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 .
DETAILED ACTION
Claims 1 – 20 posted on 06/27/2025 are presently pending in the application and have been examined below, of which claims 1, 11 and 17 are presented in independent form.
Priority
This application is a continuation of application 17/900394, now patent No. 12373554, which claimed priority date by 08/31/2022. Accordingly, the effective priority date for the subject matter defined in the pending claims of the instant application is 08/31/2022.
Drawings
The drawings were received on 06/27/2025. These drawings are accepted.
Information Disclosure Statement
The information disclosure statement (IDS) dated 06/02/2026 has been received and considered.
Examiner Notes
Examiner cites paragraphs, columns 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 entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by prior art or disclosed by the examiner.
Double Patenting
The non-statutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the "right to exclude" granted by a patent and to prevent possible harassment by multiple assignees. A non-statutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on non-statutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b). [AltContent: rect]
The filing of a terminal disclaimer by itself is not a complete reply to a non-statutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13. [AltContent: rect]
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/ patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/ patents/apply/applying-online/eterminal-disclaimer.
Claims 1 – 20 rejected on the ground of non-statutory obviousness-type double patenting as being unpatentable over claims 1 - 20 of U.S. Patent No. 12373554 (Reference Patent) in view of Lee, LP and Dangoor, see below. Although the claims at issue are not identical, they are not patentably distinct from each other because claims of the Reference Patent anticipate claims the instant application as shown below for the first claim set where most of the limitations in claim 1 of instant application are anticipated by limitations in claim 1 of the reference patent.
Claim #
Instant Application
Reference Patent (12373554)
Claim #
1
1.A computer-implemented method for generating security language queries from unstructured user input with a large language model (LLM), the method comprising:
receiving, at a computer system, an input security hunting user query reflecting a user intention;
generating a prompt for input into the LLM, the prompt comprising the input security hunting user query, query metadata, and at least one example shot comprising an example security hunting user query and a corresponding example security language query,
wherein generating the prompt comprises using a trained machine learning model to:
generate the query metadata from the input security hunting user query, and select the at least one example shot, from among a set of example shots, based on the input security hunting user query;
inputting the prompt into the LLM; and receiving, from the LLM, a security language query responsive to the prompt and reflecting the user intention.
1.A computer-implemented method comprising: receiving, at a computer system, an input security hunting user query indicating a user intention; selecting, using a trained machine learning model and based on the input security hunting user query, an example user security hunting query and corresponding example security language query;
generating, using the trained machine learning model, query metadata from the input security hunting user query;
generating a prompt, the prompt comprising: the input security hunting user query, the selected example user security hunting query, and the corresponding example security language query,
and the generated query metadata;
inputting the prompt to a large language model; and receiving a security language query from the large language model corresponding to the input security hunting user query reflective of the user intention.
1
The reference patent (12373554) discloses a method for generation a security language query by training a machine learning model for usage respective prompts for large learning model. Comparison between instant application and reference patent indicates that both are based on the same SPECS using identical drawings with respective disclosures. Both documents have the same applicant/assignee, same inventors and disclose the same inventive concept.
Compared to the reference patent, the claim set of the instant application is focused on more detailed usage of the large language model, LLM, by respective training of a machine learning model. Many of the limitations in the instant application are anticipated by the reference patent as indicated in Table above. Disclosure of the concept in independent claims of the instant application is broader than in reference patent. For a person having ordinary skills in the art would have been obvious that any language model, e.g., the LLM model, may be included in trained machine learning model that could not indicate a novelty, see MPEP § 804, § 2136, § 2137, § 2138, and § 2154.
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the reference patent, in view of respective features presented by Lee, LP and Dangoor which disclose methods for explicit implementation of a machine learning model trained using the LLM.
The independent claims are rejected under the judicially created doctrine of double patenting as being directed to the same invention as that set forth in claims of the United States Patent No. 1273554 in view of Lee and LP.
The dependent claims of the current application recite language similar to the dependent claims of the reference patent and are covered by the reference patent in view of Lee, LP and Dangoor. Accordingly, the instant application is identified as obviousness-type double patenting.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1 and 6 – 10 are rejected under 35 U.S.C. 103 as being unpatentable over Lee et al. (US 20230315856) (hereafter Lee) and in view of Lamy-Poirier (US 20220383084) (hereafter LP).
