System

Abstract

A system is provided.SOLUTION: The system includes a data collection means for collecting and learning past earthquake disaster data, a risk analysis means for analyzing a risk in real time based on the learned earthquake disaster data, an evacuation route generation means for generating an evacuation route and an action instruction based on the analysis result, and an instruction transmission means for transmitting the generated evacuation route and action instruction to a user terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In areas where earthquake disasters occur frequently, efficient evacuation instructions and action suggestions are required, but conventional methods have difficulty in fully utilizing past disaster data, making it impossible to suggest specific evacuation actions in real time.In addition, it is difficult to track whether evacuation actions were successful, making it impossible to use the information to improve future evacuation actions. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system including a data collection means for collecting and learning from past earthquake disaster data, a risk analysis means for analyzing risks in real time based on the learned earthquake disaster data, an evacuation route generation means for generating evacuation routes and action instructions based on the analysis results, and an instruction transmission means for transmitting the generated evacuation routes and action instructions to a user terminal. Furthermore, by including a location tracking means for receiving real-time location information from the user terminal and tracking the evacuation situation, and a feedback means for collecting user behavior data and evacuation success rates and using them for subsequent risk analysis and generation of action instructions, the accuracy and efficiency of evacuation behavior can be improved.

[0006] "Earthquake disaster data" refers to data that includes information on the scale, epicenter, damage extent, and related tsunamis and fires of past earthquakes.

[0007] "Data collection means" refers to devices and methods for collecting, organizing, and storing earthquake hazard data.

[0008] "Risk analysis means" refers to devices and methods for analyzing the scope of impact and damage caused by currently occurring earthquakes in real time based on collected earthquake disaster data.

[0009] The "evacuation route generation means" is a device or method for generating an optimal evacuation route and action instructions based on the information analyzed by the risk analysis means.

[0010] The "instruction sending means" refers to a device or method for sending the generated evacuation route and action instructions to the user's terminal.

[0011] A "user terminal" is a device used by a user, and includes mobile terminals such as smartphones and tablets.

[0012] The "location tracking means" is a device or method for receiving real-time location information from a user terminal and tracking the evacuation status of the user.

[0013] "Feedback means" refers to a device or method for collecting user behavior data and evacuation success rates, and using that data to improve the accuracy of risk analysis and behavioral instructions for future events. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] This invention is a disaster prevention system that analyzes risks in the event of an earthquake and proposes evacuation actions, and provides optimal evacuation routes and action instructions in real time based on past earthquake disaster data. This system is composed of three parties: a server, a terminal, and a user, each of which plays a specific role.

[0036] 1. Data collection and learning

[0037] The server first collects data on past earthquake disasters. This data includes information such as epicenters, seismic intensity, damage status, and the impact of tsunamis and fires. This data is then cleansed and formatted for analysis, after which it is trained using machine learning algorithms and deep learning models. This allows the system to identify various risk patterns in the event of an earthquake and build a predictive model.

[0038] 2. Real-time risk prediction

[0039] When a device (such as a smartphone or tablet) detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency, it sends that information to a server. The server then compares the received earthquake information with past data and analyzes the risk in the relevant area. The analysis takes into account factors such as distance from the epicenter, topographical information, and population density.

[0040] 3. Evacuation routes and suggested actions

[0041] Based on the analysis results, the server calculates the optimal evacuation route. This calculation uses current topographical information and traffic conditions (e.g., traffic congestion information, road closure information). The server then generates specific instructions along with the evacuation route. For example, specific instructions such as "head to the nearest high ground" or "evacuate to a specific evacuation shelter" are generated and sent to the device.

[0042] 4. User Behavior and Feedback

[0043] The user carries out the evacuation actions instructed from the device. Once the evacuation is complete, the user presses the "Evacuation Complete" button on the device, which sends the information to the server. The server receives the user's location information and movement trajectory in real time and tracks the evacuation status. The server also collects user behavior data and evacuation success rate, and uses this information as feedback to improve the accuracy of the system in future risk analysis and the generation of behavioral instructions.

[0044] Examples:

[0045] For example, suppose an earthquake occurs in a certain area and is detected by a device. This information is sent to a server, which compares it with past data and analyzes the risk in that area. If the server determines that there is a risk of a tsunami, it calculates an evacuation route and instructs the user to evacuate to higher ground. This instruction is sent to the device, and the user begins evacuating to higher ground. After completing the evacuation, the user presses the "Evacuation Complete" button on the device, and the information is sent to the server. In this way, quick and specific evacuation instructions can be provided.

[0046] This system aims to support quick and specific evacuation actions in the event of an earthquake disaster, thereby minimizing damage.

[0047] The processing flow will be explained below.

[0048] Step 1:

[0049] The server collects data on past earthquake disasters, including epicenters, seismic intensity, damage, and the impact of tsunamis and fires. This data is obtained from government agencies, university research institutes, disaster-related organizations, and other sources.

[0050] Step 2:

[0051] The server cleanses the collected data, removing irrelevant data, processing missing values, standardizing data formats, and otherwise formatting it into a format that is easy to analyze.

[0052] Step 3:

[0053] The server inputs the formatted data into machine learning algorithms and deep learning models to learn risk patterns in the event of an earthquake, thereby building a predictive model.

[0054] Step 4:

[0055] When a device (such as a smartphone or tablet) receives an earthquake warning from an earthquake detection sensor or the Japan Meteorological Agency, it sends the information to a server, including the earthquake's seismic intensity, epicenter, and time of occurrence.

[0056] Step 5:

[0057] The server compares the received earthquake information with past data and performs real-time risk analysis, taking into account factors such as distance from the epicenter, topographical information, and population density.

[0058] Step 6:

[0059] The server calculates the optimal evacuation route based on the analysis results, taking into account current terrain information and traffic conditions (e.g., traffic congestion, road closures).

[0060] Step 7:

[0061] The server generates specific instructions along with evacuation routes, such as "head to the nearest high ground" or "evacuate to a specific shelter."

[0062] Step 8:

[0063] The server then sends the generated evacuation route and action instructions to the terminal, allowing the user to receive specific evacuation instructions.

[0064] Step 9:

[0065] The user follows the instructions displayed on the device and begins the designated evacuation action, using the device's GPS function to check their current location and evacuation destination as they move.

[0066] Step 10:

[0067] The device transmits the user's location information and movement trajectory to the server in real time, allowing the server to track the user's evacuation status.

[0068] Step 11:

[0069] When the user completes evacuation, they press the "Evacuation Complete" button on their device. The evacuation completion information is sent to the server and recorded.

[0070] Step 12:

[0071] The server collects user behavior data and evacuation success rates, and uses feedback to improve the accuracy of risk analysis and behavioral instructions for future events, thereby continuously improving the effectiveness of the system.

[0072] Example 1

[0073] 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."

[0074] Current earthquake disaster prevention systems do not fully utilize past data, resulting in issues with the accuracy of real-time risk predictions and evacuation instructions. They also lack the functionality to track users' location information and evacuation status, making it difficult to support appropriate evacuation behavior. Furthermore, they lack a mechanism for feeding back evacuation behavior data to improve the accuracy of the system.

[0075] 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.

[0076] In this invention, the server includes a data collection means for collecting and learning past earthquake disaster data, a risk analysis means for analyzing risks in real time based on the learned earthquake disaster data, an evacuation route generation means for generating evacuation routes and action instructions based on the analysis results, and an instruction transmission means for transmitting the generated evacuation routes and action instructions to the communication device. This enables real-time risk prediction and provision of specific and optimal evacuation instructions to the user, thereby improving the accuracy and effectiveness of evacuation actions.

[0077] "Data collection means" refers to the function of collecting and learning from past earthquake disaster data.

[0078] "Risk analysis means" refers to the function of analyzing risk in real time based on learned earthquake disaster data.

[0079] "Evacuation route generation means" refers to a function that generates an evacuation route and action instructions based on the analysis results.

[0080] The "instruction sending means" refers to a function that sends the generated evacuation route and action instructions to the communication device.

[0081] "Location tracking means" refers to the function of receiving real-time location signals and tracking evacuation status.

[0082] "Feedback means" refers to the function of collecting behavioral data and evacuation success rates and using them for future risk analysis and generation of behavioral instructions.

[0083] "Server" refers to a central processing unit that manages and operates functions such as data collection, risk analysis, evacuation route generation, instruction transmission, location tracking, and feedback.

[0084] "Communication device" refers to a user terminal that receives evacuation routes and action instructions sent from the server.

