system

Abstract

The system according to this embodiment aims to significantly expand the capabilities of human operators in a man-machine system and improve safety and efficiency. [Solution] The system according to the embodiment comprises a glasses unit, a sensor unit, a suit unit, a support unit, and a preparation unit. The glasses unit comprises XR glasses. The sensor unit comprises an electroencephalogram (EEG) sensor. The suit unit comprises a haptic feedback suit. The support unit provides real-time support via a generating AI based on data collected by the glasses unit, sensor unit, and suit unit. The preparation unit anticipates the operator's intentions based on the support provided by the support unit and prepares necessary information and options in advance.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, it is difficult to fully utilize the capabilities of human operators in a man-machine system, and there are limitations in improving safety and efficiency.

[0005] The system according to the embodiment aims to greatly expand the capabilities of human operators in a man-machine system and improve safety and efficiency.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a glasses unit, a sensor unit, a suit unit, a support unit, and a preparation unit. The glasses unit comprises XR glasses. The sensor unit comprises an electroencephalogram (EEG) sensor. The suit unit comprises a haptic feedback suit. The support unit provides real-time support via a generating AI based on data collected by the glasses unit, sensor unit, and suit unit. The preparation unit anticipates the operator's intentions based on the support provided by the support unit and prepares necessary information and options in advance. [Effects of the Invention]

[0007] The system according to this embodiment can significantly extend the capabilities of human operators in a man-machine system and improve safety and efficiency. [Brief explanation of the drawing]

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

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

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

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

[0019] The smart device 14 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

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

[0028] (Example of form 1) The AISO system according to an embodiment of the present invention is a wearable device equipped with generative AI that significantly extends the capabilities of human operators in human-machine systems. This AISO system combines XR glasses, an electroencephalogram (EEG) sensor, and a haptic feedback suit to provide real-time assistance through generative AI. In advanced human-machine systems such as autonomous vehicles, surgical robots, air taxis, and spacecraft that require complex operations, it combines human judgment with machine precision to dramatically improve safety and efficiency. For example, the AISO system analyzes the operator's brainwaves and biometric information in real time and provides optimal information visually through the XR glasses. At the same time, the haptic feedback suit provides intuitive operational guidance. The generative AI anticipates the operator's intentions and prepares necessary information and options in advance. It also monitors the operator's condition and provides appropriate support according to fatigue and stress levels. In emergencies, the AI ​​instantly analyzes the situation and proposes the optimal response. The generative AI analyzes sensor data and system logs to understand the current situation and predict future developments. This provides the operator with the opportunity to take proactive measures. The system presents information in the most effective way based on the operator's experience level, cognitive style, and current physical and mental state. It generates an intuitive interface combining voice, visual, and tactile elements to reduce operator workload. It analyzes system usage data and constantly evolves to suit individual operators and specific operating environments. It generates VR training scenarios that precisely replicate actual operating environments to support operator skill improvement. By performing advanced AI processing on wearable devices, it achieves a low-latency and secure operating environment. The AISO system combines human creativity with machine precision, contributing to the realization of a safer and more efficient man-machine system. Furthermore, it is expected to contribute to CO2 emission reduction and labor savings, becoming an important technology for building a sustainable future. In this way, the AISO system can significantly extend the capabilities of human operators and improve safety and efficiency.

[0029] The AISO system according to this embodiment comprises a glasses unit, a sensor unit, a suit unit, a support unit, and a preparation unit. The glasses unit includes XR glasses and provides visual information to the operator. For example, the glasses unit can use the operator's eye-tracking data to center the most important information in the field of view. The glasses unit can also estimate the operator's emotions and adjust the color tone and brightness of the displayed information based on the estimated emotions. Furthermore, the glasses unit can analyze the operator's past operation history and automatically generate an optimal information display layout. The sensor unit includes an electroencephalogram (EEG) sensor and collects the operator's EEG data. For example, the sensor unit can analyze the operator's EEG data in real time and detect a decrease in concentration, displaying a warning. The sensor unit can also collect the operator's EEG data over a long period and learn the characteristics of individual operators. Furthermore, the sensor unit can estimate the operator's emotions and adjust the frequency of EEG data collection based on the estimated emotions. The suit unit includes a haptic feedback suit and provides haptic feedback to the operator. For example, the suit unit can estimate the operator's emotions and adjust the intensity of haptic feedback based on those emotions. The suit unit can also analyze the operator's motion data in real time and provide optimal haptic feedback. Furthermore, the suit unit can analyze the operator's past feedback history and generate feedback patterns optimized for each individual operator. The support unit provides real-time assistance through generative AI based on data collected by the glasses unit, sensor unit, and suit unit. For example, the support unit can use generative AI to analyze sensor data and system logs to understand the current situation and predict future developments. The support unit can also use generative AI to estimate the operator's emotions and adjust the assistance based on those emotions. Furthermore, the support unit can use generative AI to analyze system logs over a long period, predict future problems, and display warnings in advance.The preparation unit, based on the support provided by the support unit, anticipates the operator's intentions and prepares necessary information and options in advance. For example, the preparation unit can use generative AI to present information in the most effective way, based on the operator's experience level, cognitive style, and current physical and mental state. The preparation unit can also use generative AI to generate an intuitive interface that combines voice, visual, and tactile elements. Furthermore, the preparation unit can use generative AI to analyze system usage data and continuously evolve to suit individual operators and specific operating environments. As a result, the AISO system according to this embodiment can significantly extend the capabilities of human operators and improve safety and efficiency.

[0030] The glasses unit incorporates XR glasses to provide the operator with visual information. For example, the glasses unit can use the operator's eye-tracking data to center the most important information in their field of view. Specifically, it uses eye-tracking technology to monitor the operator's eye movements in real time and prioritizes displaying information related to where their gaze is concentrated. The glasses unit can also estimate the operator's emotions and adjust the color tone and brightness of the displayed information based on the estimated emotions. Emotion estimation is performed by combining facial recognition technology and EEG data analysis to evaluate the operator's stress level and concentration level. Furthermore, the glasses unit can analyze the operator's past operation history and automatically generate the optimal information display layout. Machine learning algorithms are used to learn the operator's behavior patterns and preferences in the operation history analysis, providing the optimal layout for each individual operator. This allows the glasses unit to reduce the operator's visual burden and support efficient information processing. In addition, the glasses unit can utilize augmented reality (AR) technology to overlay virtual information onto the real field of view. For example, it can support rapid decision-making by overlaying important data and warning messages onto the real-world scenery the operator is seeing. Furthermore, by incorporating voice recognition technology, the display content of the glasses can be changed in response to the operator's voice commands. This enables hands-free operation, improving the operator's work efficiency.

[0031] The sensor unit is equipped with an electroencephalogram (EEG) sensor and collects the operator's brainwave data. For example, the sensor unit can analyze the operator's EEG data in real time, detect a decline in concentration, and display a warning. Specifically, the EEG sensor is attached to the operator's head and detects fluctuations in brainwaves with high precision. This allows for real-time monitoring of the operator's concentration and fatigue levels, and displays a warning prompting a break as needed. The sensor unit can also collect the operator's EEG data over a long period and learn the characteristics of each individual operator. Long-term data collection allows for detailed analysis of the operator's EEG patterns and fluctuations in work efficiency, enabling the development of individualized support plans. Furthermore, the sensor unit can estimate the operator's emotions and adjust the frequency of EEG data collection based on the estimated emotions. Emotion estimation can be more accurate by using biometric data such as heart rate and skin electrical responses in addition to EEG data analysis. This allows the sensor unit to flexibly collect data according to the operator's condition and provide optimal support. In addition, the sensor unit can build a feedback system based on EEG data to support the improvement of the operator's performance. For example, when concentration levels decline, the system provides relaxing music or videos to help the operator regain focus. Furthermore, the sensor unit integrates and analyzes brainwave data with other biometric data to assess the operator's overall health, contributing to long-term health management.

