DETAILED ACTION
1. This is a Non-Final Office Action Correspondence in response to U.S. Application No. 18/936539 filed on June 23, 2025.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.
Notice of Pre-AIA or AIA Status
2. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Arguments
3. Applicants’ arguments have been considered but are not persuasive.
On pgs. 7 in regards to 35 U.S.C. 101, relating to claim 1, Applicant argues the amended claims, “To improve prompts for language models, excerpts can be extracted from relevant documents to filter out irrelevant information. The excerpts can be ranked based on relevancy to further identify relevant information, and a prompt can be generated with one or more of the excerpts.”
Examiner replies that this concept is still an abstract idea. The claim language does not recite limitations that detail a detailed process of a large language model extracting the irrelevant information. This would include the process of how irrelevant information is removed. Without this detail a human can look at information and extract mentally only the part of the information that is important to the human.
On pgs. 8-9 in regards to 35 U.S.C. 101, relating to claim 1, Applicant argues the amended claims, “The Office Action found that the original claim merely linked abstract concepts to the technological environment of language models without describing how the technology accomplishes the result. The amendments address this concern by explaining the mechanism and purpose of the claimed steps. The amended claim 1 now recites that the extracting step filters irrelevant information from the set of documents to reduce confusion of a language model. This is not a generic statement that the method involves a language model. Instead, it indicates that the filtering operation is specifically designed to address a characteristic of how language models process information (their susceptibility to confusion from irrelevant context). These amendments demonstrate that the claimed method is not simply applying abstract data organization concepts in a generic technological environment. Instead, the method is specifically tailored to the operational characteristics of language models and RAG systems. The filtering is performed because language models become confused by irrelevant information”.
Examiner replies that this concept is still an insignificant activity. Sending data to a large language model is seen as insignificant activities. The large language model is just processing the data that is received. Since the goal is to reduce large language model confusion, the focus should be on how and what information is removed during the extracting process, so when the large language model receives the processed data, it is able to process it in a less confusing manner.
On pgs. 10 in regards to 35 U.S.C. 101, relating to claim 1, Applicant argues the amended claims “Further, the ordered combination recited in amended Claim 1 amounts to significantly more than any abstract idea. The claim recites a specific process: retrieving documents, extracting and filtering excerpts to reduce LLM confusion, ranking the filtered excerpts, and augmenting the query to improve accuracy. This ordered combination is specifically designed to address the technical problem of language model confusion in RAG systems and achieves concrete improvements in system performance. Even if individual claim elements are conventional, the ordered combination may be unconventional and provide an inventive concept. While document retrieval and ranking may be known concepts, the specific combination of retrieving documents, filtering irrelevant information to reduce LLM confusion, ranking the filtered excerpts, and augmenting queries to improve language model accuracy represents an unconventional ordered combination tailored to RAG systems.”
Examiner replies that this combination is still an abstract idea that contains insignificant activities. In particular the claimed invention focuses on retrieving documents based upon a query, extracting information from the documents, ranking the information that is extracted from the documents, and then augmenting the query based upon the extract information. This is something a human can do with a pen and paper. Once a set of information is received the information can be provided to a large language model which is an insignificant activity. Applicant can amend the claim to clarify how the information is extracted and how the rankings occur based upon their relevancy to the query. The Applicant can also amend how the query is augmented based upon excerpts and how a prompt is formed to be provided to a language model.
On pgs. 11-12 in regards to 35 U.S.C. 103, relating to claim 1, Applicant argues the amended claims.
Examiner replies that a new reference was introduced to teach the amended limitations.
Claim Rejections - 35 U.S.C. §101
35 U.S.C. §101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
4. Claims 1-12 and 13-21 are rejected under 35 USC 101 as directed to an abstract idea without significantly more.
With respect to Step 1, the claims are directed to a computer-implemented method.
With respect to Step 2A Prong one independent claim, 1, specifically claim 1 recites, “performing, by the device, a ranking of the excerpts based on their relevancy to the input query” in the context of this claim encompasses the user mentally identifying different segments and placing rank on the segment. These limitations could be reasonably and practically performed by the human mind, for instance based on a human can ranking sections of text. Accordingly, the claim recites a mental process, which can be done utilizing pen and paper.
Accordingly, the claim recites an abstract idea.
Step 2A Prong Two the claims do not recite additional elements that integrate the judicial exception into a practical application.
The independent claim of 1 recites elements to be mere instructions to apply an exception, because they recite no more than an idea of a solution or outcome:
For example "retrieving, by a device, a set of documents based on their relevancy to an input query from a user interface” is seen as insignificant extra activities.
For example, “extracting, by the device, excerpts of varying sizes from the set of documents that are relevant to the input query, wherein the extracting filters information irrelevant to the input query from the set of documents” is seen as MPEP 2106.05(g) iv. Obtaining information about transactions using the Internet to verify credit card transactions, CyberSource v. Retail Decisions, Inc., 654 F.3d 1366, 1375, 99 USPQ2d 1690, 1694 (Fed. Cir. 2011);
For example, “and augmenting, by the device and based on the ranking, the input query based on one or more of the excerpts to form a prompt for input to a language model” is seen as MPEP 2106.05(g) i. Remotely accessing user-specific information through a mobile interface and pointers to retrieve the information without any description of how the mobile interface and pointers accomplish the result of retrieving previously inaccessible information, Intellectual Ventures v. Erie Indem. Co., 850 F.3d 1315, 1331, 121 USPQ2d 1928, 1939 (Fed. Cir. 2017);As discussed above with respect to integration of the abstract idea into a practical application, the additional elements are insignificant extra-solution activity. MPEP 2106.05(d)(II)(i).