As per claim 1 Lee discloses: A computer-implemented method for generating security language queries from unstructured user input with a large language model (LLM) (Lee, in para [0004-0005] and Fig. 11 discloses training of machine learning model by creating inputs based on natural language phrases, i.e., including large language model technique), the method comprising: receiving, at a computer system, an input security hunting user query reflecting a user intention (Lee, in para [0032] discloses generation of inputs for ML training using user inputs), generating a prompt for input into the LLM (Lee, in para. [0062] discloses generation of prompts associated with respective training operation), the prompt comprising the input security hunting user query (Examiner note: security hunting is met by a search for security threat, as disclosed by applicant in para. [0002] of SPECS) (Lee, in para [0029-0030] discloses operations of a management system for a search of security threats; the data are used to generate complex queries as inputs for machine learning model training [0030]),
[query metadata,]
and at least one example shot comprising an example security hunting user query and a corresponding example security language query (Lee, in para. [0062] discloses creation of prompts using different language phrases, i.e., example shots, for ML training using the LLM technique),
[wherein generating the prompt comprises using a trained machine learning model to: generate the query metadata from the input security hunting user query,]
and select the at least one example shot, from among a set of example shots, based on the input security hunting user query; inputting the prompt into the LLM; and receiving, from the LLM, a security language query responsive to the prompt and reflecting the user intention (Lee, in para. [0042, 0048] discloses usage of natural language data, i.e. LLM data, to form a template query for machine learning model training including management of security threat detection and mitigation).
Lee does not explicitly disclose creation and processing of metadata for ML training including LLM. However, LP discloses:
query metadata,
wherein generating the prompt comprises using a trained machine learning model to: generate the query metadata from the input security hunting user query
(LP, in para. [0031, 0034, 0072] discloses the Platform as a Service, PaaS system, for training machine learning models, using creation and processing metadata by implementing PaaS software controlling and managing database nodes, language queries for ML training via operation of respective virtual machines [0078, 0097] ).
It would have been obvious to one having ordinary skill in the art, before the effective filing date of the invention to modify Lee, in view of teaching of LP because they both disclose training of machine learning models using LLM and including security threat detection and treatment. The motivation to combine would be to modify method of Lee for usage and operations of metadata for ML training.
As per claim 6 Lee as modified discloses: The method of claim 1, wherein the query metadata comprises table schema data indicating tables or columns relevant to the security language query. (LP, in para. [0031, 0034, 0072] discloses the Platform as a Service, PaaS system, for training machine learning models, using creation and processing metadata by implementing PaaS software controlling and managing database nodes, language queries for ML training via operation of respective virtual machines [0078, 0097]; LP, in Figs. 7, 8 depict schedule, i.e., Table-schema, of ML training using proposed layered gradient accumulation technology [0118] as an advanced multi-layered machine learning technique [0122] used for a security threat detection [0077]).
It would have been obvious to one having ordinary skill in the art, before the effective filing date of the invention to modify Lee, in view of teaching of LP because they both disclose training of machine learning models using LLM and including security threat detection and treatment. The motivation to combine would be to modify method of Lee for usage and operations of metadata for ML training.
As per claim 7 Lee as modified discloses: The method of claim 1, wherein generating the prompt further comprises (Lee, in para. [0062] discloses generation of prompts associated with respective training operation): generating, for inclusion into the prompt, example metadata from the example security language query of the at least one example shot (LP, in para. [0031, 0034, 0072] discloses the Platform as a Service, PaaS system, for training machine learning models, using creation and processing metadata by implementing PaaS software controlling and managing database nodes, language queries for ML training via operation of respective virtual machines [0078, 0097]).
It would have been obvious to one having ordinary skill in the art, before the effective filing date of the invention to modify Lee, in view of teaching of LP because they both disclose training of machine learning models using LLM and including security threat detection and treatment. The motivation to combine would be to modify method of Lee for usage and operations of metadata for ML training.
