system

Abstract

We provide the system. [Solution] A means of obtaining information from network devices, Means for preprocessing, shaping, and filtering the acquired information, A means of analyzing the network configuration using artificial intelligence with pre-processed information, A means for generating a network configuration diagram based on the analysis results, A means of generating configuration information for new equipment based on an existing configuration, A means for applying the generated configuration information to the device, A system that includes this.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional network design, advanced expertise is required, and the network design process often relies on external professional engineers. For this reason, there are problems that the design is costly and time-consuming, and it is not easy to change or expand an existing network environment. Furthermore, when the visualization of network configurations and setting information is insufficient, operation and management may become difficult, so there is a need for a method for efficiently and visually supporting network design.

Means for Solving the Problems

[0005] This invention provides a system that automatically acquires and analyzes configuration information from network devices, understands the network configuration, generates a configuration diagram, and rapidly generates configuration information for new devices using artificial intelligence. Furthermore, it provides the generated configuration diagram visually to the user, enabling the user to easily design, modify, and manage the network themselves. This allows for efficient network design without specialized knowledge, reduces the need for outsourcing, and saves both cost and time.

[0006] "Network equipment" refers to physical or virtual devices used for data communication, including those with functions such as routers, switches, and firewalls.

[0007] "Means of obtaining information" refers to processes and technologies used to obtain configuration information from network devices, including APIs, CLIs, and scripts.

[0008] "Preprocessing" refers to the formatting and filtering of raw data to make it easier to analyze.

[0009] "Artificial intelligence" refers to technology that replicates human cognitive functions on a computer, analyzing network configurations through pattern recognition, machine learning, and other methods.

[0010] A "network diagram" is a diagram that visually represents the connections and arrangement of devices within a network, making it easier to understand the overall structure.

[0011] "Configuration information for new devices" refers to settings to be applied to newly introduced devices in accordance with the existing network configuration, and includes IP addresses, routing, security policies, and more.

[0012] A "user interface" is an operating environment for exchanging information between a computer system and a user, enabling the display of visual configuration diagrams and the confirmation of setting information. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention is a system that automatically understands and visualizes the network configuration using the configuration information of network devices, and further generates configuration information for new devices. A specific embodiment of this system is shown below.

[0035] The server first obtains configuration information from network devices. In this process, the server accesses the devices using a CLI (Command Line Interface) to retrieve the configuration information. For devices where an API is available, the server can easily obtain configuration information via a RESTful API.

[0036] Next, the server preprocesses the acquired configuration information, formatting it into a form that is easy to analyze. This process eliminates redundant settings and duplicate data, converting the information into a consistent format. This preprocessing improves the accuracy of subsequent analysis.

[0037] Subsequently, the server uses artificial intelligence algorithms to analyze the network topology from the pre-processed data. The AI ​​identifies the role and connectivity of each device within the network and indicates the traffic flow and routing paths.

[0038] Based on the analysis results, the server automatically generates a network configuration diagram, which is then visually displayed through the user interface. This diagram is useful for users to quickly understand the overall network structure, identify problem areas, and verify the design.

[0039] Furthermore, the server generates configuration information for newly introduced equipment based on the network configuration. The AI ​​analyzes existing security policies and operational rules and proposes configurations that conform to them. For example, when a router is added, settings for optimal IP address assignment and routing table updates are automatically generated.

[0040] Users can review the generated configuration information, adjust it as needed, and then apply it to new devices. They can apply the settings themselves via a terminal or utilize the server's remote configuration application function. This system enables users to efficiently and accurately design and build networks without requiring specialized knowledge.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server accesses network devices to collect configuration information. When using the CLI, the server logs into each device and executes commands to dump the configuration information. If an API is provided, the server calls the API endpoint to retrieve the configuration information.

[0044] Step 2:

[0045] The server preprocesses the collected configuration information. Specifically, it converts the information into a format that is easy to analyze and removes unnecessary information and duplicate entries. By creating a consistent data structure, it prepares the data for more accurate subsequent processing.

[0046] Step 3:

[0047] The server inputs pre-processed data into an AI algorithm to analyze the network topology. The AI ​​identifies the role of each device, its position within the network, its connections, and the protocols it uses.

[0048] Step 4:

[0049] The server generates a network diagram based on the analysis results. To create a visual representation, it uses nodes and edges to depict the connections between devices and visualize the entire topology.

[0050] Step 5:

[0051] Users can view configuration diagrams generated via the server. Through the provided interface, users can use zoom and pan functions to examine details, diagnose problems, and plan changes.

[0052] Step 6:

[0053] The server generates configuration information for the new equipment. Based on existing network policies and operational requirements, the AI ​​automatically creates the necessary settings for the newly installed equipment and configures the appropriate settings.

[0054] Step 7:

[0055] The user reviews the provided configuration information and makes manual adjustments as needed. Then, via a terminal or server, they apply the generated configuration to the new device and complete the physical or virtual network expansion.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] In traditional network management, it was necessary to manage the configuration information of multiple network devices individually, requiring a great deal of time and expertise to understand the network configuration and add new devices. As a result, the overall operational efficiency of the network decreased, and it became difficult to apply appropriate security policies and operational rules.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes means for acquiring configuration information from network devices, means for preprocessing the acquired configuration information and converting it into a unified format, and means for analyzing the network topology using AI generated from the preprocessed configuration information. This enables automatic visualization of network configurations and rapid generation of configuration information for new devices.

[0061] "Network equipment" refers to hardware or software used to configure a network, and includes devices such as routers, switches, and firewalls.

[0062] "Configuration information" refers to the parameters and rules set on network devices, including IP addresses, routing policies, and security settings.

[0063] "Preprocessing" refers to the process of formatting collected configuration information into a form that is easy to analyze, and includes tasks such as standardizing data formats and removing redundant data.

[0064] "Generative AI" is a technology that uses machine learning and artificial intelligence algorithms to perform analysis and inference from specific data, and is used in applications such as network topology analysis.

[0065] "Network topology" refers to the structure and arrangement that shows how multiple devices within a network are connected and how they communicate with each other.

[0066] "Visualization" refers to the technique of displaying data and analysis results in a visually easy-to-understand format, primarily using diagrams and graphs.

[0067] "Configuration information generation" is the process of creating appropriate configuration information for new network devices based on existing configuration information and policies.

[0068] This invention is a system for streamlining network management, and has the function of automatically acquiring, analyzing, and visualizing configuration information of network devices. First, the server acquires configuration information from network devices. In doing so, the server uses CLI (command line interface) or RESTful API via SSH, a typical network protocol. The server collects necessary information from any network device, such as routers, switches, firewalls, etc.

[0069] Next, the server preprocesses the acquired information. This preprocessing includes tasks such as filtering out redundant data using a scripting language like Python and converting the data into a consistent JSON format. This ensures data consistency and facilitates analysis.

[0070] Subsequently, the server analyzes the network topology using a generated AI model. This model, based on machine learning algorithms, identifies the connections, roles, and traffic paths between devices within the network. Based on these analysis results, the server generates a network configuration diagram and visualizes it through the user interface. Through this diagram, users can easily grasp the overall picture of the network and potential problems.

[0071] Furthermore, the server generates configuration information for new devices based on the existing network configuration. For example, when adding a new router, the server uses a generation AI model to automatically generate optimal IP address assignments and routing settings. Users can then review this generated configuration information and apply it as needed. Application methods include manual configuration via a terminal, as well as automatic application using the server's remote configuration function.

[0072] As a concrete example, when a user enters a prompt such as, "Generate a network configuration diagram and suggest IP address settings for a newly added router," the system automatically performs analysis and generates configuration information. This system helps users effectively perform network management tasks even without specialized network management knowledge.

[0073] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0074] Step 1:

[0075] The server retrieves configuration information from network devices. Specifically, based on the network prompt entered by the user, the server accesses routers and switches using SSH and executes CLI commands. The input to this process is the connection information of the network devices, and the output is the configuration data for each device. The server saves this data locally.

[0076] Step 2:

[0077] The server preprocesses the acquired configuration information. The server executes a Python script to filter out redundant and duplicate data from the collected data. The input to this process is the configuration data acquired in step 1, and the output is clean data formatted into a consistent JSON format. This formatting improves the accuracy of data analysis.

[0078] Step 3:

[0079] The server uses pre-processed data to analyze the network topology using a generative AI model. At this stage, the server runs machine learning algorithms to identify the role, connectivity, and traffic flow of each network device. The input is the clean data formatted in step 2, and the output is the detailed analysis of the network topology.

[0080] Step 4:

[0081] The server generates a network configuration diagram based on the analysis results. The diagram is drawn using Python based on the analysis results obtained in the previous step. The input is the analysis results from step 3, and the output is a visually displayable network configuration diagram. The server sends this diagram to the user terminal and displays it on the screen.

[0082] Step 5:

[0083] The user enters prompts to generate configuration information for a new device. Based on the user's input, the server re-utilizes its generation AI model to generate configuration information that takes into account the existing network policy and topology. The input consists of the user's prompts and current network data, and the output is configuration information applicable to the new device.

[0084] Step 6:

[0085] The user reviews the generated configuration information and adjusts it as needed. After adjustment, it can be manually applied to the new device via the terminal if necessary, or automatically applied using the server's remote configuration function. The input is the output configuration information from step 5, and the output is the operational status of the new device after the settings have been applied.

[0086] (Application Example 1)

[0087] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0088] In network operation and management, environments with multiple devices present challenges in terms of managing configuration information, generating network diagrams, and applying settings to new devices, all of which are time-consuming and complex. Furthermore, there is a need for a system that allows network administrators to easily understand the current network configuration and quickly and efficiently apply settings when new devices are added. In particular, the lack of real-time network status monitoring and automated configuration suggestions is a significant problem.

[0089] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0090] In this invention, the server includes means for acquiring information from network devices, means for preprocessing, shaping, and filtering the acquired information, means for analyzing the network configuration using artificial intelligence with the preprocessed information, and means for providing a user interface for displaying the analysis results on the user's mobile terminal, making the visualized configuration diagram operable on the mobile terminal. This enables visualization of the network configuration and efficient information management, allowing administrators to easily grasp the network status and quickly apply settings to new devices.

[0091] "Network equipment" refers to devices used in data centers and other network environments to mediate communications and perform data routing and management.

[0092] "Means for acquiring information" refers to methods or devices for collecting information such as settings and topology from network devices.

[0093] "Preprocessing" is the process of shaping acquired information, removing redundant or duplicate data, and converting it into a format that is easy to analyze.

[0094] "Artificial intelligence" is a program or technology that performs data analysis and prediction based on collected information, enabling advanced decision-making automatically.

[0095] "Means for analyzing network configuration" refers to methods or devices used to identify the interrelationships and data flows of devices within a network.

[0096] A "network configuration diagram" is a diagram that visually shows the placement and connection status of each device within a network.

[0097] "User interface" refers to the screens and means of operation that users use to interact with a system and obtain information.

[0098] A "mobile device" is a small electronic device that a user can carry around and that can run applications on.

[0099] "Visualization" is the process of transforming complex data into a form that is easy for humans to understand and present.

[0100] "Configuration information for new devices" refers to information about the configurations and parameters that should be applied to devices newly added to the network.

[0101] A "configuration suggestion module" is a program or system component designed to suggest optimal settings for new equipment.

[0102] The system realizing this invention includes a program for efficiently managing multiple network devices. The server is responsible for acquiring information from the network devices, collecting data via a RESTful API or CLI. This information is preprocessed to eliminate redundancy and duplication, and to make it easier to analyze. The software used here utilizes Node.js as the data processing backend.

[0103] The server uses artificial intelligence to analyze the network topology based on pre-processed data. This process utilizes AI frameworks such as TENSORFLOW®. The resulting network configuration is then formatted for visual confirmation on the user's mobile device. The smartphone application, built using Flutter®, provides an interactive network map.

[0104] Users can manipulate and verify network configuration diagrams on their terminals and generate configuration information for adding new devices in real time. A configuration suggestion module works to present the user with the optimal settings. Furthermore, the generated configuration information can be easily applied to network devices after confirmation by the user. This entire process is provided as a modularized program, with various optimizations implemented to enhance the user experience.

[0105] A concrete example is a scenario where a user uses a smartphone to check the status of routing switches within a data center. Based on the analysis results, the optimal IP address assignment for the new router is automatically suggested. An example of a prompt message is as follows:

[0106] "Obtain the latest network equipment information, analyze and visualize the topology within the data center, and then generate a proposed IP address assignment for the new router. Finally, verify this configuration and present it in a final, applicable format."

[0107] In this way, users can perform quick and accurate network management without requiring any special technical knowledge.

[0108] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0109] Step 1:

[0110] The server accesses network devices and retrieves configuration information. It uses network device access information as input and collects data via CLI or RESTful API. The output is the collected raw configuration data. Specifically, the server sends commands to each network device and logs the returned data.

