system

Abstract

We provide the system. [Solution] A means of generating emergency response scenarios using generative artificial intelligence, A means for constructing a virtual environment based on the aforementioned scenario using virtual reality technology, Means for recording user behavior, A means for evaluating the aforementioned behavior and providing the evaluation results as feedback, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot 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] Current emergency response training is often limited to scenarios based on typical situations and is insufficient for cultivating the ability to handle diverse and unpredictable situations that occur in actual emergencies. In addition, conventional training methods are difficult to provide regular practice opportunities and lack means for users to maintain and improve the knowledge and skills they have acquired. Therefore, there is a need for a training system that can respond to more realistic and diverse situations.

Means for Solving the Problems

[0005] The present invention solves the above problem by providing a system that reproduces diverse emergency response scenarios generated using generative artificial intelligence in a virtual reality environment. Specifically, the system consists of generative artificial intelligence that generates scenarios by referring to a disaster knowledge database, virtual reality technology that constructs a virtual environment based on the generated scenarios, technology that records user actions in real time, and technology that evaluates user actions and provides feedback, thereby enabling users to improve their ability to respond flexibly on a daily basis.

[0006] "Generative artificial intelligence" is an artificial intelligence technology that has the ability to generate new patterns and scenarios based on diverse input data.

[0007] "Virtual reality technology" is a technology that uses computers to provide users with a visually and aurally realistic experience.

[0008] A "disaster knowledge database" is a collection of information resources built based on past disaster cases and prediction models, and contains knowledge that is useful when a disaster occurs.

[0009] "Means of recording user behavior" refer to systems and technologies that acquire user movements, choices, and reactions in real time and store them as digital data.

[0010] "Feedback" refers to information and instructions that a system uses to communicate to a user the results of its evaluation of their actions and areas for future improvement. [Brief explanation of the drawing]

[0011] [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. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] 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.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] 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 multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0022] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0024] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0025] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0031] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0032] In implementing this invention, the server, terminal, and user work together to realize emergency response training.

[0033] First, the server accesses a disaster knowledge database and generates an appropriate training scenario, taking into account the user's learning level and past training history. The generated scenario includes the environment and conditions in which the simulation will take place, as well as the challenges that will arise. Based on this data, the server performs detailed configuration and sends it to the terminal.

[0034] Next, the terminal receives scene data sent from the server and constructs a virtual reality environment based on it. The terminal connects to the user's VR device and provides real-time visual and auditory feedback. The user can freely walk around and manipulate objects within this virtual environment. The terminal records the user's movements and choices in detail and sends them to the server.

[0035] Users are required to take actions that correspond to specific situations in the virtual reality space. For example, in a virtual office where an earthquake has occurred, they might take cover under a desk and then exit the building via a safe route. Throughout this process, the device continuously records the user's actions and transmits that data to a server.

[0036] The server evaluates the user's response based on the received behavioral data. The evaluation is based on multiple criteria, including the speed and accuracy of the response and the ability to predict risks, and the results are provided to the user as feedback. This feedback includes what went well, areas for improvement, and guidance on more advanced challenges.

[0037] As a concrete example, in an evacuation route selection scenario, multiple routes are presented, and the user is tested on their ability to choose the appropriate route. Data from the device clarifies the reasons and timing of the selection, and the accuracy of the selection is analyzed. This allows users to objectively understand their own decision-making abilities and improve them.

[0038] Thus, by utilizing generative artificial intelligence and virtual reality technology, the present invention realizes a system that provides users with realistic and diverse training experiences and enhances their ability to respond quickly during disasters.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server accesses the disaster knowledge database and generates a specific training scenario. This includes the training objective, scene setting, and disaster types to consider. Based on this information, detailed scenario data is created and sent to the terminal.

[0042] Step 2:

[0043] The system uses scenario data received by the terminal to construct a virtual reality environment. This is achieved by activating the user's VR device and configuring graphic and audio data. Different environmental settings are configured based on each scenario to recreate realistic disaster situations.

[0044] Step 3:

[0045] The user puts on a VR headset and enters the provided virtual environment. The user activates a training symbol provided by the system (e.g., a start button) to begin training. Following the scenario, the user acts based on the instructions received.

[0046] Step 4:

[0047] When a user performs an action in a virtual environment, the device records its movements and choices in real time. It uses cameras and motion sensors to collect location information and movement data, preparing it for transmission to the server.

[0048] Step 5:

[0049] The server receives data from the terminal and analyzes user behavior by applying an evaluation algorithm. This evaluation is based on criteria such as the appropriateness and efficiency of the user's actions. The evaluation results are generated and prepared as feedback for the next step.

[0050] Step 6:

[0051] The server generates feedback and sends it to the terminal, communicating the details to the user. The terminal displays the feedback results and areas for future improvement on the screen in text and audio format. This allows the user to confirm the results of their training and improve their motivation for future training.

[0052] (Example 1)

[0053] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0054] The present invention aims to efficiently improve users' ability to respond quickly and appropriately in disasters and emergencies. Conventional training systems have had difficulty providing realistic feedback, which has prevented them from maximizing user learning effectiveness. Furthermore, they have the problem of not providing flexible training that can handle multiple disaster scenarios.

[0055] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0056] In this invention, the server includes means for generating emergency response scenarios using generative artificial intelligence, means for generating the scenarios by referring to a disaster knowledge database and considering the learning history, and means for constructing a virtual environment based on the scenarios using virtual reality technology and providing feedback to the user. This allows the user to experience training based on realistic and diverse situations, and effectively improve their reaction ability and judgment.

[0057] "Generative artificial intelligence" is an intelligent system that automatically generates new information and scenarios using past data and specific algorithms.

[0058] A "disaster knowledge database" is an information repository that stores information, countermeasures, and past case studies related to various disasters, allowing that information to be retrieved and used as needed.

[0059] "Virtual reality technology" is a technology that uses computers to allow users to experience virtual environments and situations, providing simulated experiences through senses such as sight and hearing.

[0060] "Feedback" refers to providing evaluations and advice regarding a user's actions and choices, and offering information to help them improve their next actions.

[0061] "Learning history" refers to a record of training and activities a user has undertaken in the past, and is used to set the content of the next training and to track progress.

[0062] "Real-time" refers to a state in which processing and feedback are performed immediately while an event is occurring.

[0063] This invention involves a server, terminals, and users working together to realize an emergency response training system.

[0064] The server first uses a generative AI model to access a disaster knowledge database, and then generates an appropriate training scenario considering the user's past learning and training history. The generated scenario includes situations that will be reproduced in the virtual environment and tasks that the user should address. The server then structures this scenario data and transfers it to the terminal.

[0065] The terminal uses scenario data received from the server to construct a scenario-based virtual environment using virtual reality technology. The terminal interacts with the user's VR equipment to provide real-time visual and auditory feedback that the user can experience. The terminal also meticulously records the user's movements and choices and transmits this information to the server.

[0066] The user acts according to a generated scenario within the virtual environment provided by the device. This action could include, for example, evacuation procedures during an earthquake. A specific example is a scenario where the user learns how to safely evacuate a virtual office during an earthquake. In this scenario, the user would take cover under a desk and then exit the building via a safe route. An example of a prompt might be, "Generate a scenario for the user to learn how to safely evacuate from the office."

[0067] This system allows users to realistically experience various emergency response training scenarios and improve their rapid response capabilities.

[0068] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0069] Step 1:

[0070] The server accesses a disaster knowledge database and retrieves the user's learning history and past training history as input data. Based on this information, the generative AI model generates prompts and automatically creates appropriate training scenarios. The data calculations here involve extracting conditions from the input data and setting the optimal scenario parameters. Detailed configuration data for the scenario is generated as output.

[0071] Step 2:

[0072] The server sends the generated scenario data to the terminal. The input is the training scenario and its associated data created in step 1. This data is filtered in detail and converted into a format that the terminal can interpret, as it forms the basis for building the virtual reality environment. Structured data that the terminal can receive is sent as output.

[0073] Step 3:

[0074] The terminal constructs a virtual reality environment based on scenario data received from the server. The input is structured data sent from the server. The terminal uses VR equipment to provide the user with real-time visual and auditory feedback, rendering this data in 3D space and preparing an environment that the user can experience interactively. The output is the virtual environment that is actually displayed in the user's field of vision.

[0075] Step 4:

[0076] The user performs actions based on training scenarios within a virtual reality environment provided by the device. Input consists of the user's own physical movements and choices. The user takes specific actions within the virtual scenario, practicing things like evacuation procedures during an earthquake. The device records these actions and compiles them as data. Output is the user's behavioral data.

[0077] Step 5:

[0078] The terminal sends data to the server that records the user's actions in detail. The input is the user's behavior data accumulated in step 4. The terminal formats this data into a specific format and sends it to the server. As output, the behavior data is provided in a format that the server can analyze.

[0079] Step 6:

[0080] The server analyzes behavioral data received from the terminal and evaluates the user's response. The input is behavioral data sent from the terminal. The server comprehensively evaluates the speed, accuracy, and judgment of the response and generates analysis results. The output is evaluation and feedback information returned to the user, which allows the user to identify areas for improvement for the next training session.

[0081] (Application Example 1)

[0082] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0083] In modern times, there is a need to improve disaster preparedness awareness and strengthen emergency response capabilities. However, traditional training methods cannot fully replicate actual disaster situations, making effective skill improvement difficult. In addition, there is the challenge of providing individualized support tailored to each person's situation and past experience. Furthermore, there is a lack of objective evaluation of training results and feedback on their effectiveness, which hinders the continuous improvement of training.

[0084] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0085] In this invention, the server includes means for generating emergency response scenarios using generative artificial intelligence, means for constructing a virtual environment based on the scenarios using virtual reality and augmented reality technologies, and means for analyzing user behavior in real time using a mobile information terminal and recording user behavior through an information processing device. This enables the provision of individually tailored training to users in a virtual environment, as well as real-time behavioral analysis and feedback.

[0086] "Generative artificial intelligence" is an artificial intelligence technology that uses data and algorithms to generate information that is appropriate to the situation and requirements.

[0087] An "emergency response scenario" is a plan that outlines hypothetical cases and situations requiring necessary actions and decisions during a disaster or emergency.

[0088] "Virtual reality technology" is a technology that uses computer technology to allow users to experience a simulation of an environment that closely resembles reality.

[0089] Augmented reality technology is a technology that overlays digital information onto the real environment, providing users with a combination of reality and virtual reality.

[0090] A "mobile information terminal" is a portable computer device that can be used while on the go, and generally includes smartphones and tablets.

[0091] An "information processing device" is a computer system used for collecting, processing, storing, and analyzing data.

[0092] "Means of analyzing user behavior in real time" refers to methods and technologies for instantly recognizing user actions and performing analysis based on those actions.

[0093] A "database management system" is a software system for efficiently managing, searching, and updating data.

[0094] To implement this invention, a system is constructed in which a server, a terminal, and a user cooperate to conduct disaster prevention training. The server utilizes a generation AI model to generate emergency response scenarios from a disaster knowledge database based on the user's learning level and past training history. These scenarios specifically describe the environment and situation in which the simulation will be conducted, as well as the challenges the user will face. The server then configures these generated scenarios in detail and transmits them to the terminal.

[0095] The terminal constructs a virtual reality and augmented reality environment based on the received scene data. The terminal interacts with the user's mobile information device (e.g., smartphone or tablet) to provide real-time visual and auditory feedback. Unity is used to construct the environment, and internet services such as AWS (registered trademark) are used for data management. The user moves freely within this virtual or augmented reality environment to conduct disaster response training. The user's movements and choices are recorded in detail through an information processing device and transmitted to a server.

[0096] The server thoroughly evaluates the user's responses based on the received behavioral data. Evaluation criteria include the speed and accuracy of reactions, and the ability to predict risks. The evaluation results are provided to the user as feedback, guiding them to identify successes, areas for improvement, and to take on more advanced challenges. Through this feedback, users can gradually strengthen their response capabilities, increasing their ability to take swift and accurate action in actual disaster situations.

[0097] As a concrete example, when a user trains at home, the device scans the living space and provides a fire simulation. Through the application, the user trains by selecting the correct evacuation route and checking emergency supplies. In this process, the device records the user's actions and provides feedback, pointing out incorrect choices and suggesting areas for improvement, which can be used to improve future training.

[0098] An example of a prompt message might be: "Generate a scenario for disaster evacuation training. The user is in their 30s and has intermediate-level training experience. They are training with two family members. Focus on evacuation route selection and first aid."

[0099] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0100] Step 1:

[0101] The server uses a generation AI model to input prompts and references a disaster knowledge database. These prompts reflect the user's training history and current learning level. The AI ​​model extracts appropriate information from the database and generates emergency response scenarios. As output, a training scenario tailored to the user is created.

[0102] Step 2:

[0103] Based on the generated scenario, the server meticulously constructs the necessary configuration data for the virtual environment. This includes environmental parameters and simulation conditions for training. This data is then prepared for transmission to the terminal, and the configuration data is sent to the terminal as output.

[0104] Step 3:

[0105] The terminal uses configuration data received from the server to build a virtual reality and augmented reality environment. Unity is used to prepare the scenario that the user will experience. The input includes the scenario and configuration data, and the output is the virtual environment provided to the user.

