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 .
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
Examiner Notes
(1) In the case of amending the Claimed invention, Applicant is respectfully requested to indicate the portion(s) of the specification which dictate(s) the structure relied on for proper interpretation and also to verify and ascertain the metes and bounds of the claimed invention. This will assist in expediting compact prosecution. MPEP 714.02 recites: “Applicant should also specifically point out the support for any amendments made to the disclosure. See MPEP § 2163.06. An amendment which does not comply with the provisions of 37 CFR 1.121 (b), (c), (d), and (h) may be held not fully responsive. See MPEP § 714.” Amendments not pointing to specific support in the disclosure may be deemed as not complying with provisions of 37 C.F.R. 1.131 (b), (c), (d), and (h) and therefore held not fully responsive. Generic statements such as "Applicants believe no new matter has been introduced" may be deemed insufficient.
(2) Examiner cites particular columns, paragraphs, figures and line numbers in the references as applied to the claims below for the convenience of the applicant. Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested that, in preparing responses, the applicant fully consider the references in their entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the Examiner.
Remarks
Receipt of Applicant’s Amendment file on 06/25/2026 is acknowledged.
Response to Arguments
Applicant's arguments filed 06/25/2026 have been fully considered but they are not persuasive.
Regarding 35 U.S.C. 101 rejection, applicant argues that “human beings cannot mentally store vectorized data in at least one vector database, receive a query to generate a report associated with a current project using a large language model, determining a relevant context using the large language model responsive to training data of the large language model and at least a portion of the vectorized data in the at least one vector database, return the relevant context generated using the large language model, and generate and output one or more portions of the report using the large language model” (page 12, first paragraph).
Applicant further argues “ Claim 1 does not merely recite generic computer components to perform a process that could be performed in the mind. Rather, Claim 1 describes a particular process for improving the operation of a large language model (LLM) to enable the generation of reports. The process creates vectorized data that includes numerical vector values representing contents of one or more documents stored within one or more storage locations. The LLM utilizes this particular type of vectorized data in order to determine a relevant context responsive to training data of the LLM and at least a portion of this vectorized data” (page 12, second paragraph).
Applicant also argues “improving the determination of a relevant context by an LLM using both training data of the LLM and vectorized data from at least one vector database, along with the generation of a report using the improved LLM, provides a practical implementation and improvement in the generation of reports using LLMs” (page 13, first paragraph).
Respectfully, it is noted that the amended portion of the claims including “using the large language model responsive to training data of the large language model” merely illustrates the LLM utilization in process of relevant context determination for report generation; it does not show any improvement to the LLM or any adjust to LLM parameters in order illustrate the technology improvement. Thus, the argument “improving the determination of a relevant context by an LLM using both training data of the LLM and vectorized data from at least one vector database, along with the generation of a report using the improved LLM, provides a practical implementation and improvement in the generation of reports using LLMs”; rather the claims merely apply LLMs to report generation, which is not indicative of an improvement in the functioning of the computer or technology.
Further noted, “store vectorized data in at least one vector database”, “receive a query to generate a report associated with a current project”, “returning…”, ““output,…one or more portion of the report”” are merely constitute extra insignificant solution activity (see MPEP 2106.05(d), II.; receive/transmit over network; store/retrieve from memory/storage; mere data gathering and output, selecting a particular data source or type of data to be manipulated; see MPEP 2106.05(g) – presenting offers, selecting information examples).
The additional limitation “a large language model” describes generic computer components, akin to adding the word "apply it" in connection with the abstract idea (determining a relevant context: mental process).
Therefore, the rejection of claim 1 under 35 U.S.C. 101 is maintained.
The rejection of claim 11 is maintained for similar reasons.
Regarding 35 U.S.C. 102 rejection, applicant argues “Mourya does not disclose or suggest the creation of vectorized data that includes numerical vector values representing contents of one or more documents stored in one or more document storage locations, nor does Mourya disclose or suggest the determination of relevant contexts using a large language model responsive to training data of the large language model and at least a portion of the vectorized data in the at least one vector database. While disclosing a vector database 130, Mourya does not describe the creation of vectorized data within this database based upon numerical vectors representing the contents of documents. Mourya also provides no discussion of determining a relevant context in the manner now recited in Claim 1” (page 15).