[0111] Step 2:

[0112] The server preprocesses the acquired data. The input is the raw configuration data obtained in step 1, which is then formatted and filtered. Redundant information and duplicate data are removed, transforming it into a clean and consistent data structure. The output is clean data in a parseable format. Specifically, it uses regular expressions to extract and organize the necessary information and saves it to the database.

[0113] Step 3:

[0114] The server uses pre-processed data to analyze the network configuration using artificial intelligence. The input is the clean data formatted in step 2. Using a generative AI model such as TensorFlow, it analyzes the network topology and the roles of devices, and identifies traffic patterns. The output is the analysis result data regarding the network topology. Specifically, the AI ​​model performs data analysis and feeds the results back into the database.

[0115] Step 4:

[0116] The server generates a network diagram based on the analysis results and transmits it to the terminal. The input is the analysis result data from step 3. The output is a visualized network diagram. Specifically, the terminal uses Flutter to draw an interactive diagram based on the data received from the server.

[0117] Step 5:

[0118] The user views the configuration diagram on the terminal and generates configuration information corresponding to the addition of new equipment. The inputs are the network configuration diagram and the requirements of the new equipment. The configuration suggestion module generates appropriate configuration information in real time and presents it to the user. The output is the new configuration information confirmed by the user. In terms of specific operation, the user modifies and confirms the presented configuration suggestion by operating the terminal.

[0119] Step 6:

[0120] The server receives the configuration information confirmed by the user and applies it to the new device. The input is the configuration information that the user finalized in step 5. The output is the updated network configuration. Specifically, the server sends the new settings to the network device and notifies the user that the application was successful.

[0121] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0122] This invention combines a system that analyzes network configuration based on configuration information obtained from network devices and generates configuration information for new devices as needed with an emotion engine that recognizes user emotions. A specific embodiment is shown below.

[0123] The server first obtains configuration information from network devices. It accesses the devices using the CLI and extracts the configuration information, or it collects network information directly using the API.

[0124] Next, the server preprocesses the acquired information, performing filtering and formatting, and then performs network configuration analysis using an artificial intelligence algorithm. This analysis generates a topology diagram, which is then provided to the user as a visually displayed diagram.

[0125] Furthermore, this system is equipped with an emotion engine that analyzes the user's emotions from their voice and facial expressions while using the system. The emotion engine determines in real time whether the user is experiencing stress or frustration due to network conditions or configuration changes, and adjusts the interface display and suggestions accordingly.

[0126] For example, if the emotion engine detects that a user is confused while reviewing a network diagram, the server will suggest clearer explanations or additional navigation to support the user's understanding. Similarly, if a user is feeling anxious when generating configuration information for new equipment, the emotion engine will detect this and the server will provide detailed instructions or alternative solutions.

[0127] Through the terminal, users can confidently apply and manage network settings using an emotion-recognition-adjusted interface. This provides a better user experience and improves the efficiency and effectiveness of network management.

[0128] The following describes the processing flow.

[0129] Step 1:

[0130] The server accesses network devices to collect configuration information. When using the CLI, the server executes automated scripts to dump configuration information from each device. If an API is available, the server uses the API endpoint to efficiently retrieve information.

[0131] Step 2:

[0132] The server preprocesses the collected configuration information. It organizes and formats the information, removes duplicates and unnecessary data, and converts it into a format that is easy to analyze.

[0133] Step 3:

[0134] The server inputs pre-processed information into an AI algorithm to analyze the network configuration. The AI ​​identifies the function and connectivity of each device and generates data to visualize the network topology.

[0135] Step 4:

[0136] The server generates a network configuration diagram based on the analysis results. This diagram is displayed to the user as a graphical interface that intuitively shows the overall structure of the network.

[0137] Step 5:

[0138] Through the terminal, the user checks the configuration diagram and understands the current network status. The emotion engine analyzes the user's voice and facial expressions at this time and evaluates their emotional state in real time.

[0139] Step 6:

[0140] The emotion engine suggests support for actions based on the user's emotional state. For example, if the user is feeling stressed, the server will provide additional explanations or hints to help the user understand.

[0141] Step 7:

[0142] The server generates configuration information for the new device. During this process, the emotion engine provides detailed explanations of the configuration and suggests adjustments to ensure user confidence.

[0143] Step 8:

[0144] The user reviews the configuration information generated through the device and makes adjustments if necessary. If the user is satisfied with the settings, the server automatically applies the settings to the new device. Alternatively, the user can apply the settings manually.

[0145] This process allows users to manage the network with confidence, and the system responds efficiently and flexibly.

[0146] (Example 2)

[0147] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0148] In today's complex network environments, manual network configuration and setup changes by administrators require considerable effort, time, and can be emotionally stressful. Furthermore, the installation of new equipment and the generation of configuration information can lead to misconfigurations and management errors. Additionally, users often find it difficult to visually grasp and understand the network configuration, potentially hindering system operation. To address these challenges, an efficient and user-friendly network management system is essential.

[0149] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0150] In this invention, the server includes means for acquiring information from network devices, means for preprocessing, shaping, and filtering the information, and means for analyzing the network configuration using a machine learning algorithm. This enables automated analysis and visual display of the network configuration, as well as adjustment of the interface to suit the user's emotions.

[0151] "Network devices" are hardware devices used for network data communication, and include routers, switches, firewalls, and other similar devices.

[0152] "Means of acquiring information" refers to methods and technologies used to collect configuration data and operational data from network devices, and this is done through CLI or API.

[0153] "Preprocessing" is the process of organizing acquired information and formatting it into a form that is easy to analyze, and includes deleting unnecessary data and transforming data.

[0154] A "machine learning algorithm" refers to a mathematical model or statistical method used to process large amounts of data and discover useful patterns or structures.

[0155] "Means for analyzing network configuration" refers to technologies and methods for analyzing network structure and connection relationships and deriving them into a visually displayable format.

[0156] "Means for generating configuration information for new devices" refers to technologies and methods that automatically create the configuration data necessary to efficiently configure newly introduced network devices.

[0157] "Means for analyzing emotional states" refers to technologies and methods for detecting a user's emotional state based on their voice and facial expressions, and adjusting the system's response accordingly.

[0158] "Means for adjusting interface display" refers to technologies and methods that flexibly change the content of displayed screens and information in order to support user understanding.

[0159] This invention is a system for streamlining network management and reducing user stress. The system is implemented through interaction between servers, terminals, and users. Specific embodiments are described below.

[0160] Acquisition and processing of network data

[0161] First, the server accesses the network device and retrieves network configuration information using the CLI (Command Line Interface) or API (Application Programming Interface). This information includes important data related to the network configuration, such as IP addresses, routing tables, and interface settings. The retrieved data is filtered and formatted to preprocess it into a format suitable for analysis.

[0162] Network Configuration Analysis

[0163] The server uses machine learning algorithms to analyze the pre-processed information. This analysis converts the network topology into an easily understandable format, allowing it to be visually displayed as a topology diagram. By viewing this diagram, users can intuitively grasp the state of the network.

[0164] Sentiment analysis and user interface adjustments

[0165] In addition, the system is equipped with an emotion analysis engine that analyzes the user's emotional state from their voice and facial expressions. Based on this information, the server adjusts the interface display in real time and provides additional information and guidance to help the user understand.

[0166] Specific example

[0167] For example, if a user is planning to expand their office network and needs to add new equipment, the invention can help. When the user prompts, "How do I install a new switch?", the server analyzes the entire network and suggests the optimal connection port and setup procedure. If the emotion engine determines that the user's facial expression indicates confusion, it provides additional visual guides and detailed instructions to support the user.

[0168] This invention aims to reduce the stress users experience when performing complex network management and to support smooth operation.

[0169] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0170] Step 1:

[0171] The server retrieves information from network devices. Specifically, it accesses the devices using CLI or API and collects data such as IP addresses, routing tables, and interface settings. In this case, the input is raw configuration data from the network devices, and the output is a set of data acquired for analysis.

[0172] Step 2:

[0173] The server preprocesses the acquired data. Specifically, it filters out redundant information, extracts the necessary data, and formats it. This process cleanses and reformats the data, outputting it in a format suitable for analysis. The input here is raw configuration data, and the output is formatted, analyzable data.

[0174] Step 3:

[0175] The server uses machine learning algorithms to analyze the formatted data. This allows it to understand the network topology and generate a visualized topology diagram. The input is pre-processed data, and the output is structured model data representing the topology. Specifically, it can generate topology diagrams and visually display the network connectivity status.

[0176] Step 4:

[0177] The server uses an emotion analysis engine to analyze the user's voice and video. It analyzes the emotional state and adjusts the interface display as needed. The input for this step is real-time voice and video data from the user, and the output is their emotional state. Based on this information, the server dynamically provides additional support information and navigation.

[0178] Step 5:

[0179] Through the terminal, the user utilizes information and interfaces provided by the server to configure the new device. The input is the recommended configuration information received from the server, and the output is the actual device configuration applied. The user can then apply the configuration by following specific operating procedures, thereby optimizing the network.

[0180] (Application Example 2)

[0181] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0182] In managing information networks, users often face complex configurations and setting changes, which can cause stress and anxiety. There is also the risk of system failure due to incorrect decisions during configuration changes. Traditional systems have failed to alleviate user psychological burden and provide adequate support. Therefore, there is a need to provide an information network management interface that takes user emotions into consideration.

[0183] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0184] In this invention, the server includes means for acquiring information from network devices, means for preprocessing, shaping, and filtering the acquired information, and means for analyzing the configuration of the information network using artificial intelligence based on the preprocessed information. This makes it possible to reduce the psychological burden on users regarding information network management and mitigate the risk of system failures due to incorrect judgments by recognizing the user's emotions and dynamically adjusting the interface.

[0185] "Network equipment" is a general term for devices that manage the connection of information networks and perform data communication.

[0186] "Information preprocessing" is the process of shaping acquired raw data into an analyzable format and removing noise as needed.

[0187] Artificial intelligence is a technology in which computer systems mimic some aspects of human intelligence, enabling data analysis and pattern recognition.

[0188] An "information network configuration diagram" is a diagram that visually represents the elements of an information network and their connection relationships.

[0189] "Configuration information for new devices" refers to information that defines the specific configuration and operating conditions to be applied to devices newly added to the information network.

[0190] "Means of recognizing emotions" refer to technologies and devices that detect a user's emotional state and process information based on that state.

[0191] A "browsing device" is a device that provides an interface for visually displaying information and allowing users to confirm its content.

[0192] To realize this invention, collaboration between the server, terminal, and user is crucial. The server first acquires information from network devices, then formats and filters that information. This involves collecting data using a RESTful API and performing preprocessing. Next, using the preprocessed information, the server analyzes the network configuration using artificial intelligence algorithms and generates a configuration diagram. The server sends this configuration diagram to the terminal, allowing the user to visually confirm it.

[0193] Furthermore, the server utilizes an emotion recognition engine to recognize the user's emotions. This engine uses software such as OpenCV and DeepFace to analyze emotional data from the user's facial expressions and voice in real time and reflect it in the interface. As a result, the user can receive information tailored to their state, allowing for smoother operation.

[0194] For example, if a user is feeling anxious about a change in the information network, and the emotion recognition engine detects stress, the system can then provide more detailed instructions or alternatives. This improves the accuracy of information network management and reduces the occurrence of errors. An example of a prompt would be, "Explain the expected impact of this change in the information network configuration."

[0195] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0196] Step 1:

[0197] The server retrieves configuration information from network devices. It uses a RESTful API as input, receiving raw data from the devices. The output is the unprocessed configuration information stored on the server. This process involves establishing a secure connection and sending appropriate requests to the devices to collect data.

[0198] Step 2:

[0199] The raw data acquired by the server is preprocessed, formatted, and filtered. The input is the unprocessed configuration information obtained in step 1. The output is a formatted dataset containing only the necessary information. Specifically, the data format is normalized, and unnecessary noise and duplicate data are removed.

[0200] Step 3:

[0201] The server uses pre-processed data to analyze the network configuration using artificial intelligence algorithms. The input is a formatted dataset, and the output is data for a network configuration diagram. In this process, a generative AI model is used to identify connection relationships and components within the data and create a visualized topology.

[0202] Step 4:

[0203] The server generates an information network configuration diagram and sends it to the terminal, making it visually accessible to the user. The input is the data of the configuration diagram generated in step 3, and the output is the visualized configuration diagram displayed on the user's terminal. In this step, information converted to a format suitable for the user's terminal is seamlessly transferred.

[0204] Step 5:

[0205] The server recognizes the user's emotions and dynamically adjusts the interface through an emotion recognition engine. The input is the user's facial expressions and voice data, and the output is an interface adjusted according to those emotions. This process uses OpenCV and DeepFace to analyze emotion data in real time and automatically optimize parts of the UI.

[0206] Step 6:

[0207] The user performs tasks based on the information provided. They receive information at each step and manually or automatically confirm changes to the network settings. Inputs are suggestions and instructions from the server, and outputs are the application of settings to network devices. Specific actions include making actual configuration changes according to navigation guidelines.