[0106] Step 4:

[0107] The user begins training in a virtual reality environment via a device. The user works on tasks while freely performing their own movements and actions. Inputs include the user's real-time movements and choices, and output is user experience data, which is recorded on the device.

[0108] Step 5:

[0109] The terminal analyzes user behavior data in real time and transmits that data to the server via an information processing device. Inputs include user movements, choices, and generated experience data, and output is analyzed behavior data.

[0110] Step 6:

[0111] The server evaluates the user's response based on the received behavioral data. An evaluation algorithm is used to analyze reaction speed, accuracy, and judgment ability. The input is the analyzed behavioral data, and the output is the evaluation result.

[0112] Step 7:

[0113] The server uses the evaluation results to provide feedback to the user. This feedback includes areas for improvement and advice for future challenges. The input is the evaluation results, and the output is feedback information sent to the user. The user then uses this feedback to improve their skills.

[0114] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0115] This invention is a system that combines generative artificial intelligence, virtual reality technology, and means for recording user behavior and emotions, and is particularly intended to provide feedback that takes user emotions into account in emergency response training.

[0116] First, the server accesses a disaster knowledge database and generates an emergency response scenario. This includes setting up a specific disaster scene and situation. Based on this scenario, specific data is generated to build a virtual reality environment. This data includes environment settings, voice instructions, and simulation parameters. The server then sends this data to the terminal.

[0117] The device sets up a virtual reality environment based on the received scenario data and provides visual and auditory feedback to help the user immerse themselves. The user can then enter the virtual environment using VR equipment. Here, the emotion engine is activated, collecting data on the user's facial expressions, voice, and body sensors in real time to analyze their emotional state. This information is used to measure the user's stress level and sense of security.

[0118] Based on training scenarios, users take specific actions within a virtual environment. During this time, the terminal meticulously records the user's actions and transmits them to the server along with the inputted emotion data. The training process includes a function that recognizes the user's confusion or anxiety, for example, when selecting an evacuation route, and reflects this in the training results.

[0119] The server comprehensively analyzes behavioral and emotional data to assess the user's coping abilities. This assessment includes identifying appropriate behaviors under emotional pressure and areas for improvement. Based on the assessment, the server generates feedback and sends it to the terminal to provide points to consider and effective coping strategies for future training.

[0120] As a concrete example, in a flood evacuation scenario, the emotion engine evaluates how users react to a sudden rise in water levels from an emotional perspective. As a result, by providing feedback on whether users tend to panic or respond calmly, it is possible to suggest useful measures for actual emergencies.

[0121] Thus, the present invention realizes a system that provides more realistic and effective emergency response training by considering not only user behavior but also emotional data.

[0122] The following describes the processing flow.

[0123] Step 1:

[0124] The server accesses a disaster knowledge database and generates emergency response scenarios. These include the type of disaster, environmental conditions, and the difficulty level of the training. The server then prepares to send the generated scenario data to the terminal.

[0125] Step 2:

[0126] The device constructs a virtual reality environment based on the scenario data it receives. It works in conjunction with the user's VR equipment to provide an immersive experience through sight, sound, and touch. The device completes the environment setup according to the scenario.

[0127] Step 3:

[0128] The user puts on a VR headset and enters the training environment. The emotion engine starts up and prepares to sense data such as the user's facial expressions, voice, and heart rate. The user then begins to act according to the scenario.

[0129] Step 4:

[0130] The device records the user's behavior in the virtual environment. Simultaneously, the emotion engine analyzes the user's emotional state in real time and collects data. Synchronization between behavioral and emotional data is maintained.

[0131] Step 5:

[0132] The server receives behavioral and emotional data transmitted from the terminal. An evaluation algorithm is applied to comprehensively assess the appropriateness of the behavior and the emotional response. Evaluation results based on the user's performance are then generated.

[0133] Step 6:

[0134] The server sends the generated evaluation results and feedback information to the terminal. The terminal presents this information to the user visually and audibly, reporting successes and areas for improvement. It also communicates future countermeasures and training plans.

[0135] Step 7:

[0136] The user reviews the feedback provided and adjusts their response for the next training session. Based on the feedback from the emotional engine, they prepare to further improve their ability by improving their emotional control and response methods.

[0137] (Example 2)

[0138] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0139] In emergency response training, there is a challenge in providing realistic feedback that takes into account not only the user's actions but also their emotional state. Conventional systems are limited to recording the user's physical actions and are unable to collect and analyze the emotional data necessary to improve the effectiveness of the training. As a result, training that can accurately predict how users will react in a real emergency has not been provided.

[0140] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0141] In this invention, the server includes means for generating emergency response scenarios using generative AI, means for constructing a virtual environment based on the scenarios using virtual reality technology, and means for recording user behavior and emotional data in real time. This makes it possible to comprehensively evaluate the user's behavior and emotional state and provide more realistic and effective feedback.

[0142] "Generative AI" is a type of artificial intelligence that uses machine learning techniques to generate new information based on specific conditions and data.

[0143] An "emergency response scenario" is a hypothetical scenario created based on specific situations and response procedures in the event of a disaster or emergency.

[0144] "Virtual reality technology" is a system technology that uses computer graphics and sensor technology to provide users with an experience that closely resembles reality.

[0145] "Means of recording in real time" refers to devices and methods that can record a user's state and actions immediately and without delay, and use them for analysis.

[0146] "Emotional data" refers to data that indicates a user's emotional state, and is information obtained based on physiological data such as facial expressions, tone of voice, and heart rate.

[0147] "Feedback" refers to information provided to users regarding evaluations and areas for improvement as a result of training or processing.

[0148] This invention provides a system that offers feedback that takes into account user behavior and emotions during emergency response training. The system utilizes generative AI models, virtual reality technology, and real-time data collection capabilities as its primary technologies.

[0149] The server uses a generative AI model to create scenarios for responding to disasters and emergencies. These scenarios refer to information from a disaster knowledge database and include scenarios that anticipate specific situations and circumstances. Specific examples include scenarios for "floods" and "earthquakes." The created scenario data is transmitted to the terminal in digital format.

[0150] The device uses VR headsets and sensor technology to build a virtual reality environment based on scenario data and provide users with a visual and auditory experience. By immersing themselves in the virtual environment, users can participate in training under conditions that simulate actual emergencies.

[0151] As users train in a VR space, the device collects user behavioral and emotional data in real time. Emotional data is obtained from the user's facial expressions, changes in voice, and physical indicators such as heart rate. This data is used to evaluate how users react under stress.

[0152] The server comprehensively analyzes behavioral and emotional data transmitted from the terminal to evaluate the user's response capabilities. A generative AI model generates feedback based on this information, which is then transmitted to the terminal as the user's training results. This feedback includes specific advice on which actions were effective and which areas need improvement.

[0153] A concrete example of this training is evaluating whether users were able to respond quickly to rising water levels in a flood evacuation scenario. Another example of a prompt is, "Evaluate the user's emotional response in the flood scenario and generate feedback suggesting behavioral improvements." This trains users to respond effectively in real-world emergencies.

[0154] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0155] Step 1:

[0156] The server accesses a disaster knowledge database and generates emergency response scenarios using a generative AI model. It references past disaster data and training records as input to define specific disaster scenarios. During this process, machine learning algorithms are used to output scenarios that the user should train on. Specifically, the server selects scenarios such as "flood," "earthquake," and "fire," and generates data including detailed settings (e.g., rate of water level rise, evacuation route options).

[0157] Step 2:

[0158] The server sends the generated scenario data to the terminal. The generated scenario information is used as input, and the scenario data in digital format is transferred to the terminal as output. Specifically, the server assembles scenario data packets containing various configuration information and sends them to the terminal via the network.

[0159] Step 3:

[0160] The terminal receives scenario data sent from the server and constructs a virtual reality environment. It takes scenario data as input and sets up the 3D virtual environment that the user experiences as output. Specifically, the terminal controls the VR headset, performs 3D modeling in real time, and provides the user with visual and auditory feedback.

[0161] Step 4:

[0162] The user enters a VR environment and begins training. They receive feedback from their device as input, select their own actions as output, and act within the virtual environment. Specifically, the user selects an evacuation route appropriate to the disaster and follows the corresponding procedures.

[0163] Step 5:

[0164] The device records user behavior and emotional data in real time. It collects user behavior and emotional data (e.g., facial expressions, voice, heart rate) as input and stores training data digitally as output. Specifically, the device analyzes and records physiological information using built-in sensors.

[0165] Step 6:

[0166] The server comprehensively analyzes behavioral and emotional data transmitted from the terminal. It receives recorded data as input and generates a numerical output that evaluates the user's ability to respond. Specifically, the server applies statistical algorithms to analyze the data and identify user response patterns.

[0167] Step 7:

[0168] The server generates feedback based on the analysis results and sends it to the terminal. Evaluation data is used as input, and feedback information is generated to be provided to the user as output. Specifically, the server creates a feedback message containing appropriate actions and areas for improvement, which can be used to help the user in their next training session.

[0169] (Application Example 2)

[0170] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0171] Conventional emergency response training systems only evaluated user behavior, failing to consider the emotional state of users during those actions. This meant they couldn't provide realistic training that took into account users' psychological reactions and stress levels during emergencies, potentially leading to ineffective responses in actual emergencies.

[0172] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0173] In this invention, the server includes means for generating emergency response scenarios using generative artificial intelligence, means for constructing a virtual environment based on the scenarios using virtual reality technology, and means for recording the user's behavior and emotions. This makes it possible to comprehensively evaluate the user's behavior and emotions and provide individually optimized feedback.

[0174] "Generative artificial intelligence" is an active algorithm that analyzes data according to a specified purpose and automatically generates appropriate scenarios and information.

[0175] An "emergency response scenario" is a hypothetical situation designed to outline specific procedures and action plans for responding quickly and appropriately to emergencies such as disasters and accidents.

[0176] "Virtual reality technology" is a technology that uses computer simulation techniques to allow users to experience a virtual environment realistically.

[0177] A "virtual environment" is a digital space created through computer simulation that mimics the real world.

[0178] "User behavior" refers to all specific actions and behaviors that a user takes in the virtual or real world.

[0179] A "means of recording emotions" refers to a system that uses sensors and analytical algorithms to record and store a user's emotional state.

[0180] "Individualized feedback" refers to information that provides advice and suggestions for improvement tailored to a specific user, based on analysis of the user's behavior and reactions.

[0181] In this invention, a server generates emergency response scenarios using generative artificial intelligence, and these scenarios are used to construct a virtual environment using virtual reality technology. Specifically, the server refers to a disaster knowledge database to obtain basic information for constructing a detailed scenario. A terminal receives this scenario data and sets up a virtual environment that can be realistically reproduced on a VR device. Through this, the user can receive emergency response training.

[0182] Users wear VR equipment and immerse themselves in a virtual environment, acting according to training scenarios. During this process, an emotion engine analyzes the user's facial expressions, voice data, and data from sensors attached to their body in real time. This allows the system to determine the user's stress level and emotional state. The device then transmits this data to a server, which integrates and analyzes the behavioral and emotional data.

[0183] As a result, the server generates user-optimized feedback and provides points that will be useful for future training. Specifically, if a user becomes frightened or panics during a fire evacuation scenario, the system will advise on safe evacuation methods. An example of a prompt using the generative AI model is, "Generate a fire evacuation scenario, analyze employee sentiment, and generate optimal feedback."

[0184] This system design allows users to receive more practical and effective training, enabling them to acquire the appropriate response skills for emergencies.

[0185] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0186] Step 1:

[0187] The server retrieves necessary information from a disaster knowledge database and generates emergency response scenarios using artificial intelligence. The input is data retrieved from the disaster knowledge database, and the output is specific scenario information. This scenario information includes details such as the type of disaster and its occurrence.

[0188] Step 2:

[0189] The terminal uses virtual reality technology to construct a virtual environment based on scenario information received from the server. The input is the scenario information sent from the server, and the output is the virtual environment that the user can immerse themselves in using a VR device. Specifically, visual and audio elements are incorporated into the VR environment.

[0190] Step 3:

[0191] The user wears VR equipment and acts according to a training scenario within a virtual environment. Input is visual and auditory stimuli from the virtual environment, and output is user behavior data. This behavior data includes motion information such as evacuation direction and speed.

[0192] Step 4:

[0193] The device uses an emotion engine to analyze the user's facial expressions, voice, and data from sensors worn on the body in real time. The input is this emotional data, and the output is an analysis showing the user's stress level and emotional state. Based on the emotional state, feedback in the virtual environment is adjusted accordingly.

[0194] Step 5:

[0195] The device sends collected user behavioral and emotional data to the server. The input is all the data collected by the device, and the output is an integrated dataset received by the server. This dataset comprehensively records the user's responses.

[0196] Step 6:

[0197] The server integrates behavioral and emotional data to generate optimal feedback for the user. The input is the integrated dataset received by the server, and the output is the feedback information provided to the user. This feedback includes specific improvement suggestions for the next training session.

[0198] Step 7:

[0199] Users receive feedback from the server and review their actions in preparation for emergencies. The input is feedback information from the server, and the output is areas for improvement that are reflected in the user's perception and actions. These improvements will enable users to respond more effectively in subsequent training sessions.

