DETAILED ACTION
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 .
This action is in response to the original application filed on Mar. 21st 2024.
Specification
The current title of this invention is not descriptive. A new title is required that is clearly indicative of the invention to which the claims are directed.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 4, 5, 11, 12, 18 and 19 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 4 recites the limitation, “algorithmically selecting an optimal LLM from the subset of LLMs based on the user's prompts.” (Emphasis added). The term “optimal” is not defined in the claim or in the specification. This limitation makes it difficult for a person of ordinary skill in the art to recognize the claimed bounds or limits of this claim because the claim recites generic terminology to describe a critical concept of the invention. Therefore, since this claim recites immeasurable and indefinite bounds, this claim is rejected under 35 U.S.C. 112(b) for being indefinite. For examination purposes the claim will be interpreted to mean, “… selecting a[[n]] LLM …”. Dependent claim 5 depends on rejected claim 4 and is also rejected under 35 U.S.C. 112(b) by virtue of this dependency. Appropriate correction is required.
Claim 11 recites the limitation, “program instructions to algorithmically select an optimal LLM from the subset of LLMs based on the user's prompts.” (Emphasis added). The term “optimal” is not defined in the claim or in the specification. This limitation makes it difficult for a person of ordinary skill in the art to recognize the claimed bounds or limits of this claim because the claim recites generic terminology to describe a critical concept of the invention. Therefore, since this claim recites immeasurable and indefinite bounds, this claim is rejected under 35 U.S.C. 112(b) for being indefinite. For examination purposes the claim will be interpreted to mean, “… selecting a[[n]] LLM …”. Dependent claim 12 depends on rejected claim 11 and is also rejected under 35 U.S.C. 112(b) by virtue of this dependency. Appropriate correction is required.
Claim 18 recites the limitation, “program instructions to algorithmically select an optimal LLM from the subset of LLMs based on the user's prompts.” (Emphasis added). The term “optimal” is not defined in the claim or in the specification. This limitation makes it difficult for a person of ordinary skill in the art to recognize the claimed bounds or limits of this claim because the claim recites generic terminology to describe a critical concept of the invention. Therefore, since this claim recites immeasurable and indefinite bounds, this claim is rejected under 35 U.S.C. 112(b) for being indefinite. For examination purposes the claim will be interpreted to mean, “… selecting a[[n]] LLM …”. Dependent claim 19 depends on rejected claim 18 and is also rejected under 35 U.S.C. 112(b) by virtue of this dependency. Appropriate correction is required.
Claim Rejections - 35 USC § 101 – Software per se
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.
Claim 8-14 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. These claims do not fall within at least one of the four categories of patent eligible subject matter.
Claim 8 recites:
“computer program product”
“one or more computer readable storage media”
“program instructions stored on the one or more computer readable storage media”
Claims 9-14 recite:
“program instructions stored on the one or more computer readable storage media”
“program instructions to …”
The submitted specification recites "A computer program product embodiment ("CPP embodiment" or "CPP") is a term used in the present disclosure to describe any set of one, or more, storage media (also called "mediums") collectively included in a set of one, or more, storage devices that collectively include machine readable code corresponding to instructions and/or data for performing computer operations specified in a given CPP claim. A "storage device" is any tangible device that can retain and store instructions for use by a computer processor." (Detailed Description, pp. 29, [0092]), (emphasis added), which states this system could be "software only" stored on transient devices and therefore would not fall under the four categories of patent eligible subject matter per 2106.03(I): "Non-limiting examples of claims that are not directed to any of the statutory categories include: Products that do not have a physical or tangible form, such as information (often referred to as "data per se") or a computer program per se (often referred to as "software per se") when claimed as a product without any structural recitations;”.
Claim Rejections - 35 USC § 101 – Abstract Idea
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 an abstract idea without significantly more. The analysis of the claims will follow the 2019 Revised Patent Subject Matter Eligibility Guidance, 84 Fed. Reg. 50 (“2019 PEG”).
Claim 1
Step 1 – Is the claim to a process, machine, manufacture or composition of matter?
Claim 1 recites, “A computer-implemented method comprising:” therefore it is directed to the statutory category of a process.
Step 2A Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The claim recites, inter alia:
“analyzing user prompts using one or more natural language understanding techniques;” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate user prompts using natural language understanding techniques. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
“enriching the user prompts by integrating contextual data from user interaction history; and” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate a user prompt and add information to the prompt as judgement or opinion. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
“adapting the enriched user prompts to align with characteristics of Large Language Models (LLMs) and Application Programming Interfaces (API) requirements of the LLMs.” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate a LLM model and the input requirements and, based on that evaluation, alter a prompt using judgement or opinion. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
Step 2A Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application?
This claim does not recite any additional limitations which integrate the abstract idea into a practical application.
Step 2B – Does the claim recite additional elements that amount to significantly more than the judicial exception?
Finally, the claim taken as a whole does not contain an inventive concept which provides significantly more than the abstract idea and thus the claim is subject-matter ineligible.
Claim 2
Step 1 – Is the claim to a process, machine, manufacture or composition of matter?
A process, as above.
Step 2A Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The claim recites, inter alia:
“tailoring the received user prompts for a respective LLM of the respective LLMs based on characteristics of each respective LLM.” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate a prompt and alter the prompt based on that evaluation using judgement or opinions. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
Step 2A Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application?
The claim recites the additional elements, “collecting received user prompts and contextual information associated with the received user prompts; and” is an insignificant extra-solution activity required for any uses of the mental processes (see MPEP § 2106.05(g)) As such, the claim is ineligible.
Step 2B – Does the claim recite additional elements that amount to significantly more than the judicial exception?
Finally, the claim taken as a whole does not contain an inventive concept which provides significantly more than the abstract idea. The additional elements, “collecting received user prompts and contextual information associated with the received user prompts; and” is an insignificant extra-solution activity required for any uses of abstract ideas (see MPEP § 2106.05(g)), and is a well-understood, routine, conventional activity (see MPEP § 2106.05(d)(II)(i); “Receiving or transmitting data over a network, e.g., using the Internet to gather data”.
Taken alone or in combination, the additional elements of the claim do not provide an inventive concept and thus the claim is subject-matter ineligible.
Claim 3
Step 1 – Is the claim to a process, machine, manufacture or composition of matter?
A process, as above.
Step 2A Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The claim recites, inter alia:
“formatting the tailored user prompts to align with the respective LLM.” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate a LLM input requirement and alter a given prompt based on this evaluation using judgement or opinions. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
Step 2A Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application?
This claim does not recite any additional limitations which integrate the abstract idea into a practical application.
Step 2B – Does the claim recite additional elements that amount to significantly more than the judicial exception?
Finally, the claim taken as a whole does not contain an inventive concept which provides significantly more than the abstract idea and thus the claim is subject-matter ineligible.
Claim 4
Step 1 – Is the claim to a process, machine, manufacture or composition of matter?
A process, as above.