This judicial exception is not integrated into a practical application. At step 2B, the claim recites "retrieving, by a device, a set of documents based on their relevancy to an input query from a user interface”, “extracting, by the device, excerpts of varying sizes from the set of documents that are relevant to the input query, wherein the extracting filters information irrelevant to the input query from the set of documents”, “and augmenting, by the device and based on the ranking, the input query based on one or more of the excerpts to form a prompt for input to a language model”.
For example, "retrieving, by a device, a set of documents based on their relevancy to an input query from a user interface”, is seen as insignificant extra activities.
For example, “extracting, by the device, excerpts of varying sizes from the set of documents that are relevant to the input query, wherein the extracting filters information irrelevant to the input query from the set of documents” do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The additional elements are a step of transmitting data, and is recognized as well understood, routine, and conventional activity within the field of computer functions as an element of receiving or transmitting data over a network (MPEP 2106.05(d)(II)(i)).
For example, “and augmenting, by the device and based on the ranking, the input query based on one or more of the excerpts to form a prompt for input to a language model” do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The additional elements are a step of transmitting data, and is recognized as well understood, routine, and conventional activity within the field of computer functions as an element of receiving or transmitting data over a network (MPEP 2106.05(d)(II)(iv)).
With respect to Step 1, the claims are directed to a computer-implemented method.
With respect to Step 2A Prong one dependent claim, 2, specifically claim 2 recites no new abstract ideas
Accordingly, the claim recites an abstract idea.
Step 2A Prong Two the claims do not recite additional elements that integrate the judicial exception into a practical application.
The dependent claim of 2 recites elements to be mere instructions to apply an exception, because they recite no more than an idea of a solution or outcome that is not an improvement to the functioning of a computer or to another technology:
For example “wherein the language model is a large language model (LLM)” is seen as MPEP 2106.05(f) i. Remotely accessing user-specific information through a mobile interface and pointers to retrieve the information without any description of how the mobile interface and pointers accomplish the result of retrieving previously inaccessible information, Intellectual Ventures v. Erie Indem. Co., 850 F.3d 1315, 1331, 121 USPQ2d 1928, 1939 (Fed. Cir. 2017);
This judicial exception is not integrated into a practical application. At step 2B, the claim recites “wherein the language model is a large language model (LLM)”.
For example, “wherein the language model is a large language model (LLM)”, is seen as computer functions that are well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality). MPEP 2106.05(d); (II), (ii).
With respect to Step 1, the claims are directed to a computer-implemented method.
With respect to Step 2A Prong one dependent claim, 3, specifically claim 3 recites no new abstract ideas
Accordingly, the claim recites an abstract idea.
Step 2A Prong Two the claims do not recite additional elements that integrate the judicial exception into a practical application.
The dependent claim of 3 recites elements to be mere instructions to apply an exception, because they recite no more than an idea of a solution or outcome that is not an improvement to the functioning of a computer or to another technology:
For example “providing, by the device and to a user interface, an output generated by the language model in response to the prompt” is seen as insignificant extra activities.
This judicial exception is not integrated into a practical application. At step 2B, the claim recites “providing, by the device and to a user interface, an output generated by the language model in response to the prompt”.
For example, “providing, by the device and to a user interface, an output generated by the language model in response to the prompt”, is seen as computer functions that are well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality). MPEP 2106.05(d); (II), (iv).
With respect to Step 1, the claims are directed to a computer-implemented method.
With respect to Step 2A Prong one dependent claim, 4, specifically claim 4 recites "ranking the set of documents based on their relevancy to the input query, wherein the device extracts the excerpts based on this ranking” in the context of this claim encompasses the user mentally identifying different segments and placing rank on the segment. These limitations could be reasonably and practically performed by the human mind, for instance based on a human can ranking sections of text. Accordingly, the claim recites a mental process, which can be done utilizing pen and paper.
Accordingly, the claim recites an abstract idea.
Step 2A Prong Two the claim does not recite additional elements that integrate the judicial exception into a practical application.
The dependent claim of 4 recites no new additional elements.
This judicial exception is not integrated into a practical application.
With respect to Step 1, the claims are directed to a computer-implemented method.
With respect to Step 2A Prong one dependent claim, 5, specifically claim 5 recites no new abstract ideas
Accordingly, the claim recites an abstract idea.
Step 2A Prong Two the claims do not recite additional elements that integrate the judicial exception into a practical application.
The dependent claim of 5 recites elements to be mere instructions to apply an exception, because they recite no more than an idea of a solution or outcome that is not an improvement to the functioning of a computer or to another technology:
For example “providing, by the device, the set of documents to a user interface for review; and receiving, by the device and from the user interface, a selection of the set of documents, prior to extracting the excerpts” is seen as MPEP 2106.05(g) iii. Presenting offers to potential customers and gathering statistics generated based on the testing about how potential customers responded to the offers; the statistics are then used to calculate an optimized price, OIP Technologies, 788 F.3d at 1363, 115 USPQ2d at 1092-93;
This judicial exception is not integrated into a practical application. At step 2B, the claim recites “providing, by the device, the set of documents to a user interface for review; and receiving, by the device and from the user interface, a selection of the set of documents, prior to extracting the excerpts”.
For example, “providing, by the device and to a user interface, an output generated by the language model in response to the prompt”, is seen as computer functions that are well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality). MPEP 2106.05(d); (II), (iv).
With respect to Step 1, the claims are directed to a computer-implemented method.
With respect to Step 2A Prong one dependent claim, 6, specifically claim 6 recites no new abstract ideas
Accordingly, the claim recites an abstract idea.