[0085] The present invention is a disaster prevention system that performs risk analysis and evacuation instructions using past earthquake disaster data. This system is composed of a server, terminals, and users, each of which plays a specific role.

[0086] Server Roles and Functions

[0087] The server plays a central role in this system and performs the following functions:

[0088] Data collection methods

[0089] The server collects past earthquake disaster data from public databases on the Internet, earthquake research institutes, the Japan Meteorological Agency, etc. This data includes information such as the epicenter, seismic intensity, damage status, and the impact of tsunamis and fires. Specifically, the server automatically collects data using an API and stores it in an internal database.

[0090] Risk Analysis Tools

[0091] The server cleanses the collected earthquake disaster data and formats it into a format suitable for analysis. It removes duplicates, missing values, and inappropriate values ​​to create a dataset. It then uses machine learning algorithms and deep learning models (e.g., TENSORFLOW (registered trademark) and PyTorch) to train this dataset and build a predictive model for real-time risk forecasting in the event of an earthquake.

[0092] Evacuation route generation method

[0093] The server uses a machine learning model to analyze risk in the event of an earthquake and generates optimal evacuation routes based on that risk. It references current topographical information and traffic conditions (e.g., traffic congestion and road closures) using Google® Maps API and OpenStreetMap. Along with the evacuation route, it generates specific instructions, such as "head to the nearest high ground" or "evacuate to a specific evacuation shelter."

[0094] Instruction sending means

[0095] The server sends the generated evacuation route and instructions to the device via push notification or SMS, helping users to quickly begin evacuation actions.

[0096] Location Tracking Methods

[0097] The server tracks the user's evacuation status based on real-time location information received from the device, allowing it to check whether the user is evacuating as instructed and send further instructions if necessary.

[0098] Feedback Methods

[0099] The server collects data on users' evacuation behavior and the success rate of evacuation, and uses this information for future risk analysis and generation of action instructions, thereby enabling the system's accuracy to be continually improved.

[0100] Device roles and functions

[0101] The device (smartphone, tablet, etc.) is responsible for the following functions:

[0102] earthquake sensing

[0103] The device detects earthquakes using its built-in acceleration sensor or receives earthquake warnings from the Japan Meteorological Agency.

[0104] Sending information to the server

[0105] If an earthquake is detected, the device immediately sends that information and its current location to the server.

[0106] Receiving and displaying instructions

[0107] The system receives evacuation routes and instructions sent from the server and displays them to the user. It also notifies the user via push notifications and alarm sounds, encouraging them to take prompt action.

[0108] User Roles and Capabilities

[0109] The user takes evacuation action based on the information provided by the terminal.

[0110] Implementing evacuation actions

[0111] The user follows the evacuation instructions from the device and begins evacuating along the designated evacuation route, for example, heading to the nearest high ground or to a specific evacuation shelter.

[0112] Reporting completion of evacuation

[0113] Once the evacuation is complete, press the "Evacuation Complete" button on the device to send the information to the server.

[0114] Specific examples

[0115] For example, if an earthquake occurs in a certain area, the device will detect the earthquake and send that information along with the user's current location to the server. The server will compare this information with past data and analyze the risk in that area. If the server determines that there is a risk of a tsunami, it will calculate the optimal evacuation route and instruct the user to "evacuate to higher ground." This instruction is sent to the device, and the user begins evacuation accordingly. After completing the evacuation, the user presses the "evacuation complete" button on the device, and the information is sent to the server. This series of steps allows for quick and specific evacuation actions to be taken.

[0116] Prompt Sentence Examples

[0117] The following is an example of a prompt sentence that uses a generative AI model to specifically explain the operation of this system:

[0118] "Please explain how the earthquake disaster prevention system works. The system collects data on past earthquake disasters, performs risk predictions in real time, and provides optimal evacuation routes and action instructions. Please explain each processing step in detail."

[0119] The system aims to support quick and specific evacuation actions in the event of an earthquake disaster, thereby minimizing damage.

[0120] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0121] Step 1: Data collection

[0122] The server collects data on past earthquake disasters from public databases on the Internet, earthquake research institutes, the Japan Meteorological Agency, and other sources. This data includes information such as the epicenter, seismic intensity, damage status, and the impact of tsunamis and fires. The collected data is stored in the server's internal database. Specifically, it is automatically collected using an API and obtains data in JSON format. The input data is raw data on earthquake disasters, and the output data is the raw data file before cleansing.

[0123] Step 2: Data cleansing

[0124] The server cleanses the collected data. Specifically, it removes duplicate data and corrects missing or inappropriate values. For example, data showing a seismic intensity of "upper 6" is converted to the numerical value "6." This process converts the data into a format suitable for analysis. The input data is a raw data file, and the output data is a cleansed dataset.

[0125] Step 3: Training the machine learning model

[0126] The server uses the cleansed data to train machine learning algorithms and deep learning models. Libraries used include TensorFlow and PyTorch. The learning algorithms used are random forests and neural networks for risk prediction. This process builds a predictive model for real-time risk forecasting in the event of an earthquake. The input data is the cleansed dataset, and the output data is the trained predictive model.

[0127] Step 4: Earthquake detection and information transmission

[0128] A device (such as a smartphone or tablet) detects an earthquake using its built-in acceleration sensor or receives an earthquake warning from the Japan Meteorological Agency. When an earthquake is detected, the device sends this detection information along with its current location information to a server. The input data is the earthquake detection data and location information, and the output data is the data sent to the server.

[0129] Step 5: Risk analysis

[0130] The server compares the received earthquake information and location information with past data and analyzes the risk of the relevant area. Specifically, it takes into account factors such as distance from the epicenter, topographical information, and population density. This risk analysis uses a trained predictive model. The input data is earthquake information and location information, and the output data is the risk analysis results.

[0131] Step 6: Evacuation route generation and behavior instructions

[0132] The server generates the optimal evacuation route based on the risk analysis results. This generation uses geographic information services such as Google Maps API and OpenStreetMap. It also generates specific action instructions (e.g., "head to the nearest high ground" or "evacuate to a specific evacuation shelter"). The input data are the risk analysis results and current terrain and traffic information, and the output data are the evacuation route and action instructions.

[0133] Step 7: Sending instructions

[0134] The server sends the generated evacuation route and action instructions to the device. This is done using push notifications or SMS. The input data is the evacuation route and action instructions, and the output data is the data sent to the device.

[0135] Step 8: User evacuation behavior

[0136] The user follows the instructions received from the device and begins evacuation along the specified evacuation route. For example, they may head to the nearest high ground or evacuate to a specific evacuation shelter. The input data are instructions from the device, and the output is the actual evacuation behavior.

[0137] Step 9: Evacuation completion report

[0138] When the user completes evacuation, they press the "Evacuation Complete" button on their device to send evacuation completion information to the server. The input data is the evacuation completion information, and the output data is the data to be sent to the server.

[0139] Step 10: Evacuation status tracking and feedback

[0140] The server tracks the user's evacuation status based on the received evacuation completion information and user location information. It also uses the collected evacuation behavior data and evacuation success rate for future risk analysis and the generation of behavioral instructions. The input data are evacuation behavior data and completion information, and the output data is learning data used as feedback.

[0141] The above is a specific operation of each processing step in the disaster recovery system.

[0142] (Application example 1)

[0143] 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."

[0144] During earthquake disasters, it is important to provide routes and instructions for quick and safe evacuation, but current technology makes it difficult to provide optimal evacuation routes and specific instructions for action in real time according to the individual circumstances of each evacuee.In addition, there is no system in place to efficiently support evacuation using autonomous vehicles, which can result in delays in evacuation.To solve this problem, there is a need for a system that can perform risk analysis in real time during earthquake disasters and provide evacuation routes and instructions for action to autonomous vehicles.

[0145] 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.

[0146] In this invention, the server includes a data collection means for collecting and learning past earthquake disaster data, a risk analysis means for analyzing risks in real time based on the learned earthquake disaster data, an evacuation route generation means for generating evacuation routes and action instructions based on the analysis results, an instruction transmission means for transmitting the generated evacuation routes and action instructions to a user terminal, a vehicle control means for controlling an autonomous vehicle to move along the evacuation route when an earthquake occurs, and an information provision means for providing information to users via an in-vehicle display or audio guidance. This makes it possible to provide optimal evacuation routes and specific action instructions according to the individual circumstances of evacuees in the event of an earthquake disaster, and to support quick and safe evacuation using autonomous vehicles.

[0147] The "data collection means" is a system component that collects past earthquake disaster data and uses it for learning.

