system

Abstract

We provide the system. [Solution] A means of presenting questions generated using a large-scale language model in order to collect network requirements from users, A means of using an artificial intelligence agent to generate the optimal network configuration based on collected requirements, A means for automatically applying the generated network configuration to network devices, A means of monitoring network usage data in real time and autonomously troubleshooting when an anomaly is detected, A means to predict future usage based on past network usage data and support network expansion planning, 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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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] An object of the present invention is to provide a system that enables a user without expertise in network management to design an optimal network configuration between a plurality of scattered bases nationwide and deploy it quickly. Another object is to solve the problem of maximizing performance while minimizing operation costs by having the ability to immediately detect and handle network anomalies and enabling efficient real-time resource allocation.

Means for Solving the Problems

[0005] This invention comprises means for generating and presenting questions using large-scale language modeling technology to collect network requirements from users, and an artificial intelligence agent that proposes an optimal network configuration based on the collected data. It also includes means for automatically applying the generated network configuration and means for rapidly detecting anomalies and autonomously troubleshooting by monitoring network usage in real time. Furthermore, by incorporating a future demand forecasting function based on past usage data, the invention provides a system that efficiently supports network expansion planning.

[0006] A "user" is a person or organization that configures and manages a network system.

[0007] "Network requirements" is a list of conditions and preferences that users need in relation to the design and operation of a network.

[0008] A "large-scale language model" is a machine learning model used in natural language processing that has the ability to understand and generate human language using large amounts of text data.

[0009] "Means of presenting questions" refers to technologies or devices that generate questions and display them in order to collect necessary information from the user.

[0010] An "artificial intelligence agent" is a software program that collects and analyzes information, makes decisions based on the results, and acts autonomously.

[0011] "Network configuration" refers to the details of the design and placement of hardware and software necessary for a network to function properly.

[0012] "Means of automatic application" refers to processes or technologies that perform settings or changes without human intervention.

[0013] "Means of real-time monitoring" refers to technologies or systems for continuously and immediately observing and analyzing network conditions and data.

[0014] "Detecting an anomaly" refers to identifying events or unexpected conditions that are different from the norm.

[0015] "Autonomous troubleshooting" refers to the ability to automatically recognize a problem and take steps to address it.

[0016] "Past usage data" refers to records of data that the network system has processed and used up to date.

[0017] "Demand forecasting functionality" is the ability to estimate future network traffic and resource needs based on past data and trends.

[0018] A "network expansion plan" is a plan to expand the functionality and scale of a network as needed. [Brief explanation of the drawing]

[0019] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7]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 a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of 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 an 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 an emotion engine is combined.

Mode for Carrying Out the Invention

[0020] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0021] First, the language used in the following description will be explained.

[0022] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0023] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0024] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0025] 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).

[0026] 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."

[0027] [First Embodiment]

[0028] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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".

[0040] Embodiments of the present invention provide a system that allows users without network expertise to autonomously and efficiently optimize and manage network configurations across multiple locations.

[0041] At the heart of this system is a server-based program that collects user requirements and generates the optimal network configuration based on them. The server first uses LLM (Large-Scale Language Model) technology to present appropriate questions to the user. This allows the server to obtain information from the user regarding the network's purpose, scale, and preferred services.

[0042] Based on the information obtained, the server's AI agent automatically generates the optimal network configuration. This network configuration achieves high efficiency and reliability by referencing pre-learned best practices and configuration patterns. The generated configuration is sent to the terminal and executed automatically.

[0043] Furthermore, the server monitors network data in real time and optimizes performance according to usage. If a network anomaly is detected, the server quickly takes corrective action and reallocates resources to resolve the problem. This ensures that network stability is always maintained.

[0044] This system also has the ability to predict future network demand by analyzing historical data and propose expansion plans. This allows users to manage their network assets from a long-term perspective and achieve efficient expansion.

[0045] As a concrete example, when a company uses this system to establish three new locations, it can immediately deploy an autonomously constructed and efficient network. Furthermore, as the business expands or contracts, the server automatically suggests network reconfigurations, ensuring that the optimal network environment is always maintained.

[0046] As described above, the present invention offers the excellent effect of reducing the effort involved in complex network design and operation, thereby improving cost efficiency.

[0047] The following describes the processing flow.

[0048] Step 1:

[0049] The server uses a large-scale language model to generate and present multiple-choice questions to the user to identify network requirements. Through these questions, it collects information from the user such as the desired network size, the importance of the locations to be connected, and the types of applications that will be used.

[0050] Step 2:

[0051] The user answers questions presented by the server. This provides the server with the specific requirements and conditions necessary for network management.

[0052] Step 3:

[0053] The server uses an artificial intelligence agent to generate the optimal network configuration based on the collected user requirements. This generation process references a variety of pre-trained network configuration patterns and best practices.

[0054] Step 4:

[0055] The server sends the generated network configuration information to each terminal. The terminal receives this information and automatically applies the network device settings.

[0056] Step 5:

[0057] The server monitors network usage in real time, constantly observing data flow and bandwidth utilization within the network.

[0058] Step 6:

[0059] If a network anomaly occurs, the server will autonomously detect the anomaly and initiate a troubleshooting process. This includes identifying the problem area and reallocating resources.

[0060] Step 7:

[0061] The server accumulates and analyzes historical network usage data to predict future network demand. Based on this information, it proposes network expansion plans to the user.

[0062] Step 8:

[0063] Users can review the network expansion plan provided by the server, accept the proposals as needed, and update their network configuration.

[0064] (Example 1)

[0065] 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."

[0066] Operating modern communication networks is extremely complex, making effective network configuration and management difficult, especially for users without specialized communication expertise. Furthermore, insufficient resources and time are often available to quickly optimize for fluctuating network environments, potentially compromising network efficiency and reliability. Additionally, predicting future network demand and planning expansions is challenging, posing a significant obstacle to optimal long-term operation.

[0067] 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.

[0068] In this invention, the server includes data processing means for forming natural language questions to obtain information from users, computation means for analyzing the obtained information to generate an efficient and reliable communication network configuration, and application means for automatically applying the generated communication network configuration to information devices. This enables autonomous and efficient optimization and management of the communication network even without specialized communication knowledge. Furthermore, it allows for the formulation of expansion plans based on real-time monitoring and forecasting of future demand, thereby realizing stable long-term operation of the communication network.

[0069] "User" refers to a person or organization that uses communication networks or information technology, and includes users who do not possess specialized knowledge.

[0070] A "natural language question" refers to a question generated in human language so that users can easily understand and answer it.

[0071] "Data processing means" refers to technical methods and processes for collecting and analyzing information from users.

[0072] "Network configuration" refers to the design and setup of a network, and is the state of a network optimized based on specific requirements.

[0073] "Computational means" refers to technical methods for analyzing given information and generating the optimal network configuration.

[0074] "Information equipment" refers to all devices used within a network, including hardware such as routers and switches.

[0075] "Application means" refers to methods and techniques for reflecting the generated network configuration on actual network devices.

[0076] "Monitoring measures" refer to technical methods and systems that observe the state of a network in real time and detect anomalies.

[0077] "Planning tools" refer to methods and systems for predicting future network demand and formulating expansion plans based on that prediction.

[0078] This invention provides an autonomous system for users without specialized knowledge to efficiently manage communication networks. It is primarily server-centric and implemented using the various hardware and software described below.

[0079] The server first uses a generative AI model to collect necessary information from the user through natural language questions. For example, in response to a need to build a small network environment, the server generates specific questions such as "What devices will be connected to the network?" or "Are there any priorities for specific applications?" LLM technology is used to create these prompts, generating appropriate questions based on the user's input.

[0080] Next, the server uses the collected information and an AI agent acting as a computational tool to generate an efficient and reliable communication network configuration. In this process, common frameworks such as TENSORFLOW® and PyTorch are used as machine learning platforms, and the optimal configuration is designed while referring to past best practice datasets.

[0081] The generated network configuration is applied to network devices, which are information devices—for example, routers and switches. The server sends the configuration file to the terminal, and the terminal automatically updates its settings. While JSON or YAML format configuration files are used, the user does not need to directly manipulate them; the entire process is automated through the application mechanism.

[0082] Furthermore, the server uses monitoring tools to monitor the network in real time. For example, it uses Nagios or Zabbix as monitoring tools to immediately respond to traffic anomalies or device failures. This includes rerouting and traffic rebalancing.

[0083] Finally, the server analyzes historical network data, uses planning tools to predict future network demand, and proposes expansion plans to the user. In this process, the system processes instructions such as, "Based on data from the past six months, predict future traffic increases and propose a response plan."

[0084] Thus, the present invention automates the procedures necessary for managing a communication network, making the system easily accessible to users.

[0085] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0086] Step 1:

[0087] The server uses a generative AI model to create prompts and presents the user with natural language questions for information gathering.

[0088] Specific operation: The server receives the user's initial request and generates appropriate questions based on that request. For example, upon receiving a request such as "We need to set up a network at a new location," the server will generate specific questions such as "What communication speed is required?"

[0089] Input: User requests or needs (e.g., network configuration required for a new site)

[0090] Output: A list of specific questions for the user (written in natural language)

[0091] Step 2:

[0092] The user answers questions provided by the server, and the server collects information based on those answers.

[0093] Specific operation: The user answers the presented questions regarding the purpose, scale, and required services of network usage. The server receives this data and incorporates it as foundational data for the next processing step.

[0094] Input: User response data (e.g., required communication speed and type of connected device)

[0095] Output: Structured user request data for analysis

[0096] Step 3:

[0097] Based on the collected information, the server uses an AI agent to generate the optimal network configuration plan.

[0098] Specific operation: The server uses a machine learning platform to process the collected information and design the network configuration. It uses TensorFlow and PyTorch to optimize while referencing past configuration patterns. At this stage, best practices suitable for the network requirements are selected.

[0099] Input: Structured user request data

[0100] Output: Generated network configuration plan (in JSON or YAML format)

[0101] Step 4:

[0102] The network configuration plan generated by the server is delivered to the terminal, and the terminal automatically applies the settings to the network devices.

[0103] Specific operation: The terminal receives configuration files sent from the server and automatically applies settings to network devices such as routers and switches. This allows users to build a network without performing detailed technical operations.

[0104] Input: Network configuration plan from the server

[0105] Output: Settings applied to the network device

[0106] Step 5:

[0107] The server monitors the network in real time and automatically corrects any abnormalities.

[0108] Specific operation: The server monitors traffic conditions using monitoring tools (such as Nagios or Zabbix). If an anomaly is detected, the server immediately changes routes or adjusts bandwidth.

[0109] Input: Real-time network traffic data

[0110] Output: Stabilized network status after anomaly correction.

[0111] Step 6:

[0112] The server analyzes historical data, predicts future network demand, and proposes expansion plans to users.

[0113] Specific operation: The server analyzes accumulated network usage data to predict increased demand and appropriate expansion timing. It then presents the user with the optimal expansion plan.

[0114] Input: Past network usage data

[0115] Output: Future network demand forecast and proposed plan

[0116] (Application Example 1)

[0117] 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."

[0118] Configuring and managing networks and communications requires specialized knowledge and is a complex and burdensome task for many organizations. Furthermore, manual operations lack responsiveness and can compromise convenience, especially in situations where real-time optimization and anomaly detection are required. To address this, there is a need for a system that allows even users without specialized knowledge to efficiently optimize and manage networks.

[0119] 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.

[0120] In this invention, the server includes means for presenting information generated using large-scale language technology to collect communication requirements from users, means for using an artificial intelligence agent to generate an optimal communication configuration based on the collected requirements, and means for automatically applying the generated communication configuration to the device. This enables even users without specialized knowledge to efficiently optimize the communication configuration and perform real-time management and problem solving.

[0121] A "user" is an entity that utilizes a communication system to manage and optimize it.

[0122] "Communication requirements" refer to the conditions and demands that users have for a communication system, and the system must be configured accordingly.

[0123] "Large-scale language technology" refers to advanced language models used to process information from users through natural language processing.

[0124] "Means of presenting information" refers to functions that display interfaces and questions generated using large-scale language technologies to the user.

[0125] An "artificial intelligence agent" is a program that generates the optimal communication configuration based on collected requirements.

[0126] "Device" refers to the hardware or software used to apply the generated communication configuration.

[0127] "Real-time management" is the process of immediately analyzing communication data and maintaining it in a state where appropriate responses and optimizations can be made.

[0128] "Problem solving" refers to identifying abnormalities or errors in communication systems and taking prompt and appropriate countermeasures.

[0129] A system implementing this invention consists of a server equipped with a program that includes various functions such as communication requirements collection, information presentation, configuration optimization, and real-time management, and a corresponding terminal.

[0130] The server first provides an intuitive interface for users through a means of presenting information using large-scale language technology. Users can input communication requirements through this interface. For example, a user might input, "We are a medium-sized business and want to ensure a secure connection for remote work."

[0131] Next, the server utilizes an artificial intelligence agent to generate the optimal communication configuration based on the user's requirements. This agent has the ability to achieve a highly efficient and reliable array by referencing past best practices and learned configuration patterns.

[0132] The generated communication configuration is then automatically applied to the terminal. This allows users to enjoy an optimized communication environment without having to worry about a lack of technical expertise.

[0133] Furthermore, the server monitors communication data in real time and immediately initiates problem-solving processes if it detects an anomaly. For example, if an unexpected increase in traffic occurs, it will respond quickly by reallocating resources.

