System

Abstract

An object of a system according to an embodiment is to enhance system fault training by utilizing AI and to improve the skill of an operator.SOLUTION: A system according to an embodiment includes a learning unit, a scenario generation unit, a role setting unit, a progress evaluation unit, and a character generation unit. The learning unit learns settings of a network and a server of the production-environment service. The scenario generation unit generates a failure scenario based on the information learned by the learning unit. The role setting unit sets the assigned role and the action pattern at the time of training based on the scenario generated by the scenario generation unit. The progress evaluation unit performs progress and evaluation of the training based on the role and the behavior pattern set by the role setting unit. The character creation unit creates a AI character on the basis of the information evaluated by the progress evaluation 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 technology lacks effective methods for improving the quality of system failure training, which limits the improvement of operator skills.

[0005] The system of the embodiment aims to utilize AI to improve the quality of system failure training and improve the skills of operators. [Means for solving the problem]

[0006] The system according to the embodiment includes a learning unit, a scenario generation unit, a role setting unit, a progress evaluation unit, and a character generation unit. The learning unit learns the network and server settings of the production environment service. The scenario generation unit generates a failure scenario based on the information learned by the learning unit. The role setting unit sets the role and behavior pattern to be assigned during training based on the scenario generated by the scenario generation unit. The progress evaluation unit progresses and evaluates the training based on the role and behavior pattern set by the role setting unit. The character generation unit creates an AI character based on the information evaluated by the progress evaluation unit. [Effects of the Invention]

[0007] The system according to the embodiment can utilize AI to improve the quality of system failure training and enhance the skills of operators. [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) A system according to an embodiment of the present invention uses AI to support system failure training and provide operators with high-quality training opportunities. This system trains the AI ​​to learn the network and server settings of production service environments and predict system behavior in the event of a failure. Furthermore, the AI ​​generates failure scenarios, sets roles and behavioral patterns for training, progresses and evaluates the training, and creates AI characters. This allows the system to provide operators with high-quality system failure training and improve their ability to respond to actual failures.

[0029] The system according to the embodiment includes a learning unit, a scenario generation unit, a role setting unit, a progress evaluation unit, and a character generation unit. The learning unit learns the network and server settings of the production environment service. For example, the learning unit inputs network topology, server configuration files, log data, etc. into the AI ​​to understand the normal operating state of the system and predict behavior in the event of a failure. The scenario generation unit generates a failure scenario based on the information learned by the learning unit. For example, the scenario generation unit creates a scenario for when a specific server goes down or the network is disconnected. The role setting unit sets roles and behavior patterns during training based on the scenario generated by the scenario generation unit. For example, the role setting unit has the control AI take the lead in giving instructions to each team, and each team communicates by responding to the AI. The progress evaluation unit progresses and evaluates the training based on the roles and behavior patterns set by the role setting unit. For example, after the training is completed, the progress evaluation unit has the AI ​​critique the training content and provide feedback on areas for improvement and success. The character generation unit creates an AI character based on the information evaluated by the progress evaluation unit. For example, the character generation unit can create AI characters for each task and train them without human intervention, allowing the system to provide operators with high-quality system failure training and improve their ability to respond to actual failures.

[0030] The learning unit can predict signs of anomalies by learning the system's anomaly detection algorithm and analyzing log data and performance metrics. For example, the learning unit trains AI to learn the system's anomaly detection algorithm and analyzes log data and performance metrics to predict signs of anomalies. For example, it detects sudden increases in CPU usage and abnormal increases in network traffic. The learning unit also trains AI to learn anomaly detection algorithms, models the system's normal operating patterns, and detects abnormal behavior in real time. For example, it detects memory leaks and disk I / O anomalies early. The learning unit also trains AI to learn anomaly detection algorithms, identifies signs of anomalies based on past failure data, and builds predictive models. For example, it can predict system anomalies before specific error logs occur frequently. This allows for predicting signs of anomalies and responding early.

[0031] The learning unit can learn system performance data and predict the extent of impact when a failure occurs. For example, the learning unit has AI learn system performance data and predict the extent of impact when a failure occurs. For example, it predicts the services and number of users that will be affected if a specific server goes down. The learning unit also has AI learn performance data, identify system bottlenecks, and predict the extent of impact when a failure occurs. For example, it analyzes the impact of network delays and database overload on other systems. The learning unit also has AI learn past performance data and simulate the extent of impact when a failure occurs. For example, it predicts the impact on the entire system when a specific component fails. This makes it possible to predict the extent of impact when a failure occurs and take appropriate measures.

[0032] The learning unit can learn the configuration information of other systems and predict collaboration failures between multiple systems. For example, the learning unit has the AI ​​learn the configuration information of cloud services and IoT devices to predict collaboration failures between multiple systems. For example, it analyzes the impact of API changes in cloud services on other systems. The learning unit also has the AI ​​learn the configuration information of different systems and simulate collaboration failure scenarios. For example, it predicts the impact of firmware updates on IoT devices on the network. The learning unit also has the AI ​​learn the configuration information of multiple systems to detect precursors to collaboration failures. For example, it can detect the impact of resource shortages in cloud services on other systems at an early stage. This makes it possible to predict collaboration failures between multiple systems and take appropriate measures.

[0033] The learning unit can learn the system's security settings and generate response scenarios for security incidents. For example, the learning unit has AI learn the system's security settings and generate response scenarios for security incidents. For example, it automatically generates response procedures when a specific vulnerability is discovered. The learning unit also has AI learn security settings, predict the scope of impact when an incident occurs, and propose response scenarios. For example, it analyzes the scope of impact and response procedures in the event of a data leak. The learning unit also has AI learn past security incident data and generate response scenarios for when a similar incident occurs. For example, it automatically generates response procedures in the event of a DDoS attack. This allows response scenarios to be generated for security incidents, enabling quick and appropriate responses.

[0034] The scenario generation unit can learn from past failure data and automatically generate similar failure scenarios. For example, the scenario generation unit has AI learn from past failure data and automatically generate similar failure scenarios. For example, a scenario in which a specific server goes down is generated based on past data. The scenario generation unit also has AI learn from failure data, analyze failure occurrence patterns, and generate similar scenarios. For example, it generates a scenario that predicts the scope of impact in the event of a network failure. The scenario generation unit also has AI learn from past failure data, analyze the cause and impact of the failure, and generate similar scenarios. For example, it generates a response scenario in the event of a database overload. This makes it possible to generate similar failure scenarios based on past failure data, improving the accuracy of training.

