system

Abstract

We provide the system. [Solution] A means for generating customized training scenarios based on regional characteristics and participant attributes using a generative model, A means of providing a visual simulation of a generated scenario using geographic information, A means of generating real-time feedback based on user behavior, By analyzing the collected data, we can develop methods for evaluating region-specific risks and disaster preparedness. 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, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In disaster prevention training, in order to attract the interest of participants and make preparations for actual disasters more effectively, it is necessary to customize training scenarios according to regional characteristics and the attributes of participants. However, conventional disaster prevention training has had a standardized training content and has not fully reflected regional characteristics and the situations of individual participants. Also, it has been difficult to provide participants with practical experiences assuming various situations.

Means for Solving the Problems

[0005] This invention provides a means for generating customized training scenarios tailored to regional characteristics and participant attributes using a generative model. Furthermore, by including means for visualizing the generated scenarios using geographic information and providing real-time feedback to users, it provides training participants with a practical and effective disaster prevention training experience.

[0006] A "generative model" is an algorithm or system for generating new information or patterns based on data, and in this invention, it is used to create training scenarios that are tailored to regional characteristics and participant attributes.

[0007] "Regional characteristics" refer to various conditions unique to a particular geographical area, such as climate, topography, infrastructure, and disaster risk, and are important elements for optimizing the content of disaster prevention training scenarios.

[0008] "Participant attributes" refer to information about the individual person participating in the training, including age, occupation, past training experience, and health status.

[0009] A "customized training scenario" refers to a disaster preparedness training plan or program that is individually tailored based on the attributes of the participants and the characteristics of the region.

[0010] "Geographic information" refers to information about a specific location on Earth, and includes map data, location information, risk maps, etc.

[0011] "Visual simulation" refers to a technology that provides users with a virtual experience using visually generated scenarios on a computer.

[0012] "Real-time feedback" is a feedback method that enhances the effectiveness of training by providing immediate evaluations and advice on user actions and choices. [Brief explanation of the drawing]

[0013] [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]

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a 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.

[0017] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. 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.

[0019] In the following embodiments, a labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention is a system that provides customized disaster prevention training scenarios based on regional characteristics and participant attributes. This system utilizes generative models and geographic information to provide participants with realistic disaster simulations and feedback.

[0035] Program Overview

[0036] 1. Data Collection and Analysis

[0037] The server first collects regional characteristic data, participant attribute data, historical disaster data, and real-time weather data. This data is then analyzed to determine the optimal training content in the event of a disaster. For example, the server can assess the flood risk in the area and identify evacuation routes that should be used in the training.

[0038] 2. Scenario generation and customization

[0039] The server utilizes a generative model to generate training scenarios based on collected data. These scenarios include specific disaster situations and are customized to reflect region-specific risk factors and participant characteristics. For example, a training exercise with a large elderly participant will generate a scenario that includes special instructions regarding movement and evacuation.

[0040] 3. Provision of visual simulations

[0041] The device provides participants with a visual simulation based on the generated scenario. Using GIS data, it can recreate disaster situations on a local map and show evacuation routes and safe zones. This allows users to experience more realistic disaster scenarios through training.

[0042] 4. Providing real-time feedback

[0043] The server monitors user behavior in real time during the simulation and provides appropriate feedback. For example, it evaluates whether the evacuation route was chosen appropriately and points out areas for improvement as needed, thereby enhancing the effectiveness of the training.

[0044] Specific example

[0045] For example, consider a case where a disaster prevention drill simulating an earthquake is conducted in a certain region.

[0046] The server collects historical earthquake data for the region and analyzes information on vulnerable buildings and infrastructure. It also generates scenarios specifically tailored to participants, assuming they are high school students, focusing on safe actions during evacuation and how to contact family members.

[0047] The device uses the school's geographical information to display evacuation routes and visually indicate the location of emergency assembly points.

[0048] Users act within the presented simulation and receive real-time feedback from the server, allowing them to review their actions and learn areas for improvement.

[0049] In this way, this system enhances the effectiveness of disaster preparedness drills and supports participants in responding appropriately during actual disasters.

[0050] The following describes the processing flow.

[0051] Step 1:

[0052] The server collects regional characteristics data, participant attribute data, historical disaster data, and real-time weather data. This data includes geographic information obtained from regional risk maps, participant basic information, historical disaster patterns, and current weather forecasts. The server analyzes the collected data to assess disaster risk in specific areas.

[0053] Step 2:

[0054] Based on the analysis results, the server generates training scenarios using a generative model. These scenarios define specific disaster situations and are customized according to regional characteristics and participant attributes. For example, the server creates a detailed script that assumes an earthquake, specifying the magnitude of the shaking, evacuation routes, and assembly points.

[0055] Step 3:

[0056] The terminal uses the generated scenario to construct a visual simulation. The terminal utilizes GIS data to recreate disaster situations based on local maps for the user. Evacuation routes and assembly points are visually displayed on the map, and the user begins taking action in the virtual situation accordingly.

[0057] Step 4:

[0058] Users act according to simulations provided on their devices, following designated evacuation routes. During the training, users select their actions in response to situations presented and observe the results.

[0059] Step 5:

[0060] The server monitors the user's actions in real time during the simulation and collects data. The server evaluates the appropriateness of the user's choices and actions and generates immediate feedback. This feedback may be presented as an evaluation such as "The selected evacuation route is appropriate" or as advice such as "This action needs improvement."

[0061] Step 6:

[0062] After the training is complete, the terminal provides the user with comprehensive feedback. The terminal receives feedback data from the server and presents the user with a report. This report includes challenges in the training, successful actions, and suggestions for improvement. The user can use this to plan countermeasures for future training and actual disaster situations.

[0063] (Example 1)

[0064] 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."

[0065] In modern society, it is essential to conduct disaster preparedness drills that are tailored to the varying disaster risks in different regions and the characteristics of individual participants. However, conventional training systems often provided uniform scenarios without adequately considering regional characteristics or the attributes of individual participants. As a result, the effectiveness of the training was limited, and there was a risk that effective actions could not be taken when an actual disaster occurred.

[0066] 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.

[0067] In this invention, the server includes means for generating personalized scenarios based on regional characteristics and user attributes using a generative model; means for providing a visual simulation experience of the generated scenarios using geographic information; means for monitoring user behavior and generating evaluations and feedback in real time; and means for analyzing the collected information and evaluating the region-specific risks and disaster response readiness. This enables personalized and efficient disaster prevention training.

[0068] A "generative model" is an algorithm or framework that learns specific conditions or patterns based on input data and generates new data or scenarios.

[0069] "Regional characteristics" refer to the geographical, climatic, social, and economic features and conditions of a particular region.

[0070] "User attributes" refer to information about individual participants using the training or system, including characteristics such as age, occupation, experience, and physical condition.

[0071] A "scenario" is a plan or narrative that outlines the progression of a series of situations and actions set up for a specific purpose.

[0072] "Geographic information" refers to spatial data related to a specific place or region, including maps, location information, and topographic information.

[0073] "Simulated experience" refers to methods or means of recreating real-world situations and experiencing them virtually.

[0074] "Evaluation" is the process of determining the effectiveness, appropriateness, or outcome of a particular activity or behavior.

[0075] "Feedback" refers to information that provides responses to user actions and results, as well as suggestions for improvement.

[0076] "Risk" refers to the risk of damage or harm that may occur under specific circumstances or conditions.

[0077] "Disaster response preparation" refers to the measures and resources that individuals and organizations need to plan and prepare in advance so that they can respond quickly and appropriately when a disaster occurs.

[0078] As an embodiment for carrying out the present invention, this system has a configuration that provides participants with a practical disaster prevention training experience. Specific examples are shown below.

[0079] The server collects and analyzes regional characteristic data, participant attribute information, historical disaster data, and real-time weather information. Geographic Information System (GIS) software is typically used for this purpose. During the data analysis process, the server applies machine learning algorithms to assess region-specific risk factors.

[0080] The server generates disaster prevention training scenarios using an AI model based on the collected data. The generated scenarios output specific details using prompts. For example, a prompt such as "Create a disaster prevention training scenario that considers regional characteristics and participant attributes" might be used. This program customizes the scenarios individually according to the attributes of different participants.

[0081] The device provides participants with a visual simulation based on the generated training scenario. This includes displaying the progression of the disaster on the screen and highlighting evacuation routes and safe zones based on map data. This visual simulation allows users to learn realistic disaster response through training.

[0082] Users act while experiencing a simulation provided via their device. The server monitors the user's actions in real time and provides evaluations and feedback based on that. The feedback is specific and includes suggestions for improvement, allowing users to review their actions based on the training results and learn what to improve next time.

[0083] This will enable the system to conduct more personalized and effective disaster preparedness drills.

[0084] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0085] Step 1:

[0086] The server collects regional characteristics data, participant attribute data, historical disaster data, and real-time weather data as input. At this stage, the server retrieves the necessary data from various databases and APIs and processes it into a standardized format. The collected data is then used in the next analysis step.

[0087] Step 2:

[0088] The server performs analysis using the collected data. Here, machine learning algorithms are applied to evaluate region-specific risk factors. The input for this analysis is the data standardized in Step 1, and the output is a regional risk assessment report. Specifically, the server compares and analyzes past disaster patterns with the current situation.

[0089] Step 3:

[0090] The server uses a generative AI model to generate customized scenarios based on regional characteristics and participant attributes. In this step, the prompt input is "Create a disaster prevention training scenario that considers regional characteristics and participant attributes." The generated scenarios include all the information necessary for the simulation. During this process, the server incorporates different scenario settings depending on the participant factors.

[0091] Step 4:

[0092] The terminal provides the user with a visual simulation based on the generated training scenario. The input is the scenario generated in step 3, and the output is the result of a visual simulation. Specifically, the terminal utilizes GIS data to represent the progression of the disaster on a map and visually indicates evacuation routes and safe zones.

[0093] Step 5:

[0094] Users participate in the simulation using a terminal and act according to prompts. The server monitors the user's actions in real time and generates appropriate feedback. The input to this feedback process is the user's action data, and the output provides points for improvement and evaluations. Specifically, the server evaluates the accuracy of the evacuation route selected by the user and provides guidance for the next time.

[0095] (Application Example 1)

[0096] 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."

[0097] In recent years, with the increasing frequency and scale of disasters, improving individual and community disaster preparedness has become an urgent task. However, conventional training methods are based on general scenarios and are not customized to regional characteristics or participant attributes, making them less effective in actual disaster situations. Furthermore, there is insufficient mechanism for participants to identify specific areas for improvement after training.

[0098] 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.

[0099] In this invention, the server includes means for generating customized training scenarios based on regional characteristics and participant attributes using a generative model, means for providing a visual simulation of the generated scenarios using geographic information, means for generating real-time feedback based on user behavior, and means for providing an interactive experience to the user and visually indicating emergency situations using a video display device. This enables participants to receive more effective and realistic disaster preparedness training and improve their ability to act calmly during a disaster.

[0100] A "generative model" is an algorithm or system for generating disaster prevention scenarios tailored to specific purposes, based on regional characteristics and participant attributes.

[0101] "Regional characteristics" refer to the features of a particular region, such as its natural environment, geographical conditions, and socioeconomic situation, and are important elements in customizing disaster prevention scenarios.

[0102] "Participant attributes" refer to the characteristics of each individual participating in disaster prevention training, such as age, gender, occupation, and health status, and serve as criteria for optimizing the training content.

[0103] A "training scenario" is a guideline or plan that describes in detail the specific disaster situations and response actions to be assumed in disaster prevention training.

[0104] "Geographic information" refers to data that includes location and topographic information about specific points or regions, and is used for visual reproduction in disaster prevention simulations.

[0105] "Visual simulation" is a method of displaying disaster situations as video to training participants in a way that closely resembles reality, and is a means of improving the training experience.

[0106] "Real-time feedback" is a method that enhances learning effectiveness by immediately evaluating participants' behavior during training and providing immediate suggestions for improvement and guidance.

[0107] A "visual display device" is a device used to display visual information of a training scenario to the user, and is used to give participants a more realistic training experience.

[0108] To realize this invention, a sophisticated system design, including the relevant hardware and software configurations, is essential.

[0109] The server first collects data based on regional characteristics and participant attributes. This data includes historical disaster data and real-time weather information. The server uses cloud computing technologies such as AWS® Lambda to perform data analysis. Based on the analyzed data, a generative AI model is used to generate customized training scenarios tailored to regional characteristics and participant attributes. This process utilizes the OpenAI® API to form scenarios using specific prompt statements.

[0110] The generated scenarios are visually simulated using video display devices on the terminal. Using real-time 3D development platforms such as Unity, disaster situations based on local geographical information are reproduced. This is done in the form of evacuation routes and safe zones displayed on a map. Users can experience this simulation through display devices such as smart glasses.

[0111] User behavior is monitored in real time and evaluated using Google Cloud AI. The server generates and provides real-time feedback based on the user's evacuation route selection and actions. This feedback provides valuable information for participants to learn on the spot and improve their behavior.

[0112] As a concrete example, consider a simulation assuming an earthquake occurs at 10:00 AM. In this case, the user visually receives emergency information and evacuation instructions through smart glasses. The following prompt is used during the training: "Create an evacuation scenario tailored to regional characteristics and participant profiles. Participants are in a high-rise building, and there is a high proportion of elderly people at the scene."

[0113] This system allows users to improve their skills in responding quickly to disasters and ensuring their own safety and the safety of others.

[0114] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0115] Step 1:

[0116] The server collects regional characteristics data, participant attribute data, historical disaster data, and real-time weather data. This data is obtained from various data sources (e.g., weather information APIs, local government databases) and integrated. The server then uses AWS Lambda to perform data analysis, conducting risk assessments based on regional and participant characteristics to prepare for subsequent scenario generation. The results of the data analysis are stored in an appropriate data format.