[0134] Furthermore, by leveraging past usage data, the system predicts future communication demands and proposes expansion plans to users. This streamlines long-term asset management.

[0135] A concrete example of a prompt message is its use in generating new questions based on information provided by the user. For example, it might look like this: "User information: Medium-sized company, primary use of cloud services is file sharing. What is the next question to ask?"

[0136] This system aims to reduce the complexity of designing and operating communication environments and to support efficient management.

[0137] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0138] Step 1:

[0139] The server uses large-scale language technology to generate a user interface and displays questions to present communication requirements to the user. These prompts are generated based on basic information entered by the user. The input includes the user's initial communication requirements, and the output provides questions for the user to enter specific requirements.

[0140] Step 2:

[0141] The user inputs detailed communication requirements through an interface provided by the server. The user-specified conditions include requirements regarding the scale of the communication environment and specific functionalities. The input represents the user's desired communication conditions, but these are not yet optimized. The output forms a set of specific requirements for optimization.

[0142] Step 3:

[0143] The server analyzes the user's input requirements and proposes the optimal communication configuration using an artificial intelligence agent. Here, it compares the requirements with previously learned best practices to generate an optimized configuration. The input to this process is the specific communication requirements obtained in the previous step, and the output is the optimal communication configuration.

[0144] Step 4:

[0145] The generated communication configuration is automatically applied to the terminal. The terminal incorporates the received configuration into the device and provides a usable communication environment to the user. The input is the configured communication parameters, and the output is the communication network environment readily available to the user.

[0146] Step 5:

[0147] The server monitors communication data in real time and automatically initiates problem resolution processing if an anomaly is detected. Specifically, it detects and analyzes the differences between the data detected as an anomaly and the normal communication data, and quickly resolves the problem. It also reallocates resources to avoid service interruptions. The input is communication data collected in real time, and the output is the solution to the anomaly found, or the communication state after optimization.

[0148] Step 6:

[0149] The server analyzes past communication data, predicts future demand, and presents a communication expansion plan for the user. It analyzes past data patterns to predict what equipment will be needed to meet the user's future requirements. The input is historical communication data, and the output is a proposed plan including the next actions the user should take.

[0150] 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.

[0151] Embodiments of the present invention provide a system incorporating an emotion engine for recognizing user emotions and optimizing network management processes based on those emotions. In addition to conventional network configuration and management functions, this system aims to improve the user experience through emotion recognition.

[0152] Specifically, this system interacts with the user and uses an emotion engine to analyze the user's emotional state based on their voice, facial expressions, and text input. When the user presents network requirements, the server appropriately adjusts the content and tone of the questions according to the user's emotions. This process allows the user to communicate their needs accurately and without stress.

[0153] The server uses an AI agent to generate the optimal network configuration based on collected user requirements and sentiment data. By including feedback corrected by the sentiment engine, configuration suggestions that enhance user satisfaction become possible. The generated configuration is then automatically delivered to the terminal and the settings are applied.

[0154] Furthermore, the server performs real-time network monitoring and troubleshoots for anomalies, providing responses tailored to the user's emotional state. For example, if a user is feeling anxious, the server will provide detailed explanations of the problem's progress and potential solutions, striving to reassure them.

[0155] As a concrete example of this system, consider a scenario where a user who easily experiences stress from network configurations uses the system. The server detects the user's emotional state in advance and adjusts the interface to reduce that stress. Furthermore, even if the generated network configuration is complex, the system helps the user understand it through easy-to-understand explanations tailored to their emotional state, allowing them to proceed with implementation with confidence.

[0156] With these features, the system allows users to smoothly configure and operate the network without requiring specialized knowledge. The introduction of an emotional engine enables even more user-centric network management, improving overall operational efficiency and customer satisfaction.

[0157] The following describes the processing flow.

[0158] Step 1:

[0159] The user accesses the system interface to input network requirements. During this process, the user's emotional state is collected through text input, voice, or facial recognition.

[0160] Step 2:

[0161] The server uses an emotion engine to analyze the user's emotional state, determining whether the user is relaxed, stressed, etc. Based on this information, it dynamically adjusts the wording of questions and answer choices to present the user with the most appropriate questions.

[0162] Step 3:

[0163] The user answers pre-configured questions presented by the server. This ensures that the server receives detailed information about the user's network requirements and current needs.

[0164] Step 4:

[0165] The server uses an artificial intelligence agent to generate the optimal network configuration based on collected user requirements and sentiment data. By considering sentiment data, better suggestions that meet the user's needs are formed.

[0166] Step 5:

[0167] The generated network configuration is automatically sent to the terminal, and the associated network devices are configured. Emotionally responsive explanations and guidance are provided to the user, ensuring a smooth network setup process.

[0168] Step 6:

[0169] The server monitors data in real time during network operation, taking into account the user's emotional state to perform early detection and troubleshooting of anomalies. For example, if a user is feeling anxious, the server provides the user with information including the progress of the problem and reassurance.

[0170] Step 7:

[0171] Based on past network usage and sentiment data, the server predicts future network demand and proposes expansion plans to users. These proposals are presented in a way that takes user sentiment into consideration, supporting long-term management planning.

[0172] (Example 2)

[0173] 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".

[0174] Traditional network management systems operate without considering the user's emotional state, leading to problems such as user stress and insufficient understanding during network configuration and troubleshooting. Furthermore, a lack of support and interface adjustments tailored to user emotions made it difficult to improve the user experience. These challenges contributed to a decline in overall operational efficiency and customer satisfaction.

[0175] 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.

[0176] In this invention, the server includes means for collecting and analyzing the user's emotional state, means for adjusting the interface display content and sound based on the analyzed emotions, and means for using an artificial intelligence agent to generate an optimal network configuration based on the collected requirements and emotional data. This enables network management that takes user emotions into consideration and a smooth, stress-free operating experience.

[0177] A "user" is an individual or group that uses a network management system to meet their own network requirements.

[0178] "Emotional state" refers to the state of a user's emotions as determined from their voice, facial expressions, text, etc., and is used to improve the user experience.

[0179] An "interface" refers to the screen display and audio guidance that users use to interact with a network management system.

[0180] An "information processing device" refers to hardware or software that receives network configurations and performs settings based on them.

[0181] An "artificial intelligence agent" is a program or system that generates the optimal network configuration based on data collected from users.

[0182] A "large-scale language model" is a large-scale neural network-based model used to collect user requirements using natural language processing.

[0183] "Network usage data" refers to data collected in real time regarding network performance and traffic.

[0184] This invention is a system that improves the user experience by analyzing the emotional state of users and utilizing that information for network management. This system primarily operates between a server, a terminal, and a user.

[0185] The server first uses an emotion engine to collect user voice, facial expressions, and text data. This emotion engine is software equipped with a generative AI model that acquires data from hardware such as microphones and cameras. It analyzes the user's emotional state in real time and dynamically adjusts the interface based on the results. Interface adjustments include the content of on-screen messages and the tone of voice guidance.

[0186] The user enters their network requirements according to the prompts. For example, a prompt such as "Please specify if you would like to improve your network speed" might appear on the screen. This allows the user to clearly indicate their needs.

[0187] The server analyzes user requirements using a large-scale language model and generates the optimal network configuration using an artificial intelligence agent. This configuration is automatically applied to the terminal, which is an information processing device, and the settings are executed. The terminal immediately implements the generated settings, improving network performance.

[0188] Furthermore, the server monitors network usage data in real time and automatically detects anomalies. Troubleshooting is performed while considering the user's feelings, and escalates to expert support as needed. Throughout this process, appropriate information is provided to reassure the user.

[0189] In this way, a network management system that integrates user emotions allows users to have a stress-free network operation experience, and is expected to improve overall operational efficiency and customer satisfaction.

[0190] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0191] Step 1:

[0192] The user initiates a dialogue to configure network settings or troubleshoot problems. During this process, the user's voice, facial expressions, and text input are fed into the emotion analysis system. The server receives this data and uses a generative AI model to analyze the user's emotional state in real time. The analysis extracts the user's perceived stress levels and satisfaction levels.

[0193] Step 2:

[0194] The server adjusts the interface displayed to the user based on the analyzed sentiment data. Specifically, it softens the tone of on-screen messages and appropriately modifies voice guidance to reduce user stress. This allows the user to continue the interaction in a more relaxed state.

[0195] Step 3:

[0196] The user enters network requirements based on prompts provided by the server. For example, a prompt might say, "Please tell us about any dissatisfactions or areas for improvement regarding your current network connection." The user's input (requirements) is then translated into specific network needs through analysis of the server's large-scale language model.

[0197] Step 4:

[0198] The server uses an artificial intelligence agent to generate the optimal network configuration based on requirements and sentiment data collected from users. The AI ​​agent processes this input information and creates a configuration proposal that reflects the user's needs and emotions. The generated configuration proposal is output to an information processing device.

[0199] Step 5:

[0200] The terminal receives the proposed network configuration from the server and automatically applies it. The terminal then executes this configuration to improve the network environment. It also notifies the user when the configuration is complete. This allows the user to confidently monitor the network status.

[0201] Step 6:

[0202] The server monitors network usage data in real time and detects anomalies. If an anomaly is detected, the server provides appropriate troubleshooting, taking into account user sentiment data. If specific support is needed, the issue is escalated to a specialized service. Throughout this process, the user is notified of the problem's progress at each stage, providing peace of mind.

[0203] (Application Example 2)

[0204] 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".

[0205] Currently, many network management systems offer a uniform interface and configuration process, lacking mechanisms to alleviate user stress and anxiety. As a result, users may become dissatisfied with network configuration and management, and this can lead to misunderstandings and distrust, especially among emotionally sensitive users. Furthermore, if explanations and responses to network anomalies are not appropriate to the user's emotional state, it can trigger further anxiety and dissatisfaction. Solving these problems is essential.

[0206] 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.

[0207] In this invention, the server includes means for recognizing the user's emotional state and dynamically adjusting the interface for network requirements collection according to the user's emotions; autonomous automation means for selecting a notification method considering the emotional state; and means for automatically proposing resource allocation based on emotional data. This enables network management that is sensitive to the user's emotions, improving the user experience and optimizing operational efficiency.

[0208] "User emotional state" refers to the emotional state of a user, analyzed from their voice, facial expressions, text input, etc.

[0209] The "interface for collecting network requirements" refers to the screen or method used to collect network-related requirements from users.

[0210] "Information equipment" refers to electronic devices used for network configuration, data processing, and other similar tasks.

[0211] "Information usage data" refers to data generated when users use networks or information services.

[0212] "Real-time monitoring" refers to the process of continuously monitoring the status of data and systems.

[0213] "Providing explanations tailored to the user's emotional state" means providing appropriate explanations that take into account the user's current emotional state.

[0214] "Autonomous problem-solving" refers to the process of automatically resolving problems without human intervention.

[0215] "Network expansion planning" refers to developing a plan to improve network capabilities in anticipation of future demand.

[0216] "Emotionally tailored explanations" means providing information in a way that is easy for users to understand, in accordance with their emotional state.

[0217] This system detects user emotions and optimizes network management based on them. The server uses speech recognition modules and facial expression analysis software to collect emotion data from the user's voice, facial expressions, and text. Specific examples include commonly used speech recognition APIs and emotion analysis APIs. The server processes this data, presents the user with questions generated using a large-scale language model, and collects network requirements.

[0218] The server then uses collected requirements and sentiment data to generate an optimal network configuration using an artificial intelligence agent. The generated configuration is automatically applied to the user's device, which may be a smartphone or computer. Through this device, the server monitors information usage data in real time and detects anomalies. If the user is feeling anxious or stressed, the server provides the user with an emotion-appropriate response, for example, by visually showing a solution to the problem to provide reassurance.

[0219] As a concrete example of this system, when informing users of delays in public transport, the server provides detailed alternative route information in real time to alleviate user anxiety. Furthermore, if sentiment analysis detects that the user is anxious, the system autonomously optimizes itself by using a prompt message such as, "The user's current emotional state has been detected as 'anxious'. Please provide an alternative plan and reassure them."

[0220] In this way, the entire system realizes a form of network management and support that is attentive to the user's emotions.

[0221] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0222] Step 1:

[0223] The user provides emotional state data through voice, facial expressions, or text input. The server collects this data using a dedicated speech recognition module or facial expression analysis software. The input for this step is raw emotional data, and the output is processed emotional information. The server analyzes the collected data to identify the user's emotional state (e.g., anxiety, reassurance).

[0224] Step 2:

[0225] The server presents the user with questions generated using a large-scale language model. The generative AI model dynamically generates appropriate questions regarding network requirements and collects specific information from the user. The input for this step is processed sentiment information, and the output is the user's network requirements. The server adjusts the content and tone of the questions to match the user's emotions.

[0226] Step 3:

[0227] The server uses collected requirements and sentiment data to activate an artificial intelligence agent that generates the optimal network configuration. The input is user requirements and sentiment data, and the output is network configuration data. The agent designs the optimized configuration while taking sentiment data into consideration.

[0228] Step 4:

[0229] The generated network configuration is automatically applied from the server to the user's terminal. In this step, network configuration data is used as input, and the settings on the terminal are applied as output. The server reflects the settings through the terminal's information equipment.

