system

Abstract

The system according to this embodiment aims to perform self-optimization and automatic adjustment based on network performance data and traffic data. [Solution] The system according to the embodiment comprises a collection unit, a preprocessing unit, a training unit, a monitoring unit, an optimization unit, and an improvement unit. The collection unit collects network performance data and traffic data. The preprocessing unit preprocesses the data collected by the collection unit. The training unit trains a generative AI using the data preprocessed by the preprocessing unit. The monitoring unit uses the generative AI trained by the training unit to monitor the network and build a feedback loop. The optimization unit performs self-optimization and automatic adjustment of network devices based on the data monitored by the monitoring unit. The improvement unit improves the generative AI model using the feedback obtained by the optimization unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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] In the conventional technology, there is a problem that the performance of the network and the collection and optimization of traffic data are often performed manually, and it is difficult to perform efficient self-optimization and automatic adjustment.

[0005] The system according to the embodiment aims to perform self-optimization and automatic adjustment based on network performance data and traffic data.

Means for Solving the Problems

[0006] The system according to the embodiment comprises a data collection unit, a preprocessing unit, a training unit, a monitoring unit, an optimization unit, and an improvement unit. The data collection unit collects network performance data and traffic data. The preprocessing unit preprocesses the data collected by the data collection unit. The training unit trains a generative AI using the data preprocessed by the preprocessing unit. The monitoring unit uses the generative AI trained by the training unit to monitor the network and build a feedback loop. The optimization unit performs self-optimization and automatic adjustment of network devices based on the data monitored by the monitoring unit. The improvement unit improves the generative AI model using the feedback obtained by the optimization unit. [Effects of the Invention]

[0007] The system according to this embodiment can perform self-optimization and automatic adjustment based on network performance data and traffic data. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8]This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] 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), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] 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.

[0013] In the following embodiments, the tagged storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the tagged communication I / F (Interface) is an interface that includes a communication processor and an antenna, etc. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by contact of an indicator (e.g., a pen or a finger, etc.) by detecting the contact of the indicator. The microphone 38B receives user input by voice by detecting the voice of the user. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The network system according to an embodiment of the present invention is a system that incorporates generative AI technology, learns on its own, achieves optimization, and adapts improvements to realize a network that is constantly evolving through the PDCA cycle. This network system consists of the steps of data collection and preprocessing, generative AI training, network monitoring and feedback loop, self-optimization and automatic adjustment, and feedback and model improvement. For example, the network system first performs data collection and preprocessing. It collects network performance data and traffic data and performs the necessary preprocessing. This includes data cleansing, handling missing values, and scaling. Next, the network system trains the generative AI. It trains the generative AI using the collected data to learn network trends and patterns. Since training requires a large amount of data and computing resources, it is necessary to prepare an appropriate environment. After that, the network system builds a network monitoring and feedback loop. It integrates the generative AI into the production environment and builds a network monitoring and feedback loop. Network data is periodically provided to the generative AI to help it understand the current state of the network. The generative AI uses the trained model to predict network performance and traffic patterns. Furthermore, the network system performs self-optimization and automatic adjustment. Based on network trends and patterns predicted by generative AI, network devices perform self-optimization and automatic adjustments. For example, they adjust bandwidth based on predicted network load, identify bottlenecks, and automatically switch routes. Finally, the network system uses feedback and model improvement. Feedback obtained during network operation is used to improve the generative AI model. Network performance and the accuracy of traffic predictions are monitored, and model parameters are adjusted or training data is added as needed. This allows the network system to cope with the increasing complexity of network design and operation, reducing the burden on engineers. It also improves network efficiency and security.This allows network systems to improve network efficiency and security.

[0029] The network system according to the embodiment comprises a data collection unit, a data preprocessing unit, a training unit, a monitoring unit, an optimization unit, and an improvement unit. The data collection unit collects network performance data and traffic data. For example, the data collection unit collects performance data such as network latency, throughput, and packet loss rate. The data collection unit can also collect traffic data such as traffic volume, traffic patterns, and protocol types. For example, the data collection unit collects data from each device in the network and stores it in a central database. The data collection unit can also install sensors on each device in the network and collect data in real time. The data preprocessing unit preprocesses the data collected by the data collection unit. For example, the data preprocessing unit cleanses the collected data. For example, the data preprocessing unit removes outliers and normalizes the data. The data preprocessing unit can also handle missing values. For example, the data preprocessing unit imputes or removes missing values. Furthermore, the data preprocessing unit can also scale the data. For example, the data preprocessing unit standardizes or normalizes the data. The training unit trains a generative AI using the data preprocessed by the data preprocessing unit. The training unit, for example, trains the generative AI using the collected data. For example, the training unit sets the algorithms to be used and how to select the training data. The training unit needs to prepare an appropriate environment because it requires a large amount of data and computing resources to train the generative AI. The monitoring unit uses the generative AI trained by the training unit to monitor the network and build a feedback loop. For example, the monitoring unit uses the generative AI to monitor the network. For example, the monitoring unit monitors network performance and traffic patterns in real time. The monitoring unit can also issue alerts if it detects network anomalies. The optimization unit performs self-optimization and automatic adjustment of network devices based on the data monitored by the monitoring unit. For example, the optimization unit performs self-optimization of network devices. For example, the optimization unit adjusts bandwidth based on predicted network load.The optimization unit can also identify bottlenecks and automatically switch routes. The improvement unit uses the feedback obtained by the optimization unit to improve the generative AI model. For example, the improvement unit improves the generative AI model using feedback obtained during network operation. For example, the improvement unit monitors network performance and the accuracy of traffic prediction, and adjusts model parameters or adds training data as needed. As a result, the network system according to the embodiment can improve network efficiency and security.

[0030] The data collection unit collects network performance data and traffic data. Specifically, it collects performance data such as network latency, throughput, and packet loss rate. This data is collected in real time through sensors installed on each network device and stored in a central database. The data collection unit can also collect traffic data such as traffic volume, traffic patterns, and protocol types. For example, the data collection unit collects data from each network device and manages this data centrally. The data collection unit can also install sensors on each network device to collect data in real time. This allows the data collection unit to constantly monitor the network status and respond quickly if an anomaly occurs. Furthermore, the data collection unit can store the collected data on a cloud server and collaborate with other systems and departments. For example, the collected data can be made accessible to the analysis unit and the prediction unit. In addition, by adjusting the frequency and accuracy of data collection, flexible responses to specific situations and conditions are possible. As a result, the data collection unit can collect data efficiently and effectively, improving the overall system performance.

[0031] The preprocessing unit preprocesses the data collected by the data acquisition unit. Specifically, it cleanses the collected data. For example, the preprocessing unit removes outliers and normalizes the data. The preprocessing unit can also handle missing values. For example, it can impute or remove missing values. Furthermore, the preprocessing unit can scale the data. For example, it can standardize or normalize the data. This allows the preprocessing unit to convert the collected data into an appropriate format, making it suitable for analysis and training. The preprocessing unit also filters and transforms the data to improve data quality. For example, it removes noise and smooths the data. It can also compress and split the data. This allows the preprocessing unit to efficiently process large amounts of data and improve the overall system performance. Furthermore, the preprocessing unit can flexibly change settings and parameters related to data preprocessing. This allows the preprocessing unit to perform optimal preprocessing according to specific situations and conditions.

[0032] The training unit trains the generative AI using data preprocessed by the preprocessing unit. Specifically, it trains the generative AI using collected data. For example, the training unit sets the algorithms to be used and how to select the training data. The training unit needs to prepare an appropriate environment because it requires a large amount of data and computing resources to train the generative AI. The training unit monitors the generative AI training process and evaluates the progress and results of the training. For example, the training unit evaluates the quality and quantity of the training data and adds or modifies the data as needed. The training unit also adjusts the training parameters and settings to make efforts to obtain optimal training results. In this way, the training unit can maximize the performance of the generative AI and improve the efficiency and security of the network system. Furthermore, the training unit evaluates the training results and provides feedback to improve the generative AI model. In this way, the training unit can continuously improve the performance of the generative AI.