As per claim 8 Lee as modified discloses: The method of claim 1, wherein the prompt further comprises a preamble (Lee, in para. [0062] discloses generation of prompts associated with respective training operation) indicating that the LLM should generate a security language query corresponding to the input security hunting user query (Lee, in para [0029-0030] discloses operations of a management system for a search of security threats; the data are used to generate complex queries as inputs for machine learning model training [0030]).
As per claim 9 Lee as modified discloses: The method of claim 1, further comprising: displaying the security language query on a display (LP, in para. [0042] discloses a PaaS software control module operating threat detection and ML training: THE Results are displayed on a screen or using respective GUI system).
It would have been obvious to one having ordinary skill in the art, before the effective filing date of the invention to modify Lee, in view of teaching of LP because they both disclose training of machine learning models using LLM and including security threat detection and treatment. The motivation to combine would be to modify method of Lee for usage of a GUI to display detection results and training process.
As per claim 10 Lee as modified discloses: The method of claim 1, further comprising: executing the security language query in a security system (Lee, in para. [0030] discloses execution of language query in the cybersecurity management system).
Claims 2 – 5 and 11 – 20 are rejected under 35 U.S.C. 103 as being unpatentable over Lee et al. (US 20230315856) (hereafter Lee), in view of Lamy-Poirier (US 20220383084) (hereafter LP), and in view of Dangoor.et al. (US 20230237053) (hereafter Dangoor).
As per claim 2 Lee as modified does not explicitly disclose: generation of a score for respective training operations, e.g., predictions based on search actions. However, Dangoor discloses:
The method of claim 1, wherein using the trained machine learning model to select the at least one example shot (Lee, in para. [0062] discloses creation of prompts using different language phrases, i.e., example shots, for ML training using the LLM technique) comprises: using the trained machine learning model to generate scores indicative of a relevance to the user security hunting query of the set of example shots; and selecting the at least one example shot from the set based on the scores (Dangoor in para. [0026-0027] discloses generation of a score indicating a probability of query-related predictions by training using LLM model).
It would have been obvious to one having ordinary skill in the art, before the effective filing date of the invention to modify Lee-LP, in view of teaching of Dangoor because they all disclose training of machine learning models using LLM. The motivation to combine would be to modify method of Lee-LP for usage of a score for respective training operations using LLM.
As per claim 3 Lee as modified discloses: The method of claim 2, wherein selecting the at least one example shot from the set based on the scores comprises selecting a specified number of highest-scoring shots (Dangoor in para. [0062] discloses calculation and processing a highest predictive score of actions, i.e., related to a detected activity in the system).
It would have been obvious to one having ordinary skill in the art, before the effective filing date of the invention to modify Lee-LP, in view of teaching of Dangoor because they all disclose training of machine learning models using LLM. The motivation to combine would be to modify method of Lee-LP for usage of a score for respective training operations using LLM.
As per claim 4 Lee as modified discloses: The method of claim 1, further comprising: generating at least one additional prompt that differs from the prompt in at least one of the at least one example shot (Lee, in para. [0062] discloses creation of prompts using different language phrases, i.e., example shots, for ML training using the LLM technique) or the query metadata; inputting the at least one additional prompt into the LLM; receiving, from the LLM and in response to the at least one additional prompt, at least one respective additional security language query reflecting the user intention (Dangoor in para. [0062] discloses calculation and processing the highest predictive score of actions, i.e., related to a detected activity in the system, and indicating user activity/intention); scoring the security language query and the at least one additional security language query; and selecting a top scoring security language query from among the security language query and the at least one additional security language query (Dangoor in para. [0071] discloses ML training using the LLM model by processing each respective query and using highest determined score).
It would have been obvious to one having ordinary skill in the art, before the effective filing date of the invention to modify Lee-LP, in view of teaching of Dangoor because they all disclose training of machine learning models using LLM. The motivation to combine would be to modify method of Lee-LP for usage of a score for respective training operations using LLM.