[0035] The scenario generation unit can learn system dependencies and generate scenarios in which multiple failures occur in a chain reaction. For example, the scenario generation unit has AI learn system dependencies and generate scenarios in which multiple failures occur in a chain reaction. For example, it generates a scenario that analyzes the impact of a network failure on a database. The scenario generation unit also has AI learn dependencies and simulate failure scenarios for the entire system. For example, it generates a scenario that predicts the chain reaction impact when a specific component fails. The scenario generation unit also has AI learn system dependencies and generate scenarios in which multiple failures occur simultaneously. For example, it generates a response scenario when a server failure and a network failure occur simultaneously. In this way, by learning system dependencies and generating chain reaction failure scenarios, more realistic training can be provided.

[0036] The scenario generation unit can learn failure scenarios from different industries and generate failure response scenarios across different industries. For example, the scenario generation unit has AI learn failure scenarios from different industries and generate failure response scenarios across different industries. For example, it generates a scenario that combines failure scenarios from the financial industry and the manufacturing industry. The scenario generation unit also has AI learn failure data from different industries, analyzes common failure patterns, and generates response scenarios across different industries. For example, it generates a scenario that combines failure response procedures from the IT industry and the medical industry. The scenario generation unit also has AI learn failure scenarios from different industries and generates scenarios that incorporate best practices across industries. For example, it generates a scenario that combines failure response procedures from the energy industry and the telecommunications industry. In this way, by learning failure scenarios from different industries and generating failure response scenarios across different industries, a wide range of training scenarios can be provided.

[0037] The scenario generation unit can generate failure scenarios that take into account external factors such as natural disasters or cyberattacks. For example, the scenario generation unit has the AI ​​learn about external factors such as natural disasters and cyberattacks, and generates failure scenarios that take these factors into account. For example, it generates a system failure scenario when an earthquake occurs. The scenario generation unit also has the AI ​​learn about external factors, and generates a scenario in which multiple factors occur simultaneously. For example, it generates a response scenario when a cyberattack and a natural disaster occur simultaneously. The scenario generation unit also has the AI ​​learn data on past natural disasters and cyberattacks, and generates failure scenarios that take these factors into account. For example, it generates a system failure scenario when a flood occurs. This makes it possible to generate failure scenarios that take into account external factors such as natural disasters and cyberattacks, and provide realistic training.

[0038] The role setting unit can learn the past behavioral data of each person in charge and propose optimal behavioral patterns. The role setting unit, for example, has AI learn the past behavioral data of each person in charge and propose optimal behavioral patterns. For example, it generates an optimal instruction pattern for the controller based on past training data. The role setting unit also has AI learn the behavioral data of each person in charge and propose efficient behavioral patterns. For example, it generates a behavioral pattern to optimize the work procedures of the recovery team. The role setting unit also has AI learn the past behavioral data and propose optimal behavioral patterns according to each person in charge's role. For example, it generates a behavioral pattern to optimize the monitoring procedures of the monitoring team. This makes it possible to propose optimal behavioral patterns based on the past behavioral data of each person in charge and improve the effectiveness of training.

[0039] The role setting unit can learn the skill level of each person in charge and assign roles according to their skills. The role setting unit, for example, has AI learn the skill level of each person in charge and assign roles according to their skills. For example, it assigns highly skilled operators to the control role. The role setting unit also has AI learn the skill levels and proposes the optimal role assignment according to the skills of each person in charge. For example, it assigns highly skilled members to the recovery team. The role setting unit also has AI learn the skill data of each person in charge and assigns roles according to their skills, maximizing the effectiveness of training. For example, it assigns highly skilled members to the monitoring team. This makes it possible to assign roles according to the skill level of each person in charge and maximizing the effectiveness of training.

[0040] The role setting unit can learn the division of roles in different industries and propose role divisions between different industries. For example, the role setting unit has the AI ​​learn the division of roles in different industries and propose role divisions between different industries. For example, it makes a proposal that combines the division of roles between the manufacturing and IT industries. The role setting unit also has the AI ​​learn role division data from different industries, analyzes common role division patterns, and proposes role divisions between different industries. For example, it makes a proposal that combines the division of roles between the financial industry and the medical industry. The role setting unit also has the AI ​​learn the division of roles in different industries and proposes role divisions that incorporate best practices between industries. For example, it makes a proposal that combines the division of roles between the energy industry and the telecommunications industry. This makes it possible to provide a wide range of training scenarios by learning the division of roles in different industries and proposing role divisions between different industries.

[0041] The role setting unit can learn shift schedules and propose optimal training schedules. For example, the role setting unit has AI learn shift schedules and propose optimal training schedules. For example, it generates a training schedule that takes into account the working hours and break times of operators. The role setting unit also has AI learn shift data and propose optimal training times according to the schedule of each person in charge. For example, it generates a training schedule suitable for night shift workers. The role setting unit also has AI learn shift schedules and propose optimal training schedules according to the working patterns of operators. For example, it generates a training schedule suitable for weekend workers. In this way, the effectiveness of training can be maximized by learning shift schedules and proposing optimal training schedules.

[0042] The progress evaluation unit can learn real-time data during training and evaluate the progress of training in real time. For example, the progress evaluation unit has AI learn real-time data during training and evaluate the progress of training in real time. For example, it analyzes the progress and response speed of each team. The progress evaluation unit also has AI learn real-time data, evaluate the progress of training, and propose necessary adjustments. For example, it proposes additional resources for teams that are lagging behind. The progress evaluation unit also has AI learn data during training and evaluates in real time to maximize the effectiveness of training. For example, it monitors the performance of each team in real time. This makes it possible to evaluate progress based on real-time data during training and maximize the effectiveness of training.

[0043] The progress evaluation unit can learn past training data and evaluate the effectiveness of training over the long term. For example, the progress evaluation unit has AI learn past training data and evaluate the effectiveness of training over the long term. For example, it compares the effectiveness of current training based on past training results. The progress evaluation unit also has AI learn training data and evaluate long-term performance improvement. For example, it analyzes the improvement of operators' skills based on past training data. The progress evaluation unit also has AI learn past training data and evaluates the effectiveness of training over the long term and suggests areas for improvement. For example, it suggests areas for improvement in the training program based on past data. This makes it possible to evaluate the effectiveness of training over the long term based on past training data and suggest areas for improvement.