[0148] The "risk analysis means" is a system component for analyzing earthquake risk in real time based on collected data.

[0149] The "evacuation route generation means" is a system component that generates an optimal evacuation route and specific action instructions based on the results of risk analysis.

[0150] The "instruction transmitting means" is a system component for transmitting the generated evacuation route and action instructions to the user terminal.

[0151] The "vehicle control means" is a system component that controls autonomous vehicles in the event of an earthquake and moves them along evacuation routes.

[0152] The "information provision means" is a system component that provides evacuation information to users using in-vehicle displays, voice guidance, etc.

[0153] The "location tracking means" is a system component for receiving real-time location information from user terminals and tracking the evacuation situation.

[0154] The "feedback means" is a system component that collects user behavior data and evacuation success rates and uses them for future risk analysis and generation of behavioral instructions.

[0155] System Configuration

[0156] This invention is a system that collects past earthquake disaster data, performs risk analysis in real time, and provides optimal evacuation routes and action instructions. This system consists of three parties: a server, a terminal, and a user. In particular, we focus on an application example realized by a dedicated application installed in an autonomous vehicle.

[0157] Server Roles

[0158] The server first collects data on past earthquake disasters, cleansing the data, and then uses machine learning algorithms and deep learning models to learn from it. This allows it to identify risk patterns when an earthquake occurs and build a predictive model. Next, when it receives information from a device that detected an earthquake, it compares that information with past data to analyze the risk in the relevant area. The analysis takes into account data such as distance from the epicenter, topographical information, and population density. It then calculates the optimal evacuation route based on the risk analysis results and sends it to the device.

[0159] Device Role

[0160] The terminals consist of common mobile devices such as smartphones and tablets, but in this case they also include on-board computers installed in self-driving vehicles. When an earthquake is detected or an earthquake warning is received from the Japan Meteorological Agency, the information is sent to a server. When evacuation routes and specific instructions for action are sent from the server, the terminal communicates these to the user via the in-vehicle display and voice guidance system. Furthermore, the terminal also has the function of controlling the self-driving vehicle along the evacuation route using vehicle control means.

[0161] User Roles

[0162] The user begins and executes evacuation actions according to instructions from the device. When the evacuation is complete, the user presses the "Evacuation Complete" button on the device, and the information is sent to the server. The server collects the user's behavioral data and evacuation success rate, and uses this data for future risk analysis and the generation of behavioral instructions.

[0163] Hardware and Software Used

[0164] Server: Python, machine learning libraries (Scikit-Learn, TensorFlow, etc.), database (PostgreSQL)

[0165] Devices: Smartphones, tablets, in-vehicle computers for autonomous vehicles, displays, voice guidance systems

[0166] Data collection: Japan Meteorological Agency Earthquake Alert API, USGS Earthquake API

[0167] Specific examples

[0168] For example, suppose an earthquake occurs in a certain area and is detected by a device in an autonomous vehicle. This information is sent to a server, where it is compared with past data to analyze the risk in that area. If it determines that there is a risk of a tsunami, the server calculates an evacuation route and automatically guides the vehicle to higher ground, allowing the user to complete the evacuation safely.

[0169] Prompt Sentence Examples

[0170] An earthquake has occurred. Your current location is longitude 139.70, latitude 35.69. Please calculate the safest evacuation route and guide you to your destination.

[0171] In this way, the form for implementing the invention can provide optimal evacuation routes and specific instructions for actions in real time according to the individual circumstances of evacuees during earthquake disasters, and can also support quick and safe evacuation using autonomous vehicles.

[0172] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0173] Step 1:

[0174] The server collects data on past earthquake disasters. The input is earthquake data obtained from various APIs, and the output is a cleansed dataset. Data processing includes filling in incomplete data and processing outliers.

[0175] Step 2:

[0176] The server uses the cleansed data to train machine learning algorithms or deep learning models. The input is the cleansed dataset and the output is the trained model. Data operations include feature extraction and pattern identification.

[0177] Step 3:

[0178] The device detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency. The input is sensor data and earthquake warnings from the Japan Meteorological Agency API, and the output is a notification of an earthquake occurrence. Specific operations are triggered by sensors and communication modules on the device.

[0179] Step 4:

[0180] The terminal sends earthquake information to the server. The input is a notification of the earthquake occurrence, and the output is a transmission request to the server. Here, the terminal's network communication function is used.

[0181] Step 5:

[0182] The server compares the received earthquake information with past data and analyzes the risk in the relevant area. The input is earthquake information and a trained model, and the output is the risk analysis results. Data calculations take into account the distance from the epicenter and topographical information.

[0183] Step 6:

[0184] The server calculates the optimal evacuation route based on the risk analysis results and generates action instructions. The input is the risk analysis results, and the output is the evacuation route and action instructions. Specific operations include real-time traffic situation analysis using an algorithm.

[0185] Step 7:

[0186] The server sends the generated evacuation route and action instructions to the terminal. The input is the evacuation route and action instructions, and the output is a transmission request. The terminal's communication module is used again.

[0187] Step 8:

[0188] The terminal receives the evacuation route and action instructions from the server and provides them to the user via an in-car display or voice guidance. The input is the evacuation route and action instructions, and the output is the display and voice guidance. The in-car system plays an important role here.

[0189] Step 9:

[0190] The terminal controls the autonomous vehicle according to the evacuation route. The input is evacuation route information, and the output is vehicle control commands. Specific operations include route optimization by the navigation system and control of the drive-by-wire system.

[0191] Step 10:

[0192] The user presses the "Evacuation Complete" button on the device to notify that the evacuation is complete. The input is the user's touch operation, and the output is a notification of evacuation completion to the server.

[0193] Step 11:

[0194] The server receives evacuation completion notifications from users and records the user's behavioral data and evacuation success rate. The input is the evacuation completion notification, and the output is a record in the database. This will be used as a feedback tool for the next risk analysis.

[0195] Step 12:

[0196] The server uses feedback mechanisms to generate future risk analyses and action instructions. The input is the previous evacuation data, and the output is an updated predictive model. Generative AI models and prompts are used here.

[0197] 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.

[0198] This invention is a disaster prevention system that analyzes risks and suggests evacuation actions for earthquake disasters, providing optimal evacuation routes and action instructions in real time based on past earthquake disaster data. By combining this system with an emotion engine, it is possible to take the user's emotions into consideration and provide more accurate and effective evacuation instructions. This system consists of three parties: a server, a terminal, and a user, each of which plays a specific role.

[0199] 1. Data collection and learning

[0200] The server first collects data on past earthquake disasters. This data includes information such as epicenters, seismic intensity, damage status, and the impact of tsunamis and fires. This data is then cleansed and formatted for analysis. It is then trained using machine learning algorithms and deep learning models to identify risk patterns in the event of an earthquake and build a predictive model.

[0201] 2. Real-time risk prediction

[0202] When a device (such as a smartphone or tablet) detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency, it sends that information to a server. The information sent includes the earthquake's seismic intensity, epicenter, and time of occurrence. The server compares the received earthquake information with past data and analyzes the risk in the relevant area in real time.

[0203] 3. Emotion Recognition and Evaluation

[0204] The device is equipped with an emotion engine that recognizes the user's emotions. The emotion engine acquires and analyzes emotion data from the user's facial expressions, tone of voice, text input, etc., and sends the results to a server. Emotion data includes stress levels and levels of impatience.

[0205] 4. Emotion-based evacuation route and behavior suggestions

[0206] The server generates optimal evacuation routes and instructions based on the risk analysis results and emotional data from the emotion engine. If the user is in a high-stress state, the server prioritizes routes that provide a sense of security and simple instructions. The server then transmits the generated evacuation routes and instructions to the device.

[0207] 5. User Behavior and Feedback

[0208] The user carries out evacuation actions instructed by the device. They move while checking their current location and evacuation destination using the device's GPS function. The device sends the user's location information and movement trajectory to the server in real time, and the user's evacuation status is tracked.

[0209] Examples:

[0210] For example, if an earthquake occurs in a certain area and is detected by a device, the earthquake information is sent to a server, where risk analysis is performed in real time. At the same time, the device's emotion engine collects the user's emotional data, which is also sent to the server. If the server determines that the user is in a high-stress state, it selects an evacuation route that prioritizes a sense of security, generates instructions to "proceed slowly and safely," and sends these instructions to the device. The user begins evacuation according to the instructions, and once the evacuation is complete, presses the "Evacuation Complete" button on the device. This information is also sent to the server, and the success or failure of the evacuation is recorded.