[0230] Step 5:

[0231] The server monitors information usage data in real time and checks for any anomalies. The input is real-time information usage data, and the output is the anomaly detection result. If an anomaly is detected, the server provides an explanation of the situation and solutions according to the user's emotional state.

[0232] Step 6:

[0233] The server generates prompt messages based on the user's emotions and provides alternative plans or reassuring information as needed. The input is the anomaly detection result and emotion information, and the output is an appropriate prompt message and specific countermeasures. For example, the server might generate and present a message such as, "The user's current emotional state has been detected as 'anxious'. Please provide alternative plans and reassure the user."

[0234] 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.

[0235] 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.

[0236] 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.

[0237] [Second Embodiment]

[0238] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0239] 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.

[0240] 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).

[0241] 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.

[0242] 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.

[0243] 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).

[0244] 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.

[0245] 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.

[0246] 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.

[0247] 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.

[0248] 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.

[0249] 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".

[0250] Embodiments of the present invention provide a system that allows users without network expertise to autonomously and efficiently optimize and manage network configurations across multiple locations.

[0251] At the heart of this system is a server-based program that collects user requirements and generates the optimal network configuration based on them. The server first uses LLM (Large-Scale Language Model) technology to present appropriate questions to the user. This allows the server to obtain information from the user regarding the network's purpose, scale, and preferred services.

[0252] Based on the information obtained, the server's AI agent automatically generates the optimal network configuration. This network configuration achieves high efficiency and reliability by referencing pre-learned best practices and configuration patterns. The generated configuration is sent to the terminal and executed automatically.

[0253] Furthermore, the server monitors network data in real time and optimizes performance according to usage. If a network anomaly is detected, the server quickly takes corrective action and reallocates resources to resolve the problem. This ensures that network stability is always maintained.

[0254] This system also has the ability to predict future network demand by analyzing historical data and propose expansion plans. This allows users to manage their network assets from a long-term perspective and achieve efficient expansion.

[0255] As a concrete example, when a company uses this system to establish three new locations, it can immediately deploy an autonomously constructed and efficient network. Furthermore, as the business expands or contracts, the server automatically suggests network reconfigurations, ensuring that the optimal network environment is always maintained.

[0256] As described above, the present invention offers the excellent effect of reducing the effort involved in complex network design and operation, thereby improving cost efficiency.

[0257] The following describes the processing flow.

[0258] Step 1:

[0259] The server uses a large-scale language model to generate and present multiple-choice questions to the user to identify network requirements. Through these questions, it collects information from the user such as the desired network size, the importance of the locations to be connected, and the types of applications that will be used.

[0260] Step 2:

[0261] The user answers questions presented by the server. This provides the server with the specific requirements and conditions necessary for network management.

[0262] Step 3:

[0263] The server uses an artificial intelligence agent to generate the optimal network configuration based on the collected user requirements. This generation process references a variety of pre-trained network configuration patterns and best practices.

[0264] Step 4:

[0265] The server sends the generated network configuration information to each terminal. The terminal receives this information and automatically applies the network device settings.

[0266] Step 5:

[0267] The server monitors network usage in real time, constantly observing data flow and bandwidth utilization within the network.

[0268] Step 6:

[0269] If a network anomaly occurs, the server will autonomously detect the anomaly and initiate a troubleshooting process. This includes identifying the problem area and reallocating resources.

[0270] Step 7:

[0271] The server accumulates and analyzes historical network usage data to predict future network demand. Based on this information, it proposes network expansion plans to the user.

[0272] Step 8:

[0273] Users can review the network expansion plan provided by the server, accept the proposals as needed, and update their network configuration.

[0274] (Example 1)

[0275] 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."

[0276] Operating modern communication networks is extremely complex, making effective network configuration and management difficult, especially for users without specialized communication expertise. Furthermore, insufficient resources and time are often available to quickly optimize for fluctuating network environments, potentially compromising network efficiency and reliability. Additionally, predicting future network demand and planning expansions is challenging, posing a significant obstacle to optimal long-term operation.

[0277] 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.

[0278] In this invention, the server includes data processing means for forming natural language questions to obtain information from users, computation means for analyzing the obtained information to generate an efficient and reliable communication network configuration, and application means for automatically applying the generated communication network configuration to information devices. This enables autonomous and efficient optimization and management of the communication network even without specialized communication knowledge. Furthermore, it allows for the formulation of expansion plans based on real-time monitoring and forecasting of future demand, thereby realizing stable long-term operation of the communication network.

[0279] "User" refers to a person or organization that uses communication networks and information technology, and particularly includes users without specialized knowledge.

[0280] "Natural language question" refers to an inquiry generated in human language so that it can be easily understood and answered by the user.

[0281] "Data processing means" refers to technical methods and processes for collecting and analyzing information from users.

[0282] "Communication network configuration" refers to the design and setting of a network, and is the state of a network optimized based on specific requirements.

[0283] "Calculation means" refers to technical methods for analyzing given information and generating an optimal network configuration.

[0284] "Information device" refers to all devices used within a network, including hardware such as routers and switches.

[0285] "Application means" refers to methods and technologies for reflecting the generated network configuration onto actual network devices.

[0286] "Monitoring means" refers to technical methods and systems for observing the state of a network in real time and detecting abnormalities.

[0287] "Planning means" refers to methods and systems for predicting future network demands and formulating expansion plans based on them.

[0288] This invention provides an autonomous system for users without specialized knowledge to efficiently manage communication networks. It is mainly centered around a server and is realized using various hardware and software described below.

[0289] The server first uses a generative AI model to collect necessary information from the user through natural language questions. For example, in response to a need to build a small network environment, the server generates specific questions such as "What devices will be connected to the network?" or "Are there any priorities for specific applications?" LLM technology is used to create these prompts, generating appropriate questions based on the user's input.

[0290] Next, the server uses the collected information and an AI agent acting as a computational tool to generate an efficient and reliable communication network configuration. In this process, common frameworks such as TensorFlow and PyTorch are used as machine learning platforms, and the optimal configuration is designed while referring to past best practice datasets.

[0291] The generated network configuration is applied to network devices, which are information devices—for example, routers and switches. The server sends the configuration file to the terminal, and the terminal automatically updates its settings. While JSON or YAML format configuration files are used, the user does not need to directly manipulate them; the entire process is automated through the application mechanism.

[0292] Furthermore, the server uses monitoring tools to monitor the network in real time. For example, it uses Nagios or Zabbix as monitoring tools to immediately respond to traffic anomalies or device failures. This includes rerouting and traffic rebalancing.

[0293] Finally, the server analyzes historical network data, uses planning tools to predict future network demand, and proposes expansion plans to the user. In this process, the system processes instructions such as, "Based on data from the past six months, predict future traffic increases and propose a response plan."

[0294] Thus, the present invention automates the procedures necessary for managing a communication network, making the system easily accessible to users.

[0295] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0296] Step 1:

[0297] The server uses a generative AI model to create prompts and presents the user with natural language questions for information gathering.

[0298] Specific operation: The server receives the user's initial request and generates appropriate questions based on that request. For example, upon receiving a request such as "We need to set up a network at a new location," the server will generate specific questions such as "What communication speed is required?"

[0299] Input: User requests or needs (e.g., network configuration required for a new site)

[0300] Output: A list of specific questions for the user (written in natural language)

[0301] Step 2:

[0302] The user answers questions provided by the server, and the server collects information based on those answers.

[0303] Specific operation: The user answers the presented questions regarding the purpose, scale, and required services of network usage. The server receives this data and incorporates it as foundational data for the next processing step.

[0304] Input: User response data (e.g., required communication speed and type of connected device)

[0305] Output: Structured user request data for analysis

[0306] Step 3:

[0307] Based on the collected information, the server uses an AI agent to generate an optimal network configuration plan.

[0308] Specific operations: The server uses a machine learning platform to process the collected information and design the network configuration. Utilizing TensorFlow or PyTorch, optimization is carried out while referring to past configuration patterns. At this stage, best practices suitable for the network requirements are selected.

[0309] Input: Structured user request data

[0310] Output: Generated network configuration plan (in JSON or YAML format)

[0311] Step 4:

[0312] The network configuration plan generated by the server is distributed to the terminal, and the terminal automatically applies the settings to the network devices.

[0313] Specific operations: The terminal receives the configuration file sent from the server and automatically applies the settings of network devices such as routers and switches. As a result, the user can build a network without performing detailed technical operations.

[0314] Input: Network configuration plan from the server

[0315] Output: Settings applied to network devices

[0316] Step 5:

[0317] The server monitors the network in real time and automatically makes corrections if there are any abnormalities.

[0318] Specific operation: The server monitors traffic conditions using monitoring tools (such as Nagios or Zabbix). If an anomaly is detected, the server immediately changes routes or adjusts bandwidth.

[0319] Input: Real-time network traffic data

[0320] Output: Stabilized network status after anomaly correction.

[0321] Step 6:

[0322] The server analyzes historical data, predicts future network demand, and proposes expansion plans to users.

[0323] Specific operation: The server analyzes accumulated network usage data to predict increased demand and appropriate expansion timing. It then presents the user with the optimal expansion plan.

[0324] Input: Past network usage data

[0325] Output: Future network demand forecast and proposed plan

[0326] (Application Example 1)

[0327] 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."

[0328] Configuring and managing networks and communications requires specialized knowledge and is a complex and burdensome task for many organizations. Furthermore, manual operations lack responsiveness and can compromise convenience, especially in situations where real-time optimization and anomaly detection are required. To address this, there is a need for a system that allows even users without specialized knowledge to efficiently optimize and manage networks.

[0329] 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.

[0330] In this invention, the server includes means for presenting information generated using large-scale language technology to collect communication requirements from users, means for using an artificial intelligence agent to generate an optimal communication configuration based on the collected requirements, and means for automatically applying the generated communication configuration to the device. This enables even users without specialized knowledge to efficiently optimize the communication configuration and perform real-time management and problem solving.

[0331] A "user" is an entity that utilizes a communication system to manage and optimize it.

[0332] "Communication requirements" refer to the conditions and demands that users have for a communication system, and the system must be configured accordingly.

[0333] "Large-scale language technology" refers to advanced language models used to process information from users through natural language processing.

[0334] "Means of presenting information" refers to functions that display interfaces and questions generated using large-scale language technologies to the user.

[0335] An "artificial intelligence agent" is a program that generates the optimal communication configuration based on collected requirements.

[0336] "Device" refers to the hardware or software used to apply the generated communication configuration.

[0337] "Real-time management" is the process of immediately analyzing communication data and maintaining it in a state where appropriate responses and optimizations can be made.

[0338] "Problem solving" refers to identifying abnormalities or errors in communication systems and taking prompt and appropriate countermeasures.

[0339] A system implementing this invention consists of a server equipped with a program that includes various functions such as communication requirements collection, information presentation, configuration optimization, and real-time management, and a corresponding terminal.

[0340] The server first provides an intuitive interface for users through a means of presenting information using large-scale language technology. Users can input communication requirements through this interface. For example, a user might input, "We are a medium-sized business and want to ensure a secure connection for remote work."

[0341] Next, the server utilizes an artificial intelligence agent to generate the optimal communication configuration based on the user's requirements. This agent has the ability to achieve a highly efficient and reliable array by referencing past best practices and learned configuration patterns.

[0342] The generated communication configuration is then automatically applied to the terminal. This allows users to enjoy an optimized communication environment without having to worry about a lack of technical expertise.

[0343] Furthermore, the server monitors communication data in real time and immediately initiates problem-solving processes if it detects an anomaly. For example, if an unexpected increase in traffic occurs, it will respond quickly by reallocating resources.

[0344] Furthermore, by leveraging past usage data, the system predicts future communication demands and proposes expansion plans to users. This streamlines long-term asset management.

[0345] A concrete example of a prompt message is its use in generating new questions based on information provided by the user. For example, it might look like this: "User information: Medium-sized company, primary use of cloud services is file sharing. What is the next question to ask?"

[0346] This system aims to reduce the complexity of designing and operating communication environments and to support efficient management.

[0347] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0348] Step 1:

[0349] The server uses large-scale language technology to generate a user interface and displays questions to present communication requirements to the user. These prompts are generated based on basic information entered by the user. The input includes the user's initial communication requirements, and the output provides questions for the user to enter specific requirements.

[0350] Step 2:

[0351] The user inputs detailed communication requirements through an interface provided by the server. The user-specified conditions include requirements regarding the scale of the communication environment and specific functionalities. The input represents the user's desired communication conditions, but these are not yet optimized. The output forms a set of specific requirements for optimization.

[0352] Step 3:

[0353] The server analyzes the user's input requirements and proposes the optimal communication configuration using an artificial intelligence agent. Here, it compares the requirements with previously learned best practices to generate an optimized configuration. The input to this process is the specific communication requirements obtained in the previous step, and the output is the optimal communication configuration.

[0354] Step 4:

[0355] The generated communication configuration is automatically applied to the terminal. The terminal incorporates the received configuration into the device and provides a usable communication environment to the user. The input is the configured communication parameters, and the output is the communication network environment readily available to the user.

[0356] Step 5:

[0357] The server monitors communication data in real time and automatically initiates problem resolution processing if an anomaly is detected. Specifically, it detects and analyzes the differences between the data detected as an anomaly and the normal communication data, and quickly resolves the problem. It also reallocates resources to avoid service interruptions. The input is communication data collected in real time, and the output is the solution to the anomaly found, or the communication state after optimization.

