system

Abstract

We provide the system. [Solution] A means of automatically acquiring configuration data from network devices, A means for analyzing acquired configuration data using natural language processing technology to identify the meaning and relationships of each configuration item, Based on the analysis results, a means is provided to generate explanatory text for the setting items and to visualize the interrelationships between the settings. A means of presenting the generated information in a format accessible to the user, A means to identify the scope of impact when configuration changes are made and to quickly share that information with relevant parties, A means to save the analysis results as a learning resource and utilize them for work support and skill improvement, 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 recent years, with the diversification and complication of network devices, the management of configuration data has become difficult. In particular, in the face of the need to grasp the interrelationships and influence ranges of configurations, as well as to respond quickly during troubleshooting and configuration changes, there is a lack of a mechanism to efficiently support this. For this reason, the increase in time and human costs in network management has become an issue. Furthermore, since learning resources for OJT and continuous skill improvement are not sufficient, a method for supporting job acquisition without much effort is required.

Means for Solving the Problems

[0005] This invention provides a system that automatically acquires configuration data from network devices and analyzes that data using natural language processing technology. Based on the analysis results, this system automatically generates explanatory text for configuration items and visualizes it, providing users with information that can be intuitively understood. It also has a function to identify the scope of impact when configuration changes are made and immediately share it with relevant parties. Furthermore, by saving the analysis results as learning resources and making them available for on-the-job training and skill development, the system aims to improve the efficiency of network management work and enhance technical capabilities.

[0006] A "network device" is a device used in a communication network to send, receive, process, and route data.

[0007] "Configuration data" refers to data containing information necessary to control and manage the operation of network devices.

[0008] "Natural language processing technology" is the technology that allows computers to understand, interpret, and manipulate human language.

[0009] "Analysis" is the process of breaking down data and understanding its components and interrelationships.

[0010] An "explanatory text" is a piece of writing created to explain the details and meaning of specific information or data.

[0011] "Visualization" is the process of making data and information easier to understand intuitively by converting them into visual representations such as diagrams and graphs.

[0012] "Scope of impact" refers to the area or range that a particular change or event may have an effect on.

[0013] "Sharing" is the act of making information or resources available for joint use by multiple people or systems.

[0014] "Learning resources" refer to materials and information that can be utilized for knowledge acquisition and skill improvement.

[0015] "OJT" is an abbreviation for "On-the-Job Training" and is a process of acquiring skills and knowledge through actual work.

Brief Explanation of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Embodiment for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained. [[ID=ID=17]]

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of 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.

[0020] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the 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.

[0022] 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).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention provides a system for streamlining the management of configuration data across multiple network devices and for quickly understanding the scope of impact during fault response and configuration changes. The following describes a specific embodiment of this system.

[0038] The server periodically or automatically retrieves and stores configuration data for all devices connected to the network, either on a regular basis or upon user request. The server analyzes the retrieved configuration data using natural language processing techniques to clarify the meaning and interrelationships of the configuration items. For example, if a new router is added to the network, the server analyzes the router's configuration and evaluates its impact on the existing network configuration.

[0039] Based on the analysis results, the server automatically generates detailed explanatory text for each setting item. Furthermore, it creates diagrams that visually represent the interrelationships and dependencies between settings. This allows users to intuitively understand the settings and their scope of impact through their terminal.

[0040] When a user makes a configuration change, the server immediately compares the old and new settings to identify the scope of the impact. This information is quickly shared with relevant parties to support appropriate countermeasures. For example, if a user changes the port settings of a network switch, the server identifies the impact of that change on other devices and notifies the user.

[0041] Furthermore, the server saves the analysis results and generated explanatory texts as learning resources. This information can be used by users for on-the-job training and continuous skill development, contributing to improved work performance.

[0042] Thus, the present invention provides a specific embodiment for improving the efficiency of network management while simultaneously enhancing the technical capabilities of those involved.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server detects each device connected to the network and prepares to collect configuration data. The server checks the connection information in the system management database to determine if it can access each device.

[0046] Step 2:

[0047] The server automatically retrieves the latest configuration data from accessible network devices and saves it to local storage. Since the configuration data may be formatted or encrypted, the server performs appropriate data conversion and decryption.

[0048] Step 3:

[0049] The server runs a natural language processing engine to analyze the acquired configuration data. Specifically, it extracts the key and value of each configuration item and uses an AI model to understand their meaning.

[0050] Step 4:

[0051] The server generates explanatory text for the configuration items based on the analysis results. Using a generative AI model, it creates explanatory text in natural language that is easy for users to understand and identifies interrelationships between related configuration items.

[0052] Step 5:

[0053] The server generates a diagram to visually represent interrelated configuration items. This diagram illustrates network configurations and dependencies, and visualizes the impact of changes on other settings.

[0054] Step 6:

[0055] Users can review the explanatory text and diagrams generated through their device to understand the settings and their scope of impact. Furthermore, users can modify the settings as needed.

[0056] Step 7:

[0057] When changes are made, the server compares the old and new settings to identify the scope of the impact. The identified information is notified to relevant parties in real time.

[0058] Step 8:

[0059] The server stores the analysis results and generated explanatory texts in a database, which is then organized as a learning resource. Users can utilize this information to acquire new skills and improve their abilities.

[0060] (Example 1)

[0061] 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."

[0062] In network management, efficiently analyzing large amounts of configuration information collected from multiple information devices and quickly and accurately understanding their relationships is challenging. Furthermore, there is a need for a timely method to evaluate the impact of configuration changes on the entire system and provide appropriate information to stakeholders. Additionally, establishing a system that utilizes this information as a learning resource and contributes to improving technical capabilities is another challenge.

[0063] 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.

[0064] In this invention, the server includes means for automatically acquiring configuration information from an information device, means for analyzing the acquired configuration information using language processing technology to identify the meaning and relationships of the configuration items, and means for generating explanatory content for the configuration items based on the analysis results and visualizing the interrelationships. This makes it possible to efficiently manage configuration information for the entire network, quickly assess the impact of changes, and provide appropriate information to stakeholders. Furthermore, by saving the analysis results as learning resources, it can also contribute to improving technical capabilities.

[0065] An "information device" refers to a device or system connected to a network that holds and manages configuration information.

[0066] "Configuration information" refers to a collection of data that specifically indicates the various parameters and operating conditions set in an information device.

[0067] "Language processing technology" refers to techniques for interpreting and analyzing natural language, aiming to convert complex information into a form that humans can understand.

[0068] "Analysis results" refer to the output of an analysis of the significance and relationships of configuration information obtained using language processing technology.

[0069] "Explanatory content" refers to text and diagrams that explain the details of the settings based on the analysis results, providing information in a way that is easy for users to understand.

[0070] "Interrelationship" is a concept that describes how configuration information within a network is related to and influences each other.

[0071] "Impact assessment" is the process of evaluating and confirming the potential impact that a configuration change may have on other information devices or the entire system.

[0072] "Learning resources" refer to a collection of information, including analyzed data and generated explanations, that is stored for use in knowledge improvement and technical training.

[0073] This invention is a system for improving the efficiency of network management by efficiently managing configuration information collected from multiple information devices, visualizing the analysis results, and utilizing them as learning resources. Specific embodiments of this system are described below.

[0074] 1. Hardware and software configuration

[0075] The server automatically retrieves configuration information from network-connected information devices. Protocols such as SSH and SNMP can be used for this retrieval. A program running on the server analyzes the configuration information using natural language processing techniques. Here, a generative AI model is used to identify the significance and relationships between configuration items. The analyzed information is stored in a database and used for subsequent processing. Furthermore, based on the analysis results, the server generates explanatory content and visualizes the interrelationships between settings.

[0076] 2. Specific Examples of Data Processing and Calculation

[0077] For example, if a user adds a new network switch, the server retrieves the switch's configuration information and analyzes its relationship to the existing network configuration. Based on this analysis, it evaluates the potential impact of the switch configuration changes on other devices and generates a detailed explanation. Furthermore, it utilizes a generative AI model to create visualizations and provides them to the user's terminal. This allows the user to intuitively understand the impact of the configuration changes.

[0078] 3. Utilization as a learning resource

[0079] The analysis results and generated explanations are stored as learning resources in a database on the server. Users can utilize this information to support their work and improve their technical skills. For example, in training new engineers, they can efficiently acquire the knowledge necessary to perform their jobs by referring to the analysis results of past configuration change cases and their scope of impact.

[0080] Example of a prompt

[0081] "We've added a new network device. Please analyze the impact this new device will have on the existing network configuration and generate a configuration explanation based on that. A visually easy-to-understand diagram would be helpful."

[0082] In this way, the system of the present invention reduces the complexity of network management, enables rapid assessment of risks associated with configuration changes, and allows for the provision of appropriate information to relevant parties.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] Automatic retrieval of configuration information

[0086] The server automatically retrieves configuration information from all information devices connected to the network. The input is a connection request from each information device using its network protocol (e.g., SSH, SNMP), and the output is a collection of retrieved configuration information. The server stores the configuration information in a database, preparing it for use in the next processing step. This operation allows the server to maintain the latest network configuration in real time.

[0087] Step 2:

[0088] Configuration details analysis

[0089] The server analyzes the acquired configuration information using a generative AI model. The input is configuration information obtained from the database, and the output is the analysis results regarding the significance and relationships of the configuration items. Specifically, the server utilizes natural language processing techniques to identify the role each setting plays in the overall network. Through this analysis, the server gains a deeper understanding of the overall network configuration.

[0090] Step 3:

[0091] Generating explanatory content and visualized information

[0092] The server generates explanatory text for the configuration information based on the analysis results and visualizes the interrelationships. The input is the analysis results obtained in step 2, and the output is the explanatory text and visualization presented to the user. The server uses a generative AI model to create natural language and draw diagrams showing the relationships between settings. This allows the user to intuitively understand the impact of setting changes through their terminal.

[0093] Step 4:

[0094] Assessment and notification of impact

[0095] When a user changes a setting, the server immediately begins assessing the scope of the impact. The input is detailed information about the setting change made by the user, and the output is a list of the potential impacts that the change may have on other information devices and services. Specifically, the server compares the old and new settings and uses a generative AI model to evaluate the impact of the change. As a result, the server generates an evaluation report and promptly notifies the relevant parties.

[0096] Step 5:

[0097] Information storage as a learning resource

[0098] The server stores the analysis results and explanatory content as learning resources. The input is the results from steps 3 and 4, and the output is a database entry that can be used for technical improvement and work support. The server organizes this information and keeps it accessible for future reference and educational purposes. This operation allows users to learn from past cases and effectively deepen their knowledge of network management.

[0099] (Application Example 1)

[0100] 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."

[0101] Managing network device configuration data involves complex processes such as configuration changes and troubleshooting across multiple devices, requiring rapid and accurate assessment of the scope of impact. However, traditional methods often rely on manual processes for configuration management and impact assessment, which is inefficient. Furthermore, network administrators find it difficult to intuitively understand configuration data, and it is not fully utilized as a resource for improving technical skills. A new system is needed to address these challenges.

[0102] 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.

[0103] In this invention, the server includes means for automatically acquiring configuration data from network devices, means for analyzing the acquired configuration data using natural language processing technology to identify the meaning and relationships of each configuration item, and means for visually displaying the interrelationships of the analyzed configuration items and the scope of impact of changes on a mobile terminal. This enables network administrators to intuitively understand the relationships and scope of impact of settings and perform network management tasks efficiently.

[0104] "Network devices" refer to all equipment connected to a network for communication purposes, including routers, switches, and firewalls.

[0105] "Configuration data" refers to information used to control the operation of network devices, and includes IP addresses, routing information, policies, and more.

[0106] "Natural language processing technology" is a technique that uses computers to understand and analyze human language, and is used to extract the meaning and structure of text.

[0107] "Analysis" is the process of meticulously analyzing acquired data to clarify its meaning and relationships.

[0108] "Interrelationship" refers to the influence or relationship between multiple items or elements.

[0109] "Visualization" is the process of converting information and data into diagrams and graphs that are easy for humans to understand.

[0110] A "mobile terminal" refers to a portable computing device such as a smartphone or tablet.

[0111] A "generative artificial intelligence model" is a collection of machine learning algorithms that learn from large amounts of data and make autonomous decisions and predictions.

[0112] A "prompt sentence" refers to a sentence that is input to a generative AI model to prompt it to produce a specific output.

[0113] This invention is a system for streamlining network management and includes a function to automatically acquire configuration data from multiple network devices. The server collects data periodically or upon user request using a Python script and stores it in a PostgreSQL or MongoDB database. To analyze this data, the spaCy library in Python is used as a natural language processing technique to clarify the meaning and interrelationships of the configuration items.

[0114] The server uses the analysis results to generate input prompts that the AI ​​model can understand. These prompts allow the AI ​​model to perform complex analysis using cloud computing resources to identify the scope of impact. The generated information is visually presented to the mobile device through a user interface developed using React Native. This allows users to intuitively understand, in real time, the impact of network configuration changes on other devices.

[0115] A concrete example of this system could be used when adding a new network switch to a data center. When a user sends the new device's configuration to a server via a smartphone application, the server analyzes the impact of that configuration on the existing network configuration. The analysis results are displayed as a visual graph on the mobile device, allowing the user to instantly see the impact of the configuration change on other network devices. An example of an input prompt for the generated AI model might be, "Analyze how the configuration changes for the new router will affect the entire network."

