the tree structure represents relationships among the plurality of pieces of summary information. (Tomkins dual display of answers/summaries 0026, 0230, 0238, with fig. 15 and also in technical format e.g. node/tree as in fig. 22 with 0354)
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 Niu to incorporate the above claim limitations as taught by Tomkins to allow for combining prior art elements according to known methods to yield predictable results such as providing the option for the user to choose their own answer which forces reinforcement learning via user interaction or feedback i.e. input, fetches real-time, verified data from specific nodes in your knowledge tree, ensuring both generated answers are grounded in fact rather than LLM hallucinations, thus tailoring the information to different user personas simultaneously via A/B Testing in Real Time in which user selections act as high-quality training data, mapping messy natural language queries to specific, rigid nodal structures or API endpoints.
Re claim 33, Niu teaches
33. (New) The processing method according to claim 21, further comprising performing:
generating the plurality of first output information in parallel. (fig. 1 for instance parallel retrievers applied with fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060… iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis 0026-0029 RAG model as an augmented language model per se, nodes and layers fig. 3b with 0039 and utilizing historical data 0023, 0056, 0061)
generating, based on the plurality of first output information, second output information using the large language model. (as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060… iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis 0026-0029 RAG model as an augmented language model per se, nodes and layers fig. 3b with 0039 and utilizing historical data 0023, 0056, 0061)
Re claim 34, Niu teaches
34. (New) The processing method according to claim 24, further comprising:
registering a plurality of pieces of related information in advance; and (history for instance, as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060… iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis 0026-0029 RAG model as an augmented language model per se, nodes and layers fig. 3b with 0039 and utilizing historical data 0023, 0056, 0061)
retrieving, based on the analysis perspective, related information relevant to the analysis perspective from among the plurality of pieces of related information registered in advance. (history for instance, as in fig. 2 a user inputs a query into a language model and/or LLM, in which two answers or summaries per se are produced, one as an input repeated back into the LLM and another the displayed output answer derived from two internal answers 0017 0077-0082 and displaying answers there of 0060… iterative generation of input/output with the LLM based on history and user queries in vectorized form aided by RAG models for restructuring using nodes + layers as a fundamental basis 0026-0029 RAG model as an augmented language model per se, nodes and layers fig. 3b with 0039 and utilizing historical data 0023, 0056, 0061)
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 20240428044 A1 Liu; Ye et al.
Parallel LLMs with a retriever
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MICHAEL C COLUCCI whose telephone number is (571)270-1847. The examiner can normally be reached on M-F 9 AM - 5 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
Prosecution Insights