DETAILED ACTION
This office action is in response to applicant’s remarks filed on February 18, 2026 in application 18/744,949.
Claims 1, 3-7, 9-19 and 21-24 are presented for examination. Claims 1, 3, 7, 9-11, 14, 16, 19 and 21-22 are amended. Claims 2, 8, and 20 are cancelled. Claim 24 is newly added.
IDS submitted on June 17, 2024 was acknowledged.
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 .
Response to Arguments
Applicant's arguments filed February 18, 2026 have been fully considered but they are not persuasive.
In regard to the 35 USC 101 rejections, applicant stated that the invention present the new step of selecting based on … process identifiers, a subtree that represents … log entries, where summarization of a subtree is unconventional. Claim 1 present a new way to summarize a log that is too big to fit in the claimed linguistic prompt where prompt capacity is a technology problem.
Examiner disagreed. The claims as presented recited the method of generating by a large language model (LLM) a first summary of a first plurality of log entries and generating from the linguistic prompt by the LLM a second summary from the second plurality of log entries and the first summary, wherein selecting the subtree that represents the second plurality of log entries is based on the process identifiers.
The invention creates summaries from pluralities of log entries based on the process identifiers. The sequence of log entries already contains the plurality of process identifier identifying the first plurality of logs from the second plurality of logs. The selecting is interpreted to filtering the first plurality of log entries from the second plurality of log entries for input into the LLM to generate the summary.
In regard to the 35 USC 102a2, applicant stated that claims 2 and 8 are merged into independent claims 1 and 19 and therefore Blum does not anticipate claims 1 and 19. Applicant further state that claims 2 and 8 recited a subtree which excludes the root of the whole tree. Blum on the other hand teaches recursively explore and create additional steps from nodes for the tree branch, the path from the tree root to the node (para. 28, 38). Applicant further state that claim 3 that depends on merged claim 2 recited a summarization prompt which include all nodes in a branch path to the root of the path (app. Spec. para. 58).
Examiner disagreed. The term subtree could include the root or not depending where the subtree is divided. Applicant claim 3 recited “the subtree consists of a plurality of tree nodes that include a plurality of summary nodes … each summary node is based on multiple log entries” where nothing in claim 3 which depends on claim 1 recited the limitation of excluding a tree root from the subtree.
For these reasons, the rejections are maintained. Refer below for further details.
Claim Objections
Claim 24 is objected to under 37 CFR 1.75 as being a substantial duplicate of claim 23. When two claims in an application are duplicates or else are so close in content that they both cover the same thing, despite a slight difference in wording, it is proper after allowing one claim to object to the other as being a substantial duplicate of the allowed claim. See MPEP § 608.01(m).
Claim Rejections - 35 U.S.C. § 101
35 U.S.C. § 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-23 are rejected under 35 U.S.C. § 101 because the claimed invention is directed to an abstract idea without significantly more.
As to claim 1-23:
Step 1 Analysis: Is the claim to a process, machine, manufacture or composition of matter? See MPEP § 2106.03.
Yes, the claim is to a method.
Step 2A Prong One Analysis: Does the claim recite an abstract idea, law of nature, or natural phenomenon? See MPEP § 2106.04(II)(A)(1).
Yes, the limitation “generating, by the large language model (LLM) a first summary and a second summary” and “selecting, based on the plurality of process identifiers, a subtree that represents the second plurality of log entries” is the abstract idea of a mental process that can practically be performed in the human mind, with or without the use of a physical aid such as pen and paper (including an observation, evaluation, judgment, opinion). See MPEP § 2106.04(a)(2)(III).
Step 2A Prong Two Analysis: Does the claim recite additional elements that integrate the judicial exception into a practical application? See MPEP § 2106.04(d).
No, all elements are part of the abstract idea as shown above. (for independent claims)
Step 2B Analysis: Does the claim recite additional elements that amount to significantly more than the judicial exception? See MPEP § 2106.05.
No, the limitation “generating, by the large language model (LLM) a first summary and a second summary” and “selecting, based on the plurality of process identifiers, a subtree that represents the second plurality of log entries” is an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP § 2106.05(h).
Claim Rejections - 35 USC § 102
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.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1, 3-7, 9-14, 18, 19, 21-22 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Blum et al. (US 2024/0419803).
