System

Abstract

An object of a system according to an embodiment is to realize self-optimization and automatic adjustment in an operation of a network.SOLUTION: In one embodiment, a system comprises a AI collector, a pre-processor, a generative data trainer, a monitor, a feedback loop, a self-optimizer, and a model improver. The data collection unit collects data. The preprocessing part preprocesses the data collected by the data collection part. The generative AI trainer is configured to train the generative AI using the output data preprocessed by the preprocessor. The monitoring unit monitors the network using the generated AI trained by the generated AI training unit. The feedback loop unit performs feedback based on the operation data of the network monitored by the monitoring unit. The self-optimization unit performs self-optimization based on the feedback obtained by the feedback loop unit. The model improvement unit improves the model based on the data obtained by the self-optimization unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies do not adequately implement self-optimization and automatic adjustment in network operation, and there is room for improvement.

[0005] The system according to the embodiment aims to achieve self-optimization and self-adjustment in network operation. [Means for solving the problem]

[0006] The system according to the embodiment includes a data collection unit, a preprocessing unit, a generative AI training unit, a monitoring unit, a feedback loop unit, a self-optimization unit, and a model improvement unit. The data collection unit collects data. The preprocessing unit preprocesses the data collected by the data collection unit. The generative AI training unit trains the generative AI using the data preprocessed by the preprocessing unit. The monitoring unit monitors the network using the generative AI trained by the generative AI training unit. The feedback loop unit provides feedback based on operational data of the network monitored by the monitoring unit. The self-optimization unit performs self-optimization based on the feedback obtained by the feedback loop unit. The model improvement unit improves the model based on the data obtained by the self-optimization unit. [Effects of the Invention]

[0007] The system according to the embodiment can achieve self-optimization and auto-tuning in the operation of the network. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls 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), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also 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. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. 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 the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The network system according to the embodiment of the present invention is a system that constantly evolves through the PDCA cycle by learning, optimizing, and adapting to improvements. This is expected to improve the operational efficiency of the network, reduce operational costs, and improve service quality.

[0029] A network system according to an embodiment includes a data collection unit, a preprocessing unit, a generative AI training unit, a monitoring unit, a feedback loop unit, a self-optimization unit, and a model improvement unit. The data collection unit collects network operation data, such as network traffic data and error logs. The data collection unit can also collect user data. The preprocessing unit preprocesses the collected data, such as by normalizing the data. The preprocessing unit can also impute missing values ​​and perform noise removal. The generative AI training unit trains the generative AI using the preprocessed data. For example, the training is performed using a generative model. The generative AI training unit can also train using a deep learning model. The generative AI training unit can also learn traffic patterns and error patterns. The monitoring unit monitors the network using the trained generative AI, such as by performing real-time monitoring. The monitoring unit can also detect anomalies. The monitoring unit can also detect sudden increases in traffic and increases in error logs. The feedback loop unit provides feedback based on the monitored network operation data. For example, the feedback frequency is set. The feedback loop unit can also set the content of the feedback. The feedback loop unit can also set the feedback method. The self-optimization unit performs self-optimization based on the feedback. For example, the optimization is performed using an optimization algorithm. The self-optimization unit can also set evaluation criteria. The self-optimization unit can also perform optimal resource allocation. The model improvement unit improves the model based on data obtained by the self-optimization unit. For example, the model evaluation method is set. The model improvement unit can also set the frequency of improvement. The model improvement unit can also analyze feedback data and improve the model. As a result, the network system according to the embodiment can realize a network that learns by itself, achieves optimization, and adapts improvements, thereby constantly evolving through the PDCA cycle.For example, even if network traffic suddenly increases, the generative AI can monitor the situation in real time and propose appropriate countermeasures to maintain network stability. Furthermore, the generative AI's self-optimization can keep network performance at an optimal level. Furthermore, by receiving feedback and improving the model, the generative AI's accuracy improves, enabling more advanced analysis and optimization.

[0030] The data collection unit collects network traffic data or error logs, removes noise, and extracts necessary information. In the data collection unit, for example, the generation AI analyzes network traffic data in real time and instantly detects and filters out abnormal traffic patterns. For example, it detects a sudden increase in traffic that differs from normal traffic patterns and issues an alert. In the data collection unit, the generation AI analyzes error logs in real time and instantly filters out abnormal error patterns. For example, it detects errors that are concentrated in specific time periods and identifies their causes. In the data collection unit, the generation AI analyzes network operation data in real time and instantly filters out abnormal values. For example, it detects CPU usage or memory usage that exceeds the normal range and issues an alert. This improves data accuracy by collecting network traffic data and error logs, removing noise, and extracting necessary information.

[0031] The generative AI training unit can learn network traffic patterns and error patterns. For example, the generative AI training unit evaluates the reliability of data collected by the generative AI and automatically excludes unreliable data. For example, it checks the consistency and completeness of the data and excludes incomplete data. The generative AI training unit also analyzes the source and collection method of the data and excludes unreliable data so that the generative AI can evaluate the reliability of the data. For example, it excludes data from unreliable sensors. The generative AI training unit also detects abnormal values ​​and outliers in the data and excludes unreliable data so that the generative AI can evaluate the reliability of the data. For example, it excludes data with values ​​outside the normal range. In this way, by learning network traffic patterns and error patterns, the generative AI can accurately grasp the state of the network.

[0032] The monitoring unit can detect a sudden increase in traffic or an increase in error logs, analyze the information, and propose appropriate countermeasures. The monitoring unit, for example, uses an emotion estimation function to analyze the emotional state of the network administrator in real time and optimize data collection in high-stress situations. For example, if the administrator is feeling stressed, the frequency of data collection is adjusted. The monitoring unit also uses the emotion estimation function to analyze the emotional state of the network administrator and optimize data collection in high-stress situations. For example, if the administrator is feeling stressed, the timing of data collection is adjusted. The monitoring unit also uses the emotion estimation function to analyze the emotional state of the network administrator and optimize data collection in high-stress situations. For example, if the administrator is feeling stressed, the method of data collection is adjusted. In this way, it is possible to detect a sudden increase in traffic or an increase in error logs and propose appropriate countermeasures, thereby maintaining network stability.

[0033] The self-optimization unit can distribute traffic or optimally allocate resources. For example, when collecting data, the self-optimization unit collects voice data in addition to network operation data and performs multimodal data analysis. For example, the self-optimization unit analyzes voice instructions from a network administrator and associates the data with the operation data. Furthermore, when collecting data, the self-optimization unit collects image data in addition to network operation data and performs multimodal data analysis. For example, the self-optimization unit analyzes images showing the status of network devices and associates the images with the operation data. Furthermore, when collecting data, the self-optimization unit collects voice data and image data in addition to network operation data and performs multimodal data analysis. For example, the self-optimization unit analyzes voice instructions from a network administrator and images of the device status and associates the images with the operation data. This makes it possible to distribute traffic and optimally allocate resources, thereby improving network performance.