Step 2A Prong Two the claims do not recite additional elements that integrate the judicial exception into a practical application.
The dependent claim of 6 recites elements to be mere instructions to apply an exception, because they recite no more than an idea of a solution or outcome that is not an improvement to the functioning of a computer or to another technology:
For example “generating summaries of the set of documents based on their excerpts, wherein the device uses the summaries to augment the input query” is seen as MPEP 2106.05(g) iii. Presenting offers to potential customers and gathering statistics generated based on the testing about how potential customers responded to the offers; the statistics are then used to calculate an optimized price, OIP Technologies, 788 F.3d at 1363, 115 USPQ2d at 1092-93;
This judicial exception is not integrated into a practical application. At step 2B, the claim recites “generating summaries of the set of documents based on their excerpts, wherein the device uses the summaries to augment the input query”.
For example, “generating summaries of the set of documents based on their excerpts, wherein the device uses the summaries to augment the input query”, is seen as computer functions that are well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality). MPEP 2106.05(d); (II), (iv).
With respect to Step 1, the claims are directed to a computer-implemented method.
With respect to Step 2A Prong one dependent claim, 7, specifically claim 7 recites no new abstract ideas
Accordingly, the claim recites an abstract idea.
Step 2A Prong Two the claims do not recite additional elements that integrate the judicial exception into a practical application.
The dependent claim of 7 recites elements to be mere instructions to apply an exception, because they recite no more than an idea of a solution or outcome that is not an improvement to the functioning of a computer or to another technology:
For example “wherein the varying sizes comprise at least one of: a singular sentence, a paragraph, or a plurality of paragraphs” is seen as MPEP 2106.05(g) iii. Selecting information, based on types of information and availability of information in a power-grid environment, for collection, analysis and display, Electric Power Group, LLC v. Alstom S.A., 830 F.3d 1350, 1354-55, 119 USPQ2d 1739, 1742 (Fed. Cir. 2016);
This judicial exception is not integrated into a practical application. At step 2B, the claim recites “wherein the varying sizes comprise at least one of: a singular sentence, a paragraph, or a plurality of paragraphs”.
For example, “wherein the varying sizes comprise at least one of: a singular sentence, a paragraph, or a plurality of paragraphs”, is seen as computer functions that are well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality). MPEP 2106.05(d); (II), (iv).
With respect to Step 2A Prong one dependent claim, 8, specifically claim 8 recites no new abstract ideas
Accordingly, the claim recites an abstract idea.
Step 2A Prong Two the claims do not recite additional elements that integrate the judicial exception into a practical application.
The dependent claim of 8 recites elements to be mere instructions to apply an exception, because they recite no more than an idea of a solution or outcome that is not an improvement to the functioning of a computer or to another technology:
For example “wherein the device extracts the excerpts from the set of documents based in part on a request associated with the input query to augment it using context-aware retrieval augmented generation (RAG)” is seen as MPEP 2106.05(g) iii. Selecting information, based on types of information and availability of information in a power-grid environment, for collection, analysis and display, Electric Power Group, LLC v. Alstom S.A., 830 F.3d 1350, 1354-55, 119 USPQ2d 1739, 1742 (Fed. Cir. 2016);
This judicial exception is not integrated into a practical application. At step 2B, the claim recites “wherein the device extracts the excerpts from the set of documents based in part on a request associated with the input query to augment it using context-aware retrieval augmented generation (RAG)”.
For example, “wherein the device extracts the excerpts from the set of documents based in part on a request associated with the input query to augment it using context-aware retrieval augmented generation (RAG)”, is seen as computer functions that are well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality). MPEP 2106.05(d); (II), (iv).
With respect to Step 2A Prong one dependent claim, 9, specifically claim 9 recites no new abstract ideas
Accordingly, the claim recites an abstract idea.
Step 2A Prong Two the claims do not recite additional elements that integrate the judicial exception into a practical application.
The dependent claim of 9 recites elements to be mere instructions to apply an exception, because they recite no more than an idea of a solution or outcome that is not an improvement to the functioning of a computer or to another technology:
For example “wherein the device retrieves the set of documents from a larger set of documents based on their relevancy to the input query” is seen as MPEP 2106.05(g) iii. Selecting information, based on types of information and availability of information in a power-grid environment, for collection, analysis and display, Electric Power Group, LLC v. Alstom S.A., 830 F.3d 1350, 1354-55, 119 USPQ2d 1739, 1742 (Fed. Cir. 2016);
This judicial exception is not integrated into a practical application. At step 2B, the claim recites “wherein the device retrieves the set of documents from a larger set of documents based on their relevancy to the input query”.
For example, “wherein the device retrieves the set of documents from a larger set of documents based on their relevancy to the input query”, is seen as computer functions that are well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality). MPEP 2106.05(d); (II), (iv).
With respect to Step 2A Prong one dependent claim, 10, specifically claim 10 recites no new abstract ideas
Accordingly, the claim recites an abstract idea.
Step 2A Prong Two the claims do not recite additional elements that integrate the judicial exception into a practical application.
The dependent claim of 10 recites elements to be mere instructions to apply an exception, because they recite no more than an idea of a solution or outcome that is not an improvement to the functioning of a computer or to another technology:
For example “further comprising: storing, by the device, the excerpts for future augmentation of another input query” is seen as MPEP 2106.05(g) iii. Selecting information, based on types of information and availability of information in a power-grid environment, for collection, analysis and display, Electric Power Group, LLC v. Alstom S.A., 830 F.3d 1350, 1354-55, 119 USPQ2d 1739, 1742 (Fed. Cir. 2016);
This judicial exception is not integrated into a practical application. At step 2B, the claim recites “further comprising: storing, by the device, the excerpts for future augmentation of another input query”.