[0200] 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.

[0201] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0202] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0203] [Second Embodiment]

[0204] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0205] 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.

[0206] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0207] 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.

[0208] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0209] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0210] 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.

[0211] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0212] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0213] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0214] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0215] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0216] In implementing this invention, the server, terminal, and user work together to realize emergency response training.

[0217] First, the server accesses a disaster knowledge database and generates an appropriate training scenario, taking into account the user's learning level and past training history. The generated scenario includes the environment and conditions in which the simulation will take place, as well as the challenges that will arise. Based on this data, the server performs detailed configuration and sends it to the terminal.

[0218] Next, the terminal receives scene data sent from the server and constructs a virtual reality environment based on it. The terminal connects to the user's VR device and provides real-time visual and auditory feedback. The user can freely walk around and manipulate objects within this virtual environment. The terminal records the user's movements and choices in detail and sends them to the server.

[0219] Users are required to take actions that correspond to specific situations in the virtual reality space. For example, in a virtual office where an earthquake has occurred, they might take cover under a desk and then exit the building via a safe route. Throughout this process, the device continuously records the user's actions and transmits that data to a server.

[0220] The server evaluates the user's response based on the received behavioral data. The evaluation is based on multiple criteria, including the speed and accuracy of the response and the ability to predict risks, and the results are provided to the user as feedback. This feedback includes what went well, areas for improvement, and guidance on more advanced challenges.

[0221] As a concrete example, in an evacuation route selection scenario, multiple routes are presented, and the user is tested on their ability to choose the appropriate route. Data from the device clarifies the reasons and timing of the selection, and the accuracy of the selection is analyzed. This allows users to objectively understand their own decision-making abilities and improve them.

[0222] Thus, by utilizing generative artificial intelligence and virtual reality technology, the present invention realizes a system that provides users with realistic and diverse training experiences and enhances their ability to respond quickly during disasters.

[0223] The following describes the processing flow.

[0224] Step 1:

[0225] The server accesses the disaster knowledge database and generates a specific training scenario. This includes the training objective, scene setting, and disaster types to consider. Based on this information, detailed scenario data is created and sent to the terminal.

[0226] Step 2:

[0227] The system uses scenario data received by the terminal to construct a virtual reality environment. This is achieved by activating the user's VR device and configuring graphic and audio data. Different environmental settings are configured based on each scenario to recreate realistic disaster situations.

[0228] Step 3:

[0229] The user puts on a VR headset and enters the provided virtual environment. The user activates a training symbol provided by the system (e.g., a start button) to begin training. Following the scenario, the user acts based on the instructions received.

[0230] Step 4:

[0231] When a user performs an action in a virtual environment, the device records its movements and choices in real time. It uses cameras and motion sensors to collect location information and movement data, preparing it for transmission to a server.

[0232] Step 5:

[0233] The server receives data from the terminal and analyzes user behavior by applying an evaluation algorithm. This evaluation is based on criteria such as the appropriateness and efficiency of the user's actions. The evaluation results are generated and prepared as feedback for the next step.

[0234] Step 6:

[0235] The server generates feedback and sends it to the terminal, communicating the details to the user. The terminal displays the feedback results and areas for future improvement on the screen in text and audio format. This allows the user to confirm the results of their training and improve their motivation for future training.

[0236] (Example 1)

[0237] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0238] The present invention aims to efficiently improve users' ability to respond quickly and appropriately in disasters and emergencies. Conventional training systems have had difficulty providing realistic feedback, which has prevented them from maximizing user learning effectiveness. Furthermore, they have the problem of not providing flexible training that can handle multiple disaster scenarios.

[0239] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0240] In this invention, the server includes means for generating emergency response scenarios using generative artificial intelligence, means for generating the scenarios by referring to a disaster knowledge database and considering the learning history, and means for constructing a virtual environment based on the scenarios using virtual reality technology and providing feedback to the user. This allows the user to experience training based on realistic and diverse situations, and effectively improve their reaction ability and judgment.

[0241] "Generative artificial intelligence" is an intelligent system that automatically generates new information and scenarios using past data and specific algorithms.

[0242] A "disaster knowledge database" is an information repository that stores information, countermeasures, and past cases related to various disasters, allowing that information to be retrieved and used as needed.

[0243] "Virtual reality technology" is a technology that uses computers to allow users to experience virtual environments and situations, providing simulated experiences through senses such as sight and hearing.

[0244] "Feedback" refers to providing evaluations and advice regarding a user's actions and choices, and offering information to help them improve their next actions.

[0245] "Learning history" refers to a record of training and activities a user has undertaken in the past, and is used to set the content of the next training and to track progress.

[0246] "Real-time" refers to a state in which processing and feedback are performed immediately while an event is occurring.

[0247] This invention involves a server, terminals, and users working together to realize an emergency response training system.

[0248] The server first uses a generative AI model to access a disaster knowledge database, and then generates an appropriate training scenario considering the user's past learning and training history. The generated scenario includes situations that will be reproduced in the virtual environment and tasks that the user should address. The server then structures this scenario data and transfers it to the terminal.

[0249] The terminal uses scenario data received from the server to construct a scenario-based virtual environment using virtual reality technology. The terminal interacts with the user's VR equipment to provide real-time visual and auditory feedback that the user can experience. The terminal also meticulously records the user's movements and choices and transmits this information to the server.

[0250] The user acts according to a generated scenario within the virtual environment provided by the device. This action could include, for example, evacuation procedures during an earthquake. A specific example is a scenario where the user learns how to safely evacuate a virtual office during an earthquake. In this scenario, the user would take cover under a desk and then exit the building via a safe route. An example of a prompt might be, "Generate a scenario for the user to learn how to safely evacuate from the office."

[0251] This system allows users to realistically experience various emergency response training scenarios and improve their rapid response capabilities.

[0252] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0253] Step 1:

[0254] The server accesses a disaster knowledge database and retrieves the user's learning history and past training history as input data. Based on this information, the generative AI model generates prompts and automatically creates appropriate training scenarios. The data calculations here involve extracting conditions from the input data and setting the optimal scenario parameters. Detailed configuration data for the scenario is generated as output.

[0255] Step 2:

[0256] The server sends the generated scenario data to the terminal. The input is the training scenario and its associated data created in step 1. This data is filtered in detail and converted into a format that the terminal can interpret, as it forms the basis for building the virtual reality environment. Structured data that the terminal can receive is sent as output.

[0257] Step 3:

[0258] The terminal constructs a virtual reality environment based on scenario data received from the server. The input is structured data sent from the server. The terminal uses VR equipment to provide the user with real-time visual and auditory feedback, rendering this data in 3D space and preparing an environment that the user can experience interactively. The output is the virtual environment that is actually displayed in the user's field of vision.

[0259] Step 4:

[0260] The user performs actions based on training scenarios within a virtual reality environment provided by the device. Input consists of the user's own physical movements and choices. The user takes specific actions within the virtual scenario, practicing things like evacuation procedures during an earthquake. The device records these actions and compiles them as data. Output is the user's behavioral data.

[0261] Step 5:

[0262] The terminal sends data to the server that records the user's actions in detail. The input is the user's behavior data accumulated in step 4. The terminal formats this data into a specific format and sends it to the server. As output, the behavior data is provided in a format that the server can analyze.

[0263] Step 6:

[0264] The server analyzes behavioral data received from the terminal and evaluates the user's response. The input is behavioral data sent from the terminal. The server comprehensively evaluates the speed, accuracy, and judgment of the response and generates analysis results. The output is evaluation and feedback information returned to the user, which allows the user to identify areas for improvement for the next training session.

[0265] (Application Example 1)

[0266] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0267] In modern times, there is a need to improve disaster preparedness awareness and strengthen emergency response capabilities. However, traditional training methods cannot fully replicate actual disaster situations, making effective skill improvement difficult. In addition, there is the challenge of providing individualized support tailored to each person's situation and past experience. Furthermore, there is a lack of objective evaluation of training results and feedback on their effectiveness, which hinders the continuous improvement of training.

[0268] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0269] In this invention, the server includes means for generating emergency response scenarios using generative artificial intelligence, means for constructing a virtual environment based on the scenarios using virtual reality and augmented reality technologies, and means for analyzing user behavior in real time using a mobile information terminal and recording user behavior through an information processing device. This enables the provision of individually tailored training to users in a virtual environment, as well as real-time behavioral analysis and feedback.

[0270] "Generative artificial intelligence" is an artificial intelligence technology that uses data and algorithms to generate information that is appropriate to the situation and requirements.

[0271] An "emergency response scenario" is a plan that outlines hypothetical cases and situations requiring necessary actions and decisions during a disaster or emergency.

[0272] "Virtual reality technology" is a technology that uses computer technology to allow users to experience a simulation of an environment that closely resembles reality.

[0273] Augmented reality technology is a technology that overlays digital information onto the real environment, providing users with a combination of reality and virtual reality.

[0274] A "mobile information terminal" is a portable computer device that can be used while on the go, and generally includes smartphones and tablets.

[0275] An "information processing device" is a computer system used for collecting, processing, storing, and analyzing data.

[0276] "Means of analyzing user behavior in real time" refers to methods and technologies for instantly recognizing user actions and performing analysis based on those actions.

[0277] A "database management system" is a software system for efficiently managing, searching, and updating data.

[0278] To implement this invention, a system is constructed in which a server, a terminal, and a user cooperate to conduct disaster prevention training. The server utilizes a generation AI model to generate emergency response scenarios from a disaster knowledge database based on the user's learning level and past training history. These scenarios specifically describe the environment and situation in which the simulation will be conducted, as well as the challenges the user will face. The server then configures these generated scenarios in detail and transmits them to the terminal.

[0279] The terminal constructs virtual reality and augmented reality environments based on received scene data. The terminal interacts with the user's mobile device (e.g., smartphone or tablet) to provide real-time visual and auditory feedback. Unity is used to construct the environment, and internet services such as AWS are used for data management. The user moves freely within this virtual or augmented reality environment, conducting disaster response training. The user's movements and choices are recorded in detail through an information processing device and transmitted to a server.

[0280] The server evaluates the user's response in detail based on the received action data. The evaluation criteria include the speed and accuracy of the reaction, the ability to predict risks, etc. The evaluation results are provided to the user as feedback, guiding them to success points, areas for improvement, and even challenging them with more advanced tasks. Through this feedback, the user can gradually strengthen their response ability and enhance their ability to act quickly and accurately during actual disasters.

[0281] As a specific example, when the user trains at home, the terminal scans the living space and provides a simulation of a fire occurring. The user conducts training such as selecting the correct evacuation route and checking emergency supplies via the application. During this process, the terminal records the user's actions and can use the feedback on incorrect selections and improvement points for the next training.

[0282] Examples of prompt texts can be in the form of "Please generate a scenario for disaster evacuation training. The user is in their 30s, with an intermediate level of past training experience. They are training with two family members. Focus on evacuation route selection and emergency treatment."

[0283] The flow of the specific process in Application Example 1 will be described using Figure 12.

[0284] Step 1:

[0285] The server inputs the prompt text using the generation AI model and references the disaster knowledge database. This prompt text reflects the user's training history and current learning level. The AI model extracts appropriate information from the database and generates an emergency response scenario. As output, a training scenario suitable for the user is created.

[0286] Step 2:

[0287] Based on the generated scenario, the server meticulously constructs the necessary configuration data for the virtual environment. This includes environmental parameters and simulation conditions for training. This data is then prepared for transmission to the terminal, and the configuration data is sent to the terminal as output.

[0288] Step 3:

[0289] The terminal uses configuration data received from the server to build a virtual reality and augmented reality environment. Unity is used to prepare the scenario that the user will experience. The input includes the scenario and configuration data, and the output is the virtual environment provided to the user.

[0290] Step 4:

[0291] The user begins training in a virtual reality environment via a device. The user works on tasks while freely performing their own movements and actions. Inputs include the user's real-time movements and choices, and output is user experience data, which is recorded on the device.

[0292] Step 5:

[0293] The terminal analyzes user behavior data in real time and transmits that data to the server via an information processing device. Inputs include user movements, choices, and generated experience data, and output is analyzed behavior data.

[0294] Step 6:

[0295] The server evaluates the user's response based on the received behavioral data. An evaluation algorithm is used to analyze reaction speed, accuracy, and judgment ability. The input is the analyzed behavioral data, and the output is the evaluation result.

[0296] Step 7:

[0297] The server uses the evaluation results to provide feedback to the user. This feedback includes areas for improvement and advice for future challenges. The input is the evaluation results, and the output is feedback information sent to the user. The user then uses this feedback to improve their skills.

[0298] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0299] This invention is a system that combines generative artificial intelligence, virtual reality technology, and means for recording user behavior and emotions, and is particularly intended to provide feedback that takes user emotions into account in emergency response training.

[0300] First, the server accesses a disaster knowledge database and generates an emergency response scenario. This includes setting up a specific disaster scene and situation. Based on this scenario, specific data is generated to build a virtual reality environment. This data includes environment settings, voice instructions, and simulation parameters. The server then sends this data to the terminal.