[0034] The model improvement unit can analyze operational data and feedback data and update the generative AI model. The model improvement unit, for example, collects, integrates, and analyzes data from different network environments. For example, it may integrate traffic data from multiple data centers and perform analysis from a global perspective. The model improvement unit also collects, integrates, and analyzes data from different network environments. For example, it may integrate error logs from networks in different regions and perform analysis from a global perspective. The model improvement unit also collects, integrates, and analyzes data from different network environments. For example, it may integrate operational data from networks of different providers and perform analysis from a global perspective. In this way, by analyzing operational data and feedback data and updating the generative AI model, more accurate analysis and optimization become possible.

[0035] The data collection unit can collect voice data or image data in addition to network operation data and perform multimodal data analysis. For example, the data collection unit collects voice data in addition to network operation data when collecting data and performs multimodal data analysis. For example, the data collection unit analyzes voice instructions from a network administrator and associates the results with the operation data. Furthermore, the data collection unit collects image data in addition to network operation data when collecting data and performs multimodal data analysis. For example, it analyzes images showing the status of network devices and associates them with the operation data. Furthermore, the data collection unit collects voice data and image data in addition to network operation data when collecting data and performs multimodal data analysis. For example, it analyzes voice instructions from a network administrator and images of the device status and associates them with the operation data. In this way, collecting voice data and image data in addition to network operation data and performing multimodal data analysis enables more multifaceted analysis.

[0036] The data collection unit can integrate data from different network environments and perform analysis from a global perspective. The data collection unit, for example, collects data from different network environments, integrates the data, and analyzes it. For example, traffic data from multiple data centers can be integrated and analyzed from a global perspective. The data collection unit also collects data from different network environments, integrates the data, and analyzes it. For example, error logs from networks in different regions can be integrated and analyzed from a global perspective. The data collection unit also collects data from different network environments, integrates the data, and analyzes it. For example, operational data from networks of different providers can be integrated and analyzed from a global perspective. This enables a more comprehensive analysis by integrating data from different network environments and analyzing it from a global perspective.

[0037] The generative AI training unit can automatically evaluate the quality of the training data and exclude low-quality data. In the generative AI training unit, for example, the generative AI automatically evaluates the quality of the training data and excludes low-quality data. For example, it checks the consistency and completeness of the data and excludes incomplete data. In addition, the generative AI training unit automatically evaluates the quality of the training data and excludes low-quality data. For example, it analyzes the source and collection method of the data and excludes low-reliability data. In addition, the generative AI training unit automatically evaluates the quality of the training data and excludes low-quality data. For example, it detects abnormal values ​​and outliers in the data and excludes low-reliability data. In this way, by automatically evaluating the quality of the training data and excluding low-quality data, the learning accuracy of the generative AI can be improved.

[0038] The generative AI training unit can perform self-evaluation during training and adjust the learning progress in real time. For example, the generative AI training unit causes the generative AI to perform self-evaluation during training and adjust the learning progress in real time. For example, if the learning progress is slow, the amount of training data is increased. The generative AI training unit also causes the generative AI to perform self-evaluation during training and adjust the learning progress in real time. For example, if the learning progress is too fast, the quality of the training data is improved. The generative AI training unit also causes the generative AI to perform self-evaluation during training and adjust the learning progress in real time. For example, if the learning progress is uneven, the balance of the training data is adjusted. In this way, efficient learning is possible by performing self-evaluation during training and adjusting the learning progress in real time.

[0039] The generative AI training unit can train the generative AI using data from different industries and applications to increase its versatility. For example, the generative AI training unit trains the generative AI using data from different industries to increase its versatility. For example, medical data and financial data are combined to train it. The generative AI training unit also trains the generative AI using data for different applications to increase its versatility. For example, image data and audio data are combined to train it. The generative AI training unit also trains the generative AI using data from different industries and applications to increase its versatility. For example, manufacturing industry data and service industry data are combined to train it. In this way, training the generative AI using data from different industries and applications to increase its versatility makes it possible to apply it to a wide range of fields.

[0040] The generative AI training unit can translate the training data into different languages ​​and build a multilingual generative AI. The generative AI training unit, for example, translates training data into different languages ​​and builds a multilingual generative AI. For example, English data is translated into Japanese and trained. The generative AI training unit also translates training data into different languages ​​and builds a multilingual generative AI. For example, French data is translated into English and trained. The generative AI training unit also translates training data into different languages ​​and builds a multilingual generative AI. For example, Chinese data is translated into Spanish and trained. In this way, translating training data into different languages ​​and building a multilingual generative AI enables global use.

[0041] The monitoring unit analyzes network operation data in real time and can immediately detect abnormalities. For example, the generation AI in the monitoring unit analyzes network traffic data in real time and immediately detects abnormal traffic patterns. For example, it detects a sudden increase in traffic that differs from normal traffic patterns and issues an alert. The monitoring unit also analyzes error logs in real time and immediately detects abnormal error patterns. For example, it detects errors that are concentrated in specific time periods and identifies their causes. The generation AI in the monitoring unit also analyzes network operation data in real time and immediately detects abnormal values. For example, it detects CPU usage or memory usage that exceeds the normal range and issues an alert. This enables rapid response by analyzing network operation data in real time and immediately detecting abnormalities.

[0042] The feedback loop section allows the generation AI to automatically propose and implement countermeasures. For example, when the generation AI analyzes network operation data and detects an abnormality, it automatically proposes and implements countermeasures. For example, if it detects a sudden increase in traffic, it automatically distributes traffic. The feedback loop section also allows the generation AI to analyze error logs and automatically propose and implement countermeasures when it detects an abnormality. For example, if it detects a failure of a specific device, it automatically reallocates resources. The feedback loop section also allows the generation AI to analyze network operation data and automatically propose and implement countermeasures when it detects an abnormality. For example, if it detects CPU usage that exceeds the normal range, it automatically distributes the load. In this way, the generation AI can automatically propose and implement countermeasures, enabling quick response to network problems.

[0043] The monitoring unit can integrate data from different network environments and perform monitoring from a global perspective. The monitoring unit, for example, collects data from different network environments and integrates it for monitoring. For example, traffic data from multiple data centers can be integrated to perform monitoring from a global perspective. The monitoring unit also collects data from different network environments and integrates it for monitoring. For example, error logs from networks in different regions can be integrated to perform monitoring from a global perspective. The monitoring unit also collects data from different network environments and integrates it for monitoring. For example, operational data from networks of different providers can be integrated to perform monitoring from a global perspective. This enables more comprehensive monitoring by integrating data from different network environments and performing monitoring from a global perspective.

[0044] The feedback loop unit allows the generation AI to refer to best practices in different industries and propose optimal measures. For example, the feedback loop unit allows the generation AI to refer to best practices in different industries and analyze network operation data to propose optimal measures. For example, it refers to best practices in the financial industry to propose traffic distribution. The feedback loop unit also allows the generation AI to refer to best practices in different industries and analyze network operation data to propose optimal measures. For example, it refers to best practices in the medical industry to propose a method for analyzing error logs. The feedback loop unit also allows the generation AI to refer to best practices in different industries and analyze network operation data to propose optimal measures. For example, it refers to best practices in the manufacturing industry to propose optimal resource allocation. This allows the generation AI to refer to best practices in different industries and propose optimal measures, making more effective measures possible.

