DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This action is responsive to amendment filed on 5/26/26. Claims 1-20 are pending for examination.
Abstract analysis: The method of embedding queries and targeted documents to query large language model comprises practical application in AI computations and searching and is therefore compliant.
Claim Objections
Regarding claim 3 is objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (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.
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.
Claim(s) 1, 2 and 4-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Krishnan et al (USPN. 2023/0306087) in view of Pisner (USPN. 2024/0161017).
Regarding claims 1, 15 and 20, Krishnan discloses a method, apparatus and program comprising non- transitory computer readable storage medium storing instructions, for efficient handling of queries, the method comprising (fig. 1):
receiving, by communications hardware, a query from a user device (fig. 1, par. 29, query input, may be received by the server);
generating, by analysis circuitry, an embedding representation of the query (fig. 1B and 1C, par. 51, query is converted and encoded into new embeddings);
performing, by the analysis circuitry, a similarity comparison between the embedding representation of the query and a set of embedding representations (fig. 1C, items 172 and 174, par. 51, “query representations correspond to the embedding representations of the asset index library),
wherein each embedding representation represents components of a single historical document section within a historical document (figs. 1C and 2, pars. 59-60, each embeddings and asset representations are trained to encode generic knowledge of semantic concepts wherein query representation models 176 are trained to map concepts and tokens in input queries to concepts of asset training data, the asset training data and index library is equated to historical document and historical document section);
selecting, by the analysis circuitry and based on the similarity comparison, a relevant embedding representation of a historical document section stored in the historical document repository for the query (fig. 1D illustrates the training asset representation models and query representation models, see pars. 51, 52 and 59, ML models used in conjunction with plurality of representation models to perform searches of multimodal queries based on similarity wherein the embeddings may be in the same size for assets and query embeddings, see further fig. 2 the first two phases training and offline models , and par. 37, repository);
selecting, by the analysis circuitry, a large language model (LLM) from a plurality of large language models, wherein selection of the large language model (LLM) is based on a designated modality type of the target LLM and a modality type of the relevant (not taught “embedding”) representation of the historical document section (par. 61 and 64, LLM models 330 and 332 are selected for data analysis, Krishnan) but does not explicitly teach the LLM is a target LLM and does not explicitly teach the data selected is already embedded.
Pisner teaches target LLM selection on embedded data (fig. 15E, par. 189 “The multimodal CETL method may also comprise additional steps for training, testing, and validating one or more Multimodal Connectome Ensemble Predictive Models (mCEPMs) (43 in FIG. 15E) using the final jointly embedded one or more mCFVs (45-46 in FIG. 15E). At 1040 in FIG. 10C, the method may include selecting one or more Multimodal Connectome Ensemble Predictive Models (mCEPMs) machine learning models in the target domain (42 in FIG. 15E)” note, target LLM selected in target domain is mCEPM for embedding mCFVs, Pisner).
It would have been obvious to one of ordinay skill in the art at the effective filing date of the application to integrate Pisner models on embedded data in Krishnan training and retrieving multimodal asset system (fig. 2, Krishnan). One would have been motivated to combine the systems to better handle target data that is to be embedded and already has been embedded.
Krishnan in view of Pisner teach,
querying, by the analysis circuitry, the target large language model using the embedding representation of the query and the relevant embedding representation of the historical document section to generate a query response; (fig. 6, items 620-625, pars. 71-72, query and compare multimodal data to multimodal assets, by using different models as cited above, modified Krishnan); and
providing, by the communications hardware, the query response to the user device (fig. 6, item 630, par. 73, search result is provided, modified Krishnan).
2. Krishnan in view of Pisner teach: receiving, by the communications hardware, the historical document, partitioning, by the analysis circuitry, the historical document into one or more historical document sections, performing, by the analysis circuitry, a document embedding routine for each historical document section of the one or more historical document sections, the document embedding routine comprising: tokenizing, by the analysis circuitry, the historical document section into a plurality of historical document section tokens, and generating, by the analysis circuitry and based on the plurality of historical document section tokens, an embedding representation of the historical document section and storing, by the analysis circuitry, the respective embedding representation for each historical document section in the historical document repository (fig. 1A, item 122, par. 37, repository is representative of databases relating to training models, asset libraries and vectorized representations of assets and stored. See pars. 45 and 51, multimodal assets comprise tensor generation including vector representations for each of the elements of the asset and provides multilinear relationship between the vector representations in the tensor. Each row/section may represent different modality of each asset such as text segments and image segments, Krishnan).
4. Krishnan in view of Pisner teach, wherein the document embedding routine for the target historical document section comprises detecting, by the analysis circuitry, a first modality type for content within the target historical document section; detecting, by the analysis circuitry, a second modality type for the content within the historical document section, wherein the second modality type is different than the first modality type; and in response to detecting that the second modality type is different than the first modality type, partitioning, by the analysis circuitry, the historical document section into a plurality of historical document subsections based on a corresponding modality type, wherein each of the plurality of historical document subsections may be tokenized into a plurality of historical document section tokens (see pars. 45 and 51, multimodal assets comprise tensor generation including vector representations for each of the elements of the asset and provides multilinear relationship between the vector representations in the tensor. Each row/section may represent different modality of each asset such as text segments and image segments, Krishnan).
