DETAILED ACTION
This office action is responsive to the Amendments/Request for reconsideration filed on 02/11/2026 after Non-Final filed 12/03/2025. The application contains claims 1-13, 15-17, 19--20, all examined and rejected.
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 Amendment
It is acknowledged that claims 1 and 16 were amended. Claims 14 and 18 were canceled.
Response to Arguments
Applicant's arguments filed 02/11/2026 have been fully considered but they are not persuasive. Upon further review KARLBERG describes the amended portions reciting, wherein the graph database remains under the control of the user and is not provided to the large language model along with the query prompt and an output prompt. KARLBERG describes that the LLM only receives the natural language query and the initial LLM outputs graph queries (para. 0036), that the knowledge graph engine (separate from the LLM) uses to obtain context data from the enterprise knowledge graph (e.g. the graph database) (para. 0037), where access control policies associated with the user are used to filter the context data outputted from the knowledge graph engine (describes how the from the knowledge graph is under the control of the user) (para. 0038) and subsequently “Both the question and the input data (e.g., context data obtained from the graph traversal) go to the LLM as one unit.”, the context data is not the enterprise knowledge graph (e.g. the graph database), therefore the graph database remains under the control of the user and is not provided to the large language model).
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are: “a prompt module configured to determine a query prompt”; “prompt module is also configured to determine an output prompt”; “graph database management system configured to determine…” in claim 1 and 12; “the large language model configured to generate the natural language output” in claim 2 and 15; “user interface configured to allow for the determination…” in claim 4; “Neo4j system that is configured to receive the Cypher query” in claim 12 and 19.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
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) 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over DIFONZO (US 20220414228 A1) in view of KARLBERG et al. (US 20240419835 A1).
Regarding claim 1, DIFONZO (US 20220414228 A1) discloses:
a system for determining, at least by (paragraph [0067-0069], Fig. 10, which describes natural language outputs results Ref. 1004, 1008, 1012, 1016 using NLP/query generation service output that uses trained machine learning models)
the system comprising: a computer processor configured to receive a desired output dependent upon information associated with the digital network, at least by (paragraph [0033] describes receiving a first input from a user “comprising a natural language query regarding data in a graph database” paragraph [0061] describes “user submitting the natural language query: “show me machines that talk to outside IPs, have critical vulnerabilities, and host network services”)
at least by (paragraph [0060-0061] describes NLP/query generation service that takes the user’s natural language query, applies intent classification+NER+ semantic similarity and outputs the formal graph database query (e.g. generate a query dependent upon the information and the desired output); where intent classification model, NER model, semantic similarity checking algorithm are trained machine learning models equivalent to an LLM)
and a graph database management system configured to determine, dependent upon a graph database representative of at least a portion of the digital network, at least by (paragraph [0047] which describes the “cybersecurity analysis platform…CyGraph cybersecurity platform” that derives node/edge data for the graph database system, where the nodes/edges represents the network devices and services)
a response to the query as received from the large language model, at least by (paragraph [0067-0069], Fig. 10, which describes natural language outputs results Ref. 1004, 1008, 1012, 1016 using NLP/query generation service output that uses trained machine learning models (e.g. large language model) in response the query)
But DIFONZO fails to specifically describe:
(a) a large language model
(b) wherein the graph database remains under the control of the user and is not provided to the large language model along with the query prompt and an output prompt
(c) a prompt module configured to determine a query prompt to the large language model requesting the large language model to generate a query
(d) the prompt module is also configured to determine an output prompt to the large language model
However, KARLBERG teaches the above limitation(s) (a) and (c) at least by (paragraph [0036] “LLM execution component 308 which invokes (e.g., via an API call, function call, IPC) a LLM (e.g., the external generative AI system 214 or the internal generative AI system 302) to generate a graph query that includes the LLM prompt (see para. 0041-0046) (e.g. “determine a query prompt to the large language model requesting the large language model to generate a query”). Also, limitation (d) is described at least by (paragraph [0094] “invoking, by the network system, an LLM to determine a result by making a call to the LLM with the LLM prompt (e.g. “output prompt to the large language model”) and the context data obtained from the traversal of the knowledge graph; and causing presentation of the result on a user interface of a client device.”)