[0045] The self-optimizing unit analyzes network operation data in real time and can automatically perform optimal resource allocation. For example, the self-optimizing unit's generating AI analyzes network traffic data in real time and automatically performs optimal resource allocation. For example, if a sudden increase in traffic is detected, additional resources are automatically allocated. The self-optimizing unit's generating AI also analyzes error logs in real time and automatically performs optimal resource allocation. For example, if a failure of a specific device is detected, resources are automatically reallocated. The self-optimizing unit's generating AI also analyzes network operation data in real time and automatically performs optimal resource allocation. For example, if CPU usage above the normal range is detected, load balancing is automatically performed. In this way, by analyzing network operation data in real time and automatically performing optimal resource allocation, network performance can be improved.

[0046] The self-optimization unit allows the generation AI to refer to past data and make optimal adjustments during self-optimization. For example, the generation AI refers to past traffic data and makes optimal adjustments during self-optimization. For example, it optimally allocates resources based on past traffic patterns. The self-optimization unit also allows the generation AI to refer to past error logs and make optimal adjustments during self-optimization. For example, it reallocates resources based on past error patterns. The self-optimization unit also allows the generation AI to refer to past operational data and make optimal adjustments during self-optimization. For example, it distributes load based on past CPU usage. This allows the generation AI to refer to past data and make optimal adjustments during self-optimization, enabling more effective optimization.

[0047] The self-optimization unit can integrate data from different network environments and perform optimization from a global perspective. The self-optimization unit, for example, collects data from different network environments and integrates it to perform optimization. For example, traffic data from multiple data centers can be integrated to perform optimization from a global perspective. The self-optimization unit also collects data from different network environments and integrates it to perform optimization. For example, error logs from networks in different regions can be integrated to perform optimization from a global perspective. The self-optimization unit also collects data from different network environments and integrates it to perform optimization. For example, operational data from networks of different providers can be integrated to perform optimization from a global perspective. In this way, by integrating data from different network environments and performing optimization from a global perspective, more comprehensive optimization is possible.

[0048] When performing automatic adjustments, the self-optimization unit allows the generating AI to refer to best practices in different industries and make optimal adjustments. For example, the self-optimization unit allows the generating AI to refer to best practices in different industries and analyze network operation data to make optimal adjustments. For example, it refers to best practices in the financial industry to distribute traffic. The self-optimization unit also allows the generating AI to refer to best practices in different industries and analyze network operation data to make optimal adjustments. For example, it refers to best practices in the medical industry to adjust the method of analyzing error logs. The self-optimization unit also allows the generating AI to refer to best practices in different industries and analyze network operation data to make optimal adjustments. For example, it refers to best practices in the manufacturing industry to optimally allocate resources. This allows the generating AI to refer to best practices in different industries and make optimal adjustments, enabling more effective optimization.

[0049] The model improvement unit analyzes the feedback data in real time and can instantly improve the model. In the model improvement unit, for example, the generation AI analyzes the feedback data in real time and instantly improves the model. For example, it adjusts the model parameters in response to fluctuations in operational data. In addition, the model improvement unit analyzes the feedback data in real time and instantly improves the model. For example, it modifies the model algorithm in response to an increase in error logs. In addition, the model improvement unit analyzes the feedback data in real time and instantly improves the model. For example, it reconstructs the model structure in response to changes in traffic patterns. This allows for rapid response by analyzing feedback data in real time and instantly improving the model.

[0050] The model improvement unit allows the generating AI to automatically suggest and implement improvements when feedback is received. For example, the generating AI analyzes feedback data and automatically suggests and implements improvements. For example, if a sudden increase in traffic is detected, it proposes and implements traffic distribution. The generating AI also analyzes feedback data and automatically suggests and implements improvements. For example, if a failure of a specific device is detected, it proposes and implements resource reallocation. The model improvement unit also allows the generating AI to analyze feedback data and automatically propose and implement improvements. For example, if CPU usage above the normal range is detected, it proposes and implements load distribution. In this way, the generating AI automatically suggests and implements improvements, enabling quick response to network problems.

[0051] The model improvement unit can integrate feedback data from different network environments and improve the model from a global perspective. The model improvement unit, for example, collects feedback data from different network environments and integrates it to improve the model. For example, feedback data from multiple data centers is integrated to improve the model from a global perspective. The model improvement unit also collects feedback data from different network environments and integrates it to improve the model. For example, feedback data from networks in different regions is integrated to improve the model from a global perspective. The model improvement unit also collects feedback data from different network environments and integrates it to improve the model. For example, feedback data from networks of different providers is integrated to improve the model from a global perspective. In this way, by integrating feedback data from different network environments and improving the model from a global perspective, more comprehensive improvements are possible.

[0052] The model improvement unit can translate the feedback data into different languages ​​and perform multilingual model improvement. The model improvement unit, for example, translates the feedback data into different languages ​​and performs multilingual model improvement. For example, English feedback data is translated into Japanese and the model is improved. The model improvement unit also translates the feedback data into different languages ​​and performs multilingual model improvement. For example, French feedback data is translated into English and the model is improved. The model improvement unit also translates the feedback data into different languages ​​and performs multilingual model improvement. For example, Chinese feedback data is translated into Spanish and the model is improved. In this way, translating the feedback data into different languages ​​and performing multilingual model improvement enables global use.

[0053] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0054] The network system can further include an anomaly detection unit. The anomaly detection unit can analyze network operation data in real time and immediately detect anomalies. For example, it can detect a sudden increase in traffic that differs from normal traffic patterns and issue an alert. The anomaly detection unit can also detect errors that are concentrated in specific time periods and identify their causes. Furthermore, the anomaly detection unit can detect CPU usage or memory usage that exceeds the normal range and issue an alert. This allows for the network operation data to be analyzed in real time and anomalies to be immediately detected, enabling a rapid response.

[0055] The network system can further include a predictive analysis unit. The predictive analysis unit can analyze past operational data and predict future traffic patterns and error patterns. For example, the predictive analysis unit can predict the next peak time period based on past traffic data and optimally allocate resources. The predictive analysis unit can also predict the next error that is likely to occur based on past error logs and take measures in advance. Furthermore, the predictive analysis unit can predict the next abnormal value that is likely to occur based on past operational data and issue an alert in advance. In this way, by using the predictive analysis unit to predict future traffic patterns and error patterns, the stability of the network can be improved.