[0116] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0117] Step 1:

[0118] The server automatically retrieves configuration data from network devices. During this process, it uses a RESTful API to pull the latest configuration information from the devices and receives the data in JSON format. The input is the network device's API endpoint, and the output is the retrieved configuration data.

[0119] Step 2:

[0120] The server applies natural language processing techniques to analyze the acquired configuration data. Specifically, it uses the Python spaCy library to parse the data and identify the meaning and interrelationships of the configuration items. The input is configuration data in JSON format, and the output is the parsed semantic information and relationship data. In this process, keywords within the data are extracted and their correlations are calculated.

[0121] Step 3:

[0122] The server identifies the scope of impact of configuration changes based on the analysis results. This involves performing calculations that evaluate how the changes will affect other devices by referencing relevant information in the configuration management database. The input is the analyzed semantic information and related data, and the output is the result of identifying the scope of impact.

[0123] Step 4:

[0124] The server generates prompt statements for use in the generated AI model. These prompt statements are in the form of specific questions to the AI, allowing it to examine in detail how the changed settings will affect the entire network. The input is the result of identifying the scope of impact, and the output is the generated prompt statements.

[0125] Step 5:

[0126] The terminal visually presents the analysis results and prompt messages to the user. Using a React Native UI, it displays settings and the scope of their changes as graphs and diagrams. Input consists of the generated prompt messages and impact information, while output is visualized data in a user-viewable format.

[0127] Step 6:

[0128] Based on the information provided through the terminal, users can make configuration changes or perform additional analyses as needed. This supports informed decision-making in network management, enabling efficient management. The input is visualized data, and the output is the user's configuration change actions.

[0129] 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.

[0130] This invention improves the accuracy of information presentation and the user experience by combining a network management system with an emotion engine that recognizes user emotions. Embodiments of this invention will be described below.

[0131] The server automatically retrieves configuration data from network devices and analyzes it using natural language processing technology. The retrieved data is used to identify the meaning and interrelationships of each configuration item, and explanatory text for each configuration item is generated based on the analysis results. Furthermore, a diagram visually representing the interrelationships of the settings is created and presented in a user-accessible format.

[0132] The emotion engine embedded in the server analyzes video and audio data acquired from the user's device to infer the user's emotional state. Based on this information, the server dynamically changes the content and format of the data it presents, adapting to provide information in the most acceptable way for the user. For example, if it is determined that the user is confused, the explanatory text may be made more detailed, and the visualized information may be simplified.

[0133] The timing of presenting important information is also adjusted based on the user's emotional state. For users in busy situations, it's possible to delay the presentation of information and show a summary that can be understood in a short time. The emotion engine also records user feedback, which is used as data to optimize how subsequent analysis results are presented.

[0134] Furthermore, the analysis results and user sentiment data will also be used as learning resources for work support and skill improvement. This will allow users to utilize the system as part of on-the-job training and improve their network management skills.

[0135] This system is expected to enable users to perform network management tasks more efficiently and effectively, leading to faster resolution of business challenges.

[0136] The following describes the processing flow.

[0137] Step 1:

[0138] The server scans all network devices connected to the network and collects the latest configuration data. The server saves this data to its internal storage in preparation for the next analysis step.

[0139] Step 2:

[0140] The server feeds the stored configuration data into a natural language processing engine, which analyzes the meaning of each configuration item. Here, the configuration values ​​and their interrelationships are identified and understood. As a result, the server generates explanatory text for each configuration.

[0141] Step 3:

[0142] When a user requests access to the current network settings through a connected device, the server creates a visual diagram based on the generated explanatory text. This information is sent to the user's device and presented in a way that is easy for the user to access and understand.

[0143] Step 4:

[0144] The device uses its built-in camera and microphone to collect user emotion data. The device sends the video and audio to a server for analysis by an emotion engine. This process determines the user's current emotional state.

[0145] Step 5:

[0146] The server dynamically adjusts the content and presentation of information based on the user's emotional state, as determined by the emotion engine. For example, if the server determines that the user is confused, it may include detailed explanatory text or simplify visual information to make it more intuitive.

[0147] Step 6:

[0148] The user reviews the information presented through the device and makes changes to their network settings based on their understanding. They update the settings as needed and send the changes to the server.

[0149] Step 7:

[0150] The server compares the old and new settings to identify the scope of the impact and automatically notifies relevant parties of this information. This allows affected users to respond quickly.

[0151] Step 8:

[0152] The server stores analysis results and user sentiment data in a database, creating a learning resource for on-the-job training and skill development. Users can utilize this resource to improve their work skills.

[0153] (Example 2)

[0154] 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".

[0155] Traditional network management systems acquire and analyze configuration data, but they lack sufficient measures to improve the user experience based on that data. In particular, they fail to present information in a way that considers user emotions, which can result in a lack of direct contribution to user understanding and skill improvement. Furthermore, the identification of the scope of impact of configuration changes and the sharing of information are inefficient, highlighting the need for more efficient management operations.

[0156] 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.

[0157] In this invention, the server includes means for automatically acquiring configuration data from network devices, means for analyzing the acquired configuration data using natural language processing technology to identify the meaning and relationships of each configuration item, and means for analyzing the user's emotions and dynamically adjusting the content and format of the presented information according to that state. This enables the presentation of optimal information in accordance with the user's emotions, improving comprehension and streamlining network management operations.

[0158] "Network equipment" is a general term for devices used to build or manage a network communication environment.

[0159] "Configuration data" refers to specific information and parameters used to control the operation and functions of network devices.

[0160] "Natural language processing technology" refers to the technology that enables computers to understand and interpret human language, making text analysis and language generation possible.

[0161] An "explanatory text" is a piece of writing that explains a particular topic in detail to make it easier to understand.

[0162] "Visualization" is a method of representing information and data in visual forms such as diagrams and graphs to aid understanding.

[0163] "Sentiment analysis" is the process of analyzing a user's emotional state and identifying it as a numerical value or category.

[0164] "Feedback" refers to the opinions and reactions that users provide to a system or process.

[0165] "Learning resources" refer to information and tools that users can use to improve their knowledge and skills.

[0166] This invention provides an advanced system to support network management, which has the function of automatically acquiring and analyzing configuration data from network devices. In this system, a server connects to network devices using a specific protocol (e.g., SNMP or SSH) and collects configuration data. This collected data is analyzed using Python or a natural language processing library (e.g., NLTK). As a result of the analysis, the meaning of each configuration item and their interrelationships are identified, and this is generated as explanatory text and visualization data for the configuration items.

[0167] Furthermore, the server is equipped with an emotion engine to analyze the user's emotional state. By using video and audio data collected through the terminal, it infers the user's emotions. Libraries such as OpenCV and Librosa are used for this purpose. Based on the results of this analysis, the server can dynamically adjust the content and format of the information it presents, providing information in a way that is appropriate to the user's emotional state.

[0168] For example, if a user is confused while setting up a new network device, the emotion engine detects this state and, based on the analysis results, elaborates on the explanatory text and simplifies the visualization to help the user quickly understand and resolve the problem. This system allows users to effectively manage their network and quickly resolve operational challenges.

[0169] Example of a prompt:

[0170] "Analyze the following configuration data and explain the meaning and interrelationships of the configuration items: {Configuration Data}"

[0171] To realize this invention, it is necessary to properly combine and operate the software and hardware described in the process above, which will enable users to efficiently perform specific network management tasks.

[0172] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0173] Step 1:

[0174] The server connects to network devices and automatically retrieves configuration data. The input is the IP address and connection information of the network device, and the output is the retrieved configuration data. Specifically, it uses SNMP or SSH protocols to collect configuration parameters from network devices.

[0175] Step 2:

[0176] The server analyzes the acquired configuration data using a natural language processing library. The input is configuration data obtained from network devices, and the output is information identifying the meaning and relationships of each configuration item. Text analysis is performed using Python and NLTK to clearly show how each configuration item relates to others. This analysis highlights important network configuration items.

[0177] Step 3:

[0178] The server generates explanatory text for the settings based on the analysis results and creates diagrams that visualize the interrelationships between the settings. The input is relationship information between items obtained from the analysis, and the output is explanatory text and visualized information. Specifically, it generates text using a generative AI model and creates diagrams using visualization libraries such as matplotlib.

[0179] Step 4:

[0180] The device transmits the user's video and audio data to an emotion analysis engine. Inputs are the user's facial expressions and voice information, while output is the user's emotional state. Data is collected in real time via a webcam and microphone and analyzed using OpenCV and Librosa. The analysis results are sent back to the server as feedback.

[0181] Step 5:

[0182] The server dynamically adjusts the content and format of the information presented based on the user's emotional state. The input is the user's emotional state obtained in step 4, and the output is the adjusted explanatory text and visualizations. For example, if the server determines that the user is having difficulty understanding, it will take measures such as making the explanatory text more detailed. The presented information is provided as content in HTML or PDF format.

[0183] Step 6:

[0184] The user provides feedback on the presented information, and the server records this feedback. The input is the user's feedback data, and the output is its record. This feedback is used to optimize information presentation methods and improve prompts in the generating AI model, and is stored as a learning resource for work support and skill improvement.

[0185] (Application Example 2)

[0186] 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".

[0187] In modern network management, users are required to quickly understand and appropriately respond to large amounts of information. However, traditional systems fail to present this information optimally according to the user's situation and emotional state, making effective information understanding and management difficult. In particular, information presentation can burden users when they are busy or emotionally unstable. This challenge needs to be addressed.

[0188] 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.

[0189] In this invention, the server includes means for automatically acquiring configuration data from network devices, means for decomposing the acquired configuration data using natural language processing technology to determine the meaning and relationships of each configuration item, and means for analyzing the user's emotional state and dynamically adjusting the content and format of the information presented. This enables efficient and less burdensome network management by providing information in an optimal form according to the user's emotional state.

[0190] "Network equipment" refers to a group of devices that manage the transmission of information and data and optimize communication within a network.

[0191] "Configuration data" refers to data that contains information necessary to control and ensure the proper operation of network devices.

[0192] "Natural language processing technology" is a technology that allows computers to understand and process human language.

[0193] "Emotional state" refers to the type and intensity of psychological emotions a user is experiencing.

[0194] "Dynamic adjustment" means changing information and actions in real time according to the situation and conditions to optimize them.

[0195] "User" refers to an individual or organization that uses a system or device to acquire or process information.

[0196] "Information provision" refers to the act of presenting analyzed data and related knowledge to users.

[0197] "Efficient" means achieving the greatest possible result with minimal resources and time.

[0198] This invention is a system aimed at optimizing network management and has the ability to dynamically adjust information presentation according to the user's emotional state.

[0199] First, the server automatically retrieves configuration data from network devices. This configuration data contains information about the operation and performance of the network devices. The server analyzes the retrieved data using natural language processing technology to identify the meaning of each configuration item and their relationships. This streamlines the understanding and management of network settings.

[0200] Next, the emotion recognition engine installed on the server analyzes the audio and video data transmitted from the user's terminal in real time. This uses input devices such as a camera and microphone, as well as analysis software such as OpenCV and TENSORFLOW®. Through this process, the user's emotional state is inferred.

[0201] Based on these analysis results, the server uses a generative AI model to adjust the content and format of the information presented. For example, if it is determined that the user is confused, it can use detailed explanatory text and simplify the visualization of the information. Furthermore, for important information, the timing of its presentation can be changed depending on the user's situation.

[0202] For example, if a user wants to obtain news or information at home, the emotion recognition engine will detect the user's fatigue or anxiety. The server will then simplify the content and provide only the necessary information. This allows the user to obtain the necessary information appropriately without feeling burdened.

[0203] User feedback and sentiment data are stored as learning material for improving the system's business support functions and technology. This data will be useful for improving future analysis methods and the quality of information presentation.

[0204] An example of a prompt for a generative AI model is, "If the user is tired, select three major news stories from today and summarize each in two to three sentences." In this way, the server provides information tailored to the user's mood and assists with network management tasks.

[0205] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0206] Step 1:

[0207] The server automatically retrieves configuration data from network devices. This process uses protocols such as HTTP and SNMP to access the devices and download the latest configuration information. The input is the configuration data from the network devices, and the output is the configuration data stored on the server. The server then prepares this data for analysis.

[0208] Step 2:

[0209] The server analyzes configuration data obtained using natural language processing (NLP) techniques. This analysis uses a natural language processing engine (e.g., spaCy) to identify the meaning and relationships of the configuration items. The input is the configuration data stored on the server, and the output is the analysis results showing the meaning and relationships of each configuration item. Based on the analysis results, the server generates a detailed configuration document and a diagram visualizing the interrelationships.

[0210] Step 3:

[0211] The server receives audio and video data transmitted from the user's terminal and analyzes it using an emotion recognition engine. The input data consists of the user's voice and video, and the output is a judgment result indicating the user's emotional state. Using OpenCV and TensorFlow, facial expressions are analyzed from the video, and the audio data is converted to text using the Google® Cloud Speech-to-Text API for emotion analysis.

[0212] Step 4:

[0213] The server uses a generative AI model to generate the most appropriate information content and format for the user based on the results of emotion recognition. The input is the user's emotional state and the analysis results, and the output is an information summary or presentation adapted to the emotion. A prompt sentence is sent to the generative AI (e.g., GPT-4®) to obtain an appropriate information summary. Specifically, if the user is confused, a concise and easy-to-understand summary is selected.

[0214] Step 5:

[0215] The server delivers the generated information to the user's terminal, optimizing the timing of information presentation according to the user's state. Input consists of instructions regarding sentiment analysis and information presentation methods, while output is customized information displayed on the user's terminal. This allows users to receive necessary information without burden and effectively perform network management tasks.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] [Second Embodiment]

[0220] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0221] 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.