For example, “further comprising: storing, by the device, the excerpts for future augmentation of another input query”, is seen as computer functions that are well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality). MPEP 2106.05(d); (II), (iv).
With respect to Step 1, the claims are directed to a computer-implemented method.
With respect to Step 2A Prong one independent claim, 11, specifically claim 11 recites, “performing, by the device, a ranking of the excerpts based on their relevancy to the input query” in the context of this claim encompasses the user mentally identifying different segments and placing rank on the segment. These limitations could be reasonably and practically performed by the human mind, for instance based on a human can ranking sections of text. Accordingly, the claim recites a mental process, which can be done utilizing pen and paper.
Accordingly, the claim recites an abstract idea.
Step 2A Prong Two the claims do not recite additional elements that integrate the judicial exception into a practical application.
The independent claim of 11 recites elements to be mere instructions to apply an exception, because they recite no more than an idea of a solution or outcome:
For example "retrieving, by a device, a set of documents based on their relevancy to an input query from a user interface” is seen as insignificant extra activities.
For example, “extracting, by the device, excerpts of varying sizes from the set of documents that are relevant to the input query, wherein the extracting filters information irrelevant to the input query from the set of documents” is seen as MPEP 2106.05(g) iv. Obtaining information about transactions using the Internet to verify credit card transactions, CyberSource v. Retail Decisions, Inc., 654 F.3d 1366, 1375, 99 USPQ2d 1690, 1694 (Fed. Cir. 2011);
For example, “and augmenting, by the device and based on the ranking, the input query based on one or more of the excerpts to form a prompt for input to a language model” is seen as MPEP 2106.05(g) i. Remotely accessing user-specific information through a mobile interface and pointers to retrieve the information without any description of how the mobile interface and pointers accomplish the result of retrieving previously inaccessible information, Intellectual Ventures v. Erie Indem. Co., 850 F.3d 1315, 1331, 121 USPQ2d 1928, 1939 (Fed. Cir. 2017);As discussed above with respect to integration of the abstract idea into a practical application, the additional elements are insignificant extra-solution activity. MPEP 2106.05(d)(II)(i).
This judicial exception is not integrated into a practical application. At step 2B, the claim recites "retrieving, by a device, a set of documents based on their relevancy to an input query from a user interface”, “extracting, by the device, excerpts of varying sizes from the set of documents that are relevant to the input query, wherein the extracting filters information irrelevant to the input query from the set of documents”, “and augmenting, by the device and based on the ranking, the input query based on one or more of the excerpts to form a prompt for input to a language model”.
For example, "retrieving, by a device, a set of documents based on their relevancy to an input query from a user interface”, do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The additional elements are a step of transmitting data, and is recognized as well understood, routine, and conventional activity within the field of computer functions as an element of receiving or transmitting data over a network (MPEP 2106.05(d)(II)(i)).
For example, “extracting, by the device, excerpts of varying sizes from the set of documents that are relevant to the input query, wherein the extracting filters information irrelevant to the input query from the set of documents” do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The additional elements are a step of transmitting data, and is recognized as well understood, routine, and conventional activity within the field of computer functions as an element of receiving or transmitting data over a network (MPEP 2106.05(d)(II)(i)).
For example, “and augmenting, by the device and based on the ranking, the input query based on one or more of the excerpts to form a prompt for input to a language model” do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The additional elements are a step of transmitting data, and is recognized as well understood, routine, and conventional activity within the field of computer functions as an element of receiving or transmitting data over a network (MPEP 2106.05(d)(II)(iv)).
With respect to Step 1, the claims are directed to a computer-implemented method.
With respect to Step 2A Prong one dependent claim, 12, specifically claim 12 recites no new abstract ideas
Accordingly, the claim recites an abstract idea.
Step 2A Prong Two the claims do not recite additional elements that integrate the judicial exception into a practical application.
The dependent claim of 12 recites elements to be mere instructions to apply an exception, because they recite no more than an idea of a solution or outcome that is not an improvement to the functioning of a computer or to another technology:
For example “wherein the language model is a large language model (LLM)” is seen as MPEP 2106.05(f) i. Remotely accessing user-specific information through a mobile interface and pointers to retrieve the information without any description of how the mobile interface and pointers accomplish the result of retrieving previously inaccessible information, Intellectual Ventures v. Erie Indem. Co., 850 F.3d 1315, 1331, 121 USPQ2d 1928, 1939 (Fed. Cir. 2017);
This judicial exception is not integrated into a practical application. At step 2B, the claim recites “wherein the language model is a large language model (LLM)”.
For example, “wherein the language model is a large language model (LLM)”, is seen as computer functions that are well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality). MPEP 2106.05(d); (II), (ii).
With respect to Step 1, the claims are directed to a computer-implemented method.
With respect to Step 2A Prong one dependent claim, 13, specifically claim 13 recites no new abstract ideas
Accordingly, the claim recites an abstract idea.
Step 2A Prong Two the claims do not recite additional elements that integrate the judicial exception into a practical application.
The dependent claim of 13 recites elements to be mere instructions to apply an exception, because they recite no more than an idea of a solution or outcome that is not an improvement to the functioning of a computer or to another technology:
For example “providing, by the device and to a user interface, an output generated by the language model in response to the prompt” is seen as insignificant extra activities.