[0208] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0209] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0210] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0211] [Second Embodiment]

[0212] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0213] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0214] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0215] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0216] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0217] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0218] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0219] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0220] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0221] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0222] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0223] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0224] This invention is a system that automatically understands and visualizes the network configuration using the configuration information of network devices, and further generates configuration information for new devices. A specific embodiment of this system is shown below.

[0225] The server first obtains configuration information from network devices. In this process, the server accesses the devices using a CLI (Command Line Interface) to retrieve the configuration information. For devices where an API is available, the server can easily obtain configuration information via a RESTful API.

[0226] Next, the server preprocesses the acquired configuration information, formatting it into a form that is easy to analyze. This process eliminates redundant settings and duplicate data, converting the information into a consistent format. This preprocessing improves the accuracy of subsequent analysis.

[0227] Subsequently, the server uses artificial intelligence algorithms to analyze the network topology from the pre-processed data. The AI ​​identifies the role and connectivity of each device within the network and indicates the traffic flow and routing paths.

[0228] Based on the analysis results, the server automatically generates a network configuration diagram, which is then visually displayed through the user interface. This diagram is useful for users to quickly understand the overall network structure, identify problem areas, and verify the design.

[0229] Furthermore, the server generates configuration information for newly introduced equipment based on the network configuration. The AI ​​analyzes existing security policies and operational rules and proposes configurations that conform to them. For example, when a router is added, settings for optimal IP address assignment and routing table updates are automatically generated.

[0230] Users can review the generated configuration information, adjust it as needed, and then apply it to new devices. They can apply the settings themselves via a terminal or utilize the server's remote configuration application function. This system enables users to efficiently and accurately design and build networks without requiring specialized knowledge.

[0231] The following describes the processing flow.

[0232] Step 1:

[0233] The server accesses network devices to collect configuration information. When using the CLI, the server logs into each device and executes commands to dump the configuration information. If an API is provided, the server calls the API endpoint to retrieve the configuration information.

[0234] Step 2:

[0235] The server preprocesses the collected configuration information. Specifically, it converts the information into a format that is easy to analyze and removes unnecessary information and duplicate entries. By creating a consistent data structure, it prepares the data for more accurate subsequent processing.

[0236] Step 3:

[0237] The server inputs pre-processed data into an AI algorithm to analyze the network topology. The AI ​​identifies the role of each device, its position within the network, its connections, and the protocols it uses.

[0238] Step 4:

[0239] The server generates a network diagram based on the analysis results. To create a visual representation, it uses nodes and edges to depict the connections between devices and visualize the entire topology.

[0240] Step 5:

[0241] Users can view configuration diagrams generated via the server. Through the provided interface, users can use zoom and pan functions to examine details, diagnose problems, and plan changes.

[0242] Step 6:

[0243] The server generates configuration information for the new equipment. Based on existing network policies and operational requirements, the AI ​​automatically creates the necessary settings for the newly installed equipment and configures the appropriate settings.

[0244] Step 7:

[0245] The user reviews the provided configuration information and makes manual adjustments as needed. Then, via a terminal or server, they apply the generated configuration to the new device and complete the physical or virtual network expansion.

[0246] (Example 1)

[0247] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0248] In traditional network management, it was necessary to manage the configuration information of multiple network devices individually, requiring a great deal of time and expertise to understand the network configuration and add new devices. As a result, the overall operational efficiency of the network decreased, and it became difficult to apply appropriate security policies and operational rules.

[0249] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0250] In this invention, the server includes means for acquiring configuration information from network devices, means for preprocessing the acquired configuration information and converting it into a unified format, and means for analyzing the network topology using AI generated from the preprocessed configuration information. This enables automatic visualization of network configurations and rapid generation of configuration information for new devices.

[0251] "Network equipment" refers to hardware or software used to configure a network, and includes devices such as routers, switches, and firewalls.

[0252] "Configuration information" refers to the parameters and rules set on network devices, including IP addresses, routing policies, and security settings.

[0253] "Preprocessing" refers to the process of formatting collected configuration information into a form that is easy to analyze, and includes tasks such as standardizing data formats and removing redundant data.

[0254] "Generative AI" is a technology that uses machine learning and artificial intelligence algorithms to perform analysis and inference from specific data, and is used in applications such as network topology analysis.

[0255] "Network topology" refers to the structure and arrangement that shows how multiple devices within a network are connected and how they communicate with each other.

[0256] "Visualization" refers to the technique of displaying data and analysis results in a visually easy-to-understand format, primarily using diagrams and graphs.

[0257] "Configuration information generation" is the process of creating appropriate configuration information for new network devices based on existing configuration information and policies.

[0258] This invention is a system for streamlining network management, and has the function of automatically acquiring, analyzing, and visualizing configuration information of network devices. First, the server acquires configuration information from network devices. In doing so, the server uses CLI (command line interface) or RESTful API via SSH, a typical network protocol. The server collects necessary information from any network device, such as routers, switches, firewalls, etc.

[0259] Next, the server preprocesses the acquired information. This preprocessing includes tasks such as filtering out redundant data using a scripting language like Python and converting the data into a consistent JSON format. This ensures data consistency and facilitates analysis.

[0260] Subsequently, the server analyzes the network topology using a generated AI model. This model, based on machine learning algorithms, identifies the connections, roles, and traffic paths between devices within the network. Based on these analysis results, the server generates a network configuration diagram and visualizes it through the user interface. Through this diagram, users can easily grasp the overall picture of the network and potential problems.

[0261] Furthermore, the server generates configuration information for new devices based on the existing network configuration. For example, when adding a new router, the server uses a generation AI model to automatically generate optimal IP address assignments and routing settings. Users can then review this generated configuration information and apply it as needed. Application methods include manual configuration via a terminal, as well as automatic application using the server's remote configuration function.

[0262] As a concrete example, when a user enters a prompt such as, "Generate a network configuration diagram and suggest IP address settings for a newly added router," the system automatically performs analysis and generates configuration information. This system helps users effectively perform network management tasks even without specialized network management knowledge.

[0263] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0264] Step 1:

[0265] The server retrieves configuration information from network devices. Specifically, based on the network prompt entered by the user, the server accesses routers and switches using SSH and executes CLI commands. The input to this process is the connection information of the network devices, and the output is the configuration data for each device. The server saves this data locally.

[0266] Step 2:

[0267] The server preprocesses the acquired configuration information. The server executes a Python script to filter out redundant and duplicate data from the collected data. The input to this process is the configuration data acquired in step 1, and the output is clean data formatted into a consistent JSON format. This formatting improves the accuracy of data analysis.

[0268] Step 3:

[0269] The server uses pre-processed data to analyze the network topology using a generative AI model. At this stage, the server runs machine learning algorithms to identify the role, connectivity, and traffic flow of each network device. The input is the clean data formatted in step 2, and the output is the detailed analysis of the network topology.

[0270] Step 4:

[0271] The server generates a network configuration diagram based on the analysis results. The diagram is drawn using Python based on the analysis results obtained in the previous step. The input is the analysis results from step 3, and the output is a visually displayable network configuration diagram. The server sends this diagram to the user terminal and displays it on the screen.

[0272] Step 5:

[0273] The user enters prompts to generate configuration information for a new device. Based on the user's input, the server re-utilizes its generation AI model to generate configuration information that takes into account the existing network policy and topology. The input consists of the user's prompts and current network data, and the output is configuration information applicable to the new device.

[0274] Step 6:

[0275] The user reviews the generated configuration information and adjusts it as needed. After adjustment, it can be manually applied to the new device via the terminal if necessary, or automatically applied using the server's remote configuration function. The input is the output configuration information from step 5, and the output is the operational status of the new device after the settings have been applied.

[0276] (Application Example 1)

[0277] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0278] In network operation and management, environments with multiple devices present challenges in terms of managing configuration information, generating network diagrams, and applying settings to new devices, all of which are time-consuming and complex. Furthermore, there is a need for a system that allows network administrators to easily understand the current network configuration and quickly and efficiently apply settings when new devices are added. In particular, the lack of real-time network status monitoring and automated configuration suggestions is a significant problem.

[0279] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0280] In this invention, the server includes means for acquiring information from network devices, means for preprocessing the acquired information for formatting and filtering, means for analyzing the network configuration by artificial intelligence using the preprocessed information, providing a user interface for displaying the analysis result on the user's mobile terminal, and means for making the visualized configuration diagram operable on the mobile terminal. Thereby, visualization of the network configuration and efficient information management become possible, and the administrator can easily grasp the state of the network and quickly apply settings to new devices.

[0281] A "network device" is a device for mediating communication and performing data routing and management in a data center or other network environment.

[0282] The "means for acquiring information" is a method or device for collecting information such as settings and topology from network devices.

[0283] "Preprocessing" is a process of formatting the acquired information, deleting redundant and duplicate data, and converting it into a form easy to analyze.

[0284] "Artificial intelligence" is a program or technology that performs data analysis and prediction based on the collected information and enables automatic high-level judgment.

[0285] The "means for analyzing the network configuration" is a method or device used to identify the interrelationships of devices and data flow within the network.

[0286] A "network configuration diagram" is a diagram visually showing the arrangement and connection status of each device within the network.

[0287] A "user interface" refers to a screen or operating means for a user to interact with the system and obtain information.

[0288] A "mobile device" is a small electronic device that a user can carry around and that can run applications on.

[0289] "Visualization" is the process of transforming complex data into a form that is easy for humans to understand and present.

[0290] "Configuration information for new devices" refers to information about the configurations and parameters that should be applied to devices newly added to the network.

[0291] A "configuration suggestion module" is a program or system component designed to suggest optimal settings for new equipment.

[0292] The system realizing this invention includes a program for efficiently managing multiple network devices. The server is responsible for acquiring information from the network devices, collecting data via a RESTful API or CLI. This information is preprocessed to eliminate redundancy and duplication, and to make it easier to analyze. The software used here utilizes Node.js as the data processing backend.

[0293] The server uses artificial intelligence to analyze the network topology based on pre-processed data. This process utilizes AI frameworks such as TensorFlow. The resulting network configuration is then formatted so that users can visually view it on their mobile devices. The smartphone application, built using Flutter, provides an interactive network map.

[0294] Users can manipulate and verify network configuration diagrams on their terminals and generate configuration information for adding new devices in real time. A configuration suggestion module works to present the user with the optimal settings. Furthermore, the generated configuration information can be easily applied to network devices after confirmation by the user. This entire process is provided as a modularized program, with various optimizations implemented to enhance the user experience.

[0295] A concrete example is a scenario where a user uses a smartphone to check the status of routing switches within a data center. Based on the analysis results, the optimal IP address assignment for the new router is automatically suggested. An example of a prompt message is as follows:

[0296] "Obtain the latest network equipment information, analyze and visualize the topology within the data center, and then generate a proposed IP address assignment for the new router. Finally, verify this configuration and present it in a final, applicable format."

[0297] In this way, users can perform quick and accurate network management without requiring any special technical knowledge.

[0298] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0299] Step 1:

[0300] The server accesses network devices and retrieves configuration information. It uses network device access information as input and collects data via CLI or RESTful API. The output is the collected raw configuration data. Specifically, the server sends commands to each network device and logs the returned data.

[0301] Step 2:

[0302] The server preprocesses the acquired data. The input is the original configuration data obtained in Step 1, which is formatted and filtered. Redundant information and duplicate data are removed, and it is converted into a clean and consistent data structure. The output is clean data in an analyzable format. As specific operations, the necessary information is extracted and organized using regular expressions and saved in the database.

[0303] Step 3:

[0304] The server uses the preprocessed data to analyze the network configuration using artificial intelligence. The input is the clean data formatted in Step 2. Using a generative AI model such as TensorFlow, the network topology and the roles of devices are analyzed, and traffic patterns are identified. The output is analysis result data regarding the network topology. As specific operations, data analysis is performed using the AI model, and the results are fed back to the database.

[0305] Step 4:

[0306] Based on the analysis results, the server generates a network configuration diagram and transmits it to the terminal. The input is the analysis result data of Step 3. The output is a visualized network configuration diagram. As specific operations, an interactive configuration diagram is drawn using Flutter based on the data received by the terminal from the server.

[0307] Step 5:

[0308] The user checks the configuration diagram on the terminal and generates setting information corresponding to the addition of new devices. The input is the network configuration diagram and the requirements of the new devices. The setting proposal module generates appropriate setting information in real time and presents it to the user. The output is the new setting information confirmed by the user. As specific operations, the user operates the terminal to modify and confirm the presented setting proposals.

[0309] Step 6:

[0310] The server receives the configuration information confirmed by the user and applies it to the new device. The input is the configuration information that the user finalized in step 5. The output is the updated network configuration. Specifically, the server sends the new settings to the network device and notifies the user that the application was successful.

[0311] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0312] This invention combines a system that analyzes network configuration based on configuration information obtained from network devices and generates configuration information for new devices as needed with an emotion engine that recognizes user emotions. A specific embodiment is shown below.

[0313] The server first obtains configuration information from network devices. It accesses the devices using the CLI and extracts the configuration information, or it collects network information directly using the API.