Respectfully, it is noted that newly added reference AJMERA teaches the creation of vectorized data that includes numerical vector values representing contents of one or more documents stored in one or more document storage locations (paragraph [0036], documents and/or other data can be uploaded from a user device or from one or more applications; also see paragraph [0056], a corpus of data including variety of documents of different types may be received by server device; also see pargraph [0070], the embedding generation module receives documents data, or chunks and generates embedding for the chunks; also see paragraph [0060], embeddings are generated for the chunk, for example, a vector representation may be used as a numerical representation of a chunk of data; noted, “a vector representation may be used as a numerical representation of a chunk of data” is interpreted as “wherein the vectorized data comprises numerical vector values representing contents of the one or more documents”); while Mourya, paragraph [0022], teaches vector DB can be any vector database, such as Open Search or other products; vector DB can store data in a standard format, such as query data and/or context data; also see paragraph [0040], generating vector for query data and/or other data obtain, where the vector is a structured database entry; also see paragraph [0028], identify context data in vector DB 130; also see paragraph [0046], obtaining context vectors from vector DB; context vectors may include, for example, at least one record of a previously successful data entry in a standardize format that resulted in a previously validated response from LLM; noted, “identify context data in vector DB 130” and “context vectors may include, for example, at least one record of a previously successful data entry in a standardize format that resulted in a previously validated response from LLM” is interpreted as “determining a relevant context using the large language model responsive to training data of the large language model and at least a portion of the vectorized data in the at least one vector database”; also see paragraph [0016], [0029], which reads on as claimed. Therefore, the claim is rejected under 35 U.S.C. 103.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are directed to non-statutory subject matter because it does not fall within four category of patentable subject matter recited in 35 U.S.C 101 (Process, machine manufacture or composition of matter).
When considering subject matter eligibility under 35 USC 101, it must be determined whether the claim is directed to one of the four statutory categories of invention, i.e., process, machine, manufacture, or composition of matter (Step 1). If the claim does fall within one of the statutory categories, it must then be determined whether the claim is directed to a judicial exception (i.e., law of nature, natural phenomenon, and abstract idea) (Step 2A), and if so, it must additionally be determined whether the claim is a patent-eligible application of the exception. If an abstract idea is present in the claim, any element or combination of elements in the claim must be sufficient to ensure that the claim amounts to significantly more than the abstract idea itself (Step 2B). Examples of abstract ideas include fundamental economic practices; certain methods of organizing human activities; an idea itself; and mathematical relationships/formulas.
Analysis
STEP 1:
Claims 1, and 11 subject matter falls within the four statutory categories of patentable subject matter identified by 35 U.S.C. § 101: process, machine, manufacture, or composition of matter.
STEP 2A, PRONG l (Claim 1):
Under step 2A, prong 1, of the 2019 Guidance, we first look to whether the claim recites any judicial exceptions, including certain groupings of abstract ideas (i.e., mathematical concepts, certain methods of organizing human activities such as a fundamental economic practice, or mental processes). MPEP § 2106.04(a).
Limitation recites:
STEP 2A, PRONG l (Claim 1):
Under step 2A, prong 1, of the 2019 Guidance, we first look to whether the claim recites any judicial exceptions, including certain groupings of abstract ideas (i.e., mathematical concepts, certain methods of organizing human activities such as a fundamental economic practice, or mental processes). MPEP § 2106.04(a).
Limitation recites:
creating vectorized data corresponding to from one or more documents stored in from one or more document storage locations, wherein the vectorized data comprises numerical vector values representing contents of the one or more documents”
storing the vectorized data in at least one vector database;
receiving a query to generate a report associated with a current project using a large language model”
determining a relevant context using the large language model responsive to training data of the large language model and at least a portion of the vectorized data in the at least one vector database”
returning, in response to the query, a relevant context generated using the large language model ”
“generating and outputting, using the large language model and based on the relevant context, one or more portions of the report”
Claim 1 recites limitations “creating vectorized data corresponding to from one or more document…, wherein vectorize data comprises numerical value…”, human mind with aid of pen or paper can generating numerical value represent content/document; noted, storing in one or more documents storage location, which merely a description of location the content/document is located [extra insignificant solution activity].
“determining a relevant context…” covers performance of the limitation in the mind; one can mentally determine the context based on possessed knowledge in response to the question/query.
“generating and outputting, […] and based on the relevant context, one or more portions of the report”, under their broadest reasonable interpretation, covers performance of the limitation in the mind, but for the recitation of generic computer components. For example, one can mentally generating report based on recognized context.
