Detailed Action
Notice of Pre-AIA or AIA Status
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
2. Claims 1-20 are pending.
Election/Restriction
3. Restriction to one of the following inventions is required under 35 U.S.C. 121:
I. Claims 1-10 and 20, drawn to a method and system for generating domain knowledge tools, classified in G06N5/02.
II. Claims 11-19, drawn to method for a Large Language Model agent to receive a user query and generate a response to the user query based on accessed domain knowledge tools, classified in G06F40/20.
The inventions are independent or distinct, each from the other because:
Inventions I and II are related as combination and subcombination. Inventions in this relationship are distinct if it can be shown that (1) the combination as claimed does not require the particulars of the subcombination as claimed for patentability, and (2) that the subcombination has utility by itself or in other combinations (MPEP § 806.05(c)). In the instant case, the combination as claimed does not require the particulars of the subcombination as claimed because a large language model agent receives a user query and generates a response to it based on a variety of different types of domain knowledge tools. The features describing how the agent operates do not necessarily depend on how the domain knowledge tools are generated. The subcombination has separate utility such as the specific generation steps of the domain knowledge tools, which are independent of how an agent may utilize them.
The examiner has required restriction between combination and subcombination inventions. Where applicant elects a subcombination, and claims thereto are subsequently found allowable, any claim(s) depending from or otherwise requiring all the limitations of the allowable subcombination will be examined for patentability in accordance with 37 CFR 1.104. See MPEP § 821.04(a). Applicant is advised that if any claim presented in a divisional application is anticipated by, or includes all the limitations of, a claim that is allowable in the present application, such claim may be subject to provisional statutory and/or nonstatutory double patenting rejections over the claims of the instant application.
Restriction for examination purposes as indicated is proper because all the inventions listed in this action are independent or distinct for the reasons given above and there would be a serious search and/or examination burden if restriction were not required because one or more of the following reasons apply:
1) Different classification in the art.
2) The search for one invention would lead away from the search for the other invention.
Applicant is advised that the reply to this requirement to be complete must include (i) an election of an invention to be examined even though the requirement may be traversed (37 CFR 1.143) and (ii) identification of the claims encompassing the elected invention.
The election of an invention may be made with or without traverse. To reserve a right to petition, the election must be made with traverse. If the reply does not distinctly and specifically point out supposed errors in the restriction requirement, the election shall be treated as an election without traverse. Traversal must be presented at the time of election in order to be considered timely. Failure to timely traverse the requirement will result in the loss of right to petition under 37 CFR 1.144. If claims are added after the election, applicant must indicate which of these claims are readable upon the elected invention.
Should applicant traverse on the ground that the inventions are not patentably distinct, applicant should submit evidence or identify such evidence now of record showing the inventions to be obvious variants or clearly admit on the record that this is the case. In either instance, if the examiner finds one of the inventions unpatentable over the prior art, the evidence or admission may be used in a rejection under 35 U.S.C. 103 or pre-AIA 35 U.S.C. 103(a) of the other invention.
During a telephone conversation with Mr. Gianni Minutoli on 7/30/26 a provisional election was made without traverse to prosecute the invention of Invention I, claims 1-10 and 20. Affirmation of this election must be made by applicant in replying to this Office action. Claims 11-19 are withdrawn from further consideration by the examiner, 37 CFR 1.142(b), as being drawn to a non-elected invention.
Claim Rejections - 35 USC § 112
4. 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.
Claim 2 is rejected under 35 U.S.C. 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 2 recites the limitation "the digestible format" in line 2. There is insufficient antecedent basis for this limitation in the claim.
Claim Rejections - 35 USC § 102
5. In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
6. The following is a quotation of 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.
7. Claim(s) 1-3, 5-10, and 20 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Siebel et al “Siebel” (US 2025/0124069 A1).
8. Regarding claim 1, Siebel shows a method for generating domain knowledge tools for a Large Language Model (LLM) agent (Abstract, para 20, 23, 59 show generating a knowledge related tool for a LLM), the method comprising: analyzing a corpus of documents using a series of machine learning models to extract generalized information about the corpus (para 50, 111, 126 show analyzing the corpus of documents, para 68, 76, 107, 149, 161 show extracting general information from the corpus about it); and generating a domain specific agent that utilizes the generalized information to create and maintain domain knowledge tools that provide domain-specific contextually relevant information to the LLM agent (para 24, 65, 135 show an agent may be generated for a particular domain but which is in addition to and still uses the generalized corpus information, para 22, 24, 59-60, 65, 108 show the plurality of specific domain agents assisting in providing accurate responses among the many domains accessed by the LLM agent, para 59-61, 126, 130 show the agent then provides the knowledge tools which are contextually relevant to the particular domain to the orchestrator/LLM agent), the domain knowledge tools enhancing the LLM agent processing of user queries by supplying domain-specific information and context during the LLM agent generation of responses (para 22, 24, 59-60, 65, 108 show the domain tools include a plurality of specific domain agents assisting in providing accurate responses among the many domains accessed by the LLM agent, para 47, 126, 130, 169, 171 show these domain knowledge tools improve the orchestrator processing of user queries by supplying the domain particular information and context during the response to the user queries).