As per claim 5 Lee as modified discloses: The method of claim 4, wherein generating the prompt and the at least one additional prompt comprises (Lee, in para. [0062] discloses generation of prompts associated with respective training operation):
and using the sampled prior probability distributions as parameters of the trained machine learning model in generating the query metadata and selecting the example shots for the prompt (Lee, in para. [0062] discloses creation of prompts using different language phrases, i.e., example shots, for ML training using the LLM technique) and the at least one additional prompt (LP, in para. [0031, 0034, 0072] discloses the Platform as a Service, PaaS system, for training machine learning models, using creation and processing metadata by implementing PaaS software controlling and managing database nodes, language queries for ML training via operation of respective virtual machines [0078, 0097] ).
It would have been obvious to one having ordinary skill in the art, before the effective filing date of the invention to modify Lee, in view of teaching of LP because they both disclose training of machine learning models using LLM and including security threat detection and treatment). The motivation to combine would be to modify method of Lee for usage and operations of metadata for ML training.
sampling a prior probability distribution of the trained machine learning model to generate sampled prior probability distributions for the prompt and the at least one additional prompt (Dangoor, in para. [0026-0027] discloses determination and processing probabilities and respective scores for specified operations, i.e., prompt);
It would have been obvious to one having ordinary skill in the art, before the effective filing date of the invention to modify Lee-LP, in view of teaching of Dangoor because they all disclose training of machine learning models using LLM. The motivation to combine would be to modify method of Lee-LP for usage of a score for respective training operations using LLM.
As per claim 11 Lee discloses: A non-transitory computer-readable medium storing: a trained machine learning model for operating on an input security hunting (Examiner note: security hunting is met by a search for security threat, as disclosed by applicant in para. [0002] of SPECS) (Lee, in para [0029-0030] discloses operations of a management system for a search of security threats; the data are used to generate complex queries as inputs for machine learning model training [0030]) user query reflecting a user intention, the model comprising (Lee, in para. [0032, 0042, 0048] discloses analysis system controlling users with the intent to perform specified actions [0032], usage of natural language data, i.e. LLM data, to form a template query for machine learning model training including management of security threat detection and mitigation):
[a ranking head configured to select, based on the input security hunting user query, an example shot from among a set of example shots comprising respective example security hunting user queries and corresponding example security language queries,]
[and a classification head]
[configured to generate, from the input security hunting user query, query metadata;]
and computer-executable instructions configured to cause a computer processor to, upon receipt of the input security hunting user query from the user: use the trained machine learning model to generate a prompt comprising the input security hunting user query (Lee, in para. [0062] discloses generation of prompts associated with respective training operation)
Lee does not explicitly disclose creation and processing of metadata for ML training including LLM. However, LP discloses:
configured to generate, from the input security hunting user query, query metadata;
the query metadata, and the example shot; input the prompt into a large language model (LLM); and receive, from the LLM, a security language query responsive to the prompt and reflecting the user intention.
(LP, in para. [0031, 0034, 0072] discloses the Platform as a Service, PaaS system, for training machine learning models, using creation and processing metadata by implementing PaaS software controlling and managing database nodes, language queries for ML training via operation of respective virtual machines [0078, 0097]).
It would have been obvious to one having ordinary skill in the art, before the effective filing date of the invention to modify Lee, in view of teaching of LP because they both disclose training of machine learning models using LLM and including security threat detection and treatment. The motivation to combine would be to modify method of Lee for usage and operations of metadata for ML training.
Lee as modified does not explicitly disclose creation of a ranking scheme for the training and detection operations. However, Dangoor discloses
a ranking head configured to select, based on the input security hunting user query, an example shot from among a set of example shots comprising respective example security hunting user queries and corresponding example security language queries;
(Dangoor in para. [0026-0027] discloses generation of a score, i.e., ranking of operations, indicating a probability of query-related predictions by training using LLM model)
and a classification head
(Dangoor in para. [0101-0103] discloses operations classification as a one of four logical phases of the operations system for training management)
It would have been obvious to one having ordinary skill in the art, before the effective filing date of the invention to modify Lee-LP, in view of teaching of Dangoor because they all disclose training of machine learning models using LLM. The motivation to combine would be to modify method of Lee-LP for usage of a score for classification and training management using LLM.