[0211] This system not only supports quick and appropriate evacuation behavior during earthquake disasters, but also enables more effective evacuation by taking into account the user's emotional state.

[0212] The processing flow will be explained below.

[0213] Step 1:

[0214] The server collects data on past earthquake disasters, including epicenters, seismic intensity, damage, and the impact of tsunamis and fires. This data is obtained from government agencies, university research institutes, disaster-related organizations, and other sources.

[0215] Step 2:

[0216] The server cleanses the collected data and formats it in a format suitable for analysis, removing irrelevant data, handling missing values, and standardizing data formats.

[0217] Step 3:

[0218] The server uses the formatted data to train machine learning algorithms and deep learning models, identifying risk patterns in the event of an earthquake and building a predictive model.

[0219] Step 4:

[0220] When a device (smartphone or tablet) detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency, it sends that information, including the earthquake's magnitude, epicenter, and time of occurrence, to a server.

[0221] Step 5:

[0222] The server compares the received earthquake information with past data and performs real-time risk analysis, taking into account factors such as distance from the epicenter, topographical information, and population density.

[0223] Step 6:

[0224] The device's emotion engine acquires and analyzes emotional data from the user's facial expressions, tone of voice, text input, etc. The analysis results in information such as the user's stress level and degree of impatience.

[0225] Step 7:

[0226] The device then transmits the acquired emotional data, including the level of stress and impatience, to the server.

[0227] Step 8:

[0228] The server generates optimal evacuation routes and instructions based on risk analysis results and emotional data. If the user's stress level is high, the server prioritizes simpler and more reassuring routes.

[0229] Step 9:

[0230] The server then sends the generated evacuation route and instructions to the device, such as "head to the nearest high ground" or "evacuate to a designated evacuation shelter."

[0231] Step 10:

[0232] The user follows the instructions displayed on the device and begins the designated evacuation action, using the device's GPS function to check their current location and evacuation destination as they move.

[0233] Step 11:

[0234] The device transmits the user's location information and movement trajectory to the server in real time, allowing the server to track the user's evacuation status.

[0235] Step 12:

[0236] When the user completes evacuation, they press the "Evacuation Complete" button on their device. The evacuation completion information is sent to the server and recorded.

[0237] Step 13:

[0238] The server collects user behavior data and evacuation success rates, and uses feedback to improve the accuracy of risk analysis and behavioral instructions for future events, thereby continuously improving the effectiveness of the system.

[0239] Example 2

[0240] 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."

[0241] Conventional disaster prevention systems are limited to analyzing earthquake disaster risks and suggesting evacuation routes, and do not consider the user's emotional state, which can increase panic and stress during an emergency. Furthermore, evacuation route instructions are generalized, making it difficult to provide optimal instructions tailored to the user's individual situation and emotions. This can lead to ineffective evacuation behavior and reduced safety.

[0242] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a data collection means for collecting and learning past earthquake data, a risk analysis means for analyzing risks in real time based on the learned earthquake data, an emotion recognition means for acquiring user emotion data, an evacuation route generation means for analyzing the emotion data and integrating it with the risk analysis results to generate an evacuation route and action instructions, and an instruction transmission means for transmitting the generated evacuation route and action instructions to the user terminal. This makes it possible to provide an appropriate and effective evacuation route and action instructions that take into account the user's emotional state, thereby reducing stress in an emergency and improving evacuation safety.

[0243] "Data collection means" refers to the means for collecting past earthquake data and formatting it into a format suitable for analysis and learning.

[0244] "Risk analysis means" refers to a means for analyzing the risk of an earthquake occurring in real time based on collected and learned earthquake data.

[0245] The "emotion recognition means" is a means for analyzing the user's facial expression, tone of voice, text input, etc., and acquiring the user's emotional data.

[0246] The "evacuation route generation means" is a means for generating the optimal evacuation route and action instructions for the user based on the risk analysis results and emotion data.

[0247] The "instruction transmission means" is a means for transmitting the generated evacuation route and action instructions to the user terminal.

[0248] The "location tracking means" is a means for receiving real-time location information from the user terminal and tracking the evacuation status of the user.

[0249] The "feedback means" is a means for collecting user behavior data and evacuation success rates, and using the data for future risk analysis and generation of behavioral instructions.

[0250] This invention is a disaster prevention system that analyzes risks and suggests evacuation actions for earthquake disasters, and provides optimal evacuation routes and action instructions in real time based on past earthquake data and user emotion data. This system is composed of three parties: a server, a terminal, and a user, each of which plays a specific role.

[0251] First, the server has a data collection tool for collecting past earthquake data. This tool collects earthquake data using APIs from the Japan Meteorological Agency and other earthquake information providers. The collected data is cleansed and formatted for analysis using data processing libraries such as Pandas and NumPy. Then, a machine learning model is trained using TensorFlow and PyTorch. This model is used to identify risk patterns and make predictions when earthquakes occur.

[0252] Next, when a device (smartphone or tablet) detects an earthquake with its sensor or receives an earthquake warning from the Japan Meteorological Agency, earthquake information is sent to a server. The information sent includes the epicenter, seismic intensity, and time of occurrence. The server compares this information with past data and performs real-time risk analysis using cloud analysis services such as Google Cloud and Azure (registered trademark) AI.

[0253] The device is also equipped with an emotion engine that recognizes the user's emotions. The emotion engine uses tools such as OpenCV, Emotion API, and Watson (registered trademark) Tone Analyzer to acquire and analyze emotional data from the user's facial expressions, tone of voice, and text input. The resulting data, such as the user's stress level and degree of impatience, is sent to the server.

[0254] The server integrates the risk analysis results with the emotion data to generate the optimal evacuation route and behavioral instructions. For example, if the user is in a high-stress state, an evacuation route that prioritizes a sense of security will be selected, and instructions such as "proceed slowly and safely." These instructions are then sent to the device and provided to the user.

[0255] The user follows instructions from the device to carry out evacuation. Using the device's GPS function, the user moves while checking their current location and evacuation destination. The device sends the user's location information and movement trajectory to the server in real time, and the user's evacuation status is tracked.

[0256] As a concrete example, consider the case where a magnitude 7 earthquake occurs in a certain area and is detected by a device. At this time, earthquake information is sent to the server, and risk analysis is performed in real time. At the same time, the device's emotion engine collects the user's emotional data and detects that the user is in a high-stress state. Based on this, the server generates an instruction to "select an evacuation route that prioritizes a sense of security" and sends this to the device. The user begins evacuation in accordance with this instruction, and once the evacuation is complete, they press the "Evacuation Complete" button on the device, sending feedback to the server that the evacuation was successful.

[0257] An example of a prompt sentence is, "Please explain the real-time processing of a system that takes into account the user's emotions and suggests the optimal evacuation route when an earthquake occurs."

[0258] In this way, the present invention not only supports quick and appropriate evacuation behavior in the event of an earthquake disaster, but also realizes more effective evacuation by taking into account the user's emotional state.

[0259] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0260] Step 1:

[0261] The server retrieves past earthquake data.

[0262] Input: Collect earthquake data from the APIs of earthquake information providers. Specifically, access the APIs of the Japan Meteorological Agency and earthquake information providers.

[0263] Data processing: Receive collected data in JSON format and use the Pandas library to format it appropriately. Cleanse unnecessary information and missing data.

[0264] Output: A database of cleansed seismic data is generated.

[0265] Step 2:

[0266] The server trains a machine learning model based on the data.

[0267] Input: Formatted historical earthquake data. Specifically, features such as epicenter, seismic intensity, and damage status are used.

[0268] Data Computing: Using TensorFlow and PyTorch, we train an earthquake risk prediction model and identify risk patterns in the event of an earthquake based on historical earthquake data.

[0269] Output: A trained earthquake risk prediction model.

[0270] Step 3:

[0271] The device detects an earthquake or receives an earthquake alert.

[0272] Input: Data detecting earthquake vibrations from device sensors or notifications from earthquake warning systems.

[0273] Data processing: Obtain earthquake information (epicenter, seismic intensity, time of occurrence).

[0274] Output: Earthquake information is sent from the device to the server.

[0275] Step 4:

[0276] The server performs real-time risk analysis.

[0277] Input: Earthquake information sent from the device, specifically, data on the epicenter, seismic intensity, and occurrence time.

[0278] Data calculation: Analyze received earthquake information in real time and compare it with past data. Analyze risks using cloud analysis services from Google Cloud and Azure AI.