[0301] The device sets up a virtual reality environment based on the received scenario data and provides visual and auditory feedback to help the user immerse themselves. The user can then enter the virtual environment using VR equipment. Here, the emotion engine is activated, collecting data on the user's facial expressions, voice, and body sensors in real time to analyze their emotional state. This information is used to measure the user's stress level and sense of security.

[0302] Based on training scenarios, users take specific actions within a virtual environment. During this time, the terminal meticulously records the user's actions and transmits them to the server along with the inputted emotion data. The training process includes a function that recognizes the user's confusion or anxiety, for example, when selecting an evacuation route, and reflects this in the training results.

[0303] The server comprehensively analyzes the behavior and emotion data and evaluates the user's coping ability. The evaluation results include what behaviors were appropriate under emotional pressure and what areas need improvement. The server generates feedback based on the evaluation and sends it to the terminal to provide points for attention and efficient coping methods in the next training.

[0304] As a specific example, in a flood evacuation scenario, the emotion engine evaluates from an emotional aspect how the user reacts to a sudden rise in water level. As a result, it is possible to propose useful countermeasures in actual emergencies by providing feedback on whether the user tends to panic or can respond calmly.

[0305] In this way, the present invention realizes a system that provides more realistic and effective emergency response training by considering not only the user's behavior but also emotion data.

[0306] The processing flow will be described below.

[0307] Step 1:

[0308] The server accesses the disaster knowledge database and generates an emergency response scenario. This includes the type of disaster, environmental conditions, and difficulty level of the training. The server prepares to send the generated scenario data to the terminal.

[0309] Step 2:

[0310] Based on the scenario data received by the terminal, a virtual reality environment is constructed. It cooperates with the user's VR device to provide an immersive experience through vision, hearing, and touch. The terminal completes the environmental setup according to the scenario.

[0311] Step 3:

[0312] The user puts on a VR headset and enters the training environment. The emotion engine starts up and prepares to sense data such as the user's facial expressions, voice, and heart rate. The user then begins to act according to the scenario.

[0313] Step 4:

[0314] The device records the user's behavior in the virtual environment. Simultaneously, the emotion engine analyzes the user's emotional state in real time and collects data. Synchronization between behavioral and emotional data is maintained.

[0315] Step 5:

[0316] The server receives behavioral and emotional data transmitted from the terminal. An evaluation algorithm is applied to comprehensively assess the appropriateness of the behavior and the emotional response. Evaluation results based on the user's performance are then generated.

[0317] Step 6:

[0318] The server sends the generated evaluation results and feedback information to the terminal. The terminal presents this information to the user visually and audibly, reporting successes and areas for improvement. It also communicates future countermeasures and training plans.

[0319] Step 7:

[0320] The user reviews the feedback provided and adjusts their response for the next training session. Based on the feedback from the emotional engine, they prepare to further improve their ability by improving their emotional control and response methods.

[0321] (Example 2)

[0322] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0323] In emergency response training, there is a challenge in providing realistic feedback that takes into account not only the user's actions but also their emotional state. Conventional systems are limited to recording the user's physical actions and are unable to collect and analyze the emotional data necessary to improve the effectiveness of the training. As a result, training that can accurately predict how users will react in a real emergency has not been provided.

[0324] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0325] In this invention, the server includes means for generating emergency response scenarios using generative AI, means for constructing a virtual environment based on the scenarios using virtual reality technology, and means for recording user behavior and emotional data in real time. This makes it possible to comprehensively evaluate the user's behavior and emotional state and provide more realistic and effective feedback.

[0326] "Generative AI" is a type of artificial intelligence that uses machine learning techniques to generate new information based on specific conditions and data.

[0327] An "emergency response scenario" is a hypothetical scenario created based on specific situations and response procedures in the event of a disaster or emergency.

[0328] "Virtual reality technology" is a system technology that uses computer graphics and sensor technology to provide users with an experience that closely resembles reality.

[0329] "Means of recording in real time" refers to devices and methods that can record a user's state and actions immediately and without delay, and use them for analysis.

[0330] "Emotional data" refers to data that indicates a user's emotional state, and is information obtained based on physiological data such as facial expressions, tone of voice, and heart rate.

[0331] "Feedback" refers to information provided to users regarding evaluations and areas for improvement as a result of training or processing.

[0332] This invention provides a system that offers feedback that takes into account user behavior and emotions during emergency response training. The system utilizes generative AI models, virtual reality technology, and real-time data collection capabilities as its primary technologies.

[0333] The server uses a generative AI model to create scenarios for responding to disasters and emergencies. These scenarios refer to information from a disaster knowledge database and include scenarios that anticipate specific situations and circumstances. Specific examples include scenarios for "floods" and "earthquakes." The created scenario data is transmitted to the terminal in digital format.

[0334] The device uses VR headsets and sensor technology to build a virtual reality environment based on scenario data and provide users with a visual and auditory experience. By immersing themselves in the virtual environment, users can participate in training under conditions that simulate actual emergencies.

[0335] As users train in a VR space, the device collects user behavioral and emotional data in real time. Emotional data is obtained from the user's facial expressions, changes in voice, and physical indicators such as heart rate. This data is used to evaluate how users react under stress.

[0336] The server comprehensively analyzes behavioral and emotional data transmitted from the terminal to evaluate the user's response capabilities. A generative AI model generates feedback based on this information, which is then transmitted to the terminal as the user's training results. This feedback includes specific advice on which actions were effective and which areas need improvement.

[0337] A concrete example of this training is evaluating whether users were able to respond quickly to rising water levels in a flood evacuation scenario. Another example of a prompt is, "Evaluate the user's emotional response in the flood scenario and generate feedback suggesting behavioral improvements." This trains users to respond effectively in real-world emergencies.

[0338] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0339] Step 1:

[0340] The server accesses a disaster knowledge database and generates emergency response scenarios using a generative AI model. It references past disaster data and training records as input to define specific disaster scenarios. During this process, machine learning algorithms are used to output scenarios that the user should train on. Specifically, the server selects scenarios such as "flood," "earthquake," and "fire," and generates data including detailed settings (e.g., rate of water level rise, evacuation route options).

[0341] Step 2:

[0342] The server sends the generated scenario data to the terminal. The generated scenario information is used as input, and the scenario data in digital format is transferred to the terminal as output. Specifically, the server assembles scenario data packets containing various configuration information and sends them to the terminal via the network.

[0343] Step 3:

[0344] The terminal receives scenario data sent from the server and constructs a virtual reality environment. It takes scenario data as input and sets up the 3D virtual environment that the user experiences as output. Specifically, the terminal controls the VR headset, performs 3D modeling in real time, and provides the user with visual and auditory feedback.

[0345] Step 4:

[0346] The user enters a VR environment and begins training. They receive feedback from their device as input, select their own actions as output, and act within the virtual environment. Specifically, the user selects an evacuation route appropriate to the disaster and follows the corresponding procedures.

[0347] Step 5:

[0348] The device records user behavior and emotional data in real time. It collects user behavior and emotional data (e.g., facial expressions, voice, heart rate) as input and stores training data digitally as output. Specifically, the device analyzes and records physiological information using built-in sensors.

[0349] Step 6:

[0350] The server comprehensively analyzes behavioral and emotional data transmitted from the terminal. It receives recorded data as input and generates a numerical output that evaluates the user's ability to respond. Specifically, the server applies statistical algorithms to analyze the data and identify user response patterns.

[0351] Step 7:

[0352] The server generates feedback based on the analysis results and sends it to the terminal. Evaluation data is used as input, and feedback information is generated to be provided to the user as output. Specifically, the server creates a feedback message containing appropriate actions and areas for improvement, which can be used to help the user in their next training session.

[0353] (Application Example 2)

[0354] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0355] Conventional emergency response training systems only evaluated user behavior, failing to consider the emotional state of users during those actions. This meant they couldn't provide realistic training that took into account users' psychological reactions and stress levels during emergencies, potentially leading to ineffective responses in actual emergencies.

[0356] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0357] In this invention, the server includes means for generating emergency response scenarios using generative artificial intelligence, means for constructing a virtual environment based on the scenarios using virtual reality technology, and means for recording the user's behavior and emotions. This makes it possible to comprehensively evaluate the user's behavior and emotions and provide individually optimized feedback.

[0358] "Generative artificial intelligence" is an active algorithm that analyzes data according to a specified purpose and automatically generates appropriate scenarios and information.

[0359] An "emergency response scenario" is a hypothetical situation designed to outline specific procedures and action plans for responding quickly and appropriately to emergencies such as disasters and accidents.

[0360] "Virtual reality technology" is a technology that uses computer simulation techniques to allow users to experience a virtual environment realistically.

[0361] A "virtual environment" is a digital space created through computer simulation that mimics the real world.

[0362] "User behavior" refers to all specific actions and behaviors that a user takes in the virtual or real world.

[0363] A "means of recording emotions" refers to a system that uses sensors and analytical algorithms to record and store a user's emotional state.

[0364] "Individualized feedback" refers to information that provides advice and suggestions for improvement tailored to a specific user, based on analysis of the user's behavior and reactions.

[0365] In this invention, a server generates emergency response scenarios using generative artificial intelligence, and these scenarios are used to construct a virtual environment using virtual reality technology. Specifically, the server refers to a disaster knowledge database to obtain basic information for constructing a detailed scenario. A terminal receives this scenario data and sets up a virtual environment that can be realistically reproduced on a VR device. Through this, the user can receive emergency response training.

[0366] Users wear VR equipment and immerse themselves in a virtual environment, acting according to training scenarios. During this process, an emotion engine analyzes the user's facial expressions, voice data, and data from sensors attached to their body in real time. This allows the system to determine the user's stress level and emotional state. The device then transmits this data to a server, which integrates and analyzes the behavioral and emotional data.

[0367] As a result, the server generates user-optimized feedback and provides points that will be useful for future training. Specifically, if a user becomes frightened or panics during a fire evacuation scenario, the system will advise on safe evacuation methods. An example of a prompt using the generative AI model is, "Generate a fire evacuation scenario, analyze employee sentiment, and generate optimal feedback."

[0368] This system design allows users to receive more practical and effective training, enabling them to acquire the appropriate response skills for emergencies.

[0369] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0370] Step 1:

[0371] The server retrieves necessary information from a disaster knowledge database and generates emergency response scenarios using artificial intelligence. The input is data retrieved from the disaster knowledge database, and the output is specific scenario information. This scenario information includes details such as the type of disaster and its occurrence.

[0372] Step 2:

[0373] The terminal uses virtual reality technology to construct a virtual environment based on scenario information received from the server. The input is the scenario information sent from the server, and the output is the virtual environment that the user can immerse themselves in using a VR device. Specifically, visual and audio elements are incorporated into the VR environment.

[0374] Step 3:

[0375] The user wears VR equipment and acts according to a training scenario within a virtual environment. Input is visual and auditory stimuli from the virtual environment, and output is user behavior data. This behavior data includes motion information such as evacuation direction and speed.

[0376] Step 4:

[0377] The device uses an emotion engine to analyze the user's facial expressions, voice, and data from sensors worn on the body in real time. The input is this emotional data, and the output is an analysis showing the user's stress level and emotional state. Based on the emotional state, feedback in the virtual environment is adjusted accordingly.

[0378] Step 5:

[0379] The device sends collected user behavioral and emotional data to the server. The input is all the data collected by the device, and the output is an integrated dataset received by the server. This dataset comprehensively records the user's responses.

[0380] Step 6:

[0381] The server integrates behavioral and emotional data to generate optimal feedback for the user. The input is the integrated dataset received by the server, and the output is the feedback information provided to the user. This feedback includes specific improvement suggestions for the next training session.

[0382] Step 7:

[0383] Users receive feedback from the server and review their actions in preparation for emergencies. The input is feedback information from the server, and the output is areas for improvement that are reflected in the user's perception and actions. These improvements will enable users to respond more effectively in subsequent training sessions.

[0384] 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.

[0385] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0386] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0387] [Third Embodiment]

[0388] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0389] 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.

[0390] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0391] 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.

[0392] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0393] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0394] 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.

[0395] 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.

[0396] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0397] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0398] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0399] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0400] In implementing this invention, the server, terminal, and user work together to realize emergency response training.

[0401] First, the server accesses a disaster knowledge database and generates an appropriate training scenario, taking into account the user's learning level and past training history. The generated scenario includes the environment and conditions in which the simulation will take place, as well as the challenges that will arise. Based on this data, the server performs detailed configuration and sends it to the terminal.

[0402] Next, the terminal receives scene data sent from the server and constructs a virtual reality environment based on it. The terminal connects to the user's VR device and provides real-time visual and auditory feedback. The user can freely walk around and manipulate objects within this virtual environment. The terminal records the user's movements and choices in detail and sends them to the server.

[0403] Users are required to take actions that correspond to specific situations in the virtual reality space. For example, in a virtual office where an earthquake has occurred, they might take cover under a desk and then exit the building via a safe route. Throughout this process, the device continuously records the user's actions and transmits that data to a server.

[0404] The server evaluates the user's response based on the received behavioral data. The evaluation is based on multiple criteria, including the speed and accuracy of the response and the ability to predict risks, and the results are provided to the user as feedback. This feedback includes what went well, areas for improvement, and guidance on more advanced challenges.