[0032] The suit unit is equipped with a haptic feedback suit that provides tactile feedback to the operator. For example, the suit unit can estimate the operator's emotions and adjust the intensity of the haptic feedback based on the estimated emotions. Specifically, the haptic feedback suit is worn on the operator's body and provides tactile stimuli such as vibration and pressure. This allows the operator to receive information not only through sight and hearing, but also through touch. The suit unit can also analyze the operator's motion data in real time and provide optimal haptic feedback. For motion data analysis, acceleration sensors and gyroscopes are used to monitor the operator's movements and posture in detail. Furthermore, the suit unit can analyze the operator's past feedback history and generate the optimal feedback pattern for each individual operator. For feedback history analysis, machine learning algorithms are used to learn the operator's preferences and reaction patterns and provide optimal tactile stimuli. In this way, the suit unit can support the operator's senses in a multifaceted way, improving work efficiency and safety. In addition, the suit unit has the function to customize the intensity and pattern of haptic feedback, and can provide feedback that meets the individual needs of the operator. For example, in specific tasks, strong vibrations can be used to attract attention, while gentle pressure can be provided when relaxation is needed. The suit can also work in conjunction with other departments to provide haptic feedback synchronized with visual and auditory information. This allows operators to integrate information from multiple senses, resulting in more intuitive and effective support.

[0033] The support unit uses generative AI to provide real-time assistance based on data collected by the glasses unit, sensor unit, and suit unit. For example, the support unit can use generative AI to analyze sensor data and system logs to understand the current situation and predict future developments. Specifically, the generative AI integrates the collected data and analyzes the operator's behavior patterns and environmental fluctuations. This allows it to predict potential risks and problems the operator may face and propose appropriate countermeasures. The support unit can also use generative AI to estimate the operator's emotions and adjust the support content based on the estimated emotions. Emotion estimation is performed by combining the analysis of electroencephalogram (EEG) data and biometric data to evaluate the operator's stress level and concentration level. Furthermore, the support unit can use generative AI to analyze system logs over a long period of time, predict future problems, and display warnings in advance. Anomaly detection algorithms are used to detect unusual patterns and abnormal data in the analysis of system logs. This allows the support unit to not only provide real-time assistance but also handle long-term risk management and anomaly detection, improving the overall reliability and safety of the system. In addition, the support unit can use generative AI to provide advice and guidelines to improve the operator's work efficiency. For example, it can suggest optimal procedures and tool usage methods to help operators work efficiently. Furthermore, the support department can use generative AI to automatically generate training programs to assist in improving operators' skills. This allows the support department to maximize operators' capabilities and provide a safe and efficient work environment.

[0034] The preparation unit anticipates the operator's intentions and prepares necessary information and options in advance, based on the support provided by the support unit. For example, the preparation unit can use generative AI to present information in the most effective way, based on the operator's experience level, cognitive style, and current physical and mental state. Specifically, the generative AI analyzes the operator's past operation history and feedback to learn the optimal information presentation method for each individual operator. This allows operators to quickly and intuitively obtain the necessary information. The preparation unit can also use generative AI to generate intuitive interfaces that combine voice, visual, and tactile elements. For example, combining voice commands with visual guidelines allows operators to easily understand and perform complex operations. Furthermore, the preparation unit can use generative AI to analyze system usage data and continuously evolve to suit individual operators and specific operating environments. Machine learning algorithms are used to analyze usage data, learning operator behavior patterns and environmental fluctuations to provide optimal support methods. This allows the preparation unit to improve work efficiency and safety by anticipating the operator's intentions and preparing necessary information and options in advance. In addition, the preparation unit can collect operator feedback and continuously improve the accuracy and effectiveness of the support provided. For example, the preparation department can record how operators responded to the information and options provided and use that information to improve future support. The preparation department can also collaborate with other departments to optimize the operator's overall work environment. This allows the preparation department to anticipate operator intentions and prepare necessary information and options in advance, thereby improving work efficiency and safety.

[0035] The support unit can use generative AI to analyze sensor data and system logs, understand the current situation, and predict future developments. For example, the support unit can analyze sensor data in real time to grasp the current situation. It can also analyze system logs over a long period to predict future problems. Furthermore, the support unit can use predictive algorithms to perform scenario analysis of future developments. As a result, the generative AI can understand the situation and predict future developments, supporting the operator's decision-making.

[0036] The preparation unit, using generated AI, can present information in the most effective way based on the operator's experience level, cognitive style, and current physical and mental state. For example, the preparation unit analyzes the operator's past operation history to assess their experience level. It can also classify the operator's cognitive style into visual, auditory, tactile, etc., and present information accordingly. Furthermore, the preparation unit can assess the operator's physical and mental state based on biometric information such as electroencephalogram data, heart rate, and stress level. This allows for improved operational efficiency and accuracy through information presentation tailored to the operator's characteristics.

[0037] The preparation unit can generate an intuitive interface combining voice, visual, and tactile elements using generative AI. For example, the preparation unit can provide instructions to the operator using voice guidance. It can also display visual alerts and highlight important information. Furthermore, it can provide intuitive operational guidance to the operator using haptic feedback. This intuitive interface reduces the operator's workload.

[0038] The preparation unit, using generative AI, can analyze system usage data and continuously evolve to suit individual operators and specific operating environments. For example, the preparation unit can learn operator operation patterns using machine learning algorithms. It can also build feedback loops and improve the system based on operator feedback. Furthermore, the preparation unit can customize the system to suit specific operating environments, providing optimal support. This ensures the system is constantly evolving and provides optimal support.

[0039] The preparation unit can generate VR training scenarios that precisely reproduce the actual operating environment using generation AI, thereby supporting the improvement of operators' skills. For example, the preparation unit simulates the actual operating environment using VR technology. Furthermore, the preparation unit can collect detailed environmental data to improve simulation accuracy and incorporate it into the VR training scenarios. In addition, the preparation unit can generate training scenarios tailored to the operator's skill level, supporting individual skill improvement. This allows VR training scenarios to support the improvement of operators' skills.

[0040] The preparation unit, using generative AI, can perform advanced AI processing on wearable devices, enabling a low-latency and secure operating environment. For example, the preparation unit can optimize communication protocols to improve data processing speed. It can also ensure data security using encryption technology. Furthermore, the preparation unit can strengthen authentication processes to prevent unauthorized access. This allows for a low-latency and secure operating environment.

[0041] The glasses can utilize the operator's eye-tracking data to center the most important information in their field of view. For example, if the operator is fixated on a specific area, the glasses will display information related to that area in the center of their field of view. Furthermore, if the operator is reviewing multiple pieces of information, the glasses can prioritize and center the most important information. In addition, if the operator frequently moves their eyes, the glasses can predict eye movements and dynamically position information accordingly. This allows for the effective display of important information using eye-tracking data.

[0042] The Glass unit can analyze the operator's past operation history and automatically generate the optimal information display layout. For example, the Glass unit can generate a layout that prioritizes displaying information frequently used by the operator in the past. Furthermore, the Glass unit can analyze the operator's operation patterns and suggest an efficient information display layout. In addition, the Glass unit can generate customized layouts based on the operator's past operation history, tailored to specific situations. This allows for the provision of efficient information display layouts by analyzing past operation history.

[0043] The glasses unit can prioritize the display of relevant geographic information, taking into account the operator's geographical location. For example, if the operator is in a specific area, the glasses unit will prioritize the display of information related to that area. Furthermore, if the operator is on the move, the glasses unit can display real-time geographic information based on their current location. In addition, the glasses unit can automatically display information related to a specific point as the operator approaches it. This prioritizes the display of geographic information, thereby supporting the operator's decision-making.

[0044] The Glasses unit can analyze the operator's social media activity and display relevant information. For example, it can display relevant news and data based on information the operator has shared on social media. It can also prioritize displaying information shared by the operator's social media followers and friends. Furthermore, it can analyze the operator's social media activity history and display information of interest. This allows for the effective display of relevant information by analyzing social media activity.

[0045] The sensor unit can analyze the operator's brainwave data in real time, detect a decline in concentration, and display a warning. For example, the sensor unit can detect a decline in concentration from the operator's brainwave data and display a visual warning. The sensor unit can also analyze the operator's brainwave data in real time and provide an audible warning. Furthermore, the sensor unit can provide a warning through haptic feedback based on the operator's brainwave data. This allows for the detection of a decline in concentration in real time and the display of warnings, thereby maintaining the operator's performance.

[0046] The sensor unit can collect operator EEG data over a long period and learn the characteristics of each individual operator. For example, the sensor unit can collect operator EEG data over several months and learn their characteristics. Furthermore, the sensor unit can analyze the operator's EEG data and provide support based on their individual characteristics. In addition, the sensor unit can collect operator EEG data over a long period and use it to improve performance. This allows for the provision of optimal support to each individual operator through long-term data collection.

[0047] The sensor unit can analyze the operator's physical movements and brainwave data in combination to perform more accurate state assessments. For example, the sensor unit can evaluate the operator's concentration level by combining the operator's physical movements and brainwave data. It can also evaluate stress levels by analyzing the operator's physical movements and brainwave data. Furthermore, the sensor unit can evaluate fatigue levels by combining the operator's physical movements and brainwave data. In this way, combining physical movements and brainwave data enables highly accurate state assessments.