[0117] Step 2:

[0118] The server uses the OpenAI API to generate customized training scenarios using a generative AI model based on the collected data. Prompts such as "Create an evacuation scenario tailored to regional characteristics and participant profiles. Participants are in a high-rise building, and there is a high proportion of elderly people at the site." are used. The generated scenarios are output as data including specific evacuation routes and action guidelines.

[0119] Step 3:

[0120] The device uses Unity to create a visual simulation based on a generated training scenario, utilizing local geographical information. During this process, map data and GIS data are used as input to visualize the disaster scenario, indicating evacuation routes and safe locations to the user. The completed visual simulation is then transmitted to a display device, such as smart glasses, for the user to experience.

[0121] Step 4:

[0122] Users experience a visual simulation using smart glasses. User behavior data is collected in real time by sensors in the glasses and transmitted to a server. Users follow visual information and audio guidance to select and move along a safe evacuation route.

[0123] Step 5:

[0124] The server uses Google Cloud AI to analyze user behavior data and generate feedback. Based on the input behavior data, it evaluates the appropriateness of the user's evacuation route selection and adherence to safety behaviors, and identifies areas for improvement as needed. The generated feedback is provided to the user in real time, allowing the user to immediately modify their behavior.

[0125] 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.

[0126] This invention combines a system that provides customized disaster prevention training scenarios considering regional characteristics and participant attributes with an emotion engine that recognizes user emotions. This system can grasp the user's psychological state in real time and provide emotion-based feedback and adjust the training content accordingly.

[0127] Program Overview

[0128] 1. Data Collection and Analysis

[0129] The server collects regional characteristics data, participant attribute data, historical disaster data, and real-time weather data. In addition, an emotion engine acquires and analyzes user emotion data. This data is used to predict psychological responses, particularly during disasters.

[0130] 2. Scenario generation and customization

[0131] The server uses a generative model to generate training scenarios based on the analyzed data. The generated scenarios are customized to take into account expected emotional responses to specific disaster scenes. For example, instructions encouraging calmness are included for participants who are prone to stress.

[0132] 3. Provision of visual simulations

[0133] The device provides users with a visual simulation based on the generated scenario. Using GIS data, it reproduces situations that users may face on a map. Through the simulation, users receive training that closely resembles the actual conditions during a disaster.

[0134] 4. Real-time feedback based on emotional data

[0135] The server monitors the user's emotional state, obtained from the emotion engine, during the simulation. For example, if the user shows anxiety, the server provides real-time feedback corresponding to that emotion and offers advice to alleviate the anxiety.

[0136] 5. Post-training summary feedback

[0137] The device provides users with comprehensive feedback after the training is complete. The report includes changes in the user's emotions, behavioral responses, and suggestions for improvement. Users use this feedback to mentally prepare for future training or actual disaster situations.

[0138] Specific example

[0139] For example, when conducting a disaster preparedness drill simulating a typhoon in a given area, the server analyzes past typhoon data and current weather forecasts for the region to assess the impact on the participating schools. Furthermore, the emotion engine monitors the participants' psychological state, detecting anxiety and tension. The terminal simulates a map of the school's surroundings and presents evacuation routes, providing users with a practical evacuation drill. The server evaluates the routes and actions chosen by the users, provides real-time feedback as needed, and delivers a report including psychological coping strategies after the drill. This allows participants to learn how to act more effectively during disasters and strengthen their emotional preparedness.

[0140] The following describes the processing flow.

[0141] Step 1:

[0142] The server collects regional characteristic data, participant attribute data, historical disaster occurrence data, and real-time weather data. In addition, it activates an emotion engine to monitor the emotions of users participating in the training and obtain baseline emotion data. This data forms the basis for more realistic training scenarios.

[0143] Step 2:

[0144] The server analyzes the collected data and uses generative models to generate customized training scenarios. These scenarios reflect local risks, participant attributes, and individual responses based on emotional data. For example, if a particular participant is found to be sensitive to stress, the scenario will include instructions for stress reduction.

[0145] Step 3:

[0146] The device provides users with a visual simulation based on the generated scenario. It utilizes GIS maps to display the user's current location and evacuation routes in real time. Based on this visual information, users can proceed with virtual training and simulate the experience of moving to a safe evacuation site.

[0147] Step 4:

[0148] Users participate in the simulation while operating their devices. The user's behavior during training is monitored in real time by an emotion engine, which detects the user's emotional state (e.g., anxiety, reassurance, concentration, etc.).

[0149] Step 5:

[0150] The server analyzes user behavior and emotional data acquired during training. Based on the user's emotional changes, it instantly generates feedback and provides it to the user through the terminal. If the user's stress level increases, it attempts to improve the situation by providing instructions to promote relaxation and information to promote reassurance.

[0151] Step 6:

[0152] The device displays comprehensive feedback to the user after the training is complete. This feedback includes an evaluation of user behavior, an analysis of emotional changes, and suggestions for improvement. This information allows users to refine their future training and disaster response plans.

[0153] (Example 2)

[0154] 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".

[0155] Conventional disaster preparedness training systems can only provide training based on uniform scenarios and cannot conduct customized training that takes into account regional characteristics or individual emotional states. Furthermore, they do not provide real-time feedback that reflects users' emotional responses during training, making it difficult for participants to learn effective responses in actual disaster situations.

[0156] 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.

[0157] In this invention, the server includes means for generating customized training scenarios based on regional characteristics and participant attributes using a generative AI model, means for providing a visual simulation of the generated scenarios using geographic information, and means for generating real-time feedback based on user behavior and emotional data. This makes it possible to provide a more practical and effective disaster prevention training experience that takes into account regional characteristics and individual emotional states.

[0158] A "generative AI model" is an artificial intelligence technology that processes information based on regional characteristics and participant attributes to automatically create specific scenarios.

[0159] "Regional characteristics" refer to the unique environmental, geographical, and climatic conditions of a particular region, and include information related to the occurrence and impact of disasters.

[0160] "Participant attributes" refer to the personal characteristics of each individual participating in the disaster prevention drill, such as age, gender, experience, and psychological state.

[0161] A "training scenario" refers to a series of hypothetical situations created in disaster prevention training to allow participants to experience specific circumstances and learn how to respond to them.

[0162] "Visual simulation" refers to a technology that uses computer graphics and geographic information systems to visually reproduce disaster situations within a virtual environment.

[0163] "Emotional data" refers to information about the user's current psychological state, including the degree of stress and anxiety obtained from audio and video.

[0164] "Real-time feedback" refers to advice and suggestions for improvement that are provided instantly in response to the behavior and emotions of participants during training.

[0165] "Geographic information" refers to information related to a specific location, including maps and location data, and is used for creating training scenarios and visual simulations.

[0166] In implementing this invention, the server and terminals play a central role in the system. The server first collects regional characteristic data, participant attribute data, historical disaster data, and real-time weather data using external databases and APIs. This forms an integrated dataset that forms the basis of the training scenarios.

[0167] Next, the server uses an emotion engine to analyze emotions from the audio and video data provided by the user. Here, machine learning libraries such as TENSORFLOW® are used to analyze stress levels from audio and changes in facial expressions from video. This analyzed data is then considered when generating behavioral scenarios.

[0168] Next, the server uses a generative AI model to create a customized training scenario. For example, by using the prompt "Create a disaster prevention training scenario that takes into account situations that might cause anxiety for participants, based on geographical data of a specific region," a customized scenario is generated.

[0169] The device provides a visual simulation based on this generated scenario. Using technologies such as Unity and Unreal Engine, and leveraging GIS data, it realistically reproduces the disaster situation the user will face in the virtual environment. This allows the user to learn practical evacuation actions.

[0170] Furthermore, the server monitors the user's emotional state in real time during the simulation and provides appropriate feedback. For example, if the user shows signs of anxiety, the server instantly generates and provides advice and suggestions for improvement tailored to that situation.

[0171] Finally, after the training, the device provides the user with a summary of the feedback. This report includes an assessment of emotional changes and behavior, and is available to the user in PDF format. This allows the user to obtain specific and practical guidance for future training and preparations for actual disasters.

[0172] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0173] Step 1:

[0174] The server collects regional characteristics data, participant attribute data, historical disaster data, and real-time weather data from external databases and APIs. Inputs include API keys and queries for various databases. Data processing is performed using Pandas for data cleaning and integration, resulting in a processed, integrated dataset. This integrated dataset is used in subsequent steps.

[0175] Step 2:

[0176] The server utilizes an emotion engine to acquire user emotion data from audio and video. It receives user-provided audio files and video streams as input, which are analyzed using TensorFlow. Through data processing, it recognizes stress levels and changes in facial expressions, and outputs emotion analysis results. These results are useful for customizing training scenarios.

[0177] Step 3:

[0178] The server uses a generative AI model to construct customized training scenarios. Inputs include an integrated dataset, sentiment analysis results, and specific prompt sentences. The prompt sentence used to instruct the AI ​​model is "Create a training scenario that considers situations where participants might feel anxious, based on geographical data of a specific region." This generates a training scenario as output.

[0179] Step 4:

[0180] The terminal deploys a visual simulation based on the generated scenario. The input consists of the generated scenario and geographical information, and the simulation is generated using Unity or Unreal Engine. Data processing involves analyzing GIS data to construct a disaster scene in a virtual environment. The output provides a detailed visual simulation for user viewing.

[0181] Step 5:

[0182] The server monitors the user's emotional data in real time during the simulation and generates corresponding feedback. It takes real-time emotional data as input and uses NLP techniques to create appropriate feedback. Output includes advice messages and action plans to provide to the user.

[0183] Step 6:

[0184] The device provides users with comprehensive feedback after training is complete. It receives behavioral and emotional data recorded during training as input, which is then analyzed to generate a report. The output is a PDF report containing improvements in new behaviors and changes in emotions, which users can view on their own device.

[0185] (Application Example 2)

[0186] 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 device 14 will be referred to as the "terminal."

[0187] In recent years, the importance of being able to respond quickly and calmly to natural disasters and sudden security risks has increased. However, many disaster preparedness drills are uniform and lack consideration for the psychological state and emotions of participants, often raising questions about their effectiveness. In particular, the lack of training systems that can provide appropriate feedback when psychological anxiety or confusion occurs is a challenge.

[0188] 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.

[0189] In this invention, the server includes means for generating customized training scenarios based on regional characteristics and participant attributes using a generative model, means for providing a visual simulation of the generated scenarios using geographic information, and means for evaluating the user's psychological state in real time using emotion recognition technology. This makes it possible to provide feedback based on the participant's emotional state and realize a practical and psychologically effective training experience.

[0190] A "generative model" is a mathematical or computer code template used to automatically create scenarios that meet specific conditions based on regional characteristics and participant attributes.

[0191] "Geographic information" refers to information that includes relevant data about a region, and is data that indicates geographical characteristics such as location and environment.

[0192] "Emotion recognition technology" is a technology that analyzes a user's psychological state from their facial expressions, voice, text, etc., and evaluates their emotions in real time.

[0193] "Real-time feedback" is a process that provides immediate responses based on user behavior and emotions.

[0194] A "simulation" is a simulated experience in a virtual environment that virtually reproduces real-world situations, with the purpose of educating users and conducting verification.

[0195] "Psychological state" refers to the emotional and thought processes a user exhibits, and is a concept that includes internal expressions such as anxiety, joy, and tension.

[0196] "Feedback" refers to the evaluations and advice that a system provides to a user, and it is information that is adjusted in response to changes in behavior and emotions.

[0197] A description of the embodiment for carrying out the invention will be provided.

[0198] The system that realizes this application example consists of a server and terminals (e.g., smartphones), enabling customized disaster prevention training based on regional characteristics and participant attributes.

[0199] The server uses a generative model to collect and analyze regional characteristics data and participant attribute data, and generates training scenarios based on this data. This generative model utilizes cloud services to take into account geographic information within the region and uses GIS data to provide visual simulations. In addition, it uses emotion recognition technologies such as Azure Cognitive Services to evaluate the user's psychological state in real time.

[0200] The device provides the user with a visual simulation based on this generated training scenario. The software used can include map display libraries such as Leaflet.js. This allows the user to experience a simulated disaster that closely resembles an actual event. Furthermore, the user's emotional data is sent to the server, and they receive appropriate feedback in real time based on the analysis results.

[0201] As a concrete example, consider a disaster preparedness drill conducted at a local school, simulating a typhoon. The server analyzes past typhoon data and current weather forecasts, generating a training scenario based on geographical information of the area expected to be affected by the typhoon. Furthermore, an emotion engine monitors participants' psychological states, detecting anxiety and tension. The terminal uses a map of the school's surroundings to perform the simulation and presents the optimal evacuation route. Through this simulation, users can learn appropriate actions to take in the event of a disaster.

[0202] An example of a prompt message would be, "Generate an evacuation scenario for the expected typhoon at the current location, analyze the user's psychological state in real time, and provide reassuring feedback." In this way, users can learn to respond quickly and calmly during disasters.

[0203] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0204] Step 1:

[0205] The server collects regional characteristics data and participant attribute data. Meteorological data and Geographic Information System (GIS) data are also acquired at this time. The data is organized on the cloud and processed as foundational information for generating training scenarios. The collected data is integrated within the server and stored as an initial dataset.

[0206] Step 2:

[0207] The server uses a generative AI model based on the collected data to generate customized training scenarios. The input includes participant attributes and regional characteristics, and data processing based on this information generates scenarios tailored to each participant. The generated scenarios are stored in a database for later use.

[0208] Step 3:

[0209] The terminal receives training scenarios sent from the server and provides a visual simulation using geographic information. Here, a map display library such as Leaflet.js is used to execute a disaster simulation tailored to the user's location. This allows the user to visually confirm safe evacuation routes and their surrounding conditions.

[0210] Step 4:

[0211] The server uses Azure Cognitive Services to analyze user emotional data in real time. It analyzes voice and facial expression data as input and uses the results to determine the user's psychological state. The obtained emotional data is then used for subsequent feedback.

[0212] Step 5:

[0213] The server generates real-time feedback based on analyzed emotional data and sends it to the device. For users who show anxiety or stress, it creates calming instructions and encouraging messages. This generated feedback is received by the user as practical advice, which they then use to guide their actions.

