DETAILED ACTION
1. This action is responsive to Application no.18/667,295 filed 5/17/2024. All claims have been examined and are currently pending.
Notice of Pre-AIA or AIA Status
2. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 102
3. In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
4. 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)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(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.
5. Claims 1-6, 8-16, 18-19 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Sun et al (2025/0150345).
Regarding claim 1 Sun et al (2025/0150345) teaches A device (figure 1 120; fig 9; 0013: computer-implemented methods; 0035; 117 fig 9), comprising:
a processing system including a processor (fig 9 902 processor; 118); and
a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations (fig 9 904 memory; 118), the operations comprising:
obtaining first configuration data indicative of a first configuration of a first component of a communications network (0012: network management system; 13: obtaining input data related to a configuration or an operation of one or more assets in an enterprise network; 0024: the network/computing equipment and software is configuration data representing various configurations, such as enabled and disabled features;
[0026] 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.; 0056; 114);
generating a prompt configured for input to a large language model (LLM), wherein the generating of the prompt is based at least in part upon the first configuration data (0013: generating a contextualized prompt based on the input data; providing the contextualized prompt to the artificial intelligence model; 15; LLM;
[0021] The techniques presented herein, provide a unified prompt-based network management system that includes a comprehensive context-embedded automatic prompt engine i.e., an intelligent auto-prompt engine, that automatically generates contextualized prompts and is adaptable to different application scenarios (different application tasks);
facilitating input of the prompt to the LLM (13; 15; 35; 37: generates prompt for an LLM);
responsive to the input of the prompt to the LLM, receiving a knowledge graph that was generated by the LLM (0021: knowledge graph; 0021: enterprise network related information and network knowledge graphs (network topology, feature information, etc.) may be deployed jointly as context embeddings to modulate the intelligent auto-prompt engine. By incorporating domain specific context (selected network domain application), the generated prompts are highly efficient in narrowing down the prompt semantic setting, which directly improves accuracy of LLM generated solutions. Further, the contextualized prompts include reverse inference(s) that help generate tailored solutions (actionable tasks) specific to input data (user input).);
validating the knowledge graph relative to the first configuration data, wherein the validating comprises determining whether one or more discrepancies exist between the knowledge graph and the first configuration data, and wherein the validating results in feedback data (0033: the actionable tasks may involve changing the configuration of the one or more affected network devices in the enterprise network; 36-37
0043: changing a configuration of or reconfiguring a particular network device; intelligent auto-prompt engine may generate a contextualized prompt based on which;
0054: The actionable tasks 242a-i are fed back into the intelligent auto-prompt engine 210 to improve accuracy (further train the intelligent auto-prompt engine 210).; the intelligent auto-prompt engine is continuously trained via a feedback loop to improve accuracy of generated contextual prompts; 56;
65-67; 73: feedback & ground truth;
113-115);
responsive to the one or more discrepancies existing between the knowledge graph and the first configuration data, generating an updated prompt configured for input to the LLM, wherein the generating of the updated prompt is based at least in part upon the feedback data (0036: The intelligent auto-prompt engine is a multi-task actor configured to generate different network domain-dependent prompts for incorporating specialized network domain knowledge. The intelligent auto-prompt engine is trained using a reverse prompt generation module. Moreover, user profiles and network asset information (e.g., enterprise network inventory) are also employed in prompt contextualization. By using deep customization in prompt generation, the unified prompt system 120 generates specific, tailored solutions/actionable tasks in network automation. The intelligent auto-prompt engine may automatically generate prompts and adapt to different application scenarios (application tasks). User and network knowledge graphs are deployed jointly as context embeddings to modulate the intelligent auto-prompt engine. By incorporating the domain specific context, the generated prompts are highly efficient in narrowing down the prompt semantic setting, which directly maximize the accuracy of LLM generated solutions i.e., actionable tasks generated by the LLM of the unified prompt system 120.;
0037: generates different contextualized prompts; as such, the contextualized prompts are specifically tailored to the enterprise network, the user, and the task at hand;
0054: the generated contextualized prompt; 56: adapt the…prompt;
114: the artificial intelligence model may further include generating a new prompt including the context information and the solution);