[0358] Step 6:

[0359] The server analyzes past communication data, predicts future demand, and presents a communication expansion plan for the user. It analyzes past data patterns to predict what equipment will be needed to meet the user's future requirements. The input is historical communication data, and the output is a proposed plan including the next actions the user should take.

[0360] 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.

[0361] Embodiments of the present invention provide a system incorporating an emotion engine for recognizing user emotions and optimizing network management processes based on those emotions. In addition to conventional network configuration and management functions, this system aims to improve the user experience through emotion recognition.

[0362] Specifically, this system interacts with the user and uses an emotion engine to analyze the user's emotional state based on their voice, facial expressions, and text input. When the user presents network requirements, the server appropriately adjusts the content and tone of the questions according to the user's emotions. This process allows the user to communicate their needs accurately and without stress.

[0363] The server uses an AI agent to generate the optimal network configuration based on collected user requirements and sentiment data. By including feedback corrected by the sentiment engine, configuration suggestions that enhance user satisfaction become possible. The generated configuration is then automatically delivered to the terminal and the settings are applied.

[0364] Furthermore, the server performs real-time network monitoring and troubleshoots for anomalies, providing responses tailored to the user's emotional state. For example, if a user is feeling anxious, the server will provide detailed explanations of the problem's progress and potential solutions, striving to reassure them.

[0365] As a concrete example of this system, consider a scenario where a user who easily experiences stress from network configurations uses the system. The server detects the user's emotional state in advance and adjusts the interface to reduce that stress. Furthermore, even if the generated network configuration is complex, the system helps the user understand it through easy-to-understand explanations tailored to their emotional state, allowing them to proceed with implementation with confidence.

[0366] With these features, the system allows users to smoothly configure and operate the network without requiring specialized knowledge. The introduction of an emotional engine enables even more user-centric network management, improving overall operational efficiency and customer satisfaction.

[0367] The following describes the processing flow.

[0368] Step 1:

[0369] The user accesses the system interface to input network requirements. During this process, the user's emotional state is collected through text input, voice, or facial recognition.

[0370] Step 2:

[0371] The server uses an emotion engine to analyze the user's emotional state, determining whether the user is relaxed, stressed, etc. Based on this information, it dynamically adjusts the wording of questions and answer choices to present the user with the most appropriate questions.

[0372] Step 3:

[0373] The user answers pre-configured questions presented by the server. This ensures that the server receives detailed information about the user's network requirements and current needs.

[0374] Step 4:

[0375] The server uses an artificial intelligence agent to generate the optimal network configuration based on collected user requirements and sentiment data. By considering sentiment data, better suggestions that meet the user's needs are formed.

[0376] Step 5:

[0377] The generated network configuration is automatically sent to the terminal, and the associated network devices are configured. Emotionally responsive explanations and guidance are provided to the user, ensuring a smooth network setup process.

[0378] Step 6:

[0379] The server monitors data in real time during network operation, taking into account the user's emotional state to perform early detection and troubleshooting of anomalies. For example, if a user is feeling anxious, the server provides the user with information including the progress of the problem and reassurance.

[0380] Step 7:

[0381] Based on past network usage and sentiment data, the server predicts future network demand and proposes expansion plans to users. These proposals are presented in a way that takes user sentiment into consideration, supporting long-term management planning.

[0382] (Example 2)

[0383] 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".

[0384] Traditional network management systems operate without considering the user's emotional state, leading to problems such as user stress and insufficient understanding during network configuration and troubleshooting. Furthermore, a lack of support and interface adjustments tailored to user emotions made it difficult to improve the user experience. These challenges contributed to a decline in overall operational efficiency and customer satisfaction.

[0385] 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.

[0386] In this invention, the server includes means for collecting and analyzing the user's emotional state, means for adjusting the interface display content and sound based on the analyzed emotions, and means for using an artificial intelligence agent to generate an optimal network configuration based on the collected requirements and emotional data. This enables network management that takes user emotions into consideration and a smooth, stress-free operating experience.

[0387] A "user" is an individual or group that uses a network management system to meet their own network requirements.

[0388] "Emotional state" refers to the state of a user's emotions as determined from their voice, facial expressions, text, etc., and is used to improve the user experience.

[0389] An "interface" refers to the screen display and audio guidance that users use to interact with a network management system.

[0390] An "information processing device" refers to hardware or software that receives network configurations and performs settings based on them.

[0391] An "artificial intelligence agent" is a program or system that generates the optimal network configuration based on data collected from users.

[0392] A "large-scale language model" is a large-scale neural network-based model used to collect user requirements using natural language processing.

[0393] "Network usage data" refers to data collected in real time regarding network performance and traffic.

[0394] This invention is a system that improves the user experience by analyzing the emotional state of users and utilizing that information for network management. This system primarily operates between a server, a terminal, and a user.

[0395] The server first uses an emotion engine to collect user voice, facial expressions, and text data. This emotion engine is software equipped with a generative AI model that acquires data from hardware such as microphones and cameras. It analyzes the user's emotional state in real time and dynamically adjusts the interface based on the results. Interface adjustments include the content of on-screen messages and the tone of voice guidance.

[0396] The user enters their network requirements according to the prompts. For example, a prompt such as "Please specify if you would like to improve your network speed" might appear on the screen. This allows the user to clearly indicate their needs.

[0397] The server analyzes user requirements using a large-scale language model and generates the optimal network configuration using an artificial intelligence agent. This configuration is automatically applied to the terminal, which is an information processing device, and the settings are executed. The terminal immediately implements the generated settings, improving network performance.

[0398] Furthermore, the server monitors network usage data in real time and automatically detects anomalies. Troubleshooting is performed while considering the user's feelings, and escalates to expert support as needed. Throughout this process, appropriate information is provided to reassure the user.

[0399] In this way, a network management system that integrates user emotions allows users to have a stress-free network operation experience, and is expected to improve overall operational efficiency and customer satisfaction.

[0400] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0401] Step 1:

[0402] The user initiates a dialogue to configure network settings or troubleshoot problems. During this process, the user's voice, facial expressions, and text input are fed into the emotion analysis system. The server receives this data and uses a generative AI model to analyze the user's emotional state in real time. The analysis extracts the user's perceived stress levels and satisfaction levels.

[0403] Step 2:

[0404] The server adjusts the interface displayed to the user based on the analyzed sentiment data. Specifically, it softens the tone of on-screen messages and appropriately modifies voice guidance to reduce user stress. This allows the user to continue the interaction in a more relaxed state.

[0405] Step 3:

[0406] The user enters network requirements based on prompts provided by the server. For example, a prompt might say, "Please tell us about any dissatisfactions or areas for improvement regarding your current network connection." The user's input (requirements) is then translated into specific network needs through analysis of the server's large-scale language model.

[0407] Step 4:

[0408] The server uses an artificial intelligence agent to generate the optimal network configuration based on requirements and sentiment data collected from users. The AI ​​agent processes this input information and creates a configuration proposal that reflects the user's needs and emotions. The generated configuration proposal is output to an information processing device.

[0409] Step 5:

[0410] The terminal receives the proposed network configuration from the server and automatically applies it. The terminal then executes this configuration to improve the network environment. It also notifies the user when the configuration is complete. This allows the user to confidently monitor the network status.

[0411] Step 6:

[0412] The server monitors network usage data in real time and detects anomalies. If an anomaly is detected, the server provides appropriate troubleshooting, taking into account user sentiment data. If specific support is needed, the issue is escalated to a specialized service. Throughout this process, the user is notified of the problem's progress at each stage, providing peace of mind.

[0413] (Application Example 2)

[0414] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0415] Currently, many network management systems offer a uniform interface and configuration process, lacking mechanisms to alleviate user stress and anxiety. As a result, users may become dissatisfied with network configuration and management, and this can lead to misunderstandings and distrust, especially among emotionally sensitive users. Furthermore, if explanations and responses to network anomalies are not appropriate to the user's emotional state, it can trigger further anxiety and dissatisfaction. Solving these problems is essential.

[0416] 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.

[0417] In this invention, the server includes means for recognizing the user's emotional state and dynamically adjusting the interface for network requirements collection according to the user's emotions; autonomous automation means for selecting a notification method considering the emotional state; and means for automatically proposing resource allocation based on emotional data. This enables network management that is sensitive to the user's emotions, improving the user experience and optimizing operational efficiency.

[0418] "User emotional state" refers to the emotional state of a user, analyzed from their voice, facial expressions, text input, etc.

[0419] The "interface for collecting network requirements" refers to the screen or method used to collect network-related requirements from users.

[0420] "Information equipment" refers to electronic devices used for network configuration, data processing, and other similar tasks.

[0421] "Information usage data" refers to data generated when users use networks or information services.

[0422] "Real-time monitoring" refers to the process of continuously monitoring the status of data and systems.

[0423] "Providing explanations tailored to the user's emotional state" means providing appropriate explanations that take into account the user's current emotional state.

[0424] "Autonomous problem-solving" refers to the process of automatically resolving problems without human intervention.

[0425] "Network expansion planning" refers to developing a plan to improve network capabilities in anticipation of future demand.

[0426] "Emotionally tailored explanations" means providing information in a way that is easy for users to understand, in accordance with their emotional state.

[0427] This system detects user emotions and optimizes network management based on them. The server uses speech recognition modules and facial expression analysis software to collect emotion data from the user's voice, facial expressions, and text. Specific examples include commonly used speech recognition APIs and emotion analysis APIs. The server processes this data, presents the user with questions generated using a large-scale language model, and collects network requirements.

[0428] The server then uses collected requirements and sentiment data to generate an optimal network configuration using an artificial intelligence agent. The generated configuration is automatically applied to the user's device, which may be a smartphone or computer. Through this device, the server monitors information usage data in real time and detects anomalies. If the user is feeling anxious or stressed, the server provides the user with an emotion-appropriate response, for example, by visually showing a solution to the problem to provide reassurance.

[0429] As a concrete example of this system, when informing users of delays in public transport, the server provides detailed alternative route information in real time to alleviate user anxiety. Furthermore, if sentiment analysis detects that the user is anxious, the system autonomously optimizes itself by using a prompt message such as, "The user's current emotional state has been detected as 'anxious'. Please provide an alternative plan and reassure them."

[0430] In this way, the entire system realizes a form of network management and support that is attentive to the user's emotions.

[0431] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0432] Step 1:

[0433] The user provides emotional state data through voice, facial expressions, or text input. The server collects this data using a dedicated speech recognition module or facial expression analysis software. The input for this step is raw emotional data, and the output is processed emotional information. The server analyzes the collected data to identify the user's emotional state (e.g., anxiety, reassurance).

[0434] Step 2:

[0435] The server presents the user with questions generated using a large-scale language model. The generative AI model dynamically generates appropriate questions regarding network requirements and collects specific information from the user. The input for this step is processed sentiment information, and the output is the user's network requirements. The server adjusts the content and tone of the questions to match the user's emotions.

[0436] Step 3:

[0437] The server uses collected requirements and sentiment data to activate an artificial intelligence agent that generates the optimal network configuration. The input is user requirements and sentiment data, and the output is network configuration data. The agent designs the optimized configuration while taking sentiment data into consideration.

[0438] Step 4:

[0439] The generated network configuration is automatically applied from the server to the user's terminal. In this step, network configuration data is used as input, and the settings on the terminal are applied as output. The server reflects the settings through the terminal's information equipment.

[0440] Step 5:

[0441] The server monitors information usage data in real time and checks for any anomalies. The input is real-time information usage data, and the output is the anomaly detection result. If an anomaly is detected, the server provides an explanation of the situation and solutions according to the user's emotional state.

[0442] Step 6:

[0443] The server generates prompt messages based on the user's emotions and provides alternative plans or reassuring information as needed. The input is the anomaly detection result and emotion information, and the output is an appropriate prompt message and specific countermeasures. For example, the server might generate and present a message such as, "The user's current emotional state has been detected as 'anxious'. Please provide alternative plans and reassure the user."

[0444] 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.

[0445] 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.

[0446] 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.

[0447] [Third Embodiment]

[0448] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0449] 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.

[0450] 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).

[0451] 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.

[0452] 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.

[0453] 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).

[0454] 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.

[0455] 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.

[0456] 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.

[0457] 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.

[0458] 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.

[0459] 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".

[0460] Embodiments of the present invention provide a system that allows users without network expertise to autonomously and efficiently optimize and manage network configurations across multiple locations.

[0461] At the heart of this system is a server-based program that collects user requirements and generates the optimal network configuration based on them. The server first uses LLM (Large-Scale Language Model) technology to present appropriate questions to the user. This allows the server to obtain information from the user regarding the network's purpose, scale, and preferred services.

[0462] Based on the information obtained, the server's AI agent automatically generates the optimal network configuration. This network configuration achieves high efficiency and reliability by referencing pre-learned best practices and configuration patterns. The generated configuration is sent to the terminal and executed automatically.

[0463] Furthermore, the server monitors network data in real time and optimizes performance according to usage. If a network anomaly is detected, the server quickly takes corrective action and reallocates resources to resolve the problem. This ensures that network stability is always maintained.

[0464] This system also has the ability to predict future network demand by analyzing historical data and propose expansion plans. This allows users to manage their network assets from a long-term perspective and achieve efficient expansion.

[0465] As a concrete example, when a company uses this system to establish three new locations, it can immediately deploy an autonomously constructed and efficient network. Furthermore, as the business expands or contracts, the server automatically suggests network reconfigurations, ensuring that the optimal network environment is always maintained.