[0222] 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).

[0223] 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.

[0224] 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.

[0225] 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).

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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".

[0232] This invention provides a system for streamlining the management of configuration data across multiple network devices and for quickly understanding the scope of impact during fault response and configuration changes. The following describes a specific embodiment of this system.

[0233] The server periodically or automatically retrieves and stores configuration data for all devices connected to the network, either on a regular basis or upon user request. The server analyzes the retrieved configuration data using natural language processing techniques to clarify the meaning and interrelationships of the configuration items. For example, if a new router is added to the network, the server analyzes the router's configuration and evaluates its impact on the existing network configuration.

[0234] Based on the analysis results, the server automatically generates detailed explanatory text for each setting item. Furthermore, it creates diagrams that visually represent the interrelationships and dependencies between settings. This allows users to intuitively understand the settings and their scope of impact through their terminal.

[0235] When a user makes a configuration change, the server immediately compares the old and new settings to identify the scope of the impact. This information is quickly shared with relevant parties to support appropriate countermeasures. For example, if a user changes the port settings of a network switch, the server identifies the impact of that change on other devices and notifies the user.

[0236] Furthermore, the server saves the analysis results and generated explanatory texts as learning resources. This information can be used by users for on-the-job training and continuous skill development, contributing to improved work performance.

[0237] Thus, the present invention provides a specific embodiment for improving the efficiency of network management while simultaneously enhancing the technical capabilities of those involved.

[0238] The following describes the processing flow.

[0239] Step 1:

[0240] The server detects each device connected to the network and prepares to collect configuration data. The server checks the connection information in the system management database to determine if it can access each device.

[0241] Step 2:

[0242] The server automatically retrieves the latest configuration data from accessible network devices and saves it to local storage. Since the configuration data may be formatted or encrypted, the server performs appropriate data conversion and decryption.

[0243] Step 3:

[0244] The server runs a natural language processing engine to analyze the acquired configuration data. Specifically, it extracts the key and value of each configuration item and uses an AI model to understand their meaning.

[0245] Step 4:

[0246] The server generates explanatory text for the configuration items based on the analysis results. Using a generative AI model, it creates explanatory text in natural language that is easy for users to understand and identifies interrelationships between related configuration items.

[0247] Step 5:

[0248] The server generates a diagram to visually represent interrelated configuration items. This diagram illustrates network configurations and dependencies, and visualizes the impact of changes on other settings.

[0249] Step 6:

[0250] Users can review the explanatory text and diagrams generated through their device to understand the settings and their scope of impact. Furthermore, users can modify the settings as needed.

[0251] Step 7:

[0252] When changes are made, the server compares the old and new settings to identify the scope of the impact. The identified information is notified to relevant parties in real time.

[0253] Step 8:

[0254] The server stores the analysis results and generated explanatory texts in a database, which is then organized as a learning resource. Users can utilize this information to acquire new skills and improve their abilities.

[0255] (Example 1)

[0256] 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."

[0257] In network management, efficiently analyzing large amounts of configuration information collected from multiple information devices and quickly and accurately understanding their relationships is challenging. Furthermore, there is a need for a timely method to evaluate the impact of configuration changes on the entire system and provide appropriate information to stakeholders. Additionally, establishing a system that utilizes this information as a learning resource and contributes to improving technical capabilities is another challenge.

[0258] 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.

[0259] In this invention, the server includes means for automatically acquiring configuration information from an information device, means for analyzing the acquired configuration information using language processing technology to identify the meaning and relationships of the configuration items, and means for generating explanatory content for the configuration items based on the analysis results and visualizing the interrelationships. This makes it possible to efficiently manage configuration information for the entire network, quickly assess the impact of changes, and provide appropriate information to stakeholders. Furthermore, by saving the analysis results as learning resources, it can also contribute to improving technical capabilities.

[0260] An "information device" refers to a device or system connected to a network that holds and manages configuration information.

[0261] "Configuration information" refers to a collection of data that specifically indicates the various parameters and operating conditions set in an information device.

[0262] "Language processing technology" refers to techniques for interpreting and analyzing natural language, aiming to convert complex information into a form that humans can understand.

[0263] "Analysis results" refer to the output of an analysis of the significance and relationships of configuration information obtained using language processing technology.

[0264] "Explanatory content" refers to text and diagrams that explain the details of the settings based on the analysis results, providing information in a way that is easy for users to understand.

[0265] "Interrelationship" is a concept that describes how configuration information within a network is related to and influences each other.

[0266] "Impact assessment" is the process of evaluating and confirming the potential impact that a configuration change may have on other information devices or the entire system.

[0267] "Learning resources" refer to a collection of information, including analyzed data and generated explanations, that is stored for use in knowledge improvement and technical training.

[0268] This invention is a system for improving the efficiency of network management by efficiently managing configuration information collected from multiple information devices, visualizing the analysis results, and utilizing them as learning resources. Specific embodiments of this system are described below.

[0269] 1. Hardware and software configuration

[0270] The server automatically retrieves configuration information from network-connected information devices. Protocols such as SSH and SNMP can be used for this retrieval. A program running on the server analyzes the configuration information using natural language processing techniques. Here, a generative AI model is used to identify the significance and relationships between configuration items. The analyzed information is stored in a database and used for subsequent processing. Furthermore, based on the analysis results, the server generates explanatory content and visualizes the interrelationships between settings.

[0271] 2. Specific Examples of Data Processing and Calculation

[0272] For example, if a user adds a new network switch, the server retrieves the switch's configuration information and analyzes its relationship to the existing network configuration. Based on this analysis, it evaluates the potential impact of the switch configuration changes on other devices and generates a detailed explanation. Furthermore, it utilizes a generative AI model to create visualizations and provides them to the user's terminal. This allows the user to intuitively understand the impact of the configuration changes.

[0273] 3. Utilization as a learning resource

[0274] The analysis results and generated explanations are stored as learning resources in a database on the server. Users can utilize this information to support their work and improve their technical skills. For example, in training new engineers, they can efficiently acquire the knowledge necessary to perform their jobs by referring to the analysis results of past configuration change cases and their scope of impact.

[0275] Example of a prompt

[0276] "We've added a new network device. Please analyze the impact this new device will have on the existing network configuration and generate a configuration explanation based on that. A visually easy-to-understand diagram would be helpful."

[0277] In this way, the system of the present invention reduces the complexity of network management, enables rapid assessment of risks associated with configuration changes, and allows for the provision of appropriate information to relevant parties.

[0278] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0279] Step 1:

[0280] Automatic retrieval of configuration information

[0281] The server automatically obtains configuration information from all information devices connected to the network. The input is a connection request using the network protocol (e.g., SSH, SNMP) of each information device, and the output is a set of the obtained configuration information. The server stores the configuration information in a database and prepares for use in the next processing step. By this operation, the server can keep the latest configuration of the entire network in real time.

[0282] Step 2:

[0283] Analysis of Configuration Information

[0284] The server analyzes the obtained configuration information using a generated AI model. The input is the configuration information obtained from the database, and the output is the analysis result regarding the meaning and relevance of configuration items. As a specific operation, the server makes full use of natural language processing technology to identify what role each configuration plays in the entire network. Through this analysis work, the server can understand the overall picture of the network configuration more deeply.

[0285] Step 3:

[0286] Generation of Explanation Content and Visualization Information

[0287] The server generates explanation content for the configuration information based on the analysis result and visualizes the interrelationships. The input is the analysis result obtained in Step 2, and the output is the explanatory text and visualization diagram presented to the user. The server uses a generated AI model to create natural text and draw a diagram showing the relationships between configurations. By this operation, the user can intuitively understand the impact of configuration changes through the terminal.

[0288] Step 4:

[0289] Evaluation and Notification of the Affected Range ]>

[0290] When a user changes a setting, the server immediately begins assessing the scope of the impact. The input is detailed information about the setting change made by the user, and the output is a list of the potential impacts that the change may have on other information devices and services. Specifically, the server compares the old and new settings and uses a generative AI model to evaluate the impact of the change. As a result, the server generates an evaluation report and promptly notifies the relevant parties.

[0291] Step 5:

[0292] Information storage as a learning resource

[0293] The server stores the analysis results and explanatory content as learning resources. The input is the results from steps 3 and 4, and the output is a database entry that can be used for technical improvement and work support. The server organizes this information and keeps it accessible for future reference and educational purposes. This operation allows users to learn from past cases and effectively deepen their knowledge of network management.

[0294] (Application Example 1)

[0295] 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."

[0296] Managing network device configuration data involves complex processes such as configuration changes and troubleshooting across multiple devices, requiring rapid and accurate assessment of the scope of impact. However, traditional methods often rely on manual processes for configuration management and impact assessment, which is inefficient. Furthermore, network administrators find it difficult to intuitively understand configuration data, and it is not fully utilized as a resource for improving technical skills. A new system is needed to address these challenges.

[0297] 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.

[0298] In this invention, the server includes means for automatically acquiring configuration data from network devices, means for analyzing the acquired configuration data using natural language processing technology to identify the meaning and relationships of each configuration item, and means for visually displaying the interrelationships of the analyzed configuration items and the scope of impact of changes on a mobile terminal. This enables network administrators to intuitively understand the relationships and scope of impact of settings and perform network management tasks efficiently.

[0299] "Network devices" refer to all equipment connected to a network for communication purposes, including routers, switches, and firewalls.

[0300] "Configuration data" refers to information used to control the operation of network devices, and includes IP addresses, routing information, policies, and more.

[0301] "Natural language processing technology" is a technique that uses computers to understand and analyze human language, and is used to extract the meaning and structure of text.

[0302] "Analysis" is the process of meticulously analyzing acquired data to clarify its meaning and relationships.

[0303] "Interrelationship" refers to the influence or relationship between multiple items or elements.

[0304] "Visualization" is the process of converting information and data into diagrams and graphs that are easy for humans to understand.

[0305] A "mobile terminal" refers to a portable computing device such as a smartphone or tablet.

[0306] A "generative artificial intelligence model" is a collection of machine learning algorithms that learn from large amounts of data and make autonomous decisions and predictions.

[0307] The "prompt sentence" refers to the sentence input to prompt a specific output from the generative AI model.

[0308] This invention is a system for improving network management efficiency, equipped with the function of automatically acquiring configuration data from multiple network devices. The server collects data periodically or in response to user requests through a script using Python and stores it in databases such as PostgreSQL or MongoDB. To analyze this data, the spaCy library of Python is used as a natural language processing technology to clarify the meaning and interrelationships of the configuration items.

[0309] The server uses the analysis results to generate an input prompt sentence that can be understood by the generative AI model. With this prompt sentence, the AI model performs complex analysis using computing resources on the cloud to identify the scope of influence. The generated information is visually presented to the mobile terminal through a user interface developed using React Native. As a result, users can intuitively grasp in real time the impact of network configuration changes on other devices.

[0310] As a specific example, it is conceivable to use this system when adding a new network switch to a data center. When the user sends the settings of the new device to the server through the application on the smartphone, the server analyzes the impact of the settings on the existing network configuration. The analysis results are displayed on the mobile terminal as a visual graph, and the user can immediately confirm the impact of the setting change on other network devices. Examples of input prompt sentences to the generative AI model include "Please analyze how the setting change of the new router affects the entire network."

[0311] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0312] Step 1:

[0313] The server automatically retrieves configuration data from network devices. During this process, it uses a RESTful API to pull the latest configuration information from the devices and receives the data in JSON format. The input is the network device's API endpoint, and the output is the retrieved configuration data.

[0314] Step 2:

[0315] The server applies natural language processing techniques to analyze the acquired configuration data. Specifically, it uses the Python spaCy library to parse the data and identify the meaning and interrelationships of the configuration items. The input is configuration data in JSON format, and the output is the parsed semantic information and relationship data. In this process, keywords within the data are extracted and their correlations are calculated.

[0316] Step 3:

[0317] The server identifies the scope of impact of configuration changes based on the analysis results. This involves performing calculations that evaluate how the changes will affect other devices by referencing relevant information in the configuration management database. The input is the analyzed semantic information and related data, and the output is the result of identifying the scope of impact.

[0318] Step 4:

[0319] The server generates prompt statements for use in the generated AI model. These prompt statements are in the form of specific questions to the AI, allowing it to examine in detail how the changed settings will affect the entire network. The input is the result of identifying the scope of impact, and the output is the generated prompt statements.

[0320] Step 5:

[0321] The terminal visually presents the analysis results and prompt messages to the user. Using a React Native UI, it displays settings and the scope of their changes as graphs and diagrams. Input consists of the generated prompt messages and impact information, while output is visualized data in a user-viewable format.

[0322] Step 6:

[0323] Based on the information provided through the terminal, users can make configuration changes or perform additional analyses as needed. This supports informed decision-making in network management, enabling efficient management. The input is visualized data, and the output is the user's configuration change actions.

[0324] 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.

[0325] This invention improves the accuracy of information presentation and the user experience by combining a network management system with an emotion engine that recognizes user emotions. Embodiments of this invention will be described below.

[0326] The server automatically retrieves configuration data from network devices and analyzes it using natural language processing technology. The retrieved data is used to identify the meaning and interrelationships of each configuration item, and explanatory text for each configuration item is generated based on the analysis results. Furthermore, a diagram visually representing the interrelationships of the settings is created and presented in a user-accessible format.

