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 .
Claim Objections
Claim 9 is objected to because of the following informality: the claims use the abbreviations VPC and ETL without first defining VPC and ETL before use of the abbreviation in the claims. Appropriate correction is required.
Double Patenting
The nonstatutory 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 nonstatutory 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 nonstatutory 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 §§ 706.02(l)(1) - 706.02(l)(3) 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).
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The 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/process/file/efs/guidance/eTD-info-I.jsp.
Claims 1, 5, 11 and 15 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-3 and 5-6 of U.S. Application 19/067,582. Although the claims at issue are not identical, they are not patentably distinct from each other because they are obvious variants of each other.
This is a provisional nonstatutory double patenting rejection because the patentably indistinct claims have not in fact been patented.
The chart below shows the correspondence between the claims in the current application and the claims in the patent.
Instant Application 19/314,730
U.S. Application 19/067,582
1. A method, comprising: continuously obtaining Information Technology (IT) telemetry data from a plurality of disparate IT platforms including a plurality of servers, network devices, and applications, the IT telemetry data associated with log files, system traces, metrics, alerts, and infrastructure configurations for monitoring and troubleshooting an enterprise IT system;
providing an IT telemetry structured database to a Large Language Model (LLM), the Large Language Model generating a plurality of schematic inferences from the IT telemetry structured database;
receiving an enterprise IT administrator query regarding the enterprise IT system;
1. (Original) A system, comprising: a network interface configured to periodically access Information Technology (IT) telemetry data from a plurality of disparate IT platforms including a plurality of servers, network devices, and applications, the IT telemetry data associated with log files, system traces, metrics, alerts, and infrastructure configurations for monitoring and troubleshooting an enterprise IT system;
storage configured to maintain the IT telemetry structured database for a Large Language Model (LLM), the Large Language Model generating a plurality of schematic inferences from the IT telemetry structured database;
3. query from the enterprise IT administrator
5. wherein the IT telemetry data is dynamically schematized into virtual tables using Foreign Data Wrappers.
2. wherein the IT telemetry data is accessed using PostgreSQL Foreign Data Wrappers (FDWs)
5. (Original) The system of claim 1, wherein Foreign Data Wrappers (FDWs) are used to dynamically schematize the IT telemetry data into the IT telemetry structured database.
5. (Original) The system of claim 1, wherein Foreign Data Wrappers (FDWs) are used to dynamically schematize the IT telemetry data into the IT telemetry structured database.
6. (Original) The system of claim 5, wherein the FDWs are used to generate dynamic virtual tables and create the IT telemetry structured database.
Claim 11 corresponds to claim 1, and is rejected accordingly.
Claim 15 corresponds to claim 5, and is rejected accordingly.
Each patent claim in the above chart contains all the limitations recited in the corresponding claim of the current application. In other words, each patent claim is either 1) narrower than or 2) substantially equivalent to the corresponding claim of the instant application. It would have been obvious to a person of ordinary skill in the data processing art at the time the invention was made to omit elements when the remaining elements perform as before. A person of ordinary skill could have arrived at the present claims by omitting the details of the patent claims. See In re Karlson (CCPA) 136 USPQ 184, decided January 16, 1963 (“Omission of element and its function in combination is obvious expedient if remaining elements perform same functions as before.”).
Claim 1 is provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over ” US19/067,582” further in view of OMOIGUI (US 20100070448 A1) in view of Bosnjakovic (US 20250390516 A1)
Regarding claim 1, ” US19/067,582” discloses the features of claim 1 of the instant application as shown above,
‘” US19/067,582” does not explicitly teach:
referencing a plurality of query generation rules; generating a plurality of subqueries using the enterprise IT administrator query and the plurality of query generation rules, wherein responses to the plurality of subqueries are generated using the LLM using the IT telemetry structured database, wherein the plurality of subqueries are used to generate an LLM response to the enterprise IT administrator query.
However OMOIGUI discloses:
referencing a plurality of query generation rules; (OMOIGUI, [2705] Drag and Drop dynamic query generation applies to entities, semantic wildcards, smart copy and paste and/or other Dynamic Linking invocation models. As noted previously, the query generation rules can result in sequential queries.)
generating a plurality of subqueries using the enterprise IT administrator query and the plurality of query generation rules, (OMOIGUI, [1613] The server-side semantic query processor subdivides semantic queries into several sub-queries; [1660] The implementation of the sub-query would then follow the rules described above depending on whether the query contains a context predicate, is based on a knowledge type, information type, etc; [1248] The wizard compiles the query, sends the SQML to the KISes in the selected profile, and then displays the results (as sub-queries/agents) [2705] Drag and Drop dynamic query generation applies to entities, semantic wildcards, smart copy and paste and/or other Dynamic Linking invocation models. As noted previously, the query generation rules can result in sequential queries; )
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of ” US19/067,582” with the teaching of OMOIGUI to customize and “blend” Agents and the underlying related queries to optimize the presentation of the resulting information , (OMOIGUI, abstract) and also to securing information from information sources, semantically linking the information from the information sources, maintaining the semantic attributes of the body of semantically linked information, delivering requested semantic information based upon user queries and presenting semantic information according to customizable user preferences, (OMOIGUI, [0281]).