This judicial exception is not integrated into a practical application. At step 2B, the claim recites “providing, by the device and to a user interface, an output generated by the language model in response to the prompt”.
For example, “providing, by the device and to a user interface, an output generated by the language model in response to the prompt”, is seen as computer functions that are well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality). MPEP 2106.05(d); (II), (iv).
With respect to Step 1, the claims are directed to a computer-implemented method.
With respect to Step 2A Prong one dependent claim, 14, specifically claim 14 recites "ranking the set of documents based on their relevancy to the input query, wherein the device extracts the excerpts based on this ranking” in the context of this claim encompasses the user mentally identifying different segments and placing rank on the segment. These limitations could be reasonably and practically performed by the human mind, for instance based on a human can ranking sections of text. Accordingly, the claim recites a mental process, which can be done utilizing pen and paper.
Accordingly, the claim recites an abstract idea.
Step 2A Prong Two the claim does not recite additional elements that integrate the judicial exception into a practical application.
The dependent claim of 14 recites no new additional elements.
This judicial exception is not integrated into a practical application.
With respect to Step 1, the claims are directed to a computer-implemented method.
With respect to Step 2A Prong one dependent claim, 15, specifically claim 15 recites no new abstract ideas
Accordingly, the claim recites an abstract idea.
Step 2A Prong Two the claims do not recite additional elements that integrate the judicial exception into a practical application.
The dependent claim of 15 recites elements to be mere instructions to apply an exception, because they recite no more than an idea of a solution or outcome that is not an improvement to the functioning of a computer or to another technology:
For example “providing, by the device, the set of documents to a user interface for review; and receiving, by the device and from the user interface, a selection of the set of documents, prior to extracting the excerpts” is seen as MPEP 2106.05(g) iii. Presenting offers to potential customers and gathering statistics generated based on the testing about how potential customers responded to the offers; the statistics are then used to calculate an optimized price, OIP Technologies, 788 F.3d at 1363, 115 USPQ2d at 1092-93;
This judicial exception is not integrated into a practical application. At step 2B, the claim recites “providing, by the device, the set of documents to a user interface for review; and receiving, by the device and from the user interface, a selection of the set of documents, prior to extracting the excerpts”.
For example, “providing, by the device and to a user interface, an output generated by the language model in response to the prompt”, is seen as computer functions that are well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality). MPEP 2106.05(d); (II), (iv).
With respect to Step 1, the claims are directed to a computer-implemented method.
With respect to Step 2A Prong one dependent claim, 16, specifically claim 16 recites no new abstract ideas
Accordingly, the claim recites an abstract idea.
Step 2A Prong Two the claims do not recite additional elements that integrate the judicial exception into a practical application.
The dependent claim of 16 recites elements to be mere instructions to apply an exception, because they recite no more than an idea of a solution or outcome that is not an improvement to the functioning of a computer or to another technology:
For example “generating summaries of the set of documents based on their excerpts, wherein the device uses the summaries to augment the input query” is seen as MPEP 2106.05(g) iii. Presenting offers to potential customers and gathering statistics generated based on the testing about how potential customers responded to the offers; the statistics are then used to calculate an optimized price, OIP Technologies, 788 F.3d at 1363, 115 USPQ2d at 1092-93;
This judicial exception is not integrated into a practical application. At step 2B, the claim recites “generating summaries of the set of documents based on their excerpts, wherein the device uses the summaries to augment the input query”.
For example, “generating summaries of the set of documents based on their excerpts, wherein the device uses the summaries to augment the input query”, is seen as computer functions that are well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality). MPEP 2106.05(d); (II), (iv).
With respect to Step 1, the claims are directed to a computer-implemented method.
With respect to Step 2A Prong one dependent claim, 17, specifically claim 17 recites no new abstract ideas
Accordingly, the claim recites an abstract idea.
Step 2A Prong Two the claims do not recite additional elements that integrate the judicial exception into a practical application.
The dependent claim of 17 recites elements to be mere instructions to apply an exception, because they recite no more than an idea of a solution or outcome that is not an improvement to the functioning of a computer or to another technology:
For example “wherein the varying sizes comprise at least one of: a singular sentence, a paragraph, or a plurality of paragraphs” is seen as MPEP 2106.05(g) iii. Selecting information, based on types of information and availability of information in a power-grid environment, for collection, analysis and display, Electric Power Group, LLC v. Alstom S.A., 830 F.3d 1350, 1354-55, 119 USPQ2d 1739, 1742 (Fed. Cir. 2016);
This judicial exception is not integrated into a practical application. At step 2B, the claim recites “wherein the varying sizes comprise at least one of: a singular sentence, a paragraph, or a plurality of paragraphs”.
For example, “wherein the varying sizes comprise at least one of: a singular sentence, a paragraph, or a plurality of paragraphs”, is seen as computer functions that are well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality). MPEP 2106.05(d); (II), (iv).
With respect to Step 2A Prong one dependent claim, 18, specifically claim 18 recites no new abstract ideas
Accordingly, the claim recites an abstract idea.
Step 2A Prong Two the claims do not recite additional elements that integrate the judicial exception into a practical application.
The dependent claim of 18 recites elements to be mere instructions to apply an exception, because they recite no more than an idea of a solution or outcome that is not an improvement to the functioning of a computer or to another technology:
For example “wherein the device extracts the excerpts from the set of documents based in part on a request associated with the input query to augment it using context-aware retrieval augmented generation (RAG)” is seen as MPEP 2106.05(g) iii. Selecting information, based on types of information and availability of information in a power-grid environment, for collection, analysis and display, Electric Power Group, LLC v. Alstom S.A., 830 F.3d 1350, 1354-55, 119 USPQ2d 1739, 1742 (Fed. Cir. 2016);
This judicial exception is not integrated into a practical application. At step 2B, the claim recites “wherein the device extracts the excerpts from the set of documents based in part on a request associated with the input query to augment it using context-aware retrieval augmented generation (RAG)”.