Step 2A Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The claim recites, inter alia:
“categorizing the enriched user prompts based on its characteristics into specific domains and styles using natural language processing;” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate a given prompt and assign it to a category. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
“matching the categorized prompts with a subset of LLMs of the respective LLMs by querying a model behavior database; and” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to identify patterns and evaluate matching information. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
“algorithmically selecting an optimal LLM from the subset of LLMs based on the user's prompts.” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses mathematical concept of utilizing a mathematical formula to perform calculations. A human is able to apply known mathematical concepts and use mathematical algorithms to score, rate or identify the best LLM for a given prompt. This claim discloses a math operation and therefore is ineligible.
Step 2A Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application?
This claim does not recite any additional limitations which integrate the abstract idea into a practical application.
Step 2B – Does the claim recite additional elements that amount to significantly more than the judicial exception?
Finally, the claim taken as a whole does not contain an inventive concept which provides significantly more than the abstract idea and thus the claim is subject-matter ineligible.
Claim 5
Step 1 – Is the claim to a process, machine, manufacture or composition of matter?
A process, as above.
Step 2A Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The claim recites, inter alia:
“automatically selecting an optimal Large Language Model from the LLMs based on user prompts, contextual information associated with the user prompts, and characteristics of the enriched user prompt.” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate the results of an evaluation and make a judgment or opinion based on that evaluation. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
Step 2A Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application?
This claim does not recite any additional limitations which integrate the abstract idea into a practical application.
Step 2B – Does the claim recite additional elements that amount to significantly more than the judicial exception?
Finally, the claim taken as a whole does not contain an inventive concept which provides significantly more than the abstract idea and thus the claim is subject-matter ineligible.
Claim 6
Step 1 – Is the claim to a process, machine, manufacture or composition of matter?
A process, as above.
Step 2A Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The claim recites, inter alia:
“evaluating effectiveness of the tailored user prompts by integrating a feedback loop mechanism.” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate data and determine the effectiveness of the input data. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
Step 2A Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application?
This claim does not recite any additional limitations which integrate the abstract idea into a practical application.
Step 2B – Does the claim recite additional elements that amount to significantly more than the judicial exception?
Finally, the claim taken as a whole does not contain an inventive concept which provides significantly more than the abstract idea and thus the claim is subject-matter ineligible.
Claim 7
Step 1 – Is the claim to a process, machine, manufacture or composition of matter?
A process, as above.
Step 2A Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The claim recites the abstract ideas of the preceding claims from which it depends.
Step 2A Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application?
The claim recites the additional elements, “updating a model behavior database based on context provided by users and the evaluated effectiveness of the tailored user prompts.” amounts to generic computer components used as a tool to perform an existing process. Thus, the additional element amounts to no more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Step 2B – Does the claim recite additional elements that amount to significantly more than the judicial exception?
Finally, the claim taken as a whole does not contain an inventive concept which provides significantly more than the abstract idea. The additional elements, “updating a model behavior database based on context provided by users and the evaluated effectiveness of the tailored user prompts.” amounts to generic computer components used as a tool to perform an existing process. Thus, the additional element amounts to no more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Taken alone or in combination, the additional elements of the claim do not provide an inventive concept and thus the claim is subject-matter ineligible.
Claim 8
Step 1 – Is the claim to a process, machine, manufacture or composition of matter?
This claim is not directed to one of the four categories of statutory subject matter per MPEP 2106.03(I). However, for compact prosecution, the examiner will interpret this claim as falling under one of the four categories to further evaluate the claim using the Alice/Mayo test.
Step 2A Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The claim recites, inter alia:
“program instructions to analyze user prompts using one or more natural language understanding techniques;” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate user prompts using natural language understanding techniques. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
“program instructions to enrich the user prompts by integrating contextual data from user interaction history; and” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate a user prompt and add information to the prompt as judgement or opinion. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
“program instructions to adapt the enriched user prompts to align with characteristics of Large Language Models (LLMs) and Application Programming Interfaces (API) requirements of the LLMs.” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate a LLM model and the input requirements and, based on that evaluation, alter a prompt using judgement or opinion. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
Step 2A Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application?
The claim recites the additional elements, “one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions comprising:” amounts to generic computer components used as a tool to perform an existing process. Thus, the additional element amounts to no more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Step 2B – Does the claim recite additional elements that amount to significantly more than the judicial exception?
Finally, the claim taken as a whole does not contain an inventive concept which provides significantly more than the abstract idea. The additional elements, “one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions comprising:” amounts to generic computer components used as a tool to perform an existing process. Thus, the additional element amounts to no more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Taken alone or in combination, the additional elements of the claim do not provide an inventive concept and thus the claim is subject-matter ineligible.
Claim 9
Step 1 – Is the claim to a process, machine, manufacture or composition of matter?
This claim is not directed to one of the four categories of statutory subject matter per MPEP 2106.03(I). However, for compact prosecution, the examiner will interpret this claim as falling under one of the four categories to further evaluate the claim using the Alice/Mayo test.
Step 2A Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The claim recites, inter alia:
“program instructions to tailor the received user prompts for a respective LLM of the respective LLMs based on characteristics of each respective LLM.” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate a prompt and alter the prompt based on that evaluation using judgement or opinions. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
Step 2A Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application?
The claim recites the additional elements, “program instructions to collect received user prompts and contextual information associated with the received user prompts; and” is an insignificant extra-solution activity required for any uses of the mental processes (see MPEP § 2106.05(g)) As such, the claim is ineligible.
Step 2B – Does the claim recite additional elements that amount to significantly more than the judicial exception?
Finally, the claim taken as a whole does not contain an inventive concept which provides significantly more than the abstract idea. The additional elements, “program instructions to collect received user prompts and contextual information associated with the received user prompts; and” is an insignificant extra-solution activity required for any uses of abstract ideas (see MPEP § 2106.05(g)), and is a well-understood, routine, conventional activity (see MPEP § 2106.05(d)(II)(i); “Receiving or transmitting data over a network, e.g., using the Internet to gather data”.
Taken alone or in combination, the additional elements of the claim do not provide an inventive concept and thus the claim is subject-matter ineligible.
Claim 10
Step 1 – Is the claim to a process, machine, manufacture or composition of matter?
This claim is not directed to one of the four categories of statutory subject matter per MPEP 2106.03(I). However, for compact prosecution, the examiner will interpret this claim as falling under one of the four categories to further evaluate the claim using the Alice/Mayo test.
Step 2A Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The claim recites, inter alia:
“program instructions to format the tailored user prompts to align with the respective LLM.” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate a LLM input requirement and alter a given prompt based on this evaluation using judgement or opinions. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
Step 2A Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application?
This claim does not recite any additional limitations which integrate the abstract idea into a practical application.
Step 2B – Does the claim recite additional elements that amount to significantly more than the judicial exception?
Finally, the claim taken as a whole does not contain an inventive concept which provides significantly more than the abstract idea and thus the claim is subject-matter ineligible.
Claim 11
Step 1 – Is the claim to a process, machine, manufacture or composition of matter?
This claim is not directed to one of the four categories of statutory subject matter per MPEP 2106.03(I). However, for compact prosecution, the examiner will interpret this claim as falling under one of the four categories to further evaluate the claim using the Alice/Mayo test.