[0405] As a concrete example, in an evacuation route selection scenario, multiple routes are presented, and the user is tested on their ability to choose the appropriate route. Data from the device clarifies the reasons and timing of the selection, and the accuracy of the selection is analyzed. This allows users to objectively understand their own decision-making abilities and improve them.

[0406] Thus, by utilizing generative artificial intelligence and virtual reality technology, the present invention realizes a system that provides users with realistic and diverse training experiences and enhances their ability to respond quickly during disasters.

[0407] The following describes the processing flow.

[0408] Step 1:

[0409] The server accesses the disaster knowledge database and generates a specific training scenario. This includes the training objective, scene setting, and disaster types to consider. Based on this information, detailed scenario data is created and sent to the terminal.

[0410] Step 2:

[0411] The system uses scenario data received by the terminal to construct a virtual reality environment. This is achieved by activating the user's VR device and configuring graphic and audio data. Different environmental settings are configured based on each scenario to recreate realistic disaster situations.

[0412] Step 3:

[0413] The user puts on a VR headset and enters the provided virtual environment. The user activates a training symbol provided by the system (e.g., a start button) to begin training. Following the scenario, the user acts based on the instructions received.

[0414] Step 4:

[0415] When a user performs an action in a virtual environment, the device records its movements and choices in real time. It uses cameras and motion sensors to collect location information and movement data, preparing it for transmission to a server.

[0416] Step 5:

[0417] The server receives data from the terminal and analyzes user behavior by applying an evaluation algorithm. This evaluation is based on criteria such as the appropriateness and efficiency of the user's actions. The evaluation results are generated and prepared as feedback for the next step.

[0418] Step 6:

[0419] The server generates feedback and sends it to the terminal, communicating the details to the user. The terminal displays the feedback results and areas for future improvement on the screen in text and audio format. This allows the user to confirm the results of their training and improve their motivation for future training.

[0420] (Example 1)

[0421] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0422] The present invention aims to efficiently improve users' ability to respond quickly and appropriately in disasters and emergencies. Conventional training systems have had difficulty providing realistic feedback, which has prevented them from maximizing user learning effectiveness. Furthermore, they have the problem of not providing flexible training that can handle multiple disaster scenarios.

[0423] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0424] In this invention, the server includes means for generating emergency response scenarios using generative artificial intelligence, means for generating the scenarios by referring to a disaster knowledge database and considering the learning history, and means for constructing a virtual environment based on the scenarios using virtual reality technology and providing feedback to the user. This allows the user to experience training based on realistic and diverse situations, and effectively improve their reaction ability and judgment.

[0425] "Generative artificial intelligence" is an intelligent system that automatically generates new information and scenarios using past data and specific algorithms.

[0426] A "disaster knowledge database" is an information repository that stores information, countermeasures, and past case studies related to various disasters, allowing that information to be retrieved and used as needed.

[0427] "Virtual reality technology" is a technology that uses computers to allow users to experience virtual environments and situations, providing simulated experiences through senses such as sight and hearing.

[0428] "Feedback" refers to providing evaluations and advice regarding a user's actions and choices, and offering information to help them improve their next actions.

[0429] "Learning history" refers to a record of training and activities a user has undertaken in the past, and is used to set the content of the next training and to track progress.

[0430] "Real-time" refers to a state in which processing and feedback are performed immediately while an event is occurring.

[0431] This invention involves a server, terminals, and users working together to realize an emergency response training system.

[0432] The server first uses a generative AI model to access a disaster knowledge database, and then generates an appropriate training scenario considering the user's past learning and training history. The generated scenario includes situations that will be reproduced in the virtual environment and tasks that the user should address. The server then structures this scenario data and transfers it to the terminal.

[0433] The terminal uses scenario data received from the server to construct a scenario-based virtual environment using virtual reality technology. The terminal interacts with the user's VR equipment to provide real-time visual and auditory feedback that the user can experience. The terminal also meticulously records the user's movements and choices and transmits this information to the server.

[0434] The user acts according to a generated scenario within the virtual environment provided by the device. This action could include, for example, evacuation procedures during an earthquake. A specific example is a scenario where the user learns how to safely evacuate a virtual office during an earthquake. In this scenario, the user would take cover under a desk and then exit the building via a safe route. An example of a prompt might be, "Generate a scenario for the user to learn how to safely evacuate from the office."

[0435] This system allows users to realistically experience various emergency response training scenarios and improve their rapid response capabilities.

[0436] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0437] Step 1:

[0438] The server accesses a disaster knowledge database and retrieves the user's learning history and past training history as input data. Based on this information, the generative AI model generates prompts and automatically creates appropriate training scenarios. The data calculations here involve extracting conditions from the input data and setting the optimal scenario parameters. Detailed configuration data for the scenario is generated as output.

[0439] Step 2:

[0440] The server sends the generated scenario data to the terminal. The input is the training scenario and its associated data created in step 1. This data is filtered in detail and converted into a format that the terminal can interpret, as it forms the basis for building the virtual reality environment. Structured data that the terminal can receive is sent as output.

[0441] Step 3:

[0442] The terminal constructs a virtual reality environment based on scenario data received from the server. The input is structured data sent from the server. The terminal uses VR equipment to provide the user with real-time visual and auditory feedback, rendering this data in 3D space and preparing an environment that the user can experience interactively. The output is the virtual environment that is actually displayed in the user's field of vision.

[0443] Step 4:

[0444] The user performs actions based on training scenarios within a virtual reality environment provided by the device. Input consists of the user's own physical movements and choices. The user takes specific actions within the virtual scenario, practicing things like evacuation procedures during an earthquake. The device records these actions and compiles them as data. Output is the user's behavioral data.

[0445] Step 5:

[0446] The terminal sends data to the server that records the user's actions in detail. The input is the user's behavior data accumulated in step 4. The terminal formats this data into a specific format and sends it to the server. As output, the behavior data is provided in a format that the server can analyze.

[0447] Step 6:

[0448] The server analyzes behavioral data received from the terminal and evaluates the user's response. The input is behavioral data sent from the terminal. The server comprehensively evaluates the speed, accuracy, and judgment of the response and generates analysis results. The output is evaluation and feedback information returned to the user, which allows the user to identify areas for improvement for the next training session.

[0449] (Application Example 1)

[0450] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0451] In modern times, there is a need to improve disaster preparedness awareness and strengthen emergency response capabilities. However, traditional training methods cannot fully replicate actual disaster situations, making effective skill improvement difficult. In addition, there is the challenge of providing individualized support tailored to each person's situation and past experience. Furthermore, there is a lack of objective evaluation of training results and feedback on their effectiveness, which hinders the continuous improvement of training.

[0452] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0453] In this invention, the server includes means for generating emergency response scenarios using generative artificial intelligence, means for constructing a virtual environment based on the scenarios using virtual reality and augmented reality technologies, and means for analyzing user behavior in real time using a mobile information terminal and recording user behavior through an information processing device. This enables the provision of individually tailored training to users in a virtual environment, as well as real-time behavioral analysis and feedback.

[0454] "Generative artificial intelligence" is an artificial intelligence technology that uses data and algorithms to generate information that is appropriate to the situation and requirements.

[0455] An "emergency response scenario" is a plan that outlines hypothetical cases and situations requiring necessary actions and decisions during a disaster or emergency.

[0456] "Virtual reality technology" is a technology that uses computer technology to allow users to experience a simulation of an environment that closely resembles reality.

[0457] Augmented reality technology is a technology that overlays digital information onto the real environment, providing users with a combination of reality and virtual reality.

[0458] A "mobile information terminal" is a portable computer device that can be used while on the go, and generally includes smartphones and tablets.

[0459] An "information processing device" is a computer system used for collecting, processing, storing, and analyzing data.

[0460] "Means of analyzing user behavior in real time" refers to methods and technologies for instantly recognizing user actions and performing analysis based on those actions.

[0461] A "database management system" is a software system for efficiently managing, searching, and updating data.

[0462] To implement this invention, a system is constructed in which a server, a terminal, and a user cooperate to conduct disaster prevention training. The server utilizes a generation AI model to generate emergency response scenarios from a disaster knowledge database based on the user's learning level and past training history. These scenarios specifically describe the environment and situation in which the simulation will be conducted, as well as the challenges the user will face. The server then configures these generated scenarios in detail and transmits them to the terminal.

[0463] The terminal constructs virtual reality and augmented reality environments based on received scene data. The terminal interacts with the user's mobile device (e.g., smartphone or tablet) to provide real-time visual and auditory feedback. Unity is used to construct the environment, and internet services such as AWS are used for data management. The user moves freely within this virtual or augmented reality environment, conducting disaster response training. The user's movements and choices are recorded in detail through an information processing device and transmitted to a server.

[0464] The server thoroughly evaluates the user's responses based on the received behavioral data. Evaluation criteria include the speed and accuracy of reactions, and the ability to predict risks. The evaluation results are provided to the user as feedback, guiding them to identify successes, areas for improvement, and to take on more advanced challenges. Through this feedback, users can gradually strengthen their response capabilities, increasing their ability to take swift and accurate action in actual disaster situations.

[0465] As a concrete example, when a user trains at home, the device scans the living space and provides a fire simulation. Through the application, the user trains by selecting the correct evacuation route and checking emergency supplies. In this process, the device records the user's actions and provides feedback, pointing out incorrect choices and suggesting areas for improvement, which can be used to improve future training.

[0466] An example of a prompt message might be: "Generate a scenario for disaster evacuation training. The user is in their 30s and has intermediate-level training experience. They are training with two family members. Focus on evacuation route selection and first aid."

[0467] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0468] Step 1:

[0469] The server uses a generation AI model to input prompts and references a disaster knowledge database. These prompts reflect the user's training history and current learning level. The AI ​​model extracts appropriate information from the database and generates emergency response scenarios. As output, a training scenario tailored to the user is created.

[0470] Step 2:

[0471] Based on the generated scenario, the server meticulously constructs the necessary configuration data for the virtual environment. This includes environmental parameters and simulation conditions for training. This data is then prepared for transmission to the terminal, and the configuration data is sent to the terminal as output.

[0472] Step 3:

[0473] The terminal uses configuration data received from the server to build a virtual reality and augmented reality environment. Unity is used to prepare the scenario that the user will experience. The input includes the scenario and configuration data, and the output is the virtual environment provided to the user.

[0474] Step 4:

[0475] The user begins training in a virtual reality environment via a device. The user works on tasks while freely performing their own movements and actions. Inputs include the user's real-time movements and choices, and output is user experience data, which is recorded on the device.

[0476] Step 5:

[0477] The terminal analyzes user behavior data in real time and transmits that data to the server via an information processing device. Inputs include user movements, choices, and generated experience data, and output is analyzed behavior data.

[0478] Step 6:

[0479] The server evaluates the user's response based on the received behavioral data. An evaluation algorithm is used to analyze reaction speed, accuracy, and judgment ability. The input is the analyzed behavioral data, and the output is the evaluation result.

[0480] Step 7:

[0481] The server uses the evaluation results to provide feedback to the user. This feedback includes areas for improvement and advice for future challenges. The input is the evaluation results, and the output is feedback information sent to the user. The user then uses this feedback to improve their skills.

[0482] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0483] This invention is a system that combines generative artificial intelligence, virtual reality technology, and means for recording user behavior and emotions, and is particularly intended to provide feedback that takes user emotions into account in emergency response training.

[0484] First, the server accesses a disaster knowledge database and generates an emergency response scenario. This includes setting up a specific disaster scene and situation. Based on this scenario, specific data is generated to build a virtual reality environment. This data includes environment settings, voice instructions, and simulation parameters. The server then sends this data to the terminal.

[0485] The device sets up a virtual reality environment based on the received scenario data and provides visual and auditory feedback to help the user immerse themselves. The user can then enter the virtual environment using VR equipment. Here, the emotion engine is activated, collecting data on the user's facial expressions, voice, and body sensors in real time to analyze their emotional state. This information is used to measure the user's stress level and sense of security.

[0486] Based on training scenarios, users take specific actions within a virtual environment. During this time, the terminal meticulously records the user's actions and transmits them to the server along with the inputted emotion data. The training process includes a function that recognizes the user's confusion or anxiety, for example, when selecting an evacuation route, and reflects this in the training results.

[0487] The server comprehensively analyzes behavioral and emotional data to assess the user's coping abilities. This assessment includes identifying appropriate behaviors under emotional pressure and areas for improvement. Based on the assessment, the server generates feedback and sends it to the terminal to provide points to consider and effective coping strategies for future training.

[0488] As a concrete example, in a flood evacuation scenario, the emotion engine evaluates how users react to a sudden rise in water levels from an emotional perspective. As a result, by providing feedback on whether users tend to panic or respond calmly, it is possible to suggest useful measures for actual emergencies.

[0489] Thus, the present invention realizes a system that provides more realistic and effective emergency response training by considering not only user behavior but also emotional data.

[0490] The following describes the processing flow.

[0491] Step 1:

[0492] The server accesses a disaster knowledge database and generates emergency response scenarios. These include the type of disaster, environmental conditions, and the difficulty level of the training. The server then prepares to send the generated scenario data to the terminal.