As per claim 12 Lee as modified discloses: The non-transitory computer-readable medium of claim 11, wherein the trained machine learning model further comprises: a base pretrained large language model to receive the input security hunting user query, and a pooling layer (LP, in Figs. 7, 8 depict schedule, i.e., Table-schema, of ML training using proposed layered gradient accumulation technology [0118] as an advanced multi-layered machine learning technique [0122] used for a security threat detection [0077]).
It would have been obvious to one having ordinary skill in the art, before the effective filing date of the invention to modify Lee, in view of teaching of LP because they both disclose training of machine learning models using LLM and including security threat detection and treatment. The motivation to combine would be to modify method of Lee for usage and operations of metadata for ML training.
configured to receive an output of the base pretrained large language model, wherein the ranking head (Dangoor in para. [0026-0027] discloses generation of a score, i.e., ranking of operations, indicating a probability of query-related predictions by training using LLM model) and the classification head receive output of the pooling layer
(Dangoor in para. [0101-0103] discloses operations classification as a one of four logical phases of the operations system for training management)
It would have been obvious to one having ordinary skill in the art, before the effective filing date of the invention to modify Lee-LP, in view of teaching of Dangoor because they all disclose training of machine learning models using LLM. The motivation to combine would be to modify method of Lee-LP for usage of a score for classification and training management using LLM.
As per claims 13 – 16, claims 13, 14, 15 and 16 encompass same or similar scope as claims 2, 4, 7 and 10, respectively. Therefore, claims 13, 14, 15 and 16 are rejected based on the same reasons set forth above in rejecting claim 2, 4, 7, and 10.
As per claim 17 Lee discloses: A system for generating security language queries from unstructured user input with a large language model (LLM), the system comprising: a processor; and a storage device storing computer-readable instructions configured to cause the processor to, upon receipt of an input security hunting (Examiner note: security hunting is met by a search for security threat, as disclosed by applicant in para. [0002] of SPECS) (Lee, in para [0029-0030] discloses operations of a management system for a search of security threats; the data are used to generate complex queries as inputs for machine learning model training [0030]) user query reflecting a user intention, the model comprising (Lee, in para. [0032, 0042, 0048] discloses analysis system controlling users with the intent to perform specified actions [0032], usage of natural language data, i.e. LLM data, to form a template query for machine learning model training including management of security threat detection and mitigation): user query reflecting a user intention (Lee, in para. [0032, 0042, 0048] discloses analysis system controlling users with the intent to perform specified actions [0032], usage of natural language data, i.e. LLM data, to form a template query for machine learning model training including management of security threat detection and mitigation):
select, by a trained machine learning model and based on the input security hunting user query, at least one example shot, from among a set of example shots, for insertion into a prompt for input into the LLM (Lee, in para. [0062] discloses creation of prompts using different language phrases, i.e., example shots, for ML training using the LLM technique), the at least one example shot comprising an example security hunting user query and a corresponding example security language query;
Lee does not explicitly disclose creation and processing of metadata for ML training including LLM. However, LP discloses:
generate, by the trained machine learning model and based on the input security hunting user query, query metadata for insertion into the prompt;
generate the prompt for input into the LLM, the prompt comprising the input security hunting user query, the at least one example shot, and the query metadata; input the prompt into the LLM; and receive, from the LLM, a security language query responsive to the prompt and reflecting the user intention.
(LP, in para. [0031, 0034, 0072] discloses the Platform as a Service, PaaS system, for training machine learning models, using creation and processing metadata by implementing PaaS software controlling and managing database nodes, language queries for ML training via operation of respective virtual machines [0078, 0097]).
It would have been obvious to one having ordinary skill in the art, before the effective filing date of the invention to modify Lee, in view of teaching of LP because they both disclose training of machine learning models using LLM and including security threat detection and treatment. The motivation to combine would be to modify method of Lee for usage and operations of metadata for ML training.
As per claim 18 Lee as modified discloses: The system of claim 17, the instructions further configured to cause the processor to: sample a prior probability distribution of the trained machine learning model to generate sampled prior probability distributions for the prompt (Dangoor in para. [0026-0027] discloses generation of a score, i.e., ranking of operations, indicating a probability of query-related predictions by training using LLM model that includes generation of a complex query using Structured Query Language, SQL, i.e., sampling probability data) and at least one additional prompt that differs from the prompt in at least (Dangoor in para. [0026-0027] discloses generation of a score, i.e., ranking of operations, indicating a probability of query-related predictions by training using LLM model).