[0044] The progress evaluation unit can learn training evaluation criteria from different industries and perform cross-industry training evaluation. For example, the progress evaluation unit has the AI ​​learn training evaluation criteria from different industries and perform cross-industry training evaluation. For example, an evaluation that combines training evaluation criteria from the manufacturing and IT industries is performed. The progress evaluation unit also has the AI ​​learn training data from different industries, analyzes common evaluation criteria, and performs cross-industry training evaluation. For example, an evaluation that combines training evaluation criteria from the financial industry and the medical industry is performed. The progress evaluation unit also has the AI ​​learn training evaluation criteria from different industries and performs training evaluation that incorporates cross-industry best practices. For example, an evaluation that combines training evaluation criteria from the energy industry and the communications industry is performed. This makes it possible to provide a wide range of training evaluations by learning training evaluation criteria from different industries and performing cross-industry training evaluation.

[0045] The progress evaluation unit can learn from the video data of training and perform visual evaluations. For example, the progress evaluation unit has AI learn from the video data of training and perform visual evaluations. For example, it evaluates the actions and response speed of each team through video analysis. The progress evaluation unit also has AI learn from the video data, visually evaluates the progress of training, and suggests necessary adjustments. For example, it suggests additional resources for teams that are lagging behind. The progress evaluation unit also has AI learn from the video data of training and perform visual evaluations to maximize the effectiveness of training. For example, it monitors the performance of each team through video analysis. This makes it possible to perform visual evaluations based on the video data of training and maximize the effectiveness of training.

[0046] The character generation unit can learn the specialized knowledge of each person in charge and provide specialized advice. For example, the character generation unit has an AI character learn the specialized knowledge of each person in charge and provide specialized advice. For example, a control AI character explains the system recovery procedures in detail. The character generation unit also has an AI character learn specialized knowledge and provide advice according to each person's role. For example, a monitoring team AI character explains monitoring points. The character generation unit also has an AI character learn the specialized knowledge of each person in charge and provide advice in real time during training. For example, a recovery team AI character instructs the troubleshooting procedures. This allows for specialized advice to be provided based on the specialized knowledge of each person in charge, improving the effectiveness of training.

[0047] The character generation unit can learn past training data and perform realistic training simulations. The character generation unit, for example, has an AI character learn past training data and perform realistic training simulations. For example, it performs a simulation based on past failure scenarios. The character generation unit also has the AI ​​character learn the training data and perform a simulation similar to actual training. For example, it performs a simulation that reproduces the roles of each person in charge. The character generation unit also has the AI ​​character learn past training data and perform training simulations in real time. For example, it performs a real-time failure response simulation based on past data. This makes it possible to perform realistic training simulations based on past training data and improve the effectiveness of training.

[0048] The character generation unit can learn knowledge from different industries and perform cross-industry training simulations. For example, the character generation unit has an AI character learn knowledge from different industries and perform cross-industry training simulations. For example, a simulation is performed that combines knowledge from the manufacturing and IT industries. The character generation unit also has an AI character learn knowledge from different industries, analyzes a common training scenario, and performs cross-industry training simulations. For example, a simulation is performed that combines knowledge from the financial industry and the medical industry. The character generation unit also has an AI character learn knowledge from different industries and performs a training simulation that incorporates best practices from different industries. For example, a simulation is performed that combines knowledge from the energy industry and the communications industry. This makes it possible to perform cross-industry training simulations based on knowledge from different industries, thereby improving the effectiveness of training.

[0049] The character generation unit can learn different languages ​​and provide international viewing and learning. For example, the character generation unit has an AI character learn different languages ​​and provide international viewing and learning. For example, a training simulation is performed in multiple languages, such as English, French, and Chinese. The character generation unit also has the AI ​​character learn multilingual knowledge and provide training scenarios in different languages. For example, a multilingual training simulation is performed in which operators from various countries can participate. The character generation unit also has the AI ​​character learn different languages ​​and provide international viewing and learning, maximizing the effectiveness of cross-cultural training. For example, feedback is provided in different languages. This makes it possible to provide international viewing and learning based on different languages ​​and improve the learning effectiveness.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The system can further include a voice recognition unit. The voice recognition unit analyzes the operator's voice commands and allows the system to be operated by voice. For example, when the operator issues a command to check the status of a specific server by voice, the voice recognition unit analyzes the command and displays the status of the corresponding server. The voice recognition unit can also control the progress of a failure scenario based on the operator's voice instructions. For example, when the operator issues a voice command such as "Proceed to the next scenario," the system moves on to the next failure scenario. Furthermore, the voice recognition unit can analyze the operator's voice feedback in real time and evaluate the progress of the training. For example, when the operator reports problems he or she has noticed during training by voice, the content of the report is analyzed and provided as feedback for improvements to the training.

[0052] The system can further include a virtual reality (VR) unit. The VR unit can provide operators with training in a virtual environment. For example, operators wear VR headsets and conduct troubleshooting training in a virtual data center. The VR unit can also track the operators' actions and provide feedback in real time. For example, when an operator performs an appropriate operation in the virtual environment, feedback is displayed immediately. Furthermore, the VR unit can enable multiple operators to train simultaneously in the virtual environment, enabling team cooperation training. For example, it can provide a scenario in which multiple operators work together in the virtual environment to handle a troubleshooting situation.

[0053] The system can further include a gamification unit. The gamification unit can incorporate game elements into training to increase the motivation of operators. For example, points can be awarded according to the progress of training and a ranking can be displayed. The gamification unit can also award badges and titles according to the goals that operators achieve. For example, a "quick response badge" can be awarded to an operator who quickly resolves a specific failure scenario. Furthermore, the gamification unit can promote competition between operators to increase the effectiveness of training. For example, it can provide team-based training scenarios and have teams compete to see which team can most effectively respond to failures.

[0054] The system can further include a natural language processing (NLP) unit. The NLP unit can analyze the operator's text input and operate the system via text. For example, if the operator enters a text command to check the status of a specific server, the NLP unit can analyze the command and display the status of the corresponding server. The NLP unit can also analyze the operator's text feedback in real time to evaluate the progress of the training. For example, if the operator reports in text any problems they encountered during training, the NLP unit can analyze the content and provide feedback as areas for improvement in the training. Furthermore, the NLP unit can control the progress of the failure scenario based on the operator's text input. For example, if the operator gives the text command "Proceed to the next scenario," the system will proceed to the next failure scenario.

[0055] The system can further include a data visualization unit. The data visualization unit can visually display the progress and evaluation results of training. For example, the progress of training can be displayed in graphs and charts, allowing operators to intuitively understand. The data visualization unit can also visually display the evaluation results of training, allowing operators to grasp their own performance. For example, the progress and response speed of each team can be displayed in a heat map. Furthermore, the data visualization unit can visually present areas for improvement in training, allowing operators to understand specific improvement measures. For example, the areas for improvement based on the evaluation results of training can be displayed in a flowchart.