[0466] As described above, the present invention offers the excellent effect of reducing the effort involved in complex network design and operation, thereby improving cost efficiency.

[0467] The following describes the processing flow.

[0468] Step 1:

[0469] The server uses a large-scale language model to generate and present multiple-choice questions to the user to identify network requirements. Through these questions, it collects information from the user such as the desired network size, the importance of the locations to be connected, and the types of applications that will be used.

[0470] Step 2:

[0471] The user answers questions presented by the server. This provides the server with the specific requirements and conditions necessary for network management.

[0472] Step 3:

[0473] The server uses an artificial intelligence agent to generate the optimal network configuration based on the collected user requirements. This generation process references a variety of pre-trained network configuration patterns and best practices.

[0474] Step 4:

[0475] The server sends the generated network configuration information to each terminal. The terminal receives this information and automatically applies the network device settings.

[0476] Step 5:

[0477] The server monitors network usage in real time, constantly observing data flow and bandwidth utilization within the network.

[0478] Step 6:

[0479] If a network anomaly occurs, the server will autonomously detect the anomaly and initiate a troubleshooting process. This includes identifying the problem area and reallocating resources.

[0480] Step 7:

[0481] The server accumulates and analyzes historical network usage data to predict future network demand. Based on this information, it proposes network expansion plans to the user.

[0482] Step 8:

[0483] Users can review the network expansion plan provided by the server, accept the proposals as needed, and update their network configuration.

[0484] (Example 1)

[0485] 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."

[0486] Operating modern communication networks is extremely complex, making effective network configuration and management difficult, especially for users without specialized communication expertise. Furthermore, insufficient resources and time are often available to quickly optimize for fluctuating network environments, potentially compromising network efficiency and reliability. Additionally, predicting future network demand and planning expansions is challenging, posing a significant obstacle to optimal long-term operation.

[0487] 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.

[0488] In this invention, the server includes data processing means for forming natural language questions to obtain information from users, computation means for analyzing the obtained information to generate an efficient and reliable communication network configuration, and application means for automatically applying the generated communication network configuration to information devices. This enables autonomous and efficient optimization and management of the communication network even without specialized communication knowledge. Furthermore, it allows for the formulation of expansion plans based on real-time monitoring and forecasting of future demand, thereby realizing stable long-term operation of the communication network.

[0489] "User" refers to a person or organization that uses communication networks or information technology, and includes users who do not possess specialized knowledge.

[0490] A "natural language question" refers to a question generated in human language so that users can easily understand and answer it.

[0491] "Data processing means" refers to technical methods and processes for collecting and analyzing information from users.

[0492] "Network configuration" refers to the design and setup of a network, and is the state of a network optimized based on specific requirements.

[0493] "Computational means" refers to technical methods for analyzing given information and generating the optimal network configuration.

[0494] "Information equipment" refers to all devices used within a network, including hardware such as routers and switches.

[0495] "Application means" refers to methods and techniques for reflecting the generated network configuration on actual network devices.

[0496] "Monitoring measures" refer to technical methods and systems that observe the state of a network in real time and detect anomalies.

[0497] "Planning tools" refer to methods and systems for predicting future network demand and formulating expansion plans based on that prediction.

[0498] This invention provides an autonomous system for users without specialized knowledge to efficiently manage communication networks. It is primarily server-centric and implemented using the various hardware and software described below.

[0499] The server first uses a generative AI model to collect necessary information from the user through natural language questions. For example, in response to a need to build a small network environment, the server generates specific questions such as "What devices will be connected to the network?" or "Are there any priorities for specific applications?" LLM technology is used to create these prompts, generating appropriate questions based on the user's input.

[0500] Next, the server uses the collected information and an AI agent acting as a computational tool to generate an efficient and reliable communication network configuration. In this process, common frameworks such as TensorFlow and PyTorch are used as machine learning platforms, and the optimal configuration is designed while referring to past best practice datasets.

[0501] The generated network configuration is applied to network devices, which are information devices—for example, routers and switches. The server sends the configuration file to the terminal, and the terminal automatically updates its settings. While JSON or YAML format configuration files are used, the user does not need to directly manipulate them; the entire process is automated through the application mechanism.

[0502] Furthermore, the server uses monitoring tools to monitor the network in real time. For example, it uses Nagios or Zabbix as monitoring tools to immediately respond to traffic anomalies or device failures. This includes rerouting and traffic rebalancing.

[0503] Finally, the server analyzes historical network data, uses planning tools to predict future network demand, and proposes expansion plans to the user. In this process, the system processes instructions such as, "Based on data from the past six months, predict future traffic increases and propose a response plan."

[0504] Thus, the present invention automates the procedures necessary for managing a communication network, making the system easily accessible to users.

[0505] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0506] Step 1:

[0507] The server uses a generative AI model to create prompts and presents the user with natural language questions for information gathering.

[0508] Specific operation: The server receives the user's initial request and generates appropriate questions based on that request. For example, upon receiving a request such as "We need to set up a network at a new location," the server will generate specific questions such as "What communication speed is required?"

[0509] Input: User requests or needs (e.g., network configuration required for a new site)

[0510] Output: A list of specific questions for the user (written in natural language)

[0511] Step 2:

[0512] The user answers questions provided by the server, and the server collects information based on those answers.

[0513] Specific operation: The user answers the presented questions regarding the purpose, scale, and required services of network usage. The server receives this data and incorporates it as foundational data for the next processing step.

[0514] Input: User response data (e.g., required communication speed and type of connected device)

[0515] Output: Structured user request data for analysis

[0516] Step 3:

[0517] Based on the collected information, the server uses an AI agent to generate the optimal network configuration plan.

[0518] Specific operation: The server uses a machine learning platform to process the collected information and design the network configuration. It uses TensorFlow and PyTorch to optimize while referencing past configuration patterns. At this stage, best practices suitable for the network requirements are selected.

[0519] Input: Structured user request data

[0520] Output: Generated network configuration plan (in JSON or YAML format)

[0521] Step 4:

[0522] The network configuration plan generated by the server is delivered to the terminal, and the terminal automatically applies the settings to the network devices.

[0523] Specific operation: The terminal receives configuration files sent from the server and automatically applies settings to network devices such as routers and switches. This allows users to build a network without performing detailed technical operations.

[0524] Input: Network configuration plan from the server

[0525] Output: Settings applied to the network device

[0526] Step 5:

[0527] The server monitors the network in real time and automatically corrects any abnormalities.

[0528] Specific operation: The server monitors traffic conditions using monitoring tools (such as Nagios or Zabbix). If an anomaly is detected, the server immediately changes routes or adjusts bandwidth.

[0529] Input: Real-time network traffic data

[0530] Output: Stabilized network status after anomaly correction.

[0531] Step 6:

[0532] The server analyzes historical data, predicts future network demand, and proposes expansion plans to users.

[0533] Specific operation: The server analyzes accumulated network usage data to predict increased demand and appropriate expansion timing. It then presents the user with the optimal expansion plan.

[0534] Input: Past network usage data

[0535] Output: Future network demand forecast and proposed plan

[0536] (Application Example 1)

[0537] 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."

[0538] Configuring and managing networks and communications requires specialized knowledge and is a complex and burdensome task for many organizations. Furthermore, manual operations lack responsiveness and can compromise convenience, especially in situations where real-time optimization and anomaly detection are required. To address this, there is a need for a system that allows even users without specialized knowledge to efficiently optimize and manage networks.

[0539] 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.

[0540] In this invention, the server includes means for presenting information generated using large-scale language technology to collect communication requirements from users, means for using an artificial intelligence agent to generate an optimal communication configuration based on the collected requirements, and means for automatically applying the generated communication configuration to the device. This enables even users without specialized knowledge to efficiently optimize the communication configuration and perform real-time management and problem solving.

[0541] A "user" is an entity that utilizes a communication system to manage and optimize it.

[0542] "Communication requirements" refer to the conditions and demands that users have for a communication system, and the system must be configured accordingly.

[0543] "Large-scale language technology" refers to advanced language models used to process information from users through natural language processing.

[0544] "Means of presenting information" refers to functions that display interfaces and questions generated using large-scale language technologies to the user.

[0545] An "artificial intelligence agent" is a program that generates the optimal communication configuration based on collected requirements.

[0546] "Device" refers to the hardware or software used to apply the generated communication configuration.

[0547] "Real-time management" is the process of immediately analyzing communication data and maintaining it in a state where appropriate responses and optimizations can be made.

[0548] "Problem solving" refers to identifying abnormalities or errors in communication systems and taking prompt and appropriate countermeasures.

[0549] A system implementing this invention consists of a server equipped with a program that includes various functions such as communication requirements collection, information presentation, configuration optimization, and real-time management, and a corresponding terminal.

[0550] The server first provides an intuitive interface for users through a means of presenting information using large-scale language technology. Users can input communication requirements through this interface. For example, a user might input, "We are a medium-sized business and want to ensure a secure connection for remote work."

[0551] Next, the server utilizes an artificial intelligence agent to generate the optimal communication configuration based on the user's requirements. This agent has the ability to achieve a highly efficient and reliable array by referencing past best practices and learned configuration patterns.

[0552] The generated communication configuration is then automatically applied to the terminal. This allows users to enjoy an optimized communication environment without having to worry about a lack of technical expertise.

[0553] Furthermore, the server monitors communication data in real time and immediately initiates problem-solving processes if it detects an anomaly. For example, if an unexpected increase in traffic occurs, it will respond quickly by reallocating resources.

[0554] Furthermore, by leveraging past usage data, the system predicts future communication demands and proposes expansion plans to users. This streamlines long-term asset management.

[0555] A concrete example of a prompt message is its use in generating new questions based on information provided by the user. For example, it might look like this: "User information: Medium-sized company, primary use of cloud services is file sharing. What is the next question to ask?"

[0556] This system aims to reduce the complexity of designing and operating communication environments and to support efficient management.

[0557] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0558] Step 1:

[0559] The server uses large-scale language technology to generate a user interface and displays questions to present communication requirements to the user. These prompts are generated based on basic information entered by the user. The input includes the user's initial communication requirements, and the output provides questions for the user to enter specific requirements.

[0560] Step 2:

[0561] The user inputs detailed communication requirements through an interface provided by the server. The user-specified conditions include requirements regarding the scale of the communication environment and specific functionalities. The input represents the user's desired communication conditions, but these are not yet optimized. The output forms a set of specific requirements for optimization.

[0562] Step 3:

[0563] The server analyzes the user's input requirements and proposes the optimal communication configuration using an artificial intelligence agent. Here, it compares the requirements with previously learned best practices to generate an optimized configuration. The input to this process is the specific communication requirements obtained in the previous step, and the output is the optimal communication configuration.

[0564] Step 4:

[0565] The generated communication configuration is automatically applied to the terminal. The terminal incorporates the received configuration into the device and provides a usable communication environment to the user. The input is the configured communication parameters, and the output is the communication network environment readily available to the user.

[0566] Step 5:

[0567] The server monitors communication data in real time and automatically initiates problem resolution processing if an anomaly is detected. Specifically, it detects and analyzes the differences between the data detected as an anomaly and the normal communication data, and quickly resolves the problem. It also reallocates resources to avoid service interruptions. The input is communication data collected in real time, and the output is the solution to the anomaly found, or the communication state after optimization.

[0568] Step 6:

[0569] The server analyzes past communication data, predicts future demand, and presents a communication expansion plan for the user. It analyzes past data patterns to predict what equipment will be needed to meet the user's future requirements. The input is historical communication data, and the output is a proposed plan including the next actions the user should take.

[0570] 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.

[0571] Embodiments of the present invention provide a system incorporating an emotion engine for recognizing user emotions and optimizing network management processes based on those emotions. In addition to conventional network configuration and management functions, this system aims to improve the user experience through emotion recognition.

[0572] Specifically, this system interacts with the user and uses an emotion engine to analyze the user's emotional state based on their voice, facial expressions, and text input. When the user presents network requirements, the server appropriately adjusts the content and tone of the questions according to the user's emotions. This process allows the user to communicate their needs accurately and without stress.

[0573] The server uses an AI agent to generate the optimal network configuration based on collected user requirements and sentiment data. By including feedback corrected by the sentiment engine, configuration suggestions that enhance user satisfaction become possible. The generated configuration is then automatically delivered to the terminal and the settings are applied.

[0574] Furthermore, the server performs real-time network monitoring and troubleshoots for anomalies, providing responses tailored to the user's emotional state. For example, if a user is feeling anxious, the server will provide detailed explanations of the problem's progress and potential solutions, striving to reassure them.

[0575] As a concrete example of this system, consider a scenario where a user who easily experiences stress from network configurations uses the system. The server detects the user's emotional state in advance and adjusts the interface to reduce that stress. Furthermore, even if the generated network configuration is complex, the system helps the user understand it through easy-to-understand explanations tailored to their emotional state, allowing them to proceed with implementation with confidence.

[0576] With these features, the system allows users to smoothly configure and operate the network without requiring specialized knowledge. The introduction of an emotional engine enables even more user-centric network management, improving overall operational efficiency and customer satisfaction.

[0577] The following describes the processing flow.

[0578] Step 1:

[0579] The user accesses the system interface to input network requirements. During this process, the user's emotional state is collected through text input, voice, or facial recognition.