[0279] Output: Real-time risk analysis results are obtained.

[0280] Step 5:

[0281] The device collects the user's emotional data.

[0282] Input: Facial expression data from the camera, tone of voice from the microphone, and text input.

[0283] Data processing: Analyze these data using OpenCV, Emotion API, and Watson Tone Analyzer to obtain emotion data.

[0284] Output: Emotion data is obtained and sent to the server.

[0285] Step 6:

[0286] The server generates evacuation routes and action instructions taking into account emotion data.

[0287] Input: Real-time risk analysis results and sentiment data.

[0288] Data calculation: By integrating risk analysis results with emotional data, the system uses the Google Maps API to generate the optimal evacuation route based on the user's emotional state. For example, if the user is in a high-stress state, the system will select a simple and reassuring route.

[0289] Output: Optimal evacuation routes and action instructions are generated.

[0290] Step 7:

[0291] The server sends the generated evacuation route and action instructions to the terminal.

[0292] Input: Optimal evacuation route and action instructions.

[0293] Data processing: Format the data into JSON format and send it to the terminal via an HTTP request.

[0294] Output: The device receives the required information.

[0295] Step 8:

[0296] The user performs evacuation actions.

[0297] Input: Evacuation route and action instructions received from the terminal.

[0298] Specific actions: Use the GPS function to check your current location and follow a safe evacuation route.

[0299] Output: The user safely completes the evacuation.

[0300] Step 9:

[0301] The device tracks the user's evacuation status in real time.

[0302] Input: User location and movement trajectory.

[0303] Data processing: GPS data is acquired in real time and sent to the server.

[0304] Output: Evacuation status is tracked on the server.

[0305] Step 10:

[0306] When the user has completed the evacuation, he or she presses the "Evacuation Complete" button on the terminal.

[0307] Input: User presses the "Evacuation Complete" button.

[0308] Data processing: Send information about the completion of evacuation to the server.

[0309] Output: The server records a successful evacuation.

[0310] These are the specific processing steps of the program for this system, which makes it possible to support effective evacuation while taking into consideration the user's emotions.

[0311] (Application example 2)

[0312] 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."

[0313] Although systems already exist to support quick and appropriate evacuation behavior during earthquake disasters, previous systems did not take into account the user's emotional state, which can result in increased stress and anxiety. Furthermore, evacuation routes are provided based on a general approach, which does not provide appropriate instructions tailored to the user's individual emotional state. Therefore, there is a need for a system that allows users to evacuate with peace of mind.

[0314] The identification process by the identification 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 a data collection means for collecting and learning past earthquake disaster data, a risk analysis means for analyzing risks in real time based on the learned earthquake disaster data, an evacuation route generation means for generating evacuation routes and action instructions based on the analysis results, and an emotion analysis means for collecting user emotion data and reflecting it in the generation of evacuation routes. This makes it possible to provide an optimal evacuation route that takes the user's emotional state into consideration, realizing a system that allows users to evacuate quickly and safely.

[0315] "Data collection means" is a function that collects data on past earthquake disasters and formats the data for learning purposes.

[0316] The "risk analysis means" is a function that analyzes the risk in the event of an earthquake in real time based on learned earthquake disaster data.

[0317] The "evacuation route generation means" is a function that generates an optimal evacuation route and action instructions for the user based on the results of risk analysis.

[0318] The "instruction sending means" is a function that sends the generated evacuation route and action instructions to the user terminal.

[0319] The "emotion analysis means" is a function that collects the user's emotional data (stress level and degree of anxiety) and reflects that data in generating an evacuation route.

[0320] The "location tracking means" is a function that receives real-time location information from the user terminal and tracks the evacuation status of the user.

[0321] The "feedback means" is a function that collects user behavior data and evacuation success rates, and uses them for future risk analysis and generation of behavioral instructions.

[0322] The "emotion data analysis means" is a function that uses an emotion recognition engine installed on the user's terminal to analyze the user's stress level and degree of anxiety, and reflects this in generating an evacuation route.

[0323] This invention is a system that takes into consideration the emotional state of a user in the event of an earthquake disaster and provides optimal evacuation routes and action instructions. Specific embodiments of this system will be described below.

[0324] 1. Data collection and learning

[0325] The server first collects data on past earthquake disasters. This data includes information such as epicenters, seismic intensity, damage status, and the impact of tsunamis and fires. The collected data is then cleansed and formatted for analysis. It then uses machine learning algorithms and deep learning models to identify risk patterns in the event of an earthquake and build a predictive model. This process uses programming languages ​​and libraries such as Python and TensorFlow.

[0326] 2. Real-time risk prediction

[0327] When the user's device (smart glasses) detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency, it sends the information to a server. The information sent includes the earthquake's seismic intensity, epicenter, and time of occurrence. The server compares the received earthquake information with past data and analyzes the risk in the relevant area in real time.

[0328] 3. Emotion Recognition and Evaluation

[0329] The user device is equipped with an emotion recognition engine that recognizes the user's emotions. The emotion engine acquires and analyzes emotion data from the user's facial expressions, tone of voice, text input, etc., and sends the results to the server. Emotion data includes stress level and degree of impatience. This process utilizes the Emotion Recognition library.

[0330] 4. Emotion-based evacuation route and behavior suggestions

[0331] The server generates optimal evacuation routes and instructions based on the risk analysis results and emotional data from the emotion engine. If the user is in a high-stress state, the server prioritizes routes that provide a sense of security and simple instructions. The server then transmits the generated evacuation routes and instructions to the user's device.

[0332] 5. User Behavior and Feedback

[0333] The user carries out evacuation actions instructed by the device. Using the device's GPS function, the user moves while checking their current location and evacuation destination. The device sends the user's location information and movement trajectory to the server in real time, and the user's evacuation status is tracked.

[0334] Specific examples

[0335] For example, if an earthquake occurs in a certain area and is detected by a device, the earthquake information is sent to a server, where risk analysis is performed in real time. At the same time, the device's emotion engine collects the user's emotional data, which is also sent to the server. If the server determines that the user is in a high-stress state, it selects an evacuation route that prioritizes a sense of security, generates instructions to "proceed slowly and safely," and sends these instructions to the device. The user begins evacuation according to the instructions, and once the evacuation is complete, presses the "Evacuation Complete" button on the device. This information is also sent to the server, and the success or failure of the evacuation is recorded.

[0336] Prompt Sentence Examples

[0337] "Analyze the user's emotional state and suggest evacuation routes based on that data."

[0338] "Consider the user's current location when generating evacuation routes."

[0339] "To address high stress levels in users, prioritize escape routes that provide a sense of security."

[0340] This system not only supports quick and appropriate evacuation behavior during earthquake disasters, but also enables more effective evacuation by taking into account the user's emotional state.

[0341] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0342] Step 1:

[0343] The server collects data on past earthquake disasters. Specifically, it collects data on the epicenter, seismic intensity, damage status, and the impact of tsunamis and fires, and stores it in a database. It then prepares this data for analysis using machine learning algorithms and deep learning models. The input is disaster data from external data sources (such as the Japan Meteorological Agency or disaster databases), and the output is cleansed, formatted, and analyzable data.

[0344] Step 2:

[0345] The server uses machine learning algorithms and deep learning models to learn from the collected earthquake disaster data, identify risk patterns when an earthquake occurs, and build a predictive model. Specifically, the model is trained using programming languages ​​and libraries such as Python and TensorFlow. The input is formatted disaster data, and the output is a risk prediction model when an earthquake occurs.

[0346] Step 3:

[0347] When the device (smart glasses) detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency, it sends that information to the server. The input is the warning data from the earthquake detection device or the Japan Meteorological Agency, and the output is the earthquake information (seismic intensity, epicenter, and time of occurrence) sent to the server.

[0348] Step 4:

[0349] The server compares the received earthquake information with past data and analyzes the risk in the relevant area in real time. The input is earthquake information sent from the terminal, and the output is the real-time risk assessment result. This process uses a deep learning model.

[0350] Step 5:

[0351] The device is equipped with an emotion recognition engine that recognizes the user's emotions. The emotion engine acquires and analyzes emotion data from the user's facial expressions, tone of voice, text input, etc., and sends the results to a server. The input is the user's facial expression data and voice data, and the output is analyzed emotion data (stress level and degree of impatience).

[0352] Step 6:

[0353] The server generates optimal evacuation routes and action instructions by taking into account the risk analysis results as well as emotional data from the emotion engine. If the user is in a high-stress state, the system adjusts to prioritize routes that provide a sense of security and simple instructions. The inputs are real-time risk assessment results and emotional data, and the output is the optimal evacuation route and action instructions.