[0048] The sensor unit can analyze the operator's ambient sounds and identify stressors by correlating them with electroencephalogram (EEG) data. For example, the sensor unit can analyze the operator's ambient sounds and identify stressors by correlating them with EEG data. Furthermore, the sensor unit can evaluate stress levels by combining the operator's ambient sounds and EEG data. In addition, the sensor unit can analyze the operator's ambient sounds and identify factors contributing to decreased concentration by correlating them with EEG data. This makes it easier to identify stressors by correlating ambient sounds with EEG data.

[0049] The suit unit can analyze the operator's movement data in real time and provide optimal haptic feedback. For example, the suit unit can analyze the operator's movement data in real time and provide haptic feedback. Furthermore, the suit unit can adjust the optimal haptic feedback in real time based on the operator's movement data. In addition, the suit unit can analyze the operator's movement data and optimize the timing of the haptic feedback. This allows for the provision of optimal haptic feedback by analyzing movement data in real time.

[0050] The suit unit can analyze an operator's past feedback history and generate an optimal feedback pattern for each individual operator. For example, the suit unit can analyze an operator's past feedback history and generate an optimal feedback pattern. Furthermore, the suit unit can provide feedback patterns tailored to individual characteristics based on the operator's feedback history. In addition, the suit unit can analyze an operator's past feedback history and use that information to improve performance. This allows for the provision of optimal feedback to each individual operator by analyzing past feedback history.

[0051] The suit can monitor the operator's physical condition and provide haptic feedback as needed. For example, the suit can monitor the operator's physical condition and provide haptic feedback as needed. The suit can also adjust the intensity of the haptic feedback based on the operator's physical condition. Furthermore, the suit can monitor the operator's physical condition and provide haptic feedback at the appropriate time. This allows for the provision of haptic feedback as needed by monitoring the operator's physical condition.

[0052] The suit unit can change the type of haptic feedback depending on the operator's work environment. For example, the suit unit can change the type of haptic feedback depending on the operator's work environment. Furthermore, the suit unit can provide optimal haptic feedback based on the operator's work environment. In addition, the suit unit can customize the haptic feedback pattern according to the operator's work environment. This allows for more appropriate support by changing the type of haptic feedback according to the work environment.

[0053] The support unit can analyze sensor data in real time and provide optimal information to support the operator's decision-making. For example, the support unit can analyze sensor data in real time and provide optimal information to support the operator's decision-making. Furthermore, the support unit can provide visual information based on sensor data to support the operator's decision-making. In addition, the support unit can analyze sensor data in real time and provide voice guidance to support the operator's decision-making. This allows for support of operator decision-making by analyzing sensor data in real time.

[0054] The support unit can analyze system logs over a long period of time, predict future problems, and display warnings in advance. For example, the support unit can analyze system logs over a long period of time, predict future problems, and display visual warnings. It can also predict future problems based on system logs and provide voice warnings. Furthermore, the support unit can analyze system logs over a long period of time, predict future problems, and provide warnings through haptic feedback. In this way, by analyzing system logs over a long period of time, it is possible to predict future problems and display warnings in advance.

[0055] The support department can analyze the operator's past operation history and provide the optimal support method. For example, the support department can analyze the operator's past operation history and provide the optimal support method. Furthermore, the support department can provide support methods tailored to the individual characteristics of each operator based on their operation history. In addition, the support department can analyze the operator's past operation history and propose efficient support methods. Thus, by analyzing past operation history, the support department can provide the optimal support method.

[0056] The support department can customize the support provided according to the operator's work environment. For example, the support department can customize the support provided based on the operator's work environment. Furthermore, the support department can provide optimal support based on the operator's work environment. In addition, the support department can adjust the priority of support based on the operator's work environment. This allows for more appropriate support to be provided through customized support tailored to the work environment.

[0057] The preparation unit can adjust the level of detail of information to the optimal level based on the operator's experience level. For example, if the operator has a high level of experience, the preparation unit will provide detailed information. Conversely, if the operator has a low level of experience, the preparation unit can provide basic information. Furthermore, the preparation unit can dynamically adjust the level of detail of information according to the operator's experience level. This allows for more appropriate support to be provided by adjusting the level of detail of information according to the experience level.

[0058] The preparation unit can change the information presentation format according to the operator's cognitive style. For example, if the operator's cognitive style is visual, the preparation unit will provide a graphical information presentation format. Furthermore, if the operator's cognitive style is auditory, the preparation unit can also provide information verbally. In addition, the preparation unit can dynamically change the information presentation format according to the operator's cognitive style. This allows for more appropriate support to be provided by changing the information presentation format according to the cognitive style.

[0059] The preparation department can monitor the operator's physical and mental state and delay the presentation of information as needed. For example, the preparation department can monitor the operator's physical and mental state and delay the presentation of information as needed. Furthermore, the preparation department can adjust the timing of information presentation based on the operator's physical and mental state. In addition, the preparation department can monitor the operator's physical and mental state and present information at the appropriate time. This allows for more appropriate support to be provided by delaying information presentation according to the operator's physical and mental state.

[0060] The preparation unit can customize the information presented according to the operator's work environment. For example, the preparation unit can customize the information presented according to the operator's work environment. Furthermore, the preparation unit can provide optimal information based on the operator's work environment. In addition, the preparation unit can adjust the priority of the information presented according to the operator's work environment. This allows for more appropriate support through the customization of information presented according to the work environment.

[0061] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0062] The AISO system can also be equipped with a rhythm adjustment unit that monitors the operator's biological rhythms and proposes optimal work timings. For example, the rhythm adjustment unit analyzes the operator's heart rate, body temperature, and sleep patterns to suggest optimal work start times and rest periods. Furthermore, the rhythm adjustment unit can automatically generate a schedule to maximize work efficiency based on the operator's biological rhythms. In addition, the rhythm adjustment unit can adjust the priority of tasks according to the operator's biological rhythms, providing an optimal work flow. This enables an efficient work environment through work suggestions based on the operator's biological rhythms.

[0063] The AISO system can also be equipped with an ergonomics adjustment unit that analyzes the operator's movements and proposes optimal ergonomics. For example, the ergonomics adjustment unit analyzes the operator's posture and movement patterns and proposes the optimal working posture. Furthermore, the ergonomics adjustment unit can optimize the layout of the work environment based on the operator's movement data. In addition, the ergonomics adjustment unit can analyze the operator's movement history and propose ergonomic improvements to reduce fatigue from prolonged work. This allows for improved work efficiency and comfort through ergonomic suggestions based on operator movement analysis.

[0064] The AISO system can also include a tool suggestion unit that proposes the most suitable tools and resources according to the operator's work. For example, the tool suggestion unit can suggest the optimal tools and resources when the operator is performing a specific task. Furthermore, the tool suggestion unit can analyze the operator's past work history and suggest efficient tool usage methods. In addition, the tool suggestion unit can suggest the optimal tool placement according to the operator's work environment. This allows for improved work efficiency through tool suggestions tailored to the operator's work.

[0065] The AISO system can also be equipped with an environmental control unit that monitors the operator's work environment and maintains optimal temperature and humidity. For example, the environmental control unit monitors the temperature and humidity of the operator's work environment in real time and maintains optimal conditions. Furthermore, the environmental control unit can adjust the temperature and humidity according to the operator's work. In addition, the environmental control unit can customize the work environment based on the operator's individual preferences. This optimizes the temperature and humidity of the work environment, thereby improving operator comfort and efficiency.

[0066] The AISO system can also include a performance evaluation unit that assesses and provides feedback on the operator's work performance. For example, the performance evaluation unit analyzes the operator's work data and evaluates their performance. Furthermore, the performance evaluation unit can suggest areas for improvement based on the operator's past performance data. In addition, the performance evaluation unit can monitor the operator's work performance in real time and provide immediate feedback. This allows for the evaluation of the operator's work performance and facilitates improvement.

[0067] The following briefly describes the processing flow for example form 1.