[0056] The system can further be equipped with an anomaly detection unit. The anomaly detection unit can detect system anomalies in real time and issue alerts to operators. For example, it can detect sudden increases in CPU usage or abnormal increases in network traffic. The anomaly detection unit can also learn from past anomaly data and predict signs of anomalies. For example, it can predict system anomalies before specific error logs occur frequently. Furthermore, the anomaly detection unit can automatically generate response procedures in the event of an anomaly and provide them to operators. For example, it can automatically generate response procedures in the event of a specific server going down and instruct the operators on how to proceed.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The learning unit learns the network and server settings of the production environment service. For example, the learning unit inputs network topology, server configuration files, log data, etc. into the AI ​​to understand the normal operating state of the system and predict behavior in the event of a failure. Step 2: The scenario generation unit generates a failure scenario based on the information learned by the learning unit. For example, the scenario generation unit creates a scenario for when a specific server goes down or the network is disconnected. Step 3: The role setting unit sets the roles and behavior patterns for training based on the scenario generated by the scenario generation unit. For example, the role setting unit has the control AI take the lead in giving instructions to each team, and each team responds to the AI. Step 4: The progress evaluation unit progresses and evaluates the training based on the roles and behavioral patterns set by the role setting unit. For example, after the training is completed, the progress evaluation unit uses AI to critique the training content and provide feedback on areas for improvement and success. Step 5: The character generation unit creates AI characters based on the information evaluated by the progress evaluation unit. For example, the character generation unit can create AI characters for each role and train them without human intervention.

[0059] (Example 2) A system according to an embodiment of the present invention uses AI to support system failure training and provide operators with high-quality training opportunities. This system trains the AI ​​to learn the network and server settings of production service environments and predict system behavior in the event of a failure. Furthermore, the AI ​​generates failure scenarios, sets roles and behavioral patterns for training, progresses and evaluates the training, and creates AI characters. This allows the system to provide operators with high-quality system failure training and improve their ability to respond to actual failures.

[0060] The system according to the embodiment includes a learning unit, a scenario generation unit, a role setting unit, a progress evaluation unit, and a character generation unit. The learning unit learns the network and server settings of the production environment service. For example, the learning unit inputs network topology, server configuration files, log data, etc. into the AI ​​to understand the normal operating state of the system and predict behavior in the event of a failure. The scenario generation unit generates a failure scenario based on the information learned by the learning unit. For example, the scenario generation unit creates a scenario for when a specific server goes down or the network is disconnected. The role setting unit sets roles and behavior patterns during training based on the scenario generated by the scenario generation unit. For example, the role setting unit has the control AI take the lead in giving instructions to each team, and each team communicates by responding to the AI. The progress evaluation unit progresses and evaluates the training based on the roles and behavior patterns set by the role setting unit. For example, after the training is completed, the progress evaluation unit has the AI ​​critique the training content and provide feedback on areas for improvement and success. The character generation unit creates an AI character based on the information evaluated by the progress evaluation unit. For example, the character generation unit can create AI characters for each task and train them without human intervention, allowing the system to provide operators with high-quality system failure training and improve their ability to respond to actual failures.

[0061] The learning unit can predict signs of anomalies by learning the system's anomaly detection algorithm and analyzing log data and performance metrics. For example, the learning unit trains AI to learn the system's anomaly detection algorithm and analyzes log data and performance metrics to predict signs of anomalies. For example, it detects sudden increases in CPU usage and abnormal increases in network traffic. The learning unit also trains AI to learn anomaly detection algorithms, models the system's normal operating patterns, and detects abnormal behavior in real time. For example, it detects memory leaks and disk I / O anomalies early. The learning unit also trains AI to learn anomaly detection algorithms, identifies signs of anomalies based on past failure data, and builds predictive models. For example, it can predict system anomalies before specific error logs occur frequently. This allows for predicting signs of anomalies and responding early.

[0062] The learning unit can learn system performance data and predict the extent of impact when a failure occurs. For example, the learning unit has AI learn system performance data and predict the extent of impact when a failure occurs. For example, it predicts the services and number of users that will be affected if a specific server goes down. The learning unit also has AI learn performance data, identify system bottlenecks, and predict the extent of impact when a failure occurs. For example, it analyzes the impact of network delays and database overload on other systems. The learning unit also has AI learn past performance data and simulate the extent of impact when a failure occurs. For example, it predicts the impact on the entire system when a specific component fails. This makes it possible to predict the extent of impact when a failure occurs and take appropriate measures.

[0063] The learning unit can use the emotion estimation function to monitor the stress level of the operator in real time and issue an appropriate alert before stress increases. The learning unit, for example, uses the emotion estimation function to monitor the stress level of the operator in real time and issue an appropriate alert before stress increases. For example, it analyzes the operator's facial expressions and voice to calculate a stress score. The learning unit also uses the emotion estimation function to monitor the operator's stress level and suggest relaxation methods before stress increases. For example, it issues an alert recommending deep breathing or a short break. The learning unit also uses the emotion estimation function to analyze the operator's stress level in real time and notify the team leader before stress increases. For example, it sends an alert if the stress score exceeds a certain value. In this way, the operator's health can be protected by monitoring the operator's stress level in real time and issuing appropriate alerts.

[0064] The learning unit can learn the configuration information of other systems and predict collaboration failures between multiple systems. For example, the learning unit has the AI ​​learn the configuration information of cloud services and IoT devices to predict collaboration failures between multiple systems. For example, it analyzes the impact of API changes in cloud services on other systems. The learning unit also has the AI ​​learn the configuration information of different systems and simulate collaboration failure scenarios. For example, it predicts the impact of firmware updates on IoT devices on the network. The learning unit also has the AI ​​learn the configuration information of multiple systems to detect precursors to collaboration failures. For example, it can detect the impact of resource shortages in cloud services on other systems at an early stage. This makes it possible to predict collaboration failures between multiple systems and take appropriate measures.

[0065] The learning unit can learn the system's security settings and generate response scenarios for security incidents. For example, the learning unit has AI learn the system's security settings and generate response scenarios for security incidents. For example, it automatically generates response procedures when a specific vulnerability is discovered. The learning unit also has AI learn security settings, predict the scope of impact when an incident occurs, and propose response scenarios. For example, it analyzes the scope of impact and response procedures in the event of a data leak. The learning unit also has AI learn past security incident data and generate response scenarios for when a similar incident occurs. For example, it automatically generates response procedures in the event of a DDoS attack. This allows response scenarios to be generated for security incidents, enabling quick and appropriate responses.