[0493] Step 2:

[0494] The device constructs a virtual reality environment based on the scenario data it receives. It works in conjunction with the user's VR equipment to provide an immersive experience through sight, sound, and touch. The device completes the environment setup according to the scenario.

[0495] Step 3:

[0496] The user puts on a VR headset and enters the training environment. The emotion engine starts up and prepares to sense data such as the user's facial expressions, voice, and heart rate. The user then begins to act according to the scenario.

[0497] Step 4:

[0498] The device records the user's behavior in the virtual environment. Simultaneously, the emotion engine analyzes the user's emotional state in real time and collects data. Synchronization between behavioral and emotional data is maintained.

[0499] Step 5:

[0500] The server receives behavioral and emotional data transmitted from the terminal. An evaluation algorithm is applied to comprehensively assess the appropriateness of the behavior and the emotional response. Evaluation results based on the user's performance are then generated.

[0501] Step 6:

[0502] The server sends the generated evaluation results and feedback information to the terminal. The terminal presents this information to the user visually and audibly, reporting successes and areas for improvement. It also communicates future countermeasures and training plans.

[0503] Step 7:

[0504] The user reviews the feedback provided and adjusts their response for the next training session. Based on the feedback from the emotional engine, they prepare to further improve their ability by improving their emotional control and response methods.

[0505] (Example 2)

[0506] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0507] In emergency response training, there is a challenge in providing realistic feedback that takes into account not only the user's actions but also their emotional state. Conventional systems are limited to recording the user's physical actions and are unable to collect and analyze the emotional data necessary to improve the effectiveness of the training. As a result, training that can accurately predict how users will react in a real emergency has not been provided.

[0508] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0509] In this invention, the server includes means for generating emergency response scenarios using generative AI, means for constructing a virtual environment based on the scenarios using virtual reality technology, and means for recording user behavior and emotional data in real time. This makes it possible to comprehensively evaluate the user's behavior and emotional state and provide more realistic and effective feedback.

[0510] "Generative AI" is a type of artificial intelligence that uses machine learning techniques to generate new information based on specific conditions and data.

[0511] An "emergency response scenario" is a hypothetical scenario created based on specific situations and response procedures in the event of a disaster or emergency.

[0512] "Virtual reality technology" is a system technology that uses computer graphics and sensor technology to provide users with an experience that closely resembles reality.

[0513] "Means of recording in real time" refers to devices and methods that can record a user's state and actions immediately and without delay, and use them for analysis.

[0514] "Emotional data" refers to data that indicates a user's emotional state, and is information obtained based on physiological data such as facial expressions, tone of voice, and heart rate.

[0515] "Feedback" refers to information provided to users regarding evaluations and areas for improvement as a result of training or processing.

[0516] This invention provides a system that offers feedback that takes into account user behavior and emotions during emergency response training. The system utilizes generative AI models, virtual reality technology, and real-time data collection capabilities as its primary technologies.

[0517] The server uses a generative AI model to create scenarios for responding to disasters and emergencies. These scenarios refer to information from a disaster knowledge database and include scenarios that anticipate specific situations and circumstances. Specific examples include scenarios for "floods" and "earthquakes." The created scenario data is transmitted to the terminal in digital format.

[0518] The device uses VR headsets and sensor technology to build a virtual reality environment based on scenario data and provide users with a visual and auditory experience. By immersing themselves in the virtual environment, users can participate in training under conditions that simulate actual emergencies.

[0519] As users train in a VR space, the device collects user behavioral and emotional data in real time. Emotional data is obtained from the user's facial expressions, changes in voice, and physical indicators such as heart rate. This data is used to evaluate how users react under stress.

[0520] The server comprehensively analyzes behavioral and emotional data transmitted from the terminal to evaluate the user's response capabilities. A generative AI model generates feedback based on this information, which is then transmitted to the terminal as the user's training results. This feedback includes specific advice on which actions were effective and which areas need improvement.

[0521] A concrete example of this training is evaluating whether users were able to respond quickly to rising water levels in a flood evacuation scenario. Another example of a prompt is, "Evaluate the user's emotional response in the flood scenario and generate feedback suggesting behavioral improvements." This trains users to respond effectively in real-world emergencies.

[0522] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0523] Step 1:

[0524] The server accesses a disaster knowledge database and generates emergency response scenarios using a generative AI model. It references past disaster data and training records as input to define specific disaster scenarios. During this process, machine learning algorithms are used to output scenarios that the user should train on. Specifically, the server selects scenarios such as "flood," "earthquake," and "fire," and generates data including detailed settings (e.g., rate of water level rise, evacuation route options).

[0525] Step 2:

[0526] The server sends the generated scenario data to the terminal. The generated scenario information is used as input, and the scenario data in digital format is transferred to the terminal as output. Specifically, the server assembles scenario data packets containing various configuration information and sends them to the terminal via the network.

[0527] Step 3:

[0528] The terminal receives scenario data sent from the server and constructs a virtual reality environment. It takes scenario data as input and sets up the 3D virtual environment that the user experiences as output. Specifically, the terminal controls the VR headset, performs 3D modeling in real time, and provides the user with visual and auditory feedback.

[0529] Step 4:

[0530] The user enters a VR environment and begins training. They receive feedback from their device as input, select their own actions as output, and act within the virtual environment. Specifically, the user selects an evacuation route appropriate to the disaster and follows the corresponding procedures.

[0531] Step 5:

[0532] The device records user behavior and emotional data in real time. It collects user behavior and emotional data (e.g., facial expressions, voice, heart rate) as input and stores training data digitally as output. Specifically, the device analyzes and records physiological information using built-in sensors.

[0533] Step 6:

[0534] The server comprehensively analyzes behavioral and emotional data transmitted from the terminal. It receives recorded data as input and generates a numerical output that evaluates the user's ability to respond. Specifically, the server applies statistical algorithms to analyze the data and identify user response patterns.

[0535] Step 7:

[0536] The server generates feedback based on the analysis results and sends it to the terminal. Evaluation data is used as input, and feedback information is generated to be provided to the user as output. Specifically, the server creates a feedback message containing appropriate actions and areas for improvement, which can be used to help the user in their next training session.

[0537] (Application Example 2)

[0538] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0539] Conventional emergency response training systems only evaluated user behavior, failing to consider the emotional state of users during those actions. This meant they couldn't provide realistic training that took into account users' psychological reactions and stress levels during emergencies, potentially leading to ineffective responses in actual emergencies.

[0540] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0541] In this invention, the server includes means for generating emergency response scenarios using generative artificial intelligence, means for constructing a virtual environment based on the scenarios using virtual reality technology, and means for recording the user's behavior and emotions. This makes it possible to comprehensively evaluate the user's behavior and emotions and provide individually optimized feedback.

[0542] "Generative artificial intelligence" is an active algorithm that analyzes data according to a specified purpose and automatically generates appropriate scenarios and information.

[0543] An "emergency response scenario" is a hypothetical situation designed to outline specific procedures and action plans for responding quickly and appropriately to emergencies such as disasters and accidents.

[0544] "Virtual reality technology" is a technology that uses computer simulation techniques to allow users to experience a virtual environment realistically.

[0545] A "virtual environment" is a digital space created through computer simulation that mimics the real world.

[0546] "User behavior" refers to all specific actions and behaviors that a user takes in the virtual or real world.

[0547] A "means of recording emotions" refers to a system that uses sensors and analytical algorithms to record and store a user's emotional state.

[0548] "Individualized feedback" refers to information that provides advice and suggestions for improvement tailored to a specific user, based on analysis of the user's behavior and reactions.

[0549] In this invention, a server generates emergency response scenarios using generative artificial intelligence, and these scenarios are used to construct a virtual environment using virtual reality technology. Specifically, the server refers to a disaster knowledge database to obtain basic information for constructing a detailed scenario. A terminal receives this scenario data and sets up a virtual environment that can be realistically reproduced on a VR device. Through this, the user can receive emergency response training.

[0550] Users wear VR equipment and immerse themselves in a virtual environment, acting according to training scenarios. During this process, an emotion engine analyzes the user's facial expressions, voice data, and data from sensors attached to their body in real time. This allows the system to determine the user's stress level and emotional state. The device then transmits this data to a server, which integrates and analyzes the behavioral and emotional data.

[0551] As a result, the server generates user-optimized feedback and provides points that will be useful for future training. Specifically, if a user becomes frightened or panics during a fire evacuation scenario, the system will advise on safe evacuation methods. An example of a prompt using the generative AI model is, "Generate a fire evacuation scenario, analyze employee sentiment, and generate optimal feedback."

[0552] This system design allows users to receive more practical and effective training, enabling them to acquire the appropriate response skills for emergencies.

[0553] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0554] Step 1:

[0555] The server retrieves necessary information from a disaster knowledge database and generates emergency response scenarios using artificial intelligence. The input is data retrieved from the disaster knowledge database, and the output is specific scenario information. This scenario information includes details such as the type of disaster and its occurrence.

[0556] Step 2:

[0557] The terminal uses virtual reality technology to construct a virtual environment based on scenario information received from the server. The input is the scenario information sent from the server, and the output is the virtual environment that the user can immerse themselves in using a VR device. Specifically, visual and audio elements are incorporated into the VR environment.

[0558] Step 3:

[0559] The user wears VR equipment and acts according to a training scenario within a virtual environment. Input is visual and auditory stimuli from the virtual environment, and output is user behavior data. This behavior data includes motion information such as evacuation direction and speed.

[0560] Step 4:

[0561] The device uses an emotion engine to analyze the user's facial expressions, voice, and data from sensors worn on the body in real time. The input is this emotional data, and the output is an analysis showing the user's stress level and emotional state. Based on the emotional state, feedback in the virtual environment is adjusted accordingly.

[0562] Step 5:

[0563] The device sends collected user behavioral and emotional data to the server. The input is all the data collected by the device, and the output is an integrated dataset received by the server. This dataset comprehensively records the user's responses.

[0564] Step 6:

[0565] The server integrates behavioral and emotional data to generate optimal feedback for the user. The input is the integrated dataset received by the server, and the output is the feedback information provided to the user. This feedback includes specific improvement suggestions for the next training session.

[0566] Step 7:

[0567] Users receive feedback from the server and review their actions in preparation for emergencies. The input is feedback information from the server, and the output is areas for improvement that are reflected in the user's perception and actions. These improvements will enable users to respond more effectively in subsequent training sessions.

[0568] 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.

[0569] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0570] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0571] [Fourth Embodiment]

[0572] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0573] 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.

[0574] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0575] 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.

[0576] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0577] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0578] 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.

[0579] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0580] 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.

[0581] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0582] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0583] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0584] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0585] In implementing this invention, the server, terminal, and user work together to realize emergency response training.

[0586] First, the server accesses a disaster knowledge database and generates an appropriate training scenario, taking into account the user's learning level and past training history. The generated scenario includes the environment and conditions in which the simulation will take place, as well as the challenges that will arise. Based on this data, the server performs detailed configuration and sends it to the terminal.

[0587] Next, the terminal receives scene data sent from the server and constructs a virtual reality environment based on it. The terminal connects to the user's VR device and provides real-time visual and auditory feedback. The user can freely walk around and manipulate objects within this virtual environment. The terminal records the user's movements and choices in detail and sends them to the server.

[0588] Users are required to take actions that correspond to specific situations in the virtual reality space. For example, in a virtual office where an earthquake has occurred, they might take cover under a desk and then exit the building via a safe route. Throughout this process, the device continuously records the user's actions and transmits that data to a server.

[0589] The server evaluates the user's response based on the received behavioral data. The evaluation is based on multiple criteria, including the speed and accuracy of the response and the ability to predict risks, and the results are provided to the user as feedback. This feedback includes what went well, areas for improvement, and guidance on more advanced challenges.

[0590] As a concrete example, in an evacuation route selection scenario, multiple routes are presented, and the user is tested on their ability to choose the appropriate route. Data from the device clarifies the reasons and timing of the selection, and the accuracy of the selection is analyzed. This allows users to objectively understand their own decision-making abilities and improve them.

[0591] Thus, by utilizing generative artificial intelligence and virtual reality technology, the present invention realizes a system that provides users with realistic and diverse training experiences and enhances their ability to respond quickly during disasters.

[0592] The following describes the processing flow.

[0593] Step 1:

[0594] The server accesses the disaster knowledge database and generates a specific training scenario. This includes the training objective, scene setting, and disaster types to consider. Based on this information, detailed scenario data is created and sent to the terminal.

[0595] Step 2:

[0596] The system uses scenario data received by the terminal to construct a virtual reality environment. This is achieved by activating the user's VR device and configuring graphic and audio data. Different environmental settings are configured based on each scenario to recreate realistic disaster situations.

[0597] Step 3:

[0598] The user puts on a VR headset and enters the provided virtual environment. The user activates a training symbol provided by the system (e.g., a start button) to begin training. Following the scenario, the user acts based on the instructions received.

[0599] Step 4:

[0600] When a user performs an action in a virtual environment, the device records its movements and choices in real time. It uses cameras and motion sensors to collect location information and movement data, preparing it for transmission to a server.