[0068] Step 1: The glasses unit is equipped with XR glasses and provides visual information to the operator. For example, the glasses unit can use the operator's eye-tracking data to center the most important information in the field of view. The glasses unit can also estimate the operator's emotions and adjust the color tone and brightness of the displayed information based on the estimated emotions of the operator. Furthermore, the glasses unit can analyze the operator's past operation history and automatically generate the optimal information display layout. Step 2: The sensor unit is equipped with an electroencephalogram (EEG) sensor and collects the operator's EEG data. For example, the sensor unit can analyze the operator's EEG data in real time, detect a decrease in concentration, and display a warning. The sensor unit can also collect the operator's EEG data over a long period of time and learn the characteristics of each individual operator. Furthermore, the sensor unit can estimate the operator's emotions and adjust the frequency of EEG data collection based on the estimated emotions of the operator. Step 3: The suit unit is equipped with a haptic feedback suit and provides haptic feedback to the operator. For example, the suit unit can estimate the operator's emotions and adjust the intensity of the haptic feedback based on the estimated emotions. The suit unit can also analyze the operator's motion data in real time and provide optimal haptic feedback. Furthermore, the suit unit can analyze the operator's past feedback history and generate the optimal feedback pattern for each individual operator. Step 4: The support unit uses the generated AI to provide real-time support based on data collected by the glasses unit, sensor unit, and suit unit. For example, the support unit can use the generated AI to analyze sensor data and system logs to understand the current situation and predict future developments. The support unit can also use the generated AI to estimate the operator's emotions and adjust the support content based on the estimated emotions. Furthermore, the support unit can use the generated AI to analyze system logs over a long period of time, predict future problems, and display warnings in advance. Step 5: Based on the support provided by the support team, the preparation team anticipates the operator's intentions and prepares necessary information and options in advance. For example, the preparation team can use generative AI to present information in the most effective way, based on the operator's experience level, cognitive style, and current mental and physical state. The preparation team can also use generative AI to generate an intuitive interface that combines voice, visual, and tactile elements. Furthermore, the preparation team can use generative AI to analyze system usage data and continuously evolve to suit individual operators and specific operating environments.

[0069] (Example of form 2) The AISO system according to an embodiment of the present invention is a wearable device equipped with generative AI that significantly extends the capabilities of human operators in human-machine systems. This AISO system combines XR glasses, an electroencephalogram (EEG) sensor, and a haptic feedback suit to provide real-time assistance through generative AI. In advanced human-machine systems such as autonomous vehicles, surgical robots, air taxis, and spacecraft that require complex operations, it combines human judgment with machine precision to dramatically improve safety and efficiency. For example, the AISO system analyzes the operator's brainwaves and biometric information in real time and provides optimal information visually through the XR glasses. At the same time, the haptic feedback suit provides intuitive operational guidance. The generative AI anticipates the operator's intentions and prepares necessary information and options in advance. It also monitors the operator's condition and provides appropriate support according to fatigue and stress levels. In emergencies, the AI ​​instantly analyzes the situation and proposes the optimal response. The generative AI analyzes sensor data and system logs to understand the current situation and predict future developments. This provides the operator with the opportunity to take proactive measures. The system presents information in the most effective way based on the operator's experience level, cognitive style, and current physical and mental state. It generates an intuitive interface combining voice, visual, and tactile elements to reduce operator workload. It analyzes system usage data and constantly evolves to suit individual operators and specific operating environments. It generates VR training scenarios that precisely replicate actual operating environments to support operator skill improvement. By performing advanced AI processing on wearable devices, it achieves a low-latency and secure operating environment. The AISO system combines human creativity with machine precision, contributing to the realization of a safer and more efficient man-machine system. Furthermore, it is expected to contribute to CO2 emission reduction and labor savings, becoming an important technology for building a sustainable future. In this way, the AISO system can significantly extend the capabilities of human operators and improve safety and efficiency.

[0070] The AISO system according to this embodiment comprises a glasses unit, a sensor unit, a suit unit, a support unit, and a preparation unit. The glasses unit includes XR glasses and provides visual information to the operator. For example, the glasses unit can use the operator's eye-tracking data to center the most important information in the field of view. The glasses unit can also estimate the operator's emotions and adjust the color tone and brightness of the displayed information based on the estimated emotions. Furthermore, the glasses unit can analyze the operator's past operation history and automatically generate an optimal information display layout. The sensor unit includes an electroencephalogram (EEG) sensor and collects the operator's EEG data. For example, the sensor unit can analyze the operator's EEG data in real time and detect a decrease in concentration, displaying a warning. The sensor unit can also collect the operator's EEG data over a long period and learn the characteristics of individual operators. Furthermore, the sensor unit can estimate the operator's emotions and adjust the frequency of EEG data collection based on the estimated emotions. The suit unit includes a haptic feedback suit and provides haptic feedback to the operator. For example, the suit unit can estimate the operator's emotions and adjust the intensity of haptic feedback based on those emotions. The suit unit can also analyze the operator's motion data in real time and provide optimal haptic feedback. Furthermore, the suit unit can analyze the operator's past feedback history and generate feedback patterns optimized for each individual operator. The support unit provides real-time assistance through generative AI based on data collected by the glasses unit, sensor unit, and suit unit. For example, the support unit can use generative AI to analyze sensor data and system logs to understand the current situation and predict future developments. The support unit can also use generative AI to estimate the operator's emotions and adjust the assistance based on those emotions. Furthermore, the support unit can use generative AI to analyze system logs over a long period, predict future problems, and display warnings in advance.The preparation unit, based on the support provided by the support unit, anticipates the operator's intentions and prepares necessary information and options in advance. For example, the preparation unit can use generative AI to present information in the most effective way, based on the operator's experience level, cognitive style, and current physical and mental state. The preparation unit can also use generative AI to generate an intuitive interface that combines voice, visual, and tactile elements. Furthermore, the preparation unit can use generative AI to analyze system usage data and continuously evolve to suit individual operators and specific operating environments. As a result, the AISO system according to this embodiment can significantly extend the capabilities of human operators and improve safety and efficiency.

[0071] The glasses unit incorporates XR glasses to provide the operator with visual information. For example, the glasses unit can use the operator's eye-tracking data to center the most important information in their field of view. Specifically, it uses eye-tracking technology to monitor the operator's eye movements in real time and prioritizes displaying information related to where their gaze is concentrated. The glasses unit can also estimate the operator's emotions and adjust the color tone and brightness of the displayed information based on the estimated emotions. Emotion estimation is performed by combining facial recognition technology and EEG data analysis to evaluate the operator's stress level and concentration level. Furthermore, the glasses unit can analyze the operator's past operation history and automatically generate the optimal information display layout. Machine learning algorithms are used to learn the operator's behavior patterns and preferences in the operation history analysis, providing the optimal layout for each individual operator. This allows the glasses unit to reduce the operator's visual burden and support efficient information processing. In addition, the glasses unit can utilize augmented reality (AR) technology to overlay virtual information onto the real field of view. For example, it can support rapid decision-making by overlaying important data and warning messages onto the real-world scenery the operator is seeing. Furthermore, by incorporating voice recognition technology, the display content of the glasses can be changed in response to the operator's voice commands. This enables hands-free operation, improving the operator's work efficiency.

[0072] The sensor unit is equipped with an electroencephalogram (EEG) sensor and collects the operator's brainwave data. For example, the sensor unit can analyze the operator's EEG data in real time, detect a decline in concentration, and display a warning. Specifically, the EEG sensor is attached to the operator's head and detects fluctuations in brainwaves with high precision. This allows for real-time monitoring of the operator's concentration and fatigue levels, and displays a warning prompting a break as needed. The sensor unit can also collect the operator's EEG data over a long period and learn the characteristics of each individual operator. Long-term data collection allows for detailed analysis of the operator's EEG patterns and fluctuations in work efficiency, enabling the development of individualized support plans. Furthermore, the sensor unit can estimate the operator's emotions and adjust the frequency of EEG data collection based on the estimated emotions. Emotion estimation can be more accurate by using biometric data such as heart rate and skin electrical responses in addition to EEG data analysis. This allows the sensor unit to flexibly collect data according to the operator's condition and provide optimal support. In addition, the sensor unit can build a feedback system based on EEG data to support the improvement of the operator's performance. For example, when concentration levels decline, the system provides relaxing music or videos to help the operator regain focus. Furthermore, the sensor unit integrates and analyzes brainwave data with other biometric data to assess the operator's overall health, contributing to long-term health management.