[0033] The monitoring unit uses generative AI trained by the training unit to build a network monitoring and feedback loop. Specifically, it uses generative AI to monitor the network. For example, the monitoring unit monitors network performance and traffic patterns in real time. The monitoring unit can also issue alerts if it detects network anomalies. The monitoring unit uses generative AI to detect and predict network anomalies, enabling rapid response. For example, the monitoring unit can detect abnormal fluctuations in network latency and packet loss rates and immediately issue alerts. In addition, the monitoring unit can monitor changes in traffic patterns and detect potential security risks early. This allows the monitoring unit to maintain network stability and security and improve the overall reliability of the system. Furthermore, the monitoring unit provides monitoring results as feedback to the optimization and improvement units, which are used to optimize the network and improve the generative AI model. This allows the monitoring unit to effectively build a network monitoring and feedback loop and improve the overall system performance.

[0034] The optimization unit performs self-optimization and automatic adjustment of network devices based on data monitored by the monitoring unit. Specifically, it optimizes network devices. For example, the optimization unit adjusts bandwidth based on predicted network load. The optimization unit can also identify bottlenecks and automatically switch routes. The optimization unit uses generative AI to optimize the network and achieve efficient resource allocation. For example, the optimization unit analyzes network traffic patterns and selects the optimal routing path. The optimization unit also performs network load balancing, adjusting to prevent excessive load on specific devices or links. This allows the optimization unit to maximize network performance and improve the user experience. Furthermore, the optimization unit automatically adjusts network settings and parameters to maintain an optimal state. For example, the optimization unit dynamically adjusts bandwidth in response to increased traffic to ensure network stability. In addition, the optimization unit can immediately take countermeasures if it detects a network anomaly. This allows the optimization unit to maintain network efficiency and stability, improving the overall reliability of the system.

[0035] The Improvement Unit improves the Generative AI model using feedback obtained from the Optimization Unit. Specifically, it improves the Generative AI model using feedback obtained during network operation. For example, the Improvement Unit monitors network performance and traffic prediction accuracy, and adjusts model parameters and adds training data as needed. The Improvement Unit continuously improves the Generative AI model to enhance the efficiency and security of the network system. For example, the Improvement Unit analyzes network operation data and reflects it in the Generative AI model. The Improvement Unit also regularly updates the Generative AI training dataset to respond to the latest network conditions. This allows the Improvement Unit to keep the Generative AI model up-to-date and maximize network system performance. Furthermore, the Improvement Unit collects feedback on Generative AI model improvements and works with the Training Unit and Preprocessing Unit to improve model accuracy. This allows the Improvement Unit to continuously improve the Generative AI model and enhance the efficiency and security of the network system.

[0036] The data collection unit can collect network performance data and traffic data. For example, it can collect performance data such as network latency, throughput, and packet loss rate. It can also collect traffic data such as network traffic volume, traffic patterns, and protocol types. For example, the data collection unit can collect data from each device in the network and store it in a central database. The data collection unit can also install sensors on each device in the network to collect data in real time. This allows for an understanding of the network's state by collecting network performance and traffic data.

[0037] The preprocessing unit can perform data cleansing, missing value handling, and scaling of the collected data. For example, the preprocessing unit can cleanse the collected data. For example, the preprocessing unit can remove outliers and normalize the data. For example, the preprocessing unit can handle missing values ​​in the collected data. For example, the preprocessing unit can impute or remove missing values. For example, the preprocessing unit can scale the collected data. For example, the preprocessing unit can standardize or normalize the data. By performing data cleansing, missing value handling, and scaling of the collected data, the quality of the data can be improved.

[0038] The training unit can train the generative AI using the collected data. For example, the training unit sets the algorithms to be used and how to select the training data. The training unit needs to prepare an appropriate environment because it requires a large amount of data and computing resources to train the generative AI. This allows the network to learn trends and patterns by training the generative AI using the collected data.

[0039] The monitoring unit can use generative AI to build network monitoring and feedback loops. For example, the monitoring unit uses generative AI to monitor the network. For example, the monitoring unit monitors network performance and traffic patterns in real time. The monitoring unit can also issue alerts if it detects network anomalies. For example, the monitoring unit monitors network performance and traffic patterns and issues alerts if it detects anomalies. This allows for real-time understanding of the network status by using generative AI to build network monitoring and feedback loops.

[0040] The optimization unit can perform self-optimization and automatic adjustment of network devices. For example, the optimization unit can perform self-optimization of network devices. For example, the optimization unit can adjust bandwidth based on predicted network load. The optimization unit can also identify bottlenecks and automatically switch routes. For example, the optimization unit can perform self-optimization of network devices. For example, the optimization unit can adjust bandwidth based on predicted network load. The optimization unit can also identify bottlenecks and automatically switch routes. By performing self-optimization and automatic adjustment of network devices, the network can become more efficient.

[0041] The improvement unit can use feedback to improve the generative AI model. For example, the improvement unit improves the generative AI model using feedback obtained during network operation. For example, the improvement unit monitors network performance and the accuracy of traffic predictions, and adjusts model parameters or adds training data as needed. By improving the generative AI model using feedback, the improvement unit can improve network performance and the accuracy of traffic predictions.

[0042] The data collection unit can detect network anomalies and prioritize data collection when an anomaly occurs. For example, if the data collection unit detects network traffic anomalies, it will prioritize collecting data related to those anomalies. For example, if the data collection unit detects network performance degradation, it will prioritize collecting data that is causing the performance degradation. For example, if the data collection unit detects a security anomaly, it will prioritize collecting data related to that anomaly. By detecting network anomalies and prioritizing data collection when an anomaly occurs, the cause of the anomaly can be quickly identified.

[0043] The data collection unit can dynamically adjust the data collection frequency according to the network load during data collection. For example, if the network load is high, the data collection unit reduces the data collection frequency to alleviate the load. For example, if the network load is low, the data collection unit increases the data collection frequency to collect more detailed data. For example, the data collection unit monitors the network load in real time and dynamically adjusts the collection frequency. This allows for optimization of the network load by dynamically adjusting the collection frequency according to the network load.

[0044] The data collection unit can prioritize the collection of highly relevant data by considering the geographical distribution of the network during data collection. For example, the data collection unit can analyze the geographical distribution of the network and prioritize the collection of data from important regions. For example, the data collection unit can prioritize the collection of data from areas with high traffic based on the geographical distribution of the network. For example, the data collection unit can prioritize the collection of data from areas with high security risks by considering the geographical distribution of the network. In this way, by prioritizing the collection of highly relevant data while considering the geographical distribution of the network, data from important regions can be collected efficiently.

[0045] The data collection unit can analyze network usage in real time during data collection and select the optimal collection points. For example, the data collection unit analyzes network usage in real time and selects important data collection points. For example, the data collection unit prioritizes collecting data from points with high traffic based on network usage. For example, the data collection unit monitors network usage in real time and dynamically adjusts collection points. This allows for efficient collection of important data by analyzing network usage in real time and selecting the optimal collection points.

[0046] The preprocessing unit can automatically detect and remove abnormal values ​​and outliers during data cleansing. For example, the preprocessing unit automatically detects and removes abnormal values ​​during data cleansing. For example, the preprocessing unit automatically detects and removes outliers during data cleansing. For example, the preprocessing unit automatically detects and removes abnormal values ​​and outliers during data cleansing. This improves data quality by automatically detecting and removing abnormal values ​​and outliers during data cleansing.

[0047] The preprocessor can apply different scaling methods depending on the network characteristics when scaling data. For example, the preprocessor applies different scaling methods depending on the network characteristics. For example, the preprocessor selects the optimal scaling method based on the network characteristics. For example, the preprocessor dynamically adjusts the scaling method considering the network characteristics. In this way, data scaling can be optimized by applying different scaling methods depending on the network characteristics.

[0048] The preprocessing unit can select the optimal preprocessing method by considering network topology information during data preprocessing. For example, the preprocessing unit selects the optimal preprocessing method by considering network topology information. For example, the preprocessing unit dynamically adjusts the preprocessing method based on network topology information. For example, the preprocessing unit analyzes network topology information and applies the optimal preprocessing method. This allows for the optimization of data preprocessing by selecting the optimal preprocessing method by considering network topology information.

[0049] The preprocessing unit can improve the accuracy of data preprocessing by referring to historical network performance data. For example, the preprocessing unit improves the accuracy of preprocessing by referring to historical network performance data. For example, the preprocessing unit optimizes preprocessing methods that analyze historical network performance data. For example, the preprocessing unit enhances the accuracy of preprocessing by utilizing historical network performance data. This allows for improved data quality by improving preprocessing accuracy through referencing historical network performance data.