[0314] Next, the server preprocesses the acquired information, performing filtering and formatting, and then performs network configuration analysis using an artificial intelligence algorithm. This analysis generates a topology diagram, which is then provided to the user as a visually displayed diagram.

[0315] Furthermore, this system is equipped with an emotion engine that analyzes the user's emotions from their voice and facial expressions while using the system. The emotion engine determines in real time whether the user is experiencing stress or frustration due to network conditions or configuration changes, and adjusts the interface display and suggestions accordingly.

[0316] For example, if the emotion engine detects that a user is confused while reviewing a network diagram, the server will suggest clearer explanations or additional navigation to support the user's understanding. Similarly, if a user is feeling anxious when generating configuration information for new equipment, the emotion engine will detect this and the server will provide detailed instructions or alternative solutions.

[0317] Through the terminal, users can confidently apply and manage network settings using an emotion-recognition-adjusted interface. This provides a better user experience and improves the efficiency and effectiveness of network management.

[0318] The following describes the processing flow.

[0319] Step 1:

[0320] The server accesses network devices to collect configuration information. When using the CLI, the server executes automated scripts to dump configuration information from each device. If an API is available, the server uses the API endpoint to efficiently retrieve information.

[0321] Step 2:

[0322] The server preprocesses the collected configuration information. It organizes and formats the information, removes duplicates and unnecessary data, and converts it into a format that is easy to analyze.

[0323] Step 3:

[0324] The server inputs pre-processed information into an AI algorithm to analyze the network configuration. The AI ​​identifies the function and connectivity of each device and generates data to visualize the network topology.

[0325] Step 4:

[0326] The server generates a network configuration diagram based on the analysis results. This diagram is displayed to the user as a graphical interface that intuitively shows the overall structure of the network.

[0327] Step 5:

[0328] Through the terminal, the user checks the configuration diagram and understands the current network status. The emotion engine analyzes the user's voice and facial expressions at this time and evaluates their emotional state in real time.

[0329] Step 6:

[0330] The emotion engine suggests support for actions based on the user's emotional state. For example, if the user is feeling stressed, the server will provide additional explanations or hints to help the user understand.

[0331] Step 7:

[0332] The server generates configuration information for the new device. During this process, the emotion engine provides detailed explanations of the configuration and suggests adjustments to ensure user confidence.

[0333] Step 8:

[0334] The user reviews the configuration information generated through the device and makes adjustments if necessary. If the user is satisfied with the settings, the server automatically applies the settings to the new device. Alternatively, the user can apply the settings manually.

[0335] This process allows users to manage the network with confidence, and the system responds efficiently and flexibly.

[0336] (Example 2)

[0337] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0338] In today's complex network environments, manual network configuration and setup changes by administrators require considerable effort, time, and can be emotionally stressful. Furthermore, the installation of new equipment and the generation of configuration information can lead to misconfigurations and management errors. Additionally, users often find it difficult to visually grasp and understand the network configuration, potentially hindering system operation. To address these challenges, an efficient and user-friendly network management system is essential.

[0339] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0340] In this invention, the server includes means for acquiring information from network devices, means for preprocessing, shaping, and filtering the information, and means for analyzing the network configuration using a machine learning algorithm. This enables automated analysis and visual display of the network configuration, as well as adjustment of the interface to suit the user's emotions.

[0341] "Network devices" are hardware devices used for network data communication, and include routers, switches, firewalls, and other similar devices.

[0342] "Means of acquiring information" refers to methods and technologies used to collect configuration data and operational data from network devices, and this is done through CLI or API.

[0343] "Preprocessing" is the process of organizing acquired information and formatting it into a form that is easy to analyze, and includes deleting unnecessary data and transforming data.

[0344] A "machine learning algorithm" refers to a mathematical model or statistical method used to process large amounts of data and discover useful patterns or structures.

[0345] "Means for analyzing network configuration" refers to technologies and methods for analyzing network structure and connection relationships and deriving them into a visually displayable format.

[0346] "Means for generating configuration information for new devices" refers to technologies and methods that automatically create the configuration data necessary to efficiently configure newly introduced network devices.

[0347] "Means for analyzing emotional states" refers to technologies and methods for detecting a user's emotional state based on their voice and facial expressions, and adjusting the system's response accordingly.

[0348] "Means for adjusting interface display" refers to technologies and methods that flexibly change the content of displayed screens and information in order to support user understanding.

[0349] This invention is a system for streamlining network management and reducing user stress. The system is implemented through interaction between servers, terminals, and users. Specific embodiments are described below.

[0350] Acquisition and processing of network data

[0351] First, the server accesses the network device and retrieves network configuration information using the CLI (Command Line Interface) or API (Application Programming Interface). This information includes important data related to the network configuration, such as IP addresses, routing tables, and interface settings. The retrieved data is filtered and formatted to preprocess it into a format suitable for analysis.

[0352] Network Configuration Analysis

[0353] The server uses machine learning algorithms to analyze the pre-processed information. This analysis converts the network topology into an easily understandable format, allowing it to be visually displayed as a topology diagram. By viewing this diagram, users can intuitively grasp the state of the network.

[0354] Sentiment analysis and user interface adjustments

[0355] In addition, the system is equipped with an emotion analysis engine that analyzes the user's emotional state from their voice and facial expressions. Based on this information, the server adjusts the interface display in real time and provides additional information and guidance to help the user understand.

[0356] Specific example

[0357] For example, if a user is planning to expand their office network and needs to add new equipment, the invention can help. When the user prompts, "How do I install a new switch?", the server analyzes the entire network and suggests the optimal connection port and setup procedure. If the emotion engine determines that the user's facial expression indicates confusion, it provides additional visual guides and detailed instructions to support the user.

[0358] This invention aims to reduce the stress users experience when performing complex network management and to support smooth operation.

[0359] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0360] Step 1:

[0361] The server retrieves information from network devices. Specifically, it accesses the devices using CLI or API and collects data such as IP addresses, routing tables, and interface settings. In this case, the input is raw configuration data from the network devices, and the output is a set of data acquired for analysis.

[0362] Step 2:

[0363] The server preprocesses the acquired data. Specifically, it filters out redundant information, extracts the necessary data, and formats it. This process cleanses and reformats the data, outputting it in a format suitable for analysis. The input here is raw configuration data, and the output is formatted, analyzable data.

[0364] Step 3:

[0365] The server uses machine learning algorithms to analyze the formatted data. This allows it to understand the network topology and generate a visualized topology diagram. The input is pre-processed data, and the output is structured model data representing the topology. Specifically, it can generate topology diagrams and visually display the network connectivity status.

[0366] Step 4:

[0367] The server uses an emotion analysis engine to analyze the user's voice and video. It analyzes the emotional state and adjusts the interface display as needed. The input for this step is real-time voice and video data from the user, and the output is their emotional state. Based on this information, the server dynamically provides additional support information and navigation.

[0368] Step 5:

[0369] Through the terminal, the user utilizes information and interfaces provided by the server to configure the new device. The input is the recommended configuration information received from the server, and the output is the actual device configuration applied. The user can then apply the configuration by following specific operating procedures, thereby optimizing the network.

[0370] (Application Example 2)

[0371] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0372] In managing information networks, users often face complex configurations and setting changes, which can cause stress and anxiety. There is also the risk of system failure due to incorrect decisions during configuration changes. Traditional systems have failed to alleviate user psychological burden and provide adequate support. Therefore, there is a need to provide an information network management interface that takes user emotions into consideration.

[0373] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0374] In this invention, the server includes means for acquiring information from network devices, means for preprocessing, shaping, and filtering the acquired information, and means for analyzing the configuration of the information network using artificial intelligence based on the preprocessed information. This makes it possible to reduce the psychological burden on users regarding information network management and mitigate the risk of system failures due to incorrect judgments by recognizing the user's emotions and dynamically adjusting the interface.

[0375] "Network equipment" is a general term for devices that manage the connection of information networks and perform data communication.

[0376] "Information preprocessing" is the process of shaping acquired raw data into an analyzable format and removing noise as needed.

[0377] Artificial intelligence is a technology in which computer systems mimic some aspects of human intelligence, enabling data analysis and pattern recognition.

[0378] An "information network configuration diagram" is a diagram that visually represents the elements of an information network and their connection relationships.

[0379] "Configuration information for new devices" refers to information that defines the specific configuration and operating conditions to be applied to devices newly added to the information network.

[0380] "Means of recognizing emotions" refer to technologies and devices that detect a user's emotional state and process information based on that state.

[0381] A "browsing device" is a device that provides an interface for visually displaying information and allowing users to confirm its content.

[0382] To realize this invention, collaboration between the server, terminal, and user is crucial. The server first acquires information from network devices, then formats and filters that information. This involves collecting data using a RESTful API and performing preprocessing. Next, using the preprocessed information, the server analyzes the network configuration using artificial intelligence algorithms and generates a configuration diagram. The server sends this configuration diagram to the terminal, allowing the user to visually confirm it.

[0383] Furthermore, the server utilizes an emotion recognition engine to recognize the user's emotions. This engine uses software such as OpenCV and DeepFace to analyze emotional data from the user's facial expressions and voice in real time and reflect it in the interface. As a result, the user can receive information tailored to their state, allowing for smoother operation.

[0384] For example, if a user is feeling anxious about a change in the information network, and the emotion recognition engine detects stress, the system can then provide more detailed instructions or alternatives. This improves the accuracy of information network management and reduces the occurrence of errors. An example of a prompt would be, "Explain the expected impact of this change in the information network configuration."

[0385] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0386] Step 1:

[0387] The server retrieves configuration information from network devices. It uses a RESTful API as input, receiving raw data from the devices. The output is the unprocessed configuration information stored on the server. This process involves establishing a secure connection and sending appropriate requests to the devices to collect data.

[0388] Step 2:

[0389] The raw data acquired by the server is preprocessed, formatted, and filtered. The input is the unprocessed configuration information obtained in step 1. The output is a formatted dataset containing only the necessary information. Specifically, the data format is normalized, and unnecessary noise and duplicate data are removed.

[0390] Step 3:

[0391] The server uses pre-processed data to analyze the network configuration using artificial intelligence algorithms. The input is a formatted dataset, and the output is data for a network configuration diagram. In this process, a generative AI model is used to identify connection relationships and components within the data and create a visualized topology.

[0392] Step 4:

[0393] The server generates an information network configuration diagram and sends it to the terminal, making it visually accessible to the user. The input is the data of the configuration diagram generated in step 3, and the output is the visualized configuration diagram displayed on the user's terminal. In this step, information converted to a format suitable for the user's terminal is seamlessly transferred.

[0394] Step 5:

[0395] The server recognizes the user's emotions and dynamically adjusts the interface through an emotion recognition engine. The input is the user's facial expressions and voice data, and the output is an interface adjusted according to those emotions. This process uses OpenCV and DeepFace to analyze emotion data in real time and automatically optimize parts of the UI.

[0396] Step 6:

[0397] The user performs tasks based on the information provided. They receive information at each step and manually or automatically confirm changes to the network settings. Inputs are suggestions and instructions from the server, and outputs are the application of settings to network devices. Specific actions include making actual configuration changes according to navigation guidelines.

[0398] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0399] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0400] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0401] [Third Embodiment]

[0402] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0403] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0404] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0405] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0406] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0407] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0408] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0409] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0410] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0411] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0412] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0413] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0414] This invention is a system that automatically understands and visualizes the network configuration using the configuration information of network devices, and further generates configuration information for new devices. A specific embodiment of this system is shown below.

[0415] The server first obtains configuration information from network devices. In this process, the server accesses the devices using a CLI (Command Line Interface) to retrieve the configuration information. For devices where an API is available, the server can easily obtain configuration information via a RESTful API.

[0416] Next, the server preprocesses the acquired configuration information, formatting it into a form that is easy to analyze. This process eliminates redundant settings and duplicate data, converting the information into a consistent format. This preprocessing improves the accuracy of subsequent analysis.

[0417] Subsequently, the server uses artificial intelligence algorithms to analyze the network topology from the pre-processed data. The AI ​​identifies the role and connectivity of each device within the network and indicates the traffic flow and routing paths.

[0418] Based on the analysis results, the server automatically generates a network configuration diagram, which is then visually displayed through the user interface. This diagram is useful for users to quickly understand the overall network structure, identify problem areas, and verify the design.

[0419] Furthermore, the server generates configuration information for newly introduced equipment based on the network configuration. The AI ​​analyzes existing security policies and operational rules and proposes configurations that conform to them. For example, when a router is added, settings for optimal IP address assignment and routing table updates are automatically generated.

[0420] Users can review the generated configuration information, adjust it as needed, and then apply it to new devices. They can apply the settings themselves via a terminal or utilize the server's remote configuration application function. This system enables users to efficiently and accurately design and build networks without requiring specialized knowledge.

[0421] The following describes the processing flow.

[0422] Step 1:

[0423] The server accesses network devices to collect configuration information. When using the CLI, the server logs into each device and executes commands to dump the configuration information. If an API is provided, the server calls the API endpoint to retrieve the configuration information.