Step 2A Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The claim recites, inter alia:
“program instructions to categorize the enriched user prompts based on its characteristics into specific domains and styles using natural language processing;” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate a given prompt and assign it to a category. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
“program instructions to match the categorized prompts with a subset of LLMs of the respective LLMs by querying a model behavior database; and” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to identify patterns and evaluate matching information. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
“program instructions to algorithmically select an optimal LLM from the subset of LLMs based on the user's prompts.” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses mathematical concept of utilizing a mathematical formula to perform calculations. A human is able to apply known mathematical concepts and use mathematical algorithms to score, rate or identify the best LLM for a given prompt. This claim discloses a math operation and therefore is ineligible.
Step 2A Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application?
This claim does not recite any additional limitations which integrate the abstract idea into a practical application.
Step 2B – Does the claim recite additional elements that amount to significantly more than the judicial exception?
Finally, the claim taken as a whole does not contain an inventive concept which provides significantly more than the abstract idea and thus the claim is subject-matter ineligible.
Claim 12
Step 1 – Is the claim to a process, machine, manufacture or composition of matter?
This claim is not directed to one of the four categories of statutory subject matter per MPEP 2106.03(I). However, for compact prosecution, the examiner will interpret this claim as falling under one of the four categories to further evaluate the claim using the Alice/Mayo test.
Step 2A Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The claim recites, inter alia:
“program instructions to automatically select an optimal Large Language Model from the LLMs based on user prompts, contextual information associated with the user prompts, and characteristics of the enriched user prompt.” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate the results of an evaluation and make a judgment or opinion based on that evaluation. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
Step 2A Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application?
This claim does not recite any additional limitations which integrate the abstract idea into a practical application.
Step 2B – Does the claim recite additional elements that amount to significantly more than the judicial exception?
Finally, the claim taken as a whole does not contain an inventive concept which provides significantly more than the abstract idea and thus the claim is subject-matter ineligible.
Claim 13
Step 1 – Is the claim to a process, machine, manufacture or composition of matter?
This claim is not directed to one of the four categories of statutory subject matter per MPEP 2106.03(I). However, for compact prosecution, the examiner will interpret this claim as falling under one of the four categories to further evaluate the claim using the Alice/Mayo test.
Step 2A Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The claim recites, inter alia:
“program instructions to evaluate effectiveness of the tailored user prompts by integrating a feedback loop mechanism.” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate data and determine the effectiveness of the input data. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
Step 2A Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application?
This claim does not recite any additional limitations which integrate the abstract idea into a practical application.
Step 2B – Does the claim recite additional elements that amount to significantly more than the judicial exception?
Finally, the claim taken as a whole does not contain an inventive concept which provides significantly more than the abstract idea and thus the claim is subject-matter ineligible.
Claim 14
Step 1 – Is the claim to a process, machine, manufacture or composition of matter?
This claim is not directed to one of the four categories of statutory subject matter per MPEP 2106.03(I). However, for compact prosecution, the examiner will interpret this claim as falling under one of the four categories to further evaluate the claim using the Alice/Mayo test.
Step 2A Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The claim recites the abstract ideas of the preceding claims from which it depends.
Step 2A Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application?
The claim recites the additional elements, “program instructions to update a model behavior database based on context provided by users and the evaluated program instructions to effectiveness of the tailored user prompts.” amounts to generic computer components used as a tool to perform an existing process. Thus, the additional element amounts to no more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Step 2B – Does the claim recite additional elements that amount to significantly more than the judicial exception?
Finally, the claim taken as a whole does not contain an inventive concept which provides significantly more than the abstract idea. The additional elements, “program instructions to update a model behavior database based on context provided by users and the evaluated program instructions to effectiveness of the tailored user prompts.” amounts to generic computer components used as a tool to perform an existing process. Thus, the additional element amounts to no more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Taken alone or in combination, the additional elements of the claim do not provide an inventive concept and thus the claim is subject-matter ineligible.
Claim 15
Step 1 – Is the claim to a process, machine, manufacture or composition of matter?
Claim 15 recites, "A computer system comprising:" therefore it is directed to the statutory category of a machine.
Step 2A Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The claim recites, inter alia:
“program instructions to analyze user prompts using one or more natural language understanding techniques;” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate user prompts using natural language understanding techniques. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
“program instructions to enrich the user prompts by integrating contextual data from user interaction history; and” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate a user prompt and add information to the prompt as judgement or opinion. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
“program instructions to adapt the enriched user prompts to align with characteristics of Large Language Models (LLMs) and Application Programming Interfaces (API) requirements of the LLMs.” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate a LLM model and the input requirements and, based on that evaluation, alter a prompt using judgement or opinion. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
Step 2A Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application?
The claim recites the additional elements, “one or more computer processors; one or more computer readable storage media; and program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the program instructions comprising:” amounts to generic computer components used as a tool to perform an existing process. Thus, the additional element amounts to no more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Step 2B – Does the claim recite additional elements that amount to significantly more than the judicial exception?
Finally, the claim taken as a whole does not contain an inventive concept which provides significantly more than the abstract idea. The additional elements, “one or more computer processors; one or more computer readable storage media; and program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the program instructions comprising:” amounts to generic computer components used as a tool to perform an existing process. Thus, the additional element amounts to no more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Taken alone or in combination, the additional elements of the claim do not provide an inventive concept and thus the claim is subject-matter ineligible.
Claim 16
Step 1 – Is the claim to a process, machine, manufacture or composition of matter?
A machine, as above.
Step 2A Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The claim recites, inter alia:
“program instructions to tailor the received user prompts for a respective LLM of the respective LLMs based on characteristics of each respective LLM.” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate a prompt and alter the prompt based on that evaluation using judgement or opinions. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
Step 2A Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application?
The claim recites the additional elements, “program instructions to collect received user prompts and contextual information associated with the received user prompts; and” is an insignificant extra-solution activity required for any uses of the mental processes (see MPEP § 2106.05(g)) As such, the claim is ineligible.
Step 2B – Does the claim recite additional elements that amount to significantly more than the judicial exception?
Finally, the claim taken as a whole does not contain an inventive concept which provides significantly more than the abstract idea. The additional elements, “program instructions to collect received user prompts and contextual information associated with the received user prompts; and” is an insignificant extra-solution activity required for any uses of abstract ideas (see MPEP § 2106.05(g)), and is a well-understood, routine, conventional activity (see MPEP § 2106.05(d)(II)(i); “Receiving or transmitting data over a network, e.g., using the Internet to gather data”.
Taken alone or in combination, the additional elements of the claim do not provide an inventive concept and thus the claim is subject-matter ineligible.
Claim 17
Step 1 – Is the claim to a process, machine, manufacture or composition of matter?
A machine, as above.
Step 2A Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The claim recites, inter alia:
“program instructions to format the tailored user prompts to align with the respective LLM.” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate a LLM input requirement and alter a given prompt based on this evaluation using judgement or opinions. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
Step 2A Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application?
This claim does not recite any additional limitations which integrate the abstract idea into a practical application.
Step 2B – Does the claim recite additional elements that amount to significantly more than the judicial exception?