[0214] Step 6:

[0215] Users review feedback from the device and attempt to modify their behavior accordingly. They gain training experience while referring to the visual simulations provided by the device. Finally, they conduct a self-assessment and prepare for the next training session based on the report provided after the training is completed.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] [Second Embodiment]

[0220] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0221] 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.

[0222] 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).

[0223] 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.

[0224] 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.

[0225] 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).

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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".

[0232] This invention is a system that provides customized disaster prevention training scenarios based on regional characteristics and participant attributes. This system utilizes generative models and geographic information to provide participants with realistic disaster simulations and feedback.

[0233] Program Overview

[0234] 1. Data Collection and Analysis

[0235] The server first collects regional characteristic data, participant attribute data, historical disaster data, and real-time weather data. This data is then analyzed to determine the optimal training content in the event of a disaster. For example, the server can assess the flood risk in the area and identify evacuation routes that should be used in the training.

[0236] 2. Scenario generation and customization

[0237] The server utilizes a generative model to generate training scenarios based on collected data. These scenarios include specific disaster situations and are customized to reflect region-specific risk factors and participant characteristics. For example, a training exercise with a large elderly participant will generate a scenario that includes special instructions regarding movement and evacuation.

[0238] 3. Provision of visual simulations

[0239] The device provides participants with a visual simulation based on the generated scenario. Using GIS data, it can recreate disaster situations on a local map and show evacuation routes and safe zones. This allows users to experience more realistic disaster scenarios through training.

[0240] 4. Providing real-time feedback

[0241] The server monitors user behavior in real time during the simulation and provides appropriate feedback. For example, it evaluates whether the evacuation route was chosen appropriately and points out areas for improvement as needed, thereby enhancing the effectiveness of the training.

[0242] Specific example

[0243] For example, consider a case where a disaster prevention drill simulating an earthquake is conducted in a certain region.

[0244] The server collects historical earthquake data for the region and analyzes information on vulnerable buildings and infrastructure. It also generates scenarios specifically tailored to participants, assuming they are high school students, focusing on safe actions during evacuation and how to contact family members.

[0245] The device uses the school's geographical information to display evacuation routes and visually indicate the location of emergency assembly points.

[0246] Users act within the presented simulation and receive real-time feedback from the server, allowing them to review their actions and learn areas for improvement.

[0247] In this way, this system enhances the effectiveness of disaster preparedness drills and supports participants in responding appropriately during actual disasters.

[0248] The following describes the processing flow.

[0249] Step 1:

[0250] The server collects regional characteristics data, participant attribute data, historical disaster data, and real-time weather data. This data includes geographic information obtained from regional risk maps, participant basic information, historical disaster patterns, and current weather forecasts. The server analyzes the collected data to assess disaster risk in specific areas.

[0251] Step 2:

[0252] Based on the analysis results, the server generates training scenarios using a generative model. These scenarios define specific disaster situations and are customized according to regional characteristics and participant attributes. For example, the server creates a detailed script that assumes an earthquake, specifying the magnitude of the shaking, evacuation routes, and assembly points.

[0253] Step 3:

[0254] The terminal uses the generated scenario to construct a visual simulation. The terminal utilizes GIS data to recreate disaster situations based on local maps for the user. Evacuation routes and assembly points are visually displayed on the map, and the user begins taking action in the virtual situation accordingly.

[0255] Step 4:

[0256] Users act according to simulations provided on their devices, following designated evacuation routes. During the training, users select their actions in response to situations presented and observe the results.

[0257] Step 5:

[0258] The server monitors the user's actions in real time during the simulation and collects data. The server evaluates the appropriateness of the user's choices and actions and generates immediate feedback. This feedback may be presented as an evaluation such as "The selected evacuation route is appropriate" or as advice such as "This action needs improvement."

[0259] Step 6:

[0260] After the training is complete, the terminal provides the user with comprehensive feedback. The terminal receives feedback data from the server and presents the user with a report. This report includes challenges in the training, successful actions, and suggestions for improvement. The user can use this to plan countermeasures for future training and actual disaster situations.

[0261] (Example 1)

[0262] 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."

[0263] In modern society, it is essential to conduct disaster preparedness drills that are tailored to the varying disaster risks in different regions and the characteristics of individual participants. However, conventional training systems often provided uniform scenarios without adequately considering regional characteristics or the attributes of individual participants. As a result, the effectiveness of the training was limited, and there was a risk that effective actions could not be taken when an actual disaster occurred.

[0264] 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.

[0265] In this invention, the server includes means for generating personalized scenarios based on regional characteristics and user attributes using a generative model; means for providing a visual simulation experience of the generated scenarios using geographic information; means for monitoring user behavior and generating evaluations and feedback in real time; and means for analyzing the collected information and evaluating the region-specific risks and disaster response readiness. This enables personalized and efficient disaster prevention training.

[0266] A "generative model" is an algorithm or framework that learns specific conditions or patterns based on input data and generates new data or scenarios.

[0267] "Regional characteristics" refer to the geographical, climatic, social, and economic features and conditions of a particular region.

[0268] "User attributes" refer to information about individual participants using the training or system, including characteristics such as age, occupation, experience, and physical condition.

[0269] A "scenario" is a plan or narrative that outlines the progression of a series of situations and actions set up for a specific purpose.

[0270] "Geographic information" refers to spatial data related to a specific place or region, including maps, location information, and topographic information.

[0271] "Simulated experience" refers to methods or means of recreating real-world situations and experiencing them virtually.

[0272] "Evaluation" is the process of determining the effectiveness, appropriateness, or outcome of a particular activity or behavior.

[0273] "Feedback" refers to information that provides responses to user actions and results, as well as suggestions for improvement.

[0274] "Risk" refers to the risk of damage or harm that may occur under specific circumstances or conditions.

[0275] "Disaster response preparation" refers to the measures and resources that individuals and organizations need to plan and prepare in advance so that they can respond quickly and appropriately when a disaster occurs.

[0276] As an embodiment for carrying out the present invention, this system has a configuration that provides participants with a practical disaster prevention training experience. Specific examples are shown below.

[0277] The server collects and analyzes regional characteristic data, participant attribute information, historical disaster data, and real-time weather information. Geographic Information System (GIS) software is typically used for this purpose. During the data analysis process, the server applies machine learning algorithms to assess region-specific risk factors.

[0278] The server generates disaster prevention training scenarios using an AI model based on the collected data. The generated scenarios output specific details using prompts. For example, a prompt such as "Create a disaster prevention training scenario that considers regional characteristics and participant attributes" might be used. This program customizes the scenarios individually according to the attributes of different participants.

[0279] The terminal provides a visual simulation to the participants based on the generated training scenario. This includes showing the progress of the disaster on the screen and highlighting evacuation routes and safe zones based on map data. Through this visual simulation, users can learn realistic disaster response through training.

[0280] The user acts while experiencing the simulation provided via the terminal. The server monitors the user's actions in real time and provides evaluation and feedback based on them. The feedback includes specifics and suggestions for improvement, and the user can review their actions based on the training results and learn the areas for improvement for the next time.

[0281] This enables the system to conduct more individualized and effective disaster prevention training.

[0282] The flow of the specific process in Example 1 will be described using FIG. 11.

[0283] Step 1:

[0284] The server collects regional characteristic data, participant attribute data, past disaster data, and real-time weather data as inputs. At this stage, the server obtains the necessary data from various databases and APIs and processes the data into a standardized format. The collected data is used in the following analysis step.

[0285] Step 2:

[0286] The server performs analysis using the collected data. Here, a machine learning algorithm is applied to evaluate region-specific risk factors. The input for this analysis is the data standardized in Step 1, and a regional risk assessment report is obtained as the output. As a specific operation, the server conducts a comparative analysis of past disaster patterns and the current situation. <tmp <tmp

[0287] <tmp Step 3:

[0288] The server uses a generative AI model to generate customized scenarios based on regional characteristics and participant attributes. In this step, the prompt input is "Create a disaster prevention training scenario that considers regional characteristics and participant attributes." The generated scenarios include all the information necessary for the simulation. During this process, the server incorporates different scenario settings depending on the participant factors.

[0289] Step 4:

[0290] The terminal provides the user with a visual simulation based on the generated training scenario. The input is the scenario generated in step 3, and the output is the result of a visual simulation. Specifically, the terminal utilizes GIS data to represent the progression of the disaster on a map and visually indicates evacuation routes and safe zones.

[0291] Step 5:

[0292] Users participate in the simulation using a terminal and act according to prompts. The server monitors the user's actions in real time and generates appropriate feedback. The input to this feedback process is the user's action data, and the output provides points for improvement and evaluations. Specifically, the server evaluates the accuracy of the evacuation route selected by the user and provides guidance for the next time.

[0293] (Application Example 1)

[0294] 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."

[0295] In recent years, with the increasing frequency and scale of disasters, improving individual and community disaster preparedness has become an urgent task. However, conventional training methods are based on general scenarios and are not customized to regional characteristics or participant attributes, making them less effective in actual disaster situations. Furthermore, there is insufficient mechanism for participants to identify specific areas for improvement after training.

[0296] 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.

[0297] In this invention, the server includes means for generating customized training scenarios based on regional characteristics and participant attributes using a generative model, means for providing a visual simulation of the generated scenarios using geographic information, means for generating real-time feedback based on user behavior, and means for providing an interactive experience to the user and visually indicating emergency situations using a video display device. This enables participants to receive more effective and realistic disaster preparedness training and improve their ability to act calmly during a disaster.

[0298] A "generative model" is an algorithm or system for generating disaster prevention scenarios tailored to specific purposes, based on regional characteristics and participant attributes.

[0299] "Regional characteristics" refer to the features of a particular region, such as its natural environment, geographical conditions, and socioeconomic situation, and are important elements in customizing disaster prevention scenarios.

[0300] "Participant attributes" refer to the characteristics of each individual participating in disaster prevention training, such as age, gender, occupation, and health status, and serve as criteria for optimizing the training content.

[0301] A "training scenario" is a guideline or plan that describes in detail the specific disaster situations and response actions to be assumed in disaster prevention training.

[0302] "Geographic information" refers to data that includes location information and topographic information related to specific points or regions, and is used for visual reproduction in disaster prevention simulations.

[0303] "Visual simulation" refers to a method of displaying disaster situations in a realistic form as videos to training participants, and is a means to improve the training experience.

[0304] "Real-time feedback" refers to a method of enhancing the learning effect by immediately evaluating the actions of participants during training and providing improvement points and guidance on the spot.

[0305] "Video display device" refers to a device for displaying visual information of a training scenario to users, and is used for participants to obtain a more realistic training experience.

[0306] To realize this invention, an advanced system design including related hardware and software configurations is essential.

[0307] The server first collects data based on regional characteristics and participant attributes. This data includes past disaster data and real-time weather information. The server uses cloud computing technologies such as AWS Lambda to conduct data analysis. Based on the analyzed data, a customized training scenario is generated using a generative AI model according to regional characteristics and participant attributes. In this process, the OpenAI API is utilized, and specific prompt texts are used to form the scenario.

[0308] The generated scenario is visually simulated using a video display device by the terminal. A real-time 3D development platform such as Unity is used to reproduce the disaster situation based on the geographic information of the region. This is in the form of showing evacuation routes and safe zones on a map. The user can experience this simulation through a display device such as smart glasses.

[0309] User behavior is monitored in real time and evaluated using Google Cloud AI. The server generates and provides real-time feedback based on the user's evacuation route selection and actions. This feedback provides valuable information for participants to learn on the spot and improve their behavior.

[0310] As a concrete example, consider a simulation assuming an earthquake occurs at 10:00 AM. In this case, the user visually receives emergency information and evacuation instructions through smart glasses. The following prompt is used during the training: "Create an evacuation scenario tailored to regional characteristics and participant profiles. Participants are in a high-rise building, and there is a high proportion of elderly people at the scene."

[0311] This system allows users to improve their skills in responding quickly to disasters and ensuring their own safety and the safety of others.

[0312] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0313] Step 1:

[0314] The server collects regional characteristics data, participant attribute data, historical disaster data, and real-time weather data. This data is obtained from various data sources (e.g., weather information APIs, local government databases) and integrated. The server then uses AWS Lambda to perform data analysis, conducting risk assessments based on regional and participant characteristics to prepare for subsequent scenario generation. The results of the data analysis are stored in an appropriate data format.

[0315] Step 2:

[0316] The server uses the OpenAI API to generate customized training scenarios using a generative AI model based on the collected data. Prompts such as "Create an evacuation scenario tailored to regional characteristics and participant profiles. Participants are in a high-rise building, and there is a high proportion of elderly people at the site." are used. The generated scenarios are output as data including specific evacuation routes and action guidelines.

[0317] Step 3:

[0318] The device uses Unity to create a visual simulation based on a generated training scenario, utilizing local geographical information. During this process, map data and GIS data are used as input to visualize the disaster scenario, indicating evacuation routes and safe locations to the user. The completed visual simulation is then transmitted to a display device, such as smart glasses, for the user to experience.

[0319] Step 4:

[0320] Users experience a visual simulation using smart glasses. User behavior data is collected in real time by sensors in the glasses and transmitted to a server. Users follow visual information and audio guidance to select and move along a safe evacuation route.

[0321] Step 5:

[0322] The server uses Google Cloud AI to analyze user behavior data and generate feedback. Based on the input behavior data, it evaluates the appropriateness of the user's evacuation route selection and adherence to safety behaviors, and identifies areas for improvement as needed. The generated feedback is provided to the user in real time, allowing the user to immediately modify their behavior.

[0323] 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.

[0324] This invention combines a system that provides customized disaster prevention training scenarios considering regional characteristics and participant attributes with an emotion engine that recognizes user emotions. This system can grasp the user's psychological state in real time and provide emotion-based feedback and adjust the training content accordingly.

[0325] Program Overview

[0326] 1. Data Collection and Analysis

[0327] The server collects regional characteristics data, participant attribute data, historical disaster data, and real-time weather data. In addition, an emotion engine acquires and analyzes user emotion data. This data is used to predict psychological responses, particularly during disasters.