STEP 2A, PRONG 2 (Claim 1):
Limitations (b) “storing the vectorized data…” merely illustrates the stored vector data corresponding to documents in various locations, which constitute extra-insignificant solution activity (see MPEP 2106.05(d), II.; receive/transmit over network; store/retrieve from memory/storage).
Limitation (c) “receiving query..”, (e) returning, in response to the query,…” and part of (f) “output,…one or more portion of the report”, are merely constitute extra-insignificant solution activity (mere data gathering and output, selecting a particular data source or type of data to be manipulated; see MPEP 2106.05(g) – presenting offers, selecting information examples).
The additional limitations “a large language model” describe generic computer components, akin to adding the word "apply it" in connection with the abstract idea, rather than explicitly illustrates an improved way of training a machine learning model that protected the model’s knowledge about previous tasks while allowing it to effectively learn new tasks; or improvements to computer component or system performance based upon adjustments to parameters of a machine learning model associated with tasks or workstreams; Ex Parte Desjardins, Appeal No. 2024-000567 (PTAB September 26, 2025, Appeals Review Panel Decision), thus, viewed as a whole, the additional claim elements do not provide meaningful limitations sufficient to transform the abstract idea into a patent eligible application of the abstract idea such that the claims amount to “significantly more” than the abstract idea itself.
STEP 2B (Claim 1): Under step 2B, the identification of additional elements from Step 2A Prong Two is carried over, and the conclusion from Step 2A Prong Two that the additional elements are mere instructions to apply the abstract idea on a computer under MPEP 2106.05(f) is also carried over. Therefore, none of the additional elements provide significantly more.
Noted, the amended portion of the claims including “using the large language model responsive to training data of the large language model” merely illustrates the LLM utilization in process of relevant context determination for report generation; it does not show any improvement to the LLM or any adjust to LLM parameters in order illustrate the technology improvement. Thus, the argument “improving the determination of a relevant context by an LLM using both training data of the LLM and vectorized data from at least one vector database, along with the generation of a report using the improved LLM, provides a practical implementation and improvement in the generation of reports using LLMs”; rather the claims merely apply LLMs to report generation, which is not indicative of an improvement in the functioning of the computer or technology.
Claim 11 is being rejected under U.S.C. 101 for similar reason.
Claims 2-10 and 12-20 are dependent on their respective parent claims 1 and 11 respectively and include all the limitations of claims 1 and 11 respectively. Since these claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception, thus the claims are direct to abstract idea.
Claims 1-20 are therefore not drawn to eligible subject matter as they are directed to an abstract idea without significantly more.
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.
Claims 6-7, 9 , 16-17, 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 pre-AIA the applicant regards as the invention.
Claim 6 recites the limitation "the additional information" in line 2 of the claim. There is insufficient antecedent basis for this limitation in the claim.
Claim 9 recites the limitation "the additional information" in line 2 of the claim. There is insufficient antecedent basis for this limitation in the claim.
Claim 16 recites the limitation "the additional information" in line 3 of the claim. There is insufficient antecedent basis for this limitation in the claim.
Claim 19 recites the limitation "the additional information" in line 2 of the claim. There is insufficient antecedent basis for this limitation in the claim.
Dependent claims are being rejected as depending from rejection of parent claims.
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 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-3 and 11-13 are rejected under 35 U.S.C. 103 as being unpatentable over MOURYA (Pub. No. 2025/0390718 A1) in view of AJMERA (U.S. Pub. No. 2025/0181899 A1).