[0354] Step 7:

[0355] The server sends the generated evacuation route and action instructions to the terminal. The input is the optimal evacuation route and action instructions, and the output is the evacuation route and action instructions sent to the terminal.

[0356] Step 8:

[0357] The user carries out evacuation actions instructed by the device. They move while checking their current location and evacuation destination using the device's GPS function. The device sends the user's location information and movement trajectory to the server in real time, and tracks the user's evacuation status. The input is the user's current location and movement trajectory, and the output is evacuation status data sent to the server.

[0358] Step 9:

[0359] The server checks whether the user has completed evacuation and sends additional instructions or alerts as necessary. The input is real-time evacuation status data and feedback data, and the output is evacuation completion notification and additional instructions.

[0360] 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.

[0361] 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.

[0362] 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.

[0363] [Second embodiment]

[0364] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0365] 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.

[0366] 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).

[0367] 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.

[0368] 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.

[0369] 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).

[0370] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0371] 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.

[0372] 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.

[0373] 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.

[0374] 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.

[0375] 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."

[0376] This invention is a disaster prevention system that analyzes risks in the event of an earthquake and proposes evacuation actions, and provides optimal evacuation routes and action instructions in real time based on past earthquake disaster data. This system is composed of three parties: a server, a terminal, and a user, each of which plays a specific role.

[0377] 1. Data collection and learning

[0378] The server first collects data on past earthquake disasters. This data includes information such as epicenters, seismic intensity, damage status, and the impact of tsunamis and fires. This data is then cleansed and formatted for analysis, after which it is trained using machine learning algorithms and deep learning models. This allows the system to identify various risk patterns in the event of an earthquake and build a predictive model.

[0379] 2. Real-time risk prediction

[0380] When a device (such as a smartphone or tablet) detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency, it sends that information to a server. The server then compares the received earthquake information with past data and analyzes the risk in the relevant area. The analysis takes into account factors such as distance from the epicenter, topographical information, and population density.

[0381] 3. Evacuation routes and suggested actions

[0382] Based on the analysis results, the server calculates the optimal evacuation route. This calculation uses current topographical information and traffic conditions (e.g., traffic congestion information, road closure information). The server then generates specific instructions along with the evacuation route. For example, specific instructions such as "head to the nearest high ground" or "evacuate to a specific evacuation shelter" are generated and sent to the device.

[0383] 4. User Behavior and Feedback

[0384] The user carries out the evacuation actions instructed from the device. Once the evacuation is complete, the user presses the "Evacuation Complete" button on the device, which sends the information to the server. The server receives the user's location information and movement trajectory in real time and tracks the evacuation status. The server also collects user behavior data and evacuation success rate, and uses this information as feedback to improve the accuracy of the system in future risk analysis and the generation of behavioral instructions.

[0385] Examples:

[0386] For example, suppose an earthquake occurs in a certain area and is detected by a device. This information is sent to a server, which compares it with past data and analyzes the risk in that area. If the server determines that there is a risk of a tsunami, it calculates an evacuation route and instructs the user to evacuate to higher ground. This instruction is sent to the device, and the user begins evacuating to higher ground. After completing the evacuation, the user presses the "Evacuation Complete" button on the device, and the information is sent to the server. In this way, quick and specific evacuation instructions can be provided.

[0387] This system aims to support quick and specific evacuation actions in the event of an earthquake disaster, thereby minimizing damage.

[0388] The processing flow will be explained below.

[0389] Step 1:

[0390] The server collects data on past earthquake disasters, including epicenters, seismic intensity, damage, and the impact of tsunamis and fires. This data is obtained from government agencies, university research institutes, disaster-related organizations, and other sources.

[0391] Step 2:

[0392] The server cleanses the collected data, removing irrelevant data, processing missing values, standardizing data formats, and otherwise formatting it into a format that is easy to analyze.

[0393] Step 3:

[0394] The server inputs the formatted data into machine learning algorithms and deep learning models to learn risk patterns in the event of an earthquake, thereby building a predictive model.

[0395] Step 4:

[0396] When a device (such as a smartphone or tablet) receives an earthquake warning from an earthquake detection sensor or the Japan Meteorological Agency, it sends the information to a server, including the earthquake's seismic intensity, epicenter, and time of occurrence.

[0397] Step 5:

[0398] The server compares the received earthquake information with past data and performs real-time risk analysis, taking into account factors such as distance from the epicenter, topographical information, and population density.

[0399] Step 6:

[0400] The server calculates the optimal evacuation route based on the analysis results, taking into account current terrain information and traffic conditions (e.g., traffic congestion, road closures).

[0401] Step 7:

[0402] The server generates specific instructions along with evacuation routes, such as "head to the nearest high ground" or "evacuate to a specific shelter."

[0403] Step 8:

[0404] The server then sends the generated evacuation route and action instructions to the terminal, allowing the user to receive specific evacuation instructions.

[0405] Step 9:

[0406] The user follows the instructions displayed on the device and begins the designated evacuation action, using the device's GPS function to check their current location and evacuation destination as they move.

[0407] Step 10:

[0408] The device transmits the user's location information and movement trajectory to the server in real time, allowing the server to track the user's evacuation status.

[0409] Step 11:

[0410] When the user completes evacuation, they press the "Evacuation Complete" button on their device. The evacuation completion information is sent to the server and recorded.

[0411] Step 12:

[0412] The server collects user behavior data and evacuation success rates, and uses feedback to improve the accuracy of risk analysis and behavioral instructions for future events, thereby continuously improving the effectiveness of the system.

[0413] Example 1

[0414] 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."

[0415] Current earthquake disaster prevention systems do not fully utilize past data, resulting in issues with the accuracy of real-time risk predictions and evacuation instructions. They also lack the functionality to track users' location information and evacuation status, making it difficult to support appropriate evacuation behavior. Furthermore, they lack a mechanism for feeding back evacuation behavior data to improve the accuracy of the system.

[0416] 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.

[0417] In this invention, the server includes a data collection means for collecting and learning past earthquake disaster data, a risk analysis means for analyzing risks in real time based on the learned earthquake disaster data, an evacuation route generation means for generating evacuation routes and action instructions based on the analysis results, and an instruction transmission means for transmitting the generated evacuation routes and action instructions to the communication device. This enables real-time risk prediction and provision of specific and optimal evacuation instructions to the user, thereby improving the accuracy and effectiveness of evacuation actions.

[0418] "Data collection means" refers to the function of collecting and learning from past earthquake disaster data.

[0419] "Risk analysis means" refers to the function of analyzing risk in real time based on learned earthquake disaster data.

[0420] "Evacuation route generation means" refers to a function that generates an evacuation route and action instructions based on the analysis results.

[0421] The "instruction sending means" refers to a function that sends the generated evacuation route and action instructions to the communication device.

[0422] "Location tracking means" refers to the function of receiving real-time location signals and tracking evacuation status.

[0423] "Feedback means" refers to the function of collecting behavioral data and evacuation success rates and using them for future risk analysis and generation of behavioral instructions.

[0424] "Server" refers to a central processing unit that manages and operates functions such as data collection, risk analysis, evacuation route generation, instruction transmission, location tracking, and feedback.

[0425] "Communication device" refers to a user terminal that receives evacuation routes and action instructions sent from the server.

[0426] The present invention is a disaster prevention system that performs risk analysis and evacuation instructions using past earthquake disaster data. This system is composed of a server, terminals, and users, each of which plays a specific role.

[0427] Server Roles and Functions

[0428] The server plays a central role in this system and performs the following functions:

[0429] Data collection methods

[0430] The server collects past earthquake disaster data from public databases on the Internet, earthquake research institutes, the Japan Meteorological Agency, etc. This data includes information such as the epicenter, seismic intensity, damage status, and the impact of tsunamis and fires. Specifically, the server automatically collects data using an API and stores it in an internal database.

[0431] Risk Analysis Tools

[0432] The server cleanses the collected earthquake disaster data and formats it into a format suitable for analysis. It removes duplicates, missing values, and inappropriate values ​​to create a dataset. It then uses machine learning algorithms and deep learning models (e.g., TensorFlow and PyTorch) to train this dataset and build a predictive model for real-time risk forecasting in the event of an earthquake.