Regarding (b) KARLBERG further describes that the LLM only receives the natural language query and the initial LLM outputs graph queries (para. 0036), that the knowledge graph engine (separate from the LLM) uses to obtain context data from the enterprise knowledge graph (e.g. the graph database) (para. 0037), where access control policies associated with the user are used to filter the context data outputted from the knowledge graph engine (describes how the from the knowledge graph is under the control of the user) (para. 0038) and subsequently “Both the question and the input data (e.g., context data obtained from the graph traversal) go to the LLM as one unit.”, the context data is not the enterprise knowledge graph (e.g. the graph database), therefore the graph database remains under the control of the user and is not provided to the large language model)
Therefore, before the effective filing date of the invention it would have been obvious to one of ordinary skill in the art to combine the system of DIFONZO with the use of LLM’s and LLM prompts incorporated into graph query provided by KARLBERG to, “efficiently access these data stores to construct the enterprise knowledge graph and subsequently perform a query for information”, (KARLBERG, 0012).
As per claim 2, claim 1 is incorporated and DIFONZO fails to disclose:
further comprising: the large language model configured to generate the natural language output as requested by the prompt module and dependent upon the response to the query.
However, KARLBERG teaches the above limitation(s) at least by (paragraph [0094] “invoking, by the network system, an LLM to determine a result by making a call to the LLM with the LLM prompt (e.g. “output prompt to the large language model”) and the context data obtained from the traversal of the knowledge graph; and causing presentation of the result on a user interface of a client device.”)
Therefore, before the effective filing date of the invention it would have been obvious to one of ordinary skill in the art to combine the system of DIFONZO with the use of LLM’s and LLM prompts incorporated into graph query provided by KARLBERG to, “efficiently access these data stores to construct the enterprise knowledge graph and subsequently perform a query for information”, (KARLBERG, 0012).
As per claim 3, claim 2 is incorporated and DIFONZO fails to disclose:
wherein the prompt module is in communication with the large language model via the internet.
However, KARLBERG teaches the above limitation(s) at least by (paragraph [0094] “invoking, by the network system, an LLM to determine a result by making a call to the LLM with the LLM prompt (e.g. “prompt module is in communication with the large language model”) and further paragraph [0093] describes “ these operations being accessible via a network (e.g., the Internet) and via one or more appropriate interfaces (e.g., an application program interface (API)).” By having to communicate with the LLM via internet, the LLM is separate from the computer processor making the “call” using the API to the LLM via the internet.)
Therefore, before the effective filing date of the invention it would have been obvious to one of ordinary skill in the art to combine the system of DIFONZO with the use of LLM’s and LLM prompts incorporated into graph query provided by KARLBERG to, “efficiently access these data stores to construct the enterprise knowledge graph and subsequently perform a query for information”, (KARLBERG, 0012).
As per claim 4, claim 1 is incorporated and DIFONZO further discloses:
further comprising: a user interface configured to allow for the determination of the desired output dependent upon information associated with the digital network, at least by (paragraph [0047] “GUI may also comprise a series of buttons or tabs (e.g., in left panel 104) that provide access to a query builder function and/or to access the graph results for a plurality of previous queries. In some instances, the graph database system may provide pre-defined graph database query templates that allow a user to build query components from form selections.” Where previous queries and query templates are desired output dependent upon information associated with the digital network)
As per claim 5, claim 4 is incorporated and DIFONZO further discloses:
wherein the user interface allows for the selection of the desired output from a predefined list, at least by (paragraph [0047] “GUI may also comprise a series of buttons or tabs (e.g., in left panel 104) that provide access to a query builder function and/or to access the graph results for a plurality of previous queries. In some instances, the graph database system may provide pre-defined graph database query templates that allow a user to build query components from form selections.” Where the selectable pre-defined graph database query templates are selection of the desired output from a predefined list,)
As per claim 6, claim 1 is incorporated and DIFONZO fails to disclose:
wherein the output prompt and the response to the query are provided to the large language model.