[0328] 2. Scenario generation and customization

[0329] The server uses a generative model to generate training scenarios based on the analyzed data. The generated scenarios are customized to take into account expected emotional responses to specific disaster scenes. For example, instructions encouraging calmness are included for participants who are prone to stress.

[0330] 3. Provision of visual simulations

[0331] The device provides users with a visual simulation based on the generated scenario. Using GIS data, it reproduces situations that users may face on a map. Through the simulation, users receive training that closely resembles the actual conditions during a disaster.

[0332] 4. Real-time feedback based on emotional data

[0333] The server monitors the user's emotional state, obtained from the emotion engine, during the simulation. For example, if the user shows anxiety, the server provides real-time feedback corresponding to that emotion and offers advice to alleviate the anxiety.

[0334] 5. Post-training summary feedback

[0335] The device provides users with comprehensive feedback after the training is complete. The report includes changes in the user's emotions, behavioral responses, and suggestions for improvement. Users use this feedback to mentally prepare for future training or actual disaster situations.

[0336] Specific example

[0337] For example, when conducting a disaster preparedness drill simulating a typhoon in a given area, the server analyzes past typhoon data and current weather forecasts for the region to assess the impact on the participating schools. Furthermore, the emotion engine monitors the participants' psychological state, detecting anxiety and tension. The terminal simulates a map of the school's surroundings and presents evacuation routes, providing users with a practical evacuation drill. The server evaluates the routes and actions chosen by the users, provides real-time feedback as needed, and delivers a report including psychological coping strategies after the drill. This allows participants to learn how to act more effectively during disasters and strengthen their emotional preparedness.

[0338] The following describes the processing flow.

[0339] Step 1:

[0340] The server collects regional characteristic data, participant attribute data, historical disaster occurrence data, and real-time weather data. In addition, it activates an emotion engine to monitor the emotions of users participating in the training and obtain baseline emotion data. This data forms the basis for more realistic training scenarios.

[0341] Step 2:

[0342] The server analyzes the collected data and uses generative models to generate customized training scenarios. These scenarios reflect local risks, participant attributes, and individual responses based on emotional data. For example, if a particular participant is found to be sensitive to stress, the scenario will include instructions for stress reduction.

[0343] Step 3:

[0344] The device provides users with a visual simulation based on the generated scenario. It utilizes GIS maps to display the user's current location and evacuation routes in real time. Based on this visual information, users can proceed with virtual training and simulate the experience of moving to a safe evacuation site.

[0345] Step 4:

[0346] Users participate in the simulation while operating their devices. The user's behavior during training is monitored in real time by an emotion engine, which detects the user's emotional state (e.g., anxiety, reassurance, concentration, etc.).

[0347] Step 5:

[0348] The server analyzes user behavior and emotional data acquired during training. Based on the user's emotional changes, it instantly generates feedback and provides it to the user through the terminal. If the user's stress level increases, it attempts to improve the situation by providing instructions to promote relaxation and information to promote reassurance.

[0349] Step 6:

[0350] The device displays comprehensive feedback to the user after the training is complete. This feedback includes an evaluation of user behavior, an analysis of emotional changes, and suggestions for improvement. This information allows users to refine their future training and disaster response plans.

[0351] (Example 2)

[0352] 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".

[0353] Conventional disaster preparedness training systems can only provide training based on uniform scenarios and cannot conduct customized training that takes into account regional characteristics or individual emotional states. Furthermore, they do not provide real-time feedback that reflects users' emotional responses during training, making it difficult for participants to learn effective responses in actual disaster situations.

[0354] 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.

[0355] In this invention, the server includes means for generating customized training scenarios based on regional characteristics and participant attributes using a generative AI model, means for providing a visual simulation of the generated scenarios using geographic information, and means for generating real-time feedback based on user behavior and emotional data. This makes it possible to provide a more practical and effective disaster prevention training experience that takes into account regional characteristics and individual emotional states.

[0356] A "generative AI model" is an artificial intelligence technology that processes information based on regional characteristics and participant attributes to automatically create specific scenarios.

[0357] "Regional characteristics" refer to the unique environmental, geographical, and climatic conditions of a particular region, and include information related to the occurrence and impact of disasters.

[0358] "Participant attributes" refer to the personal characteristics of each individual participating in the disaster prevention drill, such as age, gender, experience, and psychological state.

[0359] A "training scenario" refers to a series of hypothetical situations created in disaster prevention training to allow participants to experience specific circumstances and learn how to respond to them.

[0360] "Visual simulation" refers to a technology that uses computer graphics and geographic information systems to visually reproduce disaster situations within a virtual environment.

[0361] "Emotional data" refers to information about the user's current psychological state, including the degree of stress and anxiety obtained from audio and video.

[0362] "Real-time feedback" refers to advice and suggestions for improvement that are provided instantly in response to the behavior and emotions of participants during training.

[0363] "Geographic information" refers to information related to a specific location, including maps and location data, and is used for creating training scenarios and visual simulations.

[0364] In implementing this invention, the server and terminals play a central role in the system. The server first collects regional characteristic data, participant attribute data, historical disaster data, and real-time weather data using external databases and APIs. This forms an integrated dataset that forms the basis of the training scenarios.

[0365] Next, the server uses an emotion engine to analyze emotions from the audio and video data provided by the user. Here, machine learning libraries such as TensorFlow are used to analyze stress levels from audio and changes in facial expressions from video. This analyzed data is then considered when generating behavioral scenarios.

[0366] Next, the server uses a generative AI model to create a customized training scenario. For example, by using the prompt "Create a disaster prevention training scenario that takes into account situations that might cause anxiety for participants, based on geographical data of a specific region," a customized scenario is generated.

[0367] The device provides a visual simulation based on this generated scenario. Using technologies such as Unity and Unreal Engine, and leveraging GIS data, it realistically reproduces the disaster situation the user will face in the virtual environment. This allows the user to learn practical evacuation actions.

[0368] Furthermore, the server monitors the user's emotional state in real time during the simulation and provides appropriate feedback. For example, if the user shows signs of anxiety, the server instantly generates and provides advice and suggestions for improvement tailored to that situation.

[0369] Finally, after the training, the device provides the user with a summary of the feedback. This report includes an assessment of emotional changes and behavior, and is available to the user in PDF format. This allows the user to obtain specific and practical guidance for future training and preparations for actual disasters.

[0370] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0371] Step 1:

[0372] The server collects regional characteristics data, participant attribute data, historical disaster data, and real-time weather data from external databases and APIs. Inputs include API keys and queries for various databases. Data processing is performed using Pandas for data cleaning and integration, resulting in a processed, integrated dataset. This integrated dataset is used in subsequent steps.

[0373] Step 2:

[0374] The server utilizes an emotion engine to acquire user emotion data from audio and video. It receives user-provided audio files and video streams as input, which are analyzed using TensorFlow. Through data processing, it recognizes stress levels and changes in facial expressions, and outputs emotion analysis results. These results are useful for customizing training scenarios.

[0375] Step 3:

[0376] The server uses a generative AI model to construct customized training scenarios. Inputs include an integrated dataset, sentiment analysis results, and specific prompt sentences. The prompt sentence used to instruct the AI ​​model is "Create a training scenario that considers situations where participants might feel anxious, based on geographical data of a specific region." This generates a training scenario as output.

[0377] Step 4:

[0378] The terminal deploys a visual simulation based on the generated scenario. The input consists of the generated scenario and geographical information, and the simulation is generated using Unity or Unreal Engine. Data processing involves analyzing GIS data to construct a disaster scene in a virtual environment. The output provides a detailed visual simulation for user viewing.

[0379] Step 5:

[0380] The server monitors the user's emotional data in real time during the simulation and generates corresponding feedback. It takes real-time emotional data as input and uses NLP techniques to create appropriate feedback. Output includes advice messages and action plans to provide to the user.

[0381] Step 6:

[0382] The device provides users with comprehensive feedback after training is complete. It receives behavioral and emotional data recorded during training as input, which is then analyzed to generate a report. The output is a PDF report containing improvements in new behaviors and changes in emotions, which users can view on their own device.

[0383] (Application Example 2)

[0384] 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."

[0385] In recent years, the importance of being able to respond quickly and calmly to natural disasters and sudden security risks has increased. However, many disaster preparedness drills are uniform and lack consideration for the psychological state and emotions of participants, often raising questions about their effectiveness. In particular, the lack of training systems that can provide appropriate feedback when psychological anxiety or confusion occurs is a challenge.

[0386] 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.

[0387] In this invention, the server includes means for generating customized training scenarios based on regional characteristics and participant attributes using a generative model, means for providing a visual simulation of the generated scenarios using geographic information, and means for evaluating the user's psychological state in real time using emotion recognition technology. This makes it possible to provide feedback based on the participant's emotional state and realize a practical and psychologically effective training experience.

[0388] A "generative model" is a mathematical or computer code template used to automatically create scenarios that meet specific conditions based on regional characteristics and participant attributes.

[0389] "Geographic information" refers to information that includes relevant data about a region, and is data that indicates geographical characteristics such as location and environment.

[0390] "Emotion recognition technology" is a technology that analyzes a user's psychological state from their facial expressions, voice, text, etc., and evaluates their emotions in real time.

[0391] "Real-time feedback" is a process that provides immediate responses based on user behavior and emotions.

[0392] A "simulation" is a simulated experience in a virtual environment that virtually reproduces real-world situations, with the purpose of educating users and conducting verification.

[0393] "Psychological state" refers to the emotional and thought processes a user exhibits, and is a concept that includes internal expressions such as anxiety, joy, and tension.

[0394] "Feedback" refers to the evaluations and advice that a system provides to a user, and it is information that is adjusted in response to changes in behavior and emotions.

[0395] A description of the embodiment for carrying out the invention will be provided.

[0396] The system that realizes this application example consists of a server and terminals (e.g., smartphones), enabling customized disaster prevention training based on regional characteristics and participant attributes.

[0397] The server uses a generative model to collect and analyze regional characteristics data and participant attribute data, and generates training scenarios based on this data. This generative model utilizes cloud services to consider geographic information within the region and uses GIS data to provide visual simulations. In addition, it uses emotion recognition technologies such as Azure Cognitive Services to evaluate the user's psychological state in real time.

[0398] The device provides the user with a visual simulation based on this generated training scenario. The software used can include map display libraries such as Leaflet.js. This allows the user to experience a simulated disaster that closely resembles an actual event. Furthermore, the user's emotional data is sent to the server, and they receive appropriate feedback in real time based on the analysis results.

[0399] As a concrete example, consider a disaster preparedness drill conducted at a local school, simulating a typhoon. The server analyzes past typhoon data and current weather forecasts, generating a training scenario based on geographical information of the area expected to be affected by the typhoon. Furthermore, an emotion engine monitors participants' psychological states, detecting anxiety and tension. The terminal uses a map of the school's surroundings to perform the simulation and presents the optimal evacuation route. Through this simulation, users can learn appropriate actions to take in the event of a disaster.

[0400] An example of a prompt message would be, "Generate an evacuation scenario for the expected typhoon at the current location, analyze the user's psychological state in real time, and provide reassuring feedback." In this way, users can learn to respond quickly and calmly during disasters.

[0401] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0402] Step 1:

[0403] The server collects regional characteristics data and participant attribute data. Meteorological data and Geographic Information System (GIS) data are also acquired at this time. The data is organized on the cloud and processed as foundational information for generating training scenarios. The collected data is integrated within the server and stored as an initial dataset.

[0404] Step 2:

[0405] The server uses a generative AI model based on the collected data to generate customized training scenarios. The input includes participant attributes and regional characteristics, and data processing based on this information generates scenarios tailored to each participant. The generated scenarios are stored in a database for later use.

[0406] Step 3:

[0407] The terminal receives training scenarios sent from the server and provides a visual simulation using geographic information. Here, a map display library such as Leaflet.js is used to execute a disaster simulation tailored to the user's location. This allows the user to visually confirm safe evacuation routes and their surrounding conditions.

[0408] Step 4:

[0409] The server uses Azure Cognitive Services to analyze user emotional data in real time. It analyzes voice and facial expression data as input and uses the results to determine the user's psychological state. The obtained emotional data is then used for subsequent feedback.

[0410] Step 5:

[0411] The server generates real-time feedback based on analyzed emotional data and sends it to the device. For users who show anxiety or stress, it creates calming instructions and encouraging messages. This generated feedback is received by the user as practical advice, which they then use to guide their actions.

[0412] Step 6:

[0413] Users review feedback from the device and attempt to modify their behavior accordingly. They gain training experience while referring to the visual simulations provided by the device. Finally, they conduct a self-assessment and prepare for the next training session based on the report provided after the training is completed.

[0414] 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.

[0415] 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.

[0416] 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.

[0417] [Third Embodiment]

[0418] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0419] 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.

[0420] 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).

[0421] 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.

[0422] 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.

[0423] 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).

[0424] 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.

[0425] 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.

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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".

[0430] This invention is a system that provides customized disaster prevention training scenarios based on regional characteristics and participant attributes. This system utilizes generative models and geographic information to provide participants with realistic disaster simulations and feedback.

[0431] Program Overview

[0432] 1. Data Collection and Analysis

[0433] The server first collects regional characteristic data, participant attribute data, historical disaster data, and real-time weather data. This data is then analyzed to determine the optimal training content in the event of a disaster. For example, the server can assess the flood risk in the area and identify evacuation routes that should be used in the training.

[0434] 2. Scenario generation and customization

[0435] The server utilizes a generative model to generate training scenarios based on collected data. These scenarios include specific disaster situations and are customized to reflect region-specific risk factors and participant characteristics. For example, a training exercise with a large elderly participant will generate a scenario that includes special instructions regarding movement and evacuation.

[0436] 3. Provision of visual simulations

[0437] The device provides participants with a visual simulation based on the generated scenario. Using GIS data, it can recreate disaster situations on a local map and show evacuation routes and safe zones. This allows users to experience more realistic disaster scenarios through training.

