system

Abstract

Provide a system. [Solution] A means for generating disaster scenarios using generation AI; a means for displaying the generated disaster scenario in a metaverse space; A means of recording the user's evacuation behavior and providing appropriate feedback; A system including:

Description

[Technical Field]

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

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

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

[0004] Conventional disaster prevention training was difficult to conduct in-person, limiting realistic experiences, resulting in a lack of practical experience for taking appropriate action in the event of a disaster. Effective feedback was also not provided, limiting the repetition and learning effect of the training. As a result, there was an issue of the disaster prevention capabilities of the entire region not improving. [Means for solving the problem]

[0005] This invention relates to a system that uses a generation AI to generate disaster scenarios and realistically recreates those scenarios in a metaverse space. Specifically, it includes a means for utilizing the generation AI to generate disaster scenarios based on the characteristics of a specified area, and a means for displaying the generated disaster scenarios in the metaverse space. It also includes a means for recording the user's evacuation behavior and providing appropriate feedback, enabling effective disaster prevention training through a realistic experience. This makes it possible to improve the disaster prevention capabilities of the entire region.

[0006] "Generative AI" refers to technology that uses artificial intelligence to automatically generate data and scenarios based on specified parameters.

[0007] A "disaster scenario" refers to a plot or setting for virtually recreating disaster situations such as earthquakes, tsunamis, and fires.

[0008] "Metaverse space" refers to a three-dimensional virtual space on the Internet constructed using virtual reality technology.

[0009] "User" refers to an individual or organization that uses the system to participate in disaster prevention simulations.

[0010] "Evacuation behavior" refers to movements and actions taken to ensure safety when a disaster occurs.

[0011] "Feedback" refers to evaluation and advice regarding the user's actions in the simulation.

[0012] "Designated Area" refers to a specific geographic area based on input parameters for the Generating AI to generate disaster scenarios.

[0013] "VR environment" means a technical environment that allows users to experience virtual reality using a headset or other device.

[0014] "Server" refers to the computer system that manages the simulation environment and processes user data and disaster scenarios.

[0015] "Terminal" refers to a device that allows a user to access the metaverse space and conduct simulations. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] This invention is a system that utilizes generative AI to provide realistic disaster prevention scenarios and allows users to conduct evacuation drills in the metaverse space. This system enables local governments, companies, schools, and the general public to conduct effective disaster prevention drills.

[0038] First, the server serves as the platform for generating disaster scenarios. The server collects various parameters for a specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.) and inputs them into the generation AI. The generation AI uses this data to generate realistic disaster scenarios. The scenarios include the intensity of earthquake shaking, the occurrence of liquefaction, and the spread of fires.

[0039] The generated disaster scenario is sent from the server to the device. The device receives this scenario data and displays it in real time within the Metaverse space. Users can access this Metaverse space using a VR headset or other device, allowing them to virtually experience a real-life disaster situation.

[0040] The user initiates evacuation actions, such as evacuating to higher ground in the event of an earthquake, fleeing a fire, or moving to a designated evacuation site. The device transmits the user's behavior data to the server in real time. This data is later analyzed and provided to the user as appropriate feedback.

[0041] As a concrete example, let's consider the case where a user participates in an earthquake scenario. First, the server collects earthquake risk data for a specified area and uses a generation AI to generate a magnitude 6 earthquake scenario. This scenario includes the risk of building collapse, evacuation route settings, and the possibility of nearby fires. Next, this scenario data is sent to the device, and the user puts on a VR headset to experience a virtual earthquake. When the user attempts to evacuate, their actions are recorded by the device and sent to the server. The server analyzes this data and provides feedback to the user on whether their evacuation actions were appropriate and how they can be improved.

[0042] This system allows users to conduct realistic evacuation drills and gain practical experience in taking appropriate action in the event of a disaster, thereby improving the disaster prevention capabilities of the entire region and promoting the creation of safe communities.

[0043] The processing flow will be explained below.

[0044] Step 1:

[0045] The server collects parameters related to the specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.) from a database.

[0046] Step 2:

[0047] The server then activates the AI ​​generator based on the collected parameters to generate realistic disaster scenarios, adding detailed scenario elements such as earthquake occurrence, risk of liquefaction, and the spread of fire.

[0048] Step 3:

[0049] The generated disaster scenarios are stored on the server, and scenarios are managed for each specified user.

[0050] Step 4:

[0051] Users can send a request to access the metaverse space to the server via their terminal, and can select the disaster scenario they want to use.

[0052] Step 5:

[0053] The server receives the user's request and sends the appropriate disaster scenario to the terminal, delivering the scenario data in real time.

[0054] Step 6:

[0055] The device analyzes disaster scenario data received from the server and displays it in the Metaverse space, while setting up a VR environment so that users can access the virtual space.

[0056] Step 7:

[0057] Users can access the metaverse using VR headsets or other devices to experience realistic disaster scenarios, such as searching for evacuation routes and evacuating to a safe location after an earthquake.

[0058] Step 8:

[0059] The device transmits user behavior data to the server in real time, including the user's travel route, evacuation speed, selected evacuation location, etc.

[0060] Step 9:

[0061] The server analyzes the received user behavior data and evaluates the evacuation behavior, determining whether the evacuation behavior was appropriate and what improvements are needed.

[0062] Step 10:

[0063] The server generates feedback based on the analysis results and sends it to the user, including successes and areas for improvement, which can be used for the next training session.

[0064] Step 11:

[0065] The user receives feedback from the server and reviews their evacuation behavior, which is expected to lead to more appropriate behavior in the next simulation.

[0066] Example 1

[0067] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0068] Traditional disaster prevention drills are often conducted at actual sites, which takes time, costs money, and requires a large number of personnel. Furthermore, there are many different scenarios that could occur in the event of a real disaster, making it difficult to cover them all. Furthermore, evaluation and feedback of drill results are often subjective, making it difficult to find effective improvement measures. In response to these issues, there is a growing need for disaster prevention training systems that use digital means.

[0069] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0070] In this invention, the server includes a means for collecting parameters based on the characteristics of a specified area, a means for providing the collected parameters as input data to a generative AI model and generating realistic disaster scenarios using prompt sentences, and a means for converting the generated disaster scenarios into JSON format and transmitting them to a terminal via a secure communication protocol. This allows users to experience realistic and diverse disaster scenarios in the metaverse space and take evacuation actions, enabling practical disaster prevention training. Furthermore, by recording users' evacuation actions and analyzing them using a machine learning algorithm, quantitative and objective feedback is provided, improving disaster prevention capabilities.

[0071] "Designated Area" refers to a particular geographic area that is considered in generating disaster scenarios.

[0072] "Parameters" are numerical values ​​or data sets that represent the characteristics of an area, including seismic intensity, topography, population density, building structure, evacuation routes, and fire risk.

[0073] A "generative AI model" refers to an artificial intelligence algorithm or machine learning model that automatically generates disaster scenarios using specified parameters as input.

[0074] A "prompt" refers to input text that provides clear instructions to a generative AI model.

[0075] A "disaster scenario" is a hypothetical disaster situation model created by a generative AI model, and refers to a detailed simulation of a specific disaster situation such as an earthquake or fire.

[0076] "JSON format" is a data format for structuring disaster scenarios and other data, and is an abbreviation for JavaScript (registered trademark) Object Notation.

[0077] A "secure communications protocol" is a communications method that ensures security when sending and receiving data, and uses encryption to maintain the confidentiality and integrity of data.

[0078] A "device" is a digital device operated by a user, including hardware such as a computer, smartphone, or VR headset.

[0079] A "metaverse space" refers to a three-dimensional virtual space where users can have virtual experiences, and is constructed using game engines such as Unity and Unreal Engine.

[0080] "Evacuation behavior" refers to the actions and behaviors of evacuation and response that users perform in a virtual disaster scenario.

[0081] "Behavioral Data" refers to recorded information about a user's evacuation behavior, including details such as the user's travel route, response actions, and use of evacuation equipment.

[0082] A "machine learning algorithm" is an algorithm used to analyze user behavior data, learning patterns and trends from the data and generating behavioral evaluations and feedback.

[0083] "Feedback" refers to information about evaluations and areas for improvement provided to users based on the analysis results.

[0084] This invention is a system that uses generative AI to provide realistic disaster scenarios in the metaverse space, allowing users to conduct evacuation drills. This invention will be explained in detail, dividing it into the server, terminals, and users.

[0085] First, the server collects parameters based on the characteristics of the specified area, including data on earthquake intensity, topography, population density, building structure, evacuation routes, fire risk, etc. The server obtains this data using public databases and geoserver APIs.

[0086] Next, the generative AI model receives these parameters and generates a disaster scenario. Specifically, the server inputs the following prompt sentences to the generative AI:

[0087] "Generate a scenario of a severe earthquake in a specified area (City A). The earthquake has a seismic intensity of 6. Collected data includes topography, population density, building structure, evacuation routes, and fire risk. Based on this data, generate a realistic disaster scenario."

[0088] The generated disaster scenario is converted into JSON format and sent from the server to the terminal via a secure communication protocol (HTTPS).

[0089] The device builds a metaverse space based on the received disaster scenario, using game engines such as Unity and Unreal Engine, and users can experience the disaster scenario in real time using a VR headset or mobile device.

[0090] When a user evacuates in the virtual space, the device records their behavioral data in real time, including the user's route, response actions, and evacuation equipment used. The recorded behavioral data is then sent back to the server, where it is analyzed using machine learning algorithms.

[0091] The server provides feedback to the user based on the analysis results. This feedback informs the user of the appropriateness of the evacuation route and areas for improvement. This allows the user to receive specific advice on how to improve their disaster prevention capabilities.

[0092] Through these steps, the system allows users to experience realistic disaster scenarios and conduct practical disaster prevention drills, thereby improving the disaster prevention capabilities of the entire region and promoting the creation of safe communities.

[0093] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0094] Step 1: Data collection

[0095] The server collects parameters based on the characteristics of the specified area (seismic intensity, topography, population density, building structure, evacuation routes, and fire risk). The input is the ID and geographic information of the specified area. The output is a dataset containing these parameters. Specifically, the server uses public databases and geoserver APIs to extract the required information.

[0096] Step 2: Prompt generation

[0097] The server creates a prompt sentence to be input to the generative AI model based on the collected parameters. The input is the parameters obtained in step 1. The output is a prompt sentence in a format that the generative AI can understand. Specifically, the server generates text containing phrases such as "specified area (City A)."

[0098] Step 3: Disaster scenario generation

[0099] The server inputs the generated prompt sentences into the generative AI model to generate realistic disaster scenarios. The input is the prompt sentence created in step 2. The output is disaster scenario data in text or JSON format. Specifically, the server executes an API request to the generative AI and receives the scenario data.

[0100] Step 4: Sending scenario data

[0101] The server converts the generated disaster scenario into JSON format and sends it to the terminal via a secure communication protocol. The input is the disaster scenario data obtained in step 3. The output is the JSON format data sent to the terminal. Specifically, the server sends the data to the client terminal using HTTPS.

[0102] Step 5: Building the Metaverse

[0103] The device constructs a metaverse space based on the scenario data received from the server. The input is the disaster scenario data in JSON format received in step 4. The output is the disaster scenario reproduced in the metaverse space. Specifically, the device uses Unity or Unreal Engine to construct a virtual space using the received data.

[0104] Step 6: Record your evacuation actions

[0105] When a user evacuates in the metaverse space, the device records the behavioral data in real time. The input is information about the user's movements and actions. The output is the recorded behavioral data. Specifically, the device records the user's movement route and actions in a log in real time.

[0106] Step 7: Sending behavioral data

[0107] The device sends the recorded behavioral data to the server. The input is the behavioral data recorded in step 6. The output is the behavioral data sent to the server. Specifically, the device sends the behavioral data to the server using WebSocket or HTTPS.

[0108] Step 8: Analyze behavioral data

[0109] The server analyzes the received behavioral data and evaluates the appropriateness of the user's evacuation behavior. The input is the behavioral data sent in step 7. The output is evaluation data containing the analysis results. Specifically, the server analyzes the behavioral data using a machine learning algorithm and generates an evaluation report.

[0110] Step 9: Provide feedback

[0111] The server provides feedback to the user based on the analysis results. The input is the evaluation data obtained in step 8. The output is the feedback information provided to the user. Specifically, the server sends the generated evaluation report to the terminal, and the user receives the feedback.

[0112] (Application example 1)

[0113] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0114] Conventional disaster prevention training mainly involves simulations in the real world, making it difficult to recreate realistic situations that can be applied in the event of an actual disaster. In addition, there is a lack of feedback for users to effectively conduct evacuation drills, making it difficult to acquire practical skills.

[0115] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0116] In this invention, the server includes means for generating disaster scenarios using a generation AI, means for displaying the generated disaster scenarios in a metaverse space, means for recording users' evacuation behavior and providing appropriate feedback, and means for users to access the metaverse space using a smart device. This allows users to experience realistic disaster scenarios in a virtual space and conduct practical disaster prevention training while judging the effectiveness of their evacuation behaviors.

[0117] "Generative AI" is an artificial intelligence that generates disaster scenarios based on specified parameters.

[0118] "Disaster scenarios" are simulation data used to recreate hypothetical disaster situations such as earthquakes, fires, and liquefaction.

[0119] A "metaverse space" is a three-dimensional virtual environment constructed using virtual reality technology, and is a space that users can experience virtually.

[0120] "Feedback" is information that is provided to users by analyzing their evacuation behavior data and providing them with information on the effectiveness of the training and areas for improvement.

[0121] A "smart device" is a smartphone, smart glasses, head-mounted display, or other electronic device that allows a user to access the Metaverse space.

[0122] "Evacuation behavior" refers to the evacuation actions that users take in a virtual space when a disaster occurs.

[0123] "Real-time" refers to the immediate reflection of generated disaster scenarios and user evacuation actions.

[0124] This invention is a system that uses generative AI to recreate realistic disaster scenarios in a metaverse space, allowing users to conduct evacuation drills using VR devices, etc.

[0125] First, the server collects various parameters of the specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.). This data is input into the generation AI, which uses this data to generate disaster scenarios that include earthquakes, fires, liquefaction, and other phenomena. An example of a specific prompt for scenario generation is, "Please simulate the impact of a magnitude 6 earthquake on major infrastructure in an area with a population density of 1,000 people per square kilometer."

[0126] The generated disaster scenario is then sent from the server to the user's device. The user puts on a VR headset or smart device and accesses the metaverse space. Here, the user experiences a virtually recreated disaster situation and performs evacuation actions. During this process, the user's movements and choices are all recorded in real time.

[0127] The device sends the user's evacuation behavior data to a server, which analyzes the data. Based on the analysis results, the server provides the user with feedback on the appropriateness of their evacuation behavior and areas for improvement. Specifically, the feedback could be something like, "When an earthquake occurs, your first response should have been to hide in a safe place indoors."

[0128] The system aims to not only raise users' disaster prevention awareness by allowing them to experience realistic disaster scenarios, but also to enable them to respond quickly and appropriately in the event of a disaster by practicing actual evacuation procedures. Use of this system will improve disaster prevention capabilities throughout the region and promote the creation of safe communities.

[0129] The specific hardware and software used are as follows. Hardware includes servers, VR headsets, smartphones, and other smart devices. Software includes generative AI models and data analysis tools. An example prompt is, "Simulate the impact of a magnitude 6 earthquake on key infrastructure in an area with a population density of 1,000 people per square kilometer."

[0130] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0131] Step 1:

[0132] The server collects parameters such as geographical information, population density, infrastructure status, and past disaster data for the specified area. Based on this data, the risk of disaster occurrence is predicted. As a specific example, the probability of an earthquake with a seismic intensity of 6 occurring and its impact area are analyzed. The input data are parameters related to the characteristics of the area, and the output data is the analyzed risk information.

[0133] Step 2:

[0134] The server inputs the collected parameters into the generative AI model, which then uses this data to generate realistic disaster scenarios. An example prompt sentence used here is, "Please simulate the impact on key infrastructure in an area with a population density of 1,000 people per square kilometer in the event of a magnitude 6 earthquake." The input data are the prompt sentence and regional parameters, and the output data is the disaster scenario.

[0135] Step 3:

[0136] The server sends the generated disaster scenario to the user's device. The device receives this scenario data and recreates the disaster scenario in the metaverse space. Specifically, it visualizes earthquake tremors, fire outbreaks, and other events in the virtual space. The input data is the disaster scenario, and the output data is the disaster simulation displayed in the metaverse space.

[0137] Step 4:

[0138] Users wear a VR headset or smart device and access the Metaverse space. They experience a virtually recreated disaster situation and take evacuation action. During this process, the user's movements and choices are recorded in real time by the device. The input data is the user's operations and behavior data, and the output data is the recorded behavior history.

[0139] Step 5:

[0140] The device sends the user's evacuation behavior data to the server. The server analyzes this data and evaluates the appropriateness of the user's behavior. Specifically, it performs an analysis such as "Was the initial response of evacuating to higher ground appropriate?" The input data is the user's behavior data, and the output data is an evaluation of the behavior and suggestions for improvement.

[0141] Step 6:

[0142] The server provides feedback to the user based on the analysis results. For example, it might say, "The initial response at the time of the earthquake was quick and appropriate, but there is room for improvement in the selection of evacuation routes." The input data is the behavioral analysis results, and the output data is feedback information.

[0143] Step 7:

[0144] Users can refer to the feedback they receive and use it in their next evacuation drill. This repetition improves their practical skills, enabling them to respond appropriately when a disaster occurs. The input data is the provided feedback, and the output data is the user's improved evacuation behavior.

[0145] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0146] This invention is a system that utilizes generative AI to provide realistic disaster scenarios, allowing users to conduct evacuation drills in the metaverse space, and also combines it with an emotion engine that recognizes users' emotions. This system enables local governments, companies, schools, and the general public to conduct effective disaster prevention drills.

[0147] First, the server serves as the platform for generating disaster scenarios. The server collects various parameters for a specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.) and inputs them into the generation AI. The generation AI uses this data to generate realistic disaster scenarios. The scenarios include the intensity of earthquake shaking, the occurrence of liquefaction, and the spread of fires.

[0148] The generated disaster scenario is sent from the server to the device. The device receives this scenario data and displays it in real time within the Metaverse space. Users can access this Metaverse space using a VR headset or other device, allowing them to virtually experience a real-life disaster situation.

[0149] Additionally, the device is equipped with an emotion engine. When the user begins evacuation, the emotion engine monitors the user's facial expressions, tone of voice, heart rate, and other factors in real time to analyze the user's emotional state. The results of this analysis are sent to the server.