In regard to claim 1, Blum et al. teach a method comprising:
generating, by a large language model (LLM), a first summary of a first plurality of log entries from a sequence of log entries (extracting insights or summarizing a large data table, instead of in lining the entire data table in the prompt, the system have available prompt instructions to prompt the LLM system to generate the adequate summarization expression, which can then be executed by the computing system. Applying the summarization code to the table reference results in a smaller table that can fit under the token limit of the LLM prompt, para. 50) that contains: a plurality of process identifiers (the investigation has proceeded from step 112-1 to step 112-1-3 to step 112-1-3-2 to step 112-1-3-2-3 to step 112-1-3-2-3-3, fig. 7, para. 51-52) the first plurality of log entries and a second plurality of log entries (LLM system performs analysis on the initial context and produce a set of suggested steps, para. 33), where each process identifiers of the plurality of process identifiers identifies a process that has a distinct address space (generated table have reference and DstIpAddress, para. 45);
selecting, based on the plurality of process identifiers, a subtree that represents the second plurality of log entries (generates new context for a node in a tree … thus nodes for the tree branch, para. 38);
generating a linguistic prompt that contains the subtree (prompting the LLM system to produce summarized context using previous context and newly generated context, para. 38, investigation of a tree branch, including investigation of 5 levels of the tree branch, fig. 7, para. 51-52); and
generating, from the linguistic prompt by the LLM (entry in the LLM system to recursively explore and create additional suggested steps, para. 38), a second summary of the sequence of log entries that is based on the second plurality of log entries and the first summary of the first plurality of log entries (LLM system generates new context for a node for the step in a tree, para. 38, chaining several prompts intertwined with data access operation, para. 4, as a result of the analyst is satisfied with a given branch, it can ask the LLM system to produce a text summary of the investigation, para. 56-57, fig. 8);
wherein the method is performed by one or more computers (summarization of context can be performed by the computing system, para. 52).
In regard to claim 3, Blum et al. teach the method of Claim 1 wherein:
the subtree consists of a plurality of tree nodes that include a plurality of summary nodes (tree where each tree node is a branching point in the investigation, para. 28);
each summary node of the plurality of summary nodes is based on multiple log entries in the sequence of log entries (a summary of the path from the tree root to the node, para. 28).
In regard to claim 4, Blum et al. teach the method of Claim 3 wherein: the linguistic prompt contains a natural sentence that indicates that the subtree contains at least one summary node; the subtree does not contain the natural sentence (the LLM system uses trained models of the LLM system, context, goals, and available skills to apply the plain language instructions to create the desired output, para. 35).
In regard to claim 5, Blum et al. teach the method of Claim 4 wherein the subtree does not contain a first summary node that is based on a second summary node of the plurality of summary nodes (the LLM system uses previous results in generating next suggested steps, para. 43, it is noted that the second summary node would use the previous results of the first summary node and therefore, the first summary node is not based on a second summary node).
In regard to claim 6, Blum et al. teach the method of Claim 3 further comprising:
generating a second linguistic prompt that contains a second subtree that contains the first plurality of log entries (the LLM system uses previous results in generating next suggested steps, para. 38, 43);
generating, based on the second linguistic prompt, a summary node in the plurality of summary nodes (the cumulative context may be a summary, para. 38).
In regard to claim 7, Blum et al. teach the method of Claim 1 wherein:
the method further comprises generating, by the LLM, a natural sentence (uses a final LLM prompt to produce the final natural language summary, para. 59);
the subtree contains the natural sentence (providing a tree interface in a user interface that causes display of the indications of suggested steps in a tree format, para. 64).
In regard to claim 9, Blum et al. teach the method of Claim 1 wherein the linguistic prompt does not contain a process identifier of the plurality of process identifiers (schemas can be obtained by the computing system where the data tables are stored, and the schemas are provided by the computing system to the prompt, para. 47).
In regard to claim 10, Blum et al. teach the method of Claim 1 wherein the subtree contains the first summary of the first plurality of log entries (a tree where each tree node is a branching point … prompt contains a description of the current state of the investigation (e.g., a summary of the path from the tree root to the node), para. 28).
In regard to claim 11, Blum et al. teach the method of Claim 1 wherein:
the linguistic prompt contains a sequence of text lines (instructions fed to the LLM system via a prompt expressed in natural language, para. 28);
the subtree contains a plurality of tree nodes (user interface represent the investigation as a tree with nodes, para. 28);
each tree node in the plurality of tree nodes is a distinct text line in the sequence of text lines (each branching point in the tree produces a set of possible nest steps, para. 28);
each tree node in the plurality of tree nodes represents a distinct log entry of the first plurality of log entries (applying the summarization code to the table reference results in a smaller table that can fit under the token limit of the LLM prompt, para. 50).
In regard to claim 12, Blum et al. teach the method of Claim 11 wherein a length of each text line in the sequence of text lines depends on a position of the text line in the subtree (providing references to the data to the LLM prompt so as to not exceed token size, para. 43, 46).