[0056] The network system may further include a user interface unit. The user interface unit may visually display the network operation status and anomaly detection results. For example, the user interface unit may display real-time traffic status in graphs and charts, allowing the administrator to intuitively understand the status. The user interface unit may also display anomaly detection results as alerts, allowing the administrator to respond quickly. Furthermore, the user interface unit may display predictive analysis results, allowing the administrator to visually check future traffic patterns and error patterns. In this way, the burden on the administrator can be reduced by visually displaying the network operation status and anomaly detection results using the user interface unit.

[0057] The network system can further include a resource management unit. The resource management unit can efficiently manage network resources and optimally allocate resources. For example, if a sudden increase in traffic is detected, additional resources can be automatically allocated. Also, if a failure of a specific device is detected, the resource management unit can automatically reallocate resources. Furthermore, if a CPU usage rate that exceeds the normal range is detected, the resource management unit can automatically distribute the load. In this way, by efficiently managing network resources using the resource management unit and optimally allocating resources, network performance can be improved.

[0058] The network system can further include a security monitoring unit. The security monitoring unit can monitor the security status of the network in real time and immediately detect any abnormalities. For example, it can detect unauthorized access and issue an alert. The security monitoring unit can also detect malware infections and take countermeasures. Furthermore, the security monitoring unit can detect network vulnerabilities and suggest fixes. In this way, the security of the network can be improved by using the security monitoring unit to monitor the security status of the network in real time and immediately detect any abnormalities.

[0059] The processing flow of the first embodiment will be briefly explained below.

[0060] Step 1: The data collection unit collects network operation data, such as network traffic data and error logs. The data collection unit can also collect user data. Step 2: The preprocessing section preprocesses the collected data. For example, it normalizes the data. The preprocessing section can also perform missing value imputation and noise removal. Step 3: The generative AI training unit trains the generative AI using the preprocessed data. For example, training can be done using a generative model or a deep learning model. It can also learn traffic patterns and error patterns. Step 4: The monitoring unit uses the trained generative AI to monitor the network. For example, it performs real-time monitoring and anomaly detection. It can also detect sudden increases in traffic and error logs. Step 5: The feedback loop unit provides feedback based on the monitored network operation data. For example, the frequency, content, and method of feedback can be configured. Step 6: The self-optimization unit performs self-optimization based on the feedback. For example, it can perform optimization using an optimization algorithm, set evaluation criteria, and perform optimal resource allocation. Step 7: The model improvement unit improves the model based on the data obtained by the self-optimization unit. For example, it can set the model evaluation method and improvement frequency, and analyze the feedback data to improve the model.

[0061] (Example 2) The network system according to the embodiment of the present invention is a system that constantly evolves through the PDCA cycle by learning, optimizing, and adapting to improvements. This is expected to improve the operational efficiency of the network, reduce operational costs, and improve service quality.

[0062] A network system according to an embodiment includes a data collection unit, a preprocessing unit, a generative AI training unit, a monitoring unit, a feedback loop unit, a self-optimization unit, and a model improvement unit. The data collection unit collects network operation data, such as network traffic data and error logs. The data collection unit can also collect user data. The preprocessing unit preprocesses the collected data, such as by normalizing the data. The preprocessing unit can also impute missing values ​​and perform noise removal. The generative AI training unit trains the generative AI using the preprocessed data. For example, the training is performed using a generative model. The generative AI training unit can also train using a deep learning model. The generative AI training unit can also learn traffic patterns and error patterns. The monitoring unit monitors the network using the trained generative AI, such as by performing real-time monitoring. The monitoring unit can also detect anomalies. The monitoring unit can also detect sudden increases in traffic and increases in error logs. The feedback loop unit provides feedback based on the monitored network operation data. For example, the feedback frequency is set. The feedback loop unit can also set the content of the feedback. The feedback loop unit can also set the feedback method. The self-optimization unit performs self-optimization based on the feedback. For example, the optimization is performed using an optimization algorithm. The self-optimization unit can also set evaluation criteria. The self-optimization unit can also perform optimal resource allocation. The model improvement unit improves the model based on data obtained by the self-optimization unit. For example, the model evaluation method is set. The model improvement unit can also set the frequency of improvement. The model improvement unit can also analyze feedback data and improve the model. As a result, the network system according to the embodiment can realize a network that learns by itself, achieves optimization, and adapts improvements, thereby constantly evolving through the PDCA cycle.For example, even if network traffic suddenly increases, the generative AI can monitor the situation in real time and propose appropriate countermeasures to maintain network stability. Furthermore, the generative AI's self-optimization can keep network performance at an optimal level. Furthermore, by receiving feedback and improving the model, the generative AI's accuracy improves, enabling more advanced analysis and optimization.

[0063] The data collection unit collects network traffic data or error logs, removes noise, and extracts necessary information. In the data collection unit, for example, the generation AI analyzes network traffic data in real time and instantly detects and filters out abnormal traffic patterns. For example, it detects a sudden increase in traffic that differs from normal traffic patterns and issues an alert. In the data collection unit, the generation AI analyzes error logs in real time and instantly filters out abnormal error patterns. For example, it detects errors that are concentrated in specific time periods and identifies their causes. In the data collection unit, the generation AI analyzes network operation data in real time and instantly filters out abnormal values. For example, it detects CPU usage or memory usage that exceeds the normal range and issues an alert. This improves data accuracy by collecting network traffic data and error logs, removing noise, and extracting necessary information.

[0064] The generative AI training unit can learn network traffic patterns and error patterns. For example, the generative AI training unit evaluates the reliability of data collected by the generative AI and automatically excludes unreliable data. For example, it checks the consistency and completeness of the data and excludes incomplete data. The generative AI training unit also analyzes the source and collection method of the data and excludes unreliable data so that the generative AI can evaluate the reliability of the data. For example, it excludes data from unreliable sensors. The generative AI training unit also detects abnormal values ​​and outliers in the data and excludes unreliable data so that the generative AI can evaluate the reliability of the data. For example, it excludes data with values ​​outside the normal range. In this way, by learning network traffic patterns and error patterns, the generative AI can accurately grasp the state of the network.

[0065] The monitoring unit can detect a sudden increase in traffic or an increase in error logs, analyze the information, and propose appropriate countermeasures. The monitoring unit, for example, uses an emotion estimation function to analyze the emotional state of the network administrator in real time and optimize data collection in high-stress situations. For example, if the administrator is feeling stressed, the frequency of data collection is adjusted. The monitoring unit also uses the emotion estimation function to analyze the emotional state of the network administrator and optimize data collection in high-stress situations. For example, if the administrator is feeling stressed, the timing of data collection is adjusted. The monitoring unit also uses the emotion estimation function to analyze the emotional state of the network administrator and optimize data collection in high-stress situations. For example, if the administrator is feeling stressed, the method of data collection is adjusted. In this way, it is possible to detect a sudden increase in traffic or an increase in error logs and propose appropriate countermeasures, thereby maintaining network stability.