However ” US19/067,582” in view of OMOIGUI does not clearly disclose: wherein responses to the plurality of subqueries are generated using the LLM using the IT telemetry structured database, wherein the plurality of subqueries are used to generate an LLM response to the enterprise IT administrator query.
However Bosnjakovic discloses:
wherein responses to the plurality of subqueries are generated using the LLM using the IT telemetry structured database, (Bosnjakovic [0040] LLMs 125 can be configured and trained to receive queries or sub-queries in a natural language format and to generate their respective responses in a natural language format]… LLMs 125 are shown in the example of FIG. 1 as residing within the database; [0072] The online resource 120 generates an answer to the query 501 by combining the responses to all of the sub-queries )
wherein the plurality of subqueries are used to generate an LLM response to the enterprise IT administrator query. (Bosnjakovic [0040] LLMs 125 can be configured and trained to receive queries or sub-queries in a natural language format and to generate their respective responses in a natural language format]… LLMs 125 are shown in the example of FIG. 1 as residing within the database; [0072] The online resource 120 generates an answer to the query 501 by combining the responses to all of the sub-queries)
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of ” US19/067,582” in view of OMOIGUI with the teaching of Bosnjakovic to improve the accuracy of such responses, (Bosnjakovic, [0021]) and also to improving the capability of an automated assistant associated with an online resource to automatically generate responses to complex user queries, (Bosnjakovic, [0024]).
Claims 1 – 9 and 11-19 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-20 of U.S. Application No. 19314761. Although the claims at issue are not identical, they are not patentably distinct from each other because they are obvious variants of each other.
The chart below shows the correspondence between the claims in the current application and the patent claims.
Current Application
U.S. Application No. 19314761
1. A method, comprising: continuously obtaining Information Technology (IT) telemetry data from a plurality of disparate IT platforms including a plurality of servers, network devices, and applications, the IT telemetry data associated with log files, system traces, metrics, alerts, and infrastructure configurations for monitoring and troubleshooting an enterprise IT system;
providing an IT telemetry structured database to a Large Language Model (LLM), the Large Language Model generating a plurality of schematic inferences from the IT telemetry structured database;
receiving an enterprise IT administrator query regarding the enterprise IT system;
referencing a plurality of query generation rules; generating a plurality of subqueries using the enterprise IT administrator query and the plurality of query generation rules,
wherein responses to the plurality of subqueries are generated using the LLM using the IT telemetry structured database, wherein the plurality of subqueries are used to generate an LLM response to the enterprise IT administrator query.
1. A method, comprising: continuously obtaining Information Technology (IT) telemetry data from a plurality of disparate IT platforms including a plurality of servers, network devices, and applications, the IT telemetry data associated with log files, system traces, metrics, alerts, and infrastructure configurations for monitoring and troubleshooting an enterprise IT system;
providing the IT telemetry data to a Large Language Model (LLM), the Large Language Model generating a plurality of schematic inferences from the IT telemetry data;
2. The method of claim 1, wherein the IT telemetry data is used to generate an IT telemetry structured database used by the LLM.
receiving an enterprise IT administrator query regarding the enterprise IT system;
generating a first plurality of subqueries using the enterprise IT administrator query and a plurality of query generation rules,
wherein a first subquery response is generated by the LLM using the IT telemetry data,
wherein the first plurality of subqueries lead to generation of an LLM response to the enterprise IT administrator query.
2. The method of claim 1, wherein a plurality of alternate query generation rules are referenced to generate a plurality of alternate queries upon generation of the subqueries.
3. The method of claim 1, wherein a plurality of alternate query generation rules are referenced to generate a plurality of alternate queries upon generation of the subqueries.
3. The method of claim 1, wherein a plurality of follow-on query generation rules are referenced to generate a plurality of follow-on queries upon generation of the subqueries.
4. The method of claim 1, wherein a plurality of follow-on query generation rules are referenced to generate a plurality of follow-on queries upon generation of the subqueries.
4. The method of claim 1, wherein the plurality of subqueries are dynamically updated based on responses to previously executed subqueries.
5. The method of claim 1, wherein the plurality of subqueries are dynamically updated based on responses to previously executed subqueries.
5. The method of claim 1, wherein the IT telemetry data is dynamically schematized into virtual tables using Foreign Data Wrappers.
6. The method of claim 1, wherein the IT telemetry data is dynamically schematized into virtual tables using Foreign Data Wrappers.
6. The method of claim 1, wherein the LLM is provided access only to IT manager specified data sources in a highly structured manner.
7. The method of claim 1, wherein the LLM is provided access only to IT manager specified data sources in a highly structured manner.
7. The method of claim 1, wherein the query generation rules include using only provided schemas and selecting only explicitly listed columns
8. The method of claim 1, wherein the query generation rules include using only provided schemas and selecting only explicitly listed column
8. The method of claim 1, further comprising incorporating curated IT knowledge bases to reduce LLM hallucinations.
9. The method of claim 1, further comprising incorporating curated IT knowledge bases to reduce LLM hallucinations.
9. The method of claim 1, wherein the LLM connects to a customer VPC through a data connector agent without ETL processing.