[0438] 4. Providing real-time feedback

[0439] The server monitors user behavior in real time during the simulation and provides appropriate feedback. For example, it evaluates whether the evacuation route was chosen appropriately and points out areas for improvement as needed, thereby enhancing the effectiveness of the training.

[0440] Specific example

[0441] For example, consider a case where a disaster prevention drill simulating an earthquake is conducted in a certain region.

[0442] The server collects historical earthquake data for the region and analyzes information on vulnerable buildings and infrastructure. It also generates scenarios specifically tailored to participants, assuming they are high school students, focusing on safe actions during evacuation and how to contact family members.

[0443] The device uses the school's geographical information to display evacuation routes and visually indicate the location of emergency assembly points.

[0444] Users act within the presented simulation and receive real-time feedback from the server, allowing them to review their actions and learn areas for improvement.

[0445] In this way, this system enhances the effectiveness of disaster preparedness drills and supports participants in responding appropriately during actual disasters.

[0446] The following describes the processing flow.

[0447] Step 1:

[0448] The server collects regional characteristics data, participant attribute data, historical disaster data, and real-time weather data. This data includes geographic information obtained from regional risk maps, participant basic information, historical disaster patterns, and current weather forecasts. The server analyzes the collected data to assess disaster risk in specific areas.

[0449] Step 2:

[0450] Based on the analysis results, the server generates training scenarios using a generative model. These scenarios define specific disaster situations and are customized according to regional characteristics and participant attributes. For example, the server creates a detailed script that assumes an earthquake, specifying the magnitude of the shaking, evacuation routes, and assembly points.

[0451] Step 3:

[0452] The terminal uses the generated scenario to construct a visual simulation. The terminal utilizes GIS data to recreate disaster situations based on local maps for the user. Evacuation routes and assembly points are visually displayed on the map, and the user begins taking action in the virtual situation accordingly.

[0453] Step 4:

[0454] Users act according to simulations provided on their devices, following designated evacuation routes. During the training, users select their actions in response to situations presented and observe the results.

[0455] Step 5:

[0456] The server monitors the user's actions in real time during the simulation and collects data. The server evaluates the appropriateness of the user's choices and actions and generates immediate feedback. This feedback may be presented as an evaluation such as "The selected evacuation route is appropriate" or as advice such as "This action needs improvement."

[0457] Step 6:

[0458] After the training is complete, the terminal provides the user with comprehensive feedback. The terminal receives feedback data from the server and presents the user with a report. This report includes challenges in the training, successful actions, and suggestions for improvement. The user can use this to plan countermeasures for future training and actual disaster situations.

[0459] (Example 1)

[0460] 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."

[0461] In modern society, it is essential to conduct disaster preparedness drills that are tailored to the varying disaster risks in different regions and the characteristics of individual participants. However, conventional training systems often provided uniform scenarios without adequately considering regional characteristics or the attributes of individual participants. As a result, the effectiveness of the training was limited, and there was a risk that effective actions could not be taken when an actual disaster occurred.

[0462] 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.

[0463] In this invention, the server includes means for generating personalized scenarios based on regional characteristics and user attributes using a generative model; means for providing a visual simulation experience of the generated scenarios using geographic information; means for monitoring user behavior and generating evaluations and feedback in real time; and means for analyzing the collected information and evaluating the region-specific risks and disaster response readiness. This enables personalized and efficient disaster prevention training.

[0464] A "generative model" is an algorithm or framework that learns specific conditions or patterns based on input data and generates new data or scenarios.

[0465] "Regional characteristics" refer to the geographical, climatic, social, and economic features and conditions of a particular region.

[0466] "User attributes" refer to information about individual participants using the training or system, including characteristics such as age, occupation, experience, and physical condition.

[0467] A "scenario" is a plan or narrative that outlines the progression of a series of situations and actions set up for a specific purpose.

[0468] "Geographic information" refers to spatial data related to a specific place or region, including maps, location information, and topographic information.

[0469] "Simulated experience" refers to methods or means of recreating real-world situations and experiencing them virtually.

[0470] "Evaluation" is the process of determining the effectiveness, appropriateness, or outcome of a particular activity or behavior.

[0471] "Feedback" refers to information that provides responses to user actions and results, as well as suggestions for improvement.

[0472] "Risk" refers to the risk of damage or harm that may occur under specific circumstances or conditions.

[0473] "Disaster response preparation" refers to the measures and resources that individuals and organizations need to plan and prepare in advance so that they can respond quickly and appropriately when a disaster occurs.

[0474] As an embodiment for carrying out the present invention, this system has a configuration that provides participants with a practical disaster prevention training experience. Specific examples are shown below.

[0475] The server collects and analyzes regional characteristic data, participant attribute information, historical disaster data, and real-time weather information. Geographic Information System (GIS) software is typically used for this purpose. During the data analysis process, the server applies machine learning algorithms to assess region-specific risk factors.

[0476] The server generates disaster prevention training scenarios using an AI model based on the collected data. The generated scenarios output specific details using prompts. For example, a prompt such as "Create a disaster prevention training scenario that considers regional characteristics and participant attributes" might be used. This program customizes the scenarios individually according to the attributes of different participants.

[0477] The device provides participants with a visual simulation based on the generated training scenario. This includes displaying the progression of the disaster on the screen and highlighting evacuation routes and safe zones based on map data. This visual simulation allows users to learn realistic disaster response through training.

[0478] Users act while experiencing a simulation provided via their device. The server monitors the user's actions in real time and provides evaluations and feedback based on that. The feedback is specific and includes suggestions for improvement, allowing users to review their actions based on the training results and learn what to improve next time.

[0479] This will enable the system to conduct more personalized and effective disaster preparedness drills.

[0480] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0481] Step 1:

[0482] The server collects regional characteristics data, participant attribute data, historical disaster data, and real-time weather data as input. At this stage, the server retrieves the necessary data from various databases and APIs and processes it into a standardized format. The collected data is then used in the next analysis step.

[0483] Step 2:

[0484] The server performs analysis using the collected data. Here, machine learning algorithms are applied to evaluate region-specific risk factors. The input for this analysis is the data standardized in Step 1, and the output is a regional risk assessment report. Specifically, the server compares and analyzes past disaster patterns with the current situation.

[0485] Step 3:

[0486] The server uses a generative AI model to generate customized scenarios based on regional characteristics and participant attributes. In this step, the prompt input is "Create a disaster prevention training scenario that considers regional characteristics and participant attributes." The generated scenarios include all the information necessary for the simulation. During this process, the server incorporates different scenario settings depending on the participant factors.

[0487] Step 4:

[0488] The terminal provides the user with a visual simulation based on the generated training scenario. The input is the scenario generated in step 3, and the output is the result of a visual simulation. Specifically, the terminal utilizes GIS data to represent the progression of the disaster on a map and visually indicates evacuation routes and safe zones.

[0489] Step 5:

[0490] Users participate in the simulation using a terminal and act according to prompts. The server monitors the user's actions in real time and generates appropriate feedback. The input to this feedback process is the user's action data, and the output provides points for improvement and evaluations. Specifically, the server evaluates the accuracy of the evacuation route selected by the user and provides guidance for the next time.

[0491] (Application Example 1)

[0492] 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."

[0493] In recent years, with the increasing frequency and scale of disasters, improving individual and community disaster preparedness has become an urgent task. However, conventional training methods are based on general scenarios and are not customized to regional characteristics or participant attributes, making them less effective in actual disaster situations. Furthermore, there is insufficient mechanism for participants to identify specific areas for improvement after training.

[0494] 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.

[0495] In this invention, the server includes means for generating customized training scenarios based on regional characteristics and participant attributes using a generative model, means for providing a visual simulation of the generated scenarios using geographic information, means for generating real-time feedback based on user behavior, and means for providing an interactive experience to the user and visually indicating emergency situations using a video display device. This enables participants to receive more effective and realistic disaster preparedness training and improve their ability to act calmly during a disaster.

[0496] A "generative model" is an algorithm or system for generating disaster prevention scenarios tailored to specific purposes, based on regional characteristics and participant attributes.

[0497] "Regional characteristics" refer to the features of a particular region, such as its natural environment, geographical conditions, and socioeconomic situation, and are important elements in customizing disaster prevention scenarios.

[0498] "Participant attributes" refer to the characteristics of each individual participating in disaster prevention training, such as age, gender, occupation, and health status, and serve as criteria for optimizing the training content.

[0499] A "training scenario" is a guideline or plan that describes in detail the specific disaster situations and response actions to be assumed in disaster prevention training.

[0500] "Geographic information" refers to data that includes location and topographic information about specific points or regions, and is used for visual reproduction in disaster prevention simulations.

[0501] "Visual simulation" is a method of displaying disaster situations as video to training participants in a way that closely resembles reality, and is a means of improving the training experience.

[0502] "Real-time feedback" is a method that enhances learning effectiveness by immediately evaluating participants' behavior during training and providing immediate suggestions for improvement and guidance.

[0503] A "visual display device" is a device used to display visual information of a training scenario to the user, and is used to give participants a more realistic training experience.

[0504] To realize this invention, a sophisticated system design, including the relevant hardware and software configurations, is essential.

[0505] The server first collects data based on regional characteristics and participant attributes. This data includes historical disaster data and real-time weather information. The server uses cloud computing technologies such as AWS Lambda to perform data analysis. Based on the analyzed data, a generative AI model is used to generate customized training scenarios that are tailored to regional characteristics and participant attributes. This process leverages the OpenAI API to form scenarios using specific prompt statements.

[0506] The generated scenarios are visually simulated using video display devices on the terminal. Using real-time 3D development platforms such as Unity, disaster situations based on local geographical information are reproduced. This is done in the form of evacuation routes and safe zones displayed on a map. Users can experience this simulation through display devices such as smart glasses.

[0507] User behavior is monitored in real time and evaluated using Google Cloud AI. The server generates and provides real-time feedback based on the user's evacuation route selection and actions. This feedback provides valuable information for participants to learn on the spot and improve their behavior.

[0508] As a concrete example, consider a simulation assuming an earthquake occurs at 10:00 AM. In this case, the user visually receives emergency information and evacuation instructions through smart glasses. The following prompt is used during the training: "Create an evacuation scenario tailored to regional characteristics and participant profiles. Participants are in a high-rise building, and there is a high proportion of elderly people at the scene."

[0509] This system allows users to improve their skills in responding quickly to disasters and ensuring their own safety and the safety of others.

[0510] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0511] Step 1:

[0512] The server collects regional characteristics data, participant attribute data, historical disaster data, and real-time weather data. This data is obtained from various data sources (e.g., weather information APIs, local government databases) and integrated. The server then uses AWS Lambda to perform data analysis, conducting risk assessments based on regional and participant characteristics to prepare for subsequent scenario generation. The results of the data analysis are stored in an appropriate data format.

[0513] Step 2:

[0514] The server uses the OpenAI API to generate customized training scenarios using a generative AI model based on the collected data. Prompts such as "Create an evacuation scenario tailored to regional characteristics and participant profiles. Participants are in a high-rise building, and there is a high proportion of elderly people at the site." are used. The generated scenarios are output as data including specific evacuation routes and action guidelines.

[0515] Step 3:

[0516] The device uses Unity to create a visual simulation based on a generated training scenario, utilizing local geographical information. During this process, map data and GIS data are used as input to visualize the disaster scenario, indicating evacuation routes and safe locations to the user. The completed visual simulation is then transmitted to a display device, such as smart glasses, for the user to experience.

[0517] Step 4:

[0518] Users experience a visual simulation using smart glasses. User behavior data is collected in real time by sensors in the glasses and transmitted to a server. Users follow visual information and audio guidance to select and move along a safe evacuation route.

[0519] Step 5:

[0520] The server uses Google Cloud AI to analyze user behavior data and generate feedback. Based on the input behavior data, it evaluates the appropriateness of the user's evacuation route selection and adherence to safety behaviors, and identifies areas for improvement as needed. The generated feedback is provided to the user in real time, allowing the user to immediately modify their behavior.

[0521] 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.

[0522] This invention combines a system that provides customized disaster prevention training scenarios considering regional characteristics and participant attributes with an emotion engine that recognizes user emotions. This system can grasp the user's psychological state in real time and provide emotion-based feedback and adjust the training content accordingly.

[0523] Program Overview

[0524] 1. Data Collection and Analysis

[0525] The server collects regional characteristics data, participant attribute data, historical disaster data, and real-time weather data. In addition, an emotion engine acquires and analyzes user emotion data. This data is used to predict psychological responses, particularly during disasters.

[0526] 2. Scenario generation and customization

[0527] The server uses a generative model to generate training scenarios based on the analyzed data. The generated scenarios are customized to take into account expected emotional responses to specific disaster scenes. For example, instructions encouraging calmness are included for participants who are prone to stress.

[0528] 3. Provision of visual simulations

[0529] The device provides users with a visual simulation based on the generated scenario. Using GIS data, it reproduces situations that users may face on a map. Through the simulation, users receive training that closely resembles the actual conditions during a disaster.

[0530] 4. Real-time feedback based on emotional data

[0531] The server monitors the user's emotional state, obtained from the emotion engine, during the simulation. For example, if the user shows anxiety, the server provides real-time feedback corresponding to that emotion and offers advice to alleviate the anxiety.

[0532] 5. Post-training summary feedback

[0533] The device provides users with comprehensive feedback after the training is complete. The report includes changes in the user's emotions, behavioral responses, and suggestions for improvement. Users use this feedback to mentally prepare for future training or actual disaster situations.

[0534] Specific example

[0535] For example, when conducting a disaster preparedness drill simulating a typhoon in a given area, the server analyzes past typhoon data and current weather forecasts for the region to assess the impact on the participating schools. Furthermore, the emotion engine monitors the participants' psychological state, detecting anxiety and tension. The terminal simulates a map of the school's surroundings and presents evacuation routes, providing users with a practical evacuation drill. The server evaluates the routes and actions chosen by the users, provides real-time feedback as needed, and delivers a report including psychological coping strategies after the drill. This allows participants to learn how to act more effectively during disasters and strengthen their emotional preparedness.