facilitating input of the updated prompt to the LLM (contextualized prompt; 13; 15; 35; 37: generates prompt for an LLM; 0043: changing a configuration of or reconfiguring a particular network device; intelligent auto-prompt engine may generate a contextualized prompt based on which);
responsive to the input of the updated prompt to the LLM, receiving an updated knowledge graph that was generated by the LLM (0033: the actionable tasks may involve changing the configuration of the one or more affected network devices in the enterprise network; 35-36; 0043; 114: new prompt including the context information); and
outputting the updated knowledge graph
([0012] Techniques presented herein provide a unified prompt-based network management system that involves an intelligent auto-prompt engine generating contextualized prompts for an artificial intelligence model. The artificial intelligence model generates instructions and/or solutions and adapts to different application scenarios based on enterprise network knowledge and reverse inference(s).;
0013: The methods further involve providing the contextualized prompt to the artificial intelligence model for generating a tailored response to the input data. The tailored response includes a set of actionable tasks to be performed with respect to the one or more assets of the enterprise network.;
0036: The intelligent auto-prompt engine is trained using a reverse prompt generation module. Moreover, user profiles and network asset information (e.g., enterprise network inventory) are also employed in prompt contextualization. By using deep customization in prompt generation, the unified prompt system 120 generates specific, tailored solutions/actionable tasks in network automation. The intelligent auto-prompt engine may automatically generate prompts and adapt to different application scenarios (application tasks). User and network knowledge graphs are deployed jointly as context embeddings to modulate the intelligent auto-prompt engine. By incorporating the domain specific context, the generated prompts are highly efficient in narrowing down the prompt semantic setting, which directly maximize the accuracy of LLM generated solutions i.e., actionable tasks generated by the LLM of the unified prompt system 120.
0054: the intelligent auto-prompt engine 210 is continuously trained via a feedback loop to improve accuracy of generated contextual prompts, which in turn improves the actionable tasks 242a-i.
0056: That is, the intelligent auto-prompt engine 210 is trained to be uniformly applied to multiple downstream tasks. In other words, the task-agnostic prompt engine is configured to generate multiple different downstream tasks (actionable tasks 242a-i) depending on the use case scenario. The intelligent auto-prompt engine 210 automatically generates different task-dependent contextual prompts to establish a knowledge base tailored to user's current tasks.;
[0086] Generally, the LLM 240 consumes prompts and output solutions. In the reverse inference framework 500, the ground truth solutions (actionable tasks) together with context 510 (such as network knowledge graph 304 and the user persona 306 of FIG. 3) are utilized to formalize the reverse prompts 506. The reverse prompts 506 are passed into the LLM 240, and accordingly the LLM 240 generates the ground truth of the original prompt i.e., the ground truth issue/instructions 508. Using the ground truth issue/instructions 508, the context 510, and task dependent instructions 512 (detailed in FIG. 7), the contextualized prompt 514 is generated.;
[0114] In one instance, in the method 800, training of the artificial intelligence model during the inference phase may include obtaining a prompt including context information about the enterprise network and user input and generating a solution including at least one actionable task by processing the prompt using the artificial intelligence model. The training of the artificial intelligence model may further include generating a new prompt including the context information and the solution and generating the at least one reverse inference by processing the new prompt using the artificial intelligence model.
- Where the claim/application and reference appear to be for training/optimizing an intelligent auto-prompt engine to perform multi-task automatic prompt generation, for network management;
Where the training involves using a first prompt, evaluating (comparing knowledge graph/network configuration), and adjusting based on such to obtain a more task-dependent contextual prompt to establish a knowledge base tailored to user's current tasks.).
Regarding claim 2 Sun teaches The device of claim 1, wherein the operations further comprise storing the updated knowledge graph in a database (fig 3, 9; para 21: network knowledge graphs (network topology, feature information, etc.); 118; 120; databases: 123; 135).
Regarding claim 3 Sun teaches The device of claim 1, wherein the LLM is part of an artificial intelligence (AI) system (0012: artificial intelligence model; 15 LLM;
0034: these actionable tasks may be generated using an artificial intelligence (AI) model or a machine learning (ML) model; LLMs are deployed, this is just one non-limiting example of AI/ML models).
Regarding claim 4 Sun teaches The device of claim 3, wherein the prompt is an AI prompt (0012: an intelligent auto-prompt engine generating contextualized prompts for an artificial intelligence model).