[0073] The suit unit is equipped with a haptic feedback suit that provides tactile feedback to the operator. For example, the suit unit can estimate the operator's emotions and adjust the intensity of the haptic feedback based on the estimated emotions. Specifically, the haptic feedback suit is worn on the operator's body and provides tactile stimuli such as vibration and pressure. This allows the operator to receive information not only through sight and hearing, but also through touch. The suit unit can also analyze the operator's motion data in real time and provide optimal haptic feedback. For motion data analysis, acceleration sensors and gyroscopes are used to monitor the operator's movements and posture in detail. Furthermore, the suit unit can analyze the operator's past feedback history and generate the optimal feedback pattern for each individual operator. For feedback history analysis, machine learning algorithms are used to learn the operator's preferences and reaction patterns and provide optimal tactile stimuli. In this way, the suit unit can support the operator's senses in a multifaceted way, improving work efficiency and safety. In addition, the suit unit has the function to customize the intensity and pattern of haptic feedback, and can provide feedback that meets the individual needs of the operator. For example, in specific tasks, strong vibrations can be used to attract attention, while gentle pressure can be provided when relaxation is needed. The suit can also work in conjunction with other departments to provide haptic feedback synchronized with visual and auditory information. This allows operators to integrate information from multiple senses, resulting in more intuitive and effective support.

[0074] The support unit uses generative AI to provide real-time assistance based on data collected by the glasses unit, sensor unit, and suit unit. For example, the support unit can use generative AI to analyze sensor data and system logs to understand the current situation and predict future developments. Specifically, the generative AI integrates the collected data and analyzes the operator's behavior patterns and environmental fluctuations. This allows it to predict potential risks and problems the operator may face and propose appropriate countermeasures. The support unit can also use generative AI to estimate the operator's emotions and adjust the support content based on the estimated emotions. Emotion estimation is performed by combining the analysis of electroencephalogram (EEG) data and biometric data to evaluate the operator's stress level and concentration level. Furthermore, the support unit can use generative AI to analyze system logs over a long period of time, predict future problems, and display warnings in advance. Anomaly detection algorithms are used to detect unusual patterns and abnormal data in the analysis of system logs. This allows the support unit to not only provide real-time assistance but also handle long-term risk management and anomaly detection, improving the overall reliability and safety of the system. In addition, the support unit can use generative AI to provide advice and guidelines to improve the operator's work efficiency. For example, it can suggest optimal procedures and tool usage methods to help operators work efficiently. Furthermore, the support department can use generative AI to automatically generate training programs to assist in improving operators' skills. This allows the support department to maximize operators' capabilities and provide a safe and efficient work environment.

[0075] The preparation unit anticipates the operator's intentions and prepares necessary information and options in advance, based on the support provided by the support unit. For example, the preparation unit can use generative AI to present information in the most effective way, based on the operator's experience level, cognitive style, and current physical and mental state. Specifically, the generative AI analyzes the operator's past operation history and feedback to learn the optimal information presentation method for each individual operator. This allows operators to quickly and intuitively obtain the necessary information. The preparation unit can also use generative AI to generate intuitive interfaces that combine voice, visual, and tactile elements. For example, combining voice commands with visual guidelines allows operators to easily understand and perform complex operations. Furthermore, the preparation unit can use generative AI to analyze system usage data and continuously evolve to suit individual operators and specific operating environments. Machine learning algorithms are used to analyze usage data, learning operator behavior patterns and environmental fluctuations to provide optimal support methods. This allows the preparation unit to improve work efficiency and safety by anticipating the operator's intentions and preparing necessary information and options in advance. In addition, the preparation unit can collect operator feedback and continuously improve the accuracy and effectiveness of the support provided. For example, the preparation department can record how operators responded to the information and options provided and use that information to improve future support. The preparation department can also collaborate with other departments to optimize the operator's overall work environment. This allows the preparation department to anticipate operator intentions and prepare necessary information and options in advance, thereby improving work efficiency and safety.

[0076] The support unit can use generative AI to analyze sensor data and system logs, understand the current situation, and predict future developments. For example, the support unit can analyze sensor data in real time to grasp the current situation. It can also analyze system logs over a long period to predict future problems. Furthermore, the support unit can use predictive algorithms to perform scenario analysis of future developments. As a result, the generative AI can understand the situation and predict future developments, supporting the operator's decision-making.

[0077] The preparation unit, using generated AI, can present information in the most effective way based on the operator's experience level, cognitive style, and current physical and mental state. For example, the preparation unit analyzes the operator's past operation history to assess their experience level. It can also classify the operator's cognitive style into visual, auditory, tactile, etc., and present information accordingly. Furthermore, the preparation unit can assess the operator's physical and mental state based on biometric information such as electroencephalogram data, heart rate, and stress level. This allows for improved operational efficiency and accuracy through information presentation tailored to the operator's characteristics.

[0078] The preparation unit can generate an intuitive interface combining voice, visual, and tactile elements using generative AI. For example, the preparation unit can provide instructions to the operator using voice guidance. It can also display visual alerts and highlight important information. Furthermore, it can provide intuitive operational guidance to the operator using haptic feedback. This intuitive interface reduces the operator's workload.

[0079] The preparation unit, using generative AI, can analyze system usage data and continuously evolve to suit individual operators and specific operating environments. For example, the preparation unit can learn operator operation patterns using machine learning algorithms. It can also build feedback loops and improve the system based on operator feedback. Furthermore, the preparation unit can customize the system to suit specific operating environments, providing optimal support. This ensures the system is constantly evolving and provides optimal support.

[0080] The preparation unit can generate VR training scenarios that precisely reproduce the actual operating environment using generation AI, thereby supporting the improvement of operators' skills. For example, the preparation unit simulates the actual operating environment using VR technology. Furthermore, the preparation unit can collect detailed environmental data to improve simulation accuracy and incorporate it into the VR training scenarios. In addition, the preparation unit can generate training scenarios tailored to the operator's skill level, supporting individual skill improvement. This allows VR training scenarios to support the improvement of operators' skills.

[0081] The preparation unit, using generative AI, can perform advanced AI processing on wearable devices, enabling a low-latency and secure operating environment. For example, the preparation unit can optimize communication protocols to improve data processing speed. It can also ensure data security using encryption technology. Furthermore, the preparation unit can strengthen authentication processes to prevent unauthorized access. This allows for a low-latency and secure operating environment.

[0082] The glasses can estimate the operator's emotions and adjust the color tone and brightness of the displayed information based on the estimated emotions. For example, if the operator is tense, the glasses can display information in calm colors to reduce visual stress. If the operator is relaxed, the glasses can display information in bright colors to enhance the enjoyment of the work. Furthermore, if the operator is tired, the glasses can display information in eye-friendly colors to reduce visual strain. In this way, visual strain can be reduced by displaying information according to the operator's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0083] The glasses can utilize the operator's eye-tracking data to center the most important information in their field of view. For example, if the operator is fixated on a specific area, the glasses will display information related to that area in the center of their field of view. Furthermore, if the operator is reviewing multiple pieces of information, the glasses can prioritize and center the most important information. In addition, if the operator frequently moves their eyes, the glasses can predict eye movements and dynamically position information accordingly. This allows for the effective display of important information using eye-tracking data.

[0084] The Glass unit can analyze the operator's past operation history and automatically generate the optimal information display layout. For example, the Glass unit can generate a layout that prioritizes displaying information frequently used by the operator in the past. Furthermore, the Glass unit can analyze the operator's operation patterns and suggest an efficient information display layout. In addition, the Glass unit can generate customized layouts based on the operator's past operation history, tailored to specific situations. This allows for the provision of efficient information display layouts by analyzing past operation history.

[0085] The glasses unit can estimate the operator's emotions and adjust the frequency of information display based on the estimated emotions. For example, if the operator is stressed, the glasses unit can reduce the frequency of information display to alleviate visual strain. Conversely, if the operator is relaxed, the glasses unit can increase the frequency of information display to improve work efficiency. Furthermore, if the operator is focused, the glasses unit can frequently display important information to improve work accuracy. In this way, visual strain can be reduced by adjusting the frequency of information display according to the operator's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0086] The glasses unit can prioritize the display of relevant geographic information, taking into account the operator's geographical location. For example, if the operator is in a specific area, the glasses unit will prioritize the display of information related to that area. Furthermore, if the operator is on the move, the glasses unit can display real-time geographic information based on their current location. In addition, the glasses unit can automatically display information related to a specific point as the operator approaches it. This prioritizes the display of geographic information, thereby supporting the operator's decision-making.

[0087] The Glasses unit can analyze the operator's social media activity and display relevant information. For example, it can display relevant news and data based on information the operator has shared on social media. It can also prioritize displaying information shared by the operator's social media followers and friends. Furthermore, it can analyze the operator's social media activity history and display information of interest. This allows for the effective display of relevant information by analyzing social media activity.