[0050] The training unit can improve the accuracy of anomaly detection by learning anomaly patterns in the network during training. For example, the training unit learns anomaly patterns in the network during training. For example, the training unit learns anomaly patterns during training to improve the accuracy of anomaly detection. For example, the training unit improves the accuracy of anomaly detection by learning anomaly patterns in the network during training. This allows for improved anomaly detection accuracy by learning anomaly patterns in the network.

[0051] The training unit can dynamically adjust the training algorithm according to the network load during training. For example, the training unit dynamically adjusts the training algorithm according to the network load. For example, the training unit monitors the network load in real time and adjusts the training algorithm. For example, the training unit optimizes the training algorithm based on the network load. By dynamically adjusting the training algorithm according to the network load, the efficiency of training can be improved.

[0052] The training unit can select training data while considering the geographical distribution of the network. For example, the training unit selects training data considering the geographical distribution of the network. For example, the training unit optimizes training data based on the geographical distribution of the network. For example, the training unit analyzes the geographical distribution of the network and selects training data. This allows for improved training accuracy by selecting training data while considering the geographical distribution of the network.

[0053] The training unit can improve the accuracy of training by referring to historical network traffic data during training. For example, the training unit can improve the accuracy of training by referring to historical network traffic data. For example, the training unit can analyze historical network traffic data and optimize the training data. For example, the training unit can improve the accuracy of training by utilizing historical network traffic data. This allows for improved training quality by referencing historical network traffic data to enhance training accuracy.

[0054] The monitoring unit can detect network anomalies in real time during monitoring and issue alerts. For example, the monitoring unit can detect network anomalies in real time and issue alerts. For example, if the monitoring unit detects a network anomaly, it will immediately issue an alert. For example, the monitoring unit will monitor network anomalies in real time and issue alerts when an anomaly occurs. This enables early detection and response to anomalies by detecting network anomalies in real time and issuing alerts.

[0055] The monitoring unit can dynamically adjust the monitoring frequency according to the network load during monitoring. For example, the monitoring unit dynamically adjusts the monitoring frequency according to the network load. For example, the monitoring unit monitors the network load in real time and adjusts the monitoring frequency. For example, the monitoring unit optimizes the monitoring frequency based on the network load. By dynamically adjusting the monitoring frequency according to the network load, the efficiency of monitoring can be improved.

[0056] The monitoring unit can select monitoring points while considering the geographical distribution of the network. For example, the monitoring unit selects monitoring points considering the geographical distribution of the network. For example, the monitoring unit optimizes monitoring points based on the geographical distribution of the network. For example, the monitoring unit analyzes the geographical distribution of the network and selects monitoring points. This allows for efficient monitoring of important areas by selecting monitoring points while considering the geographical distribution of the network.

[0057] The monitoring unit can improve the accuracy of monitoring by referring to historical network performance data during monitoring. For example, the monitoring unit improves the accuracy of monitoring by referring to historical network performance data. For example, the monitoring unit optimizes monitoring methods by analyzing historical network performance data. For example, the monitoring unit improves the accuracy of monitoring by utilizing historical network performance data. This allows for improved monitoring quality by improving monitoring accuracy through referencing historical network performance data.

[0058] The optimization unit can apply the optimization algorithm while considering the abnormal patterns of the network during optimization. For example, the optimization unit applies the optimization algorithm while considering the abnormal patterns of the network. For example, the optimization unit adjusts the optimization algorithm while considering the abnormal patterns during optimization. For example, the optimization unit analyzes the abnormal patterns of the network and applies the optimization algorithm during optimization. By doing so, the accuracy of optimization can be improved by applying the optimization algorithm while considering the abnormal patterns of the network.

[0059] The optimization unit can dynamically adjust the optimization frequency according to the network load during optimization. For example, the optimization unit dynamically adjusts the optimization frequency according to the network load. For example, the optimization unit monitors the network load in real time and adjusts the optimization frequency. For example, the optimization unit optimizes the optimization frequency based on the network load. By dynamically adjusting the optimization frequency according to the network load, the efficiency of optimization can be improved.

[0060] The optimization unit can select optimization points while considering the geographical distribution of the network. For example, the optimization unit selects optimization points while considering the geographical distribution of the network. For example, the optimization unit optimizes the optimization points based on the geographical distribution of the network. For example, the optimization unit analyzes the geographical distribution of the network and selects optimization points. By selecting optimization points while considering the geographical distribution of the network, optimization of important regions can be performed efficiently.

[0061] The optimization unit can improve the accuracy of optimization by referring to the network's past performance data during optimization. For example, the optimization unit improves the accuracy of optimization by referring to the network's past performance data. For example, the optimization unit analyzes the network's past performance data and optimizes the optimization method. For example, the optimization unit uses the network's past performance data to improve the accuracy of optimization. This allows for an improvement in the quality of optimization by improving the accuracy of optimization by referring to the network's past performance data.

[0062] The improvement unit can apply an improvement algorithm while considering abnormal network patterns during the improvement process. For example, the improvement unit applies an improvement algorithm while considering abnormal network patterns during the improvement process. For example, the improvement unit adjusts the improvement algorithm while considering abnormal patterns during the improvement process. For example, the improvement unit analyzes abnormal network patterns during the improvement process and applies an improvement algorithm. By doing so, the accuracy of the improvement can be improved by applying the improvement algorithm while considering abnormal network patterns.

[0063] The improvement unit can dynamically adjust the frequency of improvements according to the network load during the improvement process. For example, the improvement unit dynamically adjusts the frequency of improvements according to the network load. For example, the improvement unit monitors the network load in real time and adjusts the frequency of improvements. For example, the improvement unit optimizes the frequency of improvements based on the network load. This allows for improved efficiency of improvements by dynamically adjusting the frequency of improvements according to the network load.

[0064] The improvement unit can select improvement points while considering the geographical distribution of the network. For example, the improvement unit selects improvement points while considering the geographical distribution of the network. For example, the improvement unit optimizes improvement points based on the geographical distribution of the network. For example, the improvement unit analyzes the geographical distribution of the network and selects improvement points. This allows for efficient improvement of important areas by selecting improvement points while considering the geographical distribution of the network.

[0065] The improvement unit can improve the accuracy of improvements by referring to historical network performance data during the improvement process. For example, the improvement unit can improve the accuracy of improvements by referring to historical network performance data. For example, the improvement unit can optimize improvement methods by analyzing historical network performance data. For example, the improvement unit can improve the accuracy of improvements by utilizing historical network performance data. This allows for an improvement in the quality of improvements by improving the accuracy of improvements through referencing historical network performance data.

[0066] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0067] The data collection unit can collect network performance data and traffic data. For example, it can collect performance data such as network latency, throughput, and packet loss rate. It can also collect traffic data such as traffic volume, traffic patterns, and protocol types. The data collection unit can collect data from each device in the network and store it in a central database. Furthermore, the data collection unit can install sensors on each device in the network and collect data in real time. This allows for an understanding of the network's state by collecting network performance data and traffic data.

[0068] The preprocessing unit can cleanse, handle missing values, and scale the collected data. For example, the preprocessing unit can cleanse the collected data, removing outliers and normalizing the data. The preprocessing unit can also handle missing values ​​in the collected data, imputing or removing them. Furthermore, the preprocessing unit can scale the collected data, standardizing or normalizing the data. By cleansing, handling missing values, and scaling the collected data, the quality of the data can be improved.

[0069] The training unit can train generative AI using the collected data. For example, the training unit can train generative AI using the collected data. It can configure the algorithms to be used and how to select the training data. The training unit requires a large amount of data and computing resources to train generative AI, so it needs to prepare an appropriate environment. This allows the network to learn trends and patterns by training generative AI using the collected data.

[0070] The monitoring unit can use generative AI to monitor the network and build a feedback loop. For example, the monitoring unit uses generative AI to monitor the network. It can monitor network performance and traffic patterns in real time. The monitoring unit can also issue alerts if it detects network anomalies. In this way, by using generative AI to monitor the network and build a feedback loop, the network status can be understood in real time.

[0071] The optimization unit can perform self-optimization and automatic adjustment of network devices. For example, the optimization unit can perform self-optimization of network devices. It can adjust bandwidth based on predicted network load. The optimization unit can also identify bottlenecks and automatically switch routes. In this way, by performing self-optimization and automatic adjustment of network devices, the efficiency of the network can be improved.

[0072] The improvement unit can use feedback to improve the generative AI model. For example, the improvement unit can use feedback obtained during network operation to improve the generative AI model. It can monitor network performance and the accuracy of traffic predictions, and adjust model parameters or add training data as needed. This allows for improvements to network performance and traffic prediction accuracy by using feedback to improve the generative AI model.