[0066] The learning unit can use the emotion estimation function to provide customized learning content according to the emotional state of the user. The learning unit, for example, uses the emotion estimation function to provide customized learning content according to the emotional state of the user. For example, if the user is feeling stressed, it provides content that teaches relaxation methods. The learning unit also uses the emotion estimation function to suggest a training program according to the user's emotional state. For example, if the user is feeling tired, it provides effective training in a short amount of time. The learning unit also uses the emotion estimation function to provide feedback according to the user's emotional state. For example, if the user is feeling strongly positive, it provides feedback that includes words of praise. This makes it possible to provide learning content according to the user's emotional state and maximize the learning effect.

[0067] The scenario generation unit can learn from past failure data and automatically generate similar failure scenarios. For example, the scenario generation unit has AI learn from past failure data and automatically generate similar failure scenarios. For example, a scenario in which a specific server goes down is generated based on past data. The scenario generation unit also has AI learn from failure data, analyze failure occurrence patterns, and generate similar scenarios. For example, it generates a scenario that predicts the scope of impact in the event of a network failure. The scenario generation unit also has AI learn from past failure data, analyze the cause and impact of the failure, and generate similar scenarios. For example, it generates a response scenario in the event of a database overload. This makes it possible to generate similar failure scenarios based on past failure data, improving the accuracy of training.

[0068] The scenario generation unit can learn system dependencies and generate scenarios in which multiple failures occur in a chain reaction. For example, the scenario generation unit has AI learn system dependencies and generate scenarios in which multiple failures occur in a chain reaction. For example, it generates a scenario that analyzes the impact of a network failure on a database. The scenario generation unit also has AI learn dependencies and simulate failure scenarios for the entire system. For example, it generates a scenario that predicts the chain reaction impact when a specific component fails. The scenario generation unit also has AI learn system dependencies and generate scenarios in which multiple failures occur simultaneously. For example, it generates a response scenario when a server failure and a network failure occur simultaneously. In this way, by learning system dependencies and generating chain reaction failure scenarios, more realistic training can be provided.

[0069] The scenario generation unit can use the emotion estimation function to generate a failure scenario as a stress test based on the emotional reactions of the operator. The scenario generation unit, for example, uses the emotion estimation function to generate a failure scenario as a stress test based on the emotional reactions of the operator. For example, it generates a scenario that simulates a situation in which the operator feels stressed. The scenario generation unit also uses the emotion estimation function to analyze the emotional data of the operator and generate a failure scenario that reproduces a situation in which stress increases. For example, it generates a scenario in which multiple failures occur simultaneously. The scenario generation unit also uses the emotion estimation function to generate a scenario as a stress test based on the emotional reactions of the operator and evaluate the operator's response ability. For example, it generates a scenario that requires an emergency response. In this way, it is possible to generate a failure scenario as a stress test based on the operator's emotional reactions and evaluate the operator's response ability.

[0070] The scenario generation unit can learn failure scenarios from different industries and generate failure response scenarios across different industries. For example, the scenario generation unit has AI learn failure scenarios from different industries and generate failure response scenarios across different industries. For example, it generates a scenario that combines failure scenarios from the financial industry and the manufacturing industry. The scenario generation unit also has AI learn failure data from different industries, analyzes common failure patterns, and generates response scenarios across different industries. For example, it generates a scenario that combines failure response procedures from the IT industry and the medical industry. The scenario generation unit also has AI learn failure scenarios from different industries and generates scenarios that incorporate best practices across industries. For example, it generates a scenario that combines failure response procedures from the energy industry and the telecommunications industry. In this way, by learning failure scenarios from different industries and generating failure response scenarios across different industries, a wide range of training scenarios can be provided.

[0071] The scenario generation unit can generate failure scenarios that take into account external factors such as natural disasters or cyberattacks. For example, the scenario generation unit has the AI ​​learn about external factors such as natural disasters and cyberattacks, and generates failure scenarios that take these factors into account. For example, it generates a system failure scenario when an earthquake occurs. The scenario generation unit also has the AI ​​learn about external factors, and generates a scenario in which multiple factors occur simultaneously. For example, it generates a response scenario when a cyberattack and a natural disaster occur simultaneously. The scenario generation unit also has the AI ​​learn data on past natural disasters and cyberattacks, and generates failure scenarios that take these factors into account. For example, it generates a system failure scenario when a flood occurs. This makes it possible to generate failure scenarios that take into account external factors such as natural disasters and cyberattacks, and provide realistic training.

[0072] The scenario generation unit can use the emotion estimation function to generate fault scenarios with different levels of difficulty depending on the emotional state of the operator. The scenario generation unit, for example, uses the emotion estimation function to generate fault scenarios with different levels of difficulty depending on the emotional state of the operator. For example, when the operator is relaxed, it generates a highly difficult scenario. The scenario generation unit also uses the emotion estimation function to analyze the emotional data of the operator and generate a highly difficult scenario that reproduces a situation where stress increases. For example, it generates a scenario in which multiple faults occur simultaneously. The scenario generation unit also uses the emotion estimation function to generate scenarios with different levels of difficulty depending on the emotional state of the operator and evaluate the operator's response ability. For example, it generates a scenario that requires an emergency response. In this way, fault scenarios with different levels of difficulty depending on the emotional state of the operator can be generated, maximizing the effectiveness of training.

[0073] The role setting unit can learn the past behavioral data of each person in charge and propose optimal behavioral patterns. The role setting unit, for example, has AI learn the past behavioral data of each person in charge and propose optimal behavioral patterns. For example, it generates an optimal instruction pattern for the controller based on past training data. The role setting unit also has AI learn the behavioral data of each person in charge and propose efficient behavioral patterns. For example, it generates a behavioral pattern to optimize the work procedures of the recovery team. The role setting unit also has AI learn the past behavioral data and propose optimal behavioral patterns according to each person in charge's role. For example, it generates a behavioral pattern to optimize the monitoring procedures of the monitoring team. This makes it possible to propose optimal behavioral patterns based on the past behavioral data of each person in charge and improve the effectiveness of training.

[0074] The role setting unit can learn the skill level of each person in charge and assign roles according to their skills. The role setting unit, for example, has AI learn the skill level of each person in charge and assign roles according to their skills. For example, it assigns highly skilled operators to the control role. The role setting unit also has AI learn the skill levels and proposes the optimal role assignment according to the skills of each person in charge. For example, it assigns highly skilled members to the recovery team. The role setting unit also has AI learn the skill data of each person in charge and assigns roles according to their skills, maximizing the effectiveness of training. For example, it assigns highly skilled members to the monitoring team. This makes it possible to assign roles according to the skill level of each person in charge and maximizing the effectiveness of training.

