DETAILED ACTION
This is a non-final, first office action on the merits. Claims 1-20 are pending. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. Specifically, claims 1-20 are directed to an abstract idea without additional elements amounting to significantly more than the abstract idea.
With respect to Step 2A Prong One of the framework, claims 1, 8, and 15 recite an abstract idea. Claims 1, 8, and 15 include “receiving tabular data; serializing the tabular data to provide serialized data; generating a prompt comprising a persona, and a thinking style, the persona being specific to an operation of the enterprise and comprising a description of a role for executing the operation, the steps defining a sequence of actions that a model is to perform in processing the prompt, the thinking style comprising a description of how the model is to process the prompt; serialized data to the model; receiving output of the model responsive to the prompt; and executing at least one operation using the output”.
The limitations above recite an abstract idea under Step 2A Prong One. More particularly, the elements above recite mental processes-concepts performed in the human mind (including an observation, evaluation, judgment, opinion) because the elements describe a process for executing one or more operations. As a result, claims 1, 8, and 15 recite an abstract idea under Step 2A Prong One.
Claims 2-6, 9-14, and 16-20 further describe the process for executing one or more operations. As a result, claims 2-6, 9-14, and 16-20 recite an abstract idea under Step 2A Prong One for the same reasons as stated above with respect to claims 1, 8, and 15.
With respect to Step 2A Prong Two of the framework, claims 1, 8, and 15 do not include additional elements that integrate the abstract idea into a practical application. Claims 1, 8, and 15 include additional elements that do not recite an abstract idea under Step 2A Prong One. The additional elements of claims 1, 8, and 15 include large language models (LLMs), chain-of-thought (CoT), a natural language, a prompt, one or more processors, a non-transitory computer-readable storage medium, a computing device, and a computer-readable storage device. When considered in view of the claim as a whole, the additional elements do not integrate the abstract idea into a practical application because the additional computing elements are generic computing elements that are merely used as a tool to perform the recited abstract idea. As a result, claims 1, 8, and 15 do not include additional elements that integrate the abstract idea into a practical application under Step 2A Prong Two.
Further, the system claims include the additional elements of large language models (LLMs), chain-of-thought (CoT), a natural language, a prompt, one or more processors, a non-transitory computer-readable storage medium, a computing device, and a computer-readable storage device. The process claims include the additional elements of transmitting the prompt and serialized data to the LLM; receiving output of the LLM responsive to the prompt; and executing at least one operation using the output. The claims as a whole merely describe how to generally “apply” the abstract idea(s) in a computer environment. The claimed processing elements are recited at a high level of generality and are merely invoked as a tool to perform the abstract idea(s).
Claims 3, 10, and 17 do not include any additional elements beyond those recited with respect to claims 1, 8, and 15. As a result, claims 3, 10, and 17 do not include additional elements that integrate the abstract idea into a practical application under Step 2A Prong Two for the same reasons as stated above with respect to claims 1, 8, and 15.
Claims 2, 4-7, 9, 11-14, 16, and 18-20 include additional elements that do not recite an abstract idea under Step 2A Prong One. The additional elements of claims 2, 4-7, 9, 11-14, 16, and 18-20 include an LLM, a prompt, and a set of prompt. When considered in view of the claims as a whole, the additional elements do not integrate the abstract idea into a practical application because the additional computing elements do no more than generally link the use of the recited abstract idea to a particular technological environment. As a result, claims 2, 4-7, 9, 11-14, 16, and 18-20 do not include additional elements that integrate the abstract idea into a practical application under Step 2A Prong Two.
With respect to Step 2B of the framework, claims 1, 8, and 15 do not include additional elements amounting to significantly more than the abstract idea. As noted above, claims 1, 8, and 15 include additional elements that do not recite an abstract idea under Step 2A Prong One. The additional elements of claims 1, 8, and 15 include large language models (LLMs), chain-of-thought (CoT), a natural language, a prompt, one or more processors, a non-transitory computer-readable storage medium, a computing device, and a computer-readable storage device. The additional elements do not amount to significantly more than the abstract idea because the additional computing elements are generic computing elements that are merely used as a tool to perform the recited abstract idea. Further, looking at the additional elements as an ordered combination adds nothing that is not already present when considering the additional elements individually. As a result, independent claims 1, 8, and 15 do not include additional elements that amount to significantly more than the abstract idea under Step 2B.
Further, the system claims include the additional elements of large language models (LLMs), chain-of-thought (CoT), a natural language, a prompt, one or more processors, a non-transitory computer-readable storage medium, a computing device, and a computer-readable storage device. The process claims include the additional elements of transmitting the prompt and serialized data to the LLM; receiving output of the LLM responsive to the prompt; and executing at least one operation using the output. The claims as a whole merely describe how to generally “apply” the abstract idea(s) in a computer environment. The claimed processing elements are recited at a high level of generality and are merely invoked as a tool to perform the abstract idea(s).