[0088] The sensor unit can estimate the operator's emotions and adjust the method of analyzing EEG data based on the estimated emotions. For example, if the operator is tense, the sensor unit can perform EEG data analysis to promote relaxation. It can also perform EEG data analysis to enhance concentration if the operator is relaxed. Furthermore, if the operator is tired, the sensor unit can perform EEG data analysis to encourage rest. This allows for more appropriate support through EEG data analysis tailored to the operator's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0089] The sensor unit can analyze the operator's brainwave data in real time, detect a decline in concentration, and display a warning. For example, the sensor unit can detect a decline in concentration from the operator's brainwave data and display a visual warning. The sensor unit can also analyze the operator's brainwave data in real time and provide an audible warning. Furthermore, the sensor unit can provide a warning through haptic feedback based on the operator's brainwave data. This allows for the detection of a decline in concentration in real time and the display of warnings, thereby maintaining the operator's performance.

[0090] The sensor unit can collect operator EEG data over a long period and learn the characteristics of each individual operator. For example, the sensor unit can collect operator EEG data over several months and learn their characteristics. Furthermore, the sensor unit can analyze the operator's EEG data and provide support based on their individual characteristics. In addition, the sensor unit can collect operator EEG data over a long period and use it to improve performance. This allows for the provision of optimal support to each individual operator through long-term data collection.

[0091] The sensor unit can estimate the operator's emotions and adjust the frequency of EEG data collection based on the estimated emotions. For example, if the operator is tense, the sensor unit increases the frequency of EEG data collection and performs a more detailed analysis. Conversely, if the operator is relaxed, the sensor unit can decrease the frequency of EEG data collection to reduce their burden. Furthermore, if the operator is fatigued, the sensor unit can adjust the frequency of EEG data collection to provide appropriate support. This allows for more appropriate support by adjusting the data collection frequency according to the operator's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0092] The sensor unit can analyze the operator's physical movements and brainwave data in combination to perform more accurate state assessments. For example, the sensor unit can evaluate the operator's concentration level by combining the operator's physical movements and brainwave data. It can also evaluate stress levels by analyzing the operator's physical movements and brainwave data. Furthermore, the sensor unit can evaluate fatigue levels by combining the operator's physical movements and brainwave data. In this way, combining physical movements and brainwave data enables highly accurate state assessments.

[0093] The sensor unit can analyze the operator's ambient sounds and identify stressors by correlating them with electroencephalogram (EEG) data. For example, the sensor unit can analyze the operator's ambient sounds and identify stressors by correlating them with EEG data. Furthermore, the sensor unit can evaluate stress levels by combining the operator's ambient sounds and EEG data. In addition, the sensor unit can analyze the operator's ambient sounds and identify factors contributing to decreased concentration by correlating them with EEG data. This makes it easier to identify stressors by correlating ambient sounds with EEG data.

[0094] The suit can estimate the operator's emotions and adjust the intensity of haptic feedback based on the estimated emotions. For example, if the operator is tense, the suit can reduce the intensity of haptic feedback to promote relaxation. Conversely, if the operator is relaxed, the suit can increase the intensity of haptic feedback to enhance concentration. Furthermore, if the operator is tired, the suit can adjust the intensity of haptic feedback to encourage rest. This allows for more appropriate support by adjusting the intensity of haptic feedback according to the operator's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0095] The suit unit can analyze the operator's movement data in real time and provide optimal haptic feedback. For example, the suit unit can analyze the operator's movement data in real time and provide haptic feedback. Furthermore, the suit unit can adjust the optimal haptic feedback in real time based on the operator's movement data. In addition, the suit unit can analyze the operator's movement data and optimize the timing of the haptic feedback. This allows for the provision of optimal haptic feedback by analyzing movement data in real time.

[0096] The suit unit can analyze an operator's past feedback history and generate an optimal feedback pattern for each individual operator. For example, the suit unit can analyze an operator's past feedback history and generate an optimal feedback pattern. Furthermore, the suit unit can provide feedback patterns tailored to individual characteristics based on the operator's feedback history. In addition, the suit unit can analyze an operator's past feedback history and use that information to improve performance. This allows for the provision of optimal feedback to each individual operator by analyzing past feedback history.

[0097] The suit unit can estimate the operator's emotions and adjust the timing of haptic feedback based on the estimated emotions. For example, if the operator is tense, the suit unit can adjust the timing of haptic feedback to promote relaxation. It can also adjust the timing of haptic feedback to enhance concentration if the operator is relaxed. Furthermore, if the operator is tired, the suit unit can adjust the timing of haptic feedback to encourage rest. This allows for more appropriate support through the adjustment of haptic feedback timing according to the operator's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0098] The suit can monitor the operator's physical condition and provide haptic feedback as needed. For example, the suit can monitor the operator's physical condition and provide haptic feedback as needed. The suit can also adjust the intensity of the haptic feedback based on the operator's physical condition. Furthermore, the suit can monitor the operator's physical condition and provide haptic feedback at the appropriate time. This allows for the provision of haptic feedback as needed by monitoring the operator's physical condition.

[0099] The suit unit can change the type of haptic feedback depending on the operator's work environment. For example, the suit unit can change the type of haptic feedback depending on the operator's work environment. Furthermore, the suit unit can provide optimal haptic feedback based on the operator's work environment. In addition, the suit unit can customize the haptic feedback pattern according to the operator's work environment. This allows for more appropriate support by changing the type of haptic feedback according to the work environment.

[0100] The support unit can estimate the operator's emotions and adjust the support content based on the estimated emotions. For example, if the operator is tense, the support unit can provide support to promote relaxation. If the operator is relaxed, the support unit can also provide support to enhance concentration. Furthermore, if the operator is tired, the support unit can provide support to encourage rest. This allows for more appropriate support to be provided by adjusting the support content according to the operator's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0101] The support unit can analyze sensor data in real time and provide optimal information to support the operator's decision-making. For example, the support unit can analyze sensor data in real time and provide optimal information to support the operator's decision-making. Furthermore, the support unit can provide visual information based on sensor data to support the operator's decision-making. In addition, the support unit can analyze sensor data in real time and provide voice guidance to support the operator's decision-making. This allows for support of operator decision-making by analyzing sensor data in real time.

[0102] The support unit can analyze system logs over a long period of time, predict future problems, and display warnings in advance. For example, the support unit can analyze system logs over a long period of time, predict future problems, and display visual warnings. It can also predict future problems based on system logs and provide voice warnings. Furthermore, the support unit can analyze system logs over a long period of time, predict future problems, and provide warnings through haptic feedback. In this way, by analyzing system logs over a long period of time, it is possible to predict future problems and display warnings in advance.

[0103] The support unit can estimate the operator's emotions and determine the priority of support based on the estimated emotions. For example, if the operator is tense, the support unit will prioritize support that promotes relaxation. If the operator is relaxed, the support unit can also prioritize support that enhances concentration. Furthermore, if the operator is tired, the support unit can prioritize support that promotes rest. This allows for the provision of more appropriate support by prioritizing support according to the operator's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0104] The support department can analyze the operator's past operation history and provide the optimal support method. For example, the support department can analyze the operator's past operation history and provide the optimal support method. Furthermore, the support department can provide support methods tailored to the individual characteristics of each operator based on their operation history. In addition, the support department can analyze the operator's past operation history and propose efficient support methods. Thus, by analyzing past operation history, the support department can provide the optimal support method.

[0105] The support department can customize the support provided according to the operator's work environment. For example, the support department can customize the support provided based on the operator's work environment. Furthermore, the support department can provide optimal support based on the operator's work environment. In addition, the support department can adjust the priority of support based on the operator's work environment. This allows for more appropriate support to be provided through customized support tailored to the work environment.

[0106] The preparation unit can estimate the operator's emotions and adjust the information presentation method based on the estimated emotions. For example, if the operator is tense, the preparation unit can provide a simple and highly visible information presentation method. If the operator is relaxed, the preparation unit can also provide a presentation method that includes detailed information. Furthermore, if the operator is tired, the preparation unit can provide an information presentation method that reduces visual burden. This allows for more appropriate support by adjusting the information presentation method according to the operator's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0107] The preparation unit can adjust the level of detail of information to the optimal level based on the operator's experience level. For example, if the operator has a high level of experience, the preparation unit will provide detailed information. Conversely, if the operator has a low level of experience, the preparation unit can provide basic information. Furthermore, the preparation unit can dynamically adjust the level of detail of information according to the operator's experience level. This allows for more appropriate support to be provided by adjusting the level of detail of information according to the experience level.