Finally, the claim taken as a whole does not contain an inventive concept which provides significantly more than the abstract idea and thus the claim is subject-matter ineligible.
Claim 18
Step 1 – Is the claim to a process, machine, manufacture or composition of matter?
A machine, as above.
Step 2A Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The claim recites, inter alia:
“program instructions to categorize the enriched user prompts based on its characteristics into specific domains and styles using natural language processing;” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate a given prompt and assign it to a category. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
“program instructions to match the categorized prompts with a subset of LLMs of the respective LLMs by querying a model behavior database; and” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to identify patterns and evaluate matching information. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
“program instructions to algorithmically select an optimal LLM from the subset of LLMs based on the user's prompts.” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses mathematical concept of utilizing a mathematical formula to perform calculations. A human is able to apply known mathematical concepts and use mathematical algorithms to score, rate or identify the best LLM for a given prompt. This claim discloses a math operation and therefore is ineligible.
Step 2A Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application?
This claim does not recite any additional limitations which integrate the abstract idea into a practical application.
Step 2B – Does the claim recite additional elements that amount to significantly more than the judicial exception?
Finally, the claim taken as a whole does not contain an inventive concept which provides significantly more than the abstract idea and thus the claim is subject-matter ineligible.
Claim 19
Step 1 – Is the claim to a process, machine, manufacture or composition of matter?
A machine, as above.
Step 2A Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The claim recites, inter alia:
“program instructions to automatically select an optimal Large Language Model from the LLMs based on user prompts, contextual information associated with the user prompts, and characteristics of the enriched user prompt.” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate the results of an evaluation and make a judgment or opinion based on that evaluation. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
Step 2A Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application?
This claim does not recite any additional limitations which integrate the abstract idea into a practical application.
Step 2B – Does the claim recite additional elements that amount to significantly more than the judicial exception?
Finally, the claim taken as a whole does not contain an inventive concept which provides significantly more than the abstract idea and thus the claim is subject-matter ineligible.
Claim 20
Step 1 – Is the claim to a process, machine, manufacture or composition of matter?
A machine, as above.
Step 2A Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The claim recites, inter alia:
“program instructions to evaluate effectiveness of the tailored user prompts by integrating a feedback loop mechanism” Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating and observing data, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. A human is able to evaluate data and determine the effectiveness of the input data. The limitation is merely applying an abstract idea on generic computer system. See MPEP 2106.04(a)(2)(III)(c).
Step 2A Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application?
This claim does not recite any additional limitations which integrate the abstract idea into a practical application.
Step 2B – Does the claim recite additional elements that amount to significantly more than the judicial exception?
Finally, the claim taken as a whole does not contain an inventive concept which provides significantly more than the abstract idea and thus the claim is subject-matter ineligible.
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 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Teng et al, (Teng et al, “CONTEXTUALIZED LANGUAGE MODEL PROMPT WITH SENSING HUB”, US 2025/0131190 A1, Filed Oct. 23rd, 2023, hereinafter “Teng”) in view of Somech et al, (Somech et al, “ENRICHING LANGUAGE MODEL INPUT WITH CONTEXTUAL DATA”, US 2024/0311563 A1, filed Jun. 2nd, 2023, hereinafter “Somech”).
Regarding claim 1, Teng discloses, “A computer-implemented method comprising:” (Detailed Description, pp. 2, [0019]; “Various embodiments include methods, and computing devices configured to implement the methods, of generating a prompt for a large generative AI model (LXM), such as a large language model (LLM), large speech model (LSMs), large/language vision model (LVM), hybrid model, multi-modal model, etc.” This application discloses a method that is able to evaluate and alter user prompts which are then input into LLM for further processing.)
“analyzing user prompts using one or more natural language understanding techniques;” (Detailed Description, pp. 9, [0076]; “The relevance determinator 212 may be configured to use machine learning models to scrutinize user prompts 232, identify contextually relevant tokens (words or phrases) that relate to lightweight user profile summary or user prompt 232, filter out irrelevant information, score or rank the identified tokens based on the degree to which they are relevant (e.g., to the user, to the user prompt 232, to improving response accuracy, etc.), and emphasize the identified contextually relevant tokens that could lead to more accurate or useful LLM responses.” The relevance determinator in this article is able to analyze user prompts using machine learning models. The ML models are disclosed as “robust language model(s)” (See Detailed Description, pp. 4, [0038]).
Teng fails to explicitly disclose:
“enriching the user prompts by integrating contextual data from user interaction history; and”
“adapting the enriched user prompts to align with characteristics of Large Language Models (LLMs) and Application Programming Interfaces (API) requirements of the LLMs.”
However, Somech discloses, “enriching the user prompts by integrating contextual data from user interaction history; and” (Detailed Description, pp. 2, [0021-0022]; “In an illustrative example, various embodiments first receive a corpus of text, such as a written meeting transcript that includes natural language characters indicating content spoken in a meeting. Some embodiments then determine contextual data associated with the corpus of text. For example, some embodiments determine metadata associated with the meeting, such as attendees of the meeting, date of the meeting, and agenda associated with the meeting by scanning emails, attachments, chats, SMS messages, or the like. [0022] Based on the contextual data, some embodiments then determine a corpus data supplement. In some embodiments, a "corpus data supplement" is data to be added within the corpus of text as input into a model.” This application discloses a process for enriching user prompts to receive improved results from an LLM. This discloses an example where the system can integrate metadata meeting which can include user interactions such as email data, chat information, etc.)