Claims 3, 10, and 17 do not include any additional elements beyond those recited with respect to claims 1, 8, and 15. As a result, claims 3, 10, and 17 do not include additional elements that amount to significantly more than the abstract idea under Step 2B for the same reasons as stated above with respect to claims 1, 8, and 15.
Claims 2, 4-7, 9, 11-14, 16, and 18-20 include additional elements that do not recite an abstract idea under Step 2A Prong One. The additional elements of claims 2, 4-7, 9, 11-14, 16, and 18-20 include an LLM, a prompt, and a set of prompt. The additional elements do not amount to significantly more than the abstract idea because the additional computing elements do no more than generally link the use of the recited abstract idea to a particular technological environment. Further, looking at the additional elements as an ordered combination adds nothing that is not already present when considering the additional elements individually. As a result, claims 2, 4-7, 9, 11-14, 16, and 18-20 do not include additional elements that amount to significantly more than the abstract idea under Step 2B.
Therefore, the claims are directed to an abstract idea without additional elements amounting to significantly more than the abstract idea. Accordingly, claims 1-20 are rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
Claim Rejections - 35 USC § 103
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 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.
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 of this title, 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.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-6, 8-13, and 15-20 are rejected under 35 U.S.C. 103 as being unpatentable over J Kaddour, M Mozes, H Bradley, R Raileanu, R McHardy J Harris et al. (Challenges and applications of large language models), arXiv preprint arXiv:2307.10169, 2023•arxiv.org (hereinafter Harris et al.) in view of Joshi et al. (US Pub No. 2024/0386496) (hereinafter Joshi et al.).
Regarding claims 1, 8, and 15, Harris in view of Joshi discloses a computer-implemented method for executing one or more operations of an enterprise using large language models (LLMs), the method comprising:
receiving tabular data (see Harris, column 2, page 41, wherein enabling LLMs to understand charts and plots by first using a vision plot-to-text translation model to decompose the chart into a linearized data table. Once the chart or plot has been converted into a text-based data table, it is combined with the prompt);
serializing the tabular data to provide serialized data (see Harris, column 2, page 41, wherein enabling LLMs to understand charts and plots by first using a vision plot-to-text translation model (DePlot) to decompose the chart into a linearized data table. Once the chart or plot has been converted into a text-based data table, it is combined with the prompt; and column 1, page 46, wherein multi-modal sensory inputs are first converted into a text-based hierarchical summary at the sensory, event, and sub-goal levels. The hierarchical summary then prompts the LLM to detect and analyze failures. Similarly, Huang et al. [225] combine an LLM (InstructGPT, PaLM) with multiple sources of text-based environment feedback for robotic task planning);
generating a prompt comprising a persona (see Harris, column 2, page 17, wherein a prompt is an input to the LLM. The prompt syntax (e.g., length, blanks, ordering of examples) and semantics (e.g., wording, selection of examples, instructions) can have a significant impact on the model’s output; and column 2, page 47, wherein using LLMs as models for human behavior, various existing works study LLMs by analyzing their personality traits……Each character has unique traits, and the characters interact with each other through natural language. Simulating such societies, the authors observe emergent social behaviors (e.g., forming new relationships and attending events) between agents that are formed without any human interaction),
a set of chain-of-thought (CoT) steps, and a thinking style (see Harris, column 1, page 19, wherein Chain-of-Thought (CoT) [327, 601] describes a technique used to construct few-shot prompts via a series of intermediate reasoning steps leading to the final output. Answer rationales to solve algebraic problems were originally proposed in the pre-LLM era [327] and later experienced big popularity as a prompting strategy for LLMs [601]. Extensions of chain-of-thought prompting include zero-shot variants [273] and automatically generated series of reasoning steps),
the persona being specific to an operation of the enterprise and comprising a natural language description of a role for executing the operation (see Harris, column 2, page 48, wherein Each character has unique traits, and the characters interact with each other through natural language. Simulating such societies, the authors observe emergent social behaviors (e.g., forming new relationships and attending events) between agents that are formed without any human interaction…..using LLMs as models for human behavior, various existing works study LLMs by analyzing their personality traits; column 2, pages 17, 37, & 45-48, wherein designing natural language queries that steer the model’s outputs toward desired outcomes is often referred to as prompt engineering [477, 287, 606]. Fig. 6 summarizes some of the most popular prompting methods with an example adapted from Wei et al. [601]. As we can see, there are lots of equally-plausible prompting techniques, and the current state of prompt engineering still requires lots of experimentation, with little theoretical understanding of why a particular way to phrase a task is more sensible other than that it achieves better empirical results…..),
the CoT steps defining a sequence of actions that a LLM is to perform in processing the prompt, the thinking style comprising a natural language description of how the LLM is to process the prompt (see Harris, column 1, page 19, wherein Chain-of-Thought (CoT) [327, 601] describes a technique used to construct few-shot prompts via a series of intermediate reasoning steps leading to the final output; column 2, page 45, wherein LLM to propose possible next actions via iteratively scoring the most likely of a defined set of low-level tasks based on the high-level text input. The low-level task to be executed is then determined by combining the low-level tasks proposed by the LLM with affordance functions which determine the probability of the robot completing the task given the current low-level context; and column 2, page 45, wherein by providing details of the function library in the prompt, ChatGPT is then shown to be able to break down high-level natural language instructions into a set of lower-level function calls, which can then be executed on the robot if the human is satisfied it is accurate);
receiving output of the LLM responsive to the prompt (see Harris, column 1-2, page 19, wherein the LLM sequentially solves the subproblems with prompts for later-stage subproblems containing previously produced solutions, iteratively building the final output….a single LLM generates an initial output and then iteratively provides feedback on the previous output, followed by a refinement step in which the feedback is incorporated into a revised output); and
executing at least one operation using the output (see Harris, column 1, page 19, wherein combines reasoning and acting by prompting LLMs to generate reasoning traces (e.g., Chain-of-thought) and action plans, which can be executed to allow the model to interact with external environments such as Wikipedia to incorporate knowledge).