[0424] Step 2:

[0425] The server preprocesses the collected configuration information. Specifically, it converts the information into a format that is easy to analyze and removes unnecessary information and duplicate entries. By creating a consistent data structure, it prepares the data for more accurate subsequent processing.

[0426] Step 3:

[0427] The server inputs pre-processed data into an AI algorithm to analyze the network topology. The AI ​​identifies the role of each device, its position within the network, its connections, and the protocols it uses.

[0428] Step 4:

[0429] The server generates a network diagram based on the analysis results. To create a visual representation, it uses nodes and edges to depict the connections between devices and visualize the entire topology.

[0430] Step 5:

[0431] Users can view configuration diagrams generated via the server. Through the provided interface, users can use zoom and pan functions to examine details, diagnose problems, and plan changes.

[0432] Step 6:

[0433] The server generates configuration information for the new equipment. Based on existing network policies and operational requirements, the AI ​​automatically creates the necessary settings for the newly installed equipment and configures the appropriate settings.

[0434] Step 7:

[0435] The user reviews the provided configuration information and makes manual adjustments as needed. Then, via a terminal or server, they apply the generated configuration to the new device and complete the physical or virtual network expansion.

[0436] (Example 1)

[0437] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0438] In traditional network management, it was necessary to manage the configuration information of multiple network devices individually, requiring a great deal of time and expertise to understand the network configuration and add new devices. As a result, the overall operational efficiency of the network decreased, and it became difficult to apply appropriate security policies and operational rules.

[0439] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0440] In this invention, the server includes means for acquiring configuration information from network devices, means for preprocessing the acquired configuration information and converting it into a unified format, and means for analyzing the network topology using AI generated from the preprocessed configuration information. This enables automatic visualization of network configurations and rapid generation of configuration information for new devices.

[0441] "Network equipment" refers to hardware or software used to configure a network, and includes devices such as routers, switches, and firewalls.

[0442] "Configuration information" refers to the parameters and rules set on network devices, including IP addresses, routing policies, and security settings.

[0443] "Preprocessing" refers to the process of formatting collected configuration information into a form that is easy to analyze, and includes tasks such as standardizing data formats and removing redundant data.

[0444] "Generative AI" is a technology that uses machine learning and artificial intelligence algorithms to perform analysis and inference from specific data, and is used in applications such as network topology analysis.

[0445] "Network topology" refers to the structure and arrangement that shows how multiple devices within a network are connected and how they communicate with each other.

[0446] "Visualization" refers to the technique of displaying data and analysis results in a visually easy-to-understand format, primarily using diagrams and graphs.

[0447] "Configuration information generation" is the process of creating appropriate configuration information for new network devices based on existing configuration information and policies.

[0448] This invention is a system for streamlining network management, and has the function of automatically acquiring, analyzing, and visualizing configuration information of network devices. First, the server acquires configuration information from network devices. In doing so, the server uses CLI (command line interface) or RESTful API via SSH, a typical network protocol. The server collects necessary information from any network device, such as routers, switches, firewalls, etc.

[0449] Next, the server preprocesses the acquired information. This preprocessing includes tasks such as filtering out redundant data using a scripting language like Python and converting the data into a consistent JSON format. This ensures data consistency and facilitates analysis.

[0450] Subsequently, the server analyzes the network topology using a generated AI model. This model, based on machine learning algorithms, identifies the connections, roles, and traffic paths between devices within the network. Based on these analysis results, the server generates a network configuration diagram and visualizes it through the user interface. Through this diagram, users can easily grasp the overall picture of the network and potential problems.

[0451] Furthermore, the server generates configuration information for new devices based on the existing network configuration. For example, when adding a new router, the server uses a generation AI model to automatically generate optimal IP address assignments and routing settings. Users can then review this generated configuration information and apply it as needed. Application methods include manual configuration via a terminal, as well as automatic application using the server's remote configuration function.

[0452] As a concrete example, when a user enters a prompt such as, "Generate a network configuration diagram and suggest IP address settings for a newly added router," the system automatically performs analysis and generates configuration information. This system helps users effectively perform network management tasks even without specialized network management knowledge.

[0453] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0454] Step 1:

[0455] The server retrieves configuration information from network devices. Specifically, based on the network prompt entered by the user, the server accesses routers and switches using SSH and executes CLI commands. The input to this process is the connection information of the network devices, and the output is the configuration data for each device. The server saves this data locally.

[0456] Step 2:

[0457] The server preprocesses the acquired configuration information. The server executes a Python script to filter out redundant and duplicate data from the collected data. The input to this process is the configuration data acquired in step 1, and the output is clean data formatted into a consistent JSON format. This formatting improves the accuracy of data analysis.

[0458] Step 3:

[0459] The server uses pre-processed data to analyze the network topology using a generative AI model. At this stage, the server runs machine learning algorithms to identify the role, connectivity, and traffic flow of each network device. The input is the clean data formatted in step 2, and the output is the detailed analysis of the network topology.

[0460] Step 4:

[0461] The server generates a network configuration diagram based on the analysis results. The diagram is drawn using Python based on the analysis results obtained in the previous step. The input is the analysis results from step 3, and the output is a visually displayable network configuration diagram. The server sends this diagram to the user terminal and displays it on the screen.

[0462] Step 5:

[0463] The user enters prompts to generate configuration information for a new device. Based on the user's input, the server re-utilizes its generation AI model to generate configuration information that takes into account the existing network policy and topology. The input consists of the user's prompts and current network data, and the output is configuration information applicable to the new device.

[0464] Step 6:

[0465] The user reviews the generated configuration information and adjusts it as needed. After adjustment, it can be manually applied to the new device via the terminal if necessary, or automatically applied using the server's remote configuration function. The input is the output configuration information from step 5, and the output is the operational status of the new device after the settings have been applied.

[0466] (Application Example 1)

[0467] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0468] In network operation and management, environments with multiple devices present challenges in terms of managing configuration information, generating network diagrams, and applying settings to new devices, all of which are time-consuming and complex. Furthermore, there is a need for a system that allows network administrators to easily understand the current network configuration and quickly and efficiently apply settings when new devices are added. In particular, the lack of real-time network status monitoring and automated configuration suggestions is a significant problem.

[0469] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0470] In this invention, the server includes means for acquiring information from network devices, means for preprocessing, shaping, and filtering the acquired information, means for analyzing the network configuration using artificial intelligence with the preprocessed information, and means for providing a user interface for displaying the analysis results on the user's mobile terminal, making the visualized configuration diagram operable on the mobile terminal. This enables visualization of the network configuration and efficient information management, allowing administrators to easily grasp the network status and quickly apply settings to new devices.

[0471] "Network equipment" refers to devices used in data centers and other network environments to mediate communications and perform data routing and management.

[0472] "Means for acquiring information" refers to methods or devices for collecting information such as settings and topology from network devices.

[0473] "Preprocessing" is the process of shaping acquired information, removing redundant or duplicate data, and converting it into a format that is easy to analyze.

[0474] "Artificial intelligence" is a program or technology that performs data analysis and prediction based on collected information, enabling advanced decision-making automatically.

[0475] "Means for analyzing network configuration" refers to methods or devices used to identify the interrelationships and data flows of devices within a network.

[0476] A "network configuration diagram" is a diagram that visually shows the placement and connection status of each device within a network.

[0477] "User interface" refers to the screens and means of operation that users use to interact with a system and obtain information.

[0478] A "mobile device" is a small electronic device that a user can carry around and that can run applications on.

[0479] "Visualization" is the process of transforming complex data into a form that is easy for humans to understand and present.

[0480] "Configuration information for new devices" refers to information about the configurations and parameters that should be applied to devices newly added to the network.

[0481] A "configuration suggestion module" is a program or system component designed to suggest optimal settings for new equipment.

[0482] The system realizing this invention includes a program for efficiently managing multiple network devices. The server is responsible for acquiring information from the network devices, collecting data via a RESTful API or CLI. This information is preprocessed to eliminate redundancy and duplication, and to make it easier to analyze. The software used here utilizes Node.js as the data processing backend.

[0483] The server uses artificial intelligence to analyze the network topology based on pre-processed data. This process utilizes AI frameworks such as TensorFlow. The resulting network configuration is then formatted so that users can visually view it on their mobile devices. The smartphone application, built using Flutter, provides an interactive network map.

[0484] Users can manipulate and verify network configuration diagrams on their terminals and generate configuration information for adding new devices in real time. A configuration suggestion module works to present the user with the optimal settings. Furthermore, the generated configuration information can be easily applied to network devices after confirmation by the user. This entire process is provided as a modularized program, with various optimizations implemented to enhance the user experience.

[0485] A concrete example is a scenario where a user uses a smartphone to check the status of routing switches within a data center. Based on the analysis results, the optimal IP address assignment for the new router is automatically suggested. An example of a prompt message is as follows:

[0486] "Obtain the latest network equipment information, analyze and visualize the topology within the data center, and then generate a proposed IP address assignment for the new router. Finally, verify this configuration and present it in a final, applicable format."

[0487] In this way, users can perform quick and accurate network management without requiring any special technical knowledge.

[0488] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0489] Step 1:

[0490] The server accesses network devices and retrieves configuration information. It uses network device access information as input and collects data via CLI or RESTful API. The output is the collected raw configuration data. Specifically, the server sends commands to each network device and logs the returned data.

[0491] Step 2:

[0492] The server preprocesses the acquired data. The input is the raw configuration data obtained in step 1, which is then formatted and filtered. Redundant information and duplicate data are removed, transforming it into a clean and consistent data structure. The output is clean data in a parseable format. Specifically, it uses regular expressions to extract and organize the necessary information and saves it to the database.

[0493] Step 3:

[0494] The server uses pre-processed data to analyze the network configuration using artificial intelligence. The input is the clean data formatted in step 2. Using a generative AI model such as TensorFlow, it analyzes the network topology and the roles of devices, and identifies traffic patterns. The output is the analysis result data regarding the network topology. Specifically, the AI ​​model performs data analysis and feeds the results back into the database.

[0495] Step 4:

[0496] The server generates a network diagram based on the analysis results and transmits it to the terminal. The input is the analysis result data from step 3. The output is a visualized network diagram. Specifically, the terminal uses Flutter to draw an interactive diagram based on the data received from the server.

[0497] Step 5:

[0498] The user views the configuration diagram on the terminal and generates configuration information corresponding to the addition of new equipment. The inputs are the network configuration diagram and the requirements of the new equipment. The configuration suggestion module generates appropriate configuration information in real time and presents it to the user. The output is the new configuration information confirmed by the user. In terms of specific operation, the user modifies and confirms the presented configuration suggestion by operating the terminal.

[0499] Step 6:

[0500] The server receives the configuration information confirmed by the user and applies it to the new device. The input is the configuration information that the user finalized in step 5. The output is the updated network configuration. Specifically, the server sends the new settings to the network device and notifies the user that the application was successful.

[0501] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0502] This invention combines a system that analyzes network configuration based on configuration information obtained from network devices and generates configuration information for new devices as needed with an emotion engine that recognizes user emotions. A specific embodiment is shown below.

[0503] The server first obtains configuration information from network devices. It accesses the devices using the CLI and extracts the configuration information, or it collects network information directly using the API.

[0504] Next, the server preprocesses the acquired information, performing filtering and formatting, and then performs network configuration analysis using an artificial intelligence algorithm. This analysis generates a topology diagram, which is then provided to the user as a visually displayed diagram.

[0505] Furthermore, this system is equipped with an emotion engine that analyzes the user's emotions from their voice and facial expressions while using the system. The emotion engine determines in real time whether the user is experiencing stress or frustration due to network conditions or configuration changes, and adjusts the interface display and suggestions accordingly.

[0506] For example, if the emotion engine detects that a user is confused while reviewing a network diagram, the server will suggest clearer explanations or additional navigation to support the user's understanding. Similarly, if a user is feeling anxious when generating configuration information for new equipment, the emotion engine will detect this and the server will provide detailed instructions or alternative solutions.

[0507] Through the terminal, users can confidently apply and manage network settings using an emotion-recognition-adjusted interface. This provides a better user experience and improves the efficiency and effectiveness of network management.

[0508] The following describes the processing flow.

[0509] Step 1:

[0510] The server accesses network devices to collect configuration information. When using the CLI, the server executes automated scripts to dump configuration information from each device. If an API is available, the server uses the API endpoint to efficiently retrieve information.

[0511] Step 2:

[0512] The server preprocesses the collected configuration information. It organizes and formats the information, removes duplicates and unnecessary data, and converts it into a format that is easy to analyze.

[0513] Step 3:

[0514] The server inputs pre-processed information into an AI algorithm to analyze the network configuration. The AI ​​identifies the function and connectivity of each device and generates data to visualize the network topology.

[0515] Step 4:

[0516] The server generates a network configuration diagram based on the analysis results. This diagram is displayed to the user as a graphical interface that intuitively shows the overall structure of the network.

[0517] Step 5:

[0518] Through the terminal, the user checks the configuration diagram and understands the current network status. The emotion engine analyzes the user's voice and facial expressions at this time and evaluates their emotional state in real time.