[0150] The user initiates evacuation actions, such as evacuating to higher ground in the event of an earthquake, fleeing a fire, or moving to a designated evacuation site. The device transmits the user's behavioral and emotional data to the server in real time. This data is later analyzed and provided to the user as appropriate feedback.

[0151] As a concrete example, let's consider the case where a user participates in an earthquake scenario. First, the server collects earthquake risk data for a specified area and uses a generation AI to generate a magnitude 6 earthquake scenario. This scenario includes the risk of building collapse, evacuation route settings, and the possibility of nearby fires. Next, this scenario data is sent to the device, and the user puts on a VR headset to experience a virtual earthquake. As the user evacuates, their behavior and emotional data are recorded by the device and sent to the server. The server analyzes this data and provides feedback on whether the evacuation behavior was appropriate, whether the user is feeling excessive stress, and how they can improve.

[0152] This system allows users to conduct realistic evacuation drills and gain practical experience to take appropriate action in the event of a disaster. Furthermore, the introduction of an emotion engine makes it possible to incorporate the user's psychological state into the training, resulting in more effective disaster prevention drills. As a result, disaster prevention capabilities across the entire region are improved, and the creation of safer communities is promoted.

[0153] The processing flow will be explained below.

[0154] Step 1:

[0155] The server collects parameters related to the specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.) from a database.

[0156] Step 2:

[0157] The server then activates the AI ​​generator based on the collected parameters to generate realistic disaster scenarios, adding detailed scenario elements such as earthquake occurrence, risk of liquefaction, and the spread of fire.

[0158] Step 3:

[0159] The generated disaster scenarios are stored on the server, and scenarios are managed for each specified user.

[0160] Step 4:

[0161] Users can send a request to access the metaverse space to the server via their terminal, and can select the disaster scenario they want to use.

[0162] Step 5:

[0163] The server receives the user's request and sends the appropriate disaster scenario to the terminal, delivering the scenario data in real time.

[0164] Step 6:

[0165] The device analyzes disaster scenario data received from the server and displays it in the Metaverse space, while setting up a VR environment so that users can access the virtual space.

[0166] Step 7:

[0167] Users can access the metaverse using VR headsets or other devices to experience realistic disaster scenarios, such as searching for evacuation routes and evacuating to a safe location after an earthquake.

[0168] Step 8:

[0169] The device is equipped with an emotion engine that monitors the user's facial expressions, tone of voice, heart rate, etc. in real time to analyze their emotional state.

[0170] Step 9:

[0171] The emotion engine provides the analyzed emotion data to the terminal, which then transmits the data to the server.

[0172] Step 10:

[0173] The device transmits user behavioral and emotional data to the server in real time, including the user's travel route, evacuation speed, emotional state, selected evacuation location, etc.

[0174] Step 11:

[0175] The server analyzes the received user behavioral and emotional data and evaluates the evacuation behavior and emotional state, determining whether the evacuation behavior was appropriate and what improvements are needed.

[0176] Step 12:

[0177] The server generates feedback based on the analysis results and sends it to the user, including successes and areas for improvement, as well as advice on managing emotional states, which can be applied to the next training session.

[0178] Step 13:

[0179] The user receives feedback from the server and reviews their evacuation behavior, which is expected to lead to more appropriate behavior in the next simulation.

[0180] Example 2

[0181] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0182] In conventional evacuation drill systems, users have limited opportunities to experience realistic disaster situations, making it difficult for them to take appropriate action in the event of a real disaster. In addition, training does not take into account the user's emotional state, resulting in insufficient stress management and making it difficult to implement effective disaster prevention drills.

[0183] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting data on disaster risks, means for generating a disaster scenario based on the collected data using a generation AI, means for displaying the generated disaster scenario in the metaverse space, means for a user to access the metaverse space using a VR headset, means for recording the user's evacuation behavior, means for monitoring the user's emotional data, means for transmitting the user's behavioral data and emotional data to the server, and means for the server to analyze the transmitted data and provide appropriate feedback. This allows the user to virtually experience a realistic disaster situation, thereby gaining practical experience for taking appropriate action in the event of an actual disaster, and realizing training that takes emotional states into consideration.

[0184] "Disaster risk data" refers to information such as earthquake intensity, topographical information, population density, and infrastructure status that is collected to assess the likelihood and impact of disasters.

[0185] "Generative AI" is a system that uses artificial intelligence technology to automatically generate realistic disaster scenarios based on input data.

[0186] A "disaster scenario" is a simulation of a hypothetical disaster situation generated based on constructed data, and includes specific earthquake shaking, building collapse, fire spread, etc.

[0187] A "metaverse space" is a three-dimensional virtual environment constructed using virtual reality technology, in which users can interact with each other within the virtual space.

[0188] A "VR headset" is a device worn by users to immerse themselves in a virtual reality space and specifically stimulate their visual and auditory senses.

[0189] "Emotional data" refers to information that indicates the user's psychological state, specifically facial expressions, tone of voice, heart rate, etc.

[0190] "Feedback" refers to specific advice and suggestions for improvement provided to users based on the results of the server's analysis of the user's evacuation behavior and emotional data.

[0191] This invention is a system that uses generative AI to create realistic disaster scenarios, allowing users to conduct evacuation drills in the metaverse space, and combines it with an emotion engine that recognizes users' emotions. This system enables local governments, companies, schools, and the general public to conduct effective disaster prevention drills.

[0192] 1. Collecting data on disaster risk

[0193] The server collects data on disaster risk in a designated area. A cloud server is a suitable hardware option. Specific software used includes the OpenStreetMap API to obtain map information and government earthquake information APIs (such as the USGS Earthquake API) to obtain earthquake information. Collected data includes earthquake intensity, topographical information, population density, and infrastructure status.

[0194] 2. Disaster scenario generation

[0195] The server inputs the collected data into a generative AI model to generate realistic disaster scenarios. The generative AI model used is, for example, GPT-4 (registered trademark). An example of a prompt is as follows:

[0196] Designated area: Tokyo

[0197] Parameters:

[0198] Earthquake magnitude: 6

[0199] Terrain data: [latitude, longitude, elevation]

[0200] Population density: high

[0201] Infrastructure situation: traffic congestion, earthquake resistance of buildings

[0202] Generative AI: GPT-4 model

[0203] ==========

[0204] Generate disaster scenarios:

[0205] An earthquake of magnitude 6 occurs

[0206] Risk of building collapse (location: Chuo Ward, Shibuya Ward)

[0207] Setting up evacuation routes (nearest evacuation site: Shinjuku Central Park)

[0208] Possibility of fire outbreak in neighboring areas (location: Minato Ward, Chiyoda Ward)

[0209] 3. Scenario display in the metaverse space

[0210] The device receives disaster scenario data sent from the server and displays it in the Metaverse space. Specifically, a 3D virtual environment is created using Unity or Unreal Engine, and disaster scenarios are reproduced in real time. Users wear a VR headset (e.g., Oculus Rift, HTC Vive) to access this virtual space and virtually experience real-life disaster situations.

[0211] 4. Monitoring evacuation behavior and emotion data

[0212] The device is equipped with an emotion engine that monitors the user's behavior and emotions in real time when they initiate evacuation actions. Specifically, it uses a facial recognition camera, microphone, and biosensor to collect information such as the user's facial expressions, tone of voice, and heart rate.

[0213] 5. Data Collection and Analysis

[0214] The device sends the collected behavioral and emotional data to a server, which analyzes the data and provides appropriate feedback. Machine learning algorithms are effective for this analysis. For example, the server can determine whether the user's evacuation route was optimal or their stress level.

[0215] 6. Providing Feedback

[0216] Based on the analysis results, the server provides feedback to the user, including advice on the appropriateness of evacuation behavior and stress management. For example, specific advice such as "The evacuation route was appropriate" or "Next time, please act calmly" is provided.

[0217] Specific examples

[0218] For example, if a user participates in an earthquake scenario, the server first collects earthquake risk data for Tokyo and uses generation AI to generate a magnitude 6 earthquake scenario. The generated scenario includes the risk of building collapse, evacuation routes, and the possibility of nearby fires. The server then sends this scenario data to the device, and the user puts on a VR headset to experience a virtual earthquake. The user's evacuation behavior and emotional data are collected by the device, and the server provides appropriate feedback after analysis.

[0219] This system allows users to virtually experience realistic disaster situations and practice appropriate actions in the event of a real disaster. Furthermore, it can also take emotional data into account in training, making disaster prevention training more effective.

[0220] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0221] Step 1: Data collection

[0222] The server collects disaster risk data. The input includes information about a specified area, such as seismic intensity data, topographical data, population density, and infrastructure status. Specifically, earthquake data is obtained from government earthquake information APIs (e.g., USGS Earthquake API), topographical data is downloaded from the OpenStreetMap API, and population density and infrastructure status data are collected from publicly available statistical databases. The output is an integrated disaster risk dataset that includes these data.

[0223] Step 2: Disaster scenario generation

[0224] The server inputs the collected dataset into the generative AI model along with a prompt sentence. The generative AI model used is GPT-4. An example of the prompt sentence is as follows:

[0225] Designated area: Tokyo

[0226] Parameters:

[0227] Earthquake magnitude: 6

[0228] Terrain data: [latitude, longitude, elevation]

[0229] Population density: high

[0230] Infrastructure situation: traffic congestion, earthquake resistance of buildings

[0231] Generative AI: GPT-4 model

[0232] ==========

[0233] Generate disaster scenarios:

[0234] An earthquake of magnitude 6 occurs

[0235] Risk of building collapse (location: Chuo Ward, Shibuya Ward)

[0236] Setting up evacuation routes (nearest evacuation site: Shinjuku Central Park)

[0237] Possibility of fire outbreak in neighboring areas (location: Minato Ward, Chiyoda Ward)

[0238] The output is a disaster scenario created by the generative AI model.

[0239] Step 3: Sending scenario data

[0240] The server sends the generated disaster scenario data to the terminal. The input is the disaster scenario data obtained from the generation AI, and the output is the transfer of the scenario data to the terminal. Specifically, the data is transferred securely using the HTTP protocol.

[0241] Step 4: Scenario display and user access to virtual space

[0242] The device displays the received scenario data in the Metaverse space. Specifically, it uses Unity or Unreal Engine to build a virtual space and recreate a disaster scenario in real time. The input is the received disaster scenario data, and the output is a 3D virtual environment generated based on that data. The user wears a VR headset and accesses this virtual space to experience the disaster.

[0243] Step 5: Implementing and monitoring evacuation actions

[0244] The user takes evacuation actions within the virtual space, such as evacuating to higher ground, evacuating from a fire, or moving to a designated evacuation site. The device collects the user's behavioral and emotional data. Specific actions include analyzing facial expressions with a facial recognition camera, collecting voice tone with a microphone, and measuring heart rate with a biosensor. The input is the user's behavior and biometric data, and the output is behavioral and emotional data monitored in real time.

[0245] Step 6: Analyze data and provide feedback

[0246] The device sends the collected behavioral and emotional data to a server. The input is the user's behavioral and emotional data, and the output is the data sent to the server. The server analyzes the received data and provides appropriate feedback. A machine learning algorithm is used for the analysis to evaluate the appropriateness of the user's evacuation behavior and stress level. Feedback is provided with advice on how to improve evacuation behavior and stress management. Specifically, the system generates text messages and voice guidance based on the analysis results and sends them to the user.

[0247] (Application example 2)

[0248] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0249] When a disaster occurs, it is important to take appropriate evacuation actions quickly, but conventional evacuation drill systems have difficulty realistically recreating the situation and psychological state of users when an actual disaster occurs. Furthermore, evacuation support systems using autonomous vehicles are not yet fully established, so there is a lack of real-time evacuation route presentations and psychological support for users in emergencies. This can sometimes prevent users from taking appropriate evacuation actions.

[0250] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating a disaster scenario using a generation AI, means for displaying the generated disaster scenario in a metaverse space, means for recording the user's evacuation behavior and providing appropriate feedback, means for having an emotion engine for monitoring the user's emotional state, and means for providing the disaster scenario to an autonomous vehicle and suggesting an evacuation route. This allows the user to conduct evacuation drills in a realistic environment, while at the same time providing a safe evacuation route in real time using the autonomous vehicle, enabling quick and appropriate evacuation. In addition, the emotion engine can grasp the user's psychological state and provide appropriate support, making evacuation behavior more effective.

[0251] "Generative AI" is an artificial intelligence technology that generates realistic disaster scenarios using multiple data parameters as input.

[0252] A "disaster scenario" is a model that virtually represents the situation when a disaster such as an earthquake or fire occurs, generated based on the characteristics of a specified area.

[0253] The "metaverse space" is a digital virtual space constructed using virtual reality technology, where users can conduct evacuation drills and simulations through digital avatars.

[0254] The "emotion engine" is a technology that analyzes data such as a user's facial expressions, tone of voice, and heart rate to grasp the user's emotional state in real time.

[0255] An "autonomous vehicle" is a vehicle that uses artificial intelligence technology to drive autonomously and is equipped with a system that displays safe evacuation routes in the event of a disaster and controls autonomous driving.

[0256] An "evacuation route" is a route set up to allow users to safely travel to an evacuation site in the event of a disaster.

[0257] "Evacuation behavior" refers to a series of actions or behaviors that a user takes to evacuate to a safe place when a disaster occurs.

[0258] "Feedback" is information including suggestions for improvement and advice provided based on the user's evacuation behavior and psychological state.

[0259] This invention is a system that utilizes generative AI to provide realistic disaster scenarios and allows users to conduct evacuation drills in the metaverse space. Furthermore, by combining it with an emotion engine, it grasps the user's psychological state and provides appropriate feedback. It also has the function of providing disaster scenarios to autonomous vehicles and suggesting evacuation routes.

[0260] First, the server serves as the platform for generating disaster scenarios. The server collects various parameters for a specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.) and inputs them into a generative AI model. The generative AI model uses this data to generate realistic disaster scenarios. These scenarios include the intensity of earthquake shaking, the occurrence of liquefaction, and the spread of fires.

[0261] The generated disaster scenario is sent from the server to the device. The device receives this scenario data and displays it in real time within the metaverse space. Users can access this metaverse space using a VR headset or similar device to virtually experience a real-life disaster situation.

[0262] Additionally, the device is equipped with an emotion engine. When the user begins evacuation, the emotion engine monitors the user's facial expressions, tone of voice, heart rate, and other factors in real time to analyze the user's emotional state. The results of this analysis are sent to the server.

[0263] The user initiates evacuation actions. For example, assuming an earthquake has occurred, the user may evacuate to higher ground, flee from a fire, or move to a designated evacuation site. The device transmits the user's behavioral and emotional data to the server in real time. This data is later analyzed and provided to the user as appropriate feedback.

[0264] The present invention can also be applied to autonomous vehicles. The generated disaster scenarios can be provided to autonomous vehicles, and evacuation routes can be displayed in real time. The emotion engine monitors the user's psychological state and provides support such as relaxation techniques as needed.

[0265] As a concrete example, let's consider the case where a user participates in an earthquake scenario. First, the server collects earthquake risk data for a specified area and uses a generation AI to generate a magnitude 7 earthquake scenario. This scenario includes the risk of building collapse, evacuation route settings, and the possibility of nearby fires. Next, this scenario data is sent to the device, and the user puts on a VR headset to experience a virtual earthquake. As the user evacuates, their behavior and emotional data are recorded by the device and sent to the server. The server analyzes this data and provides feedback on whether the evacuation behavior was appropriate, whether the user is feeling excessive stress, and how they can improve.

[0266] An example of a prompt sentence might be:

[0267] Prompt statement:

[0268] Based on Tokyo's topography and population data, please create a simulation of real-time traffic congestion information and evacuation routes after a magnitude 7 earthquake occurs. The evacuation routes should also include the congestion status of major roads and the status of evacuation shelters.

[0269] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0270] Step 1:

[0271] The server collects parameters for the specified area (seismic intensity, topography, population density, infrastructure status, etc.). These parameters are obtained as input data and prepared to be passed to the generative AI model. Specifically, the server uses databases and real-time APIs to collect the necessary regional data.

[0272] Step 2:

[0273] The server inputs the collected parameters into a generative AI model, which then uses this data to generate realistic disaster scenarios. Specifically, prompts are used to have the generative AI perform tasks such as, "Based on Tokyo's topography and population data, please create real-time traffic congestion information and evacuation route simulations after a magnitude 7 earthquake occurs. The evacuation route should also include the congestion status of major roads and the status of evacuation shelters."

[0274] Step 3:

[0275] The generated disaster scenario is sent from the server to the terminal. The data is converted into a format suitable for display in the metaverse space and sent to the terminal as scenario data. Specifically, the data is formatted in JSON format or similar so that the terminal can interpret it.

[0276] Step 4:

[0277] The scenario data received by the device is displayed in real time within the Metaverse space. Users put on a VR headset and experience the disaster scenario generated in the virtual space. Specifically, the VR space simulates earthquake shaking, building collapse, the spread of fire, and other events.

[0278] Step 5:

[0279] The user initiates an evacuation action, such as evacuating to higher ground, escaping from a fire, or moving to a designated evacuation site. The device records the user's behavioral data. Specifically, it records the user's route and timestamps of the action.

[0280] Step 6:

[0281] The emotion engine monitors the user's facial expressions, tone of voice, heart rate, etc. in real time to analyze the user's emotional state. The analysis results are sent from the device to a server. Specifically, data is collected using devices such as cameras, microphones, and heart rate sensors, and the emotion engine analyzes it.

[0282] Step 7:

[0283] The device sends the user's behavioral and emotional data to a server. The server receives this data and analyzes the appropriateness of evacuation behavior and the user's psychological state. Specifically, it uses machine learning algorithms to analyze the data and find areas for improvement and advice.

[0284] Step 8:

[0285] The server generates appropriate feedback based on the analysis results and provides it to the user. This feedback includes points to improve in evacuation behavior and psychological support methods. Specifically, specific advice is provided in text and audio format based on the user's stress level and speed of action.

[0286] Step 9:

[0287] The generated disaster scenario is provided to an autonomous vehicle, which then suggests a safe evacuation route. The autonomous vehicle then suggests a safe evacuation route in real time, while providing support according to the user's psychological state. Specifically, the system works in conjunction with the vehicle's navigation system to calculate the optimal route.

[0288] Step 10:

[0289] The emotion engine monitors the user's emotional state even while inside an autonomous vehicle and provides support such as relaxation techniques as needed. Specifically, it collects data using cameras, microphones, and heart rate sensors inside the vehicle and analyzes the user's emotional state in real time.