[0327] The emotion engine embedded in the server analyzes video and audio data acquired from the user's device to infer the user's emotional state. Based on this information, the server dynamically changes the content and format of the data it presents, adapting to provide information in the most acceptable way for the user. For example, if it is determined that the user is confused, the explanatory text may be made more detailed, and the visualized information may be simplified.

[0328] The timing of presenting important information is also adjusted based on the user's emotional state. For users in busy situations, it's possible to delay the presentation of information and show a summary that can be understood in a short time. The emotion engine also records user feedback, which is used as data to optimize how subsequent analysis results are presented.

[0329] Furthermore, the analysis results and user sentiment data will also be used as learning resources for work support and skill improvement. This will allow users to utilize the system as part of on-the-job training and improve their network management skills.

[0330] This system is expected to enable users to perform network management tasks more efficiently and effectively, leading to faster resolution of business challenges.

[0331] The following describes the processing flow.

[0332] Step 1:

[0333] The server scans all network devices connected to the network and collects the latest configuration data. The server saves this data to its internal storage in preparation for the next analysis step.

[0334] Step 2:

[0335] The server feeds the stored configuration data into a natural language processing engine to analyze the meaning of each configuration item. Here, the configuration values ​​and their interrelationships are identified and understood. As a result, the server generates explanatory text for each configuration.

[0336] Step 3:

[0337] When a user requests access to the current network settings through a connected device, the server creates a visual diagram based on the generated explanatory text. This information is sent to the user's device and presented in a way that is easy for the user to access and understand.

[0338] Step 4:

[0339] The device uses its built-in camera and microphone to collect user emotion data. The device sends the video and audio to a server for analysis by an emotion engine. This process determines the user's current emotional state.

[0340] Step 5:

[0341] The server dynamically adjusts the content and presentation of information based on the user's emotional state, as determined by the emotion engine. For example, if the server determines that the user is confused, it may include detailed explanatory text or simplify visual information to make it more intuitive.

[0342] Step 6:

[0343] The user reviews the information presented through the device and makes changes to their network settings based on their understanding. They update the settings as needed and send the changes to the server.

[0344] Step 7:

[0345] The server compares the old and new settings to identify the scope of the impact and automatically notifies relevant parties of this information. This allows affected users to respond quickly.

[0346] Step 8:

[0347] The server stores analysis results and user sentiment data in a database, creating a learning resource for on-the-job training and skill development. Users can utilize this resource to improve their work skills.

[0348] (Example 2)

[0349] 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".

[0350] Traditional network management systems acquire and analyze configuration data, but they lack sufficient measures to improve the user experience based on that data. In particular, they fail to present information in a way that considers user emotions, which can result in a lack of direct contribution to user understanding and skill improvement. Furthermore, the identification of the scope of impact of configuration changes and the sharing of information are inefficient, highlighting the need for more efficient management operations.

[0351] 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.

[0352] In this invention, the server includes means for automatically acquiring configuration data from network devices, means for analyzing the acquired configuration data using natural language processing technology to identify the meaning and relationships of each configuration item, and means for analyzing the user's emotions and dynamically adjusting the content and format of the presented information according to that state. This enables the presentation of optimal information in accordance with the user's emotions, improving comprehension and streamlining network management operations.

[0353] "Network equipment" is a general term for devices used to build or manage a network communication environment.

[0354] "Configuration data" refers to specific information and parameters used to control the operation and functions of network devices.

[0355] "Natural language processing technology" refers to the technology that enables computers to understand and interpret human language, making text analysis and language generation possible.

[0356] An "explanatory text" is a piece of writing that explains a particular topic in detail to make it easier to understand.

[0357] "Visualization" is a method of representing information and data in visual forms such as diagrams and graphs to aid understanding.

[0358] "Sentiment analysis" is the process of analyzing a user's emotional state and identifying it as a numerical value or category.

[0359] "Feedback" refers to the opinions and reactions that users provide to a system or process.

[0360] "Learning resources" refer to information and tools that users can use to improve their knowledge and skills.

[0361] This invention provides an advanced system to support network management, which has the function of automatically acquiring and analyzing configuration data from network devices. In this system, a server connects to network devices using a specific protocol (e.g., SNMP or SSH) and collects configuration data. This collected data is analyzed using Python or a natural language processing library (e.g., NLTK). As a result of the analysis, the meaning of each configuration item and their interrelationships are identified, and this is generated as explanatory text and visualization data for the configuration items.

[0362] Furthermore, the server is equipped with an emotion engine to analyze the user's emotional state. By using video and audio data collected through the terminal, it infers the user's emotions. Libraries such as OpenCV and Librosa are used for this purpose. Based on the results of this analysis, the server can dynamically adjust the content and format of the information it presents, providing information in a way that is appropriate to the user's emotional state.

[0363] For example, if a user is confused while setting up a new network device, the emotion engine detects this state and, based on the analysis results, elaborates on the explanatory text and simplifies the visualization to help the user quickly understand and resolve the problem. This system allows users to effectively manage their network and quickly resolve operational challenges.

[0364] Example of a prompt:

[0365] "Analyze the following configuration data and explain the meaning and interrelationships of the configuration items: {Configuration Data}"

[0366] To realize this invention, it is necessary to properly combine and operate the software and hardware described in the process above, which will enable users to efficiently perform specific network management tasks.

[0367] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0368] Step 1:

[0369] The server connects to network devices and automatically retrieves configuration data. The input is the IP address and connection information of the network device, and the output is the retrieved configuration data. Specifically, it uses SNMP or SSH protocols to collect configuration parameters from network devices.

[0370] Step 2:

[0371] The server analyzes the acquired configuration data using a natural language processing library. The input is configuration data obtained from network devices, and the output is information identifying the meaning and relationships of each configuration item. Text analysis is performed using Python and NLTK to clearly show how each configuration item relates to others. This analysis highlights important network configuration items.

[0372] Step 3:

[0373] The server generates explanatory text for the settings based on the analysis results and creates diagrams that visualize the interrelationships between the settings. The input is relationship information between items obtained from the analysis, and the output is explanatory text and visualized information. Specifically, it generates text using a generative AI model and creates diagrams using visualization libraries such as matplotlib.

[0374] Step 4:

[0375] The device transmits the user's video and audio data to an emotion analysis engine. Inputs are the user's facial expressions and voice information, while output is the user's emotional state. Data is collected in real time via a webcam and microphone and analyzed using OpenCV and Librosa. The analysis results are sent back to the server as feedback.

[0376] Step 5:

[0377] The server dynamically adjusts the content and format of the information presented based on the user's emotional state. The input is the user's emotional state obtained in step 4, and the output is the adjusted explanatory text and visualizations. For example, if the server determines that the user is having difficulty understanding, it will take measures such as making the explanatory text more detailed. The presented information is provided as content in HTML or PDF format.

[0378] Step 6:

[0379] The user provides feedback on the presented information, and the server records this feedback. The input is the user's feedback data, and the output is its record. This feedback is used to optimize information presentation methods and improve prompts in the generating AI model, and is stored as a learning resource for work support and skill improvement.

[0380] (Application Example 2)

[0381] 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 as the "terminal".

[0382] In modern network management, users are required to quickly understand and appropriately respond to large amounts of information. However, traditional systems fail to present this information optimally according to the user's situation and emotional state, making effective information understanding and management difficult. In particular, information presentation can burden users when they are busy or emotionally unstable. This challenge needs to be addressed.

[0383] 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.

[0384] In this invention, the server includes means for automatically acquiring configuration data from network devices, means for decomposing the acquired configuration data using natural language processing technology to determine the meaning and relationships of each configuration item, and means for analyzing the user's emotional state and dynamically adjusting the content and format of the information presented. This enables efficient and less burdensome network management by providing information in an optimal form according to the user's emotional state.

[0385] "Network equipment" refers to a group of devices that manage the transmission of information and data and optimize communication within a network.

[0386] "Configuration data" refers to data that contains information necessary to control and ensure the proper operation of network devices.

[0387] "Natural language processing technology" is a technology that allows computers to understand and process human language.

[0388] "Emotional state" refers to the type and intensity of psychological emotions a user is experiencing.

[0389] "Dynamic adjustment" means changing information and actions in real time according to the situation and conditions to optimize them.

[0390] "User" refers to an individual or organization that uses a system or device to acquire or process information.

[0391] "Information provision" refers to the act of presenting analyzed data and related knowledge to users.

[0392] "Efficient" means achieving the greatest possible result with minimal resources and time.

[0393] This invention is a system aimed at optimizing network management and has the ability to dynamically adjust information presentation according to the user's emotional state.

[0394] First, the server automatically retrieves configuration data from network devices. This configuration data contains information about the operation and performance of the network devices. The server analyzes the retrieved data using natural language processing technology to identify the meaning of each configuration item and their relationships. This streamlines the understanding and management of network settings.

[0395] Next, the emotion recognition engine installed on the server analyzes the audio and video data transmitted from the user's device in real time. This uses input devices such as a camera and microphone, as well as analysis software such as OpenCV and TensorFlow. Through this process, the user's emotional state is estimated.

[0396] Based on these analysis results, the server uses a generative AI model to adjust the content and format of the information presented. For example, if it is determined that the user is confused, it can use detailed explanatory text and simplify the visualization of the information. Furthermore, for important information, the timing of its presentation can be changed depending on the user's situation.

[0397] For example, if a user wants to obtain news or information at home, the emotion recognition engine will detect the user's fatigue or anxiety. The server will then simplify the content and provide only the necessary information. This allows the user to obtain the necessary information appropriately without feeling burdened.

[0398] User feedback and sentiment data are stored as learning material for improving the system's business support functions and technology. This data will be useful for improving future analysis methods and the quality of information presentation.

[0399] An example of a prompt for a generative AI model is, "If the user is tired, select three major news stories from today and summarize each in two to three sentences." In this way, the server provides information tailored to the user's mood and assists with network management tasks.

[0400] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0401] Step 1:

[0402] The server automatically retrieves configuration data from network devices. This process uses protocols such as HTTP and SNMP to access the devices and download the latest configuration information. The input is the configuration data from the network devices, and the output is the configuration data stored on the server. The server then prepares this data for analysis.

[0403] Step 2:

[0404] The server analyzes configuration data obtained using natural language processing (NLP) techniques. This analysis uses a natural language processing engine (e.g., spaCy) to identify the meaning and relationships of the configuration items. The input is the configuration data stored on the server, and the output is the analysis results showing the meaning and relationships of each configuration item. Based on the analysis results, the server generates a detailed configuration document and a diagram visualizing the interrelationships.

[0405] Step 3:

[0406] The server receives audio and video data transmitted from the user's device and analyzes it using an emotion recognition engine. The input data consists of the user's voice and video, and the output is a judgment result indicating the user's emotional state. Using OpenCV and TensorFlow, facial expressions are analyzed from the video, and the Google Cloud Speech-to-Text API is used to convert the audio data into text and perform emotion analysis.

[0407] Step 4:

[0408] The server uses a generative AI model to generate the most appropriate information presentation content and format for the user, based on the results of emotion recognition. The input is the user's emotional state and the analysis results, and the output is an information summary or presentation adapted to the emotion. A prompt sentence is sent to the generative AI (e.g., GPT-4) to obtain an appropriate information summary. Specifically, if the user is confused, a concise and easy-to-understand summary is selected.

[0409] Step 5:

[0410] The server delivers the generated information to the user's terminal, optimizing the timing of information presentation according to the user's state. Input consists of instructions regarding sentiment analysis and information presentation methods, while output is customized information displayed on the user's terminal. This allows users to receive necessary information without burden and effectively perform network management tasks.

[0411] 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.

[0412] 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.

[0413] 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.

[0414] [Third Embodiment]

[0415] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0416] 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.

[0417] 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).

[0418] 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.

[0419] 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.

[0420] 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).

[0421] 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.

[0422] 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.

[0423] 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.

[0424] 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.

[0425] 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.

[0426] 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".

[0427] This invention provides a system for streamlining the management of configuration data across multiple network devices and for quickly understanding the scope of impact during fault response and configuration changes. The following describes a specific embodiment of this system.

[0428] The server periodically or automatically retrieves and stores configuration data for all devices connected to the network, either on a regular basis or upon user request. The server analyzes the retrieved configuration data using natural language processing techniques to clarify the meaning and interrelationships of the configuration items. For example, if a new router is added to the network, the server analyzes the router's configuration and evaluates its impact on the existing network configuration.

[0429] Based on the analysis results, the server automatically generates detailed explanatory text for each setting item. Furthermore, it creates diagrams that visually represent the interrelationships and dependencies between settings. This allows users to intuitively understand the settings and their scope of impact through their terminal.

[0430] When a user makes a configuration change, the server immediately compares the old and new settings to identify the scope of the impact. This information is quickly shared with relevant parties to support appropriate countermeasures. For example, if a user changes the port settings of a network switch, the server identifies the impact of that change on other devices and notifies the user.

[0431] Furthermore, the server saves the analysis results and generated explanatory texts as learning resources. This information can be used by users for on-the-job training and continuous skill development, contributing to improved work performance.

[0432] Thus, the present invention provides a specific embodiment for improving the efficiency of network management while simultaneously enhancing the technical capabilities of those involved.

[0433] The following describes the processing flow.

[0434] Step 1:

[0435] The server detects each device connected to the network and prepares to collect configuration data. The server checks the connection information in the system management database to determine if it can access each device.