Regarding claim 5 Sun teaches The device of claim 4, wherein the input of the AI prompt comprises directly inputting the AI prompt to the AI system, inputting the AI prompt to the AI system via one or more interfaces, or any combination thereof (0012: an intelligent auto-prompt engine generating contextualized prompts for an artificial intelligence model; 43; 106).
Regarding claim 6 Sun teaches The device of claim 1, wherein:
the prompt includes some or all of the first configuration data ([0105] The computer-implemented method 800 further involves at 804, generating a contextualized prompt based on the input data, network knowledge information of the enterprise network);
the updated prompt includes some or all of the first configuration data (114: the artificial intelligence model may further include generating a new prompt including the context information); or
any combination thereof.
Regarding claim 8 Sun teaches The device of claim 1, wherein the generating of the updated prompt is based at least in part upon the feedback data and the first configuration data (54-56; 65-67; 73; 114 – updated contextualized prompt based on feedback and network configuration/context).
Regarding claim 9 Sun teaches The device of claim 1, wherein the communications network comprises a plurality of routers and a plurality of switches
(0002: Enterprise networks include many assets and involve various enterprise service functions for equipment and software.; 0024 network devices…switches, routers).
Regarding claim 10 Sun teaches The device of claim 9, wherein the first component of the communications network comprises a first router of the plurality of routers, a first switch of the plurality of switches, or any combination thereof (0002: Enterprise networks include many assets and involve various enterprise service functions for equipment and software.; 0024 network devices…switches, routers).
Regarding claim 11 Sun teaches The device of claim 1, wherein:
the first configuration data is in a first format (0013: obtaining input data related to a configuration or an operation of one or more assets in an enterprise network); and
the operations further comprise:
obtaining second configuration data indicative of a second configuration of a second component of the communications network, the second component being a different component than the first component, the second configuration data being in a second format that is different from the first format (0013: obtaining input data related to a configuration or an operation of one or more assets in an enterprise network;
36-37; 37: The intelligent auto-prompt engine generates different contextualized prompts for different types of use cases. As such, the contextualized prompts are specifically tailored to the enterprise network, the user, and the task at hand (e.g., security patch, configuration change, etc.).;
[0115] In one form, the method 800 may further involve training the artificial intelligence model based on a plurality of network domain specific applications. In the method 800, the operation 804 of generating the contextualized prompt may further be based on a selected one of the plurality of network domain specific applications.);
generating another prompt configured for input to the LLM, wherein the generating of the another prompt is based at least in part upon the second configuration data (0013: generating a contextualized prompt based on the input data; providing the contextualized prompt to the artificial intelligence model; 0037; 0114: the artificial intelligence model may further include generating a new prompt including the context information );
facilitating input of the another prompt to the LLM (13; 15; 35; 37: generates prompt for an LLM);
responsive to the input of the another prompt to the LLM, receiving another knowledge graph that was generated by the LLM (0033: the actionable tasks may involve changing the configuration of the one or more affected network devices in the enterprise network; 35-36; 0043; 114: new prompt including the context information);
validating the another knowledge graph relative to the second configuration data, wherein the validating of the another knowledge graph comprises determining whether one or more other discrepancies exist between the another knowledge graph and the second configuration data, and wherein the validating the another knowledge graph results in other feedback data (0033: the actionable tasks may involve changing the configuration of the one or more affected network devices in the enterprise network; 36-37
0043: changing a configuration of or reconfiguring a particular network device; intelligent auto-prompt engine may generate a contextualized prompt based on which;
0054: The actionable tasks 242a-i are fed back into the intelligent auto-prompt engine 210 to improve accuracy (further train the intelligent auto-prompt engine 210).; the intelligent auto-prompt engine is continuously trained via a feedback loop to improve accuracy of generated contextual prompts; 56;
65-67; 73: feedback & ground truth;
113-115);