For example, “wherein the device extracts the excerpts from the set of documents based in part on a request associated with the input query to augment it using context-aware retrieval augmented generation (RAG)”, is seen as computer functions that are well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality). MPEP 2106.05(d); (II), (iv).
With respect to Step 2A Prong one dependent claim, 19, specifically claim 19 recites no new abstract ideas
Accordingly, the claim recites an abstract idea.
Step 2A Prong Two the claims do not recite additional elements that integrate the judicial exception into a practical application.
The dependent claim of 19 recites elements to be mere instructions to apply an exception, because they recite no more than an idea of a solution or outcome that is not an improvement to the functioning of a computer or to another technology:
For example “wherein the device retrieves the set of documents from a larger set of documents based on their relevancy to the input query, ” is seen as MPEP 2106.05(g) iii. Selecting information, based on types of information and availability of information in a power-grid environment, for collection, analysis and display, Electric Power Group, LLC v. Alstom S.A., 830 F.3d 1350, 1354-55, 119 USPQ2d 1739, 1742 (Fed. Cir. 2016);
This judicial exception is not integrated into a practical application. At step 2B, the claim recites “wherein the device retrieves the set of documents from a larger set of documents based on their relevancy to the input query”.
For example, “wherein the device retrieves the set of documents from a larger set of documents based on their relevancy to the input query”, is seen as computer functions that are well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality). MPEP 2106.05(d); (II), (iv).
With respect to Step 1, the claims are directed to a tangible non-transitory, computer-readable medium.
With respect to Step 2A Prong one independent claim, 20, specifically claim 20 recites, “performing, by the device, a ranking of the excerpts based on their relevancy to the input query” in the context of this claim encompasses the user mentally identifying different segments and placing rank on the segment. These limitations could be reasonably and practically performed by the human mind, for instance based on a human can ranking sections of text. Accordingly, the claim recites a mental process, which can be done utilizing pen and paper.
Accordingly, the claim recites an abstract idea.
Step 2A Prong Two the claims do not recite additional elements that integrate the judicial exception into a practical application.
The independent claim of 20 recites elements to be mere instructions to apply an exception, because they recite no more than an idea of a solution or outcome:
For example "retrieving, by a device, a set of documents based on their relevancy to an input query from a user interface” is seen as insignificant extra activities.
For example, “extracting, by the device, excerpts of varying sizes from the set of documents that are relevant to the input query, wherein the extracting filters information irrelevant to the input query from the set of documents” is seen as MPEP 2106.05(g) iv. Obtaining information about transactions using the Internet to verify credit card transactions, CyberSource v. Retail Decisions, Inc., 654 F.3d 1366, 1375, 99 USPQ2d 1690, 1694 (Fed. Cir. 2011);
For example, “and augmenting, by the device and based on the ranking, the input query based on one or more of the excerpts to form a prompt for input to a language model” is seen as MPEP 2106.05(g) i. Remotely accessing user-specific information through a mobile interface and pointers to retrieve the information without any description of how the mobile interface and pointers accomplish the result of retrieving previously inaccessible information, Intellectual Ventures v. Erie Indem. Co., 850 F.3d 1315, 1331, 121 USPQ2d 1928, 1939 (Fed. Cir. 2017);As discussed above with respect to integration of the abstract idea into a practical application, the additional elements are insignificant extra-solution activity. MPEP 2106.05(d)(II)(i).
This judicial exception is not integrated into a practical application. At step 2B, the claim recites "retrieving, by a device, a set of documents based on their relevancy to an input query from a user interface”, “extracting, by the device, excerpts of varying sizes from the set of documents that are relevant to the input query, wherein the extracting filters information irrelevant to the input query from the set of documents”, “and augmenting, by the device and based on the ranking, the input query based on one or more of the excerpts to form a prompt for input to a language model”.
For example, "retrieving, by a device, a set of documents based on their relevancy to an input query from a user interface”, is seen as insignificant extra activities.
For example, “extracting, by the device, excerpts of varying sizes from the set of documents that are relevant to the input query, wherein the extracting filters information irrelevant to the input query from the set of documents” do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The additional elements are a step of transmitting data, and is recognized as well understood, routine, and conventional activity within the field of computer functions as an element of receiving or transmitting data over a network (MPEP 2106.05(d)(II)(i)).
For example, “and augmenting, by the device and based on the ranking, the input query based on one or more of the excerpts to form a prompt for input to a language model” do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The additional elements are a step of transmitting data, and is recognized as well understood, routine, and conventional activity within the field of computer functions as an element of receiving or transmitting data over a network (MPEP 2106.05(d)(II)(iv)).
With respect to Step 1, the claims are directed to a tangible non-transitory, computer-readable medium.
With respect to Step 2A Prong one dependent claim, 21, specifically claim 21 recites, converting the excerpts into embedding representations; and ranking the embedding representations by cosine similarity with respect to embeddings of the input query in the context of this claim encompasses the user mentally identifying different segments and placing rank on the segment. These limitations could be reasonably and practically performed by the human mind, for instance based on a human can ranking sections of text. Accordingly, the claim recites a mental process, which can be done utilizing pen and paper.
Accordingly, the claim recites an abstract idea.
Step 2A Prong Two the claims do not recite additional elements that integrate the judicial exception into a practical application.