In regard to claim 13, Blum et al. teach the method of Claim 1 further comprising predefining a maximum count of log entries in the first plurality of log entries (LLM systems have a limit to the amount of information that can be input into an LLM prompt, para. 40).
In regard to claim 14, Blum et al. teach the method of Claim 13 wherein:
the method further comprises calculating, based on the maximum count of log entries in the first plurality of log entries, a count of tree levels that the second plurality of log entries will contain (LLM systems have a limit to the amount of information that can be input into an LLM prompt, para. 40);
said selecting is based on the count of tree levels (investigation of a tree branch, including investigation of 5 levels of the tree branch, fig. 7, para. 51-52) that the second plurality of log entries will contain (cumulative context is provided for subsequent node creation, para. 40, providing references to the data to the LLM prompt so as to not exceed token size, para. 43).
In regard to claim 17, Blum et al. teach the method of Claim 1 wherein:
the first plurality of log entries contains a command line option (instructions fed to the LLM system via a prompt, para. 28);
the first summary of the first plurality of log entries is based on the command line option (after executing, the LLM system generates new context for a node for the step in a tree, para. 38);
the first summary of the first plurality of log entries does not contain the command line option (the new context is a cumulative context including information created by the LLM system from previous contexts, para. 38).
In regard to claim 19, Blum et al. teach one or more computer-readable non-transitory media storing instructions that, when executed by one or more processes, cause:
generating, by a large language model (LLM), a first summary of a first plurality of log entries from a sequence of log entries (extracting insights or summarizing a large data table, instead of in lining the entire data table in the prompt, the system have available prompt instructions to prompt the LLM system to generate the adequate summarization expression, which can then be executed by the computing system. Applying the summarization code to the table reference results in a smaller table that can fit under the token limit of the LLM prompt, para. 50) that contains: a plurality of process identifiers (the investigation has proceeded from step 112-1 to step 112-1-3 to step 112-1-3-2 to step 112-1-3-2-3 to step 112-1-3-2-3-3, fig. 7, para. 51-52), the first plurality of log entries and a second plurality of log entries (LLM system performs analysis on the initial context and produce a set of suggested steps, para. 33), wherein each process identifiers of the plurality of process identifiers identifies a process that has a distinct address space (generated table have reference and DstIpAddress, para. 45);
selecting, based on the plurality of process identifiers, a subtree that represents the second plurality of log entries (generates new context for a node in a tree … thus nodes for the tree branch, para. 38);
generating a linguistic prompt that contains the subtree (prompting the LLM system to produce summarized context using previous context and newly generated context, para. 38, investigation of a tree branch, including investigation of 5 levels of the tree branch, fig. 7, para. 51-52); and
generating, from the linguistic prompt by the LLM (entry in the LLM system to recursively explore and create additional suggested steps, para. 38), a second summary of the sequence of log entries that is based on the second plurality of log entries and the first summary of the first plurality of log entries (LLM system generates new context for a node for the step in a tree, para. 38, chaining several prompts intertwined with data access operation, para. 4, as a result of the analyst is satisfied with a given branch, it can ask the LLM system to produce a text summary of the investigation, para. 56-57, fig. 8).
In regard to claim 21, Blum et al. teach the one or more computer-readable non-transitory media of Claim 19 wherein:
the subtree consists of a plurality of tree nodes that include a plurality of summary nodes (tree where each tree node is a branching point in the investigation, para. 28);
each summary node of the plurality of summary nodes is based on multiple log entries in the sequence of log entries (a summary of the path from the tree root to the node, para. 28).
In regard to claim 22, Blum et al. teach the one or more computer-readable non-transitory media of Claim 19 wherein:
the linguistic prompt contains a sequence of text lines (instructions fed to the LLM system via a prompt expressed in natural language, para. 28);
the subtree contains a plurality of tree nodes (user interface represent the investigation as a tree with nodes, para. 28);
each tree node in the plurality of tree nodes is a distinct text line in the sequence of text lines (each branching point in the tree produces a set of possible nest steps, para. 28);
each tree node in the plurality of tree nodes represents a distinct log entry of the first plurality of log entries (applying the summarization code to the table reference results in a smaller table that can fit under the token limit of the LLM prompt, para. 50).
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 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.
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 15-16, 18 and 23-24 is/are rejected under 35 U.S.C. 103 as being unpatentable over Blum et al. (US 2024/0419803) in further view of Pentyala et al. (US 2025/0384240).