Regarding claim 1, MOURYA teaches a method comprising:
receiving a query to generate a report associated with a current project using a large language model (paragraph [0026], service layer may obtain query information; when a user enters a query, product may send the query to system; service layer may obtain additional information relevant to the query, such as active time data indicating a duration of work on a project in the product, preparation time data indicating additional elapsed time between a start and an end of the project, and/or other data; also see paragraph [0039]; also see Fig. 1; also see paragraph [0021]-[0023]);
determining a relevant context using the large language model responsive to training data of the large language model and at least a portion of the vectorized data in the at least one vector database (paragraph [0022], vector DB can be any vector database, such as Open Search or other products; vector DB can store data in a standard format, such as query data and/or context data; also see paragraph [0040], generating vector for query data and/or other data obtain, where the vector is a structured database entry; also see paragraph [0028], identify context data in vector DB 130; also see paragraph [0046], obtaining context vectors from vector DB; context vectors may include, for example, at least one record of a previously successful data entry in a standardize format that resulted in a previously validated response from LLM; noted, “context vectors may include, for example, at least one record of a previously successful data entry in a standardize format that resulted in a previously validated response from LLM” is interpreted as “determining a relevant context using the large language model responsive to training data of the large language model and at least a portion of the vectorized data in the at least one vector database”; also see paragraph [0016], [0029]);
returning, in response to the query, a relevant context generated using the large language model (paragraph [0022], vector DB can be any vector database, such as Open Search or other products; vector DB can store data in a standard format, such as query data and/or context data; also see paragraph [0040], generating vector for query data and/or other data obtain, where the vector is a structured database entry; also see paragraph [0028], identify context data in vector DB 130; also see paragraph [0046], obtaining context vectors from vector DB; context vectors may include, for example, at least one record of a previously successful data entry in a standardize format that resulted in a previously validated response from LLM);
and generating and outputting, using the large language model and based on the relevant context, one or more portions of the report (paragraph [0047], forming an LLM prompt using the vector obtained; the prompt can include the query from product and the vectors obtained at 502 and 504 and may be engineered according to a predetermined format or schema; also see paragraph [0061]-[0062], formatting the response from the LLM and/or additional information tin an object that is useable by product; generating a response object having the determined format and, may send the response object to product).
MOURYA does not explicitly disclose: creating vectorized data corresponding to from one or more documents stored in from one or more document storage locations, wherein the vectorized data comprises numerical vector values representing contents of the one or more documents.
AJMERA teaches creating vectorized data corresponding to from one or more documents stored in from one or more document storage locations, wherein the vectorized data comprises numerical vector values representing contents of the one or more documents ( paragraph [0036], documents and/or other data can be uploaded from a user device or from one or more applications; also see paragraph [0056], a corpus of data including variety of documents of different types may be received by server device; also see pargraph [0070], the embedding generation module receives documents data, or chunks and generates embedding for the chunks; also see paragraph [0060], embeddings are generated for the chunk, for example, a vector representation may be used as a numerical representation of a chunk of data; noted, “a vector representation may be used as a numerical representation of a chunk of data” is interpreted as “wherein the vectorized data comprises numerical vector values representing contents of the one or more documents”).
It would have been obvious to one of ordinary skill in art before the effective filing date of the claim invention to include creating vectorized data corresponding to from one or more documents stored in from one or more document storage locations, wherein the vectorized data comprises numerical vector values representing contents of the one or more documents into automatic query enhancement of MOURYA.
Motivation to do so would be to include creating vectorized data corresponding to from one or more documents stored in from one or more document storage locations, wherein the vectorized data comprises numerical vector values representing contents of the one or more documents for improve searching and processing (AJMERA, paragraph [0060], line 5).
MOURYA as modified by AJMERA further teach:
storing the vectorized data in at least one vector database (AJMERA, pargraph [0070], the embedding generation module receives documents data, or chunks and generates embedding for the chunks; also see paragraph [0060], embeddings are generated for the chunk; also see paragraph [0061], a server device may store the embeddings in a vector database; while MOURYA, paragraph [0022], vector DB can be any vector database, such as Open Search or other products; vector DB can store data in a standard format, such as query data and/or context data).
Regarding claim 2, MOURYA as modified by AJMERA teach all claimed limitations as set forth in rejection of claim 1, further teach wherein generating and outputting the one or more portions of the report includes creating portions of the report based on the one or more documents from the one or more document storage locations according to a report schema (MOURYA, paragraph [0047], forming an LLM prompt using the vector obtained; the prompt can include the query from product and the vectors obtained at 502 and 504 and may be engineered according to a predetermined format or schema; also see paragraph [0061]-[0062], formatting the response from the LLM and/or additional information tin an object that is useable by product; generating a response object having the determined format and, may send the response object to product).
Regarding claim 3, MOURYA as modified by AJMERA teach all claimed limitations as set forth in rejection of claim 2, further teach wherein the report schema defines various formatting and structural parameters for the report (MOURYA, paragraph [0047], forming an LLM prompt using the vector obtained; the prompt can include the query from product and the vectors obtained at 502 and 504 and may be engineered according to a predetermined format or schema; also see paragraph [0061]-[0062], formatting the response from the LLM and/or additional information tin an object that is useable by product; generating a response object having the determined format and, may send the response object to product; also see Fig. 7A-C).