[0536] The following describes the processing flow.

[0537] Step 1:

[0538] The server collects regional characteristic data, participant attribute data, historical disaster occurrence data, and real-time weather data. In addition, it activates an emotion engine to monitor the emotions of users participating in the training and obtain baseline emotion data. This data forms the basis for more realistic training scenarios.

[0539] Step 2:

[0540] The server analyzes the collected data and uses generative models to generate customized training scenarios. These scenarios reflect local risks, participant attributes, and individual responses based on emotional data. For example, if a particular participant is found to be sensitive to stress, the scenario will include instructions for stress reduction.

[0541] Step 3:

[0542] The device provides users with a visual simulation based on the generated scenario. It utilizes GIS maps to display the user's current location and evacuation routes in real time. Based on this visual information, users can proceed with virtual training and simulate the experience of moving to a safe evacuation site.

[0543] Step 4:

[0544] Users participate in the simulation while operating their devices. The user's behavior during training is monitored in real time by an emotion engine, which detects the user's emotional state (e.g., anxiety, reassurance, concentration, etc.).

[0545] Step 5:

[0546] The server analyzes user behavior and emotional data acquired during training. Based on the user's emotional changes, it instantly generates feedback and provides it to the user through the terminal. If the user's stress level increases, it attempts to improve the situation by providing instructions to promote relaxation and information to promote reassurance.

[0547] Step 6:

[0548] The device displays comprehensive feedback to the user after the training is complete. This feedback includes an evaluation of user behavior, an analysis of emotional changes, and suggestions for improvement. This information allows users to refine their future training and disaster response plans.

[0549] (Example 2)

[0550] 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."

[0551] Conventional disaster preparedness training systems can only provide training based on uniform scenarios and cannot conduct customized training that takes into account regional characteristics or individual emotional states. Furthermore, they do not provide real-time feedback that reflects users' emotional responses during training, making it difficult for participants to learn effective responses in actual disaster situations.

[0552] 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.

[0553] In this invention, the server includes means for generating customized training scenarios based on regional characteristics and participant attributes using a generative AI model, means for providing a visual simulation of the generated scenarios using geographic information, and means for generating real-time feedback based on user behavior and emotional data. This makes it possible to provide a more practical and effective disaster prevention training experience that takes into account regional characteristics and individual emotional states.

[0554] A "generative AI model" is an artificial intelligence technology that processes information based on regional characteristics and participant attributes to automatically create specific scenarios.

[0555] "Regional characteristics" refer to the unique environmental, geographical, and climatic conditions of a particular region, and include information related to the occurrence and impact of disasters.

[0556] "Participant attributes" refer to the personal characteristics of each individual participating in the disaster prevention drill, such as age, gender, experience, and psychological state.

[0557] A "training scenario" refers to a series of hypothetical situations created in disaster prevention training to allow participants to experience specific circumstances and learn how to respond to them.

[0558] "Visual simulation" refers to a technology that uses computer graphics and geographic information systems to visually reproduce disaster situations within a virtual environment.

[0559] "Emotional data" refers to information about the user's current psychological state, including the degree of stress and anxiety obtained from audio and video.

[0560] "Real-time feedback" refers to advice and suggestions for improvement that are provided instantly in response to the behavior and emotions of participants during training.

[0561] "Geographic information" refers to information related to a specific location, including maps and location data, and is used for creating training scenarios and visual simulations.

[0562] In implementing this invention, the server and terminals play a central role in the system. The server first collects regional characteristic data, participant attribute data, historical disaster data, and real-time weather data using external databases and APIs. This forms an integrated dataset that forms the basis of the training scenarios.

[0563] Next, the server uses an emotion engine to analyze emotions from the audio and video data provided by the user. Here, machine learning libraries such as TensorFlow are used to analyze stress levels from audio and changes in facial expressions from video. This analyzed data is then considered when generating behavioral scenarios.

[0564] Next, the server uses a generative AI model to create a customized training scenario. For example, by using the prompt "Create a disaster prevention training scenario that takes into account situations that might cause anxiety for participants, based on geographical data of a specific region," a customized scenario is generated.

[0565] The device provides a visual simulation based on this generated scenario. Using technologies such as Unity and Unreal Engine, and leveraging GIS data, it realistically reproduces the disaster situation the user will face in the virtual environment. This allows the user to learn practical evacuation actions.

[0566] Furthermore, the server monitors the user's emotional state in real time during the simulation and provides appropriate feedback. For example, if the user shows signs of anxiety, the server instantly generates and provides advice and suggestions for improvement tailored to that situation.

[0567] Finally, after the training, the device provides the user with a summary of the feedback. This report includes an assessment of emotional changes and behavior, and is available to the user in PDF format. This allows the user to obtain specific and practical guidance for future training and preparations for actual disasters.

[0568] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0569] Step 1:

[0570] The server collects regional characteristics data, participant attribute data, historical disaster data, and real-time weather data from external databases and APIs. Inputs include API keys and queries for various databases. Data processing is performed using Pandas for data cleaning and integration, resulting in a processed, integrated dataset. This integrated dataset is used in subsequent steps.

[0571] Step 2:

[0572] The server utilizes an emotion engine to acquire user emotion data from audio and video. It receives user-provided audio files and video streams as input, which are analyzed using TensorFlow. Through data processing, it recognizes stress levels and changes in facial expressions, and outputs emotion analysis results. These results are useful for customizing training scenarios.

[0573] Step 3:

[0574] The server uses a generative AI model to construct customized training scenarios. Inputs include an integrated dataset, sentiment analysis results, and specific prompt sentences. The prompt sentence used to instruct the AI ​​model is "Create a training scenario that considers situations where participants might feel anxious, based on geographical data of a specific region." This generates a training scenario as output.

[0575] Step 4:

[0576] The terminal deploys a visual simulation based on the generated scenario. The input consists of the generated scenario and geographical information, and the simulation is generated using Unity or Unreal Engine. Data processing involves analyzing GIS data to construct a disaster scene in a virtual environment. The output provides a detailed visual simulation for user viewing.

[0577] Step 5:

[0578] The server monitors the user's emotional data in real time during the simulation and generates corresponding feedback. It takes real-time emotional data as input and uses NLP techniques to create appropriate feedback. Output includes advice messages and action plans to provide to the user.

[0579] Step 6:

[0580] The device provides users with comprehensive feedback after training is complete. It receives behavioral and emotional data recorded during training as input, which is then analyzed to generate a report. The output is a PDF report containing improvements in new behaviors and changes in emotions, which users can view on their own device.

[0581] (Application Example 2)

[0582] 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."

[0583] In recent years, the importance of being able to respond quickly and calmly to natural disasters and sudden security risks has increased. However, many disaster preparedness drills are uniform and lack consideration for the psychological state and emotions of participants, often raising questions about their effectiveness. In particular, the lack of training systems that can provide appropriate feedback when psychological anxiety or confusion occurs is a challenge.

[0584] 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.

[0585] In this invention, the server includes means for generating customized training scenarios based on regional characteristics and participant attributes using a generative model, means for providing a visual simulation of the generated scenarios using geographic information, and means for evaluating the user's psychological state in real time using emotion recognition technology. This makes it possible to provide feedback based on the participant's emotional state and realize a practical and psychologically effective training experience.

[0586] A "generative model" is a mathematical or computer code template used to automatically create scenarios that meet specific conditions based on regional characteristics and participant attributes.

[0587] "Geographic information" refers to information that includes relevant data about a region, and is data that indicates geographical characteristics such as location and environment.

[0588] "Emotion recognition technology" is a technology that analyzes a user's psychological state from their facial expressions, voice, text, etc., and evaluates their emotions in real time.

[0589] "Real-time feedback" is a process that provides immediate responses based on user behavior and emotions.

[0590] A "simulation" is a simulated experience in a virtual environment that virtually reproduces real-world situations, with the purpose of educating users and conducting verification.

[0591] "Psychological state" refers to the emotional and thought processes a user exhibits, and is a concept that includes internal expressions such as anxiety, joy, and tension.

[0592] "Feedback" refers to the evaluations and advice that a system provides to a user, and it is information that is adjusted in response to changes in behavior and emotions.

[0593] A description of the embodiment for carrying out the invention will be provided.

[0594] The system that realizes this application example consists of a server and terminals (e.g., smartphones), enabling customized disaster prevention training based on regional characteristics and participant attributes.

[0595] The server uses a generative model to collect and analyze regional characteristics data and participant attribute data, and generates training scenarios based on this data. This generative model utilizes cloud services to consider geographic information within the region and uses GIS data to provide visual simulations. In addition, it uses emotion recognition technologies such as Azure Cognitive Services to evaluate the user's psychological state in real time.

[0596] The device provides the user with a visual simulation based on this generated training scenario. The software used can include map display libraries such as Leaflet.js. This allows the user to experience a simulated disaster that closely resembles an actual event. Furthermore, the user's emotional data is sent to the server, and they receive appropriate feedback in real time based on the analysis results.

[0597] As a concrete example, consider a disaster preparedness drill conducted at a local school, simulating a typhoon. The server analyzes past typhoon data and current weather forecasts, generating a training scenario based on geographical information of the area expected to be affected by the typhoon. Furthermore, an emotion engine monitors participants' psychological states, detecting anxiety and tension. The terminal uses a map of the school's surroundings to perform the simulation and presents the optimal evacuation route. Through this simulation, users can learn appropriate actions to take in the event of a disaster.

[0598] An example of a prompt message would be, "Generate an evacuation scenario for the expected typhoon at the current location, analyze the user's psychological state in real time, and provide reassuring feedback." In this way, users can learn to respond quickly and calmly during disasters.

[0599] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0600] Step 1:

[0601] The server collects regional characteristics data and participant attribute data. Meteorological data and Geographic Information System (GIS) data are also acquired at this time. The data is organized on the cloud and processed as foundational information for generating training scenarios. The collected data is integrated within the server and stored as an initial dataset.

[0602] Step 2:

[0603] The server uses a generative AI model based on the collected data to generate customized training scenarios. The input includes participant attributes and regional characteristics, and data processing based on this information generates scenarios tailored to each participant. The generated scenarios are stored in a database for later use.

[0604] Step 3:

[0605] The terminal receives training scenarios sent from the server and provides a visual simulation using geographic information. Here, a map display library such as Leaflet.js is used to execute a disaster simulation tailored to the user's location. This allows the user to visually confirm safe evacuation routes and their surrounding conditions.

[0606] Step 4:

[0607] The server uses Azure Cognitive Services to analyze user emotional data in real time. It analyzes voice and facial expression data as input and uses the results to determine the user's psychological state. The obtained emotional data is then used for subsequent feedback.

[0608] Step 5:

[0609] The server generates real-time feedback based on analyzed emotional data and sends it to the device. For users who show anxiety or stress, it creates calming instructions and encouraging messages. This generated feedback is received by the user as practical advice, which they then use to guide their actions.

[0610] Step 6:

[0611] Users review feedback from the device and attempt to modify their behavior accordingly. They gain training experience while referring to the visual simulations provided by the device. Finally, they conduct a self-assessment and prepare for the next training session based on the report provided after the training is completed.

[0612] 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.

[0613] 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.

[0614] 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.

[0615] [Fourth Embodiment]

[0616] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0617] 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.

[0618] 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).

[0619] 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.

[0620] 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.

[0621] 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).

[0622] 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.

[0623] 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.

[0624] 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.

[0625] 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.

[0626] 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.

[0627] 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.

[0628] 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".

[0629] This invention is a system that provides customized disaster prevention training scenarios based on regional characteristics and participant attributes. This system utilizes generative models and geographic information to provide participants with realistic disaster simulations and feedback.

[0630] Program Overview

[0631] 1. Data Collection and Analysis

[0632] The server first collects regional characteristic data, participant attribute data, historical disaster data, and real-time weather data. This data is then analyzed to determine the optimal training content in the event of a disaster. For example, the server can assess the flood risk in the area and identify evacuation routes that should be used in the training.

[0633] 2. Scenario generation and customization

[0634] The server utilizes a generative model to generate training scenarios based on collected data. These scenarios include specific disaster situations and are customized to reflect region-specific risk factors and participant characteristics. For example, a training exercise with a large elderly participant will generate a scenario that includes special instructions regarding movement and evacuation.

[0635] 3. Provision of visual simulations

[0636] The device provides participants with a visual simulation based on the generated scenario. Using GIS data, it can recreate disaster situations on a local map and show evacuation routes and safe zones. This allows users to experience more realistic disaster scenarios through training.

[0637] 4. Providing real-time feedback

[0638] The server monitors user behavior in real time during the simulation and provides appropriate feedback. For example, it evaluates whether the evacuation route was chosen appropriately and points out areas for improvement as needed, thereby enhancing the effectiveness of the training.

[0639] Specific example

[0640] For example, consider a case where a disaster prevention drill simulating an earthquake is conducted in a certain region.

[0641] The server collects historical earthquake data for the region and analyzes information on vulnerable buildings and infrastructure. It also generates scenarios specifically tailored to participants, assuming they are high school students, focusing on safe actions during evacuation and how to contact family members.

[0642] The device uses the school's geographical information to display evacuation routes and visually indicate the location of emergency assembly points.

[0643] Users act within the presented simulation and receive real-time feedback from the server, allowing them to review their actions and learn areas for improvement.

[0644] In this way, this system enhances the effectiveness of disaster preparedness drills and supports participants in responding appropriately during actual disasters.

[0645] The following describes the processing flow.

[0646] Step 1:

[0647] The server collects regional characteristics data, participant attribute data, historical disaster data, and real-time weather data. This data includes geographic information obtained from regional risk maps, participant basic information, historical disaster patterns, and current weather forecasts. The server analyzes the collected data to assess disaster risk in specific areas.

[0648] Step 2:

[0649] Based on the analysis results, the server generates training scenarios using a generative model. These scenarios define specific disaster situations and are customized according to regional characteristics and participant attributes. For example, the server creates a detailed script that assumes an earthquake, specifying the magnitude of the shaking, evacuation routes, and assembly points.