[0436] Step 2:

[0437] The server automatically retrieves the latest configuration data from accessible network devices and saves it to local storage. Since the configuration data may be formatted or encrypted, the server performs appropriate data conversion and decryption.

[0438] Step 3:

[0439] The server runs a natural language processing engine to analyze the acquired configuration data. Specifically, it extracts the key and value of each configuration item and uses an AI model to understand their meaning.

[0440] Step 4:

[0441] The server generates explanatory text for the configuration items based on the analysis results. Using a generative AI model, it creates explanatory text in natural language that is easy for users to understand and identifies interrelationships between related configuration items.

[0442] Step 5:

[0443] The server generates a diagram to visually represent interrelated configuration items. This diagram illustrates network configurations and dependencies, and visualizes the impact of changes on other settings.

[0444] Step 6:

[0445] Users can review the explanatory text and diagrams generated through their device to understand the settings and their scope of impact. Furthermore, users can modify the settings as needed.

[0446] Step 7:

[0447] When changes are made, the server compares the old and new settings to identify the scope of the impact. The identified information is notified to relevant parties in real time.

[0448] Step 8:

[0449] The server stores the analysis results and generated explanatory texts in a database, which is then organized as a learning resource. Users can utilize this information to acquire new skills and improve their abilities.

[0450] (Example 1)

[0451] 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."

[0452] In network management, efficiently analyzing large amounts of configuration information collected from multiple information devices and quickly and accurately understanding their relationships is challenging. Furthermore, there is a need for a timely method to evaluate the impact of configuration changes on the entire system and provide appropriate information to stakeholders. Additionally, establishing a system that utilizes this information as a learning resource and contributes to improving technical capabilities is another challenge.

[0453] 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.

[0454] In this invention, the server includes means for automatically acquiring configuration information from an information device, means for analyzing the acquired configuration information using language processing technology to identify the meaning and relationships of the configuration items, and means for generating explanatory content for the configuration items based on the analysis results and visualizing the interrelationships. This makes it possible to efficiently manage configuration information for the entire network, quickly assess the impact of changes, and provide appropriate information to stakeholders. Furthermore, by saving the analysis results as learning resources, it can also contribute to improving technical capabilities.

[0455] An "information device" refers to a device or system connected to a network that holds and manages configuration information.

[0456] "Configuration information" refers to a collection of data that specifically indicates the various parameters and operating conditions set in an information device.

[0457] "Language processing technology" refers to techniques for interpreting and analyzing natural language, aiming to convert complex information into a form that humans can understand.

[0458] "Analysis results" refer to the output of an analysis of the significance and relationships of configuration information obtained using language processing technology.

[0459] "Explanatory content" refers to text and diagrams that explain the details of the settings based on the analysis results, providing information in a way that is easy for users to understand.

[0460] "Interrelationship" is a concept that describes how configuration information within a network is related to and influences each other.

[0461] "Impact assessment" is the process of evaluating and confirming the potential impact that a configuration change may have on other information devices or the entire system.

[0462] "Learning resources" refer to a collection of information, including analyzed data and generated explanations, that is stored for use in knowledge improvement and technical training.

[0463] This invention is a system for improving the efficiency of network management by efficiently managing configuration information collected from multiple information devices, visualizing the analysis results, and utilizing them as learning resources. Specific embodiments of this system are described below.

[0464] 1. Hardware and software configuration

[0465] The server automatically retrieves configuration information from network-connected information devices. Protocols such as SSH and SNMP can be used for this retrieval. A program running on the server analyzes the configuration information using natural language processing techniques. Here, a generative AI model is used to identify the significance and relationships between configuration items. The analyzed information is stored in a database and used for subsequent processing. Furthermore, based on the analysis results, the server generates explanatory content and visualizes the interrelationships between settings.

[0466] 2. Specific Examples of Data Processing and Calculation

[0467] For example, if a user adds a new network switch, the server retrieves the switch's configuration information and analyzes its relationship to the existing network configuration. Based on this analysis, it evaluates the potential impact of the switch configuration changes on other devices and generates a detailed explanation. Furthermore, it utilizes a generative AI model to create visualizations and provides them to the user's terminal. This allows the user to intuitively understand the impact of the configuration changes.

[0468] 3. Utilization as a learning resource

[0469] The analysis results and generated explanations are stored as learning resources in a database on the server. Users can utilize this information to support their work and improve their technical skills. For example, in training new engineers, they can efficiently acquire the knowledge necessary to perform their jobs by referring to the analysis results of past configuration change cases and their scope of impact.

[0470] Example of a prompt

[0471] "We've added a new network device. Please analyze the impact this new device will have on the existing network configuration and generate a configuration explanation based on that. A visually easy-to-understand diagram would be helpful."

[0472] In this way, the system of the present invention reduces the complexity of network management, enables rapid assessment of risks associated with configuration changes, and allows for the provision of appropriate information to relevant parties.

[0473] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0474] Step 1:

[0475] Automatic retrieval of configuration information

[0476] The server automatically retrieves configuration information from all information devices connected to the network. The input is a connection request from each information device using its network protocol (e.g., SSH, SNMP), and the output is a collection of retrieved configuration information. The server stores the configuration information in a database, preparing it for use in the next processing step. This operation allows the server to maintain the latest network configuration in real time.

[0477] Step 2:

[0478] Configuration details analysis

[0479] The server analyzes the acquired configuration information using a generative AI model. The input is configuration information obtained from the database, and the output is the analysis results regarding the significance and relationships of the configuration items. Specifically, the server utilizes natural language processing techniques to identify the role each setting plays in the overall network. Through this analysis, the server gains a deeper understanding of the overall network configuration.

[0480] Step 3:

[0481] Generating explanatory content and visualized information

[0482] The server generates explanatory text for the configuration information based on the analysis results and visualizes the interrelationships. The input is the analysis results obtained in step 2, and the output is the explanatory text and visualization presented to the user. The server uses a generative AI model to create natural language and draw diagrams showing the relationships between settings. This allows the user to intuitively understand the impact of setting changes through their terminal.

[0483] Step 4:

[0484] Assessment and notification of impact

[0485] When a user changes a setting, the server immediately begins assessing the scope of the impact. The input is detailed information about the setting change made by the user, and the output is a list of the potential impacts that the change may have on other information devices and services. Specifically, the server compares the old and new settings and uses a generative AI model to evaluate the impact of the change. As a result, the server generates an evaluation report and promptly notifies the relevant parties.

[0486] Step 5:

[0487] Information storage as a learning resource

[0488] The server stores the analysis results and explanatory content as learning resources. The input is the results from steps 3 and 4, and the output is a database entry that can be used for technical improvement and work support. The server organizes this information and keeps it accessible for future reference and educational purposes. This operation allows users to learn from past cases and effectively deepen their knowledge of network management.

[0489] (Application Example 1)

[0490] 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."

[0491] Managing network device configuration data involves complex processes such as configuration changes and troubleshooting across multiple devices, requiring rapid and accurate assessment of the scope of impact. However, traditional methods often rely on manual processes for configuration management and impact assessment, which is inefficient. Furthermore, network administrators find it difficult to intuitively understand configuration data, and it is not fully utilized as a resource for improving technical skills. A new system is needed to address these challenges.

[0492] 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.

[0493] In this invention, the server includes means for automatically acquiring configuration data from network devices, means for analyzing the acquired configuration data using natural language processing technology to identify the meaning and relationships of each configuration item, and means for visually displaying the interrelationships of the analyzed configuration items and the scope of impact of changes on a mobile terminal. This enables network administrators to intuitively understand the relationships and scope of impact of settings and perform network management tasks efficiently.

[0494] "Network devices" refer to all equipment connected to a network for communication purposes, including routers, switches, and firewalls.

[0495] "Configuration data" refers to information used to control the operation of network devices, and includes IP addresses, routing information, policies, and more.

[0496] "Natural language processing technology" is a technique that uses computers to understand and analyze human language, and is used to extract the meaning and structure of text.

[0497] "Analysis" is the process of meticulously analyzing acquired data to clarify its meaning and relationships.

[0498] "Interrelationship" refers to the influence or relationship between multiple items or elements.

[0499] "Visualization" is the process of converting information and data into diagrams and graphs that are easy for humans to understand.

[0500] A "mobile terminal" refers to a portable computing device such as a smartphone or tablet.

[0501] A "generative artificial intelligence model" is a collection of machine learning algorithms that learn from large amounts of data and make autonomous decisions and predictions.

[0502] A "prompt sentence" refers to a sentence that is input to a generative AI model to prompt it to produce a specific output.

[0503] This invention is a system for streamlining network management and includes a function to automatically acquire configuration data from multiple network devices. The server collects data periodically or upon user request using a Python script and stores it in a PostgreSQL or MongoDB database. To analyze this data, the spaCy library in Python is used as a natural language processing technique to clarify the meaning and interrelationships of the configuration items.

[0504] The server uses the analysis results to generate input prompts that the AI ​​model can understand. These prompts allow the AI ​​model to perform complex analysis using cloud computing resources to identify the scope of impact. The generated information is visually presented to the mobile device through a user interface developed using React Native. This allows users to intuitively understand, in real time, the impact of network configuration changes on other devices.

[0505] A concrete example of this system could be used when adding a new network switch to a data center. When a user sends the new device's configuration to a server via a smartphone application, the server analyzes the impact of that configuration on the existing network configuration. The analysis results are displayed as a visual graph on the mobile device, allowing the user to instantly see the impact of the configuration change on other network devices. An example of an input prompt for the generated AI model might be, "Analyze how the configuration changes for the new router will affect the entire network."

[0506] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0507] Step 1:

[0508] The server automatically retrieves configuration data from network devices. During this process, it uses a RESTful API to pull the latest configuration information from the devices and receives the data in JSON format. The input is the network device's API endpoint, and the output is the retrieved configuration data.

[0509] Step 2:

[0510] The server applies natural language processing techniques to analyze the acquired configuration data. Specifically, it uses the Python spaCy library to parse the data and identify the meaning and interrelationships of the configuration items. The input is configuration data in JSON format, and the output is the parsed semantic information and relationship data. In this process, keywords within the data are extracted and their correlations are calculated.

[0511] Step 3:

[0512] The server identifies the scope of impact of configuration changes based on the analysis results. This involves performing calculations that evaluate how the changes will affect other devices by referencing relevant information in the configuration management database. The input is the analyzed semantic information and related data, and the output is the result of identifying the scope of impact.

[0513] Step 4:

[0514] The server generates prompt statements for use in the generated AI model. These prompt statements are in the form of specific questions to the AI, allowing it to examine in detail how the changed settings will affect the entire network. The input is the result of identifying the scope of impact, and the output is the generated prompt statements.

[0515] Step 5:

[0516] The terminal visually presents the analysis results and prompt messages to the user. Using a React Native UI, it displays settings and the scope of their changes as graphs and diagrams. Input consists of the generated prompt messages and impact information, while output is visualized data in a user-viewable format.

[0517] Step 6:

[0518] Based on the information provided through the terminal, users can make configuration changes or perform additional analyses as needed. This supports informed decision-making in network management, enabling efficient management. The input is visualized data, and the output is the user's configuration change actions.

[0519] 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.

[0520] This invention improves the accuracy of information presentation and the user experience by combining a network management system with an emotion engine that recognizes user emotions. Embodiments of this invention will be described below.

[0521] The server automatically retrieves configuration data from network devices and analyzes it using natural language processing technology. The retrieved data is used to identify the meaning and interrelationships of each configuration item, and explanatory text for each configuration item is generated based on the analysis results. Furthermore, a diagram visually representing the interrelationships of the settings is created and presented in a user-accessible format.

[0522] The emotion engine embedded in the server analyzes video and audio data acquired from the user's device to infer the user's emotional state. Based on this information, the server dynamically changes the content and format of the data it presents, adapting to provide information in the most acceptable way for the user. For example, if it is determined that the user is confused, the explanatory text may be made more detailed, and the visualized information may be simplified.

[0523] The timing of presenting important information is also adjusted based on the user's emotional state. For users in busy situations, it's possible to delay the presentation of information and show a summary that can be understood in a short time. The emotion engine also records user feedback, which is used as data to optimize how subsequent analysis results are presented.

[0524] Furthermore, the analysis results and user sentiment data will also be used as learning resources for work support and skill improvement. This will allow users to utilize the system as part of on-the-job training and improve their network management skills.

[0525] This system is expected to enable users to perform network management tasks more efficiently and effectively, leading to faster resolution of business challenges.

[0526] The following describes the processing flow.

[0527] Step 1:

[0528] The server scans all network devices connected to the network and collects the latest configuration data. The server saves this data to its internal storage in preparation for the next analysis step.

[0529] Step 2:

[0530] The server feeds the stored configuration data into a natural language processing engine to analyze the meaning of each configuration item. Here, the configuration values ​​and their interrelationships are identified and understood. As a result, the server generates explanatory text for each configuration.

[0531] Step 3:

[0532] When a user requests access to the current network settings through a connected device, the server creates a visual diagram based on the generated explanatory text. This information is sent to the user's device and presented in a way that is easy for the user to access and understand.

[0533] Step 4:

[0534] The device uses its built-in camera and microphone to collect user emotion data. The device sends the video and audio to a server for analysis by an emotion engine. This process determines the user's current emotional state.

[0535] Step 5:

[0536] The server dynamically adjusts the content and presentation of information based on the user's emotional state, as determined by the emotion engine. For example, if the server determines that the user is confused, it may include detailed explanatory text or simplify visual information to make it more intuitive.