As per claims 11-13, these claims are rejected on grounds corresponding to the same rationales given above for rejected claims 1-3 respectively and are similarly rejected.
Claims 4 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over MOURYA (Pub. No. 2025/0390718 A1) in view of AJMERA (U.S. Pub. No. 2025/0181899 A1), further in view of Tiwari et al. (U.S. Pub. No. 2023/0132337 A1).
Regarding claim 4, MOURYA as modified by AJMERA teach all claimed limitations as set forth in rejection of claim 1, but do not explicitly disclose: wherein the at least one vector database includes a first vector database and a second vector database, wherein the first vector database includes vectorized data corresponding to documents pertaining to prior data associated with projects other than the current project, and wherein the second vector database includes vectorized data corresponding to documents pertaining to current data associated with the current project.
Tiwari teaches wherein the at least one vector database includes a first vector database and a second vector database, wherein the first vector database includes vectorized data corresponding to documents pertaining to prior data associated with projects other than the current project, and wherein the second vector database includes vectorized data corresponding to documents pertaining to current data associated with the current project (paragraph [0101], the project management database of the cognitive engine may include measurement vectors that may be fed as input into a neural training database; also see paragraph [0052], based on historical data and current data, the cognitive engine and/or the system for software development may configure to automatically suggest all those stories that the user team should work on in the next Sprint).
It would have been obvious to one of ordinary skill in art before the effective filing date of the claim invention to include wherein the at least one vector database includes a first vector database and a second vector database, wherein the first vector database includes vectorized data corresponding to documents pertaining to prior data associated with projects other than the current project, and wherein the second vector database includes vectorized data corresponding to documents pertaining to current data associated with the current project into automatic query enhancement of MOURYA.
Motivation to do so would be to include wherein the at least one vector database includes a first vector database and a second vector database, wherein the first vector database includes vectorized data corresponding to documents pertaining to prior data associated with projects other than the current project, and wherein the second vector database includes vectorized data corresponding to documents pertaining to current data associated with the current project to automatically assign story points to sprints of the software development project (Tiwari, paragraph [0002], line 8-10).
As per claim 14, this claim is rejected on grounds corresponding to the same rationales given above for rejected claim 4 and is similarly rejected.
Claims 5, 8-9, 15, 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over MOURYA (Pub. No. 2025/0390718 A1) in view of AJMERA (U.S. Pub. No. 2025/0181899 A1) and Tiwari et al. (U.S. Pub. No. 2023/0132337 A1), further in view of Okazaki (Pub. No. 2026/0017613 A1).
Regarding claim 5, MOURYA as modified by AJMERA and Tiwari teach all claimed limitations as set forth in rejection of claim 4, but do not explicitly disclose: determining whether to modify the report with additional vectorized data from the second vector database.
Okazaki teaches: determining whether to modify the report with additional vectorized data from the second vector database (paragraph [0096]-[0097], updating relevant documents; identifies one or more projected content item embeddings in the information flow pattern; extracting projected modifications on content items from the content item embedding; based on these content item embedding, the content item embedding information system can identify relevant documents and determine modification for those documents; the content item can provide a proposed amendment to one or more user accounts associated with relevant document; in response to approval, the content embedding information can implement the change; also see paragraph [0092], the content item embedding information system can generate a project report including information from the first document relevant; in combination with the teaching of vectorized data corresponding to current data taught by Tiwari (paragraph [0101], the project management database of the cognitive engine may include measurement vectors that may be fed as input into a neural training database; also see paragraph [0052], based on historical data and current data, the cognitive engine and/or the system for software development may configure to automatically suggest all those stories that the user team should work on in the next Sprint), it reads on as claimed).
It would have been obvious to one of ordinary skill in art before the effective filing date of the claim invention to include determining whether to modify the report with additional information into automatic query enhancement of MOURYA.
Motivation to do so would be to include determining whether to modify the report with additional information, utilizing a content item modification to predict and execute information flow pattern between teams for the modified content item (Okazaki, paragraph [0006], line 16-18).