[0290] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0291] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0292] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0293] [Second embodiment]

[0294] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0295] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0296] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0297] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0298] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0299] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0300] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0301] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0302] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0303] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0304] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0305] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0306] This invention is a system that utilizes generative AI to provide realistic disaster prevention scenarios and allows users to conduct evacuation drills in the metaverse space. This system enables local governments, companies, schools, and the general public to conduct effective disaster prevention drills.

[0307] First, the server serves as the platform for generating disaster scenarios. The server collects various parameters for a specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.) and inputs them into the generation AI. The generation AI uses this data to generate realistic disaster scenarios. The scenarios include the intensity of earthquake shaking, the occurrence of liquefaction, and the spread of fires.

[0308] The generated disaster scenario is sent from the server to the device. The device receives this scenario data and displays it in real time within the Metaverse space. Users can access this Metaverse space using a VR headset or other device, allowing them to virtually experience a real-life disaster situation.

[0309] The user initiates evacuation actions, such as evacuating to higher ground in the event of an earthquake, fleeing a fire, or moving to a designated evacuation site. The device transmits the user's behavior data to the server in real time. This data is later analyzed and provided to the user as appropriate feedback.

[0310] As a concrete example, let's consider the case where a user participates in an earthquake scenario. First, the server collects earthquake risk data for a specified area and uses a generation AI to generate a magnitude 6 earthquake scenario. This scenario includes the risk of building collapse, evacuation route settings, and the possibility of nearby fires. Next, this scenario data is sent to the device, and the user puts on a VR headset to experience a virtual earthquake. When the user attempts to evacuate, their actions are recorded by the device and sent to the server. The server analyzes this data and provides feedback to the user on whether their evacuation actions were appropriate and how they can be improved.

[0311] This system allows users to conduct realistic evacuation drills and gain practical experience in taking appropriate action in the event of a disaster, thereby improving the disaster prevention capabilities of the entire region and promoting the creation of safe communities.

[0312] The processing flow will be explained below.

[0313] Step 1:

[0314] The server collects parameters related to the specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.) from a database.

[0315] Step 2:

[0316] The server then activates the AI ​​generator based on the collected parameters to generate realistic disaster scenarios, adding detailed scenario elements such as earthquake occurrence, risk of liquefaction, and the spread of fire.

[0317] Step 3:

[0318] The generated disaster scenarios are stored on the server, and scenarios are managed for each specified user.

[0319] Step 4:

[0320] Users can send a request to access the metaverse space to the server via their terminal, and can select the disaster scenario they want to use.

[0321] Step 5:

[0322] The server receives the user's request and sends the appropriate disaster scenario to the terminal, delivering the scenario data in real time.

[0323] Step 6:

[0324] The device analyzes disaster scenario data received from the server and displays it in the Metaverse space, while setting up a VR environment so that users can access the virtual space.

[0325] Step 7:

[0326] Users can access the metaverse using VR headsets or other devices to experience realistic disaster scenarios, such as searching for evacuation routes and evacuating to a safe location after an earthquake.

[0327] Step 8:

[0328] The device transmits user behavior data to the server in real time, including the user's travel route, evacuation speed, selected evacuation location, etc.

[0329] Step 9:

[0330] The server analyzes the received user behavior data and evaluates the evacuation behavior, determining whether the evacuation behavior was appropriate and what improvements are needed.

[0331] Step 10:

[0332] The server generates feedback based on the analysis results and sends it to the user, including successes and areas for improvement, which can be used for the next training session.

[0333] Step 11:

[0334] The user receives feedback from the server and reviews their evacuation behavior, which is expected to lead to more appropriate behavior in the next simulation.

[0335] Example 1

[0336] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0337] Traditional disaster prevention drills are often conducted at actual sites, which takes time, costs money, and requires a large number of personnel. Furthermore, there are many different scenarios that could occur in the event of a real disaster, making it difficult to cover them all. Furthermore, evaluation and feedback of drill results are often subjective, making it difficult to find effective improvement measures. In response to these issues, there is a growing need for disaster prevention training systems that use digital means.

[0338] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0339] In this invention, the server includes a means for collecting parameters based on the characteristics of a specified area, a means for providing the collected parameters as input data to a generative AI model and generating realistic disaster scenarios using prompt sentences, and a means for converting the generated disaster scenarios into JSON format and transmitting them to a terminal via a secure communication protocol. This allows users to experience realistic and diverse disaster scenarios in the metaverse space and take evacuation actions, enabling practical disaster prevention training. Furthermore, by recording users' evacuation actions and analyzing them using a machine learning algorithm, quantitative and objective feedback is provided, improving disaster prevention capabilities.

[0340] "Designated Area" refers to a particular geographic area that is considered in generating disaster scenarios.

[0341] "Parameters" are numerical values ​​or data sets that represent the characteristics of an area, including seismic intensity, topography, population density, building structure, evacuation routes, and fire risk.

[0342] A "generative AI model" refers to an artificial intelligence algorithm or machine learning model that automatically generates disaster scenarios using specified parameters as input.

[0343] A "prompt" refers to input text that provides clear instructions to a generative AI model.

[0344] A "disaster scenario" is a hypothetical disaster situation model created by a generative AI model, and refers to a detailed simulation of a specific disaster situation such as an earthquake or fire.

[0345] "JSON format" is a data format for structuring disaster scenarios and other data, and is an abbreviation for JavaScript Object Notation.

[0346] A "secure communications protocol" is a communications method that ensures security when sending and receiving data, and uses encryption to maintain the confidentiality and integrity of data.

[0347] A "device" is a digital device operated by a user, including hardware such as a computer, smartphone, or VR headset.

[0348] A "metaverse space" refers to a three-dimensional virtual space where users can have virtual experiences, and is constructed using game engines such as Unity and Unreal Engine.

[0349] "Evacuation behavior" refers to the actions and behaviors of evacuation and response that users perform in a virtual disaster scenario.

[0350] "Behavioral Data" refers to recorded information about a user's evacuation behavior, including details such as the user's travel route, response actions, and use of evacuation equipment.

[0351] A "machine learning algorithm" is an algorithm used to analyze user behavior data, learning patterns and trends from the data and generating behavioral evaluations and feedback.

[0352] "Feedback" refers to information about evaluations and areas for improvement provided to users based on the analysis results.

[0353] This invention is a system that uses generative AI to provide realistic disaster scenarios in the metaverse space, allowing users to conduct evacuation drills. This invention will be explained in detail, dividing it into the server, terminals, and users.

[0354] First, the server collects parameters based on the characteristics of the specified area, including data on earthquake intensity, topography, population density, building structure, evacuation routes, fire risk, etc. The server obtains this data using public databases and geoserver APIs.

[0355] Next, the generative AI model receives these parameters and generates a disaster scenario. Specifically, the server inputs the following prompt sentences to the generative AI:

[0356] "Generate a scenario of a severe earthquake in a specified area (City A). The earthquake has a seismic intensity of 6. Collected data includes topography, population density, building structure, evacuation routes, and fire risk. Based on this data, generate a realistic disaster scenario."

[0357] The generated disaster scenario is converted into JSON format and sent from the server to the terminal via a secure communication protocol (HTTPS).

[0358] The device builds a metaverse space based on the received disaster scenario, using game engines such as Unity and Unreal Engine, and users can experience the disaster scenario in real time using a VR headset or mobile device.

[0359] When a user evacuates in the virtual space, the device records their behavioral data in real time, including the user's route, response actions, and evacuation equipment used. The recorded behavioral data is then sent back to the server, where it is analyzed using machine learning algorithms.

[0360] The server provides feedback to the user based on the analysis results. This feedback informs the user of the appropriateness of the evacuation route and areas for improvement. This allows the user to receive specific advice on how to improve their disaster prevention capabilities.

[0361] Through these steps, the system allows users to experience realistic disaster scenarios and conduct practical disaster prevention drills, thereby improving the disaster prevention capabilities of the entire region and promoting the creation of safe communities.

[0362] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0363] Step 1: Data collection

[0364] The server collects parameters based on the characteristics of the specified area (seismic intensity, topography, population density, building structure, evacuation routes, and fire risk). The input is the ID and geographic information of the specified area. The output is a dataset containing these parameters. Specifically, the server uses public databases and geoserver APIs to extract the required information.

[0365] Step 2: Prompt generation

[0366] The server creates a prompt sentence to be input to the generative AI model based on the collected parameters. The input is the parameters obtained in step 1. The output is a prompt sentence in a format that the generative AI can understand. Specifically, the server generates text containing phrases such as "specified area (City A)."

[0367] Step 3: Disaster scenario generation

[0368] The server inputs the generated prompt sentences into the generative AI model to generate realistic disaster scenarios. The input is the prompt sentence created in step 2. The output is disaster scenario data in text or JSON format. Specifically, the server executes an API request to the generative AI and receives the scenario data.

[0369] Step 4: Sending scenario data

[0370] The server converts the generated disaster scenario into JSON format and sends it to the terminal via a secure communication protocol. The input is the disaster scenario data obtained in step 3. The output is the JSON format data sent to the terminal. Specifically, the server sends the data to the client terminal using HTTPS.

[0371] Step 5: Building the Metaverse

[0372] The device constructs a metaverse space based on the scenario data received from the server. The input is the disaster scenario data in JSON format received in step 4. The output is the disaster scenario reproduced in the metaverse space. Specifically, the device uses Unity or Unreal Engine to construct a virtual space using the received data.

[0373] Step 6: Record your evacuation actions

[0374] When a user evacuates in the metaverse space, the device records the behavioral data in real time. The input is information about the user's movements and actions. The output is the recorded behavioral data. Specifically, the device records the user's movement route and actions in a log in real time.

[0375] Step 7: Sending behavioral data

[0376] The device sends the recorded behavioral data to the server. The input is the behavioral data recorded in step 6. The output is the behavioral data sent to the server. Specifically, the device sends the behavioral data to the server using WebSocket or HTTPS.

[0377] Step 8: Analyze behavioral data

[0378] The server analyzes the received behavioral data and evaluates the appropriateness of the user's evacuation behavior. The input is the behavioral data sent in step 7. The output is evaluation data containing the analysis results. Specifically, the server analyzes the behavioral data using a machine learning algorithm and generates an evaluation report.

[0379] Step 9: Provide feedback

[0380] The server provides feedback to the user based on the analysis results. The input is the evaluation data obtained in step 8. The output is the feedback information provided to the user. Specifically, the server sends the generated evaluation report to the terminal, and the user receives the feedback.

[0381] (Application example 1)

[0382] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0383] Conventional disaster prevention training mainly involves simulations in the real world, making it difficult to recreate realistic situations that can be applied in the event of an actual disaster. In addition, there is a lack of feedback for users to effectively conduct evacuation drills, making it difficult to acquire practical skills.

[0384] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0385] In this invention, the server includes means for generating disaster scenarios using a generation AI, means for displaying the generated disaster scenarios in a metaverse space, means for recording users' evacuation behavior and providing appropriate feedback, and means for users to access the metaverse space using a smart device. This allows users to experience realistic disaster scenarios in a virtual space and conduct practical disaster prevention training while judging the effectiveness of their evacuation behaviors.

[0386] "Generative AI" is an artificial intelligence that generates disaster scenarios based on specified parameters.

[0387] "Disaster scenarios" are simulation data used to recreate hypothetical disaster situations such as earthquakes, fires, and liquefaction.

[0388] A "metaverse space" is a three-dimensional virtual environment constructed using virtual reality technology, and is a space that users can experience virtually.

[0389] "Feedback" is information that is provided to users by analyzing their evacuation behavior data and providing them with information on the effectiveness of the training and areas for improvement.

[0390] A "smart device" is a smartphone, smart glasses, head-mounted display, or other electronic device that allows a user to access the Metaverse space.

[0391] "Evacuation behavior" refers to the evacuation actions that users take in a virtual space when a disaster occurs.

[0392] "Real-time" refers to the immediate reflection of generated disaster scenarios and user evacuation actions.

[0393] This invention is a system that uses generative AI to recreate realistic disaster scenarios in a metaverse space, allowing users to conduct evacuation drills using VR devices, etc.

[0394] First, the server collects various parameters of the specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.). This data is input into the generation AI, which uses this data to generate disaster scenarios that include earthquakes, fires, liquefaction, and other phenomena. An example of a specific prompt for scenario generation is, "Please simulate the impact of a magnitude 6 earthquake on major infrastructure in an area with a population density of 1,000 people per square kilometer."

[0395] The generated disaster scenario is then sent from the server to the user's device. The user puts on a VR headset or smart device and accesses the metaverse space. Here, the user experiences a virtually recreated disaster situation and performs evacuation actions. During this process, the user's movements and choices are all recorded in real time.

[0396] The device sends the user's evacuation behavior data to a server, which analyzes the data. Based on the analysis results, the server provides the user with feedback on the appropriateness of their evacuation behavior and areas for improvement. Specifically, the feedback could be something like, "When an earthquake occurs, your first response should have been to hide in a safe place indoors."

[0397] The system aims to not only raise users' disaster prevention awareness by allowing them to experience realistic disaster scenarios, but also to enable them to respond quickly and appropriately in the event of a disaster by practicing actual evacuation procedures. Use of this system will improve disaster prevention capabilities throughout the region and promote the creation of safe communities.

[0398] The specific hardware and software used are as follows. Hardware includes servers, VR headsets, smartphones, and other smart devices. Software includes generative AI models and data analysis tools. An example prompt is, "Simulate the impact of a magnitude 6 earthquake on key infrastructure in an area with a population density of 1,000 people per square kilometer."

[0399] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0400] Step 1:

[0401] The server collects parameters such as geographical information, population density, infrastructure status, and past disaster data for the specified area. Based on this data, the risk of disaster occurrence is predicted. As a specific example, the probability of an earthquake with a seismic intensity of 6 occurring and its impact area are analyzed. The input data are parameters related to the characteristics of the area, and the output data is the analyzed risk information.

[0402] Step 2:

[0403] The server inputs the collected parameters into the generative AI model, which then uses this data to generate realistic disaster scenarios. An example prompt sentence used here is, "Please simulate the impact on key infrastructure in an area with a population density of 1,000 people per square kilometer in the event of a magnitude 6 earthquake." The input data are the prompt sentence and regional parameters, and the output data is the disaster scenario.

[0404] Step 3:

[0405] The server sends the generated disaster scenario to the user's device. The device receives this scenario data and recreates the disaster scenario in the metaverse space. Specifically, it visualizes earthquake tremors, fire outbreaks, and other events in the virtual space. The input data is the disaster scenario, and the output data is the disaster simulation displayed in the metaverse space.

[0406] Step 4:

[0407] Users wear a VR headset or smart device and access the Metaverse space. They experience a virtually recreated disaster situation and take evacuation action. During this process, the user's movements and choices are recorded in real time by the device. The input data is the user's operations and behavior data, and the output data is the recorded behavior history.

[0408] Step 5:

[0409] The device sends the user's evacuation behavior data to the server. The server analyzes this data and evaluates the appropriateness of the user's behavior. Specifically, it performs an analysis such as "Was the initial response of evacuating to higher ground appropriate?" The input data is the user's behavior data, and the output data is an evaluation of the behavior and suggestions for improvement.

[0410] Step 6:

[0411] The server provides feedback to the user based on the analysis results. For example, it might say, "The initial response at the time of the earthquake was quick and appropriate, but there is room for improvement in the selection of evacuation routes." The input data is the behavioral analysis results, and the output data is feedback information.

[0412] Step 7:

[0413] Users can refer to the feedback they receive and use it in their next evacuation drill. This repetition improves their practical skills, enabling them to respond appropriately when a disaster occurs. The input data is the provided feedback, and the output data is the user's improved evacuation behavior.

[0414] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0415] This invention is a system that utilizes generative AI to provide realistic disaster scenarios, allowing users to conduct evacuation drills in the metaverse space, and also combines it with an emotion engine that recognizes users' emotions. This system enables local governments, companies, schools, and the general public to conduct effective disaster prevention drills.

[0416] First, the server serves as the platform for generating disaster scenarios. The server collects various parameters for a specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.) and inputs them into the generation AI. The generation AI uses this data to generate realistic disaster scenarios. The scenarios include the intensity of earthquake shaking, the occurrence of liquefaction, and the spread of fires.

[0417] The generated disaster scenario is sent from the server to the device. The device receives this scenario data and displays it in real time within the Metaverse space. Users can access this Metaverse space using a VR headset or other device, allowing them to virtually experience a real-life disaster situation.

[0418] Additionally, the device is equipped with an emotion engine. When the user begins evacuation, the emotion engine monitors the user's facial expressions, tone of voice, heart rate, and other factors in real time to analyze the user's emotional state. The results of this analysis are sent to the server.

[0419] The user initiates evacuation actions, such as evacuating to higher ground in the event of an earthquake, fleeing a fire, or moving to a designated evacuation site. The device transmits the user's behavioral and emotional data to the server in real time. This data is later analyzed and provided to the user as appropriate feedback.

[0420] As a concrete example, let's consider the case where a user participates in an earthquake scenario. First, the server collects earthquake risk data for a specified area and uses a generation AI to generate a magnitude 6 earthquake scenario. This scenario includes the risk of building collapse, evacuation route settings, and the possibility of nearby fires. Next, this scenario data is sent to the device, and the user puts on a VR headset to experience a virtual earthquake. As the user evacuates, their behavior and emotional data are recorded by the device and sent to the server. The server analyzes this data and provides feedback on whether the evacuation behavior was appropriate, whether the user is feeling excessive stress, and how they can improve.

[0421] This system allows users to conduct realistic evacuation drills and gain practical experience to take appropriate action in the event of a disaster. Furthermore, the introduction of an emotion engine makes it possible to incorporate the user's psychological state into the training, resulting in more effective disaster prevention drills. As a result, disaster prevention capabilities across the entire region are improved, and the creation of safer communities is promoted.

[0422] The processing flow will be explained below.

[0423] Step 1:

[0424] The server collects parameters related to the specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.) from a database.

[0425] Step 2:

[0426] The server then activates the AI ​​generator based on the collected parameters to generate realistic disaster scenarios, adding detailed scenario elements such as earthquake occurrence, risk of liquefaction, and the spread of fire.

[0427] Step 3:

[0428] The generated disaster scenarios are stored on the server, and scenarios are managed for each specified user.

[0429] Step 4:

[0430] Users can send a request to access the metaverse space to the server via their terminal, and can select the disaster scenario they want to use.