Harris et al. fails to explicitly disclose being executed by one or more processors, a non-transitory computer-readable storage medium; a computing device; a computer-readable storage device; and transmitting the prompt and serialized data to the LLM.
Analogous art Joshi discloses one or more processors; a non-transitory computer-readable storage medium; a computing device; a computer-readable storage device (see Joshi, paras [0036]-[0038]).
Analogous art Joshi discloses a natural language description of a role for executing the operation (see Joshi, abstract and para [0032], wherein due to the variety of possible natural language inputs, user control over the raw text inputs can create varying results. If the user provides a description that is too vague, the LLM system 510 may not be able to process the text to achieve useful results. In some implementations, chat bots or other prompt request tools can be used to prompt the lead to enter further details on their preferred FA attributes…..; and para [0007], wherein the machine learning model using known attributes of the leads and advisors to determine optimal lead/advisor matches and to output an initial recommendation list of lead/advisor matched pairs, receiving preferences from the end user regarding a preferred financial advisor in natural text form converting the natural text received from the end user into a form adapted to be used as input to the machine learning model, identifying financial advisor attributes in the converted natural text; and executing the deserialized machine learning model at the end user device using the financial advisor attributes to determine a list of advisor recommendations tailored for the end user);
Analogous art Joshi discloses transmitting the prompt and serialized data to the LLM (see Joshi, abstract and para [0015], wherein providing access to the serialized model to a user device via an API…..transmitting a selection from the filtered recommendations from the user for further training of the model with respect to the particular end user….a user interface (UI) 110 through which a lead or other user can select a prompt or widget to obtain an advisor recommendation or locate an advisor); and
Analogous art Joshi discloses serializing the tabular data to provide serialized data (see Joshi, abstract and para [0023], wherein enables the development of machine learning pipeline models that can be used to optimize lead-advisory matching (and other applications) and also performs serialization of data structures)).
Harris directed to a system for determining in-season crop status in an agricultural crop. Joshi directed to providing recommendations for matching leads. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Harris, regarding the System for Challenges and Applications of Large Language Models, to have included one or more processors; a non-transitory computer-readable storage medium; a computing device; a computer-readable storage device; a natural language description of a role for executing the operation; transmitting the prompt and serialized data to the LLM; and serializing the tabular data to provide serialized data because both inventions teach improving results on tasks. Further, the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable.
Regarding claims 2, 9, and 16, Harris in view of Joshi discloses the method of claim 1, wherein the prompt further comprises a set of pre-calculation steps defining calculations to be executed by the LLM on the tabular data prior to executing actions in the set of actions (see Harris, column 1, page 19, wherein Scratchpad [391] is a method to fine-tune LLMs on multi-step computation tasks such that they output intermediate reasoning steps, e.g., intermediate calculations when performing additions, into a “scratchpad” before generating the final result; column 2, page 41, wherein enabling LLMs to understand charts and plots by first using a vision plot-to-text translation model (DePlot) to decompose the chart into a linearized data table. Once the chart or plot has been converted into a text-based data table, it is combined with the prompt; and column 1, page 46, wherein multi-modal sensory inputs are first converted into a text-based hierarchical summary at the sensory, event, and sub-goal levels. The hierarchical summary then prompts the LLM to detect and analyze failures. Similarly, Huang et al. [225] combine an LLM (InstructGPT, PaLM) with multiple sources of text-based environment feedback for robotic task planning).