“adapting the enriched user prompts to align with characteristics of Large Language Models (LLMs) and Application Programming Interfaces (API) requirements of the LLMs.” (Detailed Description, pp. 16, [0118]; “In some embodiments, block 706 includes selecting or determining a portion (e.g., a particular quantity of tokens, data sources, or the like) of the contextual data to be included in the corpus data supplement based on relevance of the contextual data and/or an input size constraint of the machine learning model, as described herein. For example, if a model only has the capacity to ingest 1405 tokens, particular embodiments feed the model contextual data from the highest ranked---or most relevant-to the lowest ranked-the least relevant-until the 1405 token threshold is met.” This system is able to evaluate and alter a query with context data and modify the query to match the input requirements, or characteristics, of a selected LLM. This citation gives an example where the system modifies a user query to fit the constraints, or requirements, of a given LLM) and (Detailed Description, pp. 16-17, [0119]; “Continuing with FIG. 7, per block 708, based on the determining of the corpus data supplement, some embodiments provide the corpus of text and the corpus data supplement (which may be included within the corpus of text) as input into a machine learning model.” And “Block 708 can also include otherwise causing the corpus of text and the corpus data supplement to be used as input into the machine learning model, such as contacting various intermediate services that ultimately instruct such machine learning model to process the inputs.” Further, this system is able to send a user’s modified query to an LLM and is able to use models’ intermediate services, the API, to instruct a ML model to process the modified query.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Teng and Somech. Teng teaches a system that is able to generate a prompt for a LLM using a received prompt from a user and contextual data from different sources. Somech teaches a machine learning system that is able to receive user prompts and enrich the prompts with historical or corpus data. One of ordinary skill would have motivation to combine these inventions since both articles disclose a process of altering users queries, with contextual data, to a LLM to improve the effectiveness of a user’s query and to achieve better results from a LLM, “Various embodiments discussed herein are directed to providing a corpus data supplement (e.g., selected contextual data or metadata) as input into a model, such as a Large Language Model (LLM). Consequently, the model can generate accurate scores or data for predictions because the model is better able to distinguish between a general understanding of natural language concepts and domain specific (e.g., organizational) concepts. For example, "Red Sea" may be the name of an organization's project. A user may issue a query, such as "when is Red Sea due?" The model will interpret "Red Sea" to be an organization project name because a tag is embedded in a written meeting transcript next to the words "Red Sea," where the tag reads "[project name: business unit X],"-the corpus data supplement.” (Somech, Summary, pp. 1, [0003])
Regarding claim 2, Somech discloses, “collecting received user prompts and contextual information associated with the received user prompts; and” (Detailed Description, pp. 2, [0020]-[0021]; “In operation, some embodiments are directed to providing a corpus of text (e.g., a written document) and a corpus data supplement (e.g., metadata) as input into a machine learning model, such as an LLM. Consequently, the machine learning model can generate appropriate scores or data for predictions, such as answers to user questions, sentiment analysis, automatic summarization, text generation, machine translation, or document classification, among other use cases. [0021] In an illustrative example, various embodiments first receive a corpus of text, such as a written meeting transcript that includes natural language characters indicating content spoken in a meeting. Some embodiments then determine contextual data associated with the corpus of text. For example, some embodiments determine metadata associated with the meeting, such as attendees of the meeting, date of the meeting, and agenda associated with the meeting by scanning emails, attachments, chats, SMS messages, or the like.” This system is able to receive as input text from the user and perform general LLM functions. This example teaches the collection of user contextual data as well as user prompts for the LLM models to process.)
“tailoring the received user prompts for a respective LLM of the respective LLMs based on characteristics of each respective LLM.” (Detailed Description, pp. 16, [0118]; “In some embodiments, block 706 includes selecting or determining a portion (e.g., a particular quantity of tokens, data sources, or the like) of the contextual data to be included in the corpus data supplement based on relevance of the contextual data and/or an input size constraint of the machine learning model, as described herein. For example, if a model only has the capacity to ingest 1405 tokens, particular embodiments feed the model contextual data from the highest ranked---or most relevant-to the lowest ranked-the least relevant-until the 1405 token threshold is met.” This system is able to modify, or tailor, the users’ query to ensure it meets the input requirements, or characteristics, of the selected machine learning model. This citation gives an example of modifying a prompt to meet the computational characteristics of the selected LLM.)
Regarding claim 3, Teng discloses, “formatting the tailored user prompts to align with the respective LLM.” (Detailed Description, pp. 8, [0066]; “For example, the contextualized prompt generator 202 may be a large language model trained to generate an LXM prompt for the Cloud-LXM 203 (or a selected LXM, etc.) to include information phrased in a manner that will cause the Cloud-LXM 203 (or the selected LXM, etc.) to generate a reply that is responsive to the received user prompt 232 based on knowledge of how the Cloud-LXM 203 (or the selected LXM, etc.) responds to prompt rhetoric. The "prompt rhetoric" may refer to instructions or information that is crafted or selected strategically for an LXM.” This system is able to format the altered user prompt to match the selected LLM to receive improved results from the selected model.)
Regarding claim 4, Teng discloses, “categorizing the enriched user prompts based on its characteristics into specific domains and styles using natural language processing;” (Detailed Description, pp. 12, [0118]; “In block 352, the at least one processor may process the received user prompt by a language model that is trained to identify a category of subject matter in the received user prompt. For example, the at least one processor may prompt a specialized language model that is trained to categorize the subject matter of a received user prompt.” This system is able to process user queries and categorize them based on the characteristics of the prompt using a trained language model.)
“matching the categorized prompts with a subset of LLMs of the respective LLMs by querying a model behavior database; and” (Detailed Description, pp. 12-13, [0120]; “In block 354, the at least one processor may use the identified subject matter category to select an LXM from a plurality of available LXM models to which the prompt will be applied. For example, the at least one processor may select and use an LXM trained on culinary information in response to categorizing a user prompt that asks "How can I cook a turkey?" under "Cooking" or "Food Preparation."” This system is able to match subject matter of the prompt to a LLM designed to best handle the prompt. This system has access to a storage of LLM’s (see Fig. 2A, Reference Numbers: 214 and 203) and is able to search this storage, or database, to select the best LLM within a set of LLMs)
“algorithmically selecting an optimal LLM from the subset of LLMs based on the user's prompts.” (Detailed Description, pp. 12, [0116]; “For example, the at least one processor may select an LXM based on various factors in the user context information, including as the physical context of the user. The at least one processor may correlate the physical context with the capabilities and specialties of the available LXMs to improve the LXM output. In some embodiments, the operations in blocks 342 and 344 may be performed using sample outputs 268 to select an LXM and output the generated contextualized prompt illustrated and described with reference to FIGS. 2A-2F.” This system is able to correlate information to determine which LLM would produce the best output for the generated prompt. This citation discloses that context data may be correlated, or compared in some algorithmic function, to select the best LLM for the generated prompt.)
Regarding claim 5, Teng discloses, “automatically selecting an optimal Large Language Model from the LLMs based on user prompts, contextual information associated with the user prompts, and characteristics of the enriched user prompt.” (Detailed Description, pp. 12, [0116]; “In blocks 342 and 344, the at least one processor may select an LXM from a plurality of available LXM models based on the physical context of the user in the user context information and output the generated contextualized prompt to the selected LXM. For example, the at least one processor may select an LXM based on various factors in the user context information, including as the physical context of the user.” This system is able to select a LLM based on the given information which includes contextual data and user prompts. This discloses a system that is able to evaluate multiple forms of input data and determine which LLM would be used to produce the best output.)
Regarding claim 6, Teng discloses, “evaluating effectiveness of the tailored user prompts by integrating a feedback loop mechanism.” (Detailed Description, pp. 10, [0091]; “The score computation and re-ranking 266 component may be configured to evaluate the suitability of various model outputs based on user feedback and other context indicators, which may be used in future interactions to better prioritize model outputs. For example, the score computation and re-ranking 266 component may score, rank, or re-rank tokens based on the degree to which they are relevant (e.g., to the user, to the user prompt, to improving response accuracy, etc.).” This system can use user feedback of the models’ outputs to train and improve generated prompts.)
Regarding claim 7, Teng discloses, “updating a model behavior database based on context provided by users and the evaluated effectiveness of the tailored user prompts.” (Detailed Description, pp. 9, [0076]; “The relevance determinator 212 may be configured to use machine learning models to scrutinize user prompts 232, identify contextually relevant tokens (words or phrases) that relate to lightweight user profile summary or user prompt 232, filter out irrelevant information, score or rank the identified tokens based on the degree to which they are relevant (e.g., to the user, to the user prompt 232, to improving response accuracy, etc.), and emphasize the identified contextually relevant tokens that could lead to more accurate or useful LLM responses. In some embodiments, the machine learning models may be trained through supervised, few-shot, or zero-shot approaches. In supervised training, labels are predicted as the output based on a defined dataset. Few-shot training provides a few examples to aid in better label prediction for similar future queries. Zero-shot training utilizes pre-trained models to generalize to unseen categories.” This system is able to use feedback from a user to update models used to evaluate and generate the user prompts. As stated these models can be trained or updated using common machine learning training frameworks such as supervised learning. This discloses that multiple models, which are stored in a database, can be updated and this in turn would update the database of model.)