[0650] Step 3:

[0651] The terminal uses the generated scenario to construct a visual simulation. The terminal utilizes GIS data to recreate disaster situations based on local maps for the user. Evacuation routes and assembly points are visually displayed on the map, and the user begins taking action in the virtual situation accordingly.

[0652] Step 4:

[0653] Users act according to simulations provided on their devices, following designated evacuation routes. During the training, users select their actions in response to situations presented and observe the results.

[0654] Step 5:

[0655] The server monitors the user's actions in real time during the simulation and collects data. The server evaluates the appropriateness of the user's choices and actions and generates immediate feedback. This feedback may be presented as an evaluation such as "The selected evacuation route is appropriate" or as advice such as "This action needs improvement."

[0656] Step 6:

[0657] After the training is complete, the terminal provides the user with comprehensive feedback. The terminal receives feedback data from the server and presents the user with a report. This report includes challenges in the training, successful actions, and suggestions for improvement. The user can use this to plan countermeasures for future training and actual disaster situations.

[0658] (Example 1)

[0659] 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".

[0660] In modern society, it is essential to conduct disaster preparedness drills that are tailored to the varying disaster risks in different regions and the characteristics of individual participants. However, conventional training systems often provided uniform scenarios without adequately considering regional characteristics or the attributes of individual participants. As a result, the effectiveness of the training was limited, and there was a risk that effective actions could not be taken when an actual disaster occurred.

[0661] 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.

[0662] In this invention, the server includes means for generating personalized scenarios based on regional characteristics and user attributes using a generative model; means for providing a visual simulation experience of the generated scenarios using geographic information; means for monitoring user behavior and generating evaluations and feedback in real time; and means for analyzing the collected information and evaluating the region-specific risks and disaster response readiness. This enables personalized and efficient disaster prevention training.

[0663] A "generative model" is an algorithm or framework that learns specific conditions or patterns based on input data and generates new data or scenarios.

[0664] "Regional characteristics" refer to the geographical, climatic, social, and economic features and conditions of a particular region.

[0665] "User attributes" refer to information about individual participants using the training or system, including characteristics such as age, occupation, experience, and physical condition.

[0666] A "scenario" is a plan or narrative that outlines the progression of a series of situations and actions set up for a specific purpose.

[0667] "Geographic information" refers to spatial data related to a specific place or region, including maps, location information, and topographic information.

[0668] "Simulated experience" refers to methods or means of recreating real-world situations and experiencing them virtually.

[0669] "Evaluation" is the process of determining the effectiveness, appropriateness, or outcome of a particular activity or behavior.

[0670] "Feedback" refers to information that provides responses to user actions and results, as well as suggestions for improvement.

[0671] "Risk" refers to the risk of damage or harm that may occur under specific circumstances or conditions.

[0672] "Disaster response preparation" refers to the measures and resources that individuals and organizations need to plan and prepare in advance so that they can respond quickly and appropriately when a disaster occurs.

[0673] As an embodiment for carrying out the present invention, this system has a configuration that provides participants with a practical disaster prevention training experience. Specific examples are shown below.

[0674] The server collects and analyzes regional characteristic data, participant attribute information, historical disaster data, and real-time weather information. Geographic Information System (GIS) software is typically used for this purpose. During the data analysis process, the server applies machine learning algorithms to assess region-specific risk factors.

[0675] The server generates disaster prevention training scenarios using an AI model based on the collected data. The generated scenarios output specific details using prompts. For example, a prompt such as "Create a disaster prevention training scenario that considers regional characteristics and participant attributes" might be used. This program customizes the scenarios individually according to the attributes of different participants.

[0676] The device provides participants with a visual simulation based on the generated training scenario. This includes displaying the progression of the disaster on the screen and highlighting evacuation routes and safe zones based on map data. This visual simulation allows users to learn realistic disaster response through training.

[0677] Users act while experiencing a simulation provided via their device. The server monitors the user's actions in real time and provides evaluations and feedback based on that. The feedback is specific and includes suggestions for improvement, allowing users to review their actions based on the training results and learn what to improve next time.

[0678] This will enable the system to conduct more personalized and effective disaster preparedness drills.

[0679] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0680] Step 1:

[0681] The server collects regional characteristics data, participant attribute data, historical disaster data, and real-time weather data as input. At this stage, the server retrieves the necessary data from various databases and APIs and processes it into a standardized format. The collected data is then used in the next analysis step.

[0682] Step 2:

[0683] The server performs analysis using the collected data. Here, machine learning algorithms are applied to evaluate region-specific risk factors. The input for this analysis is the data standardized in Step 1, and the output is a regional risk assessment report. Specifically, the server compares and analyzes past disaster patterns with the current situation.

[0684] Step 3:

[0685] The server uses a generative AI model to generate customized scenarios based on regional characteristics and participant attributes. In this step, the prompt input is "Create a disaster prevention training scenario that considers regional characteristics and participant attributes." The generated scenarios include all the information necessary for the simulation. During this process, the server incorporates different scenario settings depending on the participant factors.

[0686] Step 4:

[0687] The terminal provides the user with a visual simulation based on the generated training scenario. The input is the scenario generated in step 3, and the output is the result of a visual simulation. Specifically, the terminal utilizes GIS data to represent the progression of the disaster on a map and visually indicates evacuation routes and safe zones.

[0688] Step 5:

[0689] Users participate in the simulation using a terminal and act according to prompts. The server monitors the user's actions in real time and generates appropriate feedback. The input to this feedback process is the user's action data, and the output provides points for improvement and evaluations. Specifically, the server evaluates the accuracy of the evacuation route selected by the user and provides guidance for the next time.

[0690] (Application Example 1)

[0691] 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".

[0692] In recent years, with the increasing frequency and scale of disasters, improving individual and community disaster preparedness has become an urgent task. However, conventional training methods are based on general scenarios and are not customized to regional characteristics or participant attributes, making them less effective in actual disaster situations. Furthermore, there is insufficient mechanism for participants to identify specific areas for improvement after training.

[0693] 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.

[0694] In this invention, the server includes means for generating customized training scenarios based on regional characteristics and participant attributes using a generative model, means for providing a visual simulation of the generated scenarios using geographic information, means for generating real-time feedback based on user behavior, and means for providing an interactive experience to the user and visually indicating emergency situations using a video display device. This enables participants to receive more effective and realistic disaster preparedness training and improve their ability to act calmly during a disaster.

[0695] A "generative model" is an algorithm or system for generating disaster prevention scenarios tailored to specific purposes, based on regional characteristics and participant attributes.

[0696] "Regional characteristics" refer to the features of a particular region, such as its natural environment, geographical conditions, and socioeconomic situation, and are important elements in customizing disaster prevention scenarios.

[0697] "Participant attributes" refer to the characteristics of each individual participating in disaster prevention training, such as age, gender, occupation, and health status, and serve as criteria for optimizing the training content.

[0698] A "training scenario" is a guideline or plan that describes in detail the specific disaster situations and response actions to be assumed in disaster prevention training.

[0699] "Geographic information" refers to data that includes location and topographic information about specific points or regions, and is used for visual reproduction in disaster prevention simulations.

[0700] "Visual simulation" is a method of displaying disaster situations as video to training participants in a way that closely resembles reality, and is a means of improving the training experience.

[0701] "Real-time feedback" is a method that enhances learning effectiveness by immediately evaluating participants' behavior during training and providing immediate suggestions for improvement and guidance.

[0702] A "visual display device" is a device used to display visual information of a training scenario to the user, and is used to give participants a more realistic training experience.

[0703] To realize this invention, a sophisticated system design, including the relevant hardware and software configurations, is essential.

[0704] The server first collects data based on regional characteristics and participant attributes. This data includes historical disaster data and real-time weather information. The server uses cloud computing technologies such as AWS Lambda to perform data analysis. Based on the analyzed data, a generative AI model is used to generate customized training scenarios that are tailored to regional characteristics and participant attributes. This process leverages the OpenAI API to form scenarios using specific prompt statements.

[0705] The generated scenarios are visually simulated using video display devices on the terminal. Using real-time 3D development platforms such as Unity, disaster situations based on local geographical information are reproduced. This is done in the form of evacuation routes and safe zones displayed on a map. Users can experience this simulation through display devices such as smart glasses.

[0706] User behavior is monitored in real time and evaluated using Google Cloud AI. The server generates and provides real-time feedback based on the user's evacuation route selection and actions. This feedback provides valuable information for participants to learn on the spot and improve their behavior.

[0707] As a concrete example, consider a simulation assuming an earthquake occurs at 10:00 AM. In this case, the user visually receives emergency information and evacuation instructions through smart glasses. The following prompt is used during the training: "Create an evacuation scenario tailored to regional characteristics and participant profiles. Participants are in a high-rise building, and there is a high proportion of elderly people at the scene."

[0708] This system allows users to improve their skills in responding quickly to disasters and ensuring their own safety and the safety of others.

[0709] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0710] Step 1:

[0711] The server collects regional characteristics data, participant attribute data, historical disaster data, and real-time weather data. This data is obtained from various data sources (e.g., weather information APIs, local government databases) and integrated. The server then uses AWS Lambda to perform data analysis, conducting risk assessments based on regional and participant characteristics to prepare for subsequent scenario generation. The results of the data analysis are stored in an appropriate data format.

[0712] Step 2:

[0713] The server uses the OpenAI API to generate customized training scenarios using a generative AI model based on the collected data. Prompts such as "Create an evacuation scenario tailored to regional characteristics and participant profiles. Participants are in a high-rise building, and there is a high proportion of elderly people at the site." are used. The generated scenarios are output as data including specific evacuation routes and action guidelines.

[0714] Step 3:

[0715] The device uses Unity to create a visual simulation based on a generated training scenario, utilizing local geographical information. During this process, map data and GIS data are used as input to visualize the disaster scenario, indicating evacuation routes and safe locations to the user. The completed visual simulation is then transmitted to a display device, such as smart glasses, for the user to experience.

[0716] Step 4:

[0717] Users experience a visual simulation using smart glasses. User behavior data is collected in real time by sensors in the glasses and transmitted to a server. Users follow visual information and audio guidance to select and move along a safe evacuation route.

[0718] Step 5:

[0719] The server uses Google Cloud AI to analyze user behavior data and generate feedback. Based on the input behavior data, it evaluates the appropriateness of the user's evacuation route selection and adherence to safety behaviors, and identifies areas for improvement as needed. The generated feedback is provided to the user in real time, allowing the user to immediately modify their behavior.

[0720] 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.

[0721] This invention combines a system that provides customized disaster prevention training scenarios considering regional characteristics and participant attributes with an emotion engine that recognizes user emotions. This system can grasp the user's psychological state in real time and provide emotion-based feedback and adjust the training content accordingly.

[0722] Program Overview

[0723] 1. Data Collection and Analysis

[0724] The server collects regional characteristics data, participant attribute data, historical disaster data, and real-time weather data. In addition, an emotion engine acquires and analyzes user emotion data. This data is used to predict psychological responses, particularly during disasters.

[0725] 2. Scenario generation and customization

[0726] The server uses a generative model to generate training scenarios based on the analyzed data. The generated scenarios are customized to take into account expected emotional responses to specific disaster scenes. For example, instructions encouraging calmness are included for participants who are prone to stress.

[0727] 3. Provision of visual simulations

[0728] The device provides users with a visual simulation based on the generated scenario. Using GIS data, it reproduces situations that users may face on a map. Through the simulation, users receive training that closely resembles the actual conditions during a disaster.

[0729] 4. Real-time feedback based on emotional data

[0730] The server monitors the user's emotional state, obtained from the emotion engine, during the simulation. For example, if the user shows anxiety, the server provides real-time feedback corresponding to that emotion and offers advice to alleviate the anxiety.

[0731] 5. Post-training summary feedback

[0732] The device provides users with comprehensive feedback after the training is complete. The report includes changes in the user's emotions, behavioral responses, and suggestions for improvement. Users use this feedback to mentally prepare for future training or actual disaster situations.

[0733] Specific example

[0734] For example, when conducting a disaster preparedness drill simulating a typhoon in a given area, the server analyzes past typhoon data and current weather forecasts for the region to assess the impact on the participating schools. Furthermore, the emotion engine monitors the participants' psychological state, detecting anxiety and tension. The terminal simulates a map of the school's surroundings and presents evacuation routes, providing users with a practical evacuation drill. The server evaluates the routes and actions chosen by the users, provides real-time feedback as needed, and delivers a report including psychological coping strategies after the drill. This allows participants to learn how to act more effectively during disasters and strengthen their emotional preparedness.

[0735] The following describes the processing flow.

[0736] Step 1:

[0737] The server collects regional characteristic data, participant attribute data, historical disaster occurrence data, and real-time weather data. In addition, it activates an emotion engine to monitor the emotions of users participating in the training and obtain baseline emotion data. This data forms the basis for more realistic training scenarios.

[0738] Step 2:

[0739] The server analyzes the collected data and uses generative models to generate customized training scenarios. These scenarios reflect local risks, participant attributes, and individual responses based on emotional data. For example, if a particular participant is found to be sensitive to stress, the scenario will include instructions for stress reduction.

[0740] Step 3:

[0741] The device provides users with a visual simulation based on the generated scenario. It utilizes GIS maps to display the user's current location and evacuation routes in real time. Based on this visual information, users can proceed with virtual training and simulate the experience of moving to a safe evacuation site.

[0742] Step 4:

[0743] Users participate in the simulation while operating their devices. The user's behavior during training is monitored in real time by an emotion engine, which detects the user's emotional state (e.g., anxiety, reassurance, concentration, etc.).

[0744] Step 5:

[0745] The server analyzes user behavior and emotional data acquired during training. Based on the user's emotional changes, it instantly generates feedback and provides it to the user through the terminal. If the user's stress level increases, it attempts to improve the situation by providing instructions to promote relaxation and information to promote reassurance.