[0580] Step 2:

[0581] The server uses an emotion engine to analyze the user's emotional state, determining whether the user is relaxed, stressed, etc. Based on this information, it dynamically adjusts the wording of questions and answer choices to present the user with the most appropriate questions.

[0582] Step 3:

[0583] The user answers pre-configured questions presented by the server. This ensures that the server receives detailed information about the user's network requirements and current needs.

[0584] Step 4:

[0585] The server uses an artificial intelligence agent to generate the optimal network configuration based on collected user requirements and sentiment data. By considering sentiment data, better suggestions that meet the user's needs are formed.

[0586] Step 5:

[0587] The generated network configuration is automatically sent to the terminal, and the associated network devices are configured. Emotionally responsive explanations and guidance are provided to the user, ensuring a smooth network setup process.

[0588] Step 6:

[0589] The server monitors data in real time during network operation, taking into account the user's emotional state to perform early detection and troubleshooting of anomalies. For example, if a user is feeling anxious, the server provides the user with information including the progress of the problem and reassurance.

[0590] Step 7:

[0591] Based on past network usage and sentiment data, the server predicts future network demand and proposes expansion plans to users. These proposals are presented in a way that takes user sentiment into consideration, supporting long-term management planning.

[0592] (Example 2)

[0593] 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."

[0594] Traditional network management systems operate without considering the user's emotional state, leading to problems such as user stress and insufficient understanding during network configuration and troubleshooting. Furthermore, a lack of support and interface adjustments tailored to user emotions made it difficult to improve the user experience. These challenges contributed to a decline in overall operational efficiency and customer satisfaction.

[0595] 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.

[0596] In this invention, the server includes means for collecting and analyzing the user's emotional state, means for adjusting the interface display content and sound based on the analyzed emotions, and means for using an artificial intelligence agent to generate an optimal network configuration based on the collected requirements and emotional data. This enables network management that takes user emotions into consideration and a smooth, stress-free operating experience.

[0597] A "user" is an individual or group that uses a network management system to meet their own network requirements.

[0598] "Emotional state" refers to the state of a user's emotions as determined from their voice, facial expressions, text, etc., and is used to improve the user experience.

[0599] An "interface" refers to the screen display and audio guidance that users use to interact with a network management system.

[0600] An "information processing device" refers to hardware or software that receives network configurations and performs settings based on them.

[0601] An "artificial intelligence agent" is a program or system that generates the optimal network configuration based on data collected from users.

[0602] A "large-scale language model" is a large-scale neural network-based model used to collect user requirements using natural language processing.

[0603] "Network usage data" refers to data collected in real time regarding network performance and traffic.

[0604] This invention is a system that improves the user experience by analyzing the emotional state of users and utilizing that information for network management. This system primarily operates between a server, a terminal, and a user.

[0605] The server first uses an emotion engine to collect user voice, facial expressions, and text data. This emotion engine is software equipped with a generative AI model that acquires data from hardware such as microphones and cameras. It analyzes the user's emotional state in real time and dynamically adjusts the interface based on the results. Interface adjustments include the content of on-screen messages and the tone of voice guidance.

[0606] The user enters their network requirements according to the prompts. For example, a prompt such as "Please specify if you would like to improve your network speed" might appear on the screen. This allows the user to clearly indicate their needs.

[0607] The server analyzes user requirements using a large-scale language model and generates the optimal network configuration using an artificial intelligence agent. This configuration is automatically applied to the terminal, which is an information processing device, and the settings are executed. The terminal immediately implements the generated settings, improving network performance.

[0608] Furthermore, the server monitors network usage data in real time and automatically detects anomalies. Troubleshooting is performed while considering the user's feelings, and escalates to expert support as needed. Throughout this process, appropriate information is provided to reassure the user.

[0609] In this way, a network management system that integrates user emotions allows users to have a stress-free network operation experience, and is expected to improve overall operational efficiency and customer satisfaction.

[0610] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0611] Step 1:

[0612] The user initiates a dialogue to configure network settings or troubleshoot problems. During this process, the user's voice, facial expressions, and text input are fed into the emotion analysis system. The server receives this data and uses a generative AI model to analyze the user's emotional state in real time. The analysis extracts the user's perceived stress levels and satisfaction levels.

[0613] Step 2:

[0614] The server adjusts the interface displayed to the user based on the analyzed sentiment data. Specifically, it softens the tone of on-screen messages and appropriately modifies voice guidance to reduce user stress. This allows the user to continue the interaction in a more relaxed state.

[0615] Step 3:

[0616] The user enters network requirements based on prompts provided by the server. For example, a prompt might say, "Please tell us about any dissatisfactions or areas for improvement regarding your current network connection." The user's input (requirements) is then translated into specific network needs through analysis of the server's large-scale language model.

[0617] Step 4:

[0618] The server uses an artificial intelligence agent to generate the optimal network configuration based on requirements and sentiment data collected from users. The AI ​​agent processes this input information and creates a configuration proposal that reflects the user's needs and emotions. The generated configuration proposal is output to an information processing device.

[0619] Step 5:

[0620] The terminal receives the proposed network configuration from the server and automatically applies it. The terminal then executes this configuration to improve the network environment. It also notifies the user when the configuration is complete. This allows the user to confidently monitor the network status.

[0621] Step 6:

[0622] The server monitors network usage data in real time and detects anomalies. If an anomaly is detected, the server provides appropriate troubleshooting, taking into account user sentiment data. If specific support is needed, the issue is escalated to a specialized service. Throughout this process, the user is notified of the problem's progress at each stage, providing peace of mind.

[0623] (Application Example 2)

[0624] 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."

[0625] Currently, many network management systems offer a uniform interface and configuration process, lacking mechanisms to alleviate user stress and anxiety. As a result, users may become dissatisfied with network configuration and management, and this can lead to misunderstandings and distrust, especially among emotionally sensitive users. Furthermore, if explanations and responses to network anomalies are not appropriate to the user's emotional state, it can trigger further anxiety and dissatisfaction. Solving these problems is essential.

[0626] 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.

[0627] In this invention, the server includes means for recognizing the user's emotional state and dynamically adjusting the interface for network requirements collection according to the user's emotions; autonomous automation means for selecting a notification method considering the emotional state; and means for automatically proposing resource allocation based on emotional data. This enables network management that is sensitive to the user's emotions, improving the user experience and optimizing operational efficiency.

[0628] "User emotional state" refers to the emotional state of a user, analyzed from their voice, facial expressions, text input, etc.

[0629] The "interface for collecting network requirements" refers to the screen or method used to collect network-related requirements from users.

[0630] "Information equipment" refers to electronic devices used for network configuration, data processing, and other similar tasks.

[0631] "Information usage data" refers to data generated when users use networks or information services.

[0632] "Real-time monitoring" refers to the process of continuously monitoring the status of data and systems.

[0633] "Providing explanations tailored to the user's emotional state" means providing appropriate explanations that take into account the user's current emotional state.

[0634] "Autonomous problem-solving" refers to the process of automatically resolving problems without human intervention.

[0635] "Network expansion planning" refers to developing a plan to improve network capabilities in anticipation of future demand.

[0636] "Emotionally tailored explanations" means providing information in a way that is easy for users to understand, in accordance with their emotional state.

[0637] This system detects user emotions and optimizes network management based on them. The server uses speech recognition modules and facial expression analysis software to collect emotion data from the user's voice, facial expressions, and text. Specific examples include commonly used speech recognition APIs and emotion analysis APIs. The server processes this data, presents the user with questions generated using a large-scale language model, and collects network requirements.

[0638] The server then uses collected requirements and sentiment data to generate an optimal network configuration using an artificial intelligence agent. The generated configuration is automatically applied to the user's device, which may be a smartphone or computer. Through this device, the server monitors information usage data in real time and detects anomalies. If the user is feeling anxious or stressed, the server provides the user with an emotion-appropriate response, for example, by visually showing a solution to the problem to provide reassurance.

[0639] As a concrete example of this system, when informing users of delays in public transport, the server provides detailed alternative route information in real time to alleviate user anxiety. Furthermore, if sentiment analysis detects that the user is anxious, the system autonomously optimizes itself by using a prompt message such as, "The user's current emotional state has been detected as 'anxious'. Please provide an alternative plan and reassure them."

[0640] In this way, the entire system realizes a form of network management and support that is attentive to the user's emotions.

[0641] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0642] Step 1:

[0643] The user provides emotional state data through voice, facial expressions, or text input. The server collects this data using a dedicated speech recognition module or facial expression analysis software. The input for this step is raw emotional data, and the output is processed emotional information. The server analyzes the collected data to identify the user's emotional state (e.g., anxiety, reassurance).

[0644] Step 2:

[0645] The server presents the user with questions generated using a large-scale language model. The generative AI model dynamically generates appropriate questions regarding network requirements and collects specific information from the user. The input for this step is processed sentiment information, and the output is the user's network requirements. The server adjusts the content and tone of the questions to match the user's emotions.

[0646] Step 3:

[0647] The server uses collected requirements and sentiment data to activate an artificial intelligence agent that generates the optimal network configuration. The input is user requirements and sentiment data, and the output is network configuration data. The agent designs the optimized configuration while taking sentiment data into consideration.

[0648] Step 4:

[0649] The generated network configuration is automatically applied from the server to the user's terminal. In this step, network configuration data is used as input, and the settings on the terminal are applied as output. The server reflects the settings through the terminal's information equipment.

[0650] Step 5:

[0651] The server monitors information usage data in real time and checks for any anomalies. The input is real-time information usage data, and the output is the anomaly detection result. If an anomaly is detected, the server provides an explanation of the situation and solutions according to the user's emotional state.

[0652] Step 6:

[0653] The server generates prompt messages based on the user's emotions and provides alternative plans or reassuring information as needed. The input is the anomaly detection result and emotion information, and the output is an appropriate prompt message and specific countermeasures. For example, the server might generate and present a message such as, "The user's current emotional state has been detected as 'anxious'. Please provide alternative plans and reassure the user."

[0654] 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.

[0655] 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.

[0656] 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.

[0657] [Fourth Embodiment]

[0658] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0659] 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.

[0660] 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).

[0661] 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.

[0662] 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.

[0663] 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).

[0664] 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.

[0665] 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.

[0666] 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.

[0667] 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.

[0668] 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.

[0669] 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.

[0670] 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".

[0671] Embodiments of the present invention provide a system that allows users without network expertise to autonomously and efficiently optimize and manage network configurations across multiple locations.

[0672] At the heart of this system is a server-based program that collects user requirements and generates the optimal network configuration based on them. The server first uses LLM (Large-Scale Language Model) technology to present appropriate questions to the user. This allows the server to obtain information from the user regarding the network's purpose, scale, and preferred services.

[0673] Based on the information obtained, the server's AI agent automatically generates the optimal network configuration. This network configuration achieves high efficiency and reliability by referencing pre-learned best practices and configuration patterns. The generated configuration is sent to the terminal and executed automatically.

[0674] Furthermore, the server monitors network data in real time and optimizes performance according to usage. If a network anomaly is detected, the server quickly takes corrective action and reallocates resources to resolve the problem. This ensures that network stability is always maintained.

[0675] This system also has the ability to predict future network demand by analyzing historical data and propose expansion plans. This allows users to manage their network assets from a long-term perspective and achieve efficient expansion.

[0676] As a concrete example, when a company uses this system to establish three new locations, it can immediately deploy an autonomously constructed and efficient network. Furthermore, as the business expands or contracts, the server automatically suggests network reconfigurations, ensuring that the optimal network environment is always maintained.

[0677] As described above, the present invention offers the excellent effect of reducing the effort involved in complex network design and operation, thereby improving cost efficiency.

[0678] The following describes the processing flow.

[0679] Step 1:

[0680] The server uses a large-scale language model to generate and present multiple-choice questions to the user to identify network requirements. Through these questions, it collects information from the user such as the desired network size, the importance of the locations to be connected, and the types of applications that will be used.

[0681] Step 2:

[0682] The user answers questions presented by the server. This provides the server with the specific requirements and conditions necessary for network management.

[0683] Step 3:

[0684] The server uses an artificial intelligence agent to generate the optimal network configuration based on the collected user requirements. This generation process references a variety of pre-trained network configuration patterns and best practices.

[0685] Step 4:

[0686] The server sends the generated network configuration information to each terminal. The terminal receives this information and automatically applies the network device settings.

[0687] Step 5:

[0688] The server monitors network usage in real time, constantly observing data flow and bandwidth utilization within the network.

[0689] Step 6:

[0690] If a network anomaly occurs, the server will autonomously detect the anomaly and initiate a troubleshooting process. This includes identifying the problem area and reallocating resources.

[0691] Step 7:

[0692] The server accumulates and analyzes historical network usage data to predict future network demand. Based on this information, it proposes network expansion plans to the user.

[0693] Step 8:

[0694] Users can review the network expansion plan provided by the server, accept the proposals as needed, and update their network configuration.

[0695] (Example 1)

[0696] 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".

[0697] Operating modern communication networks is extremely complex, making effective network configuration and management difficult, especially for users without specialized communication expertise. Furthermore, insufficient resources and time are often available to quickly optimize for fluctuating network environments, potentially compromising network efficiency and reliability. Additionally, predicting future network demand and planning expansions is challenging, posing a significant obstacle to optimal long-term operation.

[0698] 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.