9. Regarding claim 2, Siebel shows converting of the corpus of documents into a digestible format by converting formatted documents into a text or binary equivalent format prior to the analyzing of the corpus of documents (para 22, 26, 30, 63 for example show converting the corpus documents into a text format in order to then analyze them).
10. Regarding claim 3, the analyzing of the corpus comprises discerning logical or semantic groupings within the corpus, resulting in sections within the corpus (para 114-115, 126, 151 show determining logical and semantic groupings of the corpus based on patterns and relationships, para 111-115 show this results in chunks/sections within the corpus).
11. Regarding claim 5, the generating of the domain knowledge tools comprises creating domain-specific vectorized datastores that are utilized by the LLM agent to access the domain specific information and assist the LLM agent generation of the responses (para 58, 141, 144, 149, 155 show the domain specific vector datastores utilized by the LLM agent to access the information of the domain by which the LLM agent may generate results).
12. Regarding claim 6, the enhancing of the LLM agent processing comprises the LLM agent accessing the domain knowledge tools to provide accurate completions based upon specific prompts (para 63, 106, 110, 169 show accessing the corpus for to process specific prompts to foster additional and more accurate completion of information.
13. Regarding claim 7, Siebel shows updating the domain knowledge tools automatically by the domain specific agent as the corpus is being updated, and reflecting changes as updates occur (para 56, 58, 155, 157 show as the corpus is updated, the model and extraction tools are updated and this is reflected at least in updated prompts, para 92, 97, 145, 153 show the updates may be reflected in the dashboard).
14. Regarding claim 8, Siebel shows generating the domain knowledge tools by a plurality of domain specific agents to assist the LLM agent in providing accurate responses in various domains serviced by the LLM agent (para 22, 24, 59-60, 65, 108 show the domain tools include a plurality of specific domain agents assisting in providing accurate responses among the many domains accessed by the LLM agent).
15. Regarding claim 9, Siebel shows utilizing, by the LLM agent, the domain knowledge tools to reduce hallucinations and ensure accurate results in response to the user queries (para 22, 42, 169, 171 show the LLM agent utilizes the domain knowledge tools to reduce hallucinations and provide accurate responses to the user prompts/queries).
16. Regarding claim 10, Siebel shows upon receiving a user query, utilizing, by the LLM agent, metadata generated by the domain-specific agent to determine relevant sections of the corpus, and vectorized datastores related to those corpus sections created by the domain-specific agent to generate a response to the user query (para 39, 59, 116, 133-134 show the LLM agent uses metadata generated by a particular domain agent to extract relevant sections of the corpus and vectorized data related to those sections, to generate the response to a user prompt/query).
17. Claim 20 shows the same features as claim 1 and is rejected for the same reasons. In addition, Siebel para 25-26, 30 show the databases storing the corpus of documents, and para 203 shows the processor configured to perform the method steps.
Claim Rejections - 35 USC § 103
18. 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.
19. Claim(s) 4 is/are rejected under 35 U.S.C. 103 as being unpatentable over Siebel and Parham et al “Parham” (US 2024/0248963 A1).
20. Regarding claim 4, Siebel shows performing, for each section of the corpus, an analysis to provide representative keywords (para 195-196, 219 show the keyword analysis), summarization of a section corpus (para 78, 92, 230, 238 show summarizing the sections of the data content), and identification of related sections (para 66, 112, 170, 222 show identified related sections, para 231-233 show different agents retrieve portions of data that are related to an input). Siebel para 126, 151, 168, 170 may show section data grouped by types, but Siebel does not show correlation to predefined categories and correlation between each identified section. Parham however does show a large language model (LLM) agent with document corpus (para 22, 28, 99 show the large language model with document corpus, 142-143 show the orchestrator agent for the LLM over the document corpus, which manages many agents), with correlation of corpus sections to predefined categories (para 17, 32, 37, 61 show predefined categories, para 22, 24, 64 show defined topics and para 70, 74, 98-100 show correlation/association metric of the corpus sections to the defined categories and topics) and correlation between each identified section (para 70, 74, 98-100 show correlation/association metrics between the sections in the corpus). It would have been obvious to a person with ordinary skill in the art before the effective filing date of the claimed invention to have correlation to predefined categories and correlation between each identified section, as is shown in Parham, in the large language model agent with document corpus of Siebel, because it would provide an efficient way to quickly produce context and related data so as to more accurately answer a prompt/query.
Conclusion
21. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
a) Godbole (US 12450217 B) shows retrieval augmented generation (RAG) techniques for an LLM (large language model) agent over a corpus of documents.
b) Lan (CN 118155780 A) shows cross domain versatility for knowledge tools in a large language model agent.
22. Any inquiry concerning this communication or earlier communications from the examiner should be directed to STEVEN PAUL SAX whose telephone number is (571)272-4072. The examiner can normally be reached Monday - Friday, 9:30 - 6:00 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, Usmaan Saeed, can be reached at 571-272-4046. 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.
/STEVEN P SAX/ Primary Examiner, Art Unit 2146
Prosecution Insights