[0108] The preparation unit can change the information presentation format according to the operator's cognitive style. For example, if the operator's cognitive style is visual, the preparation unit will provide a graphical information presentation format. Furthermore, if the operator's cognitive style is auditory, the preparation unit can also provide information verbally. In addition, the preparation unit can dynamically change the information presentation format according to the operator's cognitive style. This allows for more appropriate support to be provided by changing the information presentation format according to the cognitive style.

[0109] The preparation unit can estimate the operator's emotions and adjust the timing of information presentation based on the estimated emotions. For example, if the operator is tense, the preparation unit can adjust the timing of information presentation to encourage relaxation. It can also adjust the timing of information presentation to enhance concentration if the operator is relaxed. Furthermore, if the operator is tired, the preparation unit can adjust the timing of information presentation to encourage rest. This allows for more appropriate support by adjusting the timing of information presentation according to the operator's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0110] The preparation department can monitor the operator's physical and mental state and delay the presentation of information as needed. For example, the preparation department can monitor the operator's physical and mental state and delay the presentation of information as needed. Furthermore, the preparation department can adjust the timing of information presentation based on the operator's physical and mental state. In addition, the preparation department can monitor the operator's physical and mental state and present information at the appropriate time. This allows for more appropriate support to be provided by delaying information presentation according to the operator's physical and mental state.

[0111] The preparation unit can customize the information presented according to the operator's work environment. For example, the preparation unit can customize the information presented according to the operator's work environment. Furthermore, the preparation unit can provide optimal information based on the operator's work environment. In addition, the preparation unit can adjust the priority of the information presented according to the operator's work environment. This allows for more appropriate support through the customization of information presented according to the work environment.

[0112] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0113] The AISO system can also be equipped with a rhythm adjustment unit that monitors the operator's biological rhythms and proposes optimal work timings. For example, the rhythm adjustment unit analyzes the operator's heart rate, body temperature, and sleep patterns to suggest optimal work start times and rest periods. Furthermore, the rhythm adjustment unit can automatically generate a schedule to maximize work efficiency based on the operator's biological rhythms. In addition, the rhythm adjustment unit can adjust the priority of tasks according to the operator's biological rhythms, providing an optimal work flow. This enables an efficient work environment through work suggestions based on the operator's biological rhythms.

[0114] The AISO system can also include a music provider that estimates the operator's emotions and selects music based on those emotions. For example, if the operator is stressed, the music provider will play relaxing music. It can also select music to restore energy if the operator is tired. Furthermore, if the operator is concentrating, the music provider can provide music to maintain concentration. This allows for the optimization of the work environment through music tailored to the operator's emotions.

[0115] The AISO system can also be equipped with an ergonomics adjustment unit that analyzes the operator's movements and proposes optimal ergonomics. For example, the ergonomics adjustment unit analyzes the operator's posture and movement patterns and proposes the optimal working posture. Furthermore, the ergonomics adjustment unit can optimize the layout of the work environment based on the operator's movement data. In addition, the ergonomics adjustment unit can analyze the operator's movement history and propose ergonomic improvements to reduce fatigue from prolonged work. This allows for improved work efficiency and comfort through ergonomic suggestions based on operator movement analysis.

[0116] The AISO system can also include a lighting adjustment unit that estimates the operator's emotions and adjusts the lighting environment based on those emotions. For example, if the operator is stressed, the lighting adjustment unit can provide warm-colored lighting to promote relaxation. It can also provide eye-friendly lighting if the operator is tired. Furthermore, if the operator is concentrating, it can provide bright lighting to maintain concentration. This allows for the optimization of the work environment by adjusting the lighting environment according to the operator's emotions.

[0117] The AISO system can also include an aromatherapy unit that estimates the operator's emotions and provides scents based on those emotions. For example, if the operator is stressed, the aromatherapy unit can provide a relaxing lavender scent. If the operator is tired, it can provide a mint scent to restore energy. Furthermore, if the operator is concentrating, it can provide a rosemary scent to maintain concentration. This allows for the optimization of the work environment by providing scents tailored to the operator's emotions.

[0118] The AISO system can also include a tool suggestion unit that proposes the most suitable tools and resources according to the operator's work. For example, the tool suggestion unit can suggest the optimal tools and resources when the operator is performing a specific task. Furthermore, the tool suggestion unit can analyze the operator's past work history and suggest efficient tool usage methods. In addition, the tool suggestion unit can suggest the optimal tool placement according to the operator's work environment. This allows for improved work efficiency through tool suggestions tailored to the operator's work.

[0119] The AISO system can also include a communication adjustment unit that estimates the operator's emotions and adjusts the communication method based on those emotions. For example, if the operator is tense, the communication adjustment unit may encourage communication in a relaxed tone. It can also encourage concise and clear communication if the operator is tired. Furthermore, if the operator is focused, the communication adjustment unit may suggest efficient communication methods. This allows for effective communication by adjusting the communication method according to the operator's emotions.

[0120] The AISO system can also be equipped with an environmental control unit that monitors the operator's work environment and maintains optimal temperature and humidity. For example, the environmental control unit monitors the temperature and humidity of the operator's work environment in real time and maintains optimal conditions. Furthermore, the environmental control unit can adjust the temperature and humidity according to the operator's work. In addition, the environmental control unit can customize the work environment based on the operator's individual preferences. This optimizes the temperature and humidity of the work environment, thereby improving operator comfort and efficiency.

[0121] The AISO system can also include a break suggestion unit that estimates the operator's emotions and suggests break timings based on those emotions. For example, if the operator is stressed, the break suggestion unit may suggest a break to relax. It can also suggest a break to restore energy if the operator is tired. Furthermore, if the operator is concentrating, the break suggestion unit may suggest a short break to maintain concentration. This allows for the maintenance of work efficiency and health by providing break suggestions tailored to the operator's emotions.

[0122] The AISO system can also include a performance evaluation unit that assesses and provides feedback on the operator's work performance. For example, the performance evaluation unit analyzes the operator's work data and evaluates their performance. Furthermore, the performance evaluation unit can suggest areas for improvement based on the operator's past performance data. In addition, the performance evaluation unit can monitor the operator's work performance in real time and provide immediate feedback. This allows for the evaluation of the operator's work performance and facilitates improvement.

[0123] The following briefly describes the processing flow for example form 2.

[0124] Step 1: The glasses unit is equipped with XR glasses and provides visual information to the operator. For example, the glasses unit can use the operator's eye-tracking data to center the most important information in the field of view. The glasses unit can also estimate the operator's emotions and adjust the color tone and brightness of the displayed information based on the estimated emotions of the operator. Furthermore, the glasses unit can analyze the operator's past operation history and automatically generate the optimal information display layout. Step 2: The sensor unit is equipped with an electroencephalogram (EEG) sensor and collects the operator's EEG data. For example, the sensor unit can analyze the operator's EEG data in real time, detect a decrease in concentration, and display a warning. The sensor unit can also collect the operator's EEG data over a long period of time and learn the characteristics of each individual operator. Furthermore, the sensor unit can estimate the operator's emotions and adjust the frequency of EEG data collection based on the estimated emotions of the operator. Step 3: The suit unit is equipped with a haptic feedback suit and provides haptic feedback to the operator. For example, the suit unit can estimate the operator's emotions and adjust the intensity of the haptic feedback based on the estimated emotions. The suit unit can also analyze the operator's motion data in real time and provide optimal haptic feedback. Furthermore, the suit unit can analyze the operator's past feedback history and generate the optimal feedback pattern for each individual operator. Step 4: The support unit uses the generated AI to provide real-time support based on data collected by the glasses unit, sensor unit, and suit unit. For example, the support unit can use the generated AI to analyze sensor data and system logs to understand the current situation and predict future developments. The support unit can also use the generated AI to estimate the operator's emotions and adjust the support content based on the estimated emotions. Furthermore, the support unit can use the generated AI to analyze system logs over a long period of time, predict future problems, and display warnings in advance. Step 5: Based on the support provided by the support team, the preparation team anticipates the operator's intentions and prepares necessary information and options in advance. For example, the preparation team can use generative AI to present information in the most effective way, based on the operator's experience level, cognitive style, and current mental and physical state. The preparation team can also use generative AI to generate an intuitive interface that combines voice, visual, and tactile elements. Furthermore, the preparation team can use generative AI to analyze system usage data and continuously evolve to suit individual operators and specific operating environments.