[0537] Step 6:

[0538] The user reviews the information presented through the device and makes changes to their network settings based on their understanding. They update the settings as needed and send the changes to the server.

[0539] Step 7:

[0540] The server compares the old and new settings to identify the scope of the impact and automatically notifies relevant parties of this information. This allows affected users to respond quickly.

[0541] Step 8:

[0542] The server stores analysis results and user sentiment data in a database, creating a learning resource for on-the-job training and skill development. Users can utilize this resource to improve their work skills.

[0543] (Example 2)

[0544] 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."

[0545] Traditional network management systems acquire and analyze configuration data, but they lack sufficient measures to improve the user experience based on that data. In particular, they fail to present information in a way that considers user emotions, which can result in a lack of direct contribution to user understanding and skill improvement. Furthermore, the identification of the scope of impact of configuration changes and the sharing of information are inefficient, highlighting the need for more efficient management operations.

[0546] 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.

[0547] In this invention, the server includes means for automatically acquiring configuration data from network devices, means for analyzing the acquired configuration data using natural language processing technology to identify the meaning and relationships of each configuration item, and means for analyzing the user's emotions and dynamically adjusting the content and format of the presented information according to that state. This enables the presentation of optimal information in accordance with the user's emotions, improving comprehension and streamlining network management operations.

[0548] "Network equipment" is a general term for devices used to build or manage a network communication environment.

[0549] "Configuration data" refers to specific information and parameters used to control the operation and functions of network devices.

[0550] "Natural language processing technology" refers to the technology that enables computers to understand and interpret human language, making text analysis and language generation possible.

[0551] An "explanatory text" is a piece of writing that explains a particular topic in detail to make it easier to understand.

[0552] "Visualization" is a method of representing information and data in visual forms such as diagrams and graphs to aid understanding.

[0553] "Sentiment analysis" is the process of analyzing a user's emotional state and identifying it as a numerical value or category.

[0554] "Feedback" refers to the opinions and reactions that users provide to a system or process.

[0555] "Learning resources" refer to information and tools that users can use to improve their knowledge and skills.

[0556] This invention provides an advanced system to support network management, which has the function of automatically acquiring and analyzing configuration data from network devices. In this system, a server connects to network devices using a specific protocol (e.g., SNMP or SSH) and collects configuration data. This collected data is analyzed using Python or a natural language processing library (e.g., NLTK). As a result of the analysis, the meaning of each configuration item and their interrelationships are identified, and this is generated as explanatory text and visualization data for the configuration items.

[0557] Furthermore, the server is equipped with an emotion engine to analyze the user's emotional state. By using video and audio data collected through the terminal, it infers the user's emotions. Libraries such as OpenCV and Librosa are used for this purpose. Based on the results of this analysis, the server can dynamically adjust the content and format of the information it presents, providing information in a way that is appropriate to the user's emotional state.

[0558] For example, if a user is confused while setting up a new network device, the emotion engine detects this state and, based on the analysis results, elaborates on the explanatory text and simplifies the visualization to help the user quickly understand and resolve the problem. This system allows users to effectively manage their network and quickly resolve operational challenges.

[0559] Example of a prompt:

[0560] "Analyze the following configuration data and explain the meaning and interrelationships of the configuration items: {Configuration Data}"

[0561] To realize this invention, it is necessary to properly combine and operate the software and hardware described in the process above, which will enable users to efficiently perform specific network management tasks.

[0562] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0563] Step 1:

[0564] The server connects to network devices and automatically retrieves configuration data. The input is the IP address and connection information of the network device, and the output is the retrieved configuration data. Specifically, it uses SNMP or SSH protocols to collect configuration parameters from network devices.

[0565] Step 2:

[0566] The server analyzes the acquired configuration data using a natural language processing library. The input is configuration data obtained from network devices, and the output is information identifying the meaning and relationships of each configuration item. Text analysis is performed using Python and NLTK to clearly show how each configuration item relates to others. This analysis highlights important network configuration items.

[0567] Step 3:

[0568] The server generates explanatory text for the settings based on the analysis results and creates diagrams that visualize the interrelationships between the settings. The input is relationship information between items obtained from the analysis, and the output is explanatory text and visualized information. Specifically, it generates text using a generative AI model and creates diagrams using visualization libraries such as matplotlib.

[0569] Step 4:

[0570] The device transmits the user's video and audio data to an emotion analysis engine. Inputs are the user's facial expressions and voice information, while output is the user's emotional state. Data is collected in real time via a webcam and microphone and analyzed using OpenCV and Librosa. The analysis results are sent back to the server as feedback.

[0571] Step 5:

[0572] The server dynamically adjusts the content and format of the information presented based on the user's emotional state. The input is the user's emotional state obtained in step 4, and the output is the adjusted explanatory text and visualizations. For example, if the server determines that the user is having difficulty understanding, it will take measures such as making the explanatory text more detailed. The presented information is provided as content in HTML or PDF format.

[0573] Step 6:

[0574] The user provides feedback on the presented information, and the server records this feedback. The input is the user's feedback data, and the output is its record. This feedback is used to optimize information presentation methods and improve prompts in the generating AI model, and is stored as a learning resource for work support and skill improvement.

[0575] (Application Example 2)

[0576] 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."

[0577] In modern network management, users are required to quickly understand and appropriately respond to large amounts of information. However, traditional systems fail to present this information optimally according to the user's situation and emotional state, making effective information understanding and management difficult. In particular, information presentation can burden users when they are busy or emotionally unstable. This challenge needs to be addressed.

[0578] 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.

[0579] In this invention, the server includes means for automatically acquiring configuration data from network devices, means for decomposing the acquired configuration data using natural language processing technology to determine the meaning and relationships of each configuration item, and means for analyzing the user's emotional state and dynamically adjusting the content and format of the information presented. This enables efficient and less burdensome network management by providing information in an optimal form according to the user's emotional state.

[0580] "Network equipment" refers to a group of devices that manage the transmission of information and data and optimize communication within a network.

[0581] "Configuration data" refers to data that contains information necessary to control and ensure the proper operation of network devices.

[0582] "Natural language processing technology" is a technology that allows computers to understand and process human language.

[0583] "Emotional state" refers to the type and intensity of psychological emotions a user is experiencing.

[0584] "Dynamic adjustment" means changing information and actions in real time according to the situation and conditions to optimize them.

[0585] "User" refers to an individual or organization that uses a system or device to acquire or process information.

[0586] "Information provision" refers to the act of presenting analyzed data and related knowledge to users.

[0587] "Efficient" means achieving the greatest possible result with minimal resources and time.

[0588] This invention is a system aimed at optimizing network management and has the ability to dynamically adjust information presentation according to the user's emotional state.

[0589] First, the server automatically retrieves configuration data from network devices. This configuration data contains information about the operation and performance of the network devices. The server analyzes the retrieved data using natural language processing technology to identify the meaning of each configuration item and their relationships. This streamlines the understanding and management of network settings.

[0590] Next, the emotion recognition engine installed on the server analyzes the audio and video data transmitted from the user's device in real time. This uses input devices such as a camera and microphone, as well as analysis software such as OpenCV and TensorFlow. Through this process, the user's emotional state is estimated.

[0591] Based on these analysis results, the server uses a generative AI model to adjust the content and format of the information presented. For example, if it is determined that the user is confused, it can use detailed explanatory text and simplify the visualization of the information. Furthermore, for important information, the timing of its presentation can be changed depending on the user's situation.

[0592] For example, if a user wants to obtain news or information at home, the emotion recognition engine will detect the user's fatigue or anxiety. The server will then simplify the content and provide only the necessary information. This allows the user to obtain the necessary information appropriately without feeling burdened.

[0593] User feedback and sentiment data are stored as learning material for improving the system's business support functions and technology. This data will be useful for improving future analysis methods and the quality of information presentation.

[0594] An example of a prompt for a generative AI model is, "If the user is tired, select three major news stories from today and summarize each in two to three sentences." In this way, the server provides information tailored to the user's mood and assists with network management tasks.

[0595] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0596] Step 1:

[0597] The server automatically retrieves configuration data from network devices. This process uses protocols such as HTTP and SNMP to access the devices and download the latest configuration information. The input is the configuration data from the network devices, and the output is the configuration data stored on the server. The server then prepares this data for analysis.

[0598] Step 2:

[0599] The server analyzes configuration data obtained using natural language processing (NLP) techniques. This analysis uses a natural language processing engine (e.g., spaCy) to identify the meaning and relationships of the configuration items. The input is the configuration data stored on the server, and the output is the analysis results showing the meaning and relationships of each configuration item. Based on the analysis results, the server generates a detailed configuration document and a diagram visualizing the interrelationships.

[0600] Step 3:

[0601] The server receives audio and video data transmitted from the user's device and analyzes it using an emotion recognition engine. The input data consists of the user's voice and video, and the output is a judgment result indicating the user's emotional state. Using OpenCV and TensorFlow, facial expressions are analyzed from the video, and the Google Cloud Speech-to-Text API is used to convert the audio data into text and perform emotion analysis.

[0602] Step 4:

[0603] The server uses a generative AI model to generate the most appropriate information presentation content and format for the user, based on the results of emotion recognition. The input is the user's emotional state and the analysis results, and the output is an information summary or presentation adapted to the emotion. A prompt sentence is sent to the generative AI (e.g., GPT-4) to obtain an appropriate information summary. Specifically, if the user is confused, a concise and easy-to-understand summary is selected.

[0604] Step 5:

[0605] The server delivers the generated information to the user's terminal, optimizing the timing of information presentation according to the user's state. Input consists of instructions regarding sentiment analysis and information presentation methods, while output is customized information displayed on the user's terminal. This allows users to receive necessary information without burden and effectively perform network management tasks.

[0606] 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.

[0607] 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.

[0608] 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.

[0609] [Fourth Embodiment]

[0610] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0611] 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.

[0612] 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).

[0613] 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.

[0614] 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.

[0615] 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).

[0616] 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.

[0617] 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.

[0618] 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.

[0619] 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.

[0620] 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.

[0621] 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.

[0622] 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".

[0623] This invention provides a system for streamlining the management of configuration data across multiple network devices and for quickly understanding the scope of impact during fault response and configuration changes. The following describes a specific embodiment of this system.

[0624] The server periodically or automatically retrieves and stores configuration data for all devices connected to the network, either on a regular basis or upon user request. The server analyzes the retrieved configuration data using natural language processing techniques to clarify the meaning and interrelationships of the configuration items. For example, if a new router is added to the network, the server analyzes the router's configuration and evaluates its impact on the existing network configuration.

[0625] Based on the analysis results, the server automatically generates detailed explanatory text for each setting item. Furthermore, it creates diagrams that visually represent the interrelationships and dependencies between settings. This allows users to intuitively understand the settings and their scope of impact through their terminal.

[0626] When a user makes a configuration change, the server immediately compares the old and new settings to identify the scope of the impact. This information is quickly shared with relevant parties to support appropriate countermeasures. For example, if a user changes the port settings of a network switch, the server identifies the impact of that change on other devices and notifies the user.

[0627] Furthermore, the server saves the analysis results and generated explanatory texts as learning resources. This information can be used by users for on-the-job training and continuous skill development, contributing to improved work performance.

[0628] Thus, the present invention provides a specific embodiment for improving the efficiency of network management while simultaneously enhancing the technical capabilities of those involved.

[0629] The following describes the processing flow.

[0630] Step 1:

[0631] The server detects each device connected to the network and prepares to collect configuration data. The server checks the connection information in the system management database to determine if it can access each device.

[0632] Step 2:

[0633] The server automatically retrieves the latest configuration data from accessible network devices and saves it to local storage. Since the configuration data may be formatted or encrypted, the server performs appropriate data conversion and decryption.

[0634] Step 3:

[0635] The server runs a natural language processing engine to analyze the acquired configuration data. Specifically, it extracts the key and value of each configuration item and uses an AI model to understand their meaning.

[0636] Step 4:

[0637] The server generates explanatory text for the configuration items based on the analysis results. Using a generative AI model, it creates explanatory text in natural language that is easy for users to understand and identifies interrelationships between related configuration items.

[0638] Step 5:

[0639] The server generates a diagram to visually represent interrelated configuration items. This diagram illustrates network configurations and dependencies, and visualizes the impact of changes on other settings.

[0640] Step 6:

[0641] Users can review the explanatory text and diagrams generated through their device to understand the settings and their scope of impact. Furthermore, users can modify the settings as needed.

[0642] Step 7:

[0643] When changes are made, the server compares the old and new settings to identify the scope of the impact. The identified information is notified to relevant parties in real time.

[0644] Step 8:

[0645] The server stores the analysis results and generated explanatory texts in a database, which is then organized as a learning resource. Users can utilize this information to acquire new skills and improve their abilities.

[0646] (Example 1)

[0647] 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".

[0648] In network management, efficiently analyzing large amounts of configuration information collected from multiple information devices and quickly and accurately understanding their relationships is challenging. Furthermore, there is a need for a timely method to evaluate the impact of configuration changes on the entire system and provide appropriate information to stakeholders. Additionally, establishing a system that utilizes this information as a learning resource and contributes to improving technical capabilities is another challenge.

[0649] 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.

[0650] In this invention, the server includes means for automatically acquiring configuration information from an information device, means for analyzing the acquired configuration information using language processing technology to identify the meaning and relationships of the configuration items, and means for generating explanatory content for the configuration items based on the analysis results and visualizing the interrelationships. This makes it possible to efficiently manage configuration information for the entire network, quickly assess the impact of changes, and provide appropriate information to stakeholders. Furthermore, by saving the analysis results as learning resources, it can also contribute to improving technical capabilities.