[0601] Step 5:

[0602] The server receives data from the terminal and analyzes user behavior by applying an evaluation algorithm. This evaluation is based on criteria such as the appropriateness and efficiency of the user's actions. The evaluation results are generated and prepared as feedback for the next step.

[0603] Step 6:

[0604] The server generates feedback and sends it to the terminal, communicating the details to the user. The terminal displays the feedback results and areas for future improvement on the screen in text and audio format. This allows the user to confirm the results of their training and improve their motivation for future training.

[0605] (Example 1)

[0606] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0607] The present invention aims to efficiently improve users' ability to respond quickly and appropriately in disasters and emergencies. Conventional training systems have had difficulty providing realistic feedback, which has prevented them from maximizing user learning effectiveness. Furthermore, they have the problem of not providing flexible training that can handle multiple disaster scenarios.

[0608] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0609] In this invention, the server includes means for generating emergency response scenarios using generative artificial intelligence, means for generating the scenarios by referring to a disaster knowledge database and considering the learning history, and means for constructing a virtual environment based on the scenarios using virtual reality technology and providing feedback to the user. This allows the user to experience training based on realistic and diverse situations, and effectively improve their reaction ability and judgment.

[0610] "Generative artificial intelligence" is an intelligent system that automatically generates new information and scenarios using past data and specific algorithms.

[0611] A "disaster knowledge database" is an information repository that stores information, countermeasures, and past cases related to various disasters, allowing that information to be retrieved and used as needed.

[0612] "Virtual reality technology" is a technology that uses computers to allow users to experience virtual environments and situations, providing a simulated experience through senses such as sight and hearing.

[0613] "Feedback" refers to providing evaluations and advice regarding a user's actions and choices, and offering information to help them improve their next actions.

[0614] "Learning history" refers to a record of training and activities a user has undertaken in the past, and is used to set the content of the next training and to track progress.

[0615] "Real-time" refers to a state in which processing and feedback are performed immediately while an event is occurring.

[0616] This invention involves a server, terminals, and users working together to realize an emergency response training system.

[0617] The server first uses a generative AI model to access a disaster knowledge database, and then generates an appropriate training scenario considering the user's past learning and training history. The generated scenario includes situations that will be reproduced in the virtual environment and tasks that the user should address. The server then structures this scenario data and transfers it to the terminal.

[0618] The terminal uses scenario data received from the server to construct a scenario-based virtual environment using virtual reality technology. The terminal interacts with the user's VR equipment to provide real-time visual and auditory feedback that the user can experience. The terminal also meticulously records the user's movements and choices and transmits this information to the server.

[0619] The user acts according to a generated scenario within the virtual environment provided by the device. This action could include, for example, evacuation procedures during an earthquake. A specific example is a scenario where the user learns how to safely evacuate a virtual office during an earthquake. In this scenario, the user would take cover under a desk and then exit the building via a safe route. An example of a prompt might be, "Generate a scenario for the user to learn how to safely evacuate from the office."

[0620] This system allows users to realistically experience various emergency response training scenarios and improve their rapid response capabilities.

[0621] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0622] Step 1:

[0623] The server accesses a disaster knowledge database and retrieves the user's learning history and past training history as input data. Based on this information, the generative AI model generates prompts and automatically creates appropriate training scenarios. The data calculations here involve extracting conditions from the input data and setting the optimal scenario parameters. Detailed configuration data for the scenario is generated as output.

[0624] Step 2:

[0625] The server sends the generated scenario data to the terminal. The input is the training scenario and its associated data created in step 1. This data is filtered in detail and converted into a format that the terminal can interpret, as it forms the basis for building the virtual reality environment. Structured data that the terminal can receive is sent as output.

[0626] Step 3:

[0627] The terminal constructs a virtual reality environment based on scenario data received from the server. The input is structured data sent from the server. The terminal uses VR equipment to provide the user with real-time visual and auditory feedback, rendering this data in 3D space and preparing an environment that the user can experience interactively. The output is the virtual environment that is actually displayed in the user's field of vision.

[0628] Step 4:

[0629] The user performs actions based on training scenarios within a virtual reality environment provided by the device. Input consists of the user's own physical movements and choices. The user takes specific actions within the virtual scenario, practicing things like evacuation procedures during an earthquake. The device records these actions and compiles them as data. Output is the user's behavioral data.

[0630] Step 5:

[0631] The terminal sends data to the server that records the user's actions in detail. The input is the user's behavior data accumulated in step 4. The terminal formats this data into a specific format and sends it to the server. As output, the behavior data is provided in a format that the server can analyze.

[0632] Step 6:

[0633] The server analyzes behavioral data received from the terminal and evaluates the user's response. The input is behavioral data sent from the terminal. The server comprehensively evaluates the speed, accuracy, and judgment of the response and generates analysis results. The output is evaluation and feedback information returned to the user, which allows the user to identify areas for improvement for the next training session.

[0634] (Application Example 1)

[0635] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0636] In modern times, there is a need to improve disaster preparedness awareness and strengthen emergency response capabilities. However, traditional training methods cannot fully replicate actual disaster situations, making effective skill improvement difficult. In addition, there is the challenge of providing individualized support tailored to each person's situation and past experience. Furthermore, there is a lack of objective evaluation of training results and feedback on their effectiveness, which hinders the continuous improvement of training.

[0637] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0638] In this invention, the server includes means for generating emergency response scenarios using generative artificial intelligence, means for constructing a virtual environment based on the scenarios using virtual reality and augmented reality technologies, and means for analyzing user behavior in real time using a mobile information terminal and recording user behavior through an information processing device. This enables the provision of individually tailored training to users in a virtual environment, as well as real-time behavioral analysis and feedback.

[0639] "Generative artificial intelligence" is an artificial intelligence technology that uses data and algorithms to generate information that is appropriate to the situation and requirements.

[0640] An "emergency response scenario" is a plan that outlines hypothetical cases and situations requiring necessary actions and decisions during a disaster or emergency.

[0641] "Virtual reality technology" is a technology that uses computer technology to allow users to experience a simulation of an environment that closely resembles reality.

[0642] Augmented reality technology is a technology that overlays digital information onto the real environment, providing users with a combination of reality and virtual reality.

[0643] A "mobile information terminal" is a portable computer device that can be used while on the go, and generally includes smartphones and tablets.

[0644] An "information processing device" is a computer system used for collecting, processing, storing, and analyzing data.

[0645] "Means of analyzing user behavior in real time" refers to methods and technologies for instantly recognizing user actions and performing analysis based on those actions.

[0646] A "database management system" is a software system for efficiently managing, searching, and updating data.

[0647] To implement this invention, a system is constructed in which a server, a terminal, and a user cooperate to conduct disaster prevention training. The server utilizes a generation AI model to generate emergency response scenarios from a disaster knowledge database based on the user's learning level and past training history. These scenarios specifically describe the environment and situation in which the simulation will be conducted, as well as the challenges the user will face. The server then configures these generated scenarios in detail and transmits them to the terminal.

[0648] The terminal constructs virtual reality and augmented reality environments based on received scene data. The terminal interacts with the user's mobile device (e.g., smartphone or tablet) to provide real-time visual and auditory feedback. Unity is used to construct the environment, and internet services such as AWS are used for data management. The user moves freely within this virtual or augmented reality environment, conducting disaster response training. The user's movements and choices are recorded in detail through an information processing device and transmitted to a server.

[0649] The server thoroughly evaluates the user's responses based on the received behavioral data. Evaluation criteria include the speed and accuracy of reactions, and the ability to predict risks. The evaluation results are provided to the user as feedback, guiding them to identify successes, areas for improvement, and to take on more advanced challenges. Through this feedback, users can gradually strengthen their response capabilities, increasing their ability to take swift and accurate action in actual disaster situations.

[0650] As a concrete example, when a user trains at home, the device scans the living space and provides a fire simulation. Through the application, the user trains by selecting the correct evacuation route and checking emergency supplies. In this process, the device records the user's actions and provides feedback, pointing out incorrect choices and suggesting areas for improvement, which can be used to improve future training.

[0651] An example of a prompt message might be: "Generate a scenario for disaster evacuation training. The user is in their 30s and has intermediate-level training experience. They are training with two family members. Focus on evacuation route selection and first aid."

[0652] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0653] Step 1:

[0654] The server uses a generation AI model to input prompts and references a disaster knowledge database. These prompts reflect the user's training history and current learning level. The AI ​​model extracts appropriate information from the database and generates emergency response scenarios. As output, a training scenario tailored to the user is created.

[0655] Step 2:

[0656] Based on the generated scenario, the server meticulously constructs the necessary configuration data for the virtual environment. This includes environmental parameters and simulation conditions for training. This data is then prepared for transmission to the terminal, and the configuration data is sent to the terminal as output.

[0657] Step 3:

[0658] The terminal uses configuration data received from the server to build a virtual reality and augmented reality environment. Unity is used to prepare the scenario that the user will experience. The input includes the scenario and configuration data, and the output is the virtual environment provided to the user.

[0659] Step 4:

[0660] The user begins training in a virtual reality environment via a device. The user works on tasks while freely performing their own movements and actions. Inputs include the user's real-time movements and choices, and output is user experience data, which is recorded on the device.

[0661] Step 5:

[0662] The terminal analyzes user behavior data in real time and transmits that data to the server via an information processing device. Inputs include user movements, choices, and generated experience data, and output is analyzed behavior data.

[0663] Step 6:

[0664] The server evaluates the user's response based on the received behavioral data. An evaluation algorithm is used to analyze reaction speed, accuracy, and judgment ability. The input is the analyzed behavioral data, and the output is the evaluation result.

[0665] Step 7:

[0666] The server uses the evaluation results to provide feedback to the user. This feedback includes areas for improvement and advice for future challenges. The input is the evaluation results, and the output is feedback information sent to the user. The user then uses this feedback to improve their skills.

[0667] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0668] This invention is a system that combines generative artificial intelligence, virtual reality technology, and means for recording user behavior and emotions, and is particularly intended to provide feedback that takes user emotions into account in emergency response training.

[0669] First, the server accesses a disaster knowledge database and generates an emergency response scenario. This includes setting up a specific disaster scene and situation. Based on this scenario, specific data is generated to build a virtual reality environment. This data includes environment settings, voice instructions, and simulation parameters. The server then sends this data to the terminal.

[0670] The device sets up a virtual reality environment based on the received scenario data and provides visual and auditory feedback to help the user immerse themselves. The user can then enter the virtual environment using VR equipment. Here, the emotion engine is activated, collecting data on the user's facial expressions, voice, and body sensors in real time to analyze their emotional state. This information is used to measure the user's stress level and sense of security.

[0671] Based on training scenarios, users take specific actions within a virtual environment. During this time, the terminal meticulously records the user's actions and transmits them to the server along with the inputted emotion data. The training process includes a function that recognizes the user's confusion or anxiety, for example, when selecting an evacuation route, and reflects this in the training results.

[0672] The server comprehensively analyzes behavioral and emotional data to assess the user's coping abilities. This assessment includes identifying appropriate behaviors under emotional pressure and areas for improvement. Based on the assessment, the server generates feedback and sends it to the terminal to provide points to consider and effective coping strategies for future training.

[0673] As a concrete example, in a flood evacuation scenario, the emotion engine evaluates how users react to a sudden rise in water levels from an emotional perspective. As a result, by providing feedback on whether users tend to panic or respond calmly, it is possible to suggest useful measures for actual emergencies.

[0674] Thus, the present invention realizes a system that provides more realistic and effective emergency response training by considering not only user behavior but also emotional data.

[0675] The following describes the processing flow.

[0676] Step 1:

[0677] The server accesses a disaster knowledge database and generates emergency response scenarios. These include the type of disaster, environmental conditions, and the difficulty level of the training. The server then prepares to send the generated scenario data to the terminal.

[0678] Step 2:

[0679] The device constructs a virtual reality environment based on the scenario data it receives. It works in conjunction with the user's VR equipment to provide an immersive experience through sight, sound, and touch. The device completes the environment setup according to the scenario.

[0680] Step 3:

[0681] The user puts on a VR headset and enters the training environment. The emotion engine starts up and prepares to sense data such as the user's facial expressions, voice, and heart rate. The user then begins to act according to the scenario.

[0682] Step 4:

[0683] The device records the user's behavior in the virtual environment. Simultaneously, the emotion engine analyzes the user's emotional state in real time and collects data. Synchronization between behavioral and emotional data is maintained.

[0684] Step 5:

[0685] The server receives behavioral and emotional data transmitted from the terminal. An evaluation algorithm is applied to comprehensively assess the appropriateness of the behavior and the emotional response. Evaluation results based on the user's performance are then generated.

[0686] Step 6:

[0687] The server sends the generated evaluation results and feedback information to the terminal. The terminal presents this information to the user visually and audibly, reporting successes and areas for improvement. It also communicates future countermeasures and training plans.

[0688] Step 7:

[0689] The user reviews the feedback provided and adjusts their response for the next training session. Based on the feedback from the emotional engine, they prepare to further improve their ability by improving their emotional control and response methods.

[0690] (Example 2)

[0691] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0692] In emergency response training, there is a challenge in providing realistic feedback that takes into account not only the user's actions but also their emotional state. Conventional systems are limited to recording the user's physical actions and are unable to collect and analyze the emotional data necessary to improve the effectiveness of the training. As a result, training that can accurately predict how users will react in a real emergency has not been provided.