[0699] In this invention, the server includes data processing means for forming natural language questions to obtain information from users, computation means for analyzing the obtained information to generate an efficient and reliable communication network configuration, and application means for automatically applying the generated communication network configuration to information devices. This enables autonomous and efficient optimization and management of the communication network even without specialized communication knowledge. Furthermore, it allows for the formulation of expansion plans based on real-time monitoring and forecasting of future demand, thereby realizing stable long-term operation of the communication network.

[0700] "User" refers to a person or organization that uses communication networks or information technology, and includes users who do not possess specialized knowledge.

[0701] A "natural language question" refers to a question generated in human language so that users can easily understand and answer it.

[0702] "Data processing means" refers to technical methods and processes for collecting and analyzing information from users.

[0703] "Network configuration" refers to the design and setup of a network, and is the state of a network optimized based on specific requirements.

[0704] "Computational means" refers to technical methods for analyzing given information and generating the optimal network configuration.

[0705] "Information equipment" refers to all devices used within a network, including hardware such as routers and switches.

[0706] "Application means" refers to methods and techniques for reflecting the generated network configuration on actual network devices.

[0707] "Monitoring measures" refer to technical methods and systems that observe the state of a network in real time and detect anomalies.

[0708] "Planning tools" refer to methods and systems for predicting future network demand and formulating expansion plans based on that prediction.

[0709] This invention provides an autonomous system for users without specialized knowledge to efficiently manage communication networks. It is primarily server-centric and implemented using the various hardware and software described below.

[0710] The server first uses a generative AI model to collect necessary information from the user through natural language questions. For example, in response to a need to build a small network environment, the server generates specific questions such as "What devices will be connected to the network?" or "Are there any priorities for specific applications?" LLM technology is used to create these prompts, generating appropriate questions based on the user's input.

[0711] Next, the server uses the collected information and an AI agent acting as a computational tool to generate an efficient and reliable communication network configuration. In this process, common frameworks such as TensorFlow and PyTorch are used as machine learning platforms, and the optimal configuration is designed while referring to past best practice datasets.

[0712] The generated network configuration is applied to network devices, which are information devices—for example, routers and switches. The server sends the configuration file to the terminal, and the terminal automatically updates its settings. While JSON or YAML format configuration files are used, the user does not need to directly manipulate them; the entire process is automated through the application mechanism.

[0713] Furthermore, the server uses monitoring tools to monitor the network in real time. For example, it uses Nagios or Zabbix as monitoring tools to immediately respond to traffic anomalies or device failures. This includes rerouting and traffic rebalancing.

[0714] Finally, the server analyzes historical network data, uses planning tools to predict future network demand, and proposes expansion plans to the user. In this process, the system processes instructions such as, "Based on data from the past six months, predict future traffic increases and propose a response plan."

[0715] Thus, the present invention automates the procedures necessary for managing a communication network, making the system easily accessible to users.

[0716] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0717] Step 1:

[0718] The server uses a generative AI model to create prompts and presents the user with natural language questions for information gathering.

[0719] Specific operation: The server receives the user's initial request and generates appropriate questions based on that request. For example, upon receiving a request such as "We need to set up a network at a new location," the server will generate specific questions such as "What communication speed is required?"

[0720] Input: User requests or needs (e.g., network configuration required for a new site)

[0721] Output: A list of specific questions for the user (written in natural language)

[0722] Step 2:

[0723] The user answers questions provided by the server, and the server collects information based on those answers.

[0724] Specific operation: The user answers the presented questions regarding the purpose, scale, and required services of network usage. The server receives this data and incorporates it as foundational data for the next processing step.

[0725] Input: User response data (e.g., required communication speed and type of connected device)

[0726] Output: Structured user request data for analysis

[0727] Step 3:

[0728] Based on the collected information, the server uses an AI agent to generate the optimal network configuration plan.

[0729] Specific operation: The server uses a machine learning platform to process the collected information and design the network configuration. It uses TensorFlow and PyTorch to optimize while referencing past configuration patterns. At this stage, best practices suitable for the network requirements are selected.

[0730] Input: Structured user request data

[0731] Output: Generated network configuration plan (in JSON or YAML format)

[0732] Step 4:

[0733] The network configuration plan generated by the server is delivered to the terminal, and the terminal automatically applies the settings to the network devices.

[0734] Specific operation: The terminal receives configuration files sent from the server and automatically applies settings to network devices such as routers and switches. This allows users to build a network without performing detailed technical operations.

[0735] Input: Network configuration plan from the server

[0736] Output: Settings applied to the network device

[0737] Step 5:

[0738] The server monitors the network in real time and automatically corrects any abnormalities.

[0739] Specific operation: The server monitors traffic conditions using monitoring tools (such as Nagios or Zabbix). If an anomaly is detected, the server immediately changes routes or adjusts bandwidth.

[0740] Input: Real-time network traffic data

[0741] Output: Stabilized network status after anomaly correction.

[0742] Step 6:

[0743] The server analyzes historical data, predicts future network demand, and proposes expansion plans to users.

[0744] Specific operation: The server analyzes accumulated network usage data to predict increased demand and appropriate expansion timing. It then presents the user with the optimal expansion plan.

[0745] Input: Past network usage data

[0746] Output: Future network demand forecast and proposed plan

[0747] (Application Example 1)

[0748] 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".

[0749] Configuring and managing networks and communications requires specialized knowledge and is a complex and burdensome task for many organizations. Furthermore, manual operations lack responsiveness and can compromise convenience, especially in situations where real-time optimization and anomaly detection are required. To address this, there is a need for a system that allows even users without specialized knowledge to efficiently optimize and manage networks.

[0750] 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.

[0751] In this invention, the server includes means for presenting information generated using large-scale language technology to collect communication requirements from users, means for using an artificial intelligence agent to generate an optimal communication configuration based on the collected requirements, and means for automatically applying the generated communication configuration to the device. This enables even users without specialized knowledge to efficiently optimize the communication configuration and perform real-time management and problem solving.

[0752] A "user" is an entity that utilizes a communication system to manage and optimize it.

[0753] "Communication requirements" refer to the conditions and demands that users have for a communication system, and the system must be configured accordingly.

[0754] "Large-scale language technology" refers to advanced language models used to process information from users through natural language processing.

[0755] "Means of presenting information" refers to functions that display interfaces and questions generated using large-scale language technologies to the user.

[0756] An "artificial intelligence agent" is a program that generates the optimal communication configuration based on collected requirements.

[0757] "Device" refers to the hardware or software used to apply the generated communication configuration.

[0758] "Real-time management" is the process of immediately analyzing communication data and maintaining it in a state where appropriate responses and optimizations can be made.

[0759] "Problem solving" refers to identifying abnormalities or errors in communication systems and taking prompt and appropriate countermeasures.

[0760] A system implementing this invention consists of a server equipped with a program that includes various functions such as communication requirements collection, information presentation, configuration optimization, and real-time management, and a corresponding terminal.

[0761] The server first provides an intuitive interface for users through a means of presenting information using large-scale language technology. Users can input communication requirements through this interface. For example, a user might input, "We are a medium-sized business and want to ensure a secure connection for remote work."

[0762] Next, the server utilizes an artificial intelligence agent to generate the optimal communication configuration based on the user's requirements. This agent has the ability to achieve a highly efficient and reliable array by referencing past best practices and learned configuration patterns.

[0763] The generated communication configuration is then automatically applied to the terminal. This allows users to enjoy an optimized communication environment without having to worry about a lack of technical expertise.

[0764] Furthermore, the server monitors communication data in real time and immediately initiates problem-solving processes if it detects an anomaly. For example, if an unexpected increase in traffic occurs, it will respond quickly by reallocating resources.

[0765] Furthermore, by leveraging past usage data, the system predicts future communication demands and proposes expansion plans to users. This streamlines long-term asset management.

[0766] A concrete example of a prompt message is its use in generating new questions based on information provided by the user. For example, it might look like this: "User information: Medium-sized company, primary use of cloud services is file sharing. What is the next question to ask?"

[0767] This system aims to reduce the complexity of designing and operating communication environments and to support efficient management.

[0768] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0769] Step 1:

[0770] The server uses large-scale language technology to generate a user interface and displays questions to present communication requirements to the user. These prompts are generated based on basic information entered by the user. The input includes the user's initial communication requirements, and the output provides questions for the user to enter specific requirements.

[0771] Step 2:

[0772] The user inputs detailed communication requirements through an interface provided by the server. The user-specified conditions include requirements regarding the scale of the communication environment and specific functionalities. The input represents the user's desired communication conditions, but these are not yet optimized. The output forms a set of specific requirements for optimization.

[0773] Step 3:

[0774] The server analyzes the user's input requirements and proposes the optimal communication configuration using an artificial intelligence agent. Here, it compares the requirements with previously learned best practices to generate an optimized configuration. The input to this process is the specific communication requirements obtained in the previous step, and the output is the optimal communication configuration.

[0775] Step 4:

[0776] The generated communication configuration is automatically applied to the terminal. The terminal incorporates the received configuration into the device and provides a usable communication environment to the user. The input is the configured communication parameters, and the output is the communication network environment readily available to the user.

[0777] Step 5:

[0778] The server monitors communication data in real time and automatically initiates problem resolution processing if an anomaly is detected. Specifically, it detects and analyzes the differences between the data detected as an anomaly and the normal communication data, and quickly resolves the problem. It also reallocates resources to avoid service interruptions. The input is communication data collected in real time, and the output is the solution to the anomaly found, or the communication state after optimization.

[0779] Step 6:

[0780] The server analyzes past communication data, predicts future demand, and presents a communication expansion plan for the user. It analyzes past data patterns to predict what equipment will be needed to meet the user's future requirements. The input is historical communication data, and the output is a proposed plan including the next actions the user should take.

[0781] 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.

[0782] Embodiments of the present invention provide a system incorporating an emotion engine for recognizing user emotions and optimizing network management processes based on those emotions. In addition to conventional network configuration and management functions, this system aims to improve the user experience through emotion recognition.

[0783] Specifically, this system interacts with the user and uses an emotion engine to analyze the user's emotional state based on their voice, facial expressions, and text input. When the user presents network requirements, the server appropriately adjusts the content and tone of the questions according to the user's emotions. This process allows the user to communicate their needs accurately and without stress.

[0784] The server uses an AI agent to generate the optimal network configuration based on collected user requirements and sentiment data. By including feedback corrected by the sentiment engine, configuration suggestions that enhance user satisfaction become possible. The generated configuration is then automatically delivered to the terminal and the settings are applied.

[0785] Furthermore, the server performs real-time network monitoring and troubleshoots for anomalies, providing responses tailored to the user's emotional state. For example, if a user is feeling anxious, the server will provide detailed explanations of the problem's progress and potential solutions, striving to reassure them.

[0786] As a concrete example of this system, consider a scenario where a user who easily experiences stress from network configurations uses the system. The server detects the user's emotional state in advance and adjusts the interface to reduce that stress. Furthermore, even if the generated network configuration is complex, the system helps the user understand it through easy-to-understand explanations tailored to their emotional state, allowing them to proceed with implementation with confidence.

[0787] With these features, the system allows users to smoothly configure and operate the network without requiring specialized knowledge. The introduction of an emotional engine enables even more user-centric network management, improving overall operational efficiency and customer satisfaction.

[0788] The following describes the processing flow.

[0789] Step 1:

[0790] The user accesses the system interface to input network requirements. During this process, the user's emotional state is collected through text input, voice, or facial recognition.

[0791] Step 2:

[0792] The server uses an emotion engine to analyze the user's emotional state, determining whether the user is relaxed, stressed, etc. Based on this information, it dynamically adjusts the wording of questions and answer choices to present the user with the most appropriate questions.

[0793] Step 3:

[0794] The user answers pre-configured questions presented by the server. This ensures that the server receives detailed information about the user's network requirements and current needs.

[0795] Step 4:

[0796] The server uses an artificial intelligence agent to generate the optimal network configuration based on collected user requirements and sentiment data. By considering sentiment data, better suggestions that meet the user's needs are formed.

[0797] Step 5:

[0798] The generated network configuration is automatically sent to the terminal, and the associated network devices are configured. Emotionally responsive explanations and guidance are provided to the user, ensuring a smooth network setup process.

[0799] Step 6:

[0800] The server monitors data in real time during network operation, taking into account the user's emotional state to perform early detection and troubleshooting of anomalies. For example, if a user is feeling anxious, the server provides the user with information including the progress of the problem and reassurance.

[0801] Step 7:

[0802] Based on past network usage and sentiment data, the server predicts future network demand and proposes expansion plans to users. These proposals are presented in a way that takes user sentiment into consideration, supporting long-term management planning.

[0803] (Example 2)

[0804] 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".

[0805] Traditional network management systems operate without considering the user's emotional state, leading to problems such as user stress and insufficient understanding during network configuration and troubleshooting. Furthermore, a lack of support and interface adjustments tailored to user emotions made it difficult to improve the user experience. These challenges contributed to a decline in overall operational efficiency and customer satisfaction.

[0806] 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.

[0807] In this invention, the server includes means for collecting and analyzing the user's emotional state, means for adjusting the interface display content and sound based on the analyzed emotions, and means for using an artificial intelligence agent to generate an optimal network configuration based on the collected requirements and emotional data. This enables network management that takes user emotions into consideration and a smooth, stress-free operating experience.

[0808] A "user" is an individual or group that uses a network management system to meet their own network requirements.