Regarding claim 8, Teng discloses, “A computer program product comprising: one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions comprising:” (Detailed Description, pp. 17, [0172]; “In one or more embodiments, the functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored as one or more instructions or code on a non-transitory computer-readable medium or non-transitory processor-readable medium. The operations of a method or algorithm disclosed herein may be embodied in a processor-executable software module, which may reside on a non-transitory computer-readable or processor- readable storage medium.” This application discloses a system that uses machine instructions that are stored on a non-transitory medium to be used by system processors to execute the given methods and functions.)
“program instructions to analyze user prompts using one or more natural language understanding techniques;” (Detailed Description, pp. 9, [0076]; “The relevance determinator 212 may be configured to use machine learning models to scrutinize user prompts 232, identify contextually relevant tokens (words or phrases) that relate to lightweight user profile summary or user prompt 232, filter out irrelevant information, score or rank the identified tokens based on the degree to which they are relevant (e.g., to the user, to the user prompt 232, to improving response accuracy, etc.), and emphasize the identified contextually relevant tokens that could lead to more accurate or useful LLM responses.” The relevance determinator in this article is able to analyze user prompts using machine learning models. The ML models are disclosed as “robust language model(s)” (See Detailed Description, pp. 4, [0038]).
Teng fails to explicitly disclose:
“program instructions to enrich the user prompts by integrating contextual data from user interaction history; and”
“program instructions to adapt the enriched user prompts to align with characteristics of Large Language Models (LLMs) and Application Programming Interfaces (API) requirements of the LLMs.”
However, Somech discloses, “program instructions to enrich the user prompts by integrating contextual data from user interaction history; and” (Detailed Description, pp. 2, [0021-0022]; “In an illustrative example, various embodiments first receive a corpus of text, such as a written meeting transcript that includes natural language characters indicating content spoken in a meeting. Some embodiments then determine contextual data associated with the corpus of text. For example, some embodiments determine metadata associated with the meeting, such as attendees of the meeting, date of the meeting, and agenda associated with the meeting by scanning emails, attachments, chats, SMS messages, or the like. [0022] Based on the contextual data, some embodiments then determine a corpus data supplement. In some embodiments, a "corpus data supplement" is data to be added within the corpus of text as input into a model.” This application discloses a process for enriching user prompts to receive improved results from an LLM. This discloses an example where the system can integrate metadata meeting which can include user interactions such as email data, chat information, etc.)
“program instructions to adapt the enriched user prompts to align with characteristics of Large Language Models (LLMs) and Application Programming Interfaces (API) requirements of the LLMs.” (Detailed Description, pp. 16, [0118]; “In some embodiments, block 706 includes selecting or determining a portion (e.g., a particular quantity of tokens, data sources, or the like) of the contextual data to be included in the corpus data supplement based on relevance of the contextual data and/or an input size constraint of the machine learning model, as described herein. For example, if a model only has the capacity to ingest 1405 tokens, particular embodiments feed the model contextual data from the highest ranked---or most relevant-to the lowest ranked-the least relevant-until the 1405 token threshold is met.” This system is able to evaluate and alter a query with context data and modify the query to match the input requirements, or characteristics, of a selected LLM. This citation gives an example where the system modifies a user query to fit the constraints, or requirements, of a given LLM) and (Detailed Description, pp. 16-17, [0119]; “Continuing with FIG. 7, per block 708, based on the determining of the corpus data supplement, some embodiments provide the corpus of text and the corpus data supplement (which may be included within the corpus of text) as input into a machine learning model.” And “Block 708 can also include otherwise causing the corpus of text and the corpus data supplement to be used as input into the machine learning model, such as contacting various intermediate services that ultimately instruct such machine learning model to process the inputs.” Further, this system is able to send a user’s modified query to an LLM and is able to use models’ intermediate services, the API, to instruct a ML model to process the modified query.)
Regarding claim 9, Somech discloses, “program instructions to collect received user prompts and contextual information associated with the received user prompts; and” (Detailed Description, pp. 2, [0020]-[0021]; “In operation, some embodiments are directed to providing a corpus of text (e.g., a written document) and a corpus data supplement (e.g., metadata) as input into a machine learning model, such as an LLM. Consequently, the machine learning model can generate appropriate scores or data for predictions, such as answers to user questions, sentiment analysis, automatic summarization, text generation, machine translation, or document classification, among other use cases. [0021] In an illustrative example, various embodiments first receive a corpus of text, such as a written meeting transcript that includes natural language characters indicating content spoken in a meeting. Some embodiments then determine contextual data associated with the corpus of text. For example, some embodiments determine metadata associated with the meeting, such as attendees of the meeting, date of the meeting, and agenda associated with the meeting by scanning emails, attachments, chats, SMS messages, or the like.” This system is able to receive as input text from the user and perform general LLM functions. This example teaches the collection of user contextual data as well as user prompts for the LLM models to process.)
“program instructions to tailor the received user prompts for a respective LLM of the respective LLMs based on characteristics of each respective LLM.” (Detailed Description, pp. 16, [0118]; “In some embodiments, block 706 includes selecting or determining a portion (e.g., a particular quantity of tokens, data sources, or the like) of the contextual data to be included in the corpus data supplement based on relevance of the contextual data and/or an input size constraint of the machine learning model, as described herein. For example, if a model only has the capacity to ingest 1405 tokens, particular embodiments feed the model contextual data from the highest ranked---or most relevant-to the lowest ranked-the least relevant-until the 1405 token threshold is met.” This system is able to modify, or tailor, the users’ query to ensure it meets the input requirements, or characteristics, of the selected machine learning model. This citation gives an example of modifying a prompt to meet the computational characteristics of the selected LLM.)
Regarding claim 10, Teng discloses, “program instructions to format the tailored user prompts to align with the respective LLM.” (Detailed Description, pp. 8, [0066]; “For example, the contextualized prompt generator 202 may be a large language model trained to generate an LXM prompt for the Cloud-LXM 203 (or a selected LXM, etc.) to include information phrased in a manner that will cause the Cloud-LXM 203 (or the selected LXM, etc.) to generate a reply that is responsive to the received user prompt 232 based on knowledge of how the Cloud-LXM 203 (or the selected LXM, etc.) responds to prompt rhetoric. The "prompt rhetoric" may refer to instructions or information that is crafted or selected strategically for an LXM.” This system is able to format the altered user prompt to match the selected LLM to receive improved results from the selected model.)