[0693] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0694] In this invention, the server includes means for generating emergency response scenarios using generative AI, means for constructing a virtual environment based on the scenarios using virtual reality technology, and means for recording user behavior and emotional data in real time. This makes it possible to comprehensively evaluate the user's behavior and emotional state and provide more realistic and effective feedback.

[0695] "Generative AI" is a type of artificial intelligence that uses machine learning techniques to generate new information based on specific conditions and data.

[0696] An "emergency response scenario" is a hypothetical scenario created based on specific situations and response procedures in the event of a disaster or emergency.

[0697] "Virtual reality technology" is a system technology that uses computer graphics and sensor technology to provide users with an experience that closely resembles reality.

[0698] "Means of recording in real time" refers to devices and methods that can record a user's state and actions immediately and without delay, and use them for analysis.

[0699] "Emotional data" refers to data that indicates a user's emotional state, and is information obtained based on physiological data such as facial expressions, tone of voice, and heart rate.

[0700] "Feedback" refers to information provided to users regarding evaluations and areas for improvement as a result of training or processing.

[0701] This invention provides a system that offers feedback that takes into account user behavior and emotions during emergency response training. The system utilizes generative AI models, virtual reality technology, and real-time data collection capabilities as its primary technologies.

[0702] The server uses a generative AI model to create scenarios for responding to disasters and emergencies. These scenarios refer to information from a disaster knowledge database and include scenarios that anticipate specific situations and circumstances. Specific examples include scenarios for "floods" and "earthquakes." The created scenario data is transmitted to the terminal in digital format.

[0703] The device uses VR headsets and sensor technology to build a virtual reality environment based on scenario data and provide users with a visual and auditory experience. By immersing themselves in the virtual environment, users can participate in training under conditions that simulate actual emergencies.

[0704] As users train in a VR space, the device collects user behavioral and emotional data in real time. Emotional data is obtained from the user's facial expressions, changes in voice, and physical indicators such as heart rate. This data is used to evaluate how users react under stress.

[0705] The server comprehensively analyzes behavioral and emotional data transmitted from the terminal to evaluate the user's response capabilities. A generative AI model generates feedback based on this information, which is then transmitted to the terminal as the user's training results. This feedback includes specific advice on which actions were effective and which areas need improvement.

[0706] A concrete example of this training is evaluating whether users were able to respond quickly to rising water levels in a flood evacuation scenario. Another example of a prompt is, "Evaluate the user's emotional response in the flood scenario and generate feedback suggesting behavioral improvements." This trains users to respond effectively in real-world emergencies.

[0707] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0708] Step 1:

[0709] The server accesses a disaster knowledge database and generates emergency response scenarios using a generative AI model. It references past disaster data and training records as input to define specific disaster scenarios. During this process, machine learning algorithms are used to output scenarios that the user should train on. Specifically, the server selects scenarios such as "flood," "earthquake," and "fire," and generates data including detailed settings (e.g., rate of water level rise, evacuation route options).

[0710] Step 2:

[0711] The server sends the generated scenario data to the terminal. The generated scenario information is used as input, and the scenario data in digital format is transferred to the terminal as output. Specifically, the server assembles scenario data packets containing various configuration information and sends them to the terminal via the network.

[0712] Step 3:

[0713] The terminal receives scenario data sent from the server and constructs a virtual reality environment. It takes scenario data as input and sets up the 3D virtual environment that the user experiences as output. Specifically, the terminal controls the VR headset, performs 3D modeling in real time, and provides the user with visual and auditory feedback.

[0714] Step 4:

[0715] The user enters a VR environment and begins training. They receive feedback from their device as input, select their own actions as output, and act within the virtual environment. Specifically, the user selects an evacuation route appropriate to the disaster and follows the corresponding procedures.

[0716] Step 5:

[0717] The device records user behavior and emotional data in real time. It collects user behavior and emotional data (e.g., facial expressions, voice, heart rate) as input and stores training data digitally as output. Specifically, the device analyzes and records physiological information using built-in sensors.

[0718] Step 6:

[0719] The server comprehensively analyzes behavioral and emotional data transmitted from the terminal. It receives recorded data as input and generates a numerical output that evaluates the user's ability to respond. Specifically, the server applies statistical algorithms to analyze the data and identify user response patterns.

[0720] Step 7:

[0721] The server generates feedback based on the analysis results and sends it to the terminal. Evaluation data is used as input, and feedback information is generated to be provided to the user as output. Specifically, the server creates a feedback message containing appropriate actions and areas for improvement, which can be used to help the user in their next training session.

[0722] (Application Example 2)

[0723] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0724] Conventional emergency response training systems only evaluated user behavior, failing to consider the emotional state of users during those actions. This meant they couldn't provide realistic training that took into account users' psychological reactions and stress levels during emergencies, potentially leading to ineffective responses in actual emergencies.

[0725] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0726] In this invention, the server includes means for generating emergency response scenarios using generative artificial intelligence, means for constructing a virtual environment based on the scenarios using virtual reality technology, and means for recording the user's behavior and emotions. This makes it possible to comprehensively evaluate the user's behavior and emotions and provide individually optimized feedback.

[0727] "Generative artificial intelligence" is an active algorithm that analyzes data according to a specified purpose and automatically generates appropriate scenarios and information.

[0728] An "emergency response scenario" is a hypothetical situation designed to outline specific procedures and action plans for responding quickly and appropriately to emergencies such as disasters and accidents.

[0729] "Virtual reality technology" is a technology that uses computer simulation techniques to allow users to experience a virtual environment realistically.

[0730] A "virtual environment" is a digital space created through computer simulation that mimics the real world.

[0731] "User behavior" refers to all specific actions and behaviors that a user takes in the virtual or real world.

[0732] A "means of recording emotions" refers to a system that uses sensors and analytical algorithms to record and store a user's emotional state.

[0733] "Individualized feedback" refers to information that provides advice and suggestions for improvement tailored to a specific user, based on analysis of the user's behavior and reactions.

[0734] In this invention, a server generates emergency response scenarios using generative artificial intelligence, and these scenarios are used to construct a virtual environment using virtual reality technology. Specifically, the server refers to a disaster knowledge database to obtain basic information for constructing a detailed scenario. A terminal receives this scenario data and sets up a virtual environment that can be realistically reproduced on a VR device. Through this, the user can receive emergency response training.

[0735] Users wear VR equipment and immerse themselves in a virtual environment, acting according to training scenarios. During this process, an emotion engine analyzes the user's facial expressions, voice data, and data from sensors attached to their body in real time. This allows the system to determine the user's stress level and emotional state. The device then transmits this data to a server, which integrates and analyzes the behavioral and emotional data.

[0736] As a result, the server generates user-optimized feedback and provides points that will be useful for future training. Specifically, if a user becomes frightened or panics during a fire evacuation scenario, the system will advise on safe evacuation methods. An example of a prompt using the generative AI model is, "Generate a fire evacuation scenario, analyze employee sentiment, and generate optimal feedback."

[0737] This system design allows users to receive more practical and effective training, enabling them to acquire the appropriate response skills for emergencies.

[0738] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0739] Step 1:

[0740] The server retrieves necessary information from a disaster knowledge database and generates emergency response scenarios using artificial intelligence. The input is data retrieved from the disaster knowledge database, and the output is specific scenario information. This scenario information includes details such as the type of disaster and its occurrence.

[0741] Step 2:

[0742] The terminal uses virtual reality technology to construct a virtual environment based on scenario information received from the server. The input is the scenario information sent from the server, and the output is the virtual environment that the user can immerse themselves in using a VR device. Specifically, visual and audio elements are incorporated into the VR environment.

[0743] Step 3:

[0744] The user wears VR equipment and acts according to a training scenario within a virtual environment. Input is visual and auditory stimuli from the virtual environment, and output is user behavior data. This behavior data includes motion information such as evacuation direction and speed.

[0745] Step 4:

[0746] The device uses an emotion engine to analyze the user's facial expressions, voice, and data from sensors worn on the body in real time. The input is this emotional data, and the output is an analysis showing the user's stress level and emotional state. Based on the emotional state, feedback in the virtual environment is adjusted accordingly.

[0747] Step 5:

[0748] The device sends collected user behavioral and emotional data to the server. The input is all the data collected by the device, and the output is an integrated dataset received by the server. This dataset comprehensively records the user's responses.

[0749] Step 6:

[0750] The server integrates behavioral and emotional data to generate optimal feedback for the user. The input is the integrated dataset received by the server, and the output is the feedback information provided to the user. This feedback includes specific improvement suggestions for the next training session.

[0751] Step 7:

[0752] Users receive feedback from the server and review their actions in preparation for emergencies. The input is feedback information from the server, and the output is areas for improvement that are reflected in the user's perception and actions. These improvements will enable users to respond more effectively in subsequent training sessions.

[0753] 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.

[0754] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0755] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0756] 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.

[0757] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0758] 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.

[0759] 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.

[0760] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0761] 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."

[0762] 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.

[0763] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0764] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0773] 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.

[0774] The following is further disclosed regarding the embodiments described above.

[0775] (Claim 1)

[0776] A means of generating emergency response scenarios using generative artificial intelligence,

[0777] A means for constructing a virtual environment based on the aforementioned scenario using virtual reality technology,

[0778] Means for recording user behavior,

[0779] A means for evaluating the aforementioned behavior and providing the evaluation results as feedback,

[0780] A system that includes this.

[0781] (Claim 2)

[0782] The system according to claim 1, wherein the generating artificial intelligence generates a scenario by referring to a disaster knowledge database.

[0783] (Claim 3)

[0784] The system according to claim 1, comprising means for recording user behavior in real time.

[0785] "Example 1"

[0786] (Claim 1)

[0787] A means of generating emergency response scenarios using generative artificial intelligence,

[0788] A means for generating the aforementioned scenario by referring to a disaster knowledge database and considering the learning history,

[0789] A means for constructing a virtual environment based on the aforementioned scenario using virtual reality technology and providing feedback to the user,

[0790] A means of recording user behavior in real time and collecting detailed behavioral data,

[0791] A means for evaluating the aforementioned behavioral data, providing the results as feedback, and suggesting areas for improvement,

[0792] A system that includes this.

[0793] (Claim 2)

[0794] The system according to claim 1, which generates a scenario taking into account the user's learning history.

[0795] (Claim 3)

[0796] The system according to claim 1, comprising means for recording user actions in detail and transmitting them to a server in real time.

[0797] "Application Example 1"

[0798] (Claim 1)

[0799] A means of generating emergency response scenarios using generative artificial intelligence,

[0800] Means for constructing a virtual environment based on the above scenario using virtual reality technology and augmented reality technology,

[0801] A means for recording user behavior through an information processing device,

[0802] A means for evaluating the aforementioned behavior and providing the evaluation results as feedback,

[0803] A means of analyzing user behavior in real time using mobile information terminals,

[0804] Means of using a database management system via an internet connection,

[0805] A system that includes this.

[0806] (Claim 2)

[0807] The system according to claim 1, wherein the generating artificial intelligence generates scenarios by referring to a disaster knowledge database and further takes into account the user's training history.

[0808] (Claim 3)

[0809] The system according to claim 1, comprising means for recording user behavior in real time and providing feedback in an augmented reality environment.

[0810] "Example 2 of combining an emotion engine"

[0811] (Claim 1)

[0812] A means of generating emergency response scenarios using generative AI,

[0813] A means for constructing a virtual environment based on the aforementioned scenario using virtual reality technology,

[0814] A means of recording user behavior and emotional data in real time,

[0815] A means for comprehensively evaluating the aforementioned behavioral and emotional data and providing the evaluation results as feedback,

[0816] A system that includes this.

[0817] (Claim 2)

[0818] The system according to claim 1, wherein a generating AI generates scenarios by referring to a database and uses emotional data for evaluation.

[0819] (Claim 3)

[0820] The system according to claim 1, comprising means for collecting and analyzing user emotional data in real time.

[0821] "Application example 2 when combining with an emotional engine"

[0822] (Claim 1)

[0823] A means of generating emergency response scenarios using generative artificial intelligence,

[0824] A means for constructing a virtual environment based on the aforementioned scenario using virtual reality technology,

[0825] Means for recording user behavior and emotions,

[0826] A means for evaluating the aforementioned behaviors and emotions and providing the evaluation results as individual feedback,

[0827] ...

[0828] A system that includes this.

[0829] (Claim 2)

[0830] The system according to claim 1, wherein the generating artificial intelligence generates a scenario by referring to a disaster knowledge database.

[0831] (Claim 3)

[0832] The system according to claim 1, comprising means for recording user behavior and emotions in real time. [Explanation of Symbols]

[0833] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of generating emergency response scenarios using generative artificial intelligence, A means for constructing a virtual environment based on the aforementioned scenario using virtual reality technology, Means for recording user behavior, A means for evaluating the aforementioned behavior and providing the evaluation results as feedback, A system that includes this.

2. The system according to claim 1, wherein the generating artificial intelligence generates a scenario by referring to a disaster knowledge database.

3. The system according to claim 1, comprising means for recording user behavior in real time.

Images