[0519] Step 6:

[0520] The emotion engine suggests support for actions based on the user's emotional state. For example, if the user is feeling stressed, the server will provide additional explanations or hints to help the user understand.

[0521] Step 7:

[0522] The server generates configuration information for the new device. During this process, the emotion engine provides detailed explanations of the configuration and suggests adjustments to ensure user confidence.

[0523] Step 8:

[0524] The user reviews the configuration information generated through the device and makes adjustments if necessary. If the user is satisfied with the settings, the server automatically applies the settings to the new device. Alternatively, the user can apply the settings manually.

[0525] This process allows users to manage the network with confidence, and the system responds efficiently and flexibly.

[0526] (Example 2)

[0527] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0528] In today's complex network environments, manual network configuration and setup changes by administrators require considerable effort, time, and can be emotionally stressful. Furthermore, the installation of new equipment and the generation of configuration information can lead to misconfigurations and management errors. Additionally, users often find it difficult to visually grasp and understand the network configuration, potentially hindering system operation. To address these challenges, an efficient and user-friendly network management system is essential.

[0529] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0530] In this invention, the server includes means for acquiring information from network devices, means for preprocessing, shaping, and filtering the information, and means for analyzing the network configuration using a machine learning algorithm. This enables automated analysis and visual display of the network configuration, as well as adjustment of the interface to suit the user's emotions.

[0531] "Network devices" are hardware devices used for network data communication, and include routers, switches, firewalls, and other similar devices.

[0532] "Means of acquiring information" refers to methods and technologies used to collect configuration data and operational data from network devices, and this is done through CLI or API.

[0533] "Preprocessing" is the process of organizing acquired information and formatting it into a form that is easy to analyze, and includes deleting unnecessary data and transforming data.

[0534] A "machine learning algorithm" refers to a mathematical model or statistical method used to process large amounts of data and discover useful patterns or structures.

[0535] "Means for analyzing network configuration" refers to technologies and methods for analyzing network structure and connection relationships and deriving them into a visually displayable format.

[0536] "Means for generating configuration information for new devices" refers to technologies and methods that automatically create the configuration data necessary to efficiently configure newly introduced network devices.

[0537] "Means for analyzing emotional states" refers to technologies and methods for detecting a user's emotional state based on their voice and facial expressions, and adjusting the system's response accordingly.

[0538] "Means for adjusting interface display" refers to technologies and methods that flexibly change the content of displayed screens and information in order to support user understanding.

[0539] This invention is a system for streamlining network management and reducing user stress. The system is implemented through interaction between servers, terminals, and users. Specific embodiments are described below.

[0540] Acquisition and processing of network data

[0541] First, the server accesses the network device and retrieves network configuration information using the CLI (Command Line Interface) or API (Application Programming Interface). This information includes important data related to the network configuration, such as IP addresses, routing tables, and interface settings. The retrieved data is filtered and formatted to preprocess it into a format suitable for analysis.

[0542] Network Configuration Analysis

[0543] The server uses machine learning algorithms to analyze the pre-processed information. This analysis converts the network topology into an easily understandable format, allowing it to be visually displayed as a topology diagram. By viewing this diagram, users can intuitively grasp the state of the network.

[0544] Sentiment analysis and user interface adjustments

[0545] In addition, the system is equipped with an emotion analysis engine that analyzes the user's emotional state from their voice and facial expressions. Based on this information, the server adjusts the interface display in real time and provides additional information and guidance to help the user understand.

[0546] Specific example

[0547] For example, if a user is planning to expand their office network and needs to add new equipment, the invention can help. When the user prompts, "How do I install a new switch?", the server analyzes the entire network and suggests the optimal connection port and setup procedure. If the emotion engine determines that the user's facial expression indicates confusion, it provides additional visual guides and detailed instructions to support the user.

[0548] This invention aims to reduce the stress users experience when performing complex network management and to support smooth operation.

[0549] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0550] Step 1:

[0551] The server retrieves information from network devices. Specifically, it accesses the devices using CLI or API and collects data such as IP addresses, routing tables, and interface settings. In this case, the input is raw configuration data from the network devices, and the output is a set of data acquired for analysis.

[0552] Step 2:

[0553] The server preprocesses the acquired data. Specifically, it filters out redundant information, extracts the necessary data, and formats it. This process cleanses and reformats the data, outputting it in a format suitable for analysis. The input here is raw configuration data, and the output is formatted, analyzable data.

[0554] Step 3:

[0555] The server uses machine learning algorithms to analyze the formatted data. This allows it to understand the network topology and generate a visualized topology diagram. The input is pre-processed data, and the output is structured model data representing the topology. Specifically, it can generate topology diagrams and visually display the network connectivity status.

[0556] Step 4:

[0557] The server uses an emotion analysis engine to analyze the user's voice and video. It analyzes the emotional state and adjusts the interface display as needed. The input for this step is real-time voice and video data from the user, and the output is their emotional state. Based on this information, the server dynamically provides additional support information and navigation.

[0558] Step 5:

[0559] Through the terminal, the user utilizes information and interfaces provided by the server to configure the new device. The input is the recommended configuration information received from the server, and the output is the actual device configuration applied. The user can then apply the configuration by following specific operating procedures, thereby optimizing the network.

[0560] (Application Example 2)

[0561] Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0562] In managing information networks, users often face complex configurations and setting changes, which can cause stress and anxiety. There is also the risk of system failure due to incorrect decisions during configuration changes. Traditional systems have failed to alleviate user psychological burden and provide adequate support. Therefore, there is a need to provide an information network management interface that takes user emotions into consideration.

[0563] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0564] In this invention, the server includes means for acquiring information from network devices, means for preprocessing, shaping, and filtering the acquired information, and means for analyzing the configuration of the information network using artificial intelligence based on the preprocessed information. This makes it possible to reduce the psychological burden on users regarding information network management and mitigate the risk of system failures due to incorrect judgments by recognizing the user's emotions and dynamically adjusting the interface.

[0565] "Network equipment" is a general term for devices that manage the connection of information networks and perform data communication.

[0566] "Information preprocessing" is the process of shaping acquired raw data into an analyzable format and removing noise as needed.

[0567] Artificial intelligence is a technology in which computer systems mimic some aspects of human intelligence, enabling data analysis and pattern recognition.

[0568] An "information network configuration diagram" is a diagram that visually represents the elements of an information network and their connection relationships.

[0569] "Configuration information for new devices" refers to information that defines the specific configuration and operating conditions to be applied to devices newly added to the information network.

[0570] "Means of recognizing emotions" refer to technologies and devices that detect a user's emotional state and process information based on that state.

[0571] A "browsing device" is a device that provides an interface for visually displaying information and allowing users to confirm its content.

[0572] To realize this invention, collaboration between the server, terminal, and user is crucial. The server first acquires information from network devices, then formats and filters that information. This involves collecting data using a RESTful API and performing preprocessing. Next, using the preprocessed information, the server analyzes the network configuration using artificial intelligence algorithms and generates a configuration diagram. The server sends this configuration diagram to the terminal, allowing the user to visually confirm it.

[0573] Furthermore, the server utilizes an emotion recognition engine to recognize the user's emotions. This engine uses software such as OpenCV and DeepFace to analyze emotional data from the user's facial expressions and voice in real time and reflect it in the interface. As a result, the user can receive information tailored to their state, allowing for smoother operation.

[0574] For example, if a user is feeling anxious about a change in the information network, and the emotion recognition engine detects stress, the system can then provide more detailed instructions or alternatives. This improves the accuracy of information network management and reduces the occurrence of errors. An example of a prompt would be, "Explain the expected impact of this change in the information network configuration."

[0575] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0576] Step 1:

[0577] The server retrieves configuration information from network devices. It uses a RESTful API as input, receiving raw data from the devices. The output is the unprocessed configuration information stored on the server. This process involves establishing a secure connection and sending appropriate requests to the devices to collect data.

[0578] Step 2:

[0579] The raw data acquired by the server is preprocessed, formatted, and filtered. The input is the unprocessed configuration information obtained in step 1. The output is a formatted dataset containing only the necessary information. Specifically, the data format is normalized, and unnecessary noise and duplicate data are removed.

[0580] Step 3:

[0581] The server uses pre-processed data to analyze the network configuration using artificial intelligence algorithms. The input is a formatted dataset, and the output is data for a network configuration diagram. In this process, a generative AI model is used to identify connection relationships and components within the data and create a visualized topology.

[0582] Step 4:

[0583] The server generates an information network configuration diagram and sends it to the terminal, making it visually accessible to the user. The input is the data of the configuration diagram generated in step 3, and the output is the visualized configuration diagram displayed on the user's terminal. In this step, information converted to a format suitable for the user's terminal is seamlessly transferred.

[0584] Step 5:

[0585] The server recognizes the user's emotions and dynamically adjusts the interface through an emotion recognition engine. The input is the user's facial expressions and voice data, and the output is an interface adjusted according to those emotions. This process uses OpenCV and DeepFace to analyze emotion data in real time and automatically optimize parts of the UI.

[0586] Step 6:

[0587] The user performs tasks based on the information provided. They receive information at each step and manually or automatically confirm changes to the network settings. Inputs are suggestions and instructions from the server, and outputs are the application of settings to network devices. Specific actions include making actual configuration changes according to navigation guidelines.

[0588] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0589] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0590] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0591] [Fourth Embodiment]

[0592] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0593] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0594] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0595] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0596] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0597] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0598] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0599] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0600] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0601] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0602] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0603] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0604] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0605] This invention is a system that automatically understands and visualizes the network configuration using the configuration information of network devices, and further generates configuration information for new devices. A specific embodiment of this system is shown below.

[0606] The server first obtains configuration information from network devices. In this process, the server accesses the devices using a CLI (Command Line Interface) to retrieve the configuration information. For devices where an API is available, the server can easily obtain configuration information via a RESTful API.

[0607] Next, the server preprocesses the acquired configuration information, formatting it into a form that is easy to analyze. This process eliminates redundant settings and duplicate data, converting the information into a consistent format. This preprocessing improves the accuracy of subsequent analysis.

[0608] Subsequently, the server uses artificial intelligence algorithms to analyze the network topology from the pre-processed data. The AI ​​identifies the role and connectivity of each device within the network and indicates the traffic flow and routing paths.

[0609] Based on the analysis results, the server automatically generates a network configuration diagram, which is then visually displayed through the user interface. This diagram is useful for users to quickly understand the overall network structure, identify problem areas, and verify the design.

[0610] Furthermore, the server generates configuration information for newly introduced equipment based on the network configuration. The AI ​​analyzes existing security policies and operational rules and proposes configurations that conform to them. For example, when a router is added, settings for optimal IP address assignment and routing table updates are automatically generated.

[0611] Users can review the generated configuration information, adjust it as needed, and then apply it to new devices. They can apply the settings themselves via a terminal or utilize the server's remote configuration application function. This system enables users to efficiently and accurately design and build networks without requiring specialized knowledge.

[0612] The following describes the processing flow.

[0613] Step 1:

[0614] The server accesses network devices to collect configuration information. When using the CLI, the server logs into each device and executes commands to dump the configuration information. If an API is provided, the server calls the API endpoint to retrieve the configuration information.

[0615] Step 2:

[0616] The server preprocesses the collected configuration information. Specifically, it converts the information into a format that is easy to analyze and removes unnecessary information and duplicate entries. By creating a consistent data structure, it prepares the data for more accurate subsequent processing.

[0617] Step 3:

[0618] The server inputs pre-processed data into an AI algorithm to analyze the network topology. The AI ​​identifies the role of each device, its position within the network, its connections, and the protocols it uses.

[0619] Step 4:

[0620] The server generates a network diagram based on the analysis results. To create a visual representation, it uses nodes and edges to depict the connections between devices and visualize the entire topology.

[0621] Step 5:

[0622] Users can view configuration diagrams generated via the server. Through the provided interface, users can use zoom and pan functions to examine details, diagnose problems, and plan changes.

[0623] Step 6:

[0624] The server generates configuration information for the new equipment. Based on existing network policies and operational requirements, the AI ​​automatically creates the necessary settings for the newly installed equipment and configures the appropriate settings.

[0625] Step 7:

[0626] The user reviews the provided configuration information and makes manual adjustments as needed. Then, via a terminal or server, they apply the generated configuration to the new device and complete the physical or virtual network expansion.

[0627] (Example 1)

[0628] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0629] In traditional network management, it was necessary to manage the configuration information of multiple network devices individually, requiring a great deal of time and expertise to understand the network configuration and add new devices. As a result, the overall operational efficiency of the network decreased, and it became difficult to apply appropriate security policies and operational rules.

[0630] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0631] In this invention, the server includes means for acquiring configuration information from network devices, means for preprocessing the acquired configuration information and converting it into a unified format, and means for analyzing the network topology using AI generated from the preprocessed configuration information. This enables automatic visualization of network configurations and rapid generation of configuration information for new devices.

[0632] "Network equipment" refers to hardware or software used to configure a network, and includes devices such as routers, switches, and firewalls.