10. The method of claim 1, wherein the LLM connects to a customer VPC through a data connector agent without ETL processing.
Claim 11 corresponds to claim 1, and is rejected accordingly.
Claim 12 corresponds to claim 2, and is rejected accordingly.
Claim 13 corresponds to claim 3, and is rejected accordingly.
Claim 14 corresponds to claim 4, and is rejected accordingly.
Claim 15 corresponds to claim 5, and is rejected accordingly.
Claim 16 corresponds to claim 6, and is rejected accordingly.
Claim 17 corresponds to claim 7, and is rejected accordingly.
Claim 18 corresponds to claim 8, and is rejected accordingly.
Claim 19 corresponds to claim 9, and is rejected accordingly.
Each patent claim in the above chart contains all the limitations recited in the corresponding claim of the instant application. In other words, each patent claim is either 1) narrower than or 2) substantially equivalent to the corresponding claim of the instant application. It would have been obvious to a person of ordinary skill in the data processing art at the time the invention was made to omit elements when the remaining elements perform as before. A person of ordinary skill could have arrived at the present claims by omitting the details of the patent claims. See In re Karlson (CCPA) 136 USPQ 184, decided January 16, 1963 (“Omission of element and its function in combination is obvious expedient if remaining elements perform same functions as before.”).
Claims 1, 5, 11 and 15 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1 and 4-5 of U.S. Application No. 19/067,559. Although the claims at issue are not identical, they are not patentably distinct from each other because they are obvious variants of each other.
The chart below shows the correspondence between the claims in the current application and the patent claims.
Current Application
U.S. Application No. 19/067,559
1. A method, comprising: continuously obtaining Information Technology (IT) telemetry data from a plurality of disparate IT platforms including a plurality of servers, network devices, and applications, the IT telemetry data associated with log files, system traces, metrics, alerts, and infrastructure configurations for monitoring and troubleshooting an enterprise IT system;
providing an IT telemetry structured database to a Large Language Model (LLM), the Large Language Model generating a plurality of schematic inferences from the IT telemetry structured database;
receiving an enterprise IT administrator query regarding the enterprise IT system;
1. A method, comprising: obtaining Information Technology (IT) telemetry data from a plurality of disparate IT platforms including a plurality of servers, network devices, and applications, the IT telemetry data associated with log files, system traces, metrics, alerts, and infrastructure configurations for monitoring and troubleshooting an enterprise IT system;
providing the IT telemetry structured database to a Large Language Model (LLM), the Large Language Model generating a plurality of schematic inferences from the IT telemetry structured database;
and receiving a first query from an enterprise IT administrator regarding the enterprise IT system
5. The method of claim 1, wherein the IT telemetry data is dynamically schematized into virtual tables using Foreign Data Wrappers.
4. The method of claim 1, wherein Foreign Data Wrappers (FDWs) are used to dynamically schematize the IT telemetry data into the IT telemetry structured database.
5. The method of claim 4, wherein the FDWs are used to generate dynamic virtual tables and create the IT telemetry structured database.
Claim 11 corresponds to claim 1, and is rejected accordingly.
Claim 15 corresponds to claim 5, and is rejected accordingly.
Claim 1 is provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over ” US19/067,559” further in view of OMOIGUI (US 20100070448 A1) in view of Bosnjakovic (US 20250390516 A1)
Regarding claim 1, ” US19/067,559” discloses the features of claim 1 of the instant application as shown above,
” US19/067,559” does not explicitly teach:
referencing a plurality of query generation rules; generating a plurality of subqueries using the enterprise IT administrator query and the plurality of query generation rules, wherein responses to the plurality of subqueries are generated using the LLM using the IT telemetry structured database, wherein the plurality of subqueries are used to generate an LLM response to the enterprise IT administrator query.
However OMOIGUI discloses:
referencing a plurality of query generation rules; (OMOIGUI, [2705] Drag and Drop dynamic query generation applies to entities, semantic wildcards, smart copy and paste and/or other Dynamic Linking invocation models. As noted previously, the query generation rules can result in sequential queries.)
generating a plurality of subqueries using the enterprise IT administrator query and the plurality of query generation rules, (OMOIGUI, [1613] The server-side semantic query processor subdivides semantic queries into several sub-queries; [1660] The implementation of the sub-query would then follow the rules described above depending on whether the query contains a context predicate, is based on a knowledge type, information type, etc; [1248] The wizard compiles the query, sends the SQML to the KISes in the selected profile, and then displays the results (as sub-queries/agents) [2705] Drag and Drop dynamic query generation applies to entities, semantic wildcards, smart copy and paste and/or other Dynamic Linking invocation models. As noted previously, the query generation rules can result in sequential queries; )
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of ” US19/067,582” with the teaching of OMOIGUI to customize and “blend” Agents and the underlying related queries to optimize the presentation of the resulting information , (OMOIGUI, abstract) and also to securing information from information sources, semantically linking the information from the information sources, maintaining the semantic attributes of the body of semantically linked information, delivering requested semantic information based upon user queries and presenting semantic information according to customizable user preferences, (OMOIGUI, [0281]).