In regard to claim 15, Blum et al. does not explicitly teach but Pentyala et al. teach the method of Claim 1 wherein:
said generating the first summary of the first plurality of log entries is a first generating that is performed by a first exact copy of the LLM (training using a first training dataset, para. 80);
said generating the second summary of the sequence of log entries is a second generating (each of steps 603 and 605 may further comprise jointly generating, by a combination of the first (or second) adapter neural network, a training output, para. 80);
the sequence of log entries further contains a third plurality of log entries (second training dataset, para. 80);
the method further comprises third generating, by a second exact copy of the LLM, a third summary of the third plurality of log entries (training using a second dataset, para. 80, fig. 1C, 121);
said second generating is further based on said third generating (each of steps 603 and 605 may further comprise jointly generating, by a combination of the first (or second) adapter neural network, a training output, para. 80);
said first generating and said third generating are concurrent (performing a first task, and in parallel, a second task, para. 80).
It would have been obvious to modify the method of Blum et al. by adding Pentyala et al. parallel finetuning of neural networks. A person of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to make the modification because it would aid in parallel training (para. 77).
In regard to claim 16, Blum et al. does not explicitly teach but Pentyala et al. teach the method of Claim 15 wherein said first generating and said third generating are performed by a pair of processing elements selected from a group consisting of a pair of distinct network elements (a first adapter neural network and a second adapter neural network, para. 80, fig. 1C, 110).
Refer to claim 15 for motivational statement.
In regard to claim 18, Blum et al. does not explicitly teach but Pentyala et al. teach the method of Claim 1 wherein: the first plurality of log entries is not a subsequence of the sequence of log entries or the second plurality of log entries is not a subsequence of the sequence of log entries; the first plurality of log entries is disjoint from the second plurality of log entries (LLMs are trained sequentially on different datasets, para. 19).
Refer to claim 15 for motivational statement.
In regard to claim 23, Blum et al. does not explicitly teach but Pentyala et al. teach the one or more computer-readable non-transitory media of Claim 19 wherein:
said generating the first summary of the first plurality of log entries is a first generating that is performed by a first exact copy of the LLM (training using a first training dataset, para. 80);
said generating the second summary of the sequence of log entries is a second generating (each of steps 603 and 605 may further comprise jointly generating, by a combination of the first (or second) adapter neural network, a training output, para. 80);
the sequence of log entries further contains a third plurality of log entries (second training dataset, para. 80);
the instructions further cause third generating, by a second exact copy of the LLM, a third summary of the third plurality of log entries (training using a second dataset, para. 80, fig. 1C, 121);
said second generating is further based on said third generating (each of steps 603 and 605 may further comprise jointly generating, by a combination of the first (or second) adapter neural network, a training output, para. 80);
said first generating and said third generating are concurrent (performing a first task, and in parallel, a second task, para. 80).
Refer to claim 15 for motivational statement.
In regard to claim 24, Blum et al. does not explicitly teach but Pentyala et al. teach the one or more computer-readable non-transitory media of Claim 19 wherein:
said generating the first summary of the first plurality of log entries is a first generating that is performed by a first exact copy of the LLM (training using a first training dataset, para. 80);
said generating the second summary of the sequence of log entries is a second generating (each of steps 603 and 605 may further comprise jointly generating, by a combination of the first (or second) adapter neural network, a training output, para. 80);
the sequence of log entries further contains a third plurality of log entries (second training dataset, para. 80);
the instructions further cause third generating, by a second exact copy of the LLM, a third summary of the third plurality of log entries (training using a second dataset, para. 80, fig. 1C, 121);
said second generating is further based on said third generating (each of steps 603 and 605 may further comprise jointly generating, by a combination of the first (or second) adapter neural network, a training output, para. 80);
said first generating and said third generating are concurrent (performing a first task, and in parallel, a second task, para. 80).
Refer to claim 15 for motivational statement.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. See PTO 892.
Burton (US 12,210,839) data analysis, LLM prompt-chaining
Spangler et al. (US 11,269,929) predictive analytics
Charnock et al. (US 11,972,346) improves sophisticated and large-scale disinformation
Hoang et al. (U S12,086552) Steiner tree, trained graph neural network
**********
Sadananda et al. (US 12/511,276) LLM language model
Boussina et al. (US 2025/0372219) LLM for improve accuracy of the responses
Kholodkov (US 2025/0362995) LLM for large log files
Burton (US 2025/0165717) LLM for data analysis and tree-based structures
Rigterink et al. (US 2024/0403658) LLM and tree structure
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 LOAN TRUONG whose telephone number is 408-918-7552. The examiner can normally be reached on 10AM-6PM PST M-F.
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, Ashish Thomas can be reached on 571-272-0631. 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.
/Loan L.T. Truong/Primary Examiner, Art Unit 2114
Loan.truong@uspto.gov
Prosecution Insights