[0651] An "information device" refers to a device or system connected to a network that holds and manages configuration information.

[0652] "Configuration information" refers to a collection of data that specifically indicates the various parameters and operating conditions set in an information device.

[0653] "Language processing technology" refers to techniques for interpreting and analyzing natural language, aiming to convert complex information into a form that humans can understand.

[0654] "Analysis results" refer to the output of an analysis of the significance and relationships of configuration information obtained using language processing technology.

[0655] "Explanatory content" refers to text and diagrams that explain the details of the settings based on the analysis results, providing information in a way that is easy for users to understand.

[0656] "Interrelationship" is a concept that describes how configuration information within a network is related to and influences each other.

[0657] "Impact assessment" is the process of evaluating and confirming the potential impact that a configuration change may have on other information devices or the entire system.

[0658] "Learning resources" refer to a collection of information, including analyzed data and generated explanations, that is stored for use in knowledge improvement and technical training.

[0659] This invention is a system for improving the efficiency of network management by efficiently managing configuration information collected from multiple information devices, visualizing the analysis results, and utilizing them as learning resources. Specific embodiments of this system are described below.

[0660] 1. Hardware and software configuration

[0661] The server automatically retrieves configuration information from network-connected information devices. Protocols such as SSH and SNMP can be used for this retrieval. A program running on the server analyzes the configuration information using natural language processing techniques. Here, a generative AI model is used to identify the significance and relationships between configuration items. The analyzed information is stored in a database and used for subsequent processing. Furthermore, based on the analysis results, the server generates explanatory content and visualizes the interrelationships between settings.

[0662] 2. Specific Examples of Data Processing and Calculation

[0663] For example, if a user adds a new network switch, the server retrieves the switch's configuration information and analyzes its relationship to the existing network configuration. Based on this analysis, it evaluates the potential impact of the switch configuration changes on other devices and generates a detailed explanation. Furthermore, it utilizes a generative AI model to create visualizations and provides them to the user's terminal. This allows the user to intuitively understand the impact of the configuration changes.

[0664] 3. Utilization as a learning resource

[0665] The analysis results and generated explanations are stored as learning resources in a database on the server. Users can utilize this information to support their work and improve their technical skills. For example, in training new engineers, they can efficiently acquire the knowledge necessary to perform their jobs by referring to the analysis results of past configuration change cases and their scope of impact.

[0666] Example of a prompt

[0667] "We've added a new network device. Please analyze the impact this new device will have on the existing network configuration and generate a configuration explanation based on that. A visually easy-to-understand diagram would be helpful."

[0668] In this way, the system of the present invention reduces the complexity of network management, enables rapid assessment of risks associated with configuration changes, and allows for the provision of appropriate information to relevant parties.

[0669] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0670] Step 1:

[0671] Automatic retrieval of configuration information

[0672] The server automatically retrieves configuration information from all information devices connected to the network. The input is a connection request from each information device using its network protocol (e.g., SSH, SNMP), and the output is a collection of retrieved configuration information. The server stores the configuration information in a database, preparing it for use in the next processing step. This operation allows the server to maintain the latest network configuration in real time.

[0673] Step 2:

[0674] Configuration details analysis

[0675] The server analyzes the acquired configuration information using a generative AI model. The input is configuration information obtained from the database, and the output is the analysis results regarding the significance and relationships of the configuration items. Specifically, the server utilizes natural language processing techniques to identify the role each setting plays in the overall network. Through this analysis, the server gains a deeper understanding of the overall network configuration.

[0676] Step 3:

[0677] Generating explanatory content and visualized information

[0678] The server generates explanatory text for the configuration information based on the analysis results and visualizes the interrelationships. The input is the analysis results obtained in step 2, and the output is the explanatory text and visualization presented to the user. The server uses a generative AI model to create natural language and draw diagrams showing the relationships between settings. This allows the user to intuitively understand the impact of setting changes through their terminal.

[0679] Step 4:

[0680] Assessment and notification of impact

[0681] When a user changes a setting, the server immediately begins assessing the scope of the impact. The input is detailed information about the setting change made by the user, and the output is a list of the potential impacts that the change may have on other information devices and services. Specifically, the server compares the old and new settings and uses a generative AI model to evaluate the impact of the change. As a result, the server generates an evaluation report and promptly notifies the relevant parties.

[0682] Step 5:

[0683] Information storage as a learning resource

[0684] The server stores the analysis results and explanatory content as learning resources. The input is the results from steps 3 and 4, and the output is a database entry that can be used for technical improvement and work support. The server organizes this information and keeps it accessible for future reference and educational purposes. This operation allows users to learn from past cases and effectively deepen their knowledge of network management.

[0685] (Application Example 1)

[0686] 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".

[0687] Managing network device configuration data involves complex processes such as configuration changes and troubleshooting across multiple devices, requiring rapid and accurate assessment of the scope of impact. However, traditional methods often rely on manual processes for configuration management and impact assessment, which is inefficient. Furthermore, network administrators find it difficult to intuitively understand configuration data, and it is not fully utilized as a resource for improving technical skills. A new system is needed to address these challenges.

[0688] 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.

[0689] In this invention, the server includes means for automatically acquiring configuration data from network devices, means for analyzing the acquired configuration data using natural language processing technology to identify the meaning and relationships of each configuration item, and means for visually displaying the interrelationships of the analyzed configuration items and the scope of impact of changes on a mobile terminal. This enables network administrators to intuitively understand the relationships and scope of impact of settings and perform network management tasks efficiently.

[0690] "Network devices" refer to all equipment connected to a network for communication purposes, including routers, switches, and firewalls.

[0691] "Configuration data" refers to information used to control the operation of network devices, and includes IP addresses, routing information, policies, and more.

[0692] "Natural language processing technology" is a technique that uses computers to understand and analyze human language, and is used to extract the meaning and structure of text.

[0693] "Analysis" is the process of meticulously analyzing acquired data to clarify its meaning and relationships.

[0694] "Interrelationship" refers to the influence or relationship between multiple items or elements.

[0695] "Visualization" is the process of converting information and data into diagrams and graphs that are easy for humans to understand.

[0696] A "mobile terminal" refers to a portable computing device such as a smartphone or tablet.

[0697] A "generative artificial intelligence model" is a collection of machine learning algorithms that learn from large amounts of data and make autonomous decisions and predictions.

[0698] A "prompt sentence" refers to a sentence that is input to a generative AI model to prompt it to produce a specific output.

[0699] This invention is a system for streamlining network management and includes a function to automatically acquire configuration data from multiple network devices. The server collects data periodically or upon user request using a Python script and stores it in a PostgreSQL or MongoDB database. To analyze this data, the spaCy library in Python is used as a natural language processing technique to clarify the meaning and interrelationships of the configuration items.

[0700] The server uses the analysis results to generate input prompts that the AI ​​model can understand. These prompts allow the AI ​​model to perform complex analysis using cloud computing resources to identify the scope of impact. The generated information is visually presented to the mobile device through a user interface developed using React Native. This allows users to intuitively understand, in real time, the impact of network configuration changes on other devices.

[0701] A concrete example of this system could be used when adding a new network switch to a data center. When a user sends the new device's configuration to a server via a smartphone application, the server analyzes the impact of that configuration on the existing network configuration. The analysis results are displayed as a visual graph on the mobile device, allowing the user to instantly see the impact of the configuration change on other network devices. An example of an input prompt for the generated AI model might be, "Analyze how the configuration changes for the new router will affect the entire network."

[0702] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0703] Step 1:

[0704] The server automatically retrieves configuration data from network devices. During this process, it uses a RESTful API to pull the latest configuration information from the devices and receives the data in JSON format. The input is the network device's API endpoint, and the output is the retrieved configuration data.

[0705] Step 2:

[0706] The server applies natural language processing techniques to analyze the acquired configuration data. Specifically, it uses the Python spaCy library to parse the data and identify the meaning and interrelationships of the configuration items. The input is configuration data in JSON format, and the output is the parsed semantic information and relationship data. In this process, keywords within the data are extracted and their correlations are calculated.

[0707] Step 3:

[0708] The server identifies the scope of impact of configuration changes based on the analysis results. This involves performing calculations that evaluate how the changes will affect other devices by referencing relevant information in the configuration management database. The input is the analyzed semantic information and related data, and the output is the result of identifying the scope of impact.

[0709] Step 4:

[0710] The server generates prompt statements for use in the generated AI model. These prompt statements are in the form of specific questions to the AI, allowing it to examine in detail how the changed settings will affect the entire network. The input is the result of identifying the scope of impact, and the output is the generated prompt statements.

[0711] Step 5:

[0712] The terminal visually presents the analysis results and prompt messages to the user. Using a React Native UI, it displays settings and the scope of their changes as graphs and diagrams. Input consists of the generated prompt messages and impact information, while output is visualized data in a user-viewable format.

[0713] Step 6:

[0714] Based on the information provided through the terminal, users can make configuration changes or perform additional analyses as needed. This supports informed decision-making in network management, enabling efficient management. The input is visualized data, and the output is the user's configuration change actions.

[0715] 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.

[0716] This invention improves the accuracy of information presentation and the user experience by combining a network management system with an emotion engine that recognizes user emotions. Embodiments of this invention will be described below.

[0717] The server automatically retrieves configuration data from network devices and analyzes it using natural language processing technology. The retrieved data is used to identify the meaning and interrelationships of each configuration item, and explanatory text for each configuration item is generated based on the analysis results. Furthermore, a diagram visually representing the interrelationships of the settings is created and presented in a user-accessible format.

[0718] The emotion engine embedded in the server analyzes video and audio data acquired from the user's device to infer the user's emotional state. Based on this information, the server dynamically changes the content and format of the data it presents, adapting to provide information in the most acceptable way for the user. For example, if it is determined that the user is confused, the explanatory text may be made more detailed, and the visualized information may be simplified.

[0719] The timing of presenting important information is also adjusted based on the user's emotional state. For users in busy situations, it's possible to delay the presentation of information and show a summary that can be understood in a short time. The emotion engine also records user feedback, which is used as data to optimize how subsequent analysis results are presented.

[0720] Furthermore, the analysis results and user sentiment data will also be used as learning resources for work support and skill improvement. This will allow users to utilize the system as part of on-the-job training and improve their network management skills.

[0721] This system is expected to enable users to perform network management tasks more efficiently and effectively, leading to faster resolution of business challenges.

[0722] The following describes the processing flow.

[0723] Step 1:

[0724] The server scans all network devices connected to the network and collects the latest configuration data. The server saves this data to its internal storage in preparation for the next analysis step.

[0725] Step 2:

[0726] The server feeds the stored configuration data into a natural language processing engine to analyze the meaning of each configuration item. Here, the configuration values ​​and their interrelationships are identified and understood. As a result, the server generates explanatory text for each configuration.

[0727] Step 3:

[0728] When a user requests access to the current network settings through a connected device, the server creates a visual diagram based on the generated explanatory text. This information is sent to the user's device and presented in a way that is easy for the user to access and understand.

[0729] Step 4:

[0730] The device uses its built-in camera and microphone to collect user emotion data. The device sends the video and audio to a server for analysis by an emotion engine. This process determines the user's current emotional state.

[0731] Step 5:

[0732] The server dynamically adjusts the content and presentation of information based on the user's emotional state, as determined by the emotion engine. For example, if the server determines that the user is confused, it may include detailed explanatory text or simplify visual information to make it more intuitive.

[0733] Step 6:

[0734] The user reviews the information presented through the device and makes changes to their network settings based on their understanding. They update the settings as needed and send the changes to the server.

[0735] Step 7:

[0736] The server compares the old and new settings to identify the scope of the impact and automatically notifies relevant parties of this information. This allows affected users to respond quickly.

[0737] Step 8:

[0738] The server stores analysis results and user sentiment data in a database, creating a learning resource for on-the-job training and skill development. Users can utilize this resource to improve their work skills.

[0739] (Example 2)

[0740] 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".

[0741] Traditional network management systems acquire and analyze configuration data, but they lack sufficient measures to improve the user experience based on that data. In particular, they fail to present information in a way that considers user emotions, which can result in a lack of direct contribution to user understanding and skill improvement. Furthermore, the identification of the scope of impact of configuration changes and the sharing of information are inefficient, highlighting the need for more efficient management operations.

[0742] 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.

[0743] In this invention, the server includes means for automatically acquiring configuration data from network devices, means for analyzing the acquired configuration data using natural language processing technology to identify the meaning and relationships of each configuration item, and means for analyzing the user's emotions and dynamically adjusting the content and format of the presented information according to that state. This enables the presentation of optimal information in accordance with the user's emotions, improving comprehension and streamlining network management operations.

[0744] "Network equipment" is a general term for devices used to build or manage a network communication environment.

[0745] "Configuration data" refers to specific information and parameters used to control the operation and functions of network devices.

[0746] "Natural language processing technology" refers to the technology that enables computers to understand and interpret human language, making text analysis and language generation possible.

[0747] An "explanatory text" is a piece of writing that explains a particular topic in detail to make it easier to understand.

[0748] "Visualization" is a method of representing information and data in visual forms such as diagrams and graphs to aid understanding.

[0749] "Sentiment analysis" is the process of analyzing a user's emotional state and identifying it as a numerical value or category.

[0750] "Feedback" refers to the opinions and reactions that users provide to a system or process.

[0751] "Learning resources" refer to information and tools that users can use to improve their knowledge and skills.