[0075] The role setting unit uses the emotion estimation function to assign roles according to the emotional state of the operators, thereby reducing stress. The role setting unit, for example, uses the emotion estimation function to assign roles according to the emotional state of the operators, thereby reducing stress. For example, an operator with high stress is assigned a less burdensome role. The role setting unit also uses the emotion estimation function to analyze the emotion data of the operators and assign important roles to operators with low stress. For example, a relaxed operator is assigned to a control role. The role setting unit also uses the emotion estimation function to assign roles according to the emotional state of the operators, thereby maximizing the effectiveness of training. For example, an operator with low stress is assigned to a recovery team. In this way, roles according to the emotional state of the operators can be assigned and stress can be reduced.

[0076] The role setting unit can learn the division of roles in different industries and propose role divisions between different industries. For example, the role setting unit has the AI ​​learn the division of roles in different industries and propose role divisions between different industries. For example, it makes a proposal that combines the division of roles between the manufacturing and IT industries. The role setting unit also has the AI ​​learn role division data from different industries, analyzes common role division patterns, and proposes role divisions between different industries. For example, it makes a proposal that combines the division of roles between the financial industry and the medical industry. The role setting unit also has the AI ​​learn the division of roles in different industries and proposes role divisions that incorporate best practices between industries. For example, it makes a proposal that combines the division of roles between the energy industry and the telecommunications industry. This makes it possible to provide a wide range of training scenarios by learning the division of roles in different industries and proposing role divisions between different industries.

[0077] The role setting unit can learn shift schedules and propose optimal training schedules. For example, the role setting unit has AI learn shift schedules and propose optimal training schedules. For example, it generates a training schedule that takes into account the working hours and break times of operators. The role setting unit also has AI learn shift data and propose optimal training times according to the schedule of each person in charge. For example, it generates a training schedule suitable for night shift workers. The role setting unit also has AI learn shift schedules and propose optimal training schedules according to the working patterns of operators. For example, it generates a training schedule suitable for weekend workers. In this way, the effectiveness of training can be maximized by learning shift schedules and proposing optimal training schedules.

[0078] The role setting unit can use the emotion estimation function to suggest behavioral patterns according to the emotional state of the operator, thereby maximizing the effectiveness of the training. The role setting unit, for example, uses the emotion estimation function to suggest behavioral patterns according to the emotional state of the operator, thereby maximizing the effectiveness of the training. For example, a highly difficult task is assigned to an operator with low stress. The role setting unit also uses the emotion estimation function to analyze the emotion data of the operator and suggest relaxation methods to an operator with high stress. For example, short breaks or methods of refreshing are suggested. The role setting unit also uses the emotion estimation function to suggest behavioral patterns according to the emotional state of the operator, thereby maximizing the effectiveness of the training. For example, an operator with strong positive emotions is allowed to demonstrate leadership. In this way, behavioral patterns according to the emotional state of the operator can be suggested, thereby maximizing the effectiveness of the training.

[0079] The progress evaluation unit can learn real-time data during training and evaluate the progress of training in real time. For example, the progress evaluation unit has AI learn real-time data during training and evaluate the progress of training in real time. For example, it analyzes the progress and response speed of each team. The progress evaluation unit also has AI learn real-time data, evaluate the progress of training, and propose necessary adjustments. For example, it proposes additional resources for teams that are lagging behind. The progress evaluation unit also has AI learn data during training and evaluates in real time to maximize the effectiveness of training. For example, it monitors the performance of each team in real time. This makes it possible to evaluate progress based on real-time data during training and maximize the effectiveness of training.

[0080] The progress evaluation unit can learn past training data and evaluate the effectiveness of training over the long term. For example, the progress evaluation unit has AI learn past training data and evaluate the effectiveness of training over the long term. For example, it compares the effectiveness of current training based on past training results. The progress evaluation unit also has AI learn training data and evaluate long-term performance improvement. For example, it analyzes the improvement of operators' skills based on past training data. The progress evaluation unit also has AI learn past training data and evaluates the effectiveness of training over the long term and suggests areas for improvement. For example, it suggests areas for improvement in the training program based on past data. This makes it possible to evaluate the effectiveness of training over the long term based on past training data and suggest areas for improvement.

[0081] The progress evaluation unit uses the emotion estimation function to evaluate the training based on the emotional reactions of the operator, thereby promoting emotional growth. The progress evaluation unit, for example, uses the emotion estimation function to evaluate the training based on the emotional reactions of the operator, thereby promoting emotional growth. For example, it provides feedback including words of praise to an operator with strong positive emotions. The progress evaluation unit also uses the emotion estimation function to analyze the emotion data of the operator and propose a training program to promote emotional growth. For example, it allows an operator with low stress to demonstrate leadership. The progress evaluation unit also uses the emotion estimation function to evaluate the training based on the emotional reactions of the operator, thereby promoting emotional growth. For example, it allows an operator with strong positive emotions to demonstrate leadership. In this way, it is possible to evaluate the training based on the emotional reactions of the operator, thereby promoting emotional growth.

[0082] The progress evaluation unit can learn training evaluation criteria from different industries and perform cross-industry training evaluation. For example, the progress evaluation unit has the AI ​​learn training evaluation criteria from different industries and perform cross-industry training evaluation. For example, an evaluation that combines training evaluation criteria from the manufacturing and IT industries is performed. The progress evaluation unit also has the AI ​​learn training data from different industries, analyzes common evaluation criteria, and performs cross-industry training evaluation. For example, an evaluation that combines training evaluation criteria from the financial industry and the medical industry is performed. The progress evaluation unit also has the AI ​​learn training evaluation criteria from different industries and performs training evaluation that incorporates cross-industry best practices. For example, an evaluation that combines training evaluation criteria from the energy industry and the communications industry is performed. This makes it possible to provide a wide range of training evaluations by learning training evaluation criteria from different industries and performing cross-industry training evaluation.

[0083] The progress evaluation unit can learn from the video data of training and perform visual evaluations. For example, the progress evaluation unit has AI learn from the video data of training and perform visual evaluations. For example, it evaluates the actions and response speed of each team through video analysis. The progress evaluation unit also has AI learn from the video data, visually evaluates the progress of training, and suggests necessary adjustments. For example, it suggests additional resources for teams that are lagging behind. The progress evaluation unit also has AI learn from the video data of training and perform visual evaluations to maximize the effectiveness of training. For example, it monitors the performance of each team through video analysis. This makes it possible to perform visual evaluations based on the video data of training and maximize the effectiveness of training.