[0073] The following briefly describes the processing flow for example form 1.

[0074] Step 1: The collection unit collects network performance data and traffic data. For example, it collects performance data such as network latency, throughput, and packet loss rate, as well as traffic data such as traffic volume, traffic patterns, and protocol types. The collection unit collects data from each device in the network and stores it in a central database. Alternatively, sensors can be installed on each device in the network to collect data in real time. Step 2: The preprocessing unit preprocesses the data collected by the acquisition unit. For example, it cleanses the collected data, removes outliers, normalizes the data, imputes or removes missing values, and scales the data (standardizes or normalizes it). Step 3: The training unit trains the generative AI using the data preprocessed by the preprocessing unit. For example, it sets the algorithms to be used and how to select the training data, and uses a large amount of data and computing resources to train the generative AI. Step 4: The monitoring unit uses the generative AI trained by the training unit to build a network monitoring and feedback loop. For example, it uses the generative AI to monitor network performance and traffic patterns in real time and issue alerts if anomalies are detected. Step 5: The optimization unit performs self-optimization and automatic adjustment of network devices based on data monitored by the monitoring unit. For example, it adjusts bandwidth based on network load predictions, identifies bottlenecks, and automatically switches routes. Step 6: The improvement unit uses the feedback obtained by the optimization unit to improve the generative AI model. For example, it uses feedback obtained during network operation to improve the generative AI model, monitors network performance and traffic prediction accuracy, and adjusts model parameters or adds training data as needed.

[0075] (Example of form 2) The network system according to an embodiment of the present invention is a system that incorporates generative AI technology, learns on its own, achieves optimization, and adapts improvements to realize a network that is constantly evolving through the PDCA cycle. This network system consists of the steps of data collection and preprocessing, generative AI training, network monitoring and feedback loop, self-optimization and automatic adjustment, and feedback and model improvement. For example, the network system first performs data collection and preprocessing. It collects network performance data and traffic data and performs the necessary preprocessing. This includes data cleansing, handling missing values, and scaling. Next, the network system trains the generative AI. It trains the generative AI using the collected data to learn network trends and patterns. Since training requires a large amount of data and computing resources, it is necessary to prepare an appropriate environment. After that, the network system builds a network monitoring and feedback loop. It integrates the generative AI into the production environment and builds a network monitoring and feedback loop. Network data is periodically provided to the generative AI to help it understand the current state of the network. The generative AI uses the trained model to predict network performance and traffic patterns. Furthermore, the network system performs self-optimization and automatic adjustment. Based on network trends and patterns predicted by generative AI, network devices perform self-optimization and automatic adjustments. For example, they adjust bandwidth based on predicted network load, identify bottlenecks, and automatically switch routes. Finally, the network system uses feedback and model improvement. Feedback obtained during network operation is used to improve the generative AI model. Network performance and the accuracy of traffic predictions are monitored, and model parameters are adjusted or training data is added as needed. This allows the network system to cope with the increasing complexity of network design and operation, reducing the burden on engineers. It also improves network efficiency and security.This allows network systems to improve network efficiency and security.

[0076] The network system according to the embodiment comprises a data collection unit, a data preprocessing unit, a training unit, a monitoring unit, an optimization unit, and an improvement unit. The data collection unit collects network performance data and traffic data. For example, the data collection unit collects performance data such as network latency, throughput, and packet loss rate. The data collection unit can also collect traffic data such as traffic volume, traffic patterns, and protocol types. For example, the data collection unit collects data from each device in the network and stores it in a central database. The data collection unit can also install sensors on each device in the network and collect data in real time. The data preprocessing unit preprocesses the data collected by the data collection unit. For example, the data preprocessing unit cleanses the collected data. For example, the data preprocessing unit removes outliers and normalizes the data. The data preprocessing unit can also handle missing values. For example, the data preprocessing unit imputes or removes missing values. Furthermore, the data preprocessing unit can also scale the data. For example, the data preprocessing unit standardizes or normalizes the data. The training unit trains a generative AI using the data preprocessed by the data preprocessing unit. The training unit, for example, trains the generative AI using the collected data. For example, the training unit sets the algorithms to be used and how to select the training data. The training unit needs to prepare an appropriate environment because it requires a large amount of data and computing resources to train the generative AI. The monitoring unit uses the generative AI trained by the training unit to monitor the network and build a feedback loop. For example, the monitoring unit uses the generative AI to monitor the network. For example, the monitoring unit monitors network performance and traffic patterns in real time. The monitoring unit can also issue alerts if it detects network anomalies. The optimization unit performs self-optimization and automatic adjustment of network devices based on the data monitored by the monitoring unit. For example, the optimization unit performs self-optimization of network devices. For example, the optimization unit adjusts bandwidth based on predicted network load.The optimization unit can also identify bottlenecks and automatically switch routes. The improvement unit uses the feedback obtained by the optimization unit to improve the generative AI model. For example, the improvement unit improves the generative AI model using feedback obtained during network operation. For example, the improvement unit monitors network performance and the accuracy of traffic prediction, and adjusts model parameters or adds training data as needed. As a result, the network system according to the embodiment can improve network efficiency and security.

[0077] The data collection unit collects network performance data and traffic data. Specifically, it collects performance data such as network latency, throughput, and packet loss rate. This data is collected in real time through sensors installed on each network device and stored in a central database. The data collection unit can also collect traffic data such as traffic volume, traffic patterns, and protocol types. For example, the data collection unit collects data from each network device and manages this data centrally. The data collection unit can also install sensors on each network device to collect data in real time. This allows the data collection unit to constantly monitor the network status and respond quickly if an anomaly occurs. Furthermore, the data collection unit can store the collected data on a cloud server and collaborate with other systems and departments. For example, the collected data can be made accessible to the analysis unit and the prediction unit. In addition, by adjusting the frequency and accuracy of data collection, flexible responses to specific situations and conditions are possible. As a result, the data collection unit can collect data efficiently and effectively, improving the overall system performance.

[0078] The preprocessing unit preprocesses the data collected by the data acquisition unit. Specifically, it cleanses the collected data. For example, the preprocessing unit removes outliers and normalizes the data. The preprocessing unit can also handle missing values. For example, it can impute or remove missing values. Furthermore, the preprocessing unit can scale the data. For example, it can standardize or normalize the data. This allows the preprocessing unit to convert the collected data into an appropriate format, making it suitable for analysis and training. The preprocessing unit also filters and transforms the data to improve data quality. For example, it removes noise and smooths the data. It can also compress and split the data. This allows the preprocessing unit to efficiently process large amounts of data and improve the overall system performance. Furthermore, the preprocessing unit can flexibly change settings and parameters related to data preprocessing. This allows the preprocessing unit to perform optimal preprocessing according to specific situations and conditions.

[0079] The training unit trains the generative AI using data preprocessed by the preprocessing unit. Specifically, it trains the generative AI using collected data. For example, the training unit sets the algorithms to be used and how to select the training data. The training unit needs to prepare an appropriate environment because it requires a large amount of data and computing resources to train the generative AI. The training unit monitors the generative AI training process and evaluates the progress and results of the training. For example, the training unit evaluates the quality and quantity of the training data and adds or modifies the data as needed. The training unit also adjusts the training parameters and settings to make efforts to obtain optimal training results. In this way, the training unit can maximize the performance of the generative AI and improve the efficiency and security of the network system. Furthermore, the training unit evaluates the training results and provides feedback to improve the generative AI model. In this way, the training unit can continuously improve the performance of the generative AI.

[0080] The monitoring unit uses generative AI trained by the training unit to build a network monitoring and feedback loop. Specifically, it uses generative AI to monitor the network. For example, the monitoring unit monitors network performance and traffic patterns in real time. The monitoring unit can also issue alerts if it detects network anomalies. The monitoring unit uses generative AI to detect and predict network anomalies, enabling rapid response. For example, the monitoring unit can detect abnormal fluctuations in network latency and packet loss rates and immediately issue alerts. In addition, the monitoring unit can monitor changes in traffic patterns and detect potential security risks early. This allows the monitoring unit to maintain network stability and security and improve the overall reliability of the system. Furthermore, the monitoring unit provides monitoring results as feedback to the optimization and improvement units, which are used to optimize the network and improve the generative AI model. This allows the monitoring unit to effectively build a network monitoring and feedback loop and improve the overall system performance.