Regarding claim 8, MOURYA as modified by AJMERA, Tiwari and Okazaki teach all claimed limitations as set forth in rejection of claim 5, further teach: wherein, based on determining not to modify the report, generating and outputting the one or more portions of the report includes creating portions of the report based on the documents pertaining to the prior data (Okazaki, paragraph [0096]-[0097], updating relevant documents; identifies one or more projected content item embeddings in the information flow pattern; extracting projected modifications on content items from the content item embedding; based on these content item embedding, the content item embedding information system can identify relevant documents and determine modification for those documents; the content item can provide a proposed amendment to one or more user accounts associated with relevant document; in response to approval, the content embedding information can implement the change; also see paragraph [0084], line generating the predicted content item embeddings in response to user rejection or approval of prior prediction; also see paragraph [0092], the content item embedding information system can generate a project report including information from the first document relevant; noted, as the change is rejected, thus it is an indication that the changes is not implemented as the document version is unchanged; the project report is generated based on relevant/unchanged documents, which read on as claimed).
Regarding claim 9, MOURYA as modified by AJMERA, Tiwari and Okazaki teach all claimed limitations as set forth in rejection of claim 5, further teach: wherein, based on determining to modify the report with the additional information, generating and outputting the one or more portions of the report includes: creating portions of the report based on the documents pertaining to the prior data; and creating portions of the report based on the documents pertaining to the current data associated with the current project (Okazaki, paragraph [0096]-[0097], updating relevant documents; identifies one or more projected content item embeddings in the information flow pattern; extracting projected modifications on content items from the content item embedding; based on these content item embedding, the content item embedding information system can identify relevant documents and determine modification for those documents; the content item can provide a proposed amendment to one or more user accounts associated with relevant document; in response to approval, the content embedding information can implement the change; also see paragraph [0092], the content item embedding information system can generate a project report including information from the first document relevant).
As per claims 15, 18-19, these claims are rejected on grounds corresponding to the same rationales given above for rejected claims 5, 8-9 respectively and are similarly rejected.
Claims 6-7 and 16-17 are rejected under 35 U.S.C. 103 as being unpatentable over MOURYA (Pub. No. 2025/0390718 A1) in view of AJMERA (U.S. Pub. No. 2025/0181899 A1), Tiwari et al. (U.S. Pub. No. 2023/0132337 A1), and Okazaki (Pub. No. 2026/0017613 A1), further in view of IMANI et al. (U.S. Pub. No. 2024/0362417 A1).
Regarding claim 6, MOURYA as modified by AJMERA, Tiwari and Okazaki teach all claimed limitations as set forth in rejection of claim 5, but do not explicitly disclose wherein determining whether to modify the report with the additional information includes: reviewing, using a second large language model, one or more outputs from the large language model; and determining, based on the review using the second large language model, whether to generate new outputs using the large language model.
IMANI teaches: wherein determining whether to modify the report with the additional information includes: reviewing, using a second large language model, one or more outputs from the large language model; and determining, based on the review using the second large language model, whether to generate new outputs using the large language model (Fig. 1, paragraph [0018], the LLM auditor system include an LLM 106 provides LLM outputs 14 in response to received inputs; also see pargraph [0025], the classifier model learns the distribution over the readability features; the classifier model 110 uses the distribution over the features in determining the confidence score in an accuracy of the LLM output).
It would have been obvious to one of ordinary skill in art before the effective filing date of the claim invention to include wherein determining whether to modify the report with the additional information includes: reviewing, using a second large language model, one or more outputs from the large language model; and determining, based on the review using the second large language model, whether to generate new outputs using the large language mode into automatic query enhancement of MOURYA.
Motivation to do so would be to include wherein determining whether to modify the report with the additional information includes: reviewing, using a second large language model, one or more outputs from the large language model; and determining, based on the review using the second large language model, whether to generate new outputs using the large language model to overcome issue with it can be difficult to determine if the output produced by LLMs is accurate or simply a hallucination (IMANI, paragraph [0001], line 5-8).
Regarding claim 7, MOURYA as modified by AJMERA, Tiwari, Okazaki and IMANI teach all claimed limitations as set forth in rejection of claim 6, further teach: wherein the review using the second large language model provides feedback on an accuracy of the one or more outputs from the large language model (IMANI, Fig. 1, paragraph [0018], the LLM auditor system include an LLM 106 provides LLM outputs 14 in response to received inputs; also see pargraph [0025], the classifier model learns the distribution over the readability features; the classifier model 110 uses the distribution over the features in determining the confidence score in an accuracy of the LLM output; the confidence score is a value between 0 and 1, where 0 is an incorrect answer (hallucination) and 1 is correct answer; noted, “confidence score” is interpreted as feedback regarding LLM output).