[0084] The progress evaluation unit can use the emotion estimation function to provide feedback according to the emotional state of the operator, thereby maximizing the effectiveness of the training. The progress evaluation unit, for example, uses the emotion estimation function to provide feedback according to the emotional state of the operator, thereby maximizing the effectiveness of the training. For example, feedback including words of praise is provided to an operator with strong positive emotions. The progress evaluation unit also uses the emotion estimation function to analyze the emotion data of the operator and provide feedback to promote emotional growth. For example, an operator with low stress levels is encouraged to demonstrate leadership. The progress evaluation unit also uses the emotion estimation function to provide feedback based on the emotional reactions of the operator, thereby maximizing the effectiveness of the training. For example, an operator with strong positive emotions is encouraged to demonstrate leadership. In this way, feedback according to the emotional state of the operator is provided, thereby maximizing the effectiveness of the training.

[0085] The character generation unit can learn the specialized knowledge of each person in charge and provide specialized advice. For example, the character generation unit has an AI character learn the specialized knowledge of each person in charge and provide specialized advice. For example, a control AI character explains the system recovery procedures in detail. The character generation unit also has an AI character learn specialized knowledge and provide advice according to each person's role. For example, a monitoring team AI character explains monitoring points. The character generation unit also has an AI character learn the specialized knowledge of each person in charge and provide advice in real time during training. For example, a recovery team AI character instructs the troubleshooting procedures. This allows for specialized advice to be provided based on the specialized knowledge of each person in charge, improving the effectiveness of training.

[0086] The character generation unit can learn past training data and perform realistic training simulations. The character generation unit, for example, has an AI character learn past training data and perform realistic training simulations. For example, it performs a simulation based on past failure scenarios. The character generation unit also has the AI ​​character learn the training data and perform a simulation similar to actual training. For example, it performs a simulation that reproduces the roles of each person in charge. The character generation unit also has the AI ​​character learn past training data and perform training simulations in real time. For example, it performs a real-time failure response simulation based on past data. This makes it possible to perform realistic training simulations based on past training data and improve the effectiveness of training.

[0087] The character generation unit can use the emotion estimation function to customize learning content based on the viewer's emotional response. The character generation unit, for example, uses the emotion estimation function to customize learning content based on the viewer's emotional response. For example, content that interests the viewer is preferentially provided. The character generation unit also uses the emotion estimation function to analyze the viewer's emotional data and provide learning content according to the viewer's emotional response. For example, content with a higher level of difficulty is provided when the viewer is relaxed. The character generation unit also uses the emotion estimation function to customize learning content based on the viewer's emotional response to maximize learning effectiveness. For example, content containing compliments is provided to a viewer with strong positive emotions. In this way, learning content can be customized based on the viewer's emotional response to maximize learning effectiveness.

[0088] The character generation unit can learn knowledge from different industries and perform cross-industry training simulations. For example, the character generation unit has an AI character learn knowledge from different industries and perform cross-industry training simulations. For example, a simulation is performed that combines knowledge from the manufacturing and IT industries. The character generation unit also has an AI character learn knowledge from different industries, analyzes a common training scenario, and performs cross-industry training simulations. For example, a simulation is performed that combines knowledge from the financial industry and the medical industry. The character generation unit also has an AI character learn knowledge from different industries and performs a training simulation that incorporates best practices from different industries. For example, a simulation is performed that combines knowledge from the energy industry and the communications industry. This makes it possible to perform cross-industry training simulations based on knowledge from different industries, thereby improving the effectiveness of training.

[0089] The character generation unit can learn different languages ​​and provide international viewing and learning. For example, the character generation unit has an AI character learn different languages ​​and provide international viewing and learning. For example, a training simulation is performed in multiple languages, such as English, French, and Chinese. The character generation unit also has the AI ​​character learn multilingual knowledge and provide training scenarios in different languages. For example, a multilingual training simulation is performed in which operators from various countries can participate. The character generation unit also has the AI ​​character learn different languages ​​and provide international viewing and learning, maximizing the effectiveness of cross-cultural training. For example, feedback is provided in different languages. This makes it possible to provide international viewing and learning based on different languages ​​and improve the learning effectiveness.

[0090] The character generation unit can use the emotion estimation function to provide learning content that corresponds to the viewer's emotional state, thereby maximizing the learning effect. The character generation unit, for example, uses the emotion estimation function to provide learning content that corresponds to the viewer's emotional state, thereby maximizing the learning effect. For example, when the viewer is relaxed, more difficult content is provided. The character generation unit also uses the emotion estimation function to analyze the viewer's emotional data and provide learning content that corresponds to the viewer's emotional response. For example, content that the viewer is interested in is provided preferentially. The character generation unit also uses the emotion estimation function to customize learning content based on the viewer's emotional response, thereby maximizing the learning effect. For example, content that includes compliments is provided to a viewer with strong positive emotions. This allows the character generation unit to provide learning content that corresponds to the viewer's emotional state, thereby maximizing the learning effect.

[0091] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0092] The system can further include a voice recognition unit. The voice recognition unit analyzes the operator's voice commands and allows the system to be operated by voice. For example, when the operator issues a command to check the status of a specific server by voice, the voice recognition unit analyzes the command and displays the status of the corresponding server. The voice recognition unit can also control the progress of a failure scenario based on the operator's voice instructions. For example, when the operator issues a voice command such as "Proceed to the next scenario," the system moves on to the next failure scenario. Furthermore, the voice recognition unit can analyze the operator's voice feedback in real time and evaluate the progress of the training. For example, when the operator reports problems he or she has noticed during training by voice, the content of the report is analyzed and provided as feedback for improvements to the training.

[0093] The system may further include a biometrics recognition unit. The biometrics recognition unit may analyze the operator's biometric information and provide an optimal training program for each individual operator. For example, the biometrics recognition unit may monitor the operator's heart rate and galvanic skin response to evaluate the operator's stress level. The biometrics recognition unit may also adjust the difficulty of the training based on the operator's biometric information. For example, if the operator's heart rate is high, the difficulty of the training may be lowered so that the operator can continue training in a relaxed state. Furthermore, the biometrics recognition unit may analyze the operator's biometric information over the long term and monitor changes in the operator's health condition. For example, the biometrics recognition unit may analyze the operator's heart rate fluctuations during the training period to evaluate the operator's health condition.