Regarding claim 11, Teng discloses, “program instructions to categorize the enriched user prompts based on its characteristics into specific domains and styles using natural language processing;” (Detailed Description, pp. 12, [0118]; “In block 352, the at least one processor may process the received user prompt by a language model that is trained to identify a category of subject matter in the received user prompt. For example, the at least one processor may prompt a specialized language model that is trained to categorize the subject matter of a received user prompt.” This system is able to process user queries and categorize them based on the characteristics of the prompt using a trained language model.)
“program instructions to match the categorized prompts with a subset of LLMs of the respective LLMs by querying a model behavior database; and” (Detailed Description, pp. 12-13, [0120]; “In block 354, the at least one processor may use the identified subject matter category to select an LXM from a plurality of available LXM models to which the prompt will be applied. For example, the at least one processor may select and use an LXM trained on culinary information in response to categorizing a user prompt that asks "How can I cook a turkey?" under "Cooking" or "Food Preparation."” This system is able to match subject matter of the prompt to a LLM designed to best handle the prompt. This system has access to a storage of LLM’s (see Fig. 2A, Reference Numbers: 214 and 203) and is able to search this storage, or database, to select the best LLM within a set of LLMs)
“program instructions to algorithmically select an optimal LLM from the subset of LLMs based on the user's prompts.” (Detailed Description, pp. 12, [0116]; “For example, the at least one processor may select an LXM based on various factors in the user context information, including as the physical context of the user. The at least one processor may correlate the physical context with the capabilities and specialties of the available LXMs to improve the LXM output. In some embodiments, the operations in blocks 342 and 344 may be performed using sample outputs 268 to select an LXM and output the generated contextualized prompt illustrated and described with reference to FIGS. 2A-2F.” This system is able to correlate information to determine which LLM would produce the best output for the generated prompt. This citation discloses that context data may be correlated, or compared in some algorithmic function, to select the best LLM for the generated prompt.)
Regarding claim 12, Teng discloses, “program instructions to automatically select an optimal Large Language Model from the LLMs based on user prompts, contextual information associated with the user prompts, and characteristics of the enriched user prompt.” (Detailed Description, pp. 12, [0116]; “In blocks 342 and 344, the at least one processor may select an LXM from a plurality of available LXM models based on the physical context of the user in the user context information and output the generated contextualized prompt to the selected LXM. For example, the at least one processor may select an LXM based on various factors in the user context information, including as the physical context of the user.” This system is able to select a LLM based on the given information which includes contextual data and user prompts. This discloses a system that is able to evaluate multiple forms of input data and determine which LLM would be used to produce the best output.)
Regarding claim 13, Teng discloses, “program instructions to evaluate effectiveness of the tailored user prompts by integrating a feedback loop mechanism.” (Detailed Description, pp. 10, [0091]; “The score computation and re-ranking 266 component may be configured to evaluate the suitability of various model outputs based on user feedback and other context indicators, which may be used in future interactions to better prioritize model outputs. For example, the score computation and re-ranking 266 component may score, rank, or re-rank tokens based on the degree to which they are relevant (e.g., to the user, to the user prompt, to improving response accuracy, etc.).” This system can use user feedback of the models’ outputs to train and improve generated prompts.)
Regarding claim 14, Teng discloses, “program instructions to update a model behavior database based on context provided by users and the evaluated program instructions to effectiveness of the tailored user prompts.” (Detailed Description, pp. 9, [0076]; “The relevance determinator 212 may be configured to use machine learning models to scrutinize user prompts 232, identify contextually relevant tokens (words or phrases) that relate to lightweight user profile summary or user prompt 232, filter out irrelevant information, score or rank the identified tokens based on the degree to which they are relevant (e.g., to the user, to the user prompt 232, to improving response accuracy, etc.), and emphasize the identified contextually relevant tokens that could lead to more accurate or useful LLM responses. In some embodiments, the machine learning models may be trained through supervised, few-shot, or zero-shot approaches. In supervised training, labels are predicted as the output based on a defined dataset. Few-shot training provides a few examples to aid in better label prediction for similar future queries. Zero-shot training utilizes pre-trained models to generalize to unseen categories.” This system is able to use feedback from a user to update models used to evaluate and generate the user prompts. As stated these models can be trained or updated using common machine learning training frameworks such as supervised learning. This discloses that multiple models, which are stored in a database, can be updated and this in turn would update the database of model.)
Regarding claim 15, Teng discloses, “A computer system comprising: one or more computer processors; one or more computer readable storage media; and program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the program instructions comprising:” (Detailed Description, pp. 17, [0171]; “The hardware used to implement the various illustrative logics, logical blocks, modules, and circuits described in connection with the embodiments disclosed herein may be implemented or performed with a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (TCUASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but, in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.” This application is designed to execute using generic computing methods and hardware. This system uses a generic computing systems containing processors, memory and other electronics to execute the methods and functions stored within memory.)
“program instructions to analyze user prompts using one or more natural language understanding techniques;” (Detailed Description, pp. 9, [0076]; “The relevance determinator 212 may be configured to use machine learning models to scrutinize user prompts 232, identify contextually relevant tokens (words or phrases) that relate to lightweight user profile summary or user prompt 232, filter out irrelevant information, score or rank the identified tokens based on the degree to which they are relevant (e.g., to the user, to the user prompt 232, to improving response accuracy, etc.), and emphasize the identified contextually relevant tokens that could lead to more accurate or useful LLM responses.” The relevance determinator in this article is able to analyze user prompts using machine learning models. The ML models are disclosed as “robust language model(s)” (See Detailed Description, pp. 4, [0038]).
Teng fails to explicitly disclose:
“program instructions to enrich the user prompts by integrating contextual data from user interaction history; and”
“program instructions to adapt the enriched user prompts to align with characteristics of Large Language Models (LLMs) and Application Programming Interfaces (API) requirements of the LLMs.”
However, Somech discloses, “program instructions to enrich the user prompts by integrating contextual data from user interaction history; and” (Detailed Description, pp. 2, [0021-0022]; “In an illustrative example, various embodiments first receive a corpus of text, such as a written meeting transcript that includes natural language characters indicating content spoken in a meeting. Some embodiments then determine contextual data associated with the corpus of text. For example, some embodiments determine metadata associated with the meeting, such as attendees of the meeting, date of the meeting, and agenda associated with the meeting by scanning emails, attachments, chats, SMS messages, or the like. [0022] Based on the contextual data, some embodiments then determine a corpus data supplement. In some embodiments, a "corpus data supplement" is data to be added within the corpus of text as input into a model.” This application discloses a process for enriching user prompts to receive improved results from an LLM. This discloses an example where the system can integrate metadata meeting which can include user interactions such as email data, chat information, etc.)