[0081] The optimization unit performs self-optimization and automatic adjustment of network devices based on data monitored by the monitoring unit. Specifically, it optimizes network devices. For example, the optimization unit adjusts bandwidth based on predicted network load. The optimization unit can also identify bottlenecks and automatically switch routes. The optimization unit uses generative AI to optimize the network and achieve efficient resource allocation. For example, the optimization unit analyzes network traffic patterns and selects the optimal routing path. The optimization unit also performs network load balancing, adjusting to prevent excessive load on specific devices or links. This allows the optimization unit to maximize network performance and improve the user experience. Furthermore, the optimization unit automatically adjusts network settings and parameters to maintain an optimal state. For example, the optimization unit dynamically adjusts bandwidth in response to increased traffic to ensure network stability. In addition, the optimization unit can immediately take countermeasures if it detects a network anomaly. This allows the optimization unit to maintain network efficiency and stability, improving the overall reliability of the system.

[0082] The Improvement Unit improves the Generative AI model using feedback obtained from the Optimization Unit. Specifically, it improves the Generative AI model using feedback obtained during network operation. For example, the Improvement Unit monitors network performance and traffic prediction accuracy, and adjusts model parameters and adds training data as needed. The Improvement Unit continuously improves the Generative AI model to enhance the efficiency and security of the network system. For example, the Improvement Unit analyzes network operation data and reflects it in the Generative AI model. The Improvement Unit also regularly updates the Generative AI training dataset to respond to the latest network conditions. This allows the Improvement Unit to keep the Generative AI model up-to-date and maximize network system performance. Furthermore, the Improvement Unit collects feedback on Generative AI model improvements and works with the Training Unit and Preprocessing Unit to improve model accuracy. This allows the Improvement Unit to continuously improve the Generative AI model and enhance the efficiency and security of the network system.

[0083] The data collection unit can collect network performance data and traffic data. For example, it can collect performance data such as network latency, throughput, and packet loss rate. It can also collect traffic data such as network traffic volume, traffic patterns, and protocol types. For example, the data collection unit can collect data from each device in the network and store it in a central database. The data collection unit can also install sensors on each device in the network to collect data in real time. This allows for an understanding of the network's state by collecting network performance and traffic data.

[0084] The preprocessing unit can perform data cleansing, missing value handling, and scaling of the collected data. For example, the preprocessing unit can cleanse the collected data. For example, the preprocessing unit can remove outliers and normalize the data. For example, the preprocessing unit can handle missing values ​​in the collected data. For example, the preprocessing unit can impute or remove missing values. For example, the preprocessing unit can scale the collected data. For example, the preprocessing unit can standardize or normalize the data. By performing data cleansing, missing value handling, and scaling of the collected data, the quality of the data can be improved.

[0085] The training unit can train the generative AI using the collected data. For example, the training unit sets the algorithms to be used and how to select the training data. The training unit needs to prepare an appropriate environment because it requires a large amount of data and computing resources to train the generative AI. This allows the network to learn trends and patterns by training the generative AI using the collected data.

[0086] The monitoring unit can use generative AI to build network monitoring and feedback loops. For example, the monitoring unit uses generative AI to monitor the network. For example, the monitoring unit monitors network performance and traffic patterns in real time. The monitoring unit can also issue alerts if it detects network anomalies. For example, the monitoring unit monitors network performance and traffic patterns and issues alerts if it detects anomalies. This allows for real-time understanding of the network status by using generative AI to build network monitoring and feedback loops.

[0087] The optimization unit can perform self-optimization and automatic adjustment of network devices. For example, the optimization unit can perform self-optimization of network devices. For example, the optimization unit can adjust bandwidth based on predicted network load. The optimization unit can also identify bottlenecks and automatically switch routes. For example, the optimization unit can perform self-optimization of network devices. For example, the optimization unit can adjust bandwidth based on predicted network load. The optimization unit can also identify bottlenecks and automatically switch routes. By performing self-optimization and automatic adjustment of network devices, the network can become more efficient.

[0088] The improvement unit can use feedback to improve the generative AI model. For example, the improvement unit improves the generative AI model using feedback obtained during network operation. For example, the improvement unit monitors network performance and the accuracy of traffic predictions, and adjusts model parameters or adds training data as needed. By improving the generative AI model using feedback, the improvement unit can improve network performance and the accuracy of traffic predictions.

[0089] The data collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated emotions. For example, if the user is stressed, the data collection unit reduces the frequency of data collection to alleviate network load. For example, if the user is relaxed, the data collection unit increases the frequency of data collection to collect more detailed data. For example, if the user is in a hurry, the data collection unit prioritizes collecting only important data. This reduces network load by adjusting the timing of data collection based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0090] The data collection unit can detect network anomalies and prioritize data collection when an anomaly occurs. For example, if the data collection unit detects network traffic anomalies, it will prioritize collecting data related to those anomalies. For example, if the data collection unit detects network performance degradation, it will prioritize collecting data that is causing the performance degradation. For example, if the data collection unit detects a security anomaly, it will prioritize collecting data related to that anomaly. By detecting network anomalies and prioritizing data collection when an anomaly occurs, the cause of the anomaly can be quickly identified.

[0091] The data collection unit can dynamically adjust the data collection frequency according to the network load during data collection. For example, if the network load is high, the data collection unit reduces the data collection frequency to alleviate the load. For example, if the network load is low, the data collection unit increases the data collection frequency to collect more detailed data. For example, the data collection unit monitors the network load in real time and dynamically adjusts the collection frequency. This allows for optimization of the network load by dynamically adjusting the collection frequency according to the network load.

[0092] The data collection unit can estimate the user's emotions and determine the priority of data to collect based on the estimated emotions. For example, if the user is stressed, the data collection unit will prioritize collecting only important data. If the user is relaxed, the data collection unit will prioritize collecting detailed data. If the user is in a hurry, the data collection unit will prioritize collecting data that can be collected quickly. This allows for the priority collection of important data by determining the priority of data to collect based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0093] The data collection unit can prioritize the collection of highly relevant data by considering the geographical distribution of the network during data collection. For example, the data collection unit can analyze the geographical distribution of the network and prioritize the collection of data from important regions. For example, the data collection unit can prioritize the collection of data from areas with high traffic based on the geographical distribution of the network. For example, the data collection unit can prioritize the collection of data from areas with high security risks by considering the geographical distribution of the network. In this way, by prioritizing the collection of highly relevant data while considering the geographical distribution of the network, data from important regions can be collected efficiently.

[0094] The data collection unit can analyze network usage in real time during data collection and select the optimal collection points. For example, the data collection unit analyzes network usage in real time and selects important data collection points. For example, the data collection unit prioritizes collecting data from points with high traffic based on network usage. For example, the data collection unit monitors network usage in real time and dynamically adjusts collection points. This allows for efficient collection of important data by analyzing network usage in real time and selecting the optimal collection points.

[0095] The preprocessing unit can estimate the user's emotions and adjust the data preprocessing method based on the estimated emotions. For example, if the user is stressed, the preprocessing unit applies a simple preprocessing method. For example, if the user is relaxed, the preprocessing unit applies a detailed preprocessing method. For example, if the user is in a hurry, the preprocessing unit applies a rapid preprocessing method. This allows for efficient data preprocessing by adjusting the data preprocessing method based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0096] The preprocessing unit can automatically detect and remove abnormal values ​​and outliers during data cleansing. For example, the preprocessing unit automatically detects and removes abnormal values ​​during data cleansing. For example, the preprocessing unit automatically detects and removes outliers during data cleansing. For example, the preprocessing unit automatically detects and removes abnormal values ​​and outliers during data cleansing. This improves data quality by automatically detecting and removing abnormal values ​​and outliers during data cleansing.

[0097] The preprocessor can apply different scaling methods depending on the network characteristics when scaling data. For example, the preprocessor applies different scaling methods depending on the network characteristics. For example, the preprocessor selects the optimal scaling method based on the network characteristics. For example, the preprocessor dynamically adjusts the scaling method considering the network characteristics. In this way, data scaling can be optimized by applying different scaling methods depending on the network characteristics.