However ” US19/067,559” in view of OMOIGUI does not clearly disclose: wherein responses to the plurality of subqueries are generated using the LLM using the IT telemetry structured database, wherein the plurality of subqueries are used to generate an LLM response to the enterprise IT administrator query.
However Bosnjakovic discloses:
wherein responses to the plurality of subqueries are generated using the LLM using the IT telemetry structured database, (Bosnjakovic [0040] LLMs 125 can be configured and trained to receive queries or sub-queries in a natural language format and to generate their respective responses in a natural language format]… LLMs 125 are shown in the example of FIG. 1 as residing within the database; [0072] The online resource 120 generates an answer to the query 501 by combining the responses to all of the sub-queries )
wherein the plurality of subqueries are used to generate an LLM response to the enterprise IT administrator query. (Bosnjakovic [0040] LLMs 125 can be configured and trained to receive queries or sub-queries in a natural language format and to generate their respective responses in a natural language format]… LLMs 125 are shown in the example of FIG. 1 as residing within the database; [0072] The online resource 120 generates an answer to the query 501 by combining the responses to all of the sub-queries)
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of ” US19/067,559” in view of OMOIGUI with the teaching of Bosnjakovic to improve the accuracy of such responses, (Bosnjakovic, [0021]) and also to improving the capability of an automated assistant associated with an online resource to automatically generate responses to complex user queries, (Bosnjakovic, [0024]).
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.
Claims 1-3, 8, 10-13, 18 and 20 are rejected under 35 U.S.C. 103 as being
unpatentable over Garrison (US 2022/0200928 Al) in view of Srinivasakumar (US 20260080659 A1) in view of OMOIGUI (US 20100070448 A1) in view of Bosnjakovic (US 20250390516 A1)
Regarding claim 1, Garrison discloses: A method, comprising: continuously obtaining Information Technology (IT) telemetry data from a plurality of disparate IT platforms including a plurality of servers, network devices, and applications, (Garrison, [0044] telemetry 318 obtained by monitoring products 320, such as the network/computing equipment and software 102(1)-102 (N) of the enterprise. The product telemetry 318 may include operational states, updates and configuration related data, faults, errors, etc.;[0020]-[0022], e.g. [0020]The network/computing equipment and software 102(1)-102(N) may include any type of network devices or network nodes such as controllers, access points, gateways, switches, routers, hubs, bridges, gateways, modems, firewalls, intrusion protection devices/software, repeaters, servers, and so on; [0022] The network/computing equipment and software 102(1)-102(N) may send to the cloud portal 100, via telemetry techniques, data about their operational status and configurations so that the cloud portal 100 is continuously updated about the operational status, configurations, software versions, etc. of each instance of the network/computing equipment and software 102(1 )-102(N) of an enterprise; [0030] The telemetry data 234, obtained by a provider from various enterprises, includes software types, releases, typically enabled and disabled features and so on; [0027] The product and network telemetry 214 may include telemetry data from cloud agents/collectors and underlying product telemetry for asset connectivity status, management controller, software type, software release, and configured features.)
the IT telemetry data associated with log files, system traces, metrics, alerts, and infrastructure configurations (Garrison, [0044] The product telemetry 318 may include operational states, updates and configuration related data, faults, errors; [0022] The network/computing equipment and software 102(1)-102(N) may send to the cloud portal 100, via telemetry techniques, data about their operational status and configurations so that the cloud portal 100 is continuously updated about the operational status, configurations, software versions, etc. of each instance of the network/computing equipment and software 102(1 )-102(N) of an enterprise; )
for monitoring and troubleshooting an enterprise IT system; (Garrison, [0037] The contextual insights 250 are generated using supporting material from the data and information systems 230… the contextual insights 250 may identify a network problem or a troubleshooting issue, one or more reasons for the network problem, and possible remediation actions; [0039] the cloud portal 100 extracts relevant support material (e.g., product support information) or content ( contextual alerts) from the data and information systems 230; [0044] The data sources 310 further include product telemetry 318 obtained by monitoring products 320, such as the network/computing equipment and software 102(1)-102(N) of the enterprise)
receiving an enterprise IT administrator query regarding the enterprise IT system; (Garrison, [0090]-[0092], e.g.[0090] refines and tailors the support material specific to the enterprise given the current context and a stage of adoption; the cloud portal 100 uses access controls to select network resources from the network resources of the enterprise that the logged-in user can view and act upon and/or to select specific categories and type of content. For example, if the logged-in user is a network troubleshooter, only troubleshooting related content (troubleshooting contextual data set) is selected. On the other hand, if the user is a network administrator, all network related content (network related contextual data set) is selected; [0094]-[0100], e.g. [0094] the cloud portal 100 determines whether the generated support material set matches user-selectable context in the cloud portal 100. By default, the users are provided with the high-level view 400 of FIG. 4 that represents the entire IT environment of the enterprise. The users may then select a particular area (context) using specialized views 364b-n of FIG. 3 and/or a particular geographic area or sites. For example, the user may select to view the security domain or the campus-network domain, or all enterprise sites within a particular geographic region)
However Garrison does not clearly disclose:
providing an IT telemetry structured database to a Large Language Model (LLM), the Large Language Model generating a plurality of schematic inferences from the IT telemetry structured database; referencing a plurality of query generation rules;generating a plurality of subqueries using the enterprise IT administrator query and the plurality of query generation rules, wherein responses to the plurality of subqueries are generated using the LLM using the IT telemetry structured database, wherein the plurality of subqueries are used to generate an LLM response to the enterprise IT administrator query.