“program instructions to adapt the enriched user prompts to align with characteristics of Large Language Models (LLMs) and Application Programming Interfaces (API) requirements of the LLMs.” (Detailed Description, pp. 16, [0118]; “In some embodiments, block 706 includes selecting or determining a portion (e.g., a particular quantity of tokens, data sources, or the like) of the contextual data to be included in the corpus data supplement based on relevance of the contextual data and/or an input size constraint of the machine learning model, as described herein. For example, if a model only has the capacity to ingest 1405 tokens, particular embodiments feed the model contextual data from the highest ranked---or most relevant-to the lowest ranked-the least relevant-until the 1405 token threshold is met.” This system is able to evaluate and alter a query with context data and modify the query to match the input requirements, or characteristics, of a selected LLM. This citation gives an example where the system modifies a user query to fit the constraints, or requirements, of a given LLM) and (Detailed Description, pp. 16-17, [0119]; “Continuing with FIG. 7, per block 708, based on the determining of the corpus data supplement, some embodiments provide the corpus of text and the corpus data supplement (which may be included within the corpus of text) as input into a machine learning model.” And “Block 708 can also include otherwise causing the corpus of text and the corpus data supplement to be used as input into the machine learning model, such as contacting various intermediate services that ultimately instruct such machine learning model to process the inputs.” Further, this system is able to send a user’s modified query to an LLM and is able to use models’ intermediate services, the API, to instruct a ML model to process the modified query.)
Regarding claim 16, Somech discloses, “program instructions to collect received user prompts and contextual information associated with the received user prompts; and” (Detailed Description, pp. 2, [0020]-[0021]; “In operation, some embodiments are directed to providing a corpus of text (e.g., a written document) and a corpus data supplement (e.g., metadata) as input into a machine learning model, such as an LLM. Consequently, the machine learning model can generate appropriate scores or data for predictions, such as answers to user questions, sentiment analysis, automatic summarization, text generation, machine translation, or document classification, among other use cases. [0021] In an illustrative example, various embodiments first receive a corpus of text, such as a written meeting transcript that includes natural language characters indicating content spoken in a meeting. Some embodiments then determine contextual data associated with the corpus of text. For example, some embodiments determine metadata associated with the meeting, such as attendees of the meeting, date of the meeting, and agenda associated with the meeting by scanning emails, attachments, chats, SMS messages, or the like.” This system is able to receive as input text from the user and perform general LLM functions. This example teaches the collection of user contextual data as well as user prompts for the LLM models to process.)
“program instructions to tailor the received user prompts for a respective LLM of the respective LLMs based on characteristics of each respective LLM.” (Detailed Description, pp. 16, [0118]; “In some embodiments, block 706 includes selecting or determining a portion (e.g., a particular quantity of tokens, data sources, or the like) of the contextual data to be included in the corpus data supplement based on relevance of the contextual data and/or an input size constraint of the machine learning model, as described herein. For example, if a model only has the capacity to ingest 1405 tokens, particular embodiments feed the model contextual data from the highest ranked---or most relevant-to the lowest ranked-the least relevant-until the 1405 token threshold is met.” This system is able to modify, or tailor, the users’ query to ensure it meets the input requirements, or characteristics, of the selected machine learning model. This citation gives an example of modifying a prompt to meet the computational characteristics of the selected LLM.)
Regarding claim 17, Teng discloses, “program instructions to format the tailored user prompts to align with the respective LLM.” (Detailed Description, pp. 8, [0066]; “For example, the contextualized prompt generator 202 may be a large language model trained to generate an LXM prompt for the Cloud-LXM 203 (or a selected LXM, etc.) to include information phrased in a manner that will cause the Cloud-LXM 203 (or the selected LXM, etc.) to generate a reply that is responsive to the received user prompt 232 based on knowledge of how the Cloud-LXM 203 (or the selected LXM, etc.) responds to prompt rhetoric. The "prompt rhetoric" may refer to instructions or information that is crafted or selected strategically for an LXM.” This system is able to format the altered user prompt to match the selected LLM to receive improved results from the selected model.)
Regarding claim 18, Teng discloses, “program instructions to categorize the enriched user prompts based on its characteristics into specific domains and styles using natural language processing;” (Detailed Description, pp. 12, [0118]; “In block 352, the at least one processor may process the received user prompt by a language model that is trained to identify a category of subject matter in the received user prompt. For example, the at least one processor may prompt a specialized language model that is trained to categorize the subject matter of a received user prompt.” This system is able to process user queries and categorize them based on the characteristics of the prompt using a trained language model.)
“program instructions to match the categorized prompts with a subset of LLMs of the respective LLMs by querying a model behavior database; and” (Detailed Description, pp. 12-13, [0120]; “In block 354, the at least one processor may use the identified subject matter category to select an LXM from a plurality of available LXM models to which the prompt will be applied. For example, the at least one processor may select and use an LXM trained on culinary information in response to categorizing a user prompt that asks "How can I cook a turkey?" under "Cooking" or "Food Preparation."” This system is able to match subject matter of the prompt to a LLM designed to best handle the prompt. This system has access to a storage of LLM’s (see Fig. 2A, Reference Numbers: 214 and 203) and is able to search this storage, or database, to select the best LLM within a set of LLMs)
“program instructions to algorithmically select an optimal LLM from the subset of LLMs based on the user's prompts.” (Detailed Description, pp. 12, [0116]; “For example, the at least one processor may select an LXM based on various factors in the user context information, including as the physical context of the user. The at least one processor may correlate the physical context with the capabilities and specialties of the available LXMs to improve the LXM output. In some embodiments, the operations in blocks 342 and 344 may be performed using sample outputs 268 to select an LXM and output the generated contextualized prompt illustrated and described with reference to FIGS. 2A-2F.” This system is able to correlate information to determine which LLM would produce the best output for the generated prompt. This citation discloses that context data may be correlated, or compared in some algorithmic function, to select the best LLM for the generated prompt.)
Regarding claim 19, Teng discloses, “program instructions to automatically select an optimal Large Language Model from the LLMs based on user prompts, contextual information associated with the user prompts, and characteristics of the enriched user prompt.” (Detailed Description, pp. 12, [0116]; “In blocks 342 and 344, the at least one processor may select an LXM from a plurality of available LXM models based on the physical context of the user in the user context information and output the generated contextualized prompt to the selected LXM. For example, the at least one processor may select an LXM based on various factors in the user context information, including as the physical context of the user.” This system is able to select a LLM based on the given information which includes contextual data and user prompts. This discloses a system that is able to evaluate multiple forms of input data and determine which LLM would be used to produce the best output.)
Regarding claim 20, Teng discloses, “program instructions to evaluate effectiveness of the tailored user prompts by integrating a feedback loop mechanism.” (Detailed Description, pp. 10, [0091]; “The score computation and re-ranking 266 component may be configured to evaluate the suitability of various model outputs based on user feedback and other context indicators, which may be used in future interactions to better prioritize model outputs. For example, the score computation and re-ranking 266 component may score, rank, or re-rank tokens based on the degree to which they are relevant (e.g., to the user, to the user prompt, to improving response accuracy, etc.).” This system can use user feedback of the models’ outputs to train and improve generated prompts.)
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PAUL MICHAEL GALVIN-SIEBENALER whose telephone number is (571)272-1257. The examiner can normally be reached Monday - Friday 8AM to 5PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Viker Lamardo can be reached at (571) 270-5871. 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.
/PAUL M GALVIN-SIEBENALER/Examiner, Art Unit 2147
/VIKER A LAMARDO/Supervisory Patent Examiner, Art Unit 2147
Prosecution Insights