[0431] Step 5:

[0432] The server receives the user's request and sends the appropriate disaster scenario to the terminal, delivering the scenario data in real time.

[0433] Step 6:

[0434] The device analyzes disaster scenario data received from the server and displays it in the Metaverse space, while setting up a VR environment so that users can access the virtual space.

[0435] Step 7:

[0436] Users can access the metaverse using VR headsets or other devices to experience realistic disaster scenarios, such as searching for evacuation routes and evacuating to a safe location after an earthquake.

[0437] Step 8:

[0438] The device is equipped with an emotion engine that monitors the user's facial expressions, tone of voice, heart rate, etc. in real time to analyze their emotional state.

[0439] Step 9:

[0440] The emotion engine provides the analyzed emotion data to the terminal, which then transmits the data to the server.

[0441] Step 10:

[0442] The device transmits user behavioral and emotional data to the server in real time, including the user's travel route, evacuation speed, emotional state, selected evacuation location, etc.

[0443] Step 11:

[0444] The server analyzes the received user behavioral and emotional data and evaluates the evacuation behavior and emotional state, determining whether the evacuation behavior was appropriate and what improvements are needed.

[0445] Step 12:

[0446] The server generates feedback based on the analysis results and sends it to the user, including successes and areas for improvement, as well as advice on managing emotional states, which can be applied to the next training session.

[0447] Step 13:

[0448] The user receives feedback from the server and reviews their evacuation behavior, which is expected to lead to more appropriate behavior in the next simulation.

[0449] Example 2

[0450] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0451] In conventional evacuation drill systems, users have limited opportunities to experience realistic disaster situations, making it difficult for them to take appropriate action in the event of a real disaster. In addition, training does not take into account the user's emotional state, resulting in insufficient stress management and making it difficult to implement effective disaster prevention drills.

[0452] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting data on disaster risks, means for generating a disaster scenario based on the collected data using a generation AI, means for displaying the generated disaster scenario in the metaverse space, means for a user to access the metaverse space using a VR headset, means for recording the user's evacuation behavior, means for monitoring the user's emotional data, means for transmitting the user's behavioral data and emotional data to the server, and means for the server to analyze the transmitted data and provide appropriate feedback. This allows the user to virtually experience a realistic disaster situation, thereby gaining practical experience for taking appropriate action in the event of an actual disaster, and realizing training that takes emotional states into consideration.

[0453] "Disaster risk data" refers to information such as earthquake intensity, topographical information, population density, and infrastructure status that is collected to assess the likelihood and impact of disasters.

[0454] "Generative AI" is a system that uses artificial intelligence technology to automatically generate realistic disaster scenarios based on input data.

[0455] A "disaster scenario" is a simulation of a hypothetical disaster situation generated based on constructed data, and includes specific earthquake shaking, building collapse, fire spread, etc.

[0456] A "metaverse space" is a three-dimensional virtual environment constructed using virtual reality technology, in which users can interact with each other within the virtual space.

[0457] A "VR headset" is a device worn by users to immerse themselves in a virtual reality space and specifically stimulate their visual and auditory senses.

[0458] "Emotional data" refers to information that indicates the user's psychological state, specifically facial expressions, tone of voice, heart rate, etc.

[0459] "Feedback" refers to specific advice and suggestions for improvement provided to users based on the results of the server's analysis of the user's evacuation behavior and emotional data.

[0460] This invention is a system that uses generative AI to create realistic disaster scenarios, allowing users to conduct evacuation drills in the metaverse space, and combines it with an emotion engine that recognizes users' emotions. This system enables local governments, companies, schools, and the general public to conduct effective disaster prevention drills.

[0461] 1. Collecting data on disaster risk

[0462] The server collects data on disaster risk in a designated area. A cloud server is a suitable hardware option. Specific software used includes the OpenStreetMap API to obtain map information and government earthquake information APIs (such as the USGS Earthquake API) to obtain earthquake information. Collected data includes earthquake intensity, topographical information, population density, and infrastructure status.

[0463] 2. Disaster scenario generation

[0464] The server inputs the collected data into a generative AI model to generate realistic disaster scenarios. The generative AI model used is, for example, GPT-4. An example of a prompt is as follows:

[0465] Designated area: Tokyo

[0466] Parameters:

[0467] Earthquake magnitude: 6

[0468] Terrain data: [latitude, longitude, elevation]

[0469] Population density: high

[0470] Infrastructure situation: traffic congestion, earthquake resistance of buildings

[0471] Generative AI: GPT-4 model

[0472] ==========

[0473] Generate disaster scenarios:

[0474] An earthquake of magnitude 6 occurs

[0475] Risk of building collapse (location: Chuo Ward, Shibuya Ward)

[0476] Setting up evacuation routes (nearest evacuation site: Shinjuku Central Park)

[0477] Possibility of fire outbreak in neighboring areas (location: Minato Ward, Chiyoda Ward)

[0478] 3. Scenario display in the metaverse space

[0479] The device receives disaster scenario data sent from the server and displays it in the Metaverse space. Specifically, a 3D virtual environment is created using Unity or Unreal Engine, and disaster scenarios are reproduced in real time. Users wear a VR headset (e.g., Oculus Rift, HTC Vive) to access this virtual space and virtually experience real-life disaster situations.

[0480] 4. Monitoring evacuation behavior and emotion data

[0481] The device is equipped with an emotion engine that monitors the user's behavior and emotions in real time when they initiate evacuation actions. Specifically, it uses a facial recognition camera, microphone, and biosensor to collect information such as the user's facial expressions, tone of voice, and heart rate.

[0482] 5. Data Collection and Analysis

[0483] The device sends the collected behavioral and emotional data to a server, which analyzes the data and provides appropriate feedback. Machine learning algorithms are effective for this analysis. For example, the server can determine whether the user's evacuation route was optimal or their stress level.

[0484] 6. Providing Feedback

[0485] Based on the analysis results, the server provides feedback to the user, including advice on the appropriateness of evacuation behavior and stress management. For example, specific advice such as "The evacuation route was appropriate" or "Next time, please act calmly" is provided.

[0486] Specific examples

[0487] For example, if a user participates in an earthquake scenario, the server first collects earthquake risk data for Tokyo and uses generation AI to generate a magnitude 6 earthquake scenario. The generated scenario includes the risk of building collapse, evacuation routes, and the possibility of nearby fires. The server then sends this scenario data to the device, and the user puts on a VR headset to experience a virtual earthquake. The user's evacuation behavior and emotional data are collected by the device, and the server provides appropriate feedback after analysis.

[0488] This system allows users to virtually experience realistic disaster situations and practice appropriate actions in the event of a real disaster. Furthermore, it can also take emotional data into account in training, making disaster prevention training more effective.

[0489] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0490] Step 1: Data collection

[0491] The server collects disaster risk data. The input includes information about a specified area, such as seismic intensity data, topographical data, population density, and infrastructure status. Specifically, earthquake data is obtained from government earthquake information APIs (e.g., USGS Earthquake API), topographical data is downloaded from the OpenStreetMap API, and population density and infrastructure status data are collected from publicly available statistical databases. The output is an integrated disaster risk dataset that includes these data.

[0492] Step 2: Disaster scenario generation

[0493] The server inputs the collected dataset into the generative AI model along with a prompt sentence. The generative AI model used is GPT-4. An example of the prompt sentence is as follows:

[0494] Designated area: Tokyo

[0495] Parameters:

[0496] Earthquake magnitude: 6

[0497] Terrain data: [latitude, longitude, elevation]

[0498] Population density: high

[0499] Infrastructure situation: traffic congestion, earthquake resistance of buildings

[0500] Generative AI: GPT-4 model

[0501] ==========

[0502] Generate disaster scenarios:

[0503] An earthquake of magnitude 6 occurs

[0504] Risk of building collapse (location: Chuo Ward, Shibuya Ward)

[0505] Setting up evacuation routes (nearest evacuation site: Shinjuku Central Park)

[0506] Possibility of fire outbreak in neighboring areas (location: Minato Ward, Chiyoda Ward)

[0507] The output is a disaster scenario created by the generative AI model.

[0508] Step 3: Sending scenario data

[0509] The server sends the generated disaster scenario data to the terminal. The input is the disaster scenario data obtained from the generation AI, and the output is the transfer of the scenario data to the terminal. Specifically, the data is transferred securely using the HTTP protocol.

[0510] Step 4: Scenario display and user access to virtual space

[0511] The device displays the received scenario data in the Metaverse space. Specifically, it uses Unity or Unreal Engine to build a virtual space and recreate a disaster scenario in real time. The input is the received disaster scenario data, and the output is a 3D virtual environment generated based on that data. The user wears a VR headset and accesses this virtual space to experience the disaster.

[0512] Step 5: Implementing and monitoring evacuation actions

[0513] The user takes evacuation actions within the virtual space, such as evacuating to higher ground, evacuating from a fire, or moving to a designated evacuation site. The device collects the user's behavioral and emotional data. Specific actions include analyzing facial expressions with a facial recognition camera, collecting voice tone with a microphone, and measuring heart rate with a biosensor. The input is the user's behavior and biometric data, and the output is behavioral and emotional data monitored in real time.

[0514] Step 6: Analyze data and provide feedback

[0515] The device sends the collected behavioral and emotional data to a server. The input is the user's behavioral and emotional data, and the output is the data sent to the server. The server analyzes the received data and provides appropriate feedback. A machine learning algorithm is used for the analysis to evaluate the appropriateness of the user's evacuation behavior and stress level. Feedback is provided with advice on how to improve evacuation behavior and stress management. Specifically, the system generates text messages and voice guidance based on the analysis results and sends them to the user.

[0516] (Application example 2)

[0517] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0518] When a disaster occurs, it is important to take appropriate evacuation actions quickly, but conventional evacuation drill systems have difficulty realistically recreating the situation and psychological state of users when an actual disaster occurs. Furthermore, evacuation support systems using autonomous vehicles are not yet fully established, so there is a lack of real-time evacuation route presentations and psychological support for users in emergencies. This can sometimes prevent users from taking appropriate evacuation actions.

[0519] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating a disaster scenario using a generation AI, means for displaying the generated disaster scenario in a metaverse space, means for recording the user's evacuation behavior and providing appropriate feedback, means for having an emotion engine for monitoring the user's emotional state, and means for providing the disaster scenario to an autonomous vehicle and suggesting an evacuation route. This allows the user to conduct evacuation drills in a realistic environment, while at the same time providing a safe evacuation route in real time using the autonomous vehicle, enabling quick and appropriate evacuation. In addition, the emotion engine can grasp the user's psychological state and provide appropriate support, making evacuation behavior more effective.

[0520] "Generative AI" is an artificial intelligence technology that generates realistic disaster scenarios using multiple data parameters as input.

[0521] A "disaster scenario" is a model that virtually represents the situation when a disaster such as an earthquake or fire occurs, generated based on the characteristics of a specified area.

[0522] The "metaverse space" is a digital virtual space constructed using virtual reality technology, where users can conduct evacuation drills and simulations through digital avatars.

[0523] The "emotion engine" is a technology that analyzes data such as a user's facial expressions, tone of voice, and heart rate to grasp the user's emotional state in real time.

[0524] An "autonomous vehicle" is a vehicle that uses artificial intelligence technology to drive autonomously and is equipped with a system that displays safe evacuation routes in the event of a disaster and controls autonomous driving.

[0525] An "evacuation route" is a route set up to allow users to safely travel to an evacuation site in the event of a disaster.

[0526] "Evacuation behavior" refers to a series of actions or behaviors that a user takes to evacuate to a safe place when a disaster occurs.

[0527] "Feedback" is information including suggestions for improvement and advice provided based on the user's evacuation behavior and psychological state.

[0528] This invention is a system that utilizes generative AI to provide realistic disaster scenarios and allows users to conduct evacuation drills in the metaverse space. Furthermore, by combining it with an emotion engine, it grasps the user's psychological state and provides appropriate feedback. It also has the function of providing disaster scenarios to autonomous vehicles and suggesting evacuation routes.

[0529] First, the server serves as the platform for generating disaster scenarios. The server collects various parameters for a specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.) and inputs them into a generative AI model. The generative AI model uses this data to generate realistic disaster scenarios. These scenarios include the intensity of earthquake shaking, the occurrence of liquefaction, and the spread of fires.

[0530] The generated disaster scenario is sent from the server to the device. The device receives this scenario data and displays it in real time within the metaverse space. Users can access this metaverse space using a VR headset or similar device to virtually experience a real-life disaster situation.

[0531] Additionally, the device is equipped with an emotion engine. When the user begins evacuation, the emotion engine monitors the user's facial expressions, tone of voice, heart rate, and other factors in real time to analyze the user's emotional state. The results of this analysis are sent to the server.

[0532] The user initiates evacuation actions. For example, assuming an earthquake has occurred, the user may evacuate to higher ground, flee from a fire, or move to a designated evacuation site. The device transmits the user's behavioral and emotional data to the server in real time. This data is later analyzed and provided to the user as appropriate feedback.

[0533] The present invention can also be applied to autonomous vehicles. The generated disaster scenarios can be provided to autonomous vehicles, and evacuation routes can be displayed in real time. The emotion engine monitors the user's psychological state and provides support such as relaxation techniques as needed.

[0534] As a concrete example, let's consider the case where a user participates in an earthquake scenario. First, the server collects earthquake risk data for a specified area and uses a generation AI to generate a magnitude 7 earthquake scenario. This scenario includes the risk of building collapse, evacuation route settings, and the possibility of nearby fires. Next, this scenario data is sent to the device, and the user puts on a VR headset to experience a virtual earthquake. As the user evacuates, their behavior and emotional data are recorded by the device and sent to the server. The server analyzes this data and provides feedback on whether the evacuation behavior was appropriate, whether the user is feeling excessive stress, and how they can improve.

[0535] An example of a prompt sentence might be:

[0536] Prompt statement:

[0537] Based on Tokyo's topography and population data, please create a simulation of real-time traffic congestion information and evacuation routes after a magnitude 7 earthquake occurs. The evacuation routes should also include the congestion status of major roads and the status of evacuation shelters.

[0538] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0539] Step 1:

[0540] The server collects parameters for the specified area (seismic intensity, topography, population density, infrastructure status, etc.). These parameters are obtained as input data and prepared to be passed to the generative AI model. Specifically, the server uses databases and real-time APIs to collect the necessary regional data.

[0541] Step 2:

[0542] The server inputs the collected parameters into a generative AI model, which then uses this data to generate realistic disaster scenarios. Specifically, prompts are used to have the generative AI perform tasks such as, "Based on Tokyo's topography and population data, please create real-time traffic congestion information and evacuation route simulations after a magnitude 7 earthquake occurs. The evacuation route should also include the congestion status of major roads and the status of evacuation shelters."

[0543] Step 3:

[0544] The generated disaster scenario is sent from the server to the terminal. The data is converted into a format suitable for display in the metaverse space and sent to the terminal as scenario data. Specifically, the data is formatted in JSON format or similar so that the terminal can interpret it.

[0545] Step 4:

[0546] The scenario data received by the device is displayed in real time within the Metaverse space. Users put on a VR headset and experience the disaster scenario generated in the virtual space. Specifically, the VR space simulates earthquake shaking, building collapse, the spread of fire, and other events.

[0547] Step 5:

[0548] The user initiates an evacuation action, such as evacuating to higher ground, escaping from a fire, or moving to a designated evacuation site. The device records the user's behavioral data. Specifically, it records the user's route and timestamps of the action.

[0549] Step 6:

[0550] The emotion engine monitors the user's facial expressions, tone of voice, heart rate, etc. in real time to analyze the user's emotional state. The analysis results are sent from the device to a server. Specifically, data is collected using devices such as cameras, microphones, and heart rate sensors, and the emotion engine analyzes it.

[0551] Step 7:

[0552] The device sends the user's behavioral and emotional data to a server. The server receives this data and analyzes the appropriateness of evacuation behavior and the user's psychological state. Specifically, it uses machine learning algorithms to analyze the data and find areas for improvement and advice.

[0553] Step 8:

[0554] The server generates appropriate feedback based on the analysis results and provides it to the user. This feedback includes points to improve in evacuation behavior and psychological support methods. Specifically, specific advice is provided in text and audio format based on the user's stress level and speed of action.

[0555] Step 9:

[0556] The generated disaster scenario is provided to an autonomous vehicle, which then suggests a safe evacuation route. The autonomous vehicle then suggests a safe evacuation route in real time, while providing support according to the user's psychological state. Specifically, the system works in conjunction with the vehicle's navigation system to calculate the optimal route.

[0557] Step 10:

[0558] The emotion engine monitors the user's emotional state even while inside an autonomous vehicle and provides support such as relaxation techniques as needed. Specifically, it collects data using cameras, microphones, and heart rate sensors inside the vehicle and analyzes the user's emotional state in real time.

[0559] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0560] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0561] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0562] [Third embodiment]

[0563] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0564] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0565] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0566] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0567] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0568] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0569] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0570] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0571] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0572] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0573] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0574] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0575] This invention is a system that utilizes generative AI to provide realistic disaster prevention scenarios and allows users to conduct evacuation drills in the metaverse space. This system enables local governments, companies, schools, and the general public to conduct effective disaster prevention drills.

[0576] First, the server serves as the platform for generating disaster scenarios. The server collects various parameters for a specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.) and inputs them into the generation AI. The generation AI uses this data to generate realistic disaster scenarios. The scenarios include the intensity of earthquake shaking, the occurrence of liquefaction, and the spread of fires.

[0577] The generated disaster scenario is sent from the server to the device. The device receives this scenario data and displays it in real time within the Metaverse space. Users can access this Metaverse space using a VR headset or other device, allowing them to virtually experience a real-life disaster situation.

[0578] The user initiates evacuation actions, such as evacuating to higher ground in the event of an earthquake, fleeing a fire, or moving to a designated evacuation site. The device transmits the user's behavior data to the server in real time. This data is later analyzed and provided to the user as appropriate feedback.

[0579] As a concrete example, let's consider the case where a user participates in an earthquake scenario. First, the server collects earthquake risk data for a specified area and uses a generation AI to generate a magnitude 6 earthquake scenario. This scenario includes the risk of building collapse, evacuation route settings, and the possibility of nearby fires. Next, this scenario data is sent to the device, and the user puts on a VR headset to experience a virtual earthquake. When the user attempts to evacuate, their actions are recorded by the device and sent to the server. The server analyzes this data and provides feedback to the user on whether their evacuation actions were appropriate and how they can be improved.

[0580] This system allows users to conduct realistic evacuation drills and gain practical experience in taking appropriate action in the event of a disaster, thereby improving the disaster prevention capabilities of the entire region and promoting the creation of safe communities.