[0066] The self-optimization unit can distribute traffic or optimally allocate resources. For example, when collecting data, the self-optimization unit collects voice data in addition to network operation data and performs multimodal data analysis. For example, the self-optimization unit analyzes voice instructions from a network administrator and associates the data with the operation data. Furthermore, when collecting data, the self-optimization unit collects image data in addition to network operation data and performs multimodal data analysis. For example, the self-optimization unit analyzes images showing the status of network devices and associates the images with the operation data. Furthermore, when collecting data, the self-optimization unit collects voice data and image data in addition to network operation data and performs multimodal data analysis. For example, the self-optimization unit analyzes voice instructions from a network administrator and images of the device status and associates the images with the operation data. This makes it possible to distribute traffic and optimally allocate resources, thereby improving network performance.

[0067] The model improvement unit can analyze operational data and feedback data and update the generative AI model. The model improvement unit, for example, collects, integrates, and analyzes data from different network environments. For example, it may integrate traffic data from multiple data centers and perform analysis from a global perspective. The model improvement unit also collects, integrates, and analyzes data from different network environments. For example, it may integrate error logs from networks in different regions and perform analysis from a global perspective. The model improvement unit also collects, integrates, and analyzes data from different network environments. For example, it may integrate operational data from networks of different providers and perform analysis from a global perspective. In this way, by analyzing operational data and feedback data and updating the generative AI model, more accurate analysis and optimization become possible.

[0068] The data collection unit can collect voice data or image data in addition to network operation data and perform multimodal data analysis. For example, the data collection unit collects voice data in addition to network operation data when collecting data and performs multimodal data analysis. For example, the data collection unit analyzes voice instructions from a network administrator and associates the results with the operation data. Furthermore, the data collection unit collects image data in addition to network operation data when collecting data and performs multimodal data analysis. For example, it analyzes images showing the status of network devices and associates them with the operation data. Furthermore, the data collection unit collects voice data and image data in addition to network operation data when collecting data and performs multimodal data analysis. For example, it analyzes voice instructions from a network administrator and images of the device status and associates them with the operation data. In this way, collecting voice data and image data in addition to network operation data and performing multimodal data analysis enables more multifaceted analysis.

[0069] The data collection unit can integrate data from different network environments and perform analysis from a global perspective. The data collection unit, for example, collects data from different network environments, integrates the data, and analyzes it. For example, traffic data from multiple data centers can be integrated and analyzed from a global perspective. The data collection unit also collects data from different network environments, integrates the data, and analyzes it. For example, error logs from networks in different regions can be integrated and analyzed from a global perspective. The data collection unit also collects data from different network environments, integrates the data, and analyzes it. For example, operational data from networks of different providers can be integrated and analyzed from a global perspective. This enables a more comprehensive analysis by integrating data from different network environments and analyzing it from a global perspective.

[0070] The data collection unit can use the emotion estimation function to optimize the timing of data collection based on the user's emotions. The data collection unit, for example, uses the emotion estimation function to analyze the user's emotional state and optimize the timing of data collection. For example, data collection is performed when the user is relaxed. The data collection unit also uses the emotion estimation function to analyze the user's emotional state and optimize the timing of data collection. For example, data collection is performed when the user is not feeling stressed. The data collection unit also uses the emotion estimation function to analyze the user's emotional state and optimize the timing of data collection. For example, data collection is performed when the user is feeling positive emotions. In this way, by using the emotion estimation function to optimize the timing of data collection based on the user's emotions, the burden on the user can be reduced.

[0071] The generative AI training unit can automatically evaluate the quality of the training data and exclude low-quality data. In the generative AI training unit, for example, the generative AI automatically evaluates the quality of the training data and excludes low-quality data. For example, it checks the consistency and completeness of the data and excludes incomplete data. In addition, the generative AI training unit automatically evaluates the quality of the training data and excludes low-quality data. For example, it analyzes the source and collection method of the data and excludes low-reliability data. In addition, the generative AI training unit automatically evaluates the quality of the training data and excludes low-quality data. For example, it detects abnormal values ​​and outliers in the data and excludes low-reliability data. In this way, by automatically evaluating the quality of the training data and excluding low-quality data, the learning accuracy of the generative AI can be improved.

[0072] The generative AI training unit can perform self-evaluation during training and adjust the learning progress in real time. For example, the generative AI training unit causes the generative AI to perform self-evaluation during training and adjust the learning progress in real time. For example, if the learning progress is slow, the amount of training data is increased. The generative AI training unit also causes the generative AI to perform self-evaluation during training and adjust the learning progress in real time. For example, if the learning progress is too fast, the quality of the training data is improved. The generative AI training unit also causes the generative AI to perform self-evaluation during training and adjust the learning progress in real time. For example, if the learning progress is uneven, the balance of the training data is adjusted. In this way, efficient learning is possible by performing self-evaluation during training and adjusting the learning progress in real time.

[0073] The generative AI training unit can use the emotion estimation function to analyze emotional elements contained in the training data and perform emotion-based learning. The generative AI training unit, for example, uses the emotion estimation function to analyze emotional elements contained in the training data and perform emotion-based learning. For example, it prioritizes learning from data with positive emotions. The generative AI training unit also uses the emotion estimation function to analyze emotional elements contained in the training data and perform emotion-based learning. For example, it excludes data with negative emotions. The generative AI training unit also uses the emotion estimation function to analyze emotional elements contained in the training data and perform emotion-based learning. For example, it selects training data taking into consideration the balance of emotions. In this way, by using the emotion estimation function to analyze emotional elements contained in the training data and perform emotion-based learning, it is possible to build a generative AI with understanding closer to that of humans.

[0074] The generative AI training unit can train the generative AI using data from different industries and applications to increase its versatility. For example, the generative AI training unit trains the generative AI using data from different industries to increase its versatility. For example, medical data and financial data are combined to train it. The generative AI training unit also trains the generative AI using data for different applications to increase its versatility. For example, image data and audio data are combined to train it. The generative AI training unit also trains the generative AI using data from different industries and applications to increase its versatility. For example, manufacturing industry data and service industry data are combined to train it. In this way, training the generative AI using data from different industries and applications to increase its versatility makes it possible to apply it to a wide range of fields.

[0075] The generative AI training unit can translate the training data into different languages ​​and build a multilingual generative AI. The generative AI training unit, for example, translates training data into different languages ​​and builds a multilingual generative AI. For example, English data is translated into Japanese and trained. The generative AI training unit also translates training data into different languages ​​and builds a multilingual generative AI. For example, French data is translated into English and trained. The generative AI training unit also translates training data into different languages ​​and builds a multilingual generative AI. For example, Chinese data is translated into Spanish and trained. In this way, translating training data into different languages ​​and building a multilingual generative AI enables global use.

[0076] The generative AI training unit can use the emotion estimation function to collect the user's emotional responses to the training data and improve the quality of learning. The generative AI training unit, for example, uses the emotion estimation function to collect the user's emotional responses to the training data and improve the quality of learning. For example, data with a high number of positive emotional responses is preferentially learned. The generative AI training unit also uses the emotion estimation function to collect the user's emotional responses to the training data and improve the quality of learning. For example, data with a high number of negative emotional responses is excluded. The generative AI training unit also uses the emotion estimation function to collect the user's emotional responses to the training data and improve the quality of learning. For example, the training data is selected taking into consideration the balance of emotions. In this way, by using the emotion estimation function to collect the user's emotional responses to the training data and improving the quality of learning, it is possible to build a generative AI that is more suitable for the user.