However Srinivasakumar discloses:
providing an IT telemetry structured database to a Large Language Model (LLM), the Large Language Model generating a plurality of schematic inferences from the IT telemetry structured database; (Srinivasakumar, [0101] Graph RAG may be implemented using a graph database as a source of contextual information sent to the LLM/VLM/MMLM/etc… When implementing graph RAG, the systems and methods described herein use a graph as a content store and extract relevant chunks of documents and ask the LLM/VLM/MMLM/etc. to answer using them… the graph may be used as a database, where part of a query/prompt may be mapped to a graph query, the graph query may be executed, and the LLM/VLM/MMLM/etc. may summarize the results.; [0038] an inference runtime software to execute the model(s) and provide outputs/responses to inputs (e.g., user queries, prompts, etc.); [0136] one or more software and/or hardware resources described above may be configured as a service to allow users to train or performing inferencing of information, such as image recognition, speech recognition, or other artificial intelligence services.)
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Garrison with the teaching of Srinivasakumar so that rather than (or in addition to) providing the model with chunks of data extracted from larger sized documents-which may result in a lack of context, factual correctness, language accuracy, etc.-graph RAG may also provide structured entity information to the LLM/VLM/ MMLM/etc. by combining the structured entity textual description with its many properties and relationships, allowing for deeper insights by the model, (Srinivasakumar, [0101]).
However Garrison in view of Srinivasakumar does not clearly disclose:
referencing a plurality of query generation rules; generating a plurality of subqueries using the enterprise IT administrator query and the plurality of query generation rules, wherein responses to the plurality of subqueries are generated using the LLM using the IT telemetry structured database, wherein the plurality of subqueries are used to generate an LLM response to the enterprise IT administrator query.
However OMOIGUI discloses:
referencing a plurality of query generation rules; (OMOIGUI, [2705] Drag and Drop dynamic query generation applies to entities, semantic wildcards, smart copy and paste and/or other Dynamic Linking invocation models. As noted previously, the query generation rules can result in sequential queries.)
generating a plurality of subqueries using the enterprise IT administrator query and the plurality of query generation rules, (OMOIGUI, [1613] The server-side semantic query processor subdivides semantic queries into several sub-queries; [1660] The implementation of the sub-query would then follow the rules described above depending on whether the query contains a context predicate, is based on a knowledge type, information type, etc; [1248] The wizard compiles the query, sends the SQML to the KISes in the selected profile, and then displays the results (as sub-queries/agents) [2705] Drag and Drop dynamic query generation applies to entities, semantic wildcards, smart copy and paste and/or other Dynamic Linking invocation models. As noted previously, the query generation rules can result in sequential queries; )
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Garrison in view of Srinivasakumar with the teaching of OMOIGUI to customize and “blend” Agents and the underlying related queries to optimize the presentation of the resulting information , (OMOIGUI, abstract) and also to securing information from information sources, semantically linking the information from the information sources, maintaining the semantic attributes of the body of semantically linked information, delivering requested semantic information based upon user queries and presenting semantic information according to customizable user preferences, (OMOIGUI, [0281]).
However Garrison in view of Srinivasakumar in view of OMOIGUI does not clearly disclose: wherein responses to the plurality of subqueries are generated using the LLM using the IT telemetry structured database, wherein the plurality of subqueries are used to generate an LLM response to the enterprise IT administrator query.
However Bosnjakovic discloses:
wherein responses to the plurality of subqueries are generated using the LLM using the IT telemetry structured database, (Bosnjakovic [0040] LLMs 125 can be configured and trained to receive queries or sub-queries in a natural language format and to generate their respective responses in a natural language format]… LLMs 125 are shown in the example of FIG. 1 as residing within the database; [0072] The online resource 120 generates an answer to the query 501 by combining the responses to all of the sub-queries )
wherein the plurality of subqueries are used to generate an LLM response to the enterprise IT administrator query. (Bosnjakovic [0040] LLMs 125 can be configured and trained to receive queries or sub-queries in a natural language format and to generate their respective responses in a natural language format]… LLMs 125 are shown in the example of FIG. 1 as residing within the database; [0072] The online resource 120 generates an answer to the query 501 by combining the responses to all of the sub-queries)
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Garrison in view of Srinivasakumar in view of OMOIGUI with the teaching of Bosnjakovic to improve the accuracy of such responses, (Bosnjakovic, [0021]) and also to improving the capability of an automated assistant associated with an online resource to automatically generate responses to complex user queries, (Bosnjakovic, [0024]).