[0581] The processing flow will be explained below.

[0582] Step 1:

[0583] The server collects parameters related to the specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.) from a database.

[0584] Step 2:

[0585] The server then activates the AI ​​generator based on the collected parameters to generate realistic disaster scenarios, adding detailed scenario elements such as earthquake occurrence, risk of liquefaction, and the spread of fire.

[0586] Step 3:

[0587] The generated disaster scenarios are stored on the server, and scenarios are managed for each specified user.

[0588] Step 4:

[0589] Users can send a request to access the metaverse space to the server via their terminal, and can select the disaster scenario they want to use.

[0590] Step 5:

[0591] The server receives the user's request and sends the appropriate disaster scenario to the terminal, delivering the scenario data in real time.

[0592] Step 6:

[0593] The device analyzes disaster scenario data received from the server and displays it in the Metaverse space, while setting up a VR environment so that users can access the virtual space.

[0594] Step 7:

[0595] Users can access the metaverse using VR headsets or other devices to experience realistic disaster scenarios, such as searching for evacuation routes and evacuating to a safe location after an earthquake.

[0596] Step 8:

[0597] The device transmits user behavior data to the server in real time, including the user's travel route, evacuation speed, selected evacuation location, etc.

[0598] Step 9:

[0599] The server analyzes the received user behavior data and evaluates the evacuation behavior, determining whether the evacuation behavior was appropriate and what improvements are needed.

[0600] Step 10:

[0601] The server generates feedback based on the analysis results and sends it to the user, including successes and areas for improvement, which can be used for the next training session.

[0602] Step 11:

[0603] The user receives feedback from the server and reviews their evacuation behavior, which is expected to lead to more appropriate behavior in the next simulation.

[0604] Example 1

[0605] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0606] Traditional disaster prevention drills are often conducted at actual sites, which takes time, costs money, and requires a large number of personnel. Furthermore, there are many different scenarios that could occur in the event of a real disaster, making it difficult to cover them all. Furthermore, evaluation and feedback of drill results are often subjective, making it difficult to find effective improvement measures. In response to these issues, there is a growing need for disaster prevention training systems that use digital means.

[0607] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0608] In this invention, the server includes a means for collecting parameters based on the characteristics of a specified area, a means for providing the collected parameters as input data to a generative AI model and generating realistic disaster scenarios using prompt sentences, and a means for converting the generated disaster scenarios into JSON format and transmitting them to a terminal via a secure communication protocol. This allows users to experience realistic and diverse disaster scenarios in the metaverse space and take evacuation actions, enabling practical disaster prevention training. Furthermore, by recording users' evacuation actions and analyzing them using a machine learning algorithm, quantitative and objective feedback is provided, improving disaster prevention capabilities.

[0609] "Designated Area" refers to a particular geographic area that is considered in generating disaster scenarios.

[0610] "Parameters" are numerical values ​​or data sets that represent the characteristics of an area, including seismic intensity, topography, population density, building structure, evacuation routes, and fire risk.

[0611] A "generative AI model" refers to an artificial intelligence algorithm or machine learning model that automatically generates disaster scenarios using specified parameters as input.

[0612] A "prompt" refers to input text that provides clear instructions to a generative AI model.

[0613] A "disaster scenario" is a hypothetical disaster situation model created by a generative AI model, and refers to a detailed simulation of a specific disaster situation such as an earthquake or fire.

[0614] "JSON format" is a data format for structuring disaster scenarios and other data, and is an abbreviation for JavaScript Object Notation.

[0615] A "secure communications protocol" is a communications method that ensures security when sending and receiving data, and uses encryption to maintain the confidentiality and integrity of data.

[0616] A "device" is a digital device operated by a user, including hardware such as a computer, smartphone, or VR headset.

[0617] A "metaverse space" refers to a three-dimensional virtual space where users can have virtual experiences, and is constructed using game engines such as Unity and Unreal Engine.

[0618] "Evacuation behavior" refers to the actions and behaviors of evacuation and response that users perform in a virtual disaster scenario.

[0619] "Behavioral Data" refers to recorded information about a user's evacuation behavior, including details such as the user's travel route, response actions, and use of evacuation equipment.

[0620] A "machine learning algorithm" is an algorithm used to analyze user behavior data, learning patterns and trends from the data and generating behavioral evaluations and feedback.

[0621] "Feedback" refers to information about evaluations and areas for improvement provided to users based on the analysis results.

[0622] This invention is a system that uses generative AI to provide realistic disaster scenarios in the metaverse space, allowing users to conduct evacuation drills. This invention will be explained in detail, dividing it into the server, terminals, and users.

[0623] First, the server collects parameters based on the characteristics of the specified area, including data on earthquake intensity, topography, population density, building structure, evacuation routes, fire risk, etc. The server obtains this data using public databases and geoserver APIs.

[0624] Next, the generative AI model receives these parameters and generates a disaster scenario. Specifically, the server inputs the following prompt sentences to the generative AI:

[0625] "Generate a scenario of a severe earthquake in a specified area (City A). The earthquake has a seismic intensity of 6. Collected data includes topography, population density, building structure, evacuation routes, and fire risk. Based on this data, generate a realistic disaster scenario."

[0626] The generated disaster scenario is converted into JSON format and sent from the server to the terminal via a secure communication protocol (HTTPS).

[0627] The device builds a metaverse space based on the received disaster scenario, using game engines such as Unity and Unreal Engine, and users can experience the disaster scenario in real time using a VR headset or mobile device.

[0628] When a user evacuates in the virtual space, the device records their behavioral data in real time, including the user's route, response actions, and evacuation equipment used. The recorded behavioral data is then sent back to the server, where it is analyzed using machine learning algorithms.

[0629] The server provides feedback to the user based on the analysis results. This feedback informs the user of the appropriateness of the evacuation route and areas for improvement. This allows the user to receive specific advice on how to improve their disaster prevention capabilities.

[0630] Through these steps, the system allows users to experience realistic disaster scenarios and conduct practical disaster prevention drills, thereby improving the disaster prevention capabilities of the entire region and promoting the creation of safe communities.

[0631] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0632] Step 1: Data collection

[0633] The server collects parameters based on the characteristics of the specified area (seismic intensity, topography, population density, building structure, evacuation routes, and fire risk). The input is the ID and geographic information of the specified area. The output is a dataset containing these parameters. Specifically, the server uses public databases and geoserver APIs to extract the required information.

[0634] Step 2: Prompt generation

[0635] The server creates a prompt sentence to be input to the generative AI model based on the collected parameters. The input is the parameters obtained in step 1. The output is a prompt sentence in a format that the generative AI can understand. Specifically, the server generates text containing phrases such as "specified area (City A)."

[0636] Step 3: Disaster scenario generation

[0637] The server inputs the generated prompt sentences into the generative AI model to generate realistic disaster scenarios. The input is the prompt sentence created in step 2. The output is disaster scenario data in text or JSON format. Specifically, the server executes an API request to the generative AI and receives the scenario data.

[0638] Step 4: Sending scenario data

[0639] The server converts the generated disaster scenario into JSON format and sends it to the terminal via a secure communication protocol. The input is the disaster scenario data obtained in step 3. The output is the JSON format data sent to the terminal. Specifically, the server sends the data to the client terminal using HTTPS.

[0640] Step 5: Building the Metaverse

[0641] The device constructs a metaverse space based on the scenario data received from the server. The input is the disaster scenario data in JSON format received in step 4. The output is the disaster scenario reproduced in the metaverse space. Specifically, the device uses Unity or Unreal Engine to construct a virtual space using the received data.

[0642] Step 6: Record your evacuation actions

[0643] When a user evacuates in the metaverse space, the device records the behavioral data in real time. The input is information about the user's movements and actions. The output is the recorded behavioral data. Specifically, the device records the user's movement route and actions in a log in real time.

[0644] Step 7: Sending behavioral data

[0645] The device sends the recorded behavioral data to the server. The input is the behavioral data recorded in step 6. The output is the behavioral data sent to the server. Specifically, the device sends the behavioral data to the server using WebSocket or HTTPS.

[0646] Step 8: Analyze behavioral data

[0647] The server analyzes the received behavioral data and evaluates the appropriateness of the user's evacuation behavior. The input is the behavioral data sent in step 7. The output is evaluation data containing the analysis results. Specifically, the server analyzes the behavioral data using a machine learning algorithm and generates an evaluation report.

[0648] Step 9: Provide feedback

[0649] The server provides feedback to the user based on the analysis results. The input is the evaluation data obtained in step 8. The output is the feedback information provided to the user. Specifically, the server sends the generated evaluation report to the terminal, and the user receives the feedback.

[0650] (Application example 1)

[0651] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0652] Conventional disaster prevention training mainly involves simulations in the real world, making it difficult to recreate realistic situations that can be applied in the event of an actual disaster. In addition, there is a lack of feedback for users to effectively conduct evacuation drills, making it difficult to acquire practical skills.

[0653] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0654] In this invention, the server includes means for generating disaster scenarios using a generation AI, means for displaying the generated disaster scenarios in a metaverse space, means for recording users' evacuation behavior and providing appropriate feedback, and means for users to access the metaverse space using a smart device. This allows users to experience realistic disaster scenarios in a virtual space and conduct practical disaster prevention training while judging the effectiveness of their evacuation behaviors.

[0655] "Generative AI" is an artificial intelligence that generates disaster scenarios based on specified parameters.

[0656] "Disaster scenarios" are simulation data used to recreate hypothetical disaster situations such as earthquakes, fires, and liquefaction.

[0657] A "metaverse space" is a three-dimensional virtual environment constructed using virtual reality technology, and is a space that users can experience virtually.

[0658] "Feedback" is information that is provided to users by analyzing their evacuation behavior data and providing them with information on the effectiveness of the training and areas for improvement.

[0659] A "smart device" is a smartphone, smart glasses, head-mounted display, or other electronic device that allows a user to access the Metaverse space.

[0660] "Evacuation behavior" refers to the evacuation actions that users take in a virtual space when a disaster occurs.

[0661] "Real-time" refers to the immediate reflection of generated disaster scenarios and user evacuation actions.

[0662] This invention is a system that uses generative AI to recreate realistic disaster scenarios in a metaverse space, allowing users to conduct evacuation drills using VR devices, etc.

[0663] First, the server collects various parameters of the specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.). This data is input into the generation AI, which uses this data to generate disaster scenarios that include earthquakes, fires, liquefaction, and other phenomena. An example of a specific prompt for scenario generation is, "Please simulate the impact of a magnitude 6 earthquake on major infrastructure in an area with a population density of 1,000 people per square kilometer."

[0664] The generated disaster scenario is then sent from the server to the user's device. The user puts on a VR headset or smart device and accesses the metaverse space. Here, the user experiences a virtually recreated disaster situation and performs evacuation actions. During this process, the user's movements and choices are all recorded in real time.

[0665] The device sends the user's evacuation behavior data to a server, which analyzes the data. Based on the analysis results, the server provides the user with feedback on the appropriateness of their evacuation behavior and areas for improvement. Specifically, the feedback could be something like, "When an earthquake occurs, your first response should have been to hide in a safe place indoors."

[0666] The system aims to not only raise users' disaster prevention awareness by allowing them to experience realistic disaster scenarios, but also to enable them to respond quickly and appropriately in the event of a disaster by practicing actual evacuation procedures. Use of this system will improve disaster prevention capabilities throughout the region and promote the creation of safe communities.

[0667] The specific hardware and software used are as follows. Hardware includes servers, VR headsets, smartphones, and other smart devices. Software includes generative AI models and data analysis tools. An example prompt is, "Simulate the impact of a magnitude 6 earthquake on key infrastructure in an area with a population density of 1,000 people per square kilometer."

[0668] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0669] Step 1:

[0670] The server collects parameters such as geographical information, population density, infrastructure status, and past disaster data for the specified area. Based on this data, the risk of disaster occurrence is predicted. As a specific example, the probability of an earthquake with a seismic intensity of 6 occurring and its impact area are analyzed. The input data are parameters related to the characteristics of the area, and the output data is the analyzed risk information.

[0671] Step 2:

[0672] The server inputs the collected parameters into the generative AI model, which then uses this data to generate realistic disaster scenarios. An example prompt sentence used here is, "Please simulate the impact on key infrastructure in an area with a population density of 1,000 people per square kilometer in the event of a magnitude 6 earthquake." The input data are the prompt sentence and regional parameters, and the output data is the disaster scenario.

[0673] Step 3:

[0674] The server sends the generated disaster scenario to the user's device. The device receives this scenario data and recreates the disaster scenario in the metaverse space. Specifically, it visualizes earthquake tremors, fire outbreaks, and other events in the virtual space. The input data is the disaster scenario, and the output data is the disaster simulation displayed in the metaverse space.

[0675] Step 4:

[0676] Users wear a VR headset or smart device and access the Metaverse space. They experience a virtually recreated disaster situation and take evacuation action. During this process, the user's movements and choices are recorded in real time by the device. The input data is the user's operations and behavior data, and the output data is the recorded behavior history.

[0677] Step 5:

[0678] The device sends the user's evacuation behavior data to the server. The server analyzes this data and evaluates the appropriateness of the user's behavior. Specifically, it performs an analysis such as "Was the initial response of evacuating to higher ground appropriate?" The input data is the user's behavior data, and the output data is an evaluation of the behavior and suggestions for improvement.

[0679] Step 6:

[0680] The server provides feedback to the user based on the analysis results. For example, it might say, "The initial response at the time of the earthquake was quick and appropriate, but there is room for improvement in the selection of evacuation routes." The input data is the behavioral analysis results, and the output data is feedback information.

[0681] Step 7:

[0682] Users can refer to the feedback they receive and use it in their next evacuation drill. This repetition improves their practical skills, enabling them to respond appropriately when a disaster occurs. The input data is the provided feedback, and the output data is the user's improved evacuation behavior.

[0683] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0684] This invention is a system that utilizes generative AI to provide realistic disaster scenarios, allowing users to conduct evacuation drills in the metaverse space, and also combines it with an emotion engine that recognizes users' emotions. This system enables local governments, companies, schools, and the general public to conduct effective disaster prevention drills.

[0685] First, the server serves as the platform for generating disaster scenarios. The server collects various parameters for a specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.) and inputs them into the generation AI. The generation AI uses this data to generate realistic disaster scenarios. The scenarios include the intensity of earthquake shaking, the occurrence of liquefaction, and the spread of fires.

[0686] The generated disaster scenario is sent from the server to the device. The device receives this scenario data and displays it in real time within the Metaverse space. Users can access this Metaverse space using a VR headset or other device, allowing them to virtually experience a real-life disaster situation.

[0687] Additionally, the device is equipped with an emotion engine. When the user begins evacuation, the emotion engine monitors the user's facial expressions, tone of voice, heart rate, and other factors in real time to analyze the user's emotional state. The results of this analysis are sent to the server.

[0688] The user initiates evacuation actions, such as evacuating to higher ground in the event of an earthquake, fleeing a fire, or moving to a designated evacuation site. The device transmits the user's behavioral and emotional data to the server in real time. This data is later analyzed and provided to the user as appropriate feedback.

[0689] As a concrete example, let's consider the case where a user participates in an earthquake scenario. First, the server collects earthquake risk data for a specified area and uses a generation AI to generate a magnitude 6 earthquake scenario. This scenario includes the risk of building collapse, evacuation route settings, and the possibility of nearby fires. Next, this scenario data is sent to the device, and the user puts on a VR headset to experience a virtual earthquake. As the user evacuates, their behavior and emotional data are recorded by the device and sent to the server. The server analyzes this data and provides feedback on whether the evacuation behavior was appropriate, whether the user is feeling excessive stress, and how they can improve.

[0690] This system allows users to conduct realistic evacuation drills and gain practical experience to take appropriate action in the event of a disaster. Furthermore, the introduction of an emotion engine makes it possible to incorporate the user's psychological state into the training, resulting in more effective disaster prevention drills. As a result, disaster prevention capabilities across the entire region are improved, and the creation of safer communities is promoted.

[0691] The processing flow will be explained below.

[0692] Step 1:

[0693] The server collects parameters related to the specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.) from a database.

[0694] Step 2:

[0695] The server then activates the AI ​​generator based on the collected parameters to generate realistic disaster scenarios, adding detailed scenario elements such as earthquake occurrence, risk of liquefaction, and the spread of fire.

[0696] Step 3:

[0697] The generated disaster scenarios are stored on the server, and scenarios are managed for each specified user.

[0698] Step 4:

[0699] Users can send a request to access the metaverse space to the server via their terminal, and can select the disaster scenario they want to use.

[0700] Step 5:

[0701] The server receives the user's request and sends the appropriate disaster scenario to the terminal, delivering the scenario data in real time.

[0702] Step 6:

[0703] The device analyzes disaster scenario data received from the server and displays it in the Metaverse space, while setting up a VR environment so that users can access the virtual space.

[0704] Step 7:

[0705] Users can access the metaverse using VR headsets or other devices to experience realistic disaster scenarios, such as searching for evacuation routes and evacuating to a safe location after an earthquake.

[0706] Step 8:

[0707] The device is equipped with an emotion engine that monitors the user's facial expressions, tone of voice, heart rate, etc. in real time to analyze their emotional state.

[0708] Step 9:

[0709] The emotion engine provides the analyzed emotion data to the terminal, which then transmits the data to the server.

[0710] Step 10:

[0711] The device transmits user behavioral and emotional data to the server in real time, including the user's travel route, evacuation speed, emotional state, selected evacuation location, etc.

[0712] Step 11:

[0713] The server analyzes the received user behavioral and emotional data and evaluates the evacuation behavior and emotional state, determining whether the evacuation behavior was appropriate and what improvements are needed.

[0714] Step 12:

[0715] The server generates feedback based on the analysis results and sends it to the user, including successes and areas for improvement, as well as advice on managing emotional states, which can be applied to the next training session.

[0716] Step 13:

[0717] The user receives feedback from the server and reviews their evacuation behavior, which is expected to lead to more appropriate behavior in the next simulation.

[0718] Example 2

[0719] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0720] In conventional evacuation drill systems, users have limited opportunities to experience realistic disaster situations, making it difficult for them to take appropriate action in the event of a real disaster. In addition, training does not take into account the user's emotional state, resulting in insufficient stress management and making it difficult to implement effective disaster prevention drills.