As per claims 16-17, these claims are rejected on grounds corresponding to the same rationales given above for rejected claims 6-7 respectively and are similarly rejected.
Claims 10 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over MOURYA (Pub. No. 2025/0390718 A1) in view of AJMERA (U.S. Pub. No. 2025/0181899 A1), Tiwari et al. (U.S. Pub. No. 2023/0132337 A1), and Okazaki (Pub. No. 2026/0017613 A1), further in view of Zimmerman (U.S. Patent No. 12,008,308 B1).
Regarding claim 10, MOURYA as modified by AJMERA, Tiwari and Okazaki teach all claimed limitations as set forth in rejection of claim 9, further teach wherein creating portions of the report based on the documents pertaining to the prior data and creating portions of the report based on the documents pertaining to the current data associated with the current project includes: using a third large language model to generate queries based on the current data associated with the current project to retrieve another relevant context associated with the current data (MOURYA, paragraph [0026], service layer may obtain query information; when a user enters a query, product may send the query to system; service layer may obtain additional information relevant to the query, such as active time data indicating a duration of work on a project in the product, preparation time data indicating additional elapsed time between a start and an end of the project, and/or other data; also see paragraph [0039]) but do not explicitly disclose: creating a new input by combining one or more responses from the large language model with information pertaining to the current data and sending the new input to the large language model to generate another response.
Zimmerman teaches: creating a new input by combining one or more responses from the large language model with information pertaining to the current data and sending the new input to the large language model to generate another response (Fig. 4, col. 20, line 35-43, WIP [work in progress] structured resource; also see col. 21, line 30-54, WIP structure resource can be or include a depiction or rendering of the current or work-in-progress state of the structured resource being completed; WIP structured resource can be updated in real time as suggested content is selected for inclusion in the WIP structured resource; also see col. 10, line 65-67 and col. 11, line 1-14, instructions provided to the machine-learned content generation; and can be determined based on context data; also see col. 13, line 16-20, output resource can be output by structured resource completion system; output resource can be output based on content generated by structured resource completion system; also see col. 9, line 54-65, compile input data structures from existing content of a work-in-progress (WIP) structure resource; also see col. 18, line 8-20, the input interface can include selectable suggested portion(s) output by the machine-learned content generation model in response to the input provided in the text entry fields; based on the selections to the selectable suggested portion(s), a WIP structured resource rendered can be updated; noted, as WIP is a process of continuing of work-in-progress structured resources as content is expanding based on previous output generated content in regards to context data, which reads on as claimed).
It would have been obvious to one of ordinary skill in art before the effective filing date of the claim invention to include creating a new input by combining one or more responses from the large language model with information pertaining to the current data and sending the new input to the large language model to generate another response into automatic query enhancement of MOURYA.
Motivation to do so would be to include creating a new input by combining one or more responses from the large language model with information pertaining to the current data and sending the new input to the large language model to generate another response to improve the efficiency of the interface (Zimmerman, col. 4, line 51).
MOURYA as modified by Zimmerman further teach: generating one or more outputs based on the new input and the retrieved other context (MOURYA, paragraph [0022], vector DB can be any vector database, such as Open Search or other products; vector DB can store data in a standard format, such as query data and/or context data; also see paragraph [0040], generating vector for query data and/or other data obtain, where the vector is a structured database entry; also see paragraph [0046], obtaining context vectors from vector DB; also see paragraph [0047], forming an LLM prompt using the vector obtained; the prompt can include the query from product and the vectors obtained at 502 and 504 and may be engineered according to a predetermined format or schema; also see paragraph [0061]-[0062], formatting the response from the LLM and/or additional information tin an object that is useable by product; generating a response object having the determined format and, may send the response object to product).
As per claim 20, this claim is rejected on grounds corresponding to the same rationales given above for rejected claim 10 and is similarly rejected.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KEN HOANG whose telephone number is (571)272-8401. The examiner can normally be reached M-F 7:30am-5:00pm.
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, Charles Rones can be reached at (571)272-4085. 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.
/KEN HOANG/Examiner, Art Unit 2168