[0433] Evacuation route generation method

[0434] The server uses machine learning models to analyze risk in the event of an earthquake and generates optimal evacuation routes based on that risk. It references current topographical information and traffic conditions (e.g., traffic congestion and road closures) using Google Maps API and OpenStreetMap. Along with the evacuation route, it generates specific instructions, such as "head to the nearest high ground" or "evacuate to a specific evacuation shelter."

[0435] Instruction sending means

[0436] The server sends the generated evacuation route and instructions to the device via push notification or SMS, helping users to quickly begin evacuation actions.

[0437] Location Tracking Methods

[0438] The server tracks the user's evacuation status based on real-time location information received from the device, allowing it to check whether the user is evacuating as instructed and send further instructions if necessary.

[0439] Feedback Methods

[0440] The server collects data on users' evacuation behavior and the success rate of evacuation, and uses this information for future risk analysis and generation of action instructions, thereby enabling the system's accuracy to be continually improved.

[0441] Device roles and functions

[0442] The device (smartphone, tablet, etc.) is responsible for the following functions:

[0443] earthquake sensing

[0444] The device detects earthquakes using its built-in acceleration sensor or receives earthquake warnings from the Japan Meteorological Agency.

[0445] Sending information to the server

[0446] If an earthquake is detected, the device immediately sends that information and its current location to the server.

[0447] Receiving and displaying instructions

[0448] The system receives evacuation routes and instructions sent from the server and displays them to the user. It also notifies the user via push notifications and alarm sounds, encouraging them to take prompt action.

[0449] User Roles and Capabilities

[0450] The user takes evacuation action based on the information provided by the terminal.

[0451] Implementing evacuation actions

[0452] The user follows the evacuation instructions from the device and begins evacuating along the designated evacuation route, for example, heading to the nearest high ground or to a specific evacuation shelter.

[0453] Reporting completion of evacuation

[0454] Once the evacuation is complete, press the "Evacuation Complete" button on the device to send the information to the server.

[0455] Specific examples

[0456] For example, if an earthquake occurs in a certain area, the device will detect the earthquake and send that information along with the user's current location to the server. The server will compare this information with past data and analyze the risk in that area. If the server determines that there is a risk of a tsunami, it will calculate the optimal evacuation route and instruct the user to "evacuate to higher ground." This instruction is sent to the device, and the user begins evacuation accordingly. After completing the evacuation, the user presses the "evacuation complete" button on the device, and the information is sent to the server. This series of steps allows for quick and specific evacuation actions to be taken.

[0457] Prompt Sentence Examples

[0458] The following is an example of a prompt sentence that uses a generative AI model to specifically explain the operation of this system:

[0459] "Please explain how the earthquake disaster prevention system works. The system collects data on past earthquake disasters, performs risk predictions in real time, and provides optimal evacuation routes and action instructions. Please explain each processing step in detail."

[0460] The system aims to support quick and specific evacuation actions in the event of an earthquake disaster, thereby minimizing damage.

[0461] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0462] Step 1: Data collection

[0463] The server collects data on past earthquake disasters from public databases on the Internet, earthquake research institutes, the Japan Meteorological Agency, and other sources. This data includes information such as the epicenter, seismic intensity, damage status, and the impact of tsunamis and fires. The collected data is stored in the server's internal database. Specifically, it is automatically collected using an API and obtains data in JSON format. The input data is raw data on earthquake disasters, and the output data is the raw data file before cleansing.

[0464] Step 2: Data cleansing

[0465] The server cleanses the collected data. Specifically, it removes duplicate data and corrects missing or inappropriate values. For example, data showing a seismic intensity of "upper 6" is converted to the numerical value "6." This process converts the data into a format suitable for analysis. The input data is a raw data file, and the output data is a cleansed dataset.

[0466] Step 3: Training the machine learning model

[0467] The server uses the cleansed data to train machine learning algorithms and deep learning models. Libraries used include TensorFlow and PyTorch. The learning algorithms used are random forests and neural networks for risk prediction. This process builds a predictive model for real-time risk forecasting in the event of an earthquake. The input data is the cleansed dataset, and the output data is the trained predictive model.

[0468] Step 4: Earthquake detection and information transmission

[0469] A device (such as a smartphone or tablet) detects an earthquake using its built-in acceleration sensor or receives an earthquake warning from the Japan Meteorological Agency. When an earthquake is detected, the device sends this detection information along with its current location information to a server. The input data is the earthquake detection data and location information, and the output data is the data sent to the server.

[0470] Step 5: Risk analysis

[0471] The server compares the received earthquake information and location information with past data and analyzes the risk of the relevant area. Specifically, it takes into account factors such as distance from the epicenter, topographical information, and population density. This risk analysis uses a trained predictive model. The input data is earthquake information and location information, and the output data is the risk analysis results.

[0472] Step 6: Evacuation route generation and behavior instructions

[0473] The server generates the optimal evacuation route based on the risk analysis results. This generation uses geographic information services such as Google Maps API and OpenStreetMap. It also generates specific action instructions (e.g., "head to the nearest high ground" or "evacuate to a specific evacuation shelter"). The input data are the risk analysis results and current terrain and traffic information, and the output data are the evacuation route and action instructions.

[0474] Step 7: Sending instructions

[0475] The server sends the generated evacuation route and action instructions to the device. This is done using push notifications or SMS. The input data is the evacuation route and action instructions, and the output data is the data sent to the device.

[0476] Step 8: User evacuation behavior

[0477] The user follows the instructions received from the device and begins evacuation along the specified evacuation route. For example, they may head to the nearest high ground or evacuate to a specific evacuation shelter. The input data are instructions from the device, and the output is the actual evacuation behavior.

[0478] Step 9: Evacuation completion report

[0479] When the user completes evacuation, they press the "Evacuation Complete" button on their device to send evacuation completion information to the server. The input data is the evacuation completion information, and the output data is the data to be sent to the server.

[0480] Step 10: Evacuation status tracking and feedback

[0481] The server tracks the user's evacuation status based on the received evacuation completion information and user location information. It also uses the collected evacuation behavior data and evacuation success rate for future risk analysis and the generation of behavioral instructions. The input data are evacuation behavior data and completion information, and the output data is learning data used as feedback.

[0482] The above is a specific operation of each processing step in the disaster recovery system.

[0483] (Application example 1)

[0484] 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."

[0485] During earthquake disasters, it is important to provide routes and instructions for quick and safe evacuation, but current technology makes it difficult to provide optimal evacuation routes and specific instructions for action in real time according to the individual circumstances of each evacuee.In addition, there is no system in place to efficiently support evacuation using autonomous vehicles, which can result in delays in evacuation.To solve this problem, there is a need for a system that can perform risk analysis in real time during earthquake disasters and provide evacuation routes and instructions for action to autonomous vehicles.

[0486] 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.

[0487] In this invention, the server includes a data collection means for collecting and learning past earthquake disaster data, a risk analysis means for analyzing risks in real time based on the learned earthquake disaster data, an evacuation route generation means for generating evacuation routes and action instructions based on the analysis results, an instruction transmission means for transmitting the generated evacuation routes and action instructions to a user terminal, a vehicle control means for controlling an autonomous vehicle to move along the evacuation route when an earthquake occurs, and an information provision means for providing information to users via an in-vehicle display or audio guidance. This makes it possible to provide optimal evacuation routes and specific action instructions according to the individual circumstances of evacuees in the event of an earthquake disaster, and to support quick and safe evacuation using autonomous vehicles.

[0488] The "data collection means" is a system component that collects past earthquake disaster data and uses it for learning.

[0489] The "risk analysis means" is a system component for analyzing earthquake risk in real time based on collected data.

[0490] The "evacuation route generation means" is a system component that generates an optimal evacuation route and specific action instructions based on the results of risk analysis.

[0491] The "instruction transmitting means" is a system component for transmitting the generated evacuation route and action instructions to the user terminal.

[0492] The "vehicle control means" is a system component that controls autonomous vehicles in the event of an earthquake and moves them along evacuation routes.

[0493] The "information provision means" is a system component that provides evacuation information to users using in-vehicle displays, voice guidance, etc.

[0494] The "location tracking means" is a system component for receiving real-time location information from user terminals and tracking the evacuation situation.

[0495] The "feedback means" is a system component that collects user behavior data and evacuation success rates and uses them for future risk analysis and generation of behavioral instructions.

[0496] System Configuration

[0497] This invention is a system that collects past earthquake disaster data, performs risk analysis in real time, and provides optimal evacuation routes and action instructions. This system consists of three parties: a server, a terminal, and a user. In particular, we focus on an application example realized by a dedicated application installed in an autonomous vehicle.