[0077] The monitoring unit analyzes network operation data in real time and can immediately detect abnormalities. For example, the generation AI in the monitoring unit analyzes network traffic data in real time and immediately detects abnormal traffic patterns. For example, it detects a sudden increase in traffic that differs from normal traffic patterns and issues an alert. The monitoring unit also analyzes error logs in real time and immediately detects abnormal error patterns. For example, it detects errors that are concentrated in specific time periods and identifies their causes. The generation AI in the monitoring unit also analyzes network operation data in real time and immediately detects abnormal values. For example, it detects CPU usage or memory usage that exceeds the normal range and issues an alert. This enables rapid response by analyzing network operation data in real time and immediately detecting abnormalities.

[0078] The feedback loop section allows the generation AI to automatically propose and implement countermeasures. For example, when the generation AI analyzes network operation data and detects an abnormality, it automatically proposes and implements countermeasures. For example, if it detects a sudden increase in traffic, it automatically distributes traffic. The feedback loop section also allows the generation AI to analyze error logs and automatically propose and implement countermeasures when it detects an abnormality. For example, if it detects a failure of a specific device, it automatically reallocates resources. The feedback loop section also allows the generation AI to analyze network operation data and automatically propose and implement countermeasures when it detects an abnormality. For example, if it detects CPU usage that exceeds the normal range, it automatically distributes the load. In this way, the generation AI can automatically propose and implement countermeasures, enabling quick response to network problems.

[0079] The feedback loop unit can use the emotion estimation function to analyze the emotional state of the network administrator and optimize feedback in high-stress situations. The feedback loop unit, for example, uses the emotion estimation function to analyze the emotional state of the network administrator in real time and optimize feedback in high-stress situations. For example, if the administrator is feeling stressed, the frequency of feedback is adjusted. The feedback loop unit also uses the emotion estimation function to analyze the emotional state of the network administrator and optimize feedback in high-stress situations. For example, if the administrator is feeling stressed, the content of the feedback is adjusted. The feedback loop unit also uses the emotion estimation function to analyze the emotional state of the network administrator and optimize feedback in high-stress situations. For example, if the administrator is feeling stressed, the timing of feedback is adjusted. In this way, by using the emotion estimation function to analyze the emotional state of the network administrator and optimizing feedback in high-stress situations, the burden on the administrator can be reduced.

[0080] The monitoring unit can integrate data from different network environments and perform monitoring from a global perspective. The monitoring unit, for example, collects data from different network environments and integrates it for monitoring. For example, traffic data from multiple data centers can be integrated to perform monitoring from a global perspective. The monitoring unit also collects data from different network environments and integrates it for monitoring. For example, error logs from networks in different regions can be integrated to perform monitoring from a global perspective. The monitoring unit also collects data from different network environments and integrates it for monitoring. For example, operational data from networks of different providers can be integrated to perform monitoring from a global perspective. This enables more comprehensive monitoring by integrating data from different network environments and performing monitoring from a global perspective.

[0081] The feedback loop unit allows the generation AI to refer to best practices in different industries and propose optimal measures. For example, the feedback loop unit allows the generation AI to refer to best practices in different industries and analyze network operation data to propose optimal measures. For example, it refers to best practices in the financial industry to propose traffic distribution. The feedback loop unit also allows the generation AI to refer to best practices in different industries and analyze network operation data to propose optimal measures. For example, it refers to best practices in the medical industry to propose a method for analyzing error logs. The feedback loop unit also allows the generation AI to refer to best practices in different industries and analyze network operation data to propose optimal measures. For example, it refers to best practices in the manufacturing industry to propose optimal resource allocation. This allows the generation AI to refer to best practices in different industries and propose optimal measures, making more effective measures possible.

[0082] The feedback loop unit uses the emotion estimation function to provide feedback based on the user's emotion, thereby optimizing network operation. The feedback loop unit, for example, uses the emotion estimation function to analyze the user's emotional state and provide feedback based on the emotion. For example, if the user is feeling stressed, the feedback content is adjusted. The feedback loop unit also uses the emotion estimation function to analyze the user's emotional state and provide feedback based on the emotion. For example, if the user has positive emotions, the feedback loop unit adjusts the frequency of feedback. The feedback loop unit also uses the emotion estimation function to analyze the user's emotional state and provide feedback based on the emotion. For example, if the user has negative emotions, the feedback timing is adjusted. In this way, by using the emotion estimation function to provide feedback based on the user's emotion and optimizing network operation, user satisfaction can be improved.

[0083] The self-optimizing unit analyzes network operation data in real time and can automatically perform optimal resource allocation. For example, the self-optimizing unit's generating AI analyzes network traffic data in real time and automatically performs optimal resource allocation. For example, if a sudden increase in traffic is detected, additional resources are automatically allocated. The self-optimizing unit's generating AI also analyzes error logs in real time and automatically performs optimal resource allocation. For example, if a failure of a specific device is detected, resources are automatically reallocated. The self-optimizing unit's generating AI also analyzes network operation data in real time and automatically performs optimal resource allocation. For example, if CPU usage above the normal range is detected, load balancing is automatically performed. In this way, by analyzing network operation data in real time and automatically performing optimal resource allocation, network performance can be improved.

[0084] The self-optimization unit allows the generation AI to refer to past data and make optimal adjustments during self-optimization. For example, the generation AI refers to past traffic data and makes optimal adjustments during self-optimization. For example, it optimally allocates resources based on past traffic patterns. The self-optimization unit also allows the generation AI to refer to past error logs and make optimal adjustments during self-optimization. For example, it reallocates resources based on past error patterns. The self-optimization unit also allows the generation AI to refer to past operational data and make optimal adjustments during self-optimization. For example, it distributes load based on past CPU usage. This allows the generation AI to refer to past data and make optimal adjustments during self-optimization, enabling more effective optimization.

[0085] The self-optimization unit can use the emotion estimation function to analyze the emotional state of the network administrator and perform optimization in high-stress situations. The self-optimization unit, for example, uses the emotion estimation function to analyze the emotional state of the network administrator in real time and perform optimization in high-stress situations. For example, if the administrator is feeling stressed, the frequency of optimization is adjusted. The self-optimization unit also uses the emotion estimation function to analyze the emotional state of the network administrator and perform optimization in high-stress situations. For example, if the administrator is feeling stressed, the content of optimization is adjusted. The self-optimization unit also uses the emotion estimation function to analyze the emotional state of the network administrator and perform optimization in high-stress situations. For example, if the administrator is feeling stressed, the timing of optimization is adjusted. In this way, by using the emotion estimation function to analyze the emotional state of the network administrator and perform optimization in high-stress situations, the burden on the administrator can be reduced.