5. Krishnan in view of Pisner teach, determining, by the analysis circuitry, whether the query requests an evaluation for an input document; in response to determining that the query requests the evaluation for the input document, partitioning, by the analysis circuitry, the input document into a plurality of target document sections, tokenizing, by the analysis circuitry, each target document section into a plurality of target document section tokens generating, by the analysis circuitry and based on the plurality of target document section tokens, an embedding representation of each target document section and querying, by the analysis circuitry, the target large language model using the embedding representation for each target document section and the relevant embedding representation of the historical document section (fig. 1C, pars. 49 and 51, text query is submitted as a search query and a multimodal document, the query is converted to respective embeddings based on content type, i.e., textual and image and (figs. 1C and 2, pars. 59-60, each embeddings and asset representations are trained to encode generic knowledge of semantic concepts wherein query representation models 176 are trained to map concepts and tokens in input queries to concepts of asset training data, the asset training data and index library is equated to historical document and historical document section, Krishnan), wherein the query response further comprises an evaluation assessment and the evaluation assessment comprises an evaluation status for each target document section (pars. 35 and 50, user query comprises a plurality of requirements and thresholds, such as image must match at least 95%, this requires the models to retrieve the assets that comply to the query requirements).
6. Krishnan in view of Pisner teach, wherein the evaluation assessment comprises an evaluation reason for the evaluation status (pars. 35 and 50, user query comprises a plurality of requirements and thresholds, such as image must match at least 95%, this requires the models to retrieve the assets that comply to the query requirements, see also par. 56, the evaluation reason is meeting additional data 138 criteria such as specified asset type, Krishnan).
7. Krishnan in view of Pisner teach, wherein evaluation assessment further comprises a recommendation for a target document section (pars. 39 and 56, content recommendation and meeting criteria specified, Krishnan).
8. Krishnan in view of Pisner teach, further comprising performing, by automation circuitry, a proactive action in an instance in which the evaluation assessment comprises at least one evaluation status indicative that a target document section is non-compliant (pars. 35 and 50, user query comprises a plurality of requirements and thresholds, such as image must match at least 95%, this requires the models to retrieve the assets that comply to the query requirements, see also par. 56, the evaluation reason is meeting additional data 138 criteria such as specified asset type, result may indicate no result meets the requirement, Krishnan).
9. Krishnan in view of Pisner teach, wherein performing the proactive action further comprises automatically updating, by the automation circuitry, the input document to (i) modify current language or (ii) insert new language (pars. 24, 29 and 39, system automatically provides recommendations for inserting content into a document, interactively edit, and par. 50, may insert certain types of visual assets into decuments, Krishnan).
10. Krishnan in view of Pisner teach, further comprising: detecting, by the analysis circuitry, a first modality type for content within a target document section, detecting, by the analysis circuitry, a second modality type for the content within the target document section, wherein the second modality type is different than the first modality type, and in response to detecting that the second modality type is different than the first modality type, partitioning, by the analysis circuitry, the target document section into a plurality of target document subsections based on a corresponding modality type, wherein each of the plurality of target document subsections may be tokenized into a plurality of target document section tokens (see pars. 45 and 51, multimodal assets comprise tensor generation including vector representations for each of the elements of the asset and provides multilinear relationship between the vector representations in the tensor. Each row/section may represent different modality of each asset such as text segments and image segments for query and asset matching, Krishnan).
11. Krishnan in view of Pisner teach, further comprising: determining, by the analysis circuitry, whether a number of target document section tokens for a target document section would exceed a maximum token limit and in response to determining the maximum token limit would be exceeded, partitioning, by the analysis circuitry, the target document section into a plurality of target document subsections, wherein each of the plurality of target document subsections may be tokenized into a plurality of target document section tokens (pars. 50 and 59, size restrictions and specific types of data is analyzed/partitioned with the concepts and tokens in input queries and concepts of asset data, Krishnan).
12. Krishnan in view of Pisner teach, performing, by training circuitry, a training routine, the training routine comprising: initializing, by the training circuitry, a base large language model, and adjusting, by the training circuitry, the base large language model based on a domain-specific training data set (pars. 31, 32 and 57, labeling data may be initially used to train LLM, supplemental data and training may be added to fine tune, labeling implies domain-specific training, Krishnan).
13. Krishnan in view of Pisner teach, receiving, by the communications hardware, annotated authentic domain-specific documents, wherein: each annotated authentic domain-specific document includes (i) a corresponding authentic domain-specific document, (ii) a training query prompt, (iii) and an expected response to the training query prompt, the domain-specific training data set comprises the annotated authentic domain- specific documents (pars. 39, 56 and 70, search results comprise documents responsive to query prompt and content recommendation such as annotations, Krishnan).
14 Krishnan in view of Pisner teach, wherein the historical document is at least one of a model development document and a model validation document (pars. 32-33, different types of assets, the training data may be obtained from a repository or device generated thus model development, data is validated, Krishnan).
Regarding apparatus claims 16-19, they comprise substantially the same subject matter as rejected method claims 2-14, above, and are therefore rejected on the merits.
Response to Arguments
Applicant’s arguments with respect to claim(s) 1, 2 and 4-20 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Regarding claim 3 is objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure in the field of embedded searching:
USPN. 20250111157 USPN. 20250156634 Abstract: multi LLM embedded searching
THIS ACTION IS MADE FINAL. 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 MARCIN R FILIPCZYK whose telephone number is (571)272-4019. The examiner can normally be reached M-F 7-4 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, Kavita Stanley can be reached at 571-272-8352. 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.
July 21, 2026
/MARCIN R FILIPCZYK/Primary Examiner, Art Unit 2153
Prosecution Insights