[0633] "Configuration information" refers to the parameters and rules set on network devices, including IP addresses, routing policies, and security settings.

[0634] "Preprocessing" refers to the process of formatting collected configuration information into a form that is easy to analyze, and includes tasks such as standardizing data formats and removing redundant data.

[0635] "Generative AI" is a technology that uses machine learning and artificial intelligence algorithms to perform analysis and inference from specific data, and is used in applications such as network topology analysis.

[0636] "Network topology" refers to the structure and arrangement that shows how multiple devices within a network are connected and how they communicate with each other.

[0637] "Visualization" refers to the technique of displaying data and analysis results in a visually easy-to-understand format, primarily using diagrams and graphs.

[0638] "Configuration information generation" is the process of creating appropriate configuration information for new network devices based on existing configuration information and policies.

[0639] This invention is a system for streamlining network management, and has the function of automatically acquiring, analyzing, and visualizing configuration information of network devices. First, the server acquires configuration information from network devices. In doing so, the server uses CLI (command line interface) or RESTful API via SSH, a typical network protocol. The server collects necessary information from any network device, such as routers, switches, firewalls, etc.

[0640] Next, the server preprocesses the acquired information. This preprocessing includes tasks such as filtering out redundant data using a scripting language like Python and converting the data into a consistent JSON format. This ensures data consistency and facilitates analysis.

[0641] Subsequently, the server analyzes the network topology using a generated AI model. This model, based on machine learning algorithms, identifies the connections, roles, and traffic paths between devices within the network. Based on these analysis results, the server generates a network configuration diagram and visualizes it through the user interface. Through this diagram, users can easily grasp the overall picture of the network and potential problems.

[0642] Furthermore, the server generates configuration information for new devices based on the existing network configuration. For example, when adding a new router, the server uses a generation AI model to automatically generate optimal IP address assignments and routing settings. Users can then review this generated configuration information and apply it as needed. Application methods include manual configuration via a terminal, as well as automatic application using the server's remote configuration function.

[0643] As a concrete example, when a user enters a prompt such as, "Generate a network configuration diagram and suggest IP address settings for a newly added router," the system automatically performs analysis and generates configuration information. This system helps users effectively perform network management tasks even without specialized network management knowledge.

[0644] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0645] Step 1:

[0646] The server retrieves configuration information from network devices. Specifically, based on the network prompt entered by the user, the server accesses routers and switches using SSH and executes CLI commands. The input to this process is the connection information of the network devices, and the output is the configuration data for each device. The server saves this data locally.

[0647] Step 2:

[0648] The server preprocesses the acquired configuration information. The server executes a Python script to filter out redundant and duplicate data from the collected data. The input to this process is the configuration data acquired in step 1, and the output is clean data formatted into a consistent JSON format. This formatting improves the accuracy of data analysis.

[0649] Step 3:

[0650] The server uses pre-processed data to analyze the network topology using a generative AI model. At this stage, the server runs machine learning algorithms to identify the role, connectivity, and traffic flow of each network device. The input is the clean data formatted in step 2, and the output is the detailed analysis of the network topology.

[0651] Step 4:

[0652] The server generates a network configuration diagram based on the analysis results. The diagram is drawn using Python based on the analysis results obtained in the previous step. The input is the analysis results from step 3, and the output is a visually displayable network configuration diagram. The server sends this diagram to the user terminal and displays it on the screen.

[0653] Step 5:

[0654] The user enters prompts to generate configuration information for a new device. Based on the user's input, the server re-utilizes its generation AI model to generate configuration information that takes into account the existing network policy and topology. The input consists of the user's prompts and current network data, and the output is configuration information applicable to the new device.

[0655] Step 6:

[0656] The user reviews the generated configuration information and adjusts it as needed. After adjustment, it can be manually applied to the new device via the terminal if necessary, or automatically applied using the server's remote configuration function. The input is the output configuration information from step 5, and the output is the operational status of the new device after the settings have been applied.

[0657] (Application Example 1)

[0658] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0659] In network operation and management, environments with multiple devices present challenges in terms of managing configuration information, generating network diagrams, and applying settings to new devices, all of which are time-consuming and complex. Furthermore, there is a need for a system that allows network administrators to easily understand the current network configuration and quickly and efficiently apply settings when new devices are added. In particular, the lack of real-time network status monitoring and automated configuration suggestions is a significant problem.

[0660] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0661] In this invention, the server includes means for acquiring information from network devices, means for preprocessing, shaping, and filtering the acquired information, means for analyzing the network configuration using artificial intelligence with the preprocessed information, and means for providing a user interface for displaying the analysis results on the user's mobile terminal, making the visualized configuration diagram operable on the mobile terminal. This enables visualization of the network configuration and efficient information management, allowing administrators to easily grasp the network status and quickly apply settings to new devices.

[0662] "Network equipment" refers to devices used in data centers and other network environments to mediate communications and perform data routing and management.

[0663] "Means for acquiring information" refers to methods or devices for collecting information such as settings and topology from network devices.

[0664] "Preprocessing" is the process of shaping acquired information, removing redundant or duplicate data, and converting it into a format that is easy to analyze.

[0665] "Artificial intelligence" is a program or technology that performs data analysis and prediction based on collected information, enabling advanced decision-making automatically.

[0666] "Means for analyzing network configuration" refers to methods or devices used to identify the interrelationships and data flows of devices within a network.

[0667] A "network configuration diagram" is a diagram that visually shows the placement and connection status of each device within a network.

[0668] "User interface" refers to the screens and means of operation that users use to interact with a system and obtain information.

[0669] A "mobile device" is a small electronic device that a user can carry around and that can run applications on.

[0670] "Visualization" is the process of transforming complex data into a form that is easy for humans to understand and present.

[0671] "Configuration information for new devices" refers to information about the configurations and parameters that should be applied to devices newly added to the network.

[0672] A "configuration suggestion module" is a program or system component designed to suggest optimal settings for new equipment.

[0673] The system realizing this invention includes a program for efficiently managing multiple network devices. The server is responsible for acquiring information from the network devices, collecting data via a RESTful API or CLI. This information is preprocessed to eliminate redundancy and duplication, and to make it easier to analyze. The software used here utilizes Node.js as the data processing backend.

[0674] The server uses artificial intelligence to analyze the network topology based on pre-processed data. This process utilizes AI frameworks such as TensorFlow. The resulting network configuration is then formatted so that users can visually view it on their mobile devices. The smartphone application, built using Flutter, provides an interactive network map.

[0675] Users can manipulate and verify network configuration diagrams on their terminals and generate configuration information for adding new devices in real time. A configuration suggestion module works to present the user with the optimal settings. Furthermore, the generated configuration information can be easily applied to network devices after confirmation by the user. This entire process is provided as a modularized program, with various optimizations implemented to enhance the user experience.

[0676] A concrete example is a scenario where a user uses a smartphone to check the status of routing switches within a data center. Based on the analysis results, the optimal IP address assignment for the new router is automatically suggested. An example of a prompt message is as follows:

[0677] "Obtain the latest network equipment information, analyze and visualize the topology within the data center, and then generate a proposed IP address assignment for the new router. Finally, verify this configuration and present it in a final, applicable format."

[0678] In this way, users can perform quick and accurate network management without requiring any special technical knowledge.

[0679] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0680] Step 1:

[0681] The server accesses network devices and retrieves configuration information. It uses network device access information as input and collects data via CLI or RESTful API. The output is the collected raw configuration data. Specifically, the server sends commands to each network device and logs the returned data.

[0682] Step 2:

[0683] The server preprocesses the acquired data. The input is the raw configuration data obtained in step 1, which is then formatted and filtered. Redundant information and duplicate data are removed, transforming it into a clean and consistent data structure. The output is clean data in a parseable format. Specifically, it uses regular expressions to extract and organize the necessary information and saves it to the database.

[0684] Step 3:

[0685] The server uses pre-processed data to analyze the network configuration using artificial intelligence. The input is the clean data formatted in step 2. Using a generative AI model such as TensorFlow, it analyzes the network topology and the roles of devices, and identifies traffic patterns. The output is the analysis result data regarding the network topology. Specifically, the AI ​​model performs data analysis and feeds the results back into the database.

[0686] Step 4:

[0687] The server generates a network diagram based on the analysis results and transmits it to the terminal. The input is the analysis result data from step 3. The output is a visualized network diagram. Specifically, the terminal uses Flutter to draw an interactive diagram based on the data received from the server.

[0688] Step 5:

[0689] The user views the configuration diagram on the terminal and generates configuration information corresponding to the addition of new equipment. The inputs are the network configuration diagram and the requirements of the new equipment. The configuration suggestion module generates appropriate configuration information in real time and presents it to the user. The output is the new configuration information confirmed by the user. In terms of specific operation, the user modifies and confirms the presented configuration suggestion by operating the terminal.

[0690] Step 6:

[0691] The server receives the configuration information confirmed by the user and applies it to the new device. The input is the configuration information that the user finalized in step 5. The output is the updated network configuration. Specifically, the server sends the new settings to the network device and notifies the user that the application was successful.

[0692] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0693] This invention combines a system that analyzes network configuration based on configuration information obtained from network devices and generates configuration information for new devices as needed with an emotion engine that recognizes user emotions. A specific embodiment is shown below.

[0694] The server first obtains configuration information from network devices. It accesses the devices using the CLI and extracts the configuration information, or it collects network information directly using the API.

[0695] Next, the server preprocesses the acquired information, performing filtering and formatting, and then performs network configuration analysis using an artificial intelligence algorithm. This analysis generates a topology diagram, which is then provided to the user as a visually displayed diagram.

[0696] Furthermore, this system is equipped with an emotion engine that analyzes the user's emotions from their voice and facial expressions while using the system. The emotion engine determines in real time whether the user is experiencing stress or frustration due to network conditions or configuration changes, and adjusts the interface display and suggestions accordingly.

[0697] For example, if the emotion engine detects that a user is confused while reviewing a network diagram, the server will suggest clearer explanations or additional navigation to support the user's understanding. Similarly, if a user is feeling anxious when generating configuration information for new equipment, the emotion engine will detect this and the server will provide detailed instructions or alternative solutions.

[0698] Through the terminal, users can confidently apply and manage network settings using an emotion-recognition-adjusted interface. This provides a better user experience and improves the efficiency and effectiveness of network management.

[0699] The following describes the processing flow.

[0700] Step 1:

[0701] The server accesses network devices to collect configuration information. When using the CLI, the server executes automated scripts to dump configuration information from each device. If an API is available, the server uses the API endpoint to efficiently retrieve information.

[0702] Step 2:

[0703] The server preprocesses the collected configuration information. It organizes and formats the information, removes duplicates and unnecessary data, and converts it into a format that is easy to analyze.

[0704] Step 3:

[0705] The server inputs pre-processed information into an AI algorithm to analyze the network configuration. The AI ​​identifies the function and connectivity of each device and generates data to visualize the network topology.

[0706] Step 4:

[0707] The server generates a network configuration diagram based on the analysis results. This diagram is displayed to the user as a graphical interface that intuitively shows the overall structure of the network.

[0708] Step 5:

[0709] Through the terminal, the user checks the configuration diagram and understands the current network status. The emotion engine analyzes the user's voice and facial expressions at this time and evaluates their emotional state in real time.

[0710] Step 6:

[0711] The emotion engine suggests support for actions based on the user's emotional state. For example, if the user is feeling stressed, the server will provide additional explanations or hints to help the user understand.

[0712] Step 7:

[0713] The server generates configuration information for the new device. During this process, the emotion engine provides detailed explanations of the configuration and suggests adjustments to ensure user confidence.

[0714] Step 8:

[0715] The user reviews the configuration information generated through the device and makes adjustments if necessary. If the user is satisfied with the settings, the server automatically applies the settings to the new device. Alternatively, the user can apply the settings manually.

[0716] This process allows users to manage the network with confidence, and the system responds efficiently and flexibly.

[0717] (Example 2)

[0718] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0719] In today's complex network environments, manual network configuration and setup changes by administrators require considerable effort, time, and can be emotionally stressful. Furthermore, the installation of new equipment and the generation of configuration information can lead to misconfigurations and management errors. Additionally, users often find it difficult to visually grasp and understand the network configuration, potentially hindering system operation. To address these challenges, an efficient and user-friendly network management system is essential.

[0720] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0721] In this invention, the server includes means for acquiring information from network devices, means for preprocessing, shaping, and filtering the information, and means for analyzing the network configuration using a machine learning algorithm. This enables automated analysis and visual display of the network configuration, as well as adjustment of the interface to suit the user's emotions.

[0722] "Network devices" are hardware devices used for network data communication, and include routers, switches, firewalls, and other similar devices.

[0723] "Means of acquiring information" refers to methods and technologies used to collect configuration data and operational data from network devices, and this is done through CLI or API.

[0724] "Preprocessing" is the process of organizing acquired information and formatting it into a form that is easy to analyze, and includes deleting unnecessary data and transforming data.