[0125] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0126] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0127] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0128] Each of the multiple elements described above, including the glasses unit, sensor unit, suit unit, support unit, and preparation unit, is implemented by, for example, at least one of the smart device 14 and the data processing unit 12. For example, the glasses unit provides visual information to the operator using the display 40A of the smart device 14. The sensor unit collects the operator's brainwave data using the camera 42 and microphone 38B of the smart device 14. The suit unit provides haptic feedback using the control unit 46A of the smart device 14. The support unit provides support in real time through AI generated by the specific processing unit 290 of the data processing unit 12. The preparation unit anticipates the operator's intentions using the specific processing unit 290 of the data processing unit 12 and prepares necessary information and options in advance. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0129] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0130] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0131] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0132] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0133] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0135] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0136] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0137] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0138] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0139] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0140] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0141] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0142] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0143] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0144] Each of the multiple elements described above, including the glasses unit, sensor unit, suit unit, support unit, and preparation unit, is implemented in, for example, at least one of the smart glasses 214 and the data processing unit 12. For example, the glasses unit provides visual information to the operator using the display of the smart glasses 214. The sensor unit collects the operator's brainwave data using the camera 42 and microphone 238 of the smart glasses 214. The suit unit provides haptic feedback using the control unit 46A of the smart glasses 214. The support unit provides support in real time through AI generated by the specific processing unit 290 of the data processing unit 12. The preparation unit anticipates the operator's intentions using the specific processing unit 290 of the data processing unit 12 and prepares necessary information and options in advance. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0145] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0146] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0147] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0148] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0149] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0150] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0151] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0152] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0153] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0154] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0155] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0156] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0157] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0158] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0159] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0160] Each of the multiple elements described above, including the glasses unit, sensor unit, suit unit, support unit, and preparation unit, is implemented in at least one of the following: a headset terminal 314 and a data processing unit 12. For example, the glasses unit provides visual information to the operator using the display 343 of the headset terminal 314. The sensor unit collects the operator's brainwave data using the camera 42 and microphone 238 of the headset terminal 314. The suit unit provides haptic feedback using the control unit 46A of the headset terminal 314. The support unit provides real-time support through AI generated by the specific processing unit 290 of the data processing unit 12. The preparation unit anticipates the operator's intentions using the specific processing unit 290 of the data processing unit 12 and prepares necessary information and options in advance. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0161] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0162] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0163] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0164] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0165] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0166] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0167] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0168] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0169] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0170] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0171] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0172] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0173] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0174] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0175] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0176] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0177] Each of the multiple elements described above, including the glasses unit, sensor unit, suit unit, support unit, and preparation unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the glasses unit provides visual information to the operator using the display of the robot 414. The sensor unit collects the operator's brainwave data using the camera 42 and microphone 238 of the robot 414. The suit unit provides tactile feedback using the control unit 46A of the robot 414. The support unit provides real-time support through AI generated by the specific processing unit 290 of the data processing unit 12. The preparation unit anticipates the operator's intentions using the specific processing unit 290 of the data processing unit 12 and prepares necessary information and options in advance. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0178] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0179] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0180] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0181] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0182] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0183] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0184] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0185] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0186] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0187] 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.

[0188] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0189] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0190] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0191] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0192] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0193] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0194] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0195] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0196] (Note 1) The glass part equipped with XR glasses, A sensor unit equipped with an electroencephalogram sensor, A suit equipped with haptic feedback, Based on the data collected by the glasses unit, the sensor unit, and the suit unit, a support unit provides support in real time using a generating AI. The system includes a preparation unit that, based on the support provided by the aforementioned support unit, anticipates the operator's intentions and prepares necessary information and options in advance. A system characterized by the following features. (Note 2) The aforementioned support unit, Generative AI analyzes sensor data and system logs to understand the current situation and predict future developments. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned preparation unit is The AI ​​generates information to present it in the most effective way, based on the operator's experience level, cognitive style, and current mental and physical state. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned preparation unit is Generative AI generates intuitive interfaces that combine voice, sight, and touch. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned preparation unit is The generated AI analyzes system usage data and constantly evolves to suit individual operators and specific operating environments. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned preparation unit is The AI ​​generates VR training scenarios that precisely replicate actual operating environments, supporting the improvement of operators' skills. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned preparation unit is Generative AI enables advanced AI processing on wearable devices, resulting in a low-latency and secure operating environment. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned glass portion is The system estimates the operator's emotions and adjusts the color tone and brightness of the displayed information based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned glass portion is By using the operator's eye-tracking data, the most important information is placed at the center of their field of vision. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned glass portion is The system analyzes the operator's past operation history and automatically generates the optimal information display layout. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned glass portion is The system estimates the operator's emotions and adjusts the frequency of information display based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned glass portion is Considering the operator's geographical location, relevant geographical information will be displayed preferentially. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned glass portion is Analyze the operator's social media activity and display relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned sensor unit is The system estimates the operator's emotions and adjusts the EEG data analysis method based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned sensor unit is The system analyzes the operator's brainwave data in real time, detects a decrease in concentration, and displays a warning. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned sensor unit is The system collects operator electroencephalogram (EEG) data over a long period of time to learn the characteristics of each individual operator. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned sensor unit is The system estimates the operator's emotions and adjusts the frequency of EEG data collection based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned sensor unit is By combining and analyzing the operator's physical movements and electroencephalogram (EEG) data, a more accurate assessment of their condition can be performed. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned sensor unit is The system analyzes the operator's ambient sounds and correlates them with electroencephalogram (EEG) data to identify stressors. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned suit part is, The system estimates the operator's emotions and adjusts the intensity of haptic feedback based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned suit part is, It analyzes operator movement data in real time and provides optimal haptic feedback. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned suit part is, Analyze the operator's past feedback history and generate the optimal feedback pattern for each individual operator. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned suit part is, The system estimates the operator's emotions and adjusts the timing of haptic feedback based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned suit part is, The system monitors the operator's physical condition and provides haptic feedback as needed. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned suit part is, The type of haptic feedback can be changed depending on the operator's work environment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned support unit, The system estimates the operator's emotions and adjusts the support provided based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned support unit, It analyzes sensor data in real time and provides optimal information to support operator decision-making. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned support unit, The system analyzes system logs over a long period of time to predict future problems and display warnings in advance. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned support unit, The system estimates the operator's emotions and determines the priority of support based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned support unit, We analyze the operator's past operation history and provide the most suitable support method. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned support unit, Customize the support provided according to the operator's work environment. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned preparation unit is The system estimates the operator's emotions and adjusts the way information is presented based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned preparation unit is Adjust the level of detail in the information to the optimal level based on the operator's experience level. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned preparation unit is The format of information presentation is changed according to the operator's cognitive style. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned preparation unit is The system estimates the operator's emotions and adjusts the timing of information presentation based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned preparation unit is Monitor the operator's physical and mental state and delay the presentation of information if necessary. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned preparation unit is Customize the information presented according to the operator's work environment. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0197] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The glass part equipped with XR glasses, A sensor unit equipped with an electroencephalogram sensor, A suit equipped with haptic feedback, Based on the data collected by the glasses unit, the sensor unit, and the suit unit, a support unit provides support in real time using generated AI. The system includes a preparation unit that, based on the support provided by the aforementioned support unit, anticipates the operator's intentions and prepares necessary information and options in advance. A system characterized by the following features.

2. The aforementioned support unit, The AI ​​generates data and analyzes sensor data and system logs to understand the current situation and predict future developments. The system according to feature 1.

3. The aforementioned preparation unit is The AI ​​generates information to present it in the most effective way, based on the operator's experience level, cognitive style, and current mental and physical state. The system according to feature 1.

4. The aforementioned preparation unit is Generative AI generates intuitive interfaces that combine voice, sight, and touch. The system according to feature 1.

5. The aforementioned preparation unit is The generated AI analyzes system usage data and constantly evolves to suit individual operators and specific operating environments. The system according to feature 1.

6. The aforementioned preparation unit is By using AI-generated scenarios, we create VR training scenarios that precisely reproduce actual operating environments, supporting the improvement of operators' skills. The system according to feature 1.

7. The aforementioned preparation unit is Generative AI enables advanced AI processing on wearable devices, resulting in a low-latency and secure operating environment. The system according to feature 1.

8. The aforementioned glass portion is The system estimates the operator's emotions and adjusts the color tone and brightness of the displayed information based on the estimated emotions. The system according to feature 1.

9. The aforementioned glass portion is By using the operator's eye-tracking data, the most important information is placed at the center of their field of vision. The system according to feature 1.

10. The aforementioned glass portion is The system analyzes the operator's past operation history and automatically generates the optimal information display layout. The system according to feature 1.

Images