[0098] The preprocessing unit can estimate the user's emotions and determine the priority of preprocessing based on the estimated emotions. For example, if the user is stressed, the preprocessing unit will prioritize preprocessing important data. For example, if the user is relaxed, the preprocessing unit will prioritize preprocessing detailed data. For example, if the user is in a hurry, the preprocessing unit will prioritize data that can be preprocessed quickly. This allows for prioritizing the preprocessing of important data by determining the priority of preprocessing based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0099] The preprocessing unit can estimate the user's emotions and determine the priority of preprocessing based on the estimated emotions. For example, if the user is stressed, the preprocessing unit will prioritize preprocessing important data. For example, if the user is relaxed, the preprocessing unit will prioritize preprocessing detailed data. For example, if the user is in a hurry, the preprocessing unit will prioritize data that can be preprocessed quickly. This allows for prioritizing the preprocessing of important data by determining the priority of preprocessing based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0100] The preprocessing unit can select the optimal preprocessing method by considering network topology information during data preprocessing. For example, the preprocessing unit selects the optimal preprocessing method by considering network topology information. For example, the preprocessing unit dynamically adjusts the preprocessing method based on network topology information. For example, the preprocessing unit analyzes network topology information and applies the optimal preprocessing method. This allows for the optimization of data preprocessing by selecting the optimal preprocessing method by considering network topology information.

[0101] The preprocessing unit can improve the accuracy of data preprocessing by referring to historical network performance data. For example, the preprocessing unit improves the accuracy of preprocessing by referring to historical network performance data. For example, the preprocessing unit optimizes preprocessing methods that analyze historical network performance data. For example, the preprocessing unit enhances the accuracy of preprocessing by utilizing historical network performance data. This allows for improved data quality by improving preprocessing accuracy through referencing historical network performance data.

[0102] The training unit can estimate the user's emotions and select training data based on those estimated emotions. For example, if the user is stressed, the training unit will prioritize selecting important data for training. If the user is relaxed, for example, the training unit will select detailed data for training. If the user is in a hurry, for example, the training unit will select data that allows for quick training. This allows important data to be used preferentially for training by selecting training data based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0103] The training unit can improve the accuracy of anomaly detection by learning anomaly patterns in the network during training. For example, the training unit learns anomaly patterns in the network during training. For example, the training unit learns anomaly patterns during training to improve the accuracy of anomaly detection. For example, the training unit improves the accuracy of anomaly detection by learning anomaly patterns in the network during training. This allows for improved anomaly detection accuracy by learning anomaly patterns in the network.

[0104] The training unit can dynamically adjust the training algorithm according to the network load during training. For example, the training unit dynamically adjusts the training algorithm according to the network load. For example, the training unit monitors the network load in real time and adjusts the training algorithm. For example, the training unit optimizes the training algorithm based on the network load. By dynamically adjusting the training algorithm according to the network load, the efficiency of training can be improved.

[0105] The training unit can estimate the user's emotions and determine training priorities based on those estimated emotions. For example, if the user is stressed, the training unit will prioritize important training. For example, if the user is relaxed, the training unit will prioritize detailed training. For example, if the user is in a hurry, the training unit will prioritize data that allows for quick training. This allows important training to be prioritized by determining training priorities based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0106] The training unit can select training data while considering the geographical distribution of the network. For example, the training unit selects training data considering the geographical distribution of the network. For example, the training unit optimizes training data based on the geographical distribution of the network. For example, the training unit analyzes the geographical distribution of the network and selects training data. This allows for improved training accuracy by selecting training data while considering the geographical distribution of the network.

[0107] The training unit can improve the accuracy of training by referring to historical network traffic data during training. For example, the training unit can improve the accuracy of training by referring to historical network traffic data. For example, the training unit can analyze historical network traffic data and optimize the training data. For example, the training unit can improve the accuracy of training by utilizing historical network traffic data. This allows for improved training quality by referencing historical network traffic data to enhance training accuracy.

[0108] The monitoring unit can estimate the user's emotions and adjust the display method of the monitoring based on the estimated user emotions. For example, if the user is tense, the monitoring unit provides a simple and highly visible display method. For example, if the user is relaxed, the monitoring unit provides a display method that includes detailed information. For example, if the user is in a hurry, the monitoring unit provides a display method that gets straight to the point. In this way, by adjusting the display method of the monitoring based on the user's emotions, a display method that is easy for the user to understand can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0109] The monitoring unit can detect network anomalies in real time during monitoring and issue alerts. For example, the monitoring unit can detect network anomalies in real time and issue alerts. For example, if the monitoring unit detects a network anomaly, it will immediately issue an alert. For example, the monitoring unit will monitor network anomalies in real time and issue alerts when an anomaly occurs. This enables early detection and response to anomalies by detecting network anomalies in real time and issuing alerts.

[0110] The monitoring unit can dynamically adjust the monitoring frequency according to the network load during monitoring. For example, the monitoring unit dynamically adjusts the monitoring frequency according to the network load. For example, the monitoring unit monitors the network load in real time and adjusts the monitoring frequency. For example, the monitoring unit optimizes the monitoring frequency based on the network load. By dynamically adjusting the monitoring frequency according to the network load, the efficiency of monitoring can be improved.

[0111] The monitoring unit can estimate the user's emotions and determine monitoring priorities based on the estimated emotions. For example, if the user is stressed, the monitoring unit will prioritize important monitoring items. For example, if the user is relaxed, the monitoring unit will prioritize detailed monitoring items. For example, if the user is in a hurry, the monitoring unit will prioritize items that can be monitored quickly. This allows for priority monitoring of important items by determining monitoring priorities based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0112] The monitoring unit can select monitoring points while considering the geographical distribution of the network. For example, the monitoring unit selects monitoring points considering the geographical distribution of the network. For example, the monitoring unit optimizes monitoring points based on the geographical distribution of the network. For example, the monitoring unit analyzes the geographical distribution of the network and selects monitoring points. This allows for efficient monitoring of important areas by selecting monitoring points while considering the geographical distribution of the network.

[0113] The monitoring unit can improve the accuracy of monitoring by referring to historical network performance data during monitoring. For example, the monitoring unit improves the accuracy of monitoring by referring to historical network performance data. For example, the monitoring unit optimizes monitoring methods by analyzing historical network performance data. For example, the monitoring unit improves the accuracy of monitoring by utilizing historical network performance data. This allows for improved monitoring quality by improving monitoring accuracy through referencing historical network performance data.

[0114] The optimization unit can estimate the user's emotions and adjust the optimization method based on the estimated emotions. For example, if the user is stressed, the optimization unit applies a simple optimization method. For example, if the user is relaxed, the optimization unit applies a detailed optimization method. For example, if the user is in a hurry, the optimization unit applies a method that performs rapid optimization. In this way, the efficiency of optimization can be improved by adjusting the optimization method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0115] The optimization unit can apply the optimization algorithm while considering the abnormal patterns of the network during optimization. For example, the optimization unit applies the optimization algorithm while considering the abnormal patterns of the network. For example, the optimization unit adjusts the optimization algorithm while considering the abnormal patterns during optimization. For example, the optimization unit analyzes the abnormal patterns of the network and applies the optimization algorithm during optimization. By doing so, the accuracy of optimization can be improved by applying the optimization algorithm while considering the abnormal patterns of the network.

[0116] The optimization unit can dynamically adjust the optimization frequency according to the network load during optimization. For example, the optimization unit dynamically adjusts the optimization frequency according to the network load. For example, the optimization unit monitors the network load in real time and adjusts the optimization frequency. For example, the optimization unit optimizes the optimization frequency based on the network load. By dynamically adjusting the optimization frequency according to the network load, the efficiency of optimization can be improved.

[0117] The optimization unit can estimate the user's emotions and determine optimization priorities based on those emotions. For example, if the user is stressed, the optimization unit will prioritize important optimizations. If the user is relaxed, the optimization unit will prioritize detailed optimizations. If the user is in a hurry, the optimization unit will prioritize items that require quick optimization. This allows for prioritizing important optimizations by determining optimization priorities based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0118] The optimization unit can select optimization points while considering the geographical distribution of the network. For example, the optimization unit selects optimization points while considering the geographical distribution of the network. For example, the optimization unit optimizes the optimization points based on the geographical distribution of the network. For example, the optimization unit analyzes the geographical distribution of the network and selects optimization points. By selecting optimization points while considering the geographical distribution of the network, optimization of important regions can be performed efficiently.

[0119] The optimization unit can improve the accuracy of optimization by referring to the network's past performance data during optimization. For example, the optimization unit improves the accuracy of optimization by referring to the network's past performance data. For example, the optimization unit analyzes the network's past performance data and optimizes the optimization method. For example, the optimization unit uses the network's past performance data to improve the accuracy of optimization. This allows for an improvement in the quality of optimization by improving the accuracy of optimization by referring to the network's past performance data.