[0721] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting data on disaster risks, means for generating a disaster scenario based on the collected data using a generation AI, means for displaying the generated disaster scenario in the metaverse space, means for a user to access the metaverse space using a VR headset, means for recording the user's evacuation behavior, means for monitoring the user's emotional data, means for transmitting the user's behavioral data and emotional data to the server, and means for the server to analyze the transmitted data and provide appropriate feedback. This allows the user to virtually experience a realistic disaster situation, thereby gaining practical experience for taking appropriate action in the event of an actual disaster, and realizing training that takes emotional states into consideration.

[0722] "Disaster risk data" refers to information such as earthquake intensity, topographical information, population density, and infrastructure status that is collected to assess the likelihood and impact of disasters.

[0723] "Generative AI" is a system that uses artificial intelligence technology to automatically generate realistic disaster scenarios based on input data.

[0724] A "disaster scenario" is a simulation of a hypothetical disaster situation generated based on constructed data, and includes specific earthquake shaking, building collapse, fire spread, etc.

[0725] A "metaverse space" is a three-dimensional virtual environment constructed using virtual reality technology, in which users can interact with each other within the virtual space.

[0726] A "VR headset" is a device worn by users to immerse themselves in a virtual reality space and specifically stimulate their visual and auditory senses.

[0727] "Emotional data" refers to information that indicates the user's psychological state, specifically facial expressions, tone of voice, heart rate, etc.

[0728] "Feedback" refers to specific advice and suggestions for improvement provided to users based on the results of the server's analysis of the user's evacuation behavior and emotional data.

[0729] This invention is a system that uses generative AI to create realistic disaster scenarios, allowing users to conduct evacuation drills in the metaverse space, and combines it with an emotion engine that recognizes users' emotions. This system enables local governments, companies, schools, and the general public to conduct effective disaster prevention drills.

[0730] 1. Collecting data on disaster risk

[0731] The server collects data on disaster risk in a designated area. A cloud server is a suitable hardware option. Specific software used includes the OpenStreetMap API to obtain map information and government earthquake information APIs (such as the USGS Earthquake API) to obtain earthquake information. Collected data includes earthquake intensity, topographical information, population density, and infrastructure status.

[0732] 2. Disaster scenario generation

[0733] The server inputs the collected data into a generative AI model to generate realistic disaster scenarios. The generative AI model used is, for example, GPT-4. An example of a prompt is as follows:

[0734] Designated area: Tokyo

[0735] Parameters:

[0736] Earthquake magnitude: 6

[0737] Terrain data: [latitude, longitude, elevation]

[0738] Population density: high

[0739] Infrastructure situation: traffic congestion, earthquake resistance of buildings

[0740] Generative AI: GPT-4 model

[0741] ==========

[0742] Generate disaster scenarios:

[0743] An earthquake of magnitude 6 occurs

[0744] Risk of building collapse (location: Chuo Ward, Shibuya Ward)

[0745] Setting up evacuation routes (nearest evacuation site: Shinjuku Central Park)

[0746] Possibility of fire outbreak in neighboring areas (location: Minato Ward, Chiyoda Ward)

[0747] 3. Scenario display in the metaverse space

[0748] The device receives disaster scenario data sent from the server and displays it in the Metaverse space. Specifically, a 3D virtual environment is created using Unity or Unreal Engine, and disaster scenarios are reproduced in real time. Users wear a VR headset (e.g., Oculus Rift, HTC Vive) to access this virtual space and virtually experience real-life disaster situations.

[0749] 4. Monitoring evacuation behavior and emotion data

[0750] The device is equipped with an emotion engine that monitors the user's behavior and emotions in real time when they initiate evacuation actions. Specifically, it uses a facial recognition camera, microphone, and biosensor to collect information such as the user's facial expressions, tone of voice, and heart rate.

[0751] 5. Data Collection and Analysis

[0752] The device sends the collected behavioral and emotional data to a server, which analyzes the data and provides appropriate feedback. Machine learning algorithms are effective for this analysis. For example, the server can determine whether the user's evacuation route was optimal or their stress level.

[0753] 6. Providing Feedback

[0754] Based on the analysis results, the server provides feedback to the user, including advice on the appropriateness of evacuation behavior and stress management. For example, specific advice such as "The evacuation route was appropriate" or "Next time, please act calmly" is provided.

[0755] Specific examples

[0756] For example, if a user participates in an earthquake scenario, the server first collects earthquake risk data for Tokyo and uses generation AI to generate a magnitude 6 earthquake scenario. The generated scenario includes the risk of building collapse, evacuation routes, and the possibility of nearby fires. The server then sends this scenario data to the device, and the user puts on a VR headset to experience a virtual earthquake. The user's evacuation behavior and emotional data are collected by the device, and the server provides appropriate feedback after analysis.

[0757] This system allows users to virtually experience realistic disaster situations and practice appropriate actions in the event of a real disaster. Furthermore, it can also take emotional data into account in training, making disaster prevention training more effective.

[0758] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0759] Step 1: Data collection

[0760] The server collects disaster risk data. The input includes information about a specified area, such as seismic intensity data, topographical data, population density, and infrastructure status. Specifically, earthquake data is obtained from government earthquake information APIs (e.g., USGS Earthquake API), topographical data is downloaded from the OpenStreetMap API, and population density and infrastructure status data are collected from publicly available statistical databases. The output is an integrated disaster risk dataset that includes these data.

[0761] Step 2: Disaster scenario generation

[0762] The server inputs the collected dataset into the generative AI model along with a prompt sentence. The generative AI model used is GPT-4. An example of the prompt sentence is as follows:

[0763] Designated area: Tokyo

[0764] Parameters:

[0765] Earthquake magnitude: 6

[0766] Terrain data: [latitude, longitude, elevation]

[0767] Population density: high

[0768] Infrastructure situation: traffic congestion, earthquake resistance of buildings

[0769] Generative AI: GPT-4 model

[0770] ==========

[0771] Generate disaster scenarios:

[0772] An earthquake of magnitude 6 occurs

[0773] Risk of building collapse (location: Chuo Ward, Shibuya Ward)

[0774] Setting up evacuation routes (nearest evacuation site: Shinjuku Central Park)

[0775] Possibility of fire outbreak in neighboring areas (location: Minato Ward, Chiyoda Ward)

[0776] The output is a disaster scenario created by the generative AI model.

[0777] Step 3: Sending scenario data

[0778] The server sends the generated disaster scenario data to the terminal. The input is the disaster scenario data obtained from the generation AI, and the output is the transfer of the scenario data to the terminal. Specifically, the data is transferred securely using the HTTP protocol.

[0779] Step 4: Scenario display and user access to virtual space

[0780] The device displays the received scenario data in the Metaverse space. Specifically, it uses Unity or Unreal Engine to build a virtual space and recreate a disaster scenario in real time. The input is the received disaster scenario data, and the output is a 3D virtual environment generated based on that data. The user wears a VR headset and accesses this virtual space to experience the disaster.

[0781] Step 5: Implementing and monitoring evacuation actions

[0782] The user takes evacuation actions within the virtual space, such as evacuating to higher ground, evacuating from a fire, or moving to a designated evacuation site. The device collects the user's behavioral and emotional data. Specific actions include analyzing facial expressions with a facial recognition camera, collecting voice tone with a microphone, and measuring heart rate with a biosensor. The input is the user's behavior and biometric data, and the output is behavioral and emotional data monitored in real time.

[0783] Step 6: Analyze data and provide feedback

[0784] The device sends the collected behavioral and emotional data to a server. The input is the user's behavioral and emotional data, and the output is the data sent to the server. The server analyzes the received data and provides appropriate feedback. A machine learning algorithm is used for the analysis to evaluate the appropriateness of the user's evacuation behavior and stress level. Feedback is provided with advice on how to improve evacuation behavior and stress management. Specifically, the system generates text messages and voice guidance based on the analysis results and sends them to the user.

[0785] (Application example 2)

[0786] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0787] When a disaster occurs, it is important to take appropriate evacuation actions quickly, but conventional evacuation drill systems have difficulty realistically recreating the situation and psychological state of users when an actual disaster occurs. Furthermore, evacuation support systems using autonomous vehicles are not yet fully established, so there is a lack of real-time evacuation route presentations and psychological support for users in emergencies. This can sometimes prevent users from taking appropriate evacuation actions.

[0788] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating a disaster scenario using a generation AI, means for displaying the generated disaster scenario in a metaverse space, means for recording the user's evacuation behavior and providing appropriate feedback, means for having an emotion engine for monitoring the user's emotional state, and means for providing the disaster scenario to an autonomous vehicle and suggesting an evacuation route. This allows the user to conduct evacuation drills in a realistic environment, while at the same time providing a safe evacuation route in real time using the autonomous vehicle, enabling quick and appropriate evacuation. In addition, the emotion engine can grasp the user's psychological state and provide appropriate support, making evacuation behavior more effective.

[0789] "Generative AI" is an artificial intelligence technology that generates realistic disaster scenarios using multiple data parameters as input.

[0790] A "disaster scenario" is a model that virtually represents the situation when a disaster such as an earthquake or fire occurs, generated based on the characteristics of a specified area.

[0791] The "metaverse space" is a digital virtual space constructed using virtual reality technology, where users can conduct evacuation drills and simulations through digital avatars.

[0792] The "emotion engine" is a technology that analyzes data such as a user's facial expressions, tone of voice, and heart rate to grasp the user's emotional state in real time.

[0793] An "autonomous vehicle" is a vehicle that uses artificial intelligence technology to drive autonomously and is equipped with a system that displays safe evacuation routes in the event of a disaster and controls autonomous driving.

[0794] An "evacuation route" is a route set up to allow users to safely travel to an evacuation site in the event of a disaster.

[0795] "Evacuation behavior" refers to a series of actions or behaviors that a user takes to evacuate to a safe place when a disaster occurs.

[0796] "Feedback" is information including suggestions for improvement and advice provided based on the user's evacuation behavior and psychological state.

[0797] This invention is a system that utilizes generative AI to provide realistic disaster scenarios and allows users to conduct evacuation drills in the metaverse space. Furthermore, by combining it with an emotion engine, it grasps the user's psychological state and provides appropriate feedback. It also has the function of providing disaster scenarios to autonomous vehicles and suggesting evacuation routes.

[0798] First, the server serves as the platform for generating disaster scenarios. The server collects various parameters for a specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.) and inputs them into a generative AI model. The generative AI model uses this data to generate realistic disaster scenarios. These scenarios include the intensity of earthquake shaking, the occurrence of liquefaction, and the spread of fires.

[0799] The generated disaster scenario is sent from the server to the device. The device receives this scenario data and displays it in real time within the metaverse space. Users can access this metaverse space using a VR headset or similar device to virtually experience a real-life disaster situation.

[0800] Additionally, the device is equipped with an emotion engine. When the user begins evacuation, the emotion engine monitors the user's facial expressions, tone of voice, heart rate, and other factors in real time to analyze the user's emotional state. The results of this analysis are sent to the server.

[0801] The user initiates evacuation actions. For example, assuming an earthquake has occurred, the user may evacuate to higher ground, flee from a fire, or move to a designated evacuation site. The device transmits the user's behavioral and emotional data to the server in real time. This data is later analyzed and provided to the user as appropriate feedback.

[0802] The present invention can also be applied to autonomous vehicles. The generated disaster scenarios can be provided to autonomous vehicles, and evacuation routes can be displayed in real time. The emotion engine monitors the user's psychological state and provides support such as relaxation techniques as needed.

[0803] As a concrete example, let's consider the case where a user participates in an earthquake scenario. First, the server collects earthquake risk data for a specified area and uses a generation AI to generate a magnitude 7 earthquake scenario. This scenario includes the risk of building collapse, evacuation route settings, and the possibility of nearby fires. Next, this scenario data is sent to the device, and the user puts on a VR headset to experience a virtual earthquake. As the user evacuates, their behavior and emotional data are recorded by the device and sent to the server. The server analyzes this data and provides feedback on whether the evacuation behavior was appropriate, whether the user is feeling excessive stress, and how they can improve.

[0804] An example of a prompt sentence might be:

[0805] Prompt statement:

[0806] Based on Tokyo's topography and population data, please create a simulation of real-time traffic congestion information and evacuation routes after a magnitude 7 earthquake occurs. The evacuation routes should also include the congestion status of major roads and the status of evacuation shelters.

[0807] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0808] Step 1:

[0809] The server collects parameters for the specified area (seismic intensity, topography, population density, infrastructure status, etc.). These parameters are obtained as input data and prepared to be passed to the generative AI model. Specifically, the server uses databases and real-time APIs to collect the necessary regional data.

[0810] Step 2:

[0811] The server inputs the collected parameters into a generative AI model, which then uses this data to generate realistic disaster scenarios. Specifically, prompts are used to have the generative AI perform tasks such as, "Based on Tokyo's topography and population data, please create real-time traffic congestion information and evacuation route simulations after a magnitude 7 earthquake occurs. The evacuation route should also include the congestion status of major roads and the status of evacuation shelters."

[0812] Step 3:

[0813] The generated disaster scenario is sent from the server to the terminal. The data is converted into a format suitable for display in the metaverse space and sent to the terminal as scenario data. Specifically, the data is formatted in JSON format or similar so that the terminal can interpret it.

[0814] Step 4:

[0815] The scenario data received by the device is displayed in real time within the Metaverse space. Users put on a VR headset and experience the disaster scenario generated in the virtual space. Specifically, the VR space simulates earthquake shaking, building collapse, the spread of fire, and other events.

[0816] Step 5:

[0817] The user initiates an evacuation action, such as evacuating to higher ground, escaping from a fire, or moving to a designated evacuation site. The device records the user's behavioral data. Specifically, it records the user's route and timestamps of the action.

[0818] Step 6:

[0819] The emotion engine monitors the user's facial expressions, tone of voice, heart rate, etc. in real time to analyze the user's emotional state. The analysis results are sent from the device to a server. Specifically, data is collected using devices such as cameras, microphones, and heart rate sensors, and the emotion engine analyzes it.

[0820] Step 7:

[0821] The device sends the user's behavioral and emotional data to a server. The server receives this data and analyzes the appropriateness of evacuation behavior and the user's psychological state. Specifically, it uses machine learning algorithms to analyze the data and find areas for improvement and advice.

[0822] Step 8:

[0823] The server generates appropriate feedback based on the analysis results and provides it to the user. This feedback includes points to improve in evacuation behavior and psychological support methods. Specifically, specific advice is provided in text and audio format based on the user's stress level and speed of action.

[0824] Step 9:

[0825] The generated disaster scenario is provided to an autonomous vehicle, which then suggests a safe evacuation route. The autonomous vehicle then suggests a safe evacuation route in real time, while providing support according to the user's psychological state. Specifically, the system works in conjunction with the vehicle's navigation system to calculate the optimal route.

[0826] Step 10:

[0827] The emotion engine monitors the user's emotional state even while inside an autonomous vehicle and provides support such as relaxation techniques as needed. Specifically, it collects data using cameras, microphones, and heart rate sensors inside the vehicle and analyzes the user's emotional state in real time.

[0828] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0829] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0830] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0831] [Fourth embodiment]

[0832] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0833] 7, a 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.

[0834] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0835] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0836] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0837] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0838] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0839] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0840] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0841] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0842] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0843] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0844] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0845] This invention is a system that utilizes generative AI to provide realistic disaster prevention scenarios and allows users to conduct evacuation drills in the metaverse space. This system enables local governments, companies, schools, and the general public to conduct effective disaster prevention drills.

[0846] First, the server serves as the platform for generating disaster scenarios. The server collects various parameters for a specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.) and inputs them into the generation AI. The generation AI uses this data to generate realistic disaster scenarios. The scenarios include the intensity of earthquake shaking, the occurrence of liquefaction, and the spread of fires.

[0847] The generated disaster scenario is sent from the server to the device. The device receives this scenario data and displays it in real time within the Metaverse space. Users can access this Metaverse space using a VR headset or other device, allowing them to virtually experience a real-life disaster situation.

[0848] The user initiates evacuation actions, such as evacuating to higher ground in the event of an earthquake, fleeing a fire, or moving to a designated evacuation site. The device transmits the user's behavior data to the server in real time. This data is later analyzed and provided to the user as appropriate feedback.

[0849] As a concrete example, let's consider the case where a user participates in an earthquake scenario. First, the server collects earthquake risk data for a specified area and uses a generation AI to generate a magnitude 6 earthquake scenario. This scenario includes the risk of building collapse, evacuation route settings, and the possibility of nearby fires. Next, this scenario data is sent to the device, and the user puts on a VR headset to experience a virtual earthquake. When the user attempts to evacuate, their actions are recorded by the device and sent to the server. The server analyzes this data and provides feedback to the user on whether their evacuation actions were appropriate and how they can be improved.

[0850] This system allows users to conduct realistic evacuation drills and gain practical experience in taking appropriate action in the event of a disaster, thereby improving the disaster prevention capabilities of the entire region and promoting the creation of safe communities.

[0851] The processing flow will be explained below.

[0852] Step 1:

[0853] The server collects parameters related to the specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.) from a database.

[0854] Step 2:

[0855] The server then activates the AI ​​generator based on the collected parameters to generate realistic disaster scenarios, adding detailed scenario elements such as earthquake occurrence, risk of liquefaction, and the spread of fire.

[0856] Step 3:

[0857] The generated disaster scenarios are stored on the server, and scenarios are managed for each specified user.

[0858] Step 4:

[0859] Users can send a request to access the metaverse space to the server via their terminal, and can select the disaster scenario they want to use.

[0860] Step 5:

[0861] The server receives the user's request and sends the appropriate disaster scenario to the terminal, delivering the scenario data in real time.

[0862] Step 6:

[0863] The device analyzes disaster scenario data received from the server and displays it in the Metaverse space, while setting up a VR environment so that users can access the virtual space.

[0864] Step 7:

[0865] Users can access the metaverse using VR headsets or other devices to experience realistic disaster scenarios, such as searching for evacuation routes and evacuating to a safe location after an earthquake.

[0866] Step 8:

[0867] The device transmits user behavior data to the server in real time, including the user's travel route, evacuation speed, selected evacuation location, etc.

[0868] Step 9:

[0869] The server analyzes the received user behavior data and evaluates the evacuation behavior, determining whether the evacuation behavior was appropriate and what improvements are needed.

[0870] Step 10:

[0871] The server generates feedback based on the analysis results and sends it to the user, including successes and areas for improvement, which can be used for the next training session.

[0872] Step 11:

[0873] The user receives feedback from the server and reviews their evacuation behavior, which is expected to lead to more appropriate behavior in the next simulation.