Claim 11 corresponds to claim 1, and is rejected accordingly.
Regarding claim 2, Garrison in view of Srinivasakumar in view of OMOIGUI in view of Bosnjakovic discloses all of the features with respect to claim 1as outlined above. Garrison in view of Srinivasakumar does not clearly disclose: wherein a plurality of alternate query generation rules are referenced to generate a plurality of alternate queries upon generation of the subqueries.
However OMOIGUI discloses:
wherein a plurality of alternate query generation rules are referenced to generate a plurality of alternate queries upon generation of the subqueries. (OMOIGUI, [2705] Drag and Drop dynamic query generation applies to entities, semantic wildcards, smart copy and paste and/or other Dynamic Linking invocation models. As noted previously, the query generation rules can result in sequential queries; [1613] The server-side semantic query processor subdivides semantic queries into several sub-queries; [1248] The wizard compiles the query, sends the SQML to the KISes in the selected profile, and then displays the results (as sub-queries/agents) ).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Garrison in view of Srinivasakumar with the teaching of OMOIGUI to customize and “blend” Agents and the underlying related queries to optimize the presentation of the resulting information , (OMOIGUI, abstract) and also to securing information from information sources, semantically linking the information from the information sources, maintaining the semantic attributes of the body of semantically linked information, delivering requested semantic information based upon user queries and presenting semantic information according to customizable user preferences, (OMOIGUI, [0281]).
Claim 12 corresponds to claim 2, and is rejected accordingly.
Regarding claim 3, Garrison in view of Srinivasakumar in view of OMOIGUI in view of Bosnjakovic discloses all of the features with respect to claim 1as outlined above. Garrison in view of Srinivasakumar does not clearly disclose: wherein a plurality of follow-on query generation rules are referenced to generate a plurality of follow-on queries upon generation of the subqueries.
However OMOIGUI discloses:
wherein a plurality of follow-on query generation rules are referenced to generate a plurality of follow-on queries upon generation of the subqueries. (OMOIGUI, [2705] Drag and Drop dynamic query generation applies to entities, semantic wildcards, smart copy and paste and/or other Dynamic Linking invocation models. As noted previously, the query generation rules can result in sequential queries; [1613] The server-side semantic query processor subdivides semantic queries into several sub-queries; [1248] The wizard compiles the query, sends the SQML to the KISes in the selected profile, and then displays the results (as sub-queries/agents)).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Garrison in view of Srinivasakumar with the teaching of OMOIGUI to customize and “blend” Agents and the underlying related queries to optimize the presentation of the resulting information, (OMOIGUI, abstract) and also to securing information from information sources, semantically linking the information from the information sources, maintaining the semantic attributes of the body of semantically linked information, delivering requested semantic information based upon user queries and presenting semantic information according to customizable user preferences, (OMOIGUI, [0281]).
Claim 13 corresponds to claim 3, and is rejected accordingly.
Regarding claim 8, Garrison in view of Srinivasakumar in view of OMOIGUI in view of Bosnjakovic discloses all of the features with respect to claim 1as outlined above. Claim 8 further recites: incorporating curated IT knowledge bases ( Garrison [0112] unify disparate cross-domain data including enterprise's behavior, product telemetry, enterprise network or IT data, and a knowledge base and generate holistic and contextualized digital representations of the enterprise IT environment. The techniques presented herein further thread the disparate cross-domain data to support targeted enterprise use cases to unlock and enable enterprise success of managing its IT environment)
However Garrison does not clearly disclose:
incorporating curated IT knowledge bases to reduce LLM hallucinations.
However Srinivasakumar discloses:
incorporating curated IT knowledge bases to reduce LLM hallucinations.
(Srinivasakumar, [0101] Graph RAG may be implemented using a graph database as a source of contextual information sent to the LLM/VLM/MMLM/etc… When implementing graph RAG, the systems and methods described herein use a graph as a content store and extract relevant chunks of documents and ask the LLM/VLM/MMLM/etc. to answer using them… the graph may be used as a database, where part of a query/prompt may be mapped to a graph query, the graph query may be executed, and the LLM/VLM/MMLM/etc. may summarize the results.; [0038] an inference runtime software to execute the model(s) and provide outputs/responses to inputs (e.g., user queries, prompts, etc.); [0136] one or more software and/or hardware resources described above may be configured as a service to allow users to train or performing inferencing of information, such as image recognition, speech recognition, or other artificial intelligence services.)
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Garrison with the teaching of Srinivasakumar so that rather than (or in addition to) providing the model with chunks of data extracted from larger sized documents-which may result in a lack of context, factual correctness, language accuracy, etc.-graph RAG may also provide structured entity information to the LLM/VLM/ MMLM/etc. by combining the structured entity textual description with its many properties and relationships, allowing for deeper insights by the model, (Srinivasakumar, [0101]).
Claim 18 corresponds to claim 8, and is rejected accordingly.
Regarding claim 10, Garrison in view of Srinivasakumar in view of OMOIGUI in view of Bosnjakovic discloses all of the features with respect to claim 1as outlined above. Garrison in view of Srinivasakumar does not clearly disclose: wherein the enterprise IT administrator query is deconstructed into the plurality of subqueries displayed in real-time.