[0086] The self-optimization unit can integrate data from different network environments and perform optimization from a global perspective. The self-optimization unit, for example, collects data from different network environments and integrates it to perform optimization. For example, traffic data from multiple data centers can be integrated to perform optimization from a global perspective. The self-optimization unit also collects data from different network environments and integrates it to perform optimization. For example, error logs from networks in different regions can be integrated to perform optimization from a global perspective. The self-optimization unit also collects data from different network environments and integrates it to perform optimization. For example, operational data from networks of different providers can be integrated to perform optimization from a global perspective. In this way, by integrating data from different network environments and performing optimization from a global perspective, more comprehensive optimization is possible.

[0087] When performing automatic adjustments, the self-optimization unit allows the generating AI to refer to best practices in different industries and make optimal adjustments. For example, the self-optimization unit allows the generating AI to refer to best practices in different industries and analyze network operation data to make optimal adjustments. For example, it refers to best practices in the financial industry to distribute traffic. The self-optimization unit also allows the generating AI to refer to best practices in different industries and analyze network operation data to make optimal adjustments. For example, it refers to best practices in the medical industry to adjust the method of analyzing error logs. The self-optimization unit also allows the generating AI to refer to best practices in different industries and analyze network operation data to make optimal adjustments. For example, it refers to best practices in the manufacturing industry to optimally allocate resources. This allows the generating AI to refer to best practices in different industries and make optimal adjustments, enabling more effective optimization.

[0088] The self-optimization unit uses the emotion estimation function to perform optimization based on the user's emotions, thereby optimizing network operation. The self-optimization unit, for example, uses the emotion estimation function to analyze the user's emotional state and perform optimization based on the emotions. For example, if the user is feeling stressed, the self-optimization unit adjusts the content of optimization. The self-optimization unit also uses the emotion estimation function to analyze the user's emotional state and perform optimization based on the emotions. For example, if the user has positive emotions, the self-optimization unit adjusts the frequency of optimization. The self-optimization unit also uses the emotion estimation function to analyze the user's emotional state and perform optimization based on the emotions. For example, if the user has negative emotions, the self-optimization unit adjusts the timing of optimization. In this way, by using the emotion estimation function to perform optimization based on the user's emotions and optimizing network operation, user satisfaction can be improved.

[0089] The model improvement unit analyzes the feedback data in real time and can instantly improve the model. In the model improvement unit, for example, the generation AI analyzes the feedback data in real time and instantly improves the model. For example, it adjusts the model parameters in response to fluctuations in operational data. In addition, the model improvement unit analyzes the feedback data in real time and instantly improves the model. For example, it modifies the model algorithm in response to an increase in error logs. In addition, the model improvement unit analyzes the feedback data in real time and instantly improves the model. For example, it reconstructs the model structure in response to changes in traffic patterns. This allows for rapid response by analyzing feedback data in real time and instantly improving the model.

[0090] The model improvement unit allows the generating AI to automatically suggest and implement improvements when feedback is received. For example, the generating AI analyzes feedback data and automatically suggests and implements improvements. For example, if a sudden increase in traffic is detected, it proposes and implements traffic distribution. The generating AI also analyzes feedback data and automatically suggests and implements improvements. For example, if a failure of a specific device is detected, it proposes and implements resource reallocation. The model improvement unit also allows the generating AI to analyze feedback data and automatically propose and implement improvements. For example, if CPU usage above the normal range is detected, it proposes and implements load distribution. In this way, the generating AI automatically suggests and implements improvements, enabling quick response to network problems.

[0091] The model improvement unit can use the emotion estimation function to analyze emotional elements included in the feedback data and improve the model based on the emotions. The model improvement unit, for example, uses the emotion estimation function to analyze emotional elements included in the feedback data and improve the model based on the emotions. For example, feedback with positive emotions is preferentially reflected. The model improvement unit also uses the emotion estimation function to analyze emotional elements included in the feedback data and improve the model based on the emotions. For example, feedback with negative emotions is excluded. The model improvement unit also uses the emotion estimation function to analyze emotional elements included in the feedback data and improve the model based on the emotions. For example, feedback is reflected taking into account the balance of emotions. In this way, by using the emotion estimation function to analyze emotional elements included in the feedback data and improve the model based on emotions, it is possible to build a generative AI that is more suitable for the user.

[0092] The model improvement unit can integrate feedback data from different network environments and improve the model from a global perspective. The model improvement unit, for example, collects feedback data from different network environments and integrates it to improve the model. For example, feedback data from multiple data centers is integrated to improve the model from a global perspective. The model improvement unit also collects feedback data from different network environments and integrates it to improve the model. For example, feedback data from networks in different regions is integrated to improve the model from a global perspective. The model improvement unit also collects feedback data from different network environments and integrates it to improve the model. For example, feedback data from networks of different providers is integrated to improve the model from a global perspective. In this way, by integrating feedback data from different network environments and improving the model from a global perspective, more comprehensive improvements are possible.

[0093] The model improvement unit can translate the feedback data into different languages ​​and perform multilingual model improvement. The model improvement unit, for example, translates the feedback data into different languages ​​and performs multilingual model improvement. For example, English feedback data is translated into Japanese and the model is improved. The model improvement unit also translates the feedback data into different languages ​​and performs multilingual model improvement. For example, French feedback data is translated into English and the model is improved. The model improvement unit also translates the feedback data into different languages ​​and performs multilingual model improvement. For example, Chinese feedback data is translated into Spanish and the model is improved. In this way, translating the feedback data into different languages ​​and performing multilingual model improvement enables global use.

[0094] The model improvement unit can use the emotion estimation function to collect feedback based on the user's emotions and improve the model. For example, the model improvement unit uses the emotion estimation function to analyze the user's emotional state and collect feedback based on the emotions. For example, if the user has positive emotions, the model improvement unit adjusts the content of the feedback. The model improvement unit also uses the emotion estimation function to analyze the user's emotional state and collect feedback based on the emotions. For example, if the user is feeling stressed, the model improvement unit adjusts the frequency of the feedback. The model improvement unit also uses the emotion estimation function to analyze the user's emotional state and collect feedback based on the emotions. For example, if the user has negative emotions, the model improvement unit adjusts the timing of the feedback. In this way, by using the emotion estimation function to collect feedback based on the user's emotions and improve the model, it is possible to build a generative AI that is more suitable for the user.

[0095] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0096] The network system can further include an anomaly detection unit. The anomaly detection unit can analyze network operation data in real time and immediately detect anomalies. For example, it can detect a sudden increase in traffic that differs from normal traffic patterns and issue an alert. The anomaly detection unit can also detect errors that are concentrated in specific time periods and identify their causes. Furthermore, the anomaly detection unit can detect CPU usage or memory usage that exceeds the normal range and issue an alert. This allows for the network operation data to be analyzed in real time and anomalies to be immediately detected, enabling a rapid response.