It would have been obvious to one having ordinary skill in the art, before the effective filing date of the invention to modify Lee-LP, in view of teaching of Dangoor because they all disclose training of machine learning models using LLM. The motivation to combine would be to modify method of Lee-LP for usage of a score for classification and training management using LLM.
Lee as modified further discloses:
one of the at Least one example shot or the query metadata;
use the sampled prior probability distributions as parameters of the trained machine learning model in generating the query metadata (LP, in para. [0031, 0034, 0072] discloses the Platform as a Service, PaaS system, for training machine learning models, using creation and processing metadata by implementing PaaS software controlling and managing database nodes, language queries for ML training via operation of respective virtual machines [0078, 0097]).
It would have been obvious to one having ordinary skill in the art, before the effective filing date of the invention to modify Lee, in view of teaching of LP because they both disclose training of machine learning models using LLM and including security threat detection and treatment. The motivation to combine would be to modify method of Lee for usage and operations of metadata for ML training.
Lee as modified further discloses: and selecting the example shots for the prompt and the at least one additional prompt (Lee, in para. [0062] discloses creation of prompts using different language phrases, i.e., example shots, for ML training using the LLM technique); generate the at least one additional prompt; input the at least one additional prompt into the LLM; receive, from the LLM and in response to the at least one additional prompt, at least one respective additional security language query reflecting the user intention (Lee, in para. [0032, 0042, 0048] discloses analysis system controlling users with the intent to perform specified actions [0032], usage of natural language data, i.e. LLM data, to form a template query for machine learning model training including management of security threat detection and mitigation);
score the security language query and the at least one additional security language query; and select a top scoring security language query from among the security language query and the at least one additional security language query (Dangoor in para. [0026-0027] discloses generation of a score, i.e., ranking of operations, indicating a probability of query-related predictions by training using LLM model).
It would have been obvious to one having ordinary skill in the art, before the effective filing date of the invention to modify Lee-LP, in view of teaching of Dangoor because they all disclose training of machine learning models using LLM. The motivation to combine would be to modify method of Lee-LP for usage of a score for classification and training management using LLM.
As per claim 19 Lee as modified discloses: The system of claim 17, wherein selecting the at least one example shot comprises: using the trained machine learning model to generate scores indicative of a relevance to the user security hunting query of the example shots (Dangoor in para. [0071] discloses ML training using the LLM model by processing each respective query and using highest determined score); and selecting the at least one example shot from the set based on the scores. (Dangoor in para. [0062] discloses calculation and processing the highest predictive score of actions, i.e., related to a detected activity in the system, and indicating user activity/intention);
It would have been obvious to one having ordinary skill in the art, before the effective filing date of the invention to modify Lee-LP, in view of teaching of Dangoor because they all disclose training of machine learning models using LLM. The motivation to combine would be to modify method of Lee-LP for usage of a score for respective training operations using LLM.
As per claim 20 Lee as modified discloses: The system of claim 17, the computer-readable instructions further configured to cause the processor to at least one of: display the security language query on a display; or execute the security language query in a security system (LP, in para. [0042] discloses a PaaS software control module operating threat detection and ML training: THE Results are displayed on a screen or using respective GUI system).
It would have been obvious to one having ordinary skill in the art, before the effective filing date of the invention to modify Lee, in view of teaching of LP because they both disclose training of machine learning models using LLM and including security threat detection and treatment. The motivation to combine would be to modify method of Lee for usage of a GUI to display detection results and training process.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure: Newman US_20230083512, Sharifi US_20240210194, Vu US_20240020546, Wei US_20230394328.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to VLADIMIR IVANOVICH GAVRILENKO whose telephone number is (313)446-6530. The examiner can normally be reached on Monday-Friday 7:30-4:30 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, Lynn Feild can be reached on (571) 272-2092. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/VLADIMIR I GAVRILENKO/Examiner, Art Unit 2431
Prosecution Insights