However OMOIGUI discloses:
wherein the enterprise IT administrator query is deconstructed into the plurality of subqueries displayed in real-time. (OMOIGUI, 1613] The server-side semantic query processor subdivides semantic queries into several sub-queries; [3245] "Live Views" (Live Sub-Queries)… create a quick sub-query and specify their top competitors as publisher pivots. This chart can be displayed in a slide-out view alongside the default chart. Other mini-queries can also be created to have "Live Views." This will be very powerful for the purposes of Live ( or Real-Time) Analytics)
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Garrison in view of Srinivasakumar with the teaching of OMOIGUI to customize and “blend” Agents and the underlying related queries to optimize the presentation of the resulting information , (OMOIGUI, abstract) and also to securing information from information sources, semantically linking the information from the information sources, maintaining the semantic attributes of the body of semantically linked information, delivering requested semantic information based upon user queries and presenting semantic information according to customizable user preferences, (OMOIGUI, [0281]).
Claim 20 corresponds to claim 10, and is rejected accordingly.
Claims 4 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Garrison (US 2022/0200928 Al) in view of Srinivasakumar (US 20260080659 A1) in view of OMOIGUI (US 20100070448 A1) in view of Bosnjakovic (US 20250390516 A1) in view of Kulkarni (US 2025/0348485 Al)
Regarding claim 4, Garrison in view of Srinivasakumar in view of OMOIGUI in view of Bosnjakovic discloses all of the features with respect to claim 1as outlined above. Garrison in view of Srinivasakumar in view of OMOIGUI in view of Bosnjakovic does not clearly disclose: wherein the plurality of subqueries are dynamically updated based on responses to previously executed subqueries.
However Kulkarni discloses:
wherein the plurality of subqueries are dynamically updated based on responses to previously executed subqueries. (Kulkarni [0049] modify the sub-query to be dependent on one or more responses from one or more other of the sub-queries")
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Garrison in view of Srinivasakumar in view of OMOIGUI in view of Bosnjakovic with the teaching of Kulkarni so that the system can await the sub-query response prior to causing the given sub-query to be processed using its corresponding tool(s) and also the system can additionally refine the given sub-query, using the sub-query response on which it is dependent, prior to interacting with the tool(s) to cause processing of the sub-query. Moreover, the system can coordinate the order and timing of processing of each of the sub-queries., (Kulkarni, [0051]) .
Claim 14 corresponds to claim 4, and is rejected accordingly.
Claims 5 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Garrison (US 2022/0200928 Al) in view of Srinivasakumar (US 20260080659 A1) in view of OMOIGUI (US 20100070448 A1) in view of Bosnjakovic (US 20250390516 A1) in view of Erdogan (US 20140067792 A1)
Regarding claim 5, Garrison in view of Srinivasakumar in view of OMOIGUI in view of Bosnjakovic discloses all of the features with respect to claim 1 as outlined above. Garrison in view of Srinivasakumar in view of OMOIGUI in view of Bosnjakovic does not clearly disclose: wherein the IT telemetry data is dynamically schematized into virtual tables using Foreign Data Wrappers.
However Erdogan discloses:
wherein the IT telemetry data is dynamically schematized into virtual tables using Foreign Data Wrappers. (Erdogan, [0048], when a new field is added to the semi-structured data, directly loading it into the database requires the conversion script to emit this new field's value to intermediate files. In contrast, foreign data wrappers can immediately pick up the new field from the underlying data once the user alters the foreign table's schema to include this field.)
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Garrison in view of Srinivasakumar in view of OMOIGUI in view of Bosnjakovic with the teaching of Erdogan to avoid the loading of data into database tables and the associated expense of data duplication and data shuffling across a network. Further, the disclosed approach more easily adapts to the changes in the underlying data, (Erdogan, [0048]).
Claim 15 corresponds to claim 5, and is rejected accordingly.
Claims 6 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Garrison (US 2022/0200928 Al) in view of Srinivasakumar (US 20260080659 A1) in view of OMOIGUI (US 20100070448 A1) in view of Bosnjakovic (US 20250390516 A1) in view of Mukherjee (US20240354436A1)
Regarding claim 6, Garrison in view of Srinivasakumar in view of OMOIGUI in view of Bosnjakovic discloses all of the features with respect to claim 1as outlined above. Claim 6 further recites: provided access only to IT manager specified data sources in a highly structured manner. (Garrison, [0090]-[0092], e.g.[0090] refines and tailors the support material specific to the enterprise given the current context and a stage of adoption; the cloud portal 100 uses access controls to select network resources from the network resources of the enterprise that the logged-in user can view and act upon and/or to select specific categories and type of content. For example, if the logged-in user is a network troubleshooter, only troubleshooting related content (troubleshooting contextual data set) is selected. On the other hand, if the user is a network administrator, all network related content (network related contextual data set) is selected; [0094]-[0100], e.g. [0094] the cloud portal 100 determines whether the generated support material set matches user-selectable context in the cloud portal 100. By default, the users are provided with the high-level view 400 of FIG. 4 that represents the entire IT environment of the enterprise. The users may then select a particular area (context) using specialized views 364b-n of FIG. 3 and/or a particular geographic area or sites. For example, the user may select to view the security domain or the campus-network domain, or all enterprise sites within a particular geographic region)
However Garrison in view of Srinivasakumar in view of OMOIGUI in view of Bosnjakovic does not clearly disclose: wherein the LLM is provided access only to IT manager specified data sources in a highly structured manner.