[0097] The network system can further include a predictive analysis unit. The predictive analysis unit can analyze past operational data and predict future traffic patterns and error patterns. For example, the predictive analysis unit can predict the next peak time period based on past traffic data and optimally allocate resources. The predictive analysis unit can also predict the next error that is likely to occur based on past error logs and take measures in advance. Furthermore, the predictive analysis unit can predict the next abnormal value that is likely to occur based on past operational data and issue an alert in advance. In this way, by using the predictive analysis unit to predict future traffic patterns and error patterns, the stability of the network can be improved.

[0098] The network system may further include a user interface unit. The user interface unit may visually display the network operation status and anomaly detection results. For example, the user interface unit may display real-time traffic status in graphs and charts, allowing the administrator to intuitively understand the status. The user interface unit may also display anomaly detection results as alerts, allowing the administrator to respond quickly. Furthermore, the user interface unit may display predictive analysis results, allowing the administrator to visually check future traffic patterns and error patterns. In this way, the burden on the administrator can be reduced by visually displaying the network operation status and anomaly detection results using the user interface unit.

[0099] The network system can further include a resource management unit. The resource management unit can efficiently manage network resources and optimally allocate resources. For example, if a sudden increase in traffic is detected, additional resources can be automatically allocated. Also, if a failure of a specific device is detected, the resource management unit can automatically reallocate resources. Furthermore, if a CPU usage rate that exceeds the normal range is detected, the resource management unit can automatically distribute the load. In this way, by efficiently managing network resources using the resource management unit and optimally allocating resources, network performance can be improved.

[0100] The network system can further include a security monitoring unit. The security monitoring unit can monitor the security status of the network in real time and immediately detect any abnormalities. For example, it can detect unauthorized access and issue an alert. The security monitoring unit can also detect malware infections and take countermeasures. Furthermore, the security monitoring unit can detect network vulnerabilities and suggest fixes. In this way, the security of the network can be improved by using the security monitoring unit to monitor the security status of the network in real time and immediately detect any abnormalities.

[0101] The network system can further use the emotion estimation function to provide feedback based on the user's emotions. For example, if the user is feeling stressed, the content of the feedback can be adjusted. Also, if the user has positive emotions, the frequency of the feedback can be adjusted. Furthermore, if the user has negative emotions, the timing of the feedback can be adjusted. In this way, by using the emotion estimation function to provide feedback based on the user's emotions, it is possible to improve user satisfaction.

[0102] The network system can further use the emotion estimation function to analyze the emotional state of the network administrator and optimize data collection in high-stress situations. For example, if the administrator is feeling stressed, the frequency of data collection can be adjusted. Also, if the administrator is feeling stressed, the timing of data collection can be adjusted. Furthermore, if the administrator is feeling stressed, the method of data collection can be adjusted. In this way, by using the emotion estimation function to analyze the emotional state of the network administrator and optimizing data collection in high-stress situations, the burden on the administrator can be reduced.

[0103] The network system can also use its emotion estimation function to analyze the emotional elements contained in the training data and perform emotion-based learning. For example, it can prioritize learning from data containing positive emotions, or it can filter out data containing negative emotions. Furthermore, it can select training data with consideration for emotional balance. This allows the network system to use its emotion estimation function to analyze the emotional elements contained in the training data and perform emotion-based learning, thereby building a generative AI with understanding closer to that of humans.

[0104] The network system can further use the emotion estimation function to optimize the timing of data collection based on the user's emotions. For example, data collection can be performed when the user is relaxed. Also, data collection can be performed when the user is not feeling stressed. Furthermore, data collection can be performed when the user is feeling positive emotions. In this way, by using the emotion estimation function to optimize the timing of data collection based on the user's emotions, the burden on the user can be reduced.

[0105] The network system can further use the emotion estimation function to collect feedback based on the user's emotions and improve the model. For example, if the user has positive emotions, the content of the feedback can be adjusted. Also, if the user is feeling stressed, the frequency of feedback can be adjusted. Furthermore, if the user has negative emotions, the timing of feedback can be adjusted. In this way, by using the emotion estimation function to collect feedback based on the user's emotions and improve the model, it is possible to build a generative AI that is more suited to the user.

[0106] The processing flow of the second embodiment will be briefly explained below.

[0107] Step 1: The data collection unit collects network operation data, such as network traffic data and error logs. The data collection unit can also collect user data. Step 2: The preprocessing section preprocesses the collected data. For example, it normalizes the data. The preprocessing section can also perform missing value imputation and noise removal. Step 3: The generative AI training unit trains the generative AI using the preprocessed data. For example, training can be done using a generative model or a deep learning model. It can also learn traffic patterns and error patterns. Step 4: The monitoring unit uses the trained generative AI to monitor the network. For example, it performs real-time monitoring and anomaly detection. It can also detect sudden increases in traffic and error logs. Step 5: The feedback loop unit provides feedback based on the monitored network operation data. For example, the frequency, content, and method of feedback can be configured. Step 6: The self-optimization unit performs self-optimization based on the feedback. For example, it can perform optimization using an optimization algorithm, set evaluation criteria, and perform optimal resource allocation. Step 7: The model improvement unit improves the model based on the data obtained by the self-optimization unit. For example, it can set the model evaluation method and improvement frequency, and analyze the feedback data to improve the model.

[0108] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0109] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0110] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0111] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0112] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0113] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0114] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, 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. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0115] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0116] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0117] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0118] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0119] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0120] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0121] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0122] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0123] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0125] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0126] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0127] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0128] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0129] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. 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. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0130] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0132] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0133] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0134] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0135] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0136] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0137] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0138] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0140] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0141] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0142] 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.

[0143] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0144] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. 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. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0145] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0146] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0147] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0148] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0149] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0150] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0151] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0152] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0153] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0154] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0155] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0156] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0157] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0158] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0159] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0160] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0161] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0162] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0163] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0164] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0165] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0166] 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.

[0167] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0168] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0169] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific process may be a single processor.

[0170] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0171] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0172] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0173] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0174] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0175] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a data collection unit that collects data; a preprocessing unit that preprocesses the data collected by the data collection unit; a generation AI training unit that trains the generation AI using the data preprocessed by the preprocessing unit; a monitoring unit that monitors the network using the generation AI trained by the generation AI training unit; a feedback loop unit that performs feedback based on the network operation data monitored by the monitoring unit; a self-optimization unit that performs self-optimization based on the feedback obtained by the feedback loop unit; a model improvement unit that improves the model based on the data obtained by the self-optimization unit. A system characterized by:

2. The data collection unit Collecting traffic data or error logs from the network, filtering out noise, and extracting necessary information 2. The system of claim 1.

3. The generation AI training unit: Learn the traffic patterns and error patterns of the network 2. The system of claim 1.

4. The monitoring unit Detects sudden increases in traffic or error logs, analyzes the information, and proposes appropriate measures 2. The system of claim 1.

5. The self-optimization unit Distributing traffic or optimizing resource allocation 2. The system of claim 1.

Images