responsive to the one or more other discrepancies existing between the another knowledge graph and the second configuration data, generating another updated prompt configured for input to the LLM, wherein the generating of the another updated prompt is based at least in part upon the other feedback data (0036: The intelligent auto-prompt engine is a multi-task actor configured to generate different network domain-dependent prompts for incorporating specialized network domain knowledge. The intelligent auto-prompt engine is trained using a reverse prompt generation module. Moreover, user profiles and network asset information (e.g., enterprise network inventory) are also employed in prompt contextualization. By using deep customization in prompt generation, the unified prompt system 120 generates specific, tailored solutions/actionable tasks in network automation. The intelligent auto-prompt engine may automatically generate prompts and adapt to different application scenarios (application tasks). User and network knowledge graphs are deployed jointly as context embeddings to modulate the intelligent auto-prompt engine. By incorporating the domain specific context, the generated prompts are highly efficient in narrowing down the prompt semantic setting, which directly maximize the accuracy of LLM generated solutions i.e., actionable tasks generated by the LLM of the unified prompt system 120.;
0037: generates different contextualized prompts; as such, the contextualized prompts are specifically tailored to the enterprise network, the user, and the task at hand;
0054: the generated contextualized prompt; 56: adapt the..prompt;
114: the artificial intelligence model may further include generating a new prompt including the context information and the solution);
facilitating input of the another updated prompt to the LLM (13; 15; 35; 37: generates prompt for an LLM);
responsive to the input of the another updated prompt to the LLM, receiving another updated knowledge graph that was generated by the LLM (0033: the actionable tasks may involve changing the configuration of the one or more affected network devices in the enterprise network; 35-36; 0043; 114: new prompt including the context information); and
outputting the another updated knowledge graph
([0021] The techniques presented herein, provide a unified prompt-based network management system that includes a comprehensive context-embedded automatic prompt engine i.e., an intelligent auto-prompt engine, that automatically generates contextualized prompts and is adaptable to different application scenarios (different application tasks);
12; 13; 36; 54; 56; 86; 114).
Regarding claim 12 Sun teaches The device of claim 11, wherein the operations further comprise storing the another updated knowledge graph in a database (fig 3, 9; para 21: network knowledge graphs (network topology, feature information, etc.); 118; 120; databases: 123; 135).
Regarding claim 13 Sun teaches The device of claim 1, wherein the operations further comprise:
responsive to the receiving of the updated knowledge graph, generating another prompt configured for input to the LLM, wherein the generating of the another prompt is based at least in part upon the updated knowledge graph;
facilitating input of the another prompt to the LLM;
responsive to the input of the another prompt to the LLM, receiving network visualization data that was generated by the LLM;
validating the network visualization data relative to the first configuration data, wherein the validating comprises determining whether one or more other discrepancies exist between the network visualization data and the first configuration data, and wherein the validating of the network visualization data results in other feedback data;
responsive to the one or more other discrepancies existing between the network visualization data and the first configuration data, generating another updated prompt configured for input to the LLM, wherein the generating of the another updated prompt is based at least in part upon the other feedback data;
facilitating input of the another updated prompt to the LLM;
responsive to the input of the another updated prompt to the LLM, receiving updated network visualization data that was generated by the LLM; and
outputting the updated network visualization data
Where the claim recites limitations similar to claims 1 and 11 and is rejected for similar rationale and reasoning
The claim further mentions knowledge graph, and then network visualization, reciting the limitations and now incorporating the network visualization language in prompt optimization.
Sun teaches network visualization data (0021: enterprise network related information and network knowledge graphs (network topology, feature information, etc.;
0060: The network knowledge graph 304 is generated based on network knowledge information about the enterprise network. The network knowledge graph 304 may include the topology of the enterprise network, data related a plurality of network features, asset inventory of the enterprise network, and/or telemetry data about operation or configuration of the network devices or enterprise assets. In one example embodiment, the network knowledge graph 304 includes a plurality of products 308a-p (i.e., enterprise assets that include network devices such as routers, switches, servers, etc.) and a plurality of features 310a-q that are being executed on various enterprise assets. Additionally, the network knowledge graph 304 may further include various configurations for the plurality of features 310a-q (enabled/disabled, etc.).)
PNG
media_image1.png
169
272
media_image1.png
Greyscale
PNG
media_image2.png
378
742
media_image2.png
Greyscale
Where the network visualization data is a representation of the knowledge graph, is taught by Sun, and therefore is rejected based on rationale as presented in claims 1 and 11.
Regarding claim 14 Sun teaches The device of claim 13, wherein the updated network visualization data is configured to facilitate generation of a visualization of a network topography (fig 3; para 21; 60).