[0874] Example 1

[0875] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0876] Traditional disaster prevention drills are often conducted at actual sites, which takes time, costs money, and requires a large number of personnel. Furthermore, there are many different scenarios that could occur in the event of a real disaster, making it difficult to cover them all. Furthermore, evaluation and feedback of drill results are often subjective, making it difficult to find effective improvement measures. In response to these issues, there is a growing need for disaster prevention training systems that use digital means.

[0877] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0878] In this invention, the server includes a means for collecting parameters based on the characteristics of a specified area, a means for providing the collected parameters as input data to a generative AI model and generating realistic disaster scenarios using prompt sentences, and a means for converting the generated disaster scenarios into JSON format and transmitting them to a terminal via a secure communication protocol. This allows users to experience realistic and diverse disaster scenarios in the metaverse space and take evacuation actions, enabling practical disaster prevention training. Furthermore, by recording users' evacuation actions and analyzing them using a machine learning algorithm, quantitative and objective feedback is provided, improving disaster prevention capabilities.

[0879] "Designated Area" refers to a particular geographic area that is considered in generating disaster scenarios.

[0880] "Parameters" are numerical values ​​or data sets that represent the characteristics of an area, including seismic intensity, topography, population density, building structure, evacuation routes, and fire risk.

[0881] A "generative AI model" refers to an artificial intelligence algorithm or machine learning model that automatically generates disaster scenarios using specified parameters as input.

[0882] A "prompt" refers to input text that provides clear instructions to a generative AI model.

[0883] A "disaster scenario" is a hypothetical disaster situation model created by a generative AI model, and refers to a detailed simulation of a specific disaster situation such as an earthquake or fire.

[0884] "JSON format" is a data format for structuring disaster scenarios and other data, and is an abbreviation for JavaScript Object Notation.

[0885] A "secure communications protocol" is a communications method that ensures security when sending and receiving data, and uses encryption to maintain the confidentiality and integrity of data.

[0886] A "device" is a digital device operated by a user, including hardware such as a computer, smartphone, or VR headset.

[0887] A "metaverse space" refers to a three-dimensional virtual space where users can have virtual experiences, and is constructed using game engines such as Unity and Unreal Engine.

[0888] "Evacuation behavior" refers to the actions and behaviors of evacuation and response that users perform in a virtual disaster scenario.

[0889] "Behavioral Data" refers to recorded information about a user's evacuation behavior, including details such as the user's travel route, response actions, and use of evacuation equipment.

[0890] A "machine learning algorithm" is an algorithm used to analyze user behavior data, learning patterns and trends from the data and generating behavioral evaluations and feedback.

[0891] "Feedback" refers to information about evaluations and areas for improvement provided to users based on the analysis results.

[0892] This invention is a system that uses generative AI to provide realistic disaster scenarios in the metaverse space, allowing users to conduct evacuation drills. This invention will be explained in detail, dividing it into the server, terminals, and users.

[0893] First, the server collects parameters based on the characteristics of the specified area, including data on earthquake intensity, topography, population density, building structure, evacuation routes, fire risk, etc. The server obtains this data using public databases and geoserver APIs.

[0894] Next, the generative AI model receives these parameters and generates a disaster scenario. Specifically, the server inputs the following prompt sentences to the generative AI:

[0895] "Generate a scenario of a severe earthquake in a specified area (City A). The earthquake has a seismic intensity of 6. Collected data includes topography, population density, building structure, evacuation routes, and fire risk. Based on this data, generate a realistic disaster scenario."

[0896] The generated disaster scenario is converted into JSON format and sent from the server to the terminal via a secure communication protocol (HTTPS).

[0897] The device builds a metaverse space based on the received disaster scenario, using game engines such as Unity and Unreal Engine, and users can experience the disaster scenario in real time using a VR headset or mobile device.

[0898] When a user evacuates in the virtual space, the device records their behavioral data in real time, including the user's route, response actions, and evacuation equipment used. The recorded behavioral data is then sent back to the server, where it is analyzed using machine learning algorithms.

[0899] The server provides feedback to the user based on the analysis results. This feedback informs the user of the appropriateness of the evacuation route and areas for improvement. This allows the user to receive specific advice on how to improve their disaster prevention capabilities.

[0900] Through these steps, the system allows users to experience realistic disaster scenarios and conduct practical disaster prevention drills, thereby improving the disaster prevention capabilities of the entire region and promoting the creation of safe communities.

[0901] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0902] Step 1: Data collection

[0903] The server collects parameters based on the characteristics of the specified area (seismic intensity, topography, population density, building structure, evacuation routes, and fire risk). The input is the ID and geographic information of the specified area. The output is a dataset containing these parameters. Specifically, the server uses public databases and geoserver APIs to extract the required information.

[0904] Step 2: Prompt generation

[0905] The server creates a prompt sentence to be input to the generative AI model based on the collected parameters. The input is the parameters obtained in step 1. The output is a prompt sentence in a format that the generative AI can understand. Specifically, the server generates text containing phrases such as "specified area (City A)."

[0906] Step 3: Disaster scenario generation

[0907] The server inputs the generated prompt sentences into the generative AI model to generate realistic disaster scenarios. The input is the prompt sentence created in step 2. The output is disaster scenario data in text or JSON format. Specifically, the server executes an API request to the generative AI and receives the scenario data.

[0908] Step 4: Sending scenario data

[0909] The server converts the generated disaster scenario into JSON format and sends it to the terminal via a secure communication protocol. The input is the disaster scenario data obtained in step 3. The output is the JSON format data sent to the terminal. Specifically, the server sends the data to the client terminal using HTTPS.

[0910] Step 5: Building the Metaverse

[0911] The device constructs a metaverse space based on the scenario data received from the server. The input is the disaster scenario data in JSON format received in step 4. The output is the disaster scenario reproduced in the metaverse space. Specifically, the device uses Unity or Unreal Engine to construct a virtual space using the received data.

[0912] Step 6: Record your evacuation actions

[0913] When a user evacuates in the metaverse space, the device records the behavioral data in real time. The input is information about the user's movements and actions. The output is the recorded behavioral data. Specifically, the device records the user's movement route and actions in a log in real time.

[0914] Step 7: Sending behavioral data

[0915] The device sends the recorded behavioral data to the server. The input is the behavioral data recorded in step 6. The output is the behavioral data sent to the server. Specifically, the device sends the behavioral data to the server using WebSocket or HTTPS.

[0916] Step 8: Analyze behavioral data

[0917] The server analyzes the received behavioral data and evaluates the appropriateness of the user's evacuation behavior. The input is the behavioral data sent in step 7. The output is evaluation data containing the analysis results. Specifically, the server analyzes the behavioral data using a machine learning algorithm and generates an evaluation report.

[0918] Step 9: Provide feedback

[0919] The server provides feedback to the user based on the analysis results. The input is the evaluation data obtained in step 8. The output is the feedback information provided to the user. Specifically, the server sends the generated evaluation report to the terminal, and the user receives the feedback.

[0920] (Application example 1)

[0921] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0922] Conventional disaster prevention training mainly involves simulations in the real world, making it difficult to recreate realistic situations that can be applied in the event of an actual disaster. In addition, there is a lack of feedback for users to effectively conduct evacuation drills, making it difficult to acquire practical skills.

[0923] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0924] In this invention, the server includes means for generating disaster scenarios using a generation AI, means for displaying the generated disaster scenarios in a metaverse space, means for recording users' evacuation behavior and providing appropriate feedback, and means for users to access the metaverse space using a smart device. This allows users to experience realistic disaster scenarios in a virtual space and conduct practical disaster prevention training while judging the effectiveness of their evacuation behaviors.

[0925] "Generative AI" is an artificial intelligence that generates disaster scenarios based on specified parameters.

[0926] "Disaster scenarios" are simulation data used to recreate hypothetical disaster situations such as earthquakes, fires, and liquefaction.

[0927] A "metaverse space" is a three-dimensional virtual environment constructed using virtual reality technology, and is a space that users can experience virtually.

[0928] "Feedback" is information that is provided to users by analyzing their evacuation behavior data and providing them with information on the effectiveness of the training and areas for improvement.

[0929] A "smart device" is a smartphone, smart glasses, head-mounted display, or other electronic device that allows a user to access the Metaverse space.

[0930] "Evacuation behavior" refers to the evacuation actions that users take in a virtual space when a disaster occurs.

[0931] "Real-time" refers to the immediate reflection of generated disaster scenarios and user evacuation actions.

[0932] This invention is a system that uses generative AI to recreate realistic disaster scenarios in a metaverse space, allowing users to conduct evacuation drills using VR devices, etc.

[0933] First, the server collects various parameters of the specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.). This data is input into the generation AI, which uses this data to generate disaster scenarios that include earthquakes, fires, liquefaction, and other phenomena. An example of a specific prompt for scenario generation is, "Please simulate the impact of a magnitude 6 earthquake on major infrastructure in an area with a population density of 1,000 people per square kilometer."

[0934] The generated disaster scenario is then sent from the server to the user's device. The user puts on a VR headset or smart device and accesses the metaverse space. Here, the user experiences a virtually recreated disaster situation and performs evacuation actions. During this process, the user's movements and choices are all recorded in real time.

[0935] The device sends the user's evacuation behavior data to a server, which analyzes the data. Based on the analysis results, the server provides the user with feedback on the appropriateness of their evacuation behavior and areas for improvement. Specifically, the feedback could be something like, "When an earthquake occurs, your first response should have been to hide in a safe place indoors."

[0936] The system aims to not only raise users' disaster prevention awareness by allowing them to experience realistic disaster scenarios, but also to enable them to respond quickly and appropriately in the event of a disaster by practicing actual evacuation procedures. Use of this system will improve disaster prevention capabilities throughout the region and promote the creation of safe communities.

[0937] The specific hardware and software used are as follows. Hardware includes servers, VR headsets, smartphones, and other smart devices. Software includes generative AI models and data analysis tools. An example prompt is, "Simulate the impact of a magnitude 6 earthquake on key infrastructure in an area with a population density of 1,000 people per square kilometer."

[0938] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0939] Step 1:

[0940] The server collects parameters such as geographical information, population density, infrastructure status, and past disaster data for the specified area. Based on this data, the risk of disaster occurrence is predicted. As a specific example, the probability of an earthquake with a seismic intensity of 6 occurring and its impact area are analyzed. The input data are parameters related to the characteristics of the area, and the output data is the analyzed risk information.

[0941] Step 2:

[0942] The server inputs the collected parameters into the generative AI model, which then uses this data to generate realistic disaster scenarios. An example prompt sentence used here is, "Please simulate the impact on key infrastructure in an area with a population density of 1,000 people per square kilometer in the event of a magnitude 6 earthquake." The input data are the prompt sentence and regional parameters, and the output data is the disaster scenario.

[0943] Step 3:

[0944] The server sends the generated disaster scenario to the user's device. The device receives this scenario data and recreates the disaster scenario in the metaverse space. Specifically, it visualizes earthquake tremors, fire outbreaks, and other events in the virtual space. The input data is the disaster scenario, and the output data is the disaster simulation displayed in the metaverse space.

[0945] Step 4:

[0946] Users wear a VR headset or smart device and access the Metaverse space. They experience a virtually recreated disaster situation and take evacuation action. During this process, the user's movements and choices are recorded in real time by the device. The input data is the user's operations and behavior data, and the output data is the recorded behavior history.

[0947] Step 5:

[0948] The device sends the user's evacuation behavior data to the server. The server analyzes this data and evaluates the appropriateness of the user's behavior. Specifically, it performs an analysis such as "Was the initial response of evacuating to higher ground appropriate?" The input data is the user's behavior data, and the output data is an evaluation of the behavior and suggestions for improvement.

[0949] Step 6:

[0950] The server provides feedback to the user based on the analysis results. For example, it might say, "The initial response at the time of the earthquake was quick and appropriate, but there is room for improvement in the selection of evacuation routes." The input data is the behavioral analysis results, and the output data is feedback information.

[0951] Step 7:

[0952] Users can refer to the feedback they receive and use it in their next evacuation drill. This repetition improves their practical skills, enabling them to respond appropriately when a disaster occurs. The input data is the provided feedback, and the output data is the user's improved evacuation behavior.

[0953] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0954] This invention is a system that utilizes generative AI to provide realistic disaster scenarios, allowing users to conduct evacuation drills in the metaverse space, and also combines it with an emotion engine that recognizes users' emotions. This system enables local governments, companies, schools, and the general public to conduct effective disaster prevention drills.

[0955] First, the server serves as the platform for generating disaster scenarios. The server collects various parameters for a specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.) and inputs them into the generation AI. The generation AI uses this data to generate realistic disaster scenarios. The scenarios include the intensity of earthquake shaking, the occurrence of liquefaction, and the spread of fires.

[0956] The generated disaster scenario is sent from the server to the device. The device receives this scenario data and displays it in real time within the Metaverse space. Users can access this Metaverse space using a VR headset or other device, allowing them to virtually experience a real-life disaster situation.

[0957] Additionally, the device is equipped with an emotion engine. When the user begins evacuation, the emotion engine monitors the user's facial expressions, tone of voice, heart rate, and other factors in real time to analyze the user's emotional state. The results of this analysis are sent to the server.

[0958] The user initiates evacuation actions, such as evacuating to higher ground in the event of an earthquake, fleeing a fire, or moving to a designated evacuation site. The device transmits the user's behavioral and emotional data to the server in real time. This data is later analyzed and provided to the user as appropriate feedback.

[0959] As a concrete example, let's consider the case where a user participates in an earthquake scenario. First, the server collects earthquake risk data for a specified area and uses a generation AI to generate a magnitude 6 earthquake scenario. This scenario includes the risk of building collapse, evacuation route settings, and the possibility of nearby fires. Next, this scenario data is sent to the device, and the user puts on a VR headset to experience a virtual earthquake. As the user evacuates, their behavior and emotional data are recorded by the device and sent to the server. The server analyzes this data and provides feedback on whether the evacuation behavior was appropriate, whether the user is feeling excessive stress, and how they can improve.

[0960] This system allows users to conduct realistic evacuation drills and gain practical experience to take appropriate action in the event of a disaster. Furthermore, the introduction of an emotion engine makes it possible to incorporate the user's psychological state into the training, resulting in more effective disaster prevention drills. As a result, disaster prevention capabilities across the entire region are improved, and the creation of safer communities is promoted.

[0961] The processing flow will be explained below.

[0962] Step 1:

[0963] The server collects parameters related to the specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.) from a database.

[0964] Step 2:

[0965] The server then activates the AI ​​generator based on the collected parameters to generate realistic disaster scenarios, adding detailed scenario elements such as earthquake occurrence, risk of liquefaction, and the spread of fire.

[0966] Step 3:

[0967] The generated disaster scenarios are stored on the server, and scenarios are managed for each specified user.

[0968] Step 4:

[0969] Users can send a request to access the metaverse space to the server via their terminal, and can select the disaster scenario they want to use.

[0970] Step 5:

[0971] The server receives the user's request and sends the appropriate disaster scenario to the terminal, delivering the scenario data in real time.

[0972] Step 6:

[0973] The device analyzes disaster scenario data received from the server and displays it in the Metaverse space, while setting up a VR environment so that users can access the virtual space.

[0974] Step 7:

[0975] Users can access the metaverse using VR headsets or other devices to experience realistic disaster scenarios, such as searching for evacuation routes and evacuating to a safe location after an earthquake.

[0976] Step 8:

[0977] The device is equipped with an emotion engine that monitors the user's facial expressions, tone of voice, heart rate, etc. in real time to analyze their emotional state.

[0978] Step 9:

[0979] The emotion engine provides the analyzed emotion data to the terminal, which then transmits the data to the server.

[0980] Step 10:

[0981] The device transmits user behavioral and emotional data to the server in real time, including the user's travel route, evacuation speed, emotional state, selected evacuation location, etc.

[0982] Step 11:

[0983] The server analyzes the received user behavioral and emotional data and evaluates the evacuation behavior and emotional state, determining whether the evacuation behavior was appropriate and what improvements are needed.

[0984] Step 12:

[0985] The server generates feedback based on the analysis results and sends it to the user, including successes and areas for improvement, as well as advice on managing emotional states, which can be applied to the next training session.

[0986] Step 13:

[0987] The user receives feedback from the server and reviews their evacuation behavior, which is expected to lead to more appropriate behavior in the next simulation.

[0988] Example 2

[0989] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0990] In conventional evacuation drill systems, users have limited opportunities to experience realistic disaster situations, making it difficult for them to take appropriate action in the event of a real disaster. In addition, training does not take into account the user's emotional state, resulting in insufficient stress management and making it difficult to implement effective disaster prevention drills.

[0991] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting data on disaster risks, means for generating a disaster scenario based on the collected data using a generation AI, means for displaying the generated disaster scenario in the metaverse space, means for a user to access the metaverse space using a VR headset, means for recording the user's evacuation behavior, means for monitoring the user's emotional data, means for transmitting the user's behavioral data and emotional data to the server, and means for the server to analyze the transmitted data and provide appropriate feedback. This allows the user to virtually experience a realistic disaster situation, thereby gaining practical experience for taking appropriate action in the event of an actual disaster, and realizing training that takes emotional states into consideration.

[0992] "Disaster risk data" refers to information such as earthquake intensity, topographical information, population density, and infrastructure status that is collected to assess the likelihood and impact of disasters.

[0993] "Generative AI" is a system that uses artificial intelligence technology to automatically generate realistic disaster scenarios based on input data.

[0994] A "disaster scenario" is a simulation of a hypothetical disaster situation generated based on constructed data, and includes specific earthquake shaking, building collapse, fire spread, etc.

[0995] A "metaverse space" is a three-dimensional virtual environment constructed using virtual reality technology, in which users can interact with each other within the virtual space.

[0996] A "VR headset" is a device worn by users to immerse themselves in a virtual reality space and specifically stimulate their visual and auditory senses.

[0997] "Emotional data" refers to information that indicates the user's psychological state, specifically facial expressions, tone of voice, heart rate, etc.

[0998] "Feedback" refers to specific advice and suggestions for improvement provided to users based on the results of the server's analysis of the user's evacuation behavior and emotional data.

[0999] This invention is a system that uses generative AI to create realistic disaster scenarios, allowing users to conduct evacuation drills in the metaverse space, and combines it with an emotion engine that recognizes users' emotions. This system enables local governments, companies, schools, and the general public to conduct effective disaster prevention drills.

[1000] 1. Collecting data on disaster risk

[1001] The server collects data on disaster risk in a designated area. A cloud server is a suitable hardware option. Specific software used includes the OpenStreetMap API to obtain map information and government earthquake information APIs (such as the USGS Earthquake API) to obtain earthquake information. Collected data includes earthquake intensity, topographical information, population density, and infrastructure status.