[0809] "Emotional state" refers to the state of a user's emotions as determined from their voice, facial expressions, text, etc., and is used to improve the user experience.

[0810] An "interface" refers to the screen display and audio guidance that users use to interact with a network management system.

[0811] An "information processing device" refers to hardware or software that receives network configurations and performs settings based on them.

[0812] An "artificial intelligence agent" is a program or system that generates the optimal network configuration based on data collected from users.

[0813] A "large-scale language model" is a large-scale neural network-based model used to collect user requirements using natural language processing.

[0814] "Network usage data" refers to data collected in real time regarding network performance and traffic.

[0815] This invention is a system that improves the user experience by analyzing the emotional state of users and utilizing that information for network management. This system primarily operates between a server, a terminal, and a user.

[0816] The server first uses an emotion engine to collect user voice, facial expressions, and text data. This emotion engine is software equipped with a generative AI model that acquires data from hardware such as microphones and cameras. It analyzes the user's emotional state in real time and dynamically adjusts the interface based on the results. Interface adjustments include the content of on-screen messages and the tone of voice guidance.

[0817] The user enters their network requirements according to the prompts. For example, a prompt such as "Please specify if you would like to improve your network speed" might appear on the screen. This allows the user to clearly indicate their needs.

[0818] The server analyzes user requirements using a large-scale language model and generates the optimal network configuration using an artificial intelligence agent. This configuration is automatically applied to the terminal, which is an information processing device, and the settings are executed. The terminal immediately implements the generated settings, improving network performance.

[0819] Furthermore, the server monitors network usage data in real time and automatically detects anomalies. Troubleshooting is performed while considering the user's feelings, and escalates to expert support as needed. Throughout this process, appropriate information is provided to reassure the user.

[0820] In this way, a network management system that integrates user emotions allows users to have a stress-free network operation experience, and is expected to improve overall operational efficiency and customer satisfaction.

[0821] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0822] Step 1:

[0823] The user initiates a dialogue to configure network settings or troubleshoot problems. During this process, the user's voice, facial expressions, and text input are fed into the emotion analysis system. The server receives this data and uses a generative AI model to analyze the user's emotional state in real time. The analysis extracts the user's perceived stress levels and satisfaction levels.

[0824] Step 2:

[0825] The server adjusts the interface displayed to the user based on the analyzed sentiment data. Specifically, it softens the tone of on-screen messages and appropriately modifies voice guidance to reduce user stress. This allows the user to continue the interaction in a more relaxed state.

[0826] Step 3:

[0827] The user enters network requirements based on prompts provided by the server. For example, a prompt might say, "Please tell us about any dissatisfactions or areas for improvement regarding your current network connection." The user's input (requirements) is then translated into specific network needs through analysis of the server's large-scale language model.

[0828] Step 4:

[0829] The server uses an artificial intelligence agent to generate the optimal network configuration based on requirements and sentiment data collected from users. The AI ​​agent processes this input information and creates a configuration proposal that reflects the user's needs and emotions. The generated configuration proposal is output to an information processing device.

[0830] Step 5:

[0831] The terminal receives the proposed network configuration from the server and automatically applies it. The terminal then executes this configuration to improve the network environment. It also notifies the user when the configuration is complete. This allows the user to confidently monitor the network status.

[0832] Step 6:

[0833] The server monitors network usage data in real time and detects anomalies. If an anomaly is detected, the server provides appropriate troubleshooting, taking into account user sentiment data. If specific support is needed, the issue is escalated to a specialized service. Throughout this process, the user is notified of the problem's progress at each stage, providing peace of mind.

[0834] (Application Example 2)

[0835] 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".

[0836] Currently, many network management systems offer a uniform interface and configuration process, lacking mechanisms to alleviate user stress and anxiety. As a result, users may become dissatisfied with network configuration and management, and this can lead to misunderstandings and distrust, especially among emotionally sensitive users. Furthermore, if explanations and responses to network anomalies are not appropriate to the user's emotional state, it can trigger further anxiety and dissatisfaction. Solving these problems is essential.

[0837] 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.

[0838] In this invention, the server includes means for recognizing the user's emotional state and dynamically adjusting the interface for network requirements collection according to the user's emotions; autonomous automation means for selecting a notification method considering the emotional state; and means for automatically proposing resource allocation based on emotional data. This enables network management that is sensitive to the user's emotions, improving the user experience and optimizing operational efficiency.

[0839] "User emotional state" refers to the emotional state of a user, analyzed from their voice, facial expressions, text input, etc.

[0840] The "interface for collecting network requirements" refers to the screen or method used to collect network-related requirements from users.

[0841] "Information equipment" refers to electronic devices used for network configuration, data processing, and other similar tasks.

[0842] "Information usage data" refers to data generated when users use networks or information services.

[0843] "Real-time monitoring" refers to the process of continuously monitoring the status of data and systems.

[0844] "Providing explanations tailored to the user's emotional state" means providing appropriate explanations that take into account the user's current emotional state.

[0845] "Autonomous problem-solving" refers to the process of automatically resolving problems without human intervention.

[0846] "Network expansion planning" refers to developing a plan to improve network capabilities in anticipation of future demand.

[0847] "Emotionally tailored explanations" means providing information in a way that is easy for users to understand, in accordance with their emotional state.

[0848] This system detects user emotions and optimizes network management based on them. The server uses speech recognition modules and facial expression analysis software to collect emotion data from the user's voice, facial expressions, and text. Specific examples include commonly used speech recognition APIs and emotion analysis APIs. The server processes this data, presents the user with questions generated using a large-scale language model, and collects network requirements.

[0849] The server then uses collected requirements and sentiment data to generate an optimal network configuration using an artificial intelligence agent. The generated configuration is automatically applied to the user's device, which may be a smartphone or computer. Through this device, the server monitors information usage data in real time and detects anomalies. If the user is feeling anxious or stressed, the server provides the user with an emotion-appropriate response, for example, by visually showing a solution to the problem to provide reassurance.

[0850] As a concrete example of this system, when informing users of delays in public transport, the server provides detailed alternative route information in real time to alleviate user anxiety. Furthermore, if sentiment analysis detects that the user is anxious, the system autonomously optimizes itself by using a prompt message such as, "The user's current emotional state has been detected as 'anxious'. Please provide an alternative plan and reassure them."

[0851] In this way, the entire system realizes a form of network management and support that is attentive to the user's emotions.

[0852] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0853] Step 1:

[0854] The user provides emotional state data through voice, facial expressions, or text input. The server collects this data using a dedicated speech recognition module or facial expression analysis software. The input for this step is raw emotional data, and the output is processed emotional information. The server analyzes the collected data to identify the user's emotional state (e.g., anxiety, reassurance).

[0855] Step 2:

[0856] The server presents the user with questions generated using a large-scale language model. The generative AI model dynamically generates appropriate questions regarding network requirements and collects specific information from the user. The input for this step is processed sentiment information, and the output is the user's network requirements. The server adjusts the content and tone of the questions to match the user's emotions.

[0857] Step 3:

[0858] The server uses collected requirements and sentiment data to activate an artificial intelligence agent that generates the optimal network configuration. The input is user requirements and sentiment data, and the output is network configuration data. The agent designs the optimized configuration while taking sentiment data into consideration.

[0859] Step 4:

[0860] The generated network configuration is automatically applied from the server to the user's terminal. In this step, network configuration data is used as input, and the settings on the terminal are applied as output. The server reflects the settings through the terminal's information equipment.

[0861] Step 5:

[0862] The server monitors information usage data in real time and checks for any anomalies. The input is real-time information usage data, and the output is the anomaly detection result. If an anomaly is detected, the server provides an explanation of the situation and solutions according to the user's emotional state.

[0863] Step 6:

[0864] The server generates prompt messages based on the user's emotions and provides alternative plans or reassuring information as needed. The input is the anomaly detection result and emotion information, and the output is an appropriate prompt message and specific countermeasures. For example, the server might generate and present a message such as, "The user's current emotional state has been detected as 'anxious'. Please provide alternative plans and reassure the user."

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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."

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] 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.

[0882] 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.

[0883] 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.

[0884] 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.

[0885] 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.

[0886] The following is further disclosed regarding the embodiments described above.

[0887] (Claim 1)

[0888] A means of presenting questions generated using a large-scale language model in order to collect network requirements from users,

[0889] A means of using an artificial intelligence agent to generate the optimal network configuration based on collected requirements,

[0890] A means for automatically applying the generated network configuration to network devices,

[0891] A means of monitoring network usage data in real time and autonomously troubleshooting when an anomaly is detected,

[0892] A means to predict future usage based on past network usage data and support network expansion planning,

[0893] A system that includes this.

[0894] (Claim 2)

[0895] The system according to claim 1, which automatically proposes the optimal resource allocation to improve performance and cost efficiency based on network usage data collected in real time.

[0896] (Claim 3)

[0897] The system according to claim 1, characterized by autonomous automation that enables the proposal and application of a network configuration to be carried out without user approval.

[0898] "Example 1"

[0899] (Claim 1)

[0900] A data processing means for forming natural language questions in order to obtain information from the user,

[0901] A computing means for analyzing acquired information to generate an efficient and reliable communication network configuration,

[0902] An application means for automatically applying the generated communication network configuration to an information device,

[0903] A monitoring system that monitors communication network data and autonomously corrects anomalies,

[0904] A planning tool that analyzes past communication network data to predict future demand and facilitates expansion planning,

[0905] A system that includes this.

[0906] (Claim 2)

[0907] The system according to claim 1, which automatically proposes resource allocation to improve performance and cost efficiency based on real-time acquired network data.

[0908] (Claim 3)

[0909] The system according to claim 1, characterized by autonomous operation that proposes and applies a communication network configuration without the user's approval.

[0910] "Application Example 1"

[0911] (Claim 1)

[0912] A means of presenting information generated using large-scale language technology in order to collect communication requirements from users,

[0913] A means of using an artificial intelligence agent to generate the optimal communication configuration based on collected requirements,

[0914] A means for automatically applying the generated communication configuration to the device,

[0915] A means of autonomously resolving problems when anomalies are detected, by monitoring communication usage data in real time.

[0916] A means to predict future usage based on past communication usage data and support the planning of communication expansion,

[0917] A means comprising a management device that monitors the communication status in real time and accepts optimization suggestions,

[0918] A system that includes this.

[0919] (Claim 2)

[0920] The system according to claim 1, which automatically proposes the optimal material distribution to improve performance and resource efficiency based on communication usage data collected in real time.

[0921] (Claim 3)

[0922] The system according to claim 1, characterized by autonomous automation that enables the proposal and application of a communication configuration to be carried out without user approval.

[0923] "Example 2 of combining an emotion engine"

[0924] (Claim 1)

[0925] A means of collecting and analyzing the emotional state of users,

[0926] A means of adjusting the interface display content and sound based on analyzed emotions,

[0927] A means of presenting questions generated using a large-scale language model in order to collect network requirements from users,

[0928] A means of using an artificial intelligence agent to generate the optimal network configuration based on collected requirements and sentiment data,

[0929] A means for automatically applying the generated network configuration to an information processing device,

[0930] A method for monitoring network usage data in real time and troubleshooting while considering emotional states when anomalies are detected,

[0931] A means to predict future usage based on past network usage data and support the planning of data communication expansion,

[0932] A system that includes this.

[0933] (Claim 2)

[0934] The system according to claim 1, which automatically proposes the optimal resource allocation to improve performance and cost efficiency based on network usage data and user sentiment data collected in real time.

[0935] (Claim 3)

[0936] The system according to claim 1, characterized by autonomous automation that enables the proposal and application of a network configuration that reflects the user's emotional state without user approval.

[0937] "Application example 2 when combining with an emotional engine"

[0938] (Claim 1)

[0939] A means of recognizing the user's emotional state and dynamically adjusting the interface during network requirements collection according to the user's emotions,

[0940] A means of presenting questions generated using a large-scale language model in order to collect network requirements from users,

[0941] A means of using an artificial intelligence agent to generate an optimal network configuration based on collected requirements and sentiment data,

[0942] A means for automatically applying the generated network configuration to information devices,

[0943] A means of autonomously addressing problems by monitoring information usage data in real time and providing explanations tailored to emotional states when anomalies are detected,

[0944] A means of predicting future usage based on past information usage data and supporting network expansion plans through explanations tailored to user emotions,

[0945] A system that includes this.

[0946] (Claim 2)

[0947] The system according to claim 1, which automatically proposes the optimal resource allocation to improve performance and cost efficiency based on real-time collected information usage data and sentiment data.

[0948] (Claim 3)

[0949] The system according to claim 1, which enables the proposal and application of a network configuration without user approval, and further features autonomous automation that selects a notification method taking into account emotional state. [Explanation of Symbols]

[0950] 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 presenting questions generated using a large-scale language model in order to collect network requirements from users, A means of using an artificial intelligence agent to generate the optimal network configuration based on collected requirements, A means for automatically applying the generated network configuration to network devices, A means of monitoring network usage data in real time and autonomously troubleshooting when an anomaly is detected, A means to predict future usage based on past network usage data and support network expansion planning, A system that includes this.

2. The system according to claim 1, which automatically proposes the optimal resource allocation to improve performance and cost efficiency based on network usage data collected in real time.

3. The system according to claim 1, characterized by autonomous automation that enables the proposal and application of a network configuration to be carried out without user approval.

Images