[0120] The improvement unit can estimate the user's emotions and adjust the improvement method based on the estimated emotions. For example, if the user is stressed, the improvement unit will apply a simple improvement method. For example, if the user is relaxed, the improvement unit will apply a detailed improvement method. For example, if the user is in a hurry, the improvement unit will apply a method that provides rapid improvement. This improves the efficiency of improvement by adjusting the improvement method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0121] The improvement unit can apply an improvement algorithm while considering abnormal network patterns during the improvement process. For example, the improvement unit applies an improvement algorithm while considering abnormal network patterns during the improvement process. For example, the improvement unit adjusts the improvement algorithm while considering abnormal patterns during the improvement process. For example, the improvement unit analyzes abnormal network patterns during the improvement process and applies an improvement algorithm. By doing so, the accuracy of the improvement can be improved by applying the improvement algorithm while considering abnormal network patterns.

[0122] The improvement unit can dynamically adjust the frequency of improvements according to the network load during the improvement process. For example, the improvement unit dynamically adjusts the frequency of improvements according to the network load. For example, the improvement unit monitors the network load in real time and adjusts the frequency of improvements. For example, the improvement unit optimizes the frequency of improvements based on the network load. This allows for improved efficiency of improvements by dynamically adjusting the frequency of improvements according to the network load.

[0123] The improvement unit can estimate the user's emotions and determine the priority of improvements based on those emotions. For example, if the user is stressed, the improvement unit will prioritize important improvements. For example, if the user is relaxed, the improvement unit will prioritize detailed improvements. For example, if the user is in a hurry, the improvement unit will prioritize items that can be improved quickly. This allows for prioritizing important improvements by determining the priority of improvements based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0124] The improvement unit can select improvement points while considering the geographical distribution of the network. For example, the improvement unit selects improvement points while considering the geographical distribution of the network. For example, the improvement unit optimizes improvement points based on the geographical distribution of the network. For example, the improvement unit analyzes the geographical distribution of the network and selects improvement points. This allows for efficient improvement of important areas by selecting improvement points while considering the geographical distribution of the network.

[0125] The improvement unit can improve the accuracy of improvements by referring to historical network performance data during the improvement process. For example, the improvement unit can improve the accuracy of improvements by referring to historical network performance data. For example, the improvement unit can optimize improvement methods by analyzing historical network performance data. For example, the improvement unit can improve the accuracy of improvements by utilizing historical network performance data. This allows for an improvement in the quality of improvements by improving the accuracy of improvements through referencing historical network performance data.

[0126] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0127] The data collection unit can collect network performance data and traffic data. For example, it can collect performance data such as network latency, throughput, and packet loss rate. It can also collect traffic data such as traffic volume, traffic patterns, and protocol types. The data collection unit can collect data from each device in the network and store it in a central database. Furthermore, the data collection unit can install sensors on each device in the network and collect data in real time. This allows for an understanding of the network's state by collecting network performance data and traffic data.

[0128] The preprocessing unit can cleanse, handle missing values, and scale the collected data. For example, the preprocessing unit can cleanse the collected data, removing outliers and normalizing the data. The preprocessing unit can also handle missing values ​​in the collected data, imputing or removing them. Furthermore, the preprocessing unit can scale the collected data, standardizing or normalizing the data. By cleansing, handling missing values, and scaling the collected data, the quality of the data can be improved.

[0129] The training unit can train generative AI using the collected data. For example, the training unit can train generative AI using the collected data. It can configure the algorithms to be used and how to select the training data. The training unit requires a large amount of data and computing resources to train generative AI, so it needs to prepare an appropriate environment. This allows the network to learn trends and patterns by training generative AI using the collected data.

[0130] The monitoring unit can use generative AI to monitor the network and build a feedback loop. For example, the monitoring unit uses generative AI to monitor the network. It can monitor network performance and traffic patterns in real time. The monitoring unit can also issue alerts if it detects network anomalies. In this way, by using generative AI to monitor the network and build a feedback loop, the network status can be understood in real time.

[0131] The optimization unit can perform self-optimization and automatic adjustment of network devices. For example, the optimization unit can perform self-optimization of network devices. It can adjust bandwidth based on predicted network load. The optimization unit can also identify bottlenecks and automatically switch routes. In this way, by performing self-optimization and automatic adjustment of network devices, the efficiency of the network can be improved.

[0132] The improvement unit can use feedback to improve the generative AI model. For example, the improvement unit can use feedback obtained during network operation to improve the generative AI model. It can monitor network performance and the accuracy of traffic predictions, and adjust model parameters or add training data as needed. This allows for improvements to network performance and traffic prediction accuracy by using feedback to improve the generative AI model.

[0133] The data collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated emotions. For example, if the user is stressed, the frequency of data collection is reduced to lessen the network load. If the user is relaxed, the frequency of data collection is increased to collect more detailed data. If the user is in a hurry, only important data is prioritized for collection. This reduces the network load by adjusting the timing of data collection based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0134] The preprocessing unit can estimate the user's emotions and adjust the data preprocessing method based on the estimated emotions. For example, if the user is stressed, a simple preprocessing method is applied. If the user is relaxed, a detailed preprocessing method is applied. If the user is in a hurry, a fast preprocessing method is applied. This allows for efficient data preprocessing by adjusting the data preprocessing method based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0135] The training unit can estimate the user's emotions and select training data based on those emotions. For example, if the user is stressed, important data will be prioritized for training. If the user is relaxed, detailed data will be selected for training. If the user is in a hurry, data that allows for quick training will be selected. This allows for the selection of training data based on the user's emotions, ensuring that important data is used preferentially for training. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0136] The monitoring unit can estimate the user's emotions and adjust the display method of the monitoring based on the estimated user emotions. For example, if the user is tense, it provides a simple and highly visible display method. If the user is relaxed, it provides a display method that includes detailed information. If the user is in a hurry, it provides a display method that gets straight to the point. In this way, by adjusting the display method of the monitoring based on the user's emotions, it is possible to provide a display method that is easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0137] The following briefly describes the processing flow for example form 2.

[0138] Step 1: The collection unit collects network performance data and traffic data. For example, it collects performance data such as network latency, throughput, and packet loss rate, as well as traffic data such as traffic volume, traffic patterns, and protocol types. The collection unit collects data from each device in the network and stores it in a central database. Alternatively, sensors can be installed on each device in the network to collect data in real time. Step 2: The preprocessing unit preprocesses the data collected by the acquisition unit. For example, it cleanses the collected data, removes outliers, normalizes the data, imputes or removes missing values, and scales the data (standardizes or normalizes it). Step 3: The training unit trains the generative AI using the data preprocessed by the preprocessing unit. For example, it sets the algorithms to be used and how to select the training data, and uses a large amount of data and computing resources to train the generative AI. Step 4: The monitoring unit uses the generative AI trained by the training unit to build a network monitoring and feedback loop. For example, it uses the generative AI to monitor network performance and traffic patterns in real time and issue alerts if anomalies are detected. Step 5: The optimization unit performs self-optimization and automatic adjustment of network devices based on data monitored by the monitoring unit. For example, it adjusts bandwidth based on network load predictions, identifies bottlenecks, and automatically switches routes. Step 6: The improvement unit uses the feedback obtained by the optimization unit to improve the generative AI model. For example, it uses feedback obtained during network operation to improve the generative AI model, monitors network performance and traffic prediction accuracy, and adjusts model parameters or adds training data as needed.

[0139] 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.

[0140] Data generation model 58 is a form of 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> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0141] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements described above, including the data collection unit, preprocessing unit, training unit, monitoring unit, optimization unit, and improvement unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the data collection unit collects network performance data and traffic data using the sensors and cameras of the smart device 14. The preprocessing unit cleanses and scales the collected data using the specific processing unit 290 of the data processing unit 12. The training unit trains the generated AI using the specific processing unit 290 of the data processing unit 12. The monitoring unit monitors the network using the control unit 46A of the smart device 14 and builds a feedback loop. The optimization unit performs self-optimization and automatic adjustment of the network device using the specific processing unit 290 of the data processing unit 12. The improvement unit improves the model of the generated AI using the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0143] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0144] 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.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0146] 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.

[0147] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0148] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] 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.

[0150] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] 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.