However Mukherjee discloses:
wherein the LLM is provided access only to IT manager specified data sources in a highly structured manner. (Mukherjee, [0007] permissioning of data can be respected and a system or user can ensure that one or more LLMs only provides, for example, responses that are based on permitted information sources that users are authorized to access)
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Garrison in view of Srinivasakumar in view of OMOIGUI in view of Bosnjakovic with the teaching of Mukherjee to ensure that one or more LLMs only provides, for example, responses that are based on permitted information sources that users are authorized to access so that user can enable LLMs to search a large corpus of data relevant to user queries while simultaneously avoid providing impermissible documents to LLMs, thus advantageously facilitating effective search on large corpus of documents and helping preserve confidentiality of sensitive information, (Mukherjee, [0007]).
Claim 16 corresponds to claim 6, and is rejected accordingly.
Claims 7 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Garrison (US 2022/0200928 Al) in view of Srinivasakumar (US 20260080659 A1) in view of OMOIGUI (US 20100070448 A1) in view of Bosnjakovic (US 20250390516 A1) in view of TRUONG (US20240330279A1)
Regarding claim 7, Garrison in view of Srinivasakumar in view of OMOIGUI in view of Bosnjakovic discloses all of the features with respect to claim 1 as outlined above. Garrison in view of Srinivasakumar in view of OMOIGUI in view of Bosnjakovic does not clearly disclose: wherein the query generation rules include using only provided schemas and selecting only explicitly listed columns.
However TRUONG discloses:
wherein the query generation rules include using only provided schemas and selecting only explicitly listed columns. (TRUONG [0030] database schema 230 can specify database tables, column names, data types for each field, and/or relationships between different portions of data stored in database 114; [0031] At step 304, example initialization module 208 of natural language application 120 generates example requests and associated example queries using predefined templates and the database schema 230 received at step 302; [0028] ask prompt generation module 206 to generate a prompt that includes specific instructions on which columns of tables in database 114 and/or which formulas language model 204 should use when generating a query. In such cases, request processing module 202 can use a map (not shown) that encodes industry/domain knowledge to determine the specific instructions on which columns of tables in the database 114 and/or which formulas the language model 204 should use.)
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Garrison in view of Srinivasakumar in view of OMOIGUI in view of Bosnjakovic with the teaching of TRUONG to generate more accurate database queries that capture the user intent in user requests by learning from example queries associated with example requests that are most similar to the user requests. The generated queries can also be optimized to utilize computational resources efficiently by learning from relatively efficient example queries, (TRUONG, [0009]).
Claim 17 corresponds to claim 7, and is rejected accordingly.
Claims 9 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Garrison (US 2022/0200928 Al) in view of Srinivasakumar (US 20260080659 A1) in view of OMOIGUI (US 20100070448 A1) in view of Bosnjakovic (US 20250390516 A1) in view of Mardikar (US20240354423)
Regarding claim 9, Garrison in view of Srinivasakumar in view of OMOIGUI in view of Bosnjakovic discloses all of the features with respect to claim 1as outlined above. Garrison in view of Srinivasakumar in view of OMOIGUI in view of Bosnjakovic does not clearly disclose: wherein the LLM connects to a customer VPC through a data connector agent without ETL processing.
However Mardikar discloses:
wherein the LLM connects to a customer VPC through a data connector agent without ETL processing. (Mardikar, [0064] For example, the VPC 220 can maintain a set of application services. The set of application services of the VPC 220 can include a frontend service 222, an AI service 224, a backend service 226, and an access management service 228; [0066] the AI service 224 can use at least one ML model ( e.g., a generative AI model) to generate the response; [0031] an ML model includes a language model… a language model can be a large language model (LLM))
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Garrison in view of Srinivasakumar in view of OMOIGUI in view of Bosnjakovic with the teaching of Mardikar to provide a secure, logically isolated private section of a public cloud environment that is hosted remotely by the provider of the public cloud environment, (Mardikar, [0063]) and also to access a virtual environment for managing the cybersecurity of the computing system, (Mardikar, abstract).
Claim 19 corresponds to claim 9, and is rejected accordingly.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Faezeh Forouharnejad whose telephone number is (571)270-7416. The examiner can normally be reached on Mondays, Wednesdays and Thursdays.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Shah Sanjiv can be reached on (571)272-4098. 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 Patent Center and the Private Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from Patent Center or Private PAIR. Status information for unpublished applications is available through Patent Center and Private PAIR to authorized users only. Should you have questions about access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free)
/F.F. /
Examiner, Art Unit 2166
/KHANH B PHAM/Primary Examiner, Art Unit 2166
Prosecution Insights