[0725] A "machine learning algorithm" refers to a mathematical model or statistical method used to process large amounts of data and discover useful patterns or structures.

[0726] "Means for analyzing network configuration" refers to technologies and methods for analyzing network structure and connection relationships and deriving them into a visually displayable format.

[0727] "Means for generating configuration information for new devices" refers to technologies and methods that automatically create the configuration data necessary to efficiently configure newly introduced network devices.

[0728] "Means for analyzing emotional states" refers to technologies and methods for detecting a user's emotional state based on their voice and facial expressions, and adjusting the system's response accordingly.

[0729] "Means for adjusting interface display" refers to technologies and methods that flexibly change the content of displayed screens and information in order to support user understanding.

[0730] This invention is a system for streamlining network management and reducing user stress. The system is implemented through interaction between servers, terminals, and users. Specific embodiments are described below.

[0731] Acquisition and processing of network data

[0732] First, the server accesses the network device and retrieves network configuration information using the CLI (Command Line Interface) or API (Application Programming Interface). This information includes important data related to the network configuration, such as IP addresses, routing tables, and interface settings. The retrieved data is filtered and formatted to preprocess it into a format suitable for analysis.

[0733] Network Configuration Analysis

[0734] The server uses machine learning algorithms to analyze the pre-processed information. This analysis converts the network topology into an easily understandable format, allowing it to be visually displayed as a topology diagram. By viewing this diagram, users can intuitively grasp the state of the network.

[0735] Sentiment analysis and user interface adjustments

[0736] In addition, the system is equipped with an emotion analysis engine that analyzes the user's emotional state from their voice and facial expressions. Based on this information, the server adjusts the interface display in real time and provides additional information and guidance to help the user understand.

[0737] Specific example

[0738] For example, if a user is planning to expand their office network and needs to add new equipment, the invention can help. When the user prompts, "How do I install a new switch?", the server analyzes the entire network and suggests the optimal connection port and setup procedure. If the emotion engine determines that the user's facial expression indicates confusion, it provides additional visual guides and detailed instructions to support the user.

[0739] This invention aims to reduce the stress users experience when performing complex network management and to support smooth operation.

[0740] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0741] Step 1:

[0742] The server retrieves information from network devices. Specifically, it accesses the devices using CLI or API and collects data such as IP addresses, routing tables, and interface settings. In this case, the input is raw configuration data from the network devices, and the output is a set of data acquired for analysis.

[0743] Step 2:

[0744] The server preprocesses the acquired data. Specifically, it filters out redundant information, extracts the necessary data, and formats it. This process cleanses and reformats the data, outputting it in a format suitable for analysis. The input here is raw configuration data, and the output is formatted, analyzable data.

[0745] Step 3:

[0746] The server uses machine learning algorithms to analyze the formatted data. This allows it to understand the network topology and generate a visualized topology diagram. The input is pre-processed data, and the output is structured model data representing the topology. Specifically, it can generate topology diagrams and visually display the network connectivity status.

[0747] Step 4:

[0748] The server uses an emotion analysis engine to analyze the user's voice and video. It analyzes the emotional state and adjusts the interface display as needed. The input for this step is real-time voice and video data from the user, and the output is their emotional state. Based on this information, the server dynamically provides additional support information and navigation.

[0749] Step 5:

[0750] Through the terminal, the user utilizes information and interfaces provided by the server to configure the new device. The input is the recommended configuration information received from the server, and the output is the actual device configuration applied. The user can then apply the configuration by following specific operating procedures, thereby optimizing the network.

[0751] (Application Example 2)

[0752] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0753] In managing information networks, users often face complex configurations and setting changes, which can cause stress and anxiety. There is also the risk of system failure due to incorrect decisions during configuration changes. Traditional systems have failed to alleviate user psychological burden and provide adequate support. Therefore, there is a need to provide an information network management interface that takes user emotions into consideration.

[0754] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0755] In this invention, the server includes means for acquiring information from network devices, means for preprocessing, shaping, and filtering the acquired information, and means for analyzing the configuration of the information network using artificial intelligence based on the preprocessed information. This makes it possible to reduce the psychological burden on users regarding information network management and mitigate the risk of system failures due to incorrect judgments by recognizing the user's emotions and dynamically adjusting the interface.

[0756] "Network equipment" is a general term for devices that manage the connection of information networks and perform data communication.

[0757] "Information preprocessing" is the process of shaping acquired raw data into an analyzable format and removing noise as needed.

[0758] Artificial intelligence is a technology in which computer systems mimic some aspects of human intelligence, enabling data analysis and pattern recognition.

[0759] An "information network configuration diagram" is a diagram that visually represents the elements of an information network and their connection relationships.

[0760] "Configuration information for new devices" refers to information that defines the specific configuration and operating conditions to be applied to devices newly added to the information network.

[0761] "Means of recognizing emotions" refer to technologies and devices that detect a user's emotional state and process information based on that state.

[0762] A "browsing device" is a device that provides an interface for visually displaying information and allowing users to confirm its content.

[0763] To realize this invention, collaboration between the server, terminal, and user is crucial. The server first acquires information from network devices, then formats and filters that information. This involves collecting data using a RESTful API and performing preprocessing. Next, using the preprocessed information, the server analyzes the network configuration using artificial intelligence algorithms and generates a configuration diagram. The server sends this configuration diagram to the terminal, allowing the user to visually confirm it.

[0764] Furthermore, the server utilizes an emotion recognition engine to recognize the user's emotions. This engine uses software such as OpenCV and DeepFace to analyze emotional data from the user's facial expressions and voice in real time and reflect it in the interface. As a result, the user can receive information tailored to their state, allowing for smoother operation.

[0765] For example, if a user is feeling anxious about a change in the information network, and the emotion recognition engine detects stress, the system can then provide more detailed instructions or alternatives. This improves the accuracy of information network management and reduces the occurrence of errors. An example of a prompt would be, "Explain the expected impact of this change in the information network configuration."

[0766] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0767] Step 1:

[0768] The server retrieves configuration information from network devices. It uses a RESTful API as input, receiving raw data from the devices. The output is the unprocessed configuration information stored on the server. This process involves establishing a secure connection and sending appropriate requests to the devices to collect data.

[0769] Step 2:

[0770] The raw data acquired by the server is preprocessed, formatted, and filtered. The input is the unprocessed configuration information obtained in step 1. The output is a formatted dataset containing only the necessary information. Specifically, the data format is normalized, and unnecessary noise and duplicate data are removed.

[0771] Step 3:

[0772] The server uses pre-processed data to analyze the network configuration using artificial intelligence algorithms. The input is a formatted dataset, and the output is data for a network configuration diagram. In this process, a generative AI model is used to identify connection relationships and components within the data and create a visualized topology.

[0773] Step 4:

[0774] The server generates an information network configuration diagram and sends it to the terminal, making it visually accessible to the user. The input is the data of the configuration diagram generated in step 3, and the output is the visualized configuration diagram displayed on the user's terminal. In this step, information converted to a format suitable for the user's terminal is seamlessly transferred.

[0775] Step 5:

[0776] The server recognizes the user's emotions and dynamically adjusts the interface through an emotion recognition engine. The input is the user's facial expressions and voice data, and the output is an interface adjusted according to those emotions. This process uses OpenCV and DeepFace to analyze emotion data in real time and automatically optimize parts of the UI.

[0777] Step 6:

[0778] The user performs tasks based on the information provided. They receive information at each step and manually or automatically confirm changes to the network settings. Inputs are suggestions and instructions from the server, and outputs are the application of settings to network devices. Specific actions include making actual configuration changes according to navigation guidelines.

[0779] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0780] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0781] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0782] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0783] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0784] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0785] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0786] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0787] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0788] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0789] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0790] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0791] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0792] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0793] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0794] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0795] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0796] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0797] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0798] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0799] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0800] The following is further disclosed regarding the embodiments described above.

[0801] (Claim 1)

[0802] A means of obtaining information from network devices,

[0803] Means for preprocessing, shaping, and filtering the acquired information,

[0804] A means of analyzing the network configuration using artificial intelligence with pre-processed information,

[0805] A means for generating a network configuration diagram based on the analysis results,

[0806] A means of generating configuration information for new equipment based on an existing configuration,

[0807] A means for applying the generated configuration information to the device,

[0808] A system that includes this.

[0809] (Claim 2)

[0810] The system according to claim 1, wherein the means for generating configuration information for new devices includes a configuration suggestion module that proposes configuration information in real time, taking into account the network policy and configuration.

[0811] (Claim 3)

[0812] The system according to claim 1, wherein the network configuration diagram generation means includes a viewer that visually displays the configuration diagram through a user interface.

[0813] "Example 1"

[0814] (Claim 1)

[0815] A means for obtaining configuration information from a network device,

[0816] A means for preprocessing the acquired configuration information and converting it into a unified format,

[0817] A means for analyzing network topology using generated AI from pre-processed configuration information,

[0818] A means for automatically generating a visualized network configuration diagram based on the analysis results,

[0819] A means for generating configuration information for a new device, taking into account the existing network configuration and policies,

[0820] A means for applying the generated configuration information to the new device,

[0821] A system that includes this.

[0822] (Claim 2)

[0823] The system according to claim 1, wherein the configuration information generation means for new devices includes a configuration suggestion module that proposes configuration information in real time, taking into account the network policy and topology.

[0824] (Claim 3)

[0825] The system according to claim 1, wherein the network configuration diagram generation means includes a display module that visually displays the configuration diagram through a user output device.

[0826] "Application Example 1"

[0827] (Claim 1)

[0828] A means of obtaining information from network devices,

[0829] Means for preprocessing, shaping, and filtering the acquired information,

[0830] A means of analyzing the network configuration using artificial intelligence with pre-processed information,

[0831] A means for generating a network configuration diagram based on the analysis results,

[0832] A means of generating configuration information for new equipment based on an existing configuration,

[0833] A means for applying the generated configuration information to the device,

[0834] A user interface is provided to display the analysis results on the user's mobile device, and a means is provided to make the visualized configuration diagram operable on the mobile device.

[0835] A system that includes this.

[0836] (Claim 2)

[0837] The system according to claim 1, wherein the means for generating configuration information for new devices includes a configuration suggestion module that proposes configuration information in real time, taking into account the network policy and configuration, and has an interface that can be viewed and edited by the user on a mobile terminal.

[0838] (Claim 3)

[0839] The system according to claim 1, wherein the network configuration diagram generation means includes a viewer that visually displays the configuration diagram through a user interface, and makes the configuration information applicable to network devices by remote operation using a mobile terminal.

[0840] "Example 2 of combining an emotion engine"

[0841] (Claim 1)

[0842] A means of obtaining information from a network device,

[0843] Means for preprocessing, shaping, and filtering the acquired information,

[0844] A means for analyzing the network configuration using a machine learning algorithm with preprocessed information,

[0845] A means for generating and visually displaying a network configuration diagram based on the analysis results,

[0846] A means for generating configuration information for a new device based on an existing configuration,

[0847] Means for applying the generated configuration information to the device,

[0848] A means for analyzing the user's emotional state and adjusting the interface display,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, wherein the means for generating configuration information for a new device includes a configuration suggestion module that proposes configuration information in real time, taking into account the rules and configuration of the network.

[0852] (Claim 3)

[0853] The system according to claim 1, wherein the network configuration diagram generation means includes a viewer that visually displays the configuration diagram through a user interface, and further includes a module that adjusts the display content based on the user's emotions.

[0854] "Application example 2 of combining emotional engines"

[0855] (Claim 1)

[0856] A means of obtaining information from a network device,

[0857] Means for preprocessing, shaping, and filtering the acquired information,

[0858] A means for analyzing the structure of an information network using artificial intelligence with pre-processed information,

[0859] A means for generating an information network configuration diagram based on the analysis results,

[0860] A means for generating configuration information for a new device based on an existing configuration,

[0861] Means for applying the generated configuration information to the device,

[0862] A means of recognizing user emotions and dynamically adjusting the interface,

[0863] A system that includes this.

[0864] (Claim 2)

[0865] The system according to claim 1, wherein the means for generating configuration information for a new device includes a configuration suggestion module that immediately proposes configuration information taking into account the rules and configuration of the information network.

[0866] (Claim 3)

[0867] The system according to claim 1, wherein the information network configuration diagram generation means includes a viewing device that visually displays the configuration diagram through a user interface, and provides explanations and suggestions that are adjusted based on the user's feelings. [Explanation of Symbols]

[0868] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of obtaining information from network devices, A means for preprocessing, shaping, and filtering the acquired information, A means of analyzing the network configuration using artificial intelligence with pre-processed information, A means for generating a network configuration diagram based on the analysis results, A means of generating configuration information for new equipment based on an existing configuration, A means for applying the generated configuration information to the device, A system that includes this.

2. The system according to claim 1, wherein the means for generating configuration information for new devices includes a configuration suggestion module that proposes configuration information in real time, taking into account the network policy and configuration.

3. The system according to claim 1, wherein the network configuration diagram generation means includes a viewer that visually displays the configuration diagram through a user interface.

Images