However, KARLBERG teaches the above limitation(s) at least by (paragraph [0094] “invoking, by the network system, an LLM to determine a result by making a call to the LLM with the LLM prompt (e.g. “output prompt to the large language model”) and the context data obtained from the traversal of the knowledge graph; and causing presentation of the result on a user interface of a client device.”)
Therefore, before the effective filing date of the invention it would have been obvious to one of ordinary skill in the art to combine the system of DIFONZO with the use of LLM’s and LLM prompts incorporated into graph query provided by KARLBERG to, “efficiently access these data stores to construct the enterprise knowledge graph and subsequently perform a query for information”, (KARLBERG, 0012).
As per claim 7, claim 1 is incorporated and DIFONZO fails to disclose:
wherein the output prompt and information dependent upon the response to the query are provided to the large language model and the response to the query is not provided directly to the large language model.
However, KARLBERG teaches the above limitation(s) at least by (paragraph [0094] “invoking, by the network system, an LLM to determine a result by making a call to the LLM with the LLM prompt (e.g. “output prompt to the large language model”) and the context data obtained from the traversal of the knowledge graph; and causing presentation of the result on a user interface of a client device,” which describes providing the LLM/output prompt and context data (e.g. “information dependent upon the response to the query”) to the LLM to generate a response, as such the the LLM/output prompt and context data is not the response that is directly provided to the LLM.
Therefore, before the effective filing date of the invention it would have been obvious to one of ordinary skill in the art to combine the system of DIFONZO with the use of LLM’s and LLM prompts incorporated into graph query provided by KARLBERG to, “efficiently access these data stores to construct the enterprise knowledge graph and subsequently perform a query for information”, (KARLBERG, 0012).
As per claim 8, claim 1 is incorporated and DIFONZO fails to disclose:
wherein the query prompt and the output prompt as determined by the prompt module are different from one another.
However, KARLBERG teaches the above limitation(s) at least by (paragraph [0036] “LLM execution component 308 which invokes (e.g., via an API call, function call, IPC) a LLM (e.g., the external generative AI system 214 or the internal generative AI system 302) to generate a graph query that includes the LLM prompt (see para. 0041-0046) and paragraph [0094] “invoking, by the network system, an LLM to determine a result by making a call to the LLM with the LLM prompt (e.g. “output prompt”) which show the two different prompts)
Therefore, before the effective filing date of the invention it would have been obvious to one of ordinary skill in the art to combine the system of DIFONZO with the use of LLM’s and LLM prompts incorporated into graph query provided by KARLBERG to, “efficiently access these data stores to construct the enterprise knowledge graph and subsequently perform a query for information”, (KARLBERG, 0012).
As per claim 9, claim 1 is incorporated and DIFONZO further discloses:
wherein the desired output is at least one of the following: an explanation as to why one device on the digital network failed to connect to another device on the digital network; an analysis as to how the digital network responds to an outage of at least one specified device; and an answer to an inquiry asking how many devices and the names of those devices that are connected to a first device on the digital network, at least by (paragraph [0048] “portion of the query is an instruction to identify Inside IP addresses that have a crucial vulnerability. Then the final “return r, s, t, limit 10” portion of the query is an instruction to identify those combined relationships, i.e., Inside IP addresses that support and network services and are talking to outside IP addresses, with the number of results listed” paragraph [0069] “returns the number of edge connections a specific node”)
As per claim 10, claim 1 is incorporated and DIFONZO further discloses:
wherein the natural language output as generated by the large language model is indicative of an outcome of an event affecting the digital network as represented by the graph database, at least by (paragraph [0067-0069], Fig. 10, which describes natural language outputs results Ref. 1004, 1008, 1012, 1016 using NLP/query generation service output that uses trained machine learning models (e.g. large language model) in response the query based on “determined intents or other output from the graph analytic algorithms”)
But DIFONZO fails to specifically recite the large language model
However, KARLBERG teaches the above limitation(s) at least by (paragraph [0094] “invoking, by the network system, an LLM to determine a result by making a call to the LLM with the LLM prompt (e.g. “natural language output as generated by the large language model”) and the context data obtained from the traversal of the knowledge graph; and causing presentation of the result on a user interface of a client device.”)