Regarding claim 15 Sun teaches A non-transitory machine-readable medium comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations, the operations comprising:
obtaining a knowledge graph indicative of a first configuration of a first component of a communications network, wherein the knowledge graph is obtained from a large language model (LLM) responsive to input to the LLM of a first prompt that had been based upon first configuration data indicative of the first configuration of the first component;
generating a second prompt configured for input to the LLM, wherein the generating of the second prompt is based at least in part upon the knowledge graph;
facilitating input of the second prompt to the LLM;
responsive to the input of the second prompt to the LLM, receiving network visualization data that was generated by the LLM;
validating the network visualization data relative to the knowledge graph, wherein the validating comprises determining whether one or more discrepancies exist between the network visualization data and the knowledge graph, and wherein the validating of the network visualization data results in feedback data;
responsive to the one or more discrepancies existing between the network visualization data and the knowledge graph, generating an updated prompt configured for input to the LLM, wherein the generating of the updated prompt is based at least in part upon the feedback data;
facilitating input of the updated prompt to the LLM;
responsive to the input of the updated prompt to the LLM, receiving updated network visualization data that was generated by the LLM; and
outputting the updated network visualization data.
Recites limitations similar to claims 1, 11, and specifically claim 13, and is rejected for similar rationale and reasoning.
Regarding claim 16 Sun teaches The non-transitory machine-readable medium of claim 15, wherein the updated network visualization data is configured to facilitate generation of a visualization of a network topography.
Recites limitations similar to claim 14 and is rejected for similar rationale and reasoning.
Regarding claim 18 Sun teaches A method, comprising:
obtaining, by a processing system including a processor, configuration data, wherein the configuration data comprises first configuration data indicative of a first configuration of a first component of a communications network and second configuration data indicative of a second configuration of a second component of the communications network, wherein the first configuration data is in a first format associated with a first component manufacturer, wherein the second configuration data is in a second format associated with a second component manufacturer, wherein the first component manufacturer is a different manufacturer than the second component manufacturer, and wherein the first format is a different format than the second format;
generating, by the processing system, a first prompt configured for input to a large language model (LLM), wherein the generating of the first prompt is based at least in part upon the first configuration data;
facilitating, by the processing system, input of the first prompt to the LLM;
responsive to the input of the first prompt to the LLM, receiving, by the processing system, a first knowledge graph that was generated by the LLM;
responsive to the receiving of the first knowledge graph, generating, by the processing system, a second prompt configured for input to the LLM, wherein the generating of the second prompt is based at least in part upon the first knowledge graph;
facilitating, by the processing system, input of the second prompt to the LLM;
responsive to the input of the second prompt to the LLM, receiving, by the processing system, first network visualization data that was generated by the LLM; and
outputting, by the processing system, the first network visualization data.
Recites limitations similar to claims 1, 11, and specifically claim 13, and is rejected for similar rationale and reasoning,
Where the claims still recite generating an updated/second/new prompt based on knowledge graph information
Regarding claim 19 Sun teaches The method of claim 18, further comprising:
generating, by the processing system, a third prompt configured for input to the LLM, wherein the generating of the third prompt is based at least in part upon the second configuration data;
facilitating, by the processing system, input of the third prompt to the LLM;
responsive to the input of the third prompt to the LLM, receiving, by the processing system, a second knowledge graph that was generated by the LLM;
responsive to the receiving of the second knowledge graph, generating, by the processing system, a fourth prompt configured for input to the LLM, wherein the generating of the fourth prompt is based at least in part upon the second knowledge graph;
facilitating, by the processing system, input of the fourth prompt to the LLM;
responsive to the input of the fourth prompt to the LLM, receiving, by the processing system, second network visualization data that was generated by the LLM; and
outputting, by the processing system, the second network visualization data.
Recites limitations similar to claims 1, 11, and specifically claim 13, and is rejected for similar rationale and reasoning.
Where the claims still recite generating an updated/second/new prompt based on knowledge graph information
Claim Rejections - 35 USC § 103
6. 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.
7. Claims 7, 17 are rejected under 35 U.S.C. 103 as being unpatentable over Sun in view of Wang et al (2021/0173873).
Regarding claim 7 Sun teaches a knowledge graph, but does not specifically teach where Wang teaches The device of claim 1, wherein the updated knowledge graph is in a JavaScript Object Notation (JSON) LD file (0032 JSON LD).
It would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate a JSON LD file to still allow for the use of a knowledge graph in network management presenting a reasonable expectation of success. Sun already teaches the use of a knowledge graph, and one could implement a JSON LD file specifically to still allow for the use of knowledge graph (with context and meaning of the JSON LD) in AI network management as discussed in Sun.