[1002] 2. Disaster scenario generation

[1003] The server inputs the collected data into a generative AI model to generate realistic disaster scenarios. The generative AI model used is, for example, GPT-4. An example of a prompt is as follows:

[1004] Designated area: Tokyo

[1005] Parameters:

[1006] Earthquake magnitude: 6

[1007] Terrain data: [latitude, longitude, elevation]

[1008] Population density: high

[1009] Infrastructure situation: traffic congestion, earthquake resistance of buildings

[1010] Generative AI: GPT-4 model

[1011] ==========

[1012] Generate disaster scenarios:

[1013] An earthquake of magnitude 6 occurs

[1014] Risk of building collapse (location: Chuo Ward, Shibuya Ward)

[1015] Setting up evacuation routes (nearest evacuation site: Shinjuku Central Park)

[1016] Possibility of fire outbreak in neighboring areas (location: Minato Ward, Chiyoda Ward)

[1017] 3. Scenario display in the metaverse space

[1018] The device receives disaster scenario data sent from the server and displays it in the Metaverse space. Specifically, a 3D virtual environment is created using Unity or Unreal Engine, and disaster scenarios are reproduced in real time. Users wear a VR headset (e.g., Oculus Rift, HTC Vive) to access this virtual space and virtually experience real-life disaster situations.

[1019] 4. Monitoring evacuation behavior and emotion data

[1020] The device is equipped with an emotion engine that monitors the user's behavior and emotions in real time when they initiate evacuation actions. Specifically, it uses a facial recognition camera, microphone, and biosensor to collect information such as the user's facial expressions, tone of voice, and heart rate.

[1021] 5. Data Collection and Analysis

[1022] The device sends the collected behavioral and emotional data to a server, which analyzes the data and provides appropriate feedback. Machine learning algorithms are effective for this analysis. For example, the server can determine whether the user's evacuation route was optimal or their stress level.

[1023] 6. Providing Feedback

[1024] Based on the analysis results, the server provides feedback to the user, including advice on the appropriateness of evacuation behavior and stress management. For example, specific advice such as "The evacuation route was appropriate" or "Next time, please act calmly" is provided.

[1025] Specific examples

[1026] For example, if a user participates in an earthquake scenario, the server first collects earthquake risk data for Tokyo and uses generation AI to generate a magnitude 6 earthquake scenario. The generated scenario includes the risk of building collapse, evacuation routes, and the possibility of nearby fires. The server then sends this scenario data to the device, and the user puts on a VR headset to experience a virtual earthquake. The user's evacuation behavior and emotional data are collected by the device, and the server provides appropriate feedback after analysis.

[1027] This system allows users to virtually experience realistic disaster situations and practice appropriate actions in the event of a real disaster. Furthermore, it can also take emotional data into account in training, making disaster prevention training more effective.

[1028] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1029] Step 1: Data collection

[1030] The server collects disaster risk data. The input includes information about a specified area, such as seismic intensity data, topographical data, population density, and infrastructure status. Specifically, earthquake data is obtained from government earthquake information APIs (e.g., USGS Earthquake API), topographical data is downloaded from the OpenStreetMap API, and population density and infrastructure status data are collected from publicly available statistical databases. The output is an integrated disaster risk dataset that includes these data.

[1031] Step 2: Disaster scenario generation

[1032] The server inputs the collected dataset into the generative AI model along with a prompt sentence. The generative AI model used is GPT-4. An example of the prompt sentence is as follows:

[1033] Designated area: Tokyo

[1034] Parameters:

[1035] Earthquake magnitude: 6

[1036] Terrain data: [latitude, longitude, elevation]

[1037] Population density: high

[1038] Infrastructure situation: traffic congestion, earthquake resistance of buildings

[1039] Generative AI: GPT-4 model

[1040] ==========

[1041] Generate disaster scenarios:

[1042] An earthquake of magnitude 6 occurs

[1043] Risk of building collapse (location: Chuo Ward, Shibuya Ward)

[1044] Setting up evacuation routes (nearest evacuation site: Shinjuku Central Park)

[1045] Possibility of fire outbreak in neighboring areas (location: Minato Ward, Chiyoda Ward)

[1046] The output is a disaster scenario created by the generative AI model.

[1047] Step 3: Sending scenario data

[1048] The server sends the generated disaster scenario data to the terminal. The input is the disaster scenario data obtained from the generation AI, and the output is the transfer of the scenario data to the terminal. Specifically, the data is transferred securely using the HTTP protocol.

[1049] Step 4: Scenario display and user access to virtual space

[1050] The device displays the received scenario data in the Metaverse space. Specifically, it uses Unity or Unreal Engine to build a virtual space and recreate a disaster scenario in real time. The input is the received disaster scenario data, and the output is a 3D virtual environment generated based on that data. The user wears a VR headset and accesses this virtual space to experience the disaster.

[1051] Step 5: Implementing and monitoring evacuation actions

[1052] The user takes evacuation actions within the virtual space, such as evacuating to higher ground, evacuating from a fire, or moving to a designated evacuation site. The device collects the user's behavioral and emotional data. Specific actions include analyzing facial expressions with a facial recognition camera, collecting voice tone with a microphone, and measuring heart rate with a biosensor. The input is the user's behavior and biometric data, and the output is behavioral and emotional data monitored in real time.

[1053] Step 6: Analyze data and provide feedback

[1054] The device sends the collected behavioral and emotional data to a server. The input is the user's behavioral and emotional data, and the output is the data sent to the server. The server analyzes the received data and provides appropriate feedback. A machine learning algorithm is used for the analysis to evaluate the appropriateness of the user's evacuation behavior and stress level. Feedback is provided with advice on how to improve evacuation behavior and stress management. Specifically, the system generates text messages and voice guidance based on the analysis results and sends them to the user.

[1055] (Application example 2)

[1056] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1057] When a disaster occurs, it is important to take appropriate evacuation actions quickly, but conventional evacuation drill systems have difficulty realistically recreating the situation and psychological state of users when an actual disaster occurs. Furthermore, evacuation support systems using autonomous vehicles are not yet fully established, so there is a lack of real-time evacuation route presentations and psychological support for users in emergencies. This can sometimes prevent users from taking appropriate evacuation actions.

[1058] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating a disaster scenario using a generation AI, means for displaying the generated disaster scenario in a metaverse space, means for recording the user's evacuation behavior and providing appropriate feedback, means for having an emotion engine for monitoring the user's emotional state, and means for providing the disaster scenario to an autonomous vehicle and suggesting an evacuation route. This allows the user to conduct evacuation drills in a realistic environment, while at the same time providing a safe evacuation route in real time using the autonomous vehicle, enabling quick and appropriate evacuation. In addition, the emotion engine can grasp the user's psychological state and provide appropriate support, making evacuation behavior more effective.

[1059] "Generative AI" is an artificial intelligence technology that generates realistic disaster scenarios using multiple data parameters as input.

[1060] A "disaster scenario" is a model that virtually represents the situation when a disaster such as an earthquake or fire occurs, generated based on the characteristics of a specified area.

[1061] The "metaverse space" is a digital virtual space constructed using virtual reality technology, where users can conduct evacuation drills and simulations through digital avatars.

[1062] The "emotion engine" is a technology that analyzes data such as a user's facial expressions, tone of voice, and heart rate to grasp the user's emotional state in real time.

[1063] An "autonomous vehicle" is a vehicle that uses artificial intelligence technology to drive autonomously and is equipped with a system that displays safe evacuation routes in the event of a disaster and controls autonomous driving.

[1064] An "evacuation route" is a route set up to allow users to safely travel to an evacuation site in the event of a disaster.

[1065] "Evacuation behavior" refers to a series of actions or behaviors that a user takes to evacuate to a safe place when a disaster occurs.

[1066] "Feedback" is information including suggestions for improvement and advice provided based on the user's evacuation behavior and psychological state.

[1067] This invention is a system that utilizes generative AI to provide realistic disaster scenarios and allows users to conduct evacuation drills in the metaverse space. Furthermore, by combining it with an emotion engine, it grasps the user's psychological state and provides appropriate feedback. It also has the function of providing disaster scenarios to autonomous vehicles and suggesting evacuation routes.

[1068] First, the server serves as the platform for generating disaster scenarios. The server collects various parameters for a specified area (e.g., seismic intensity, topography, population density, infrastructure status, etc.) and inputs them into a generative AI model. The generative AI model uses this data to generate realistic disaster scenarios. These scenarios include the intensity of earthquake shaking, the occurrence of liquefaction, and the spread of fires.

[1069] The generated disaster scenario is sent from the server to the device. The device receives this scenario data and displays it in real time within the metaverse space. Users can access this metaverse space using a VR headset or similar device to virtually experience a real-life disaster situation.

[1070] Additionally, the device is equipped with an emotion engine. When the user begins evacuation, the emotion engine monitors the user's facial expressions, tone of voice, heart rate, and other factors in real time to analyze the user's emotional state. The results of this analysis are sent to the server.

[1071] The user initiates evacuation actions. For example, assuming an earthquake has occurred, the user may evacuate to higher ground, flee from a fire, or move to a designated evacuation site. The device transmits the user's behavioral and emotional data to the server in real time. This data is later analyzed and provided to the user as appropriate feedback.

[1072] The present invention can also be applied to autonomous vehicles. The generated disaster scenarios can be provided to autonomous vehicles, and evacuation routes can be displayed in real time. The emotion engine monitors the user's psychological state and provides support such as relaxation techniques as needed.

[1073] As a concrete example, let's consider the case where a user participates in an earthquake scenario. First, the server collects earthquake risk data for a specified area and uses a generation AI to generate a magnitude 7 earthquake scenario. This scenario includes the risk of building collapse, evacuation route settings, and the possibility of nearby fires. Next, this scenario data is sent to the device, and the user puts on a VR headset to experience a virtual earthquake. As the user evacuates, their behavior and emotional data are recorded by the device and sent to the server. The server analyzes this data and provides feedback on whether the evacuation behavior was appropriate, whether the user is feeling excessive stress, and how they can improve.

[1074] An example of a prompt sentence might be:

[1075] Prompt statement:

[1076] Based on Tokyo's topography and population data, please create a simulation of real-time traffic congestion information and evacuation routes after a magnitude 7 earthquake occurs. The evacuation routes should also include the congestion status of major roads and the status of evacuation shelters.

[1077] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1078] Step 1:

[1079] The server collects parameters for the specified area (seismic intensity, topography, population density, infrastructure status, etc.). These parameters are obtained as input data and prepared to be passed to the generative AI model. Specifically, the server uses databases and real-time APIs to collect the necessary regional data.

[1080] Step 2:

[1081] The server inputs the collected parameters into a generative AI model, which then uses this data to generate realistic disaster scenarios. Specifically, prompts are used to have the generative AI perform tasks such as, "Based on Tokyo's topography and population data, please create real-time traffic congestion information and evacuation route simulations after a magnitude 7 earthquake occurs. The evacuation route should also include the congestion status of major roads and the status of evacuation shelters."

[1082] Step 3:

[1083] The generated disaster scenario is sent from the server to the terminal. The data is converted into a format suitable for display in the metaverse space and sent to the terminal as scenario data. Specifically, the data is formatted in JSON format or similar so that the terminal can interpret it.

[1084] Step 4:

[1085] The scenario data received by the device is displayed in real time within the Metaverse space. Users put on a VR headset and experience the disaster scenario generated in the virtual space. Specifically, the VR space simulates earthquake shaking, building collapse, the spread of fire, and other events.

[1086] Step 5:

[1087] The user initiates an evacuation action, such as evacuating to higher ground, escaping from a fire, or moving to a designated evacuation site. The device records the user's behavioral data. Specifically, it records the user's route and timestamps of the action.

[1088] Step 6:

[1089] The emotion engine monitors the user's facial expressions, tone of voice, heart rate, etc. in real time to analyze the user's emotional state. The analysis results are sent from the device to a server. Specifically, data is collected using devices such as cameras, microphones, and heart rate sensors, and the emotion engine analyzes it.

[1090] Step 7:

[1091] The device sends the user's behavioral and emotional data to a server. The server receives this data and analyzes the appropriateness of evacuation behavior and the user's psychological state. Specifically, it uses machine learning algorithms to analyze the data and find areas for improvement and advice.

[1092] Step 8:

[1093] The server generates appropriate feedback based on the analysis results and provides it to the user. This feedback includes points to improve in evacuation behavior and psychological support methods. Specifically, specific advice is provided in text and audio format based on the user's stress level and speed of action.

[1094] Step 9:

[1095] The generated disaster scenario is provided to an autonomous vehicle, which then suggests a safe evacuation route. The autonomous vehicle then suggests a safe evacuation route in real time, while providing support according to the user's psychological state. Specifically, the system works in conjunction with the vehicle's navigation system to calculate the optimal route.

[1096] Step 10:

[1097] The emotion engine monitors the user's emotional state even while inside an autonomous vehicle and provides support such as relaxation techniques as needed. Specifically, it collects data using cameras, microphones, and heart rate sensors inside the vehicle and analyzes the user's emotional state in real time.

[1098] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1099] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1100] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1101] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1102] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1103] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1104] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1105] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1106] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1107] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1108] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1109] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1110] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1111] 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.

[1112] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1113] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1114] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1115] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1116] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1117] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1118] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1119] The following is further disclosed regarding the above embodiment.

[1120] (Claim 1)

[1121] A means for generating disaster scenarios using generative AI;

[1122] a means for displaying the generated disaster scenario in a metaverse space;

[1123] A means of recording the user's evacuation behavior and providing appropriate feedback;

[1124] A system including:

[1125] (Claim 2)

[1126] The system according to claim 1, further comprising a means for generating a disaster scenario using parameters based on the characteristics of a specified area as input.

[1127] (Claim 3)

[1128] The system according to claim 1, further comprising a means for adjusting the metaverse space in real time in accordance with the generated disaster scenario and encouraging users to take evacuation action.

[1129] (Claim 4)

[1130] The system of claim 1, further comprising a means for collecting user operations in real time, analyzing them using a generating AI, and suggesting improvements to the user's evacuation behavior.

[1131] (Claim 5)

[1132] The system according to claim 1, further comprising means for generating the disaster scenario, displaying the metaverse space, and providing feedback, all via a network.

[1133] "Example 1"

[1134] (Claim 1)

[1135] means for collecting parameters based on characteristics of a designated area;

[1136] A means for supplying the collected parameters as input data to a generative AI model and generating a realistic disaster scenario using a prompt sentence;

[1137] means for converting the generated disaster scenario into a JSON format and transmitting the JSON format to a terminal via a secure communication protocol;

[1138] A means for constructing a metaverse space based on the received disaster scenario and displaying it to a user using a VR headset or a mobile device;

[1139] A means for recording data on a user's evacuation behavior in a virtual space;

[1140] a means for transmitting the recorded user behavior data to a server and analyzing the data using a machine learning algorithm;

[1141] a means of providing feedback to the user based on the analysis results;

[1142] A system including:

[1143] (Claim 2)

[1144] The system of claim 1, wherein the generative AI model comprises means for generating disaster scenarios using parameters based on regional characteristics such as earthquake intensity, topography, population density, building structure, evacuation routes, and fire risk.

[1145] (Claim 3)

[1146] The system according to claim 1, further comprising means for adjusting the metaverse space in real time in accordance with the received disaster scenario and encouraging users to take evacuation action.

[1147] "Application Example 1"

[1148] (Claim 1)

[1149] A means for generating disaster scenarios using generative AI;

[1150] a means for displaying the generated disaster scenario in a metaverse space;

[1151] A means of recording the user's evacuation behavior and providing appropriate feedback;

[1152] A means for users to access the metaverse space using smart devices,

[1153] A system including:

[1154] (Claim 2)

[1155] The system according to claim 1, further comprising a means for generating a disaster scenario using parameters based on the characteristics of a specified area as input.

[1156] (Claim 3)

[1157] The system according to claim 1, further comprising a means for adjusting the metaverse space in real time in accordance with the generated disaster scenario and encouraging users to take evacuation action.

[1158] "Example 2: Combining Emotion Engines"

[1159] (Claim 1)

[1160] means of collecting data on disaster risk;

[1161] A means of generating disaster scenarios based on collected data using generative AI;

[1162] a means for displaying the generated disaster scenario in a metaverse space;

[1163] A means for users to access the Metaverse space using a VR headset;

[1164] a means for recording the evacuation behavior of the user;

[1165] a means for monitoring user emotional data;

[1166] means for transmitting user behavioral data and emotion data to a server;

[1167] a means for the server to analyze the transmitted data and provide appropriate feedback;

[1168] A system including:

[1169] (Claim 2)

[1170] The system according to claim 1, further comprising a means for generating a disaster scenario using parameters based on the characteristics of a specified area as input.

[1171] (Claim 3)

[1172] The system according to claim 1, further comprising a means for adjusting the metaverse space in real time in accordance with the generated disaster scenario and encouraging users to take evacuation action.

[1173] "Application example 2 when combining emotion engines"

[1174] (Claim 1)

[1175] A means for generating disaster scenarios using generative AI;

[1176] a means for displaying the generated disaster scenario in a metaverse space;

[1177] A means of recording the user's evacuation behavior and providing appropriate feedback;

[1178] means for providing an emotion engine for monitoring an emotional state of a user;

[1179] A means for providing disaster scenarios to autonomous vehicles and suggesting evacuation routes;

[1180] A system including:

[1181] (Claim 2)

[1182] The system according to claim 1, further comprising a means for generating a disaster scenario using parameters based on the characteristics of a specified area as input.

[1183] (Claim 3)

[1184] The system of claim 1, further comprising means for adjusting the metaverse space in real time in accordance with the generated disaster scenario and promoting evacuation behavior of autonomous vehicles. [Explanation of symbols]

[1185] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for generating disaster scenarios using generative AI; a means for displaying the generated disaster scenario in a metaverse space; A means of recording the user's evacuation behavior and providing appropriate feedback; A system including:

2. The system according to claim 1, further comprising means for the generation AI to generate a disaster scenario using parameters based on the characteristics of the designated area as input.

3. The system according to claim 1 , further comprising means for adjusting the metaverse space in real time in accordance with the generated disaster scenario and encouraging users to take evacuation action.

4. The system of claim 1 further comprises a means for collecting user operations in real time, analyzing them using a generating AI, and suggesting improvements to the user's evacuation behavior.

5. The system according to claim 1 , further comprising means for generating the disaster scenario, displaying the metaverse space, and providing feedback, all via a network.

Images