[0156] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] Each of the multiple elements described above, including the data collection unit, preprocessing unit, training unit, monitoring unit, optimization unit, and improvement unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the data collection unit collects network performance data and traffic data using the sensors and cameras of the smart glasses 214. The preprocessing unit cleanses and scales the collected data using the specific processing unit 290 of the data processing unit 12. The training unit trains the generated AI using the specific processing unit 290 of the data processing unit 12. The monitoring unit monitors the network using the control unit 46A of the smart glasses 214 and builds a feedback loop. The optimization unit performs self-optimization and automatic adjustment of the network device using the specific processing unit 290 of the data processing unit 12. The improvement unit improves the model of the generated AI using the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0159] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0160] 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.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0162] 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.

[0163] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0164] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] 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.

[0166] 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.

[0167] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0168] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0169] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0170] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0171] 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.

[0172] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0173] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0174] Each of the multiple elements described above, including the data collection unit, preprocessing unit, training unit, monitoring unit, optimization unit, and improvement unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the data collection unit collects network performance data and traffic data using the sensors and cameras of the headset terminal 314. The preprocessing unit cleanses and scales the collected data using the specific processing unit 290 of the data processing unit 12. The training unit trains the generated AI using the specific processing unit 290 of the data processing unit 12. The monitoring unit monitors the network using the control unit 46A of the headset terminal 314 and builds a feedback loop. The optimization unit performs self-optimization and automatic adjustment of network devices using the specific processing unit 290 of the data processing unit 12. The improvement unit improves the model of the generated AI using the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0175] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0176] 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.

[0177] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0178] 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.

[0179] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0180] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0181] 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.

[0182] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0183] 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.

[0184] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0185] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0186] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0187] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0188] 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.

[0189] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0190] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0191] Each of the multiple elements described above, including the data collection unit, preprocessing unit, training unit, monitoring unit, optimization unit, and improvement unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the data collection unit collects network performance data and traffic data using the sensors and cameras of the robot 414. The preprocessing unit cleanses and scales the collected data using the specific processing unit 290 of the data processing unit 12. The training unit trains the generated AI using the specific processing unit 290 of the data processing unit 12. The monitoring unit monitors the network using the control unit 46A of the robot 414 and builds a feedback loop. The optimization unit performs self-optimization and automatic adjustment of network devices using the specific processing unit 290 of the data processing unit 12. The improvement unit improves the model of the generated AI using the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the devices and control units is not limited to the example described above and can be modified in various ways.

[0192] 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.

[0193] Figure 9 shows the 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.

[0194] 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.

[0195] 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.

[0196] 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, and motorcycles, 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 based, for example, 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.

[0197] 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."

[0198] 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.

[0199] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0208] 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 other things 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.

[0209] 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.

[0210] (Note 1) A collection unit that collects network performance data and traffic data, A preprocessing unit that preprocesses the data collected by the aforementioned collection unit, A training unit that trains a generated AI using data preprocessed by the aforementioned preprocessing unit, A monitoring unit that uses the generative AI trained by the aforementioned training unit to monitor the network and build a feedback loop, An optimization unit performs self-optimization and automatic adjustment of network devices based on data monitored by the aforementioned monitoring unit, The system includes an improvement unit that improves the model of the generated AI using feedback obtained by the optimization unit. A system characterized by the following features. (Note 2) The aforementioned collection unit is Collect network performance data and traffic data. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned pre-processing unit, The collected data is cleansed, missing values ​​are handled, and scaling is performed. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned training department Use the collected data to train the generative AI. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned monitoring unit, Using generative AI to build network monitoring and feedback loops. The system described in Appendix 1, characterized by the features described herein. (Note 6) The optimization unit, Performs self-optimization and automatic adjustment of network devices. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned improvement unit is, Use feedback to improve the generative AI model. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is We estimate the user's emotions and adjust the timing of data collection based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is It detects network anomalies and prioritizes data collection when an anomaly occurs. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is During data collection, the collection frequency is dynamically adjusted according to the network load. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is It estimates the user's emotions and prioritizes the data to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is When collecting data, the geographical distribution of the network is taken into consideration, and highly relevant data is prioritized for collection. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned collection unit is During data collection, network usage is analyzed in real time to select the optimal collection point. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned pre-processing unit, We estimate the user's emotions and adjust the data preprocessing method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned pre-processing unit, During data cleansing, it automatically detects and removes abnormal values ​​and outliers. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned pre-processing unit, When scaling data, different scaling methods are applied depending on the network characteristics. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned pre-processing unit, The system estimates the user's emotions and determines the priority of preprocessing based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned pre-processing unit, The system estimates the user's emotions and determines the priority of preprocessing based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned pre-processing unit, During data preprocessing, the optimal preprocessing method is selected by considering the network topology information. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned pre-processing unit, During data preprocessing, historical network performance data is referenced to improve the accuracy of the preprocessing. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned training department The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned training department By training the network to learn anomaly patterns, the accuracy of anomaly detection can be improved. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned training department During training, the training algorithm is dynamically adjusted according to the network load. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned training department It estimates the user's emotions and determines training priorities based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned training department During training, select training data considering the geographical distribution of the network. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned training department During training, historical network traffic data is referenced to improve training accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned monitoring unit, It estimates the user's emotions and adjusts how monitoring is displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned monitoring unit, During monitoring, network anomalies are detected in real time and alerts are issued. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned monitoring unit, During monitoring, the monitoring frequency is dynamically adjusted according to the network load. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned monitoring unit, It estimates user sentiment and determines monitoring priorities based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned monitoring unit, During monitoring, select monitoring points considering the geographical distribution of the network. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned monitoring unit, During monitoring, historical network performance data is referenced to improve monitoring accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 33) The optimization unit, It estimates the user's emotions and adjusts the optimization method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 34) The optimization unit, During optimization, the optimization algorithm is applied while considering the anomaly patterns of the network. The system described in Appendix 1, characterized by the features described herein. (Note 35) The optimization unit, During optimization, the frequency of optimization is dynamically adjusted according to the network load. The system described in Appendix 1, characterized by the features described herein. (Note 36) The optimization unit, It estimates user emotions and determines optimization priorities based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 37) The optimization unit, During optimization, the geographical distribution of the network is taken into consideration when selecting optimization points. The system described in Appendix 1, characterized by the features described herein. (Note 38) The optimization unit, During optimization, historical network performance data is referenced to improve the accuracy of the optimization. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned improvement unit is, It estimates user sentiment and adjusts improvement methods based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned improvement unit is, When making improvements, the improvement algorithm is applied while considering the network anomaly patterns. The system described in Appendix 1, characterized by the features described herein. (Note 41) The aforementioned improvement unit is, During improvements, the frequency of improvements is dynamically adjusted according to the network load. The system described in Appendix 1, characterized by the features described herein. (Note 42) The aforementioned improvement unit is, We estimate user emotions and determine improvement priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 43) The aforementioned improvement unit is, When making improvements, select improvement points considering the geographical distribution of the network. The system described in Appendix 1, characterized by the features described herein. (Note 44) The aforementioned improvement unit is, When making improvements, historical network performance data is referenced to enhance the accuracy of the improvements. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0211] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A collection unit that collects network performance data and traffic data, A preprocessing unit that preprocesses the data collected by the aforementioned collection unit, A training unit that trains a generated AI using data preprocessed by the aforementioned preprocessing unit, A monitoring unit that uses the generative AI trained by the aforementioned training unit to monitor the network and build a feedback loop, An optimization unit performs self-optimization and automatic adjustment of network devices based on data monitored by the aforementioned monitoring unit, The system includes an improvement unit that improves the model of the generated AI using feedback obtained by the optimization unit. A system characterized by the following features.

2. The aforementioned pre-processing unit, The collected data is cleansed, missing values ​​are handled, and scaling is performed. The system according to feature 1.

3. The aforementioned training department Use the collected data to train a generative AI. The system according to feature 1.

4. The aforementioned monitoring unit, Using generative AI to build network monitoring and feedback loops. The system according to feature 1.

5. The optimization unit, Performs self-optimization and automatic adjustment of network devices. The system according to feature 1.

6. The aforementioned improvement unit is, Use feedback to improve generative AI models. The system according to feature 1.

7. The aforementioned collection unit is We estimate the user's emotions and adjust the timing of data collection based on those estimated emotions. The system according to feature 1.

Images