Regarding claims 3, 10, and 17, Harris in view of Joshi discloses the method of claim 1, wherein the tabular data is serialized using a text template (see Harris, column 1-2, page 19, wherein Ask Me Anything [24] uses multiple prompt templates (called prompt chains), which are used to reformat few-shot example inputs into an open ended question-answering format…..the prompt text to steer model outputs).
Regarding claims 4, 11, and 18, Harris in view of Joshi discloses the method of claim 1, wherein the prompt is generated using a prompt template (see Harris, column 1-2, page 19, wherein Ask Me Anything [24] uses multiple prompt templates (called prompt chains), which are used to reformat few-shot example inputs into an open ended question-answering format…..the prompt text to steer model outputs).
Regarding claims 5, 12, and 19, Harris in view of Joshi discloses the method of claim 1, wherein the prompt enables the LLM to access one or more of an external data source and an external tool (see Harris, column 1, page 34, wherein chatbot LLMs with up to 137B parameters, focusing on safety (via supervised fine-tuning on human annotations) and factual grounding (via access to external knowledge sources)).
Regarding claims 6, 13, and 20, Harris in view of Joshi discloses the method of claim 5, wherein the external tool comprises a mathematics counsel that is executable by the LLM to perform mathematical calculations (see Harris, column 1, page 19, wherein Examiner interpret “a mathematics counsel” as giving an AI access to an external computational tool or programming environment…..Scratchpad [391] is a method to fine-tune LLMs on multi-step computation tasks such that they output intermediate reasoning steps, e.g., intermediate calculations when performing additions, into a “scratchpad” before generating the final result…ReAct [640] combines reasoning and acting by prompting LLMs to generate reasoning traces (e.g., Chain-of-thought) and action plans, which can be executed to allow the model to interact with external environments such as Wikipedia to incorporate knowledge; and….column 1-2, page 34, wherein the prompt enables the LLM to access one or more of an external data source and an external tool (see Harris, column 1, page 34, wherein chatbot LLMs with up to 137B parameters, focusing on safety (via supervised fine-tuning on human annotations) and factual grounding (via access to external knowledge sources….).
Claims 7 and 14 and are rejected under 35 U.S.C. 103 as being unpatentable over J Kaddour, M Mozes, H Bradley, R Raileanu, R McHardy J Harris et al. (Challenges and applications of large language models), arXiv preprint arXiv:2307.10169, 2023•arxiv.org (hereinafter Harris et al.) in view of Joshi et al. (US Pub No. 2024/0386496) (hereinafter Joshi et al.), and further in view of Chiang et al. (US Pub No. 2024/0354792) (hereinafter Chiang et al.).
Regarding claims 7 and 14, Harris in view of Joshi discloses the method of claim 1, wherein the prompt is provided from a set of prompts (see Harris, column 1, page 19, wherein Multi-Turn Prompting methods iteratively chain prompts and their answers together).
Harris et al. fails to explicitly disclose wherein each prompt being specific to an operation of the enterprise.
Analogous art Chiang discloses the prompt is provided from a set of prompts, each prompt being specific to an operation of the enterprise (see Chiang, para [0035], wherein a series of prompts, including chain-of-thought prompts that may be initiated automatically by a prompt management system and/or in response to questions from a user provided by way of an input from a user interface device. The prompts may additionally include ad-hoc prompts initiated to further analyze a dataset, such as in response to follow-up questions initiated by a user (i.e., entities (the term "entity" as used herein refers to a corporation, organization, person, or other entity); and para [0041], wherein the inputs may include prompts for the prompt management system 102 may execute operations, and the outputs may include task results 110 generated by the prompt management system 102 as a product of executing tasks that may be responsive to various prompts).
Harris directed to a system for determining in-season crop status in an agricultural crop. Chiang directed to providing recommendations for matching leads. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Harris, regarding the System for Challenges and Applications of Large Language Models, to have included the prompt is provided from a set of prompts, each prompt being specific to an operation of the enterprise because both inventions teach improving results on tasks. Further, the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable.
Conclusion
The prior arts made of record and not relied upon is considered pertinent to applicant's disclosure. (US Pub No. 2023/0030608; US Pat No. 12,346,333; US Pub No. 2022/0138004; US Pub No. 2023/0394328; US Pub No. 2025/0139378; and J Wei, X Wang, D Schuurmans, M Bosma, F Xia, E Chi, QV Le, D Zhou (Chain-of-thought prompting elicits reasoning in large language models), Advances in neural information processing systems, 2022•proceedings.neurips.cc.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HAFIZ A KASSIM whose telephone number is (571)272-8534. The examiner can normally be reached 9:00 - 5:00 PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Rutao Wu can be reached at 571-272-6045. 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.
/HAFIZ A KASSIM/Primary Examiner, Art Unit 3623 07/18/2026
Prosecution Insights