The independent claim of 21 recites elements to be mere instructions to apply an exception, because they recite no more than an idea of a solution or outcome:
For example, " converting the excerpts into embedding representations; and ranking the embedding representations by cosine similarity with respect to embeddings of the input query” is seen as insignificant extra activities.
Claim Rejections - 35 USC § 103
5. In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
6. 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.
7. Claim(s) 1-11 and 13-20 is/are rejected under 35 U.S.C. 103 as being unpatentable by Zang et al. U.S. Patent Application Publication No. 2025/0147991 (herein as ‘Zang’) and further in view of Moon et al. U.S. Patent No. 6,898,591 (herein as ‘Moon’).
As to claim 1 Zang teaches a method for augmenting an input query to form a prompt for input to a language model using context-aware retrieval augmented generation (RAG), comprising:
retrieving, by a device, a set of documents based on their relevancy to an input query from a user interface (Fig. 3 (204) and Par. 0057 Zang discloses receiving a set of documents associated with a query);
performing, by the device, a ranking of the excerpts based on their relevancy to the input query (Par. 0032 Zang discloses ranking text based upon query terms appearing in the documents);
and augmenting, by the device and based on the ranking, the input query based on one or more of the excerpts to form a prompt for input to a language model, and inputting, by the device, the prompt to the language model (Par. 0073 and Fig. 3(306) Zang discloses the input and documents are applied to a LLM reader which generates a generated answer. The generated answer is later used as input into LLM grader.).
Zang does not teach but Moon teaches extracting, by the device, excerpts of varying sizes from the set of documents that are relevant to the input query, wherein the extracting filters information irrelevant to the input query from the set of documents (Col. 3 Lines 50-59 Moon discloses receiving information in response to a request. The system then extracts unwanted information from the received information).
Zang and Moon are analogous art because they are in the same field of endeavor, query processing. It would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify the query of Zang to include the removing unwanted data of Evans, to allow for accessing content in order to provide more relevant data to the user (Col. 1 Lines 35-65 and Col. 2 Lines 1-5 Moon).
As to claim 2 Zang in combination with Moon teaches each and every limitation of claim 1.
In addition Zang teaches wherein the language model is a large language model (LLM) (Fig.1 and Par. 0017 Zang discloses a LLM, known as large language model).
As to claim 3 Zang in combination with Moon teaches each and every limitation of claim 1.
In addition Zang teaches further comprising: providing, by the device and to the user interface, an output generated by the language model in response to the prompt (Par. 0071 and Fig. 3 (318) Zang discloses generating a response to the grader).
As to claim 4 Zang in combination with Moon teaches each and every limitation of claim 1.
In addition Zang teaches further comprising: ranking the set of documents based on their relevancy to the input query, wherein the device extracts the excerpts based on this ranking (Par. 0064 Zang discloses retrieving the articles or documents based upon the relevance to the query).
As to claim 5 Zang in combination with Moon teaches each and every limitation of claim 1.
In addition Zang teaches further comprising: providing, by the device, the set of documents to user interface for review; and receiving, by the device and from the user interface, a selection of the set of documents, prior to extracting the excerpts (Par. 0027 Zang discloses users can review the topics used to build the database source).
As to claim 6 Zang in combination with Moon teaches each and every limitation of claim 1.
In addition Zang teaches further comprising: generating summaries of the set of documents based on their excerpts, wherein the device uses the summaries to augment the input query (Par. 0038 Zang discloses summarizing key information from among the list of retrieved candidate documents relevant to the input query).
As to claim 7 Zang in combination with Moon teaches each and every limitation of claim 1.
In addition Zang teaches wherein the varying sizes comprise at least one of: a singular sentence, a paragraph, or a plurality of paragraphs (Par. 0048-0053 Zang discloses text of different sizes).
As to claim 8 Zang in combination with Moon teaches each and every limitation of claim 1.
In addition Zang teaches wherein the device extracts the excerpts from the set of documents based in part on a request associated with the input query to augment it using context-aware (Par. 0038 Zang discloses summarizing key information from among the list of retrieved candidate documents relevant to the input query).
As to claim 9 Zang in combination with Moon teaches each and every limitation of claim 1.
In addition Zang teaches wherein the device retrieves the set of documents from a larger set of documents based on their relevancy to the input query (Par. 0038 Zang discloses summarizing key information from among the list of retrieved candidate documents relevant to the input query).
As to claim 10 Zang in combination with Moon teaches each and every limitation of claim 1.
In addition Zang teaches further comprising: storing, by the device, the excerpts for future augmentation of another input query (Par. 0044 Zang discloses using only the top 3 of the ranked documents to perform a second augmentation with the grader).
As to claim 11 Zang teaches an apparatus, comprising: one or more network interfaces (Par. 0022 Zang discloses a communications network);
a processor coupled to the one or more network interfaces and configured to execute one or more processes (Par. 0092 Zang discloses a processor);
and a memory configured to store a process that is executable by the processor, the process when executed configured to using context-aware retrieval augmented generation (RAG) (Par. 0094 Zang discloses a memory);:
retrieve a set of documents based on their relevancy to an input query from a user interface (Fig. 4 (204) and Par. 0057 Zang discloses receiving a set of documents associated with a query);
perform a ranking of the excerpts based on their relevancy to the input query (Par. 0032 Zang discloses ranking text based upon query terms appearing in the documents);
and augment, based on the ranking, the input query based on one or more of the excerpts to form a prompt for input to a language model and input the prompt to the language model (Par. 0073 and Fig. 3(306) Zang discloses the input and documents are applied to a LLM reader which generates a generated answer. The generated answer is later used as input into LLM grader.).