[0746] Step 6:

[0747] The device displays comprehensive feedback to the user after the training is complete. This feedback includes an evaluation of user behavior, an analysis of emotional changes, and suggestions for improvement. This information allows users to refine their future training and disaster response plans.

[0748] (Example 2)

[0749] 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".

[0750] Conventional disaster preparedness training systems can only provide training based on uniform scenarios and cannot conduct customized training that takes into account regional characteristics or individual emotional states. Furthermore, they do not provide real-time feedback that reflects users' emotional responses during training, making it difficult for participants to learn effective responses in actual disaster situations.

[0751] 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.

[0752] In this invention, the server includes means for generating customized training scenarios based on regional characteristics and participant attributes using a generative AI model, means for providing a visual simulation of the generated scenarios using geographic information, and means for generating real-time feedback based on user behavior and emotional data. This makes it possible to provide a more practical and effective disaster prevention training experience that takes into account regional characteristics and individual emotional states.

[0753] A "generative AI model" is an artificial intelligence technology that processes information based on regional characteristics and participant attributes to automatically create specific scenarios.

[0754] "Regional characteristics" refer to the unique environmental, geographical, and climatic conditions of a particular region, and include information related to the occurrence and impact of disasters.

[0755] "Participant attributes" refer to the personal characteristics of each individual participating in the disaster prevention drill, such as age, gender, experience, and psychological state.

[0756] A "training scenario" refers to a series of hypothetical situations created in disaster prevention training to allow participants to experience specific circumstances and learn how to respond to them.

[0757] "Visual simulation" refers to a technology that uses computer graphics and geographic information systems to visually reproduce disaster situations within a virtual environment.

[0758] "Emotional data" refers to information about the user's current psychological state, including the degree of stress and anxiety obtained from audio and video.

[0759] "Real-time feedback" refers to advice and suggestions for improvement that are provided instantly in response to the behavior and emotions of participants during training.

[0760] "Geographic information" refers to information related to a specific location, including maps and location data, and is used for creating training scenarios and visual simulations.

[0761] In implementing this invention, the server and terminals play a central role in the system. The server first collects regional characteristic data, participant attribute data, historical disaster data, and real-time weather data using external databases and APIs. This forms an integrated dataset that forms the basis of the training scenarios.

[0762] Next, the server uses an emotion engine to analyze emotions from the audio and video data provided by the user. Here, machine learning libraries such as TensorFlow are used to analyze stress levels from audio and changes in facial expressions from video. This analyzed data is then considered when generating behavioral scenarios.

[0763] Next, the server uses a generative AI model to create a customized training scenario. For example, by using the prompt "Create a disaster prevention training scenario that takes into account situations that might cause anxiety for participants, based on geographical data of a specific region," a customized scenario is generated.

[0764] The device provides a visual simulation based on this generated scenario. Using technologies such as Unity and Unreal Engine, and leveraging GIS data, it realistically reproduces the disaster situation the user will face in the virtual environment. This allows the user to learn practical evacuation actions.

[0765] Furthermore, the server monitors the user's emotional state in real time during the simulation and provides appropriate feedback. For example, if the user shows signs of anxiety, the server instantly generates and provides advice and suggestions for improvement tailored to that situation.

[0766] Finally, after the training, the device provides the user with a summary of the feedback. This report includes an assessment of emotional changes and behavior, and is available to the user in PDF format. This allows the user to obtain specific and practical guidance for future training and preparations for actual disasters.

[0767] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0768] Step 1:

[0769] The server collects regional characteristics data, participant attribute data, historical disaster data, and real-time weather data from external databases and APIs. Inputs include API keys and queries for various databases. Data processing is performed using Pandas for data cleaning and integration, resulting in a processed, integrated dataset. This integrated dataset is used in subsequent steps.

[0770] Step 2:

[0771] The server utilizes an emotion engine to acquire user emotion data from audio and video. It receives user-provided audio files and video streams as input, which are analyzed using TensorFlow. Through data processing, it recognizes stress levels and changes in facial expressions, and outputs emotion analysis results. These results are useful for customizing training scenarios.

[0772] Step 3:

[0773] The server uses a generative AI model to construct customized training scenarios. Inputs include an integrated dataset, sentiment analysis results, and specific prompt sentences. The prompt sentence used to instruct the AI ​​model is "Create a training scenario that considers situations where participants might feel anxious, based on geographical data of a specific region." This generates a training scenario as output.

[0774] Step 4:

[0775] The terminal deploys a visual simulation based on the generated scenario. The input consists of the generated scenario and geographical information, and the simulation is generated using Unity or Unreal Engine. Data processing involves analyzing GIS data to construct a disaster scene in a virtual environment. The output provides a detailed visual simulation for user viewing.

[0776] Step 5:

[0777] The server monitors the user's emotional data in real time during the simulation and generates corresponding feedback. It takes real-time emotional data as input and uses NLP techniques to create appropriate feedback. Output includes advice messages and action plans to provide to the user.

[0778] Step 6:

[0779] The device provides users with comprehensive feedback after training is complete. It receives behavioral and emotional data recorded during training as input, which is then analyzed to generate a report. The output is a PDF report containing improvements in new behaviors and changes in emotions, which users can view on their own device.

[0780] (Application Example 2)

[0781] 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".

[0782] In recent years, the importance of being able to respond quickly and calmly to natural disasters and sudden security risks has increased. However, many disaster preparedness drills are uniform and lack consideration for the psychological state and emotions of participants, often raising questions about their effectiveness. In particular, the lack of training systems that can provide appropriate feedback when psychological anxiety or confusion occurs is a challenge.

[0783] 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.

[0784] In this invention, the server includes means for generating customized training scenarios based on regional characteristics and participant attributes using a generative model, means for providing a visual simulation of the generated scenarios using geographic information, and means for evaluating the user's psychological state in real time using emotion recognition technology. This makes it possible to provide feedback based on the participant's emotional state and realize a practical and psychologically effective training experience.

[0785] A "generative model" is a mathematical or computer code template used to automatically create scenarios that meet specific conditions based on regional characteristics and participant attributes.

[0786] "Geographic information" refers to information that includes relevant data about a region, and is data that indicates geographical characteristics such as location and environment.

[0787] "Emotion recognition technology" is a technology that analyzes a user's psychological state from their facial expressions, voice, text, etc., and evaluates their emotions in real time.

[0788] "Real-time feedback" is a process that provides immediate responses based on user behavior and emotions.

[0789] A "simulation" is a simulated experience in a virtual environment that virtually reproduces real-world situations, with the purpose of educating users and conducting verification.

[0790] "Psychological state" refers to the emotional and thought processes a user exhibits, and is a concept that includes internal expressions such as anxiety, joy, and tension.

[0791] "Feedback" refers to the evaluations and advice that a system provides to a user, and it is information that is adjusted in response to changes in behavior and emotions.

[0792] A description of the embodiment for carrying out the invention will be provided.

[0793] The system that realizes this application example consists of a server and terminals (e.g., smartphones), enabling customized disaster prevention training based on regional characteristics and participant attributes.

[0794] The server uses a generative model to collect and analyze regional characteristics data and participant attribute data, and generates training scenarios based on this data. This generative model utilizes cloud services to consider geographic information within the region and uses GIS data to provide visual simulations. In addition, it uses emotion recognition technologies such as Azure Cognitive Services to evaluate the user's psychological state in real time.

[0795] The device provides the user with a visual simulation based on this generated training scenario. The software used can include map display libraries such as Leaflet.js. This allows the user to experience a simulated disaster that closely resembles an actual event. Furthermore, the user's emotional data is sent to the server, and they receive appropriate feedback in real time based on the analysis results.

[0796] As a concrete example, consider a disaster preparedness drill conducted at a local school, simulating a typhoon. The server analyzes past typhoon data and current weather forecasts, generating a training scenario based on geographical information of the area expected to be affected by the typhoon. Furthermore, an emotion engine monitors participants' psychological states, detecting anxiety and tension. The terminal uses a map of the school's surroundings to perform the simulation and presents the optimal evacuation route. Through this simulation, users can learn appropriate actions to take in the event of a disaster.

[0797] An example of a prompt message would be, "Generate an evacuation scenario for the expected typhoon at the current location, analyze the user's psychological state in real time, and provide reassuring feedback." In this way, users can learn to respond quickly and calmly during disasters.

[0798] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0799] Step 1:

[0800] The server collects regional characteristics data and participant attribute data. Meteorological data and Geographic Information System (GIS) data are also acquired at this time. The data is organized on the cloud and processed as foundational information for generating training scenarios. The collected data is integrated within the server and stored as an initial dataset.

[0801] Step 2:

[0802] The server uses a generative AI model based on the collected data to generate customized training scenarios. The input includes participant attributes and regional characteristics, and data processing based on this information generates scenarios tailored to each participant. The generated scenarios are stored in a database for later use.

[0803] Step 3:

[0804] The terminal receives training scenarios sent from the server and provides a visual simulation using geographic information. Here, a map display library such as Leaflet.js is used to execute a disaster simulation tailored to the user's location. This allows the user to visually confirm safe evacuation routes and their surrounding conditions.

[0805] Step 4:

[0806] The server uses Azure Cognitive Services to analyze user emotional data in real time. It analyzes voice and facial expression data as input and uses the results to determine the user's psychological state. The obtained emotional data is then used for subsequent feedback.

[0807] Step 5:

[0808] The server generates real-time feedback based on analyzed emotional data and sends it to the device. For users who show anxiety or stress, it creates calming instructions and encouraging messages. This generated feedback is received by the user as practical advice, which they then use to guide their actions.

[0809] Step 6:

[0810] Users review feedback from the device and attempt to modify their behavior accordingly. They gain training experience while referring to the visual simulations provided by the device. Finally, they conduct a self-assessment and prepare for the next training session based on the report provided after the training is completed.

[0811] 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.

[0812] 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.

[0813] 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 robot 414.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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."

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] The following is further disclosed regarding the embodiments described above.

[0833] (Claim 1)

[0834] A means for generating customized training scenarios based on regional characteristics and participant attributes using a generative model,

[0835] A means of providing a visual simulation of a generated scenario using geographic information,

[0836] A means of generating real-time feedback based on user behavior,

[0837] By analyzing the collected data, we can develop methods for evaluating region-specific risks and disaster preparedness.

[0838] A system that includes this.

[0839] (Claim 2)

[0840] The system according to claim 1, which provides users with a practical disaster prevention training experience based on a generated training scenario.

[0841] (Claim 3)

[0842] The system according to claim 1, which provides the user with a comprehensive feedback report after the completion of training.

[0843] "Example 1"

[0844] (Claim 1)

[0845] A means for generating personalized scenarios based on regional characteristics and user attributes using a generative model,

[0846] A means of providing a visual simulation experience of a generated scenario using geographic information,

[0847] A means of monitoring user behavior and generating evaluations and feedback in real time,

[0848] A means of analyzing the collected information and evaluating the specific risks and disaster response preparations of that region,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, which provides users with realistic crisis response training based on a generated scenario.

[0852] (Claim 3)

[0853] The system according to claim 1, which provides the user with a comprehensive evaluation report after the completion of training.

[0854] "Application Example 1"

[0855] (Claim 1)

[0856] A means for generating customized training scenarios based on regional characteristics and participant attributes using a generative model,

[0857] A means of providing a visual simulation of a generated scenario using geographic information,

[0858] A means of generating real-time feedback based on user behavior,

[0859] By analyzing the collected data, we can develop methods for evaluating region-specific risks and disaster preparedness.

[0860] A means of providing users with an interactive experience using a video display device and visually indicating the situation in an emergency,

[0861] A system that includes this.

[0862] (Claim 2)

[0863] The system according to claim 1, which provides users with a practical disaster prevention training experience based on a generated training scenario.

[0864] (Claim 3)

[0865] The system according to claim 1, which provides the user with a comprehensive feedback report after the completion of training.

[0866] "Example 2 of combining an emotion engine"

[0867] (Claim 1)

[0868] A means for generating customized training scenarios based on regional characteristics and participant attributes using a generative AI model,

[0869] A means of providing a visual simulation of a generated scenario using geographic information,

[0870] A means of generating real-time feedback based on user behavior and sentiment data,

[0871] By analyzing the collected data, we can develop methods for evaluating region-specific risks and disaster preparedness.

[0872] A means of analyzing the user's emotional state and providing appropriate feedback during training,

[0873] A system that includes this.

[0874] (Claim 2)

[0875] The system according to claim 1, which provides users with a practical disaster prevention training experience based on a generated training scenario.

[0876] (Claim 3)

[0877] The system according to claim 1, which provides the user with a summary feedback report after the completion of training, including changes in emotional data.

[0878] "Application example 2 when combining with an emotional engine"

[0879] (Claim 1)

[0880] A means for generating customized training scenarios based on regional characteristics and participant attributes using a generative model,

[0881] A means of providing a visual simulation of a generated scenario using geographic information,

[0882] A means of evaluating a user's psychological state in real time using emotion recognition technology,

[0883] A means of generating real-time feedback based on user behavior and sentiment data,

[0884] By analyzing the collected data, we can develop methods for evaluating region-specific risks and disaster preparedness.

[0885] A system that includes this.

[0886] (Claim 2)

[0887] The system according to claim 1, which provides users with a practical disaster prevention training experience based on a generated training scenario and provides evacuation guidance in response to changes in their emotions.

[0888] (Claim 3)

[0889] The system according to claim 1, which provides the user with a comprehensive feedback report after the completion of training, including suggestions for emotional improvement. [Explanation of symbols]

[0890] 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 for generating customized training scenarios based on regional characteristics and participant attributes using a generative model, A means of providing a visual simulation of a generated scenario using geographic information, A means of generating real-time feedback based on user behavior, By analyzing the collected data, we can develop methods for evaluating region-specific risks and disaster preparedness. A system that includes this.

2. The system according to claim 1, which provides a user with a practical disaster prevention training experience based on a generated training scenario.

3. The system according to claim 1, which provides the user with a comprehensive feedback report after the completion of training.

Images