[0094] The system can further include a virtual reality (VR) unit. The VR unit can provide operators with training in a virtual environment. For example, operators wear VR headsets and conduct troubleshooting training in a virtual data center. The VR unit can also track the operators' actions and provide feedback in real time. For example, when an operator performs an appropriate operation in the virtual environment, feedback is displayed immediately. Furthermore, the VR unit can enable multiple operators to train simultaneously in the virtual environment, enabling team cooperation training. For example, it can provide a scenario in which multiple operators work together in the virtual environment to handle a troubleshooting situation.

[0095] The system can further include a gamification unit. The gamification unit can incorporate game elements into training to increase the motivation of operators. For example, points can be awarded according to the progress of training and a ranking can be displayed. The gamification unit can also award badges and titles according to the goals that operators achieve. For example, a "quick response badge" can be awarded to an operator who quickly resolves a specific failure scenario. Furthermore, the gamification unit can promote competition between operators to increase the effectiveness of training. For example, it can provide team-based training scenarios and have teams compete to see which team can most effectively respond to failures.

[0096] The system can further use the emotion estimation function to adjust the progress of training based on the emotional state of the operator. For example, if the operator is feeling stressed, the system can temporarily ease the progress of training to provide time for the operator to relax. The emotion estimation function can also be used to provide feedback according to the operator's emotional state. For example, if the operator is showing positive emotions, the system can provide feedback including compliments. The emotion estimation function can also be used to adjust the difficulty of training based on the operator's emotional state. For example, if the operator is relaxed, the system can provide a more difficult scenario to promote the operator's skill improvement.

[0097] The system can further include a natural language processing (NLP) unit. The NLP unit can analyze the operator's text input and operate the system via text. For example, if the operator enters a text command to check the status of a specific server, the NLP unit can analyze the command and display the status of the corresponding server. The NLP unit can also analyze the operator's text feedback in real time to evaluate the progress of the training. For example, if the operator reports in text any problems they encountered during training, the NLP unit can analyze the content and provide feedback as areas for improvement in the training. Furthermore, the NLP unit can control the progress of the failure scenario based on the operator's text input. For example, if the operator gives the text command "Proceed to the next scenario," the system will proceed to the next failure scenario.

[0098] The system can further use the emotion estimation function to customize training feedback based on the operator's emotional state. For example, if the operator is feeling stressed, feedback suggesting relaxation techniques can be provided. The emotion estimation function can also be used to suggest training programs based on the operator's emotional state. For example, if the operator is feeling tired, effective training can be provided in a short period of time. The emotion estimation function can also be used to adjust the progress of training based on the operator's emotional state. For example, if the operator is relaxed, a more difficult scenario can be provided to promote the operator's skill improvement.

[0099] The system can further include a data visualization unit. The data visualization unit can visually display the progress and evaluation results of training. For example, the progress of training can be displayed in graphs and charts, allowing operators to intuitively understand. The data visualization unit can also visually display the evaluation results of training, allowing operators to grasp their own performance. For example, the progress and response speed of each team can be displayed in a heat map. Furthermore, the data visualization unit can visually present areas for improvement in training, allowing operators to understand specific improvement measures. For example, the areas for improvement based on the evaluation results of training can be displayed in a flowchart.

[0100] The system can further use an emotion estimation function to adjust the progress of the training in real time based on the emotional state of the operator. For example, if the operator is feeling stressed, the system can temporarily ease the progress of the training to provide time for the operator to relax. The emotion estimation function can also be used to provide feedback in real time according to the operator's emotional state. For example, if the operator is showing positive emotions, the system can provide feedback including compliments. The emotion estimation function can also be used to adjust the difficulty of the training in real time based on the operator's emotional state. For example, if the operator is relaxed, the system can provide a more difficult scenario to promote the operator's skill improvement.

[0101] The system can further be equipped with an anomaly detection unit. The anomaly detection unit can detect system anomalies in real time and issue alerts to operators. For example, it can detect sudden increases in CPU usage or abnormal increases in network traffic. The anomaly detection unit can also learn from past anomaly data and predict signs of anomalies. For example, it can predict system anomalies before specific error logs occur frequently. Furthermore, the anomaly detection unit can automatically generate response procedures in the event of an anomaly and provide them to operators. For example, it can automatically generate response procedures in the event of a specific server going down and instruct the operators on how to proceed.

[0102] The processing flow of the second embodiment will be briefly explained below.

[0103] Step 1: The learning unit learns the network and server settings of the production environment service. For example, the learning unit inputs network topology, server configuration files, log data, etc. into the AI ​​to understand the normal operating state of the system and predict behavior in the event of a failure. Step 2: The scenario generation unit generates a failure scenario based on the information learned by the learning unit. For example, the scenario generation unit creates a scenario for when a specific server goes down or the network is disconnected. Step 3: The role setting unit sets the roles and behavior patterns for training based on the scenario generated by the scenario generation unit. For example, the role setting unit has the control AI take the lead in giving instructions to each team, and each team responds to the AI. Step 4: The progress evaluation unit progresses and evaluates the training based on the roles and behavioral patterns set by the role setting unit. For example, after the training is completed, the progress evaluation unit uses AI to critique the training content and provide feedback on areas for improvement and success. Step 5: The character generation unit creates AI characters based on the information evaluated by the progress evaluation unit. For example, the character generation unit can create AI characters for each role and train them without human intervention.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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).

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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 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.

[0121] 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.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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 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.

[0136] 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.

[0137] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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 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.

[0149] 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.

[0150] 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.

[0151] 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 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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).

[0157] 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.

[0158] 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."

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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]

[0171] 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 learning department that learns the network and server settings of the production environment service, and a scenario generation unit that generates a fault scenario based on the information learned by the learning unit; a role setting unit that sets a role and a behavior pattern during training based on the scenario generated by the scenario generation unit; a progress evaluation unit that progresses and evaluates training based on the role and behavior pattern set by the role setting unit; a character generation unit that generates an AI character based on the information evaluated by the progress evaluation unit. A system characterized by:

2. The learning unit By learning the system's anomaly detection algorithm and analyzing log data and performance metrics, the system can predict signs of anomalies.

2. The system of claim 1.

3. The learning unit Learns system performance data and predicts the extent of impact when a failure occurs 2. The system of claim 1.

4. The learning unit Monitors operator stress levels in real time and issues appropriate alerts before stress levels rise 2. The system of claim 1.

5. The learning unit Learns the configuration information of other systems and predicts communication problems between multiple systems 2. The system of claim 1.

6. The learning unit Learn system security settings and generate response scenarios for security incidents 2. The system of claim 1.

Images