Zang does not teach but Moon teaches extract excerpts of varying sizes from the set of documents that are relevant to the input query, wherein the extracting filters information irrelevant to the input query from the set of documents (Col. 3 Lines 50-59 Moon discloses receiving information in response to a request. The system then extracts unwanted information from the received information).
Zang and Moon are analogous art because they are in the same field of endeavor, query processing. It would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify the query of Zang to include the removing unwanted data of Evans, to allow for accessing content in order to provide more relevant data to the user (Col. 1 Lines 35-65 and Col. 2 Lines 1-5 Moon).
As to claim 13 Zang in combination with Moon teaches each and every limitation of claim 11.
In addition Zang teaches wherein the process when executed is further configured to: provide, to the user interface, an output generated by the language model in response to the prompt (Par. 0071 and Fig. 3 (318) Zang discloses generating a response to the grader).
As to claim 14 Zang in combination with Moon teaches each and every limitation of claim 11.
In addition Zang teaches wherein the process when executed is further configured to: rank the set of documents based on their relevancy to the input query, wherein the apparatus extracts the excerpts based on this ranking (Par. 0064 Zang discloses retrieving the articles or documents based upon the relevance to the query).
As to claim 15 Zang in combination with Moon teaches each and every limitation of claim 11.
In addition Zang teaches wherein the process when executed is further configured to: provide the set of documents to a user interface for review; and receive, from the user interface, a selection of the set of documents, prior to extracting the excerpts (Par. 0027 Zang discloses users can review the topics used to build the database source).
As to claim 16 Zang in combination with Moon teaches each and every limitation of claim 11.
In addition Zang teaches wherein the process when executed is further configured to: generate summaries of the set of documents based on their excerpts, wherein the apparatus uses the summaries to augment the input query (Par. 0038 Zang discloses summarizing key information from among the list of retrieved candidate documents relevant to the input query).
As to claim 17 Zang in combination with Moon teaches each and every limitation of claim 11.
In addition Zang teaches wherein the varying sizes comprise at least one of: a singular sentence, a paragraph, or a plurality of paragraphs (Par. 0048-0053 Zang discloses text of different sizes).
As to claim 18 Zang in combination with Moon teaches each and every limitation of claim 11.
In addition Zang teaches wherein the apparatus extracts the excerpts from the set of documents based in part on a request associated with the input query to augment it using context-aware RAG (Par. 0038 Zang discloses summarizing key information from among the list of retrieved candidate documents relevant to the input query).
As to claim 19 Zang in combination with Moon teaches each and every limitation of claim 11.
In addition Zang teaches wherein the apparatus retrieves the set of documents from a larger set of documents based on their relevancy to the input query (Par. 0038 Zang discloses summarizing key information from among the list of retrieved candidate documents relevant to the input query).
As to claim 20 Zang teaches a tangible, non-transitory, computer-readable medium storing program instructions that cause a device to execute a process using context-aware retrieval augmented generation (RAG) comprising:
retrieving, by a device, a set of documents based on their relevancy to an input query from a user interface (Fig. 4 (204) and Par. 0057 Zang discloses receiving a set of documents associated with a query);
performing, by the device, a ranking of the excerpts based on their relevancy to the input query (Par. 0032 Zang discloses ranking text based upon query terms appearing in the documents);
and augmenting, by the device and based on the ranking, the input query based on one or more of the excerpts to form a prompt for input to a language model, and inputting, by the device, the prompt to the language model (Par. 0073 and Fig. 3(306) Zang discloses the input and documents are applied to a LLM reader which generates a generated answer. The generated answer is later used as input into LLM grader).
Zang does not teach but Moon teaches extracting, by the device, excerpts of varying sizes from the set of documents that are relevant to the input query, wherein the extracting filters information irrelevant to the input query from the set of documents (Col. 3 Lines 50-59 Moon discloses receiving information in response to a request. The system then extracts unwanted information from the received information).
Zang and Moon are analogous art because they are in the same field of endeavor, query processing. It would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify the query of Zang to include the removing unwanted data of Evans, to allow for accessing content in order to provide more relevant data to the user (Col. 1 Lines 35-65 and Col. 2 Lines 1-5 Moon).
6. Claim(s) 21 is rejected under 35 U.S.C. 103 as being unpatentable by Zang et al. U.S. Patent Application Publication No. 2025/0147991 (herein as ‘Zang’) and further in view of Moon et al. U.S. Patent No. 6,898,591 (herein as ‘Moon’) and Liu et al. U.S. Patent Application Publication No. 2026/0044538 (herein as ‘Liu’).
As to claim 21 Zang in combination with Liu teaches each and every limitation of claim 1.
In addition Liu teaches converting the excerpts into embedding representations; and ranking the embedding representations by cosine similarity with respect to embeddings of the input query. (Par. 0023 Zang discloses ranking embeddings based upon the similarity measure).
Zang and Moon are analogous art because they are in the same field of endeavor, query processing. It would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify the query of Zang to include the removing unwanted data of Evans, to allow for accessing content in order to provide more relevant data to the user (Col. 1 Lines 35-65 and Col. 2 Lines 1-5 Moon).
Conclusion
8. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. The databases searched US-PGPUB,USPAT,USOCR,EPO,JPO and DERWENT.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JERMAINE A MINCEY whose telephone number is (571)270-5010. The examiner can normally be reached 8am EST until 5pm EST.
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, Ann J Lo can be reached at (571) 272-9767. 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.
/JERMAINE A MINCEY/Examiner, Art Unit 2159
Prosecution Insights