Therefore, before the effective filing date of the invention it would have been obvious to one of ordinary skill in the art to combine the system of DIFONZO with the use of LLM’s and LLM prompts incorporated into graph query provided by KARLBERG to, “efficiently access these data stores to construct the enterprise knowledge graph and subsequently perform a query for information”, (KARLBERG, 0012).
As per claim 11, claim 1 is incorporated and DIFONZO further discloses:
wherein the query as received from the large language model is a Cypher query, at least by (paragraph [0114] “generates the resulting query as translated to the Neo4j Cypher language”)
But DIFONZO fails to specifically recite the large language model
However, KARLBERG teaches the above limitation(s) at least by (paragraph [0027] “a first LLM generates a graph query (e.g., in Cypher language)”)
Therefore, before the effective filing date of the invention it would have been obvious to one of ordinary skill in the art to combine the system of DIFONZO with the use of LLM’s and LLM prompts incorporated into graph query provided by KARLBERG to, “efficiently access these data stores to construct the enterprise knowledge graph and subsequently perform a query for information”, (KARLBERG, 0012).
As per claim 12, claim 11 is incorporated and DIFONZO further discloses:
wherein the graph database management system is a Neo4j system that is configured to receive the Cypher query and generate a response to the Cypher query dependent upon the graph database, at least by (paragraph [0114] “generates the resulting query as translated to the Neo4j Cypher language”, paragraph [0047] the query language for the graph database (e.g., the Neo4J graph))
As per claim 13, claim 11 is incorporated and DIFONZO further discloses:
further comprising: storage media within which the graph database is stored, and wherein the graph database management system is in communication with the storage media to access the graph database, at least by (paragraph [0036] describes the storage media storing the graph database and paragraph [0043,0047] describes the graph database platform within the cybersecurity analysis platform which provides a communication with the graph database via interactive graphical user interface (GUI) )
As per claim 14 and 18, canceled.
As per claim 15, claim 1 is incorporated and DIFONZO further discloses:
wherein the graph database management system is configured to determine the response to the query automatically in response to the reception of the query, at least by (paragraph [0030] describes “automated processing and translation of natural language-based user queries into graph database queries” and paragraph [0048] further describes the query automatically being performed to determine a response to the query)
Claims 16, 17, 19 recite equivalent claim limitations as claims 1, 3, {11, 12} and above, except that they set forth the claimed invention as a system as such they are rejected for the same reasons as applied hereinabove.
As per claim 20, claim 16 is incorporated and DIFONZO further discloses:
wherein the digital network includes multiple interconnected devices with those devices and the interconnectivity of those devices being represented by information within the graph database, at least by (paragraph [0047] “graph shown in the main panel 102 of the GUI comprises the set of nodes (represented in the figure by node names or unique identifiers for a variety of different node types, e.g., virtual machines, IP addresses, services, warfighting functions (WfF), and non-lightweight directory interchange format (non-LDIF) entities) and edges)
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Sun et al. (US 20250150345 A1): paragraph [0042, 0053, 0072].
Attawar et al. (“NLSQL: Generating and Executing SQL Queries via Natural Language Using Large Language Models”): Abstract, Sec B., Fig. 1.
Vangala et al. (US 20240419918 A1): Abstract, para. 0054
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 DENNIS TRUONG whose telephone number is (571)270-3157. The examiner can normally be reached Monday - Friday 8:30 am - 5:30 pm PT.
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, Amy Ng can be reached at (571) 270-1698. 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.
/DENNIS TRUONG/Primary Examiner, Art Unit 2152 05/19/2026
Prosecution Insights