Regarding claim 17 Sun teaches visualization of the network topography but does not specifically teach where Wang teaches The non-transitory machine-readable medium of claim 16, wherein the visualization of the network topography is a hierarchical visualization (fig 2; 0028; 0038).
It would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the hierarchical visualization for an improved rendering of the network components, further showing their connections and arrangement.
8. Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over Sun in view of Wang in further view of Donaldson (2010/0088273).
Regarding claim 20 Sun teaches The method of claim 19, further comprising:
storing, by the processing system, the first knowledge graph in a database (fig 3, 9; para 21: network knowledge graphs (network topology, feature information, etc.); 118; 120; databases: 123; 135);
storing, by the processing system, the second knowledge graph in the database (fig 3, 9; para 21: network knowledge graphs (network topology, feature information, etc.); 118; 120; databases: 123; 135);
storing, by the processing system, the first network visualization data in the database (fig 3; 9; para 21; 60 network knowledge graph 304; 120; databases: 123; 135); and
storing, by the processing system, the second network visualization data in the database (fig 3; 9; para 21; 60 network knowledge graph 304; 120; databases: 123; 135);
but does not specifically teach
wherein each of the first knowledge graph and the second knowledge graph is in a respective JavaScript Object Notation (JSON) LD file; and
wherein each of the first network visualization data and the second network visualization data is in a respective file that is in a JavaScript format.
Wang teaches
wherein each of the first knowledge graph and the second knowledge graph is in a respective JavaScript Object Notation (JSON) LD file (0032).
It would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate a JSON LD file to still allow for the use of a knowledge graph in network management presenting a reasonable expectation of success.
Sun and Wang do not teach, where Donaldson teaches wherein each of the first network visualization data and the second network visualization data is in a respective file that is in a JavaScript format (0035: network visualization may be implemented on a computer…using Javascript).
It would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate and present the visualization using javascript for improved and more dyanamic and interactive presentation of the network components.
Conclusion
9. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure: See PTO-892.
Yan et al (11,968,088)
Abstract: Example implementations include a method, apparatus, and computer-readable medium configured for generating a network configuration using a large language model (LLM). The apparatus receives, at an interface between a user and LLM, a natural language intent for a network configuration. The apparatus requests the large language model to update the network configuration to an updated network configuration that satisfies the natural language intent in a declarative network configuration language. The apparatus verifies whether the updated network configuration satisfies a configuration syntax of the declarative network configuration language to detect an error. The apparatus requests the large language model to update the updated network configuration to correct the error. The apparatus deploys the updated network configuration to a user network.
Karlberg et al (2024/0419835)
Abstract: Systems and methods are directed to incorporating large language model (LLM) prompts into graph queries using graph query language and executing these graph queries. The system receives a graph query that includes a LLM prompt in the graph query language. The LLM prompt comprises an input context and a query to be answered. Based on the graph query, the system traverses a knowledge graph to obtain context data associated with the input context. The context data may be constrained by access control policies of an enterprise providing the knowledge graph. A context table may be generated using the context data based on the input context indicated in the LLM prompt. The system then invokes an LLM to determine a result by applying the query of the LLM prompt to the context data obtained from the traversal of the knowledge graph. The result is then presented on a user interface of a client device.
Lee Altmann et al (2025/0315694)
Abstract: A computer implemented method for generating a Knowledge Graph (KG) representing relationships between a plurality of Machine Learning (ML) tasks relating to a computing infrastructure. The method comprises constructing a plurality of nodes representing the plurality of ML tasks. The method further comprises constructing a plurality of edges forming an edge graph and connecting the nodes among the plurality of nodes. The construction of the plurality of edge comprises: applying an encoder ML model to the plurality of nodes to generate an initial edge graph, applying a decoder ML model to the initial edge graph to output reconstructions of ML tasks, calculating a loss function, evaluating the determined loss function using a convergence criterion, and, on satisfaction of the convergence criterion, outputting a final edge graph.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHAUN A ROBERTS whose telephone number is (571)270-7541. The examiner can normally be reached Monday-Friday 9-5 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, Andrew Flanders can be reached on 571-272-7516. 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.
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 or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/SHAUN ROBERTS/Primary Examiner, Art Unit 2655
Prosecution Insights