[0752] This invention provides an advanced system to support network management, which has the function of automatically acquiring and analyzing configuration data from network devices. In this system, a server connects to network devices using a specific protocol (e.g., SNMP or SSH) and collects configuration data. This collected data is analyzed using Python or a natural language processing library (e.g., NLTK). As a result of the analysis, the meaning of each configuration item and their interrelationships are identified, and this is generated as explanatory text and visualization data for the configuration items.

[0753] Furthermore, the server is equipped with an emotion engine to analyze the user's emotional state. By using video and audio data collected through the terminal, it infers the user's emotions. Libraries such as OpenCV and Librosa are used for this purpose. Based on the results of this analysis, the server can dynamically adjust the content and format of the information it presents, providing information in a way that is appropriate to the user's emotional state.

[0754] For example, if a user is confused while setting up a new network device, the emotion engine detects this state and, based on the analysis results, elaborates on the explanatory text and simplifies the visualization to help the user quickly understand and resolve the problem. This system allows users to effectively manage their network and quickly resolve operational challenges.

[0755] Example of a prompt:

[0756] "Analyze the following configuration data and explain the meaning and interrelationships of the configuration items: {Configuration Data}"

[0757] To realize this invention, it is necessary to properly combine and operate the software and hardware described in the process above, which will enable users to efficiently perform specific network management tasks.

[0758] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0759] Step 1:

[0760] The server connects to network devices and automatically retrieves configuration data. The input is the IP address and connection information of the network device, and the output is the retrieved configuration data. Specifically, it uses SNMP or SSH protocols to collect configuration parameters from network devices.

[0761] Step 2:

[0762] The server analyzes the acquired configuration data using a natural language processing library. The input is configuration data obtained from network devices, and the output is information identifying the meaning and relationships of each configuration item. Text analysis is performed using Python and NLTK to clearly show how each configuration item relates to others. This analysis highlights important network configuration items.

[0763] Step 3:

[0764] The server generates explanatory text for the settings based on the analysis results and creates diagrams that visualize the interrelationships between the settings. The input is relationship information between items obtained from the analysis, and the output is explanatory text and visualized information. Specifically, it generates text using a generative AI model and creates diagrams using visualization libraries such as matplotlib.

[0765] Step 4:

[0766] The device transmits the user's video and audio data to an emotion analysis engine. Inputs are the user's facial expressions and voice information, while output is the user's emotional state. Data is collected in real time via a webcam and microphone and analyzed using OpenCV and Librosa. The analysis results are sent back to the server as feedback.

[0767] Step 5:

[0768] The server dynamically adjusts the content and format of the information presented based on the user's emotional state. The input is the user's emotional state obtained in step 4, and the output is the adjusted explanatory text and visualizations. For example, if the server determines that the user is having difficulty understanding, it will take measures such as making the explanatory text more detailed. The presented information is provided as content in HTML or PDF format.

[0769] Step 6:

[0770] The user provides feedback on the presented information, and the server records this feedback. The input is the user's feedback data, and the output is its record. This feedback is used to optimize information presentation methods and improve prompts in the generating AI model, and is stored as a learning resource for work support and skill improvement.

[0771] (Application Example 2)

[0772] 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".

[0773] In modern network management, users are required to quickly understand and appropriately respond to large amounts of information. However, traditional systems fail to present this information optimally according to the user's situation and emotional state, making effective information understanding and management difficult. In particular, information presentation can burden users when they are busy or emotionally unstable. This challenge needs to be addressed.

[0774] 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.

[0775] In this invention, the server includes means for automatically acquiring configuration data from network devices, means for decomposing the acquired configuration data using natural language processing technology to determine the meaning and relationships of each configuration item, and means for analyzing the user's emotional state and dynamically adjusting the content and format of the information presented. This enables efficient and less burdensome network management by providing information in an optimal form according to the user's emotional state.

[0776] "Network equipment" refers to a group of devices that manage the transmission of information and data and optimize communication within a network.

[0777] "Configuration data" refers to data that contains information necessary to control and ensure the proper operation of network devices.

[0778] "Natural language processing technology" is a technology that allows computers to understand and process human language.

[0779] "Emotional state" refers to the type and intensity of psychological emotions a user is experiencing.

[0780] "Dynamic adjustment" means changing information and actions in real time according to the situation and conditions to optimize them.

[0781] "User" refers to an individual or organization that uses a system or device to acquire or process information.

[0782] "Information provision" refers to the act of presenting analyzed data and related knowledge to users.

[0783] "Efficient" means achieving the greatest possible result with minimal resources and time.

[0784] This invention is a system aimed at optimizing network management and has the ability to dynamically adjust information presentation according to the user's emotional state.

[0785] First, the server automatically retrieves configuration data from network devices. This configuration data contains information about the operation and performance of the network devices. The server analyzes the retrieved data using natural language processing technology to identify the meaning of each configuration item and their relationships. This streamlines the understanding and management of network settings.

[0786] Next, the emotion recognition engine installed on the server analyzes the audio and video data transmitted from the user's device in real time. This uses input devices such as a camera and microphone, as well as analysis software such as OpenCV and TensorFlow. Through this process, the user's emotional state is estimated.

[0787] Based on these analysis results, the server uses a generative AI model to adjust the content and format of the information presented. For example, if it is determined that the user is confused, it can use detailed explanatory text and simplify the visualization of the information. Furthermore, for important information, the timing of its presentation can be changed depending on the user's situation.

[0788] For example, if a user wants to obtain news or information at home, the emotion recognition engine will detect the user's fatigue or anxiety. The server will then simplify the content and provide only the necessary information. This allows the user to obtain the necessary information appropriately without feeling burdened.

[0789] User feedback and sentiment data are stored as learning material for improving the system's business support functions and technology. This data will be useful for improving future analysis methods and the quality of information presentation.

[0790] An example of a prompt for a generative AI model is, "If the user is tired, select three major news stories from today and summarize each in two to three sentences." In this way, the server provides information tailored to the user's mood and assists with network management tasks.

[0791] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0792] Step 1:

[0793] The server automatically retrieves configuration data from network devices. This process uses protocols such as HTTP and SNMP to access the devices and download the latest configuration information. The input is the configuration data from the network devices, and the output is the configuration data stored on the server. The server then prepares this data for analysis.

[0794] Step 2:

[0795] The server analyzes configuration data obtained using natural language processing (NLP) techniques. This analysis uses a natural language processing engine (e.g., spaCy) to identify the meaning and relationships of the configuration items. The input is the configuration data stored on the server, and the output is the analysis results showing the meaning and relationships of each configuration item. Based on the analysis results, the server generates a detailed configuration document and a diagram visualizing the interrelationships.

[0796] Step 3:

[0797] The server receives audio and video data transmitted from the user's device and analyzes it using an emotion recognition engine. The input data consists of the user's voice and video, and the output is a judgment result indicating the user's emotional state. Using OpenCV and TensorFlow, facial expressions are analyzed from the video, and the Google Cloud Speech-to-Text API is used to convert the audio data into text and perform emotion analysis.

[0798] Step 4:

[0799] The server uses a generative AI model to generate the most appropriate information presentation content and format for the user, based on the results of emotion recognition. The input is the user's emotional state and the analysis results, and the output is an information summary or presentation adapted to the emotion. A prompt sentence is sent to the generative AI (e.g., GPT-4) to obtain an appropriate information summary. Specifically, if the user is confused, a concise and easy-to-understand summary is selected.

[0800] Step 5:

[0801] The server delivers the generated information to the user's terminal, optimizing the timing of information presentation according to the user's state. Input consists of instructions regarding sentiment analysis and information presentation methods, while output is customized information displayed on the user's terminal. This allows users to receive necessary information without burden and effectively perform network management tasks.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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."

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] The following is further disclosed regarding the embodiments described above.

[0824] (Claim 1)

[0825] A means of automatically acquiring configuration data from network devices,

[0826] A means for analyzing acquired configuration data using natural language processing technology to identify the meaning and relationships of each configuration item,

[0827] Based on the analysis results, a means is provided to generate explanatory text for the setting items and to visualize the interrelationships between the settings.

[0828] A means of presenting the generated information in a format accessible to the user,

[0829] A means to identify the scope of impact when configuration changes are made and to quickly share that information with relevant parties,

[0830] A means to save the analysis results as a learning resource and utilize them for work support and skill improvement,

[0831] A system that includes this.

[0832] (Claim 2)

[0833] The system according to claim 1, comprising means for automatically creating a setting change history by comparing the old and new versions of acquired setting data.

[0834] (Claim 3)

[0835] The system according to claim 1, comprising means for providing generated explanatory text and related visualization information to the user's terminal in real time.

[0836] "Example 1"

[0837] (Claim 1)

[0838] A means for automatically acquiring configuration information from an information device,

[0839] A means for analyzing acquired configuration information using language processing technology to identify the significance and relationships of each configuration item,

[0840] Based on the analysis results, a means is provided to generate explanatory content for the setting items and to visualize the interrelationships between the settings.

[0841] A means of presenting the generated information in a format accessible to the user,

[0842] A means to identify the scope of impact when configuration changes are made and to quickly share that information with relevant parties,

[0843] A means to save the analysis results as learning resources and utilize them for work support and technology improvement,

[0844] A means to assess the impact of information, compare information before and after the change, and assess potential impacts,

[0845] A system that includes this.

[0846] (Claim 2)

[0847] The system according to claim 1, comprising means for automatically creating a setting change history by comparing the old and new versions of acquired setting information.

[0848] (Claim 3)

[0849] The system according to claim 1, comprising means for immediately providing the generated explanatory content and related visualization information to the user's terminal.

[0850] "Application Example 1"

[0851] (Claim 1)

[0852] A means of automatically acquiring configuration data from network devices,

[0853] A means for analyzing acquired configuration data using natural language processing technology to identify the meaning and relationships of each configuration item,

[0854] Based on the analysis results, a means is provided to generate explanatory text for the setting items and to visualize the interrelationships between the settings.

[0855] A means of presenting the generated information in a format accessible to the user,

[0856] A means to identify the scope of impact when configuration changes are made and to quickly share that information with relevant parties,

[0857] A means to save the analysis results as a learning resource and utilize them for work support and skill improvement,

[0858] A means of visually displaying the interrelationships of analyzed configuration items and the scope of impact of changes on a mobile terminal,

[0859] A means for outputting input prompt sentences to a generated artificial intelligence model based on user input,

[0860] A system that includes this.

[0861] (Claim 2)

[0862] The system according to claim 1, comprising means for automatically creating a setting change history by comparing the old and new versions of acquired setting data.

[0863] (Claim 3)

[0864] The system according to claim 1, comprising means for providing generated explanatory text and related visualization information to a user's portable computing device in real time.

[0865] "Example 2 of combining an emotion engine"

[0866] (Claim 1)

[0867] A means of automatically acquiring configuration data from network devices,

[0868] A means for analyzing acquired configuration data using natural language processing technology to identify the meaning and relationships of each configuration item,

[0869] Based on the analysis results, a means is provided to generate explanatory text for the setting items and to visualize the interrelationships between the settings.

[0870] A means of presenting the generated information in a format accessible to the user,

[0871] A means for analyzing the user's emotions and dynamically adjusting the content and format of the information presented according to that state,

[0872] A means of recording user feedback and optimizing the presentation method of analysis results,

[0873] A means to save the analysis results as a learning resource and utilize them for work support and skill improvement,

[0874] A system that includes this.

[0875] (Claim 2)

[0876] The system according to claim 1, comprising means for automatically creating a setting change history by comparing the old and new versions of acquired setting data.

[0877] (Claim 3)

[0878] The system according to claim 1, comprising means for providing generated explanatory text and related visualization information in real time.

[0879] "Application example 2 when combining with an emotional engine"

[0880] (Claim 1)

[0881] A means of automatically obtaining configuration data from network devices,

[0882] A means for decomposing acquired configuration data using natural language processing technology and determining the meaning and relationships of each configuration item,

[0883] Based on the analysis results, explanatory text for the setting items is generated, and a means of visually representing the interrelationships between the settings is provided.

[0884] A means of providing the generated information in a format accessible to users,

[0885] A means of analyzing the user's emotional state and dynamically adjusting the content and format of the information presented,

[0886] A method for optimizing the timing of presenting important information using emotion analysis results,

[0887] A means to save the analysis content and emotional data as learning material and to utilize it for job support and skill improvement,

[0888] A system that includes this.

[0889] (Claim 2)

[0890] The system according to claim 1, comprising means for automatically creating a setting change history by comparing the history of acquired setting data.

[0891] (Claim 3)

[0892] The system according to claim 1, comprising means for providing generated explanatory text and related visualization information to the user's terminal in real time, and for adaptively adjusting the displayed content based on the user's sentiment analysis. [Explanation of symbols]

[0893] 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 automatically acquiring configuration data from network devices, A means for analyzing acquired configuration data using natural language processing technology to identify the meaning and relationships of each configuration item, Based on the analysis results, a means is provided to generate explanatory text for the setting items and to visualize the interrelationships between the settings. A means of presenting the generated information in a format accessible to the user, A means to identify the scope of impact when settings are changed and to quickly share that information with relevant parties, A means to save the analysis results as a learning resource and utilize them for work support and skill improvement, A system that includes this.

2. The system according to claim 1, comprising means for automatically creating a setting change history by comparing the old and new versions of acquired setting data.

3. The system according to claim 1, comprising means for providing generated explanatory text and related visualization information to the user's terminal in real time.

Images