[0498] Server Roles

[0499] The server first collects data on past earthquake disasters, cleansing the data, and then uses machine learning algorithms and deep learning models to learn from it. This allows it to identify risk patterns when an earthquake occurs and build a predictive model. Next, when it receives information from a device that detected an earthquake, it compares that information with past data to analyze the risk in the relevant area. The analysis takes into account data such as distance from the epicenter, topographical information, and population density. It then calculates the optimal evacuation route based on the risk analysis results and sends it to the device.

[0500] Device Role

[0501] The terminals consist of common mobile devices such as smartphones and tablets, but in this case they also include on-board computers installed in self-driving vehicles. When an earthquake is detected or an earthquake warning is received from the Japan Meteorological Agency, the information is sent to a server. When evacuation routes and specific instructions for action are sent from the server, the terminal communicates these to the user via the in-vehicle display and voice guidance system. Furthermore, the terminal also has the function of controlling the self-driving vehicle along the evacuation route using vehicle control means.

[0502] User Roles

[0503] The user begins and executes evacuation actions according to instructions from the device. When the evacuation is complete, the user presses the "Evacuation Complete" button on the device, and the information is sent to the server. The server collects the user's behavioral data and evacuation success rate, and uses this data for future risk analysis and the generation of behavioral instructions.

[0504] Hardware and Software Used

[0505] Server: Python, machine learning libraries (Scikit-Learn, TensorFlow, etc.), database (PostgreSQL)

[0506] Devices: Smartphones, tablets, in-vehicle computers for autonomous vehicles, displays, voice guidance systems

[0507] Data collection: Japan Meteorological Agency Earthquake Alert API, USGS Earthquake API

[0508] Specific examples

[0509] For example, suppose an earthquake occurs in a certain area and is detected by a device in an autonomous vehicle. This information is sent to a server, where it is compared with past data to analyze the risk in that area. If it determines that there is a risk of a tsunami, the server calculates an evacuation route and automatically guides the vehicle to higher ground, allowing the user to complete the evacuation safely.

[0510] Prompt Sentence Examples

[0511] An earthquake has occurred. Your current location is longitude 139.70, latitude 35.69. Please calculate the safest evacuation route and guide you to your destination.

[0512] In this way, the form for implementing the invention can provide optimal evacuation routes and specific instructions for actions in real time according to the individual circumstances of evacuees during earthquake disasters, and can also support quick and safe evacuation using autonomous vehicles.

[0513] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0514] Step 1:

[0515] The server collects data on past earthquake disasters. The input is earthquake data obtained from various APIs, and the output is a cleansed dataset. Data processing includes filling in incomplete data and processing outliers.

[0516] Step 2:

[0517] The server uses the cleansed data to train machine learning algorithms or deep learning models. The input is the cleansed dataset and the output is the trained model. Data operations include feature extraction and pattern identification.

[0518] Step 3:

[0519] The device detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency. The input is sensor data and earthquake warnings from the Japan Meteorological Agency API, and the output is a notification of an earthquake occurrence. Specific operations are triggered by sensors and communication modules on the device.

[0520] Step 4:

[0521] The terminal sends earthquake information to the server. The input is a notification of the earthquake occurrence, and the output is a transmission request to the server. Here, the terminal's network communication function is used.

[0522] Step 5:

[0523] The server compares the received earthquake information with past data and analyzes the risk in the relevant area. The input is earthquake information and a trained model, and the output is the risk analysis results. Data calculations take into account the distance from the epicenter and topographical information.

[0524] Step 6:

[0525] The server calculates the optimal evacuation route based on the risk analysis results and generates action instructions. The input is the risk analysis results, and the output is the evacuation route and action instructions. Specific operations include real-time traffic situation analysis using an algorithm.

[0526] Step 7:

[0527] The server sends the generated evacuation route and action instructions to the terminal. The input is the evacuation route and action instructions, and the output is a transmission request. The terminal's communication module is used again.

[0528] Step 8:

[0529] The terminal receives the evacuation route and action instructions from the server and provides them to the user via an in-car display or voice guidance. The input is the evacuation route and action instructions, and the output is the display and voice guidance. The in-car system plays an important role here.

[0530] Step 9:

[0531] The terminal controls the autonomous vehicle according to the evacuation route. The input is evacuation route information, and the output is vehicle control commands. Specific operations include route optimization by the navigation system and control of the drive-by-wire system.

[0532] Step 10:

[0533] The user presses the "Evacuation Complete" button on the device to notify that the evacuation is complete. The input is the user's touch operation, and the output is a notification of evacuation completion to the server.

[0534] Step 11:

[0535] The server receives evacuation completion notifications from users and records the user's behavioral data and evacuation success rate. The input is the evacuation completion notification, and the output is a record in the database. This will be used as a feedback tool for the next risk analysis.

[0536] Step 12:

[0537] The server uses feedback mechanisms to generate future risk analyses and action instructions. The input is the previous evacuation data, and the output is an updated predictive model. Generative AI models and prompts are used here.

[0538] 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.

[0539] This invention is a disaster prevention system that analyzes risks and suggests evacuation actions for earthquake disasters, providing optimal evacuation routes and action instructions in real time based on past earthquake disaster data. By combining this system with an emotion engine, it is possible to take the user's emotions into consideration and provide more accurate and effective evacuation instructions. This system consists of three parties: a server, a terminal, and a user, each of which plays a specific role.

[0540] 1. Data collection and learning

[0541] The server first collects data on past earthquake disasters. This data includes information such as epicenters, seismic intensity, damage status, and the impact of tsunamis and fires. This data is then cleansed and formatted for analysis. It is then trained using machine learning algorithms and deep learning models to identify risk patterns in the event of an earthquake and build a predictive model.

[0542] 2. Real-time risk prediction

[0543] When a device (such as a smartphone or tablet) detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency, it sends that information to a server. The information sent includes the earthquake's seismic intensity, epicenter, and time of occurrence. The server compares the received earthquake information with past data and analyzes the risk in the relevant area in real time.

[0544] 3. Emotion Recognition and Evaluation

[0545] The device is equipped with an emotion engine that recognizes the user's emotions. The emotion engine acquires and analyzes emotion data from the user's facial expressions, tone of voice, text input, etc., and sends the results to a server. Emotion data includes stress levels and levels of impatience.

[0546] 4. Emotion-based evacuation route and behavior suggestions

[0547] The server generates optimal evacuation routes and instructions based on the risk analysis results and emotional data from the emotion engine. If the user is in a high-stress state, the server prioritizes routes that provide a sense of security and simple instructions. The server then transmits the generated evacuation routes and instructions to the device.

[0548] 5. User Behavior and Feedback

[0549] The user carries out evacuation actions instructed by the device. They move while checking their current location and evacuation destination using the device's GPS function. The device sends the user's location information and movement trajectory to the server in real time, and the user's evacuation status is tracked.

[0550] Examples:

[0551] For example, if an earthquake occurs in a certain area and is detected by a device, the earthquake information is sent to a server, where risk analysis is performed in real time. At the same time, the device's emotion engine collects the user's emotional data, which is also sent to the server. If the server determines that the user is in a high-stress state, it selects an evacuation route that prioritizes a sense of security, generates instructions to "proceed slowly and safely," and sends these instructions to the device. The user begins evacuation according to the instructions, and once the evacuation is complete, presses the "Evacuation Complete" button on the device. This information is also sent to the server, and the success or failure of the evacuation is recorded.

[0552] This system not only supports quick and appropriate evacuation behavior during earthquake disasters, but also enables more effective evacuation by taking into account the user's emotional state.

[0553] The processing flow will be explained below.

[0554] Step 1:

[0555] The server collects data on past earthquake disasters, including epicenters, seismic intensity, damage, and the impact of tsunamis and fires. This data is obtained from government agencies, university research institutes, disaster-related organizations, and other sources.

[0556] Step 2:

[0557] The server cleanses the collected data and formats it in a format suitable for analysis, removing irrelevant data, handling missing values, and standardizing data formats.

[0558] Step 3:

[0559] The server uses the formatted data to train machine learning algorithms and deep learning models, identifying risk patterns in the event of an earthquake and building a predictive model.

[0560] Step 4:

[0561] When a device (smartphone or tablet) detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency, it sends that information, including the earthquake's magnitude, epicenter, and time of occurrence, to a server.

[0562] Step 5:

[0563] The server compares the received earthquake information with past data and performs real-time risk analysis, taking into account factors such as distance from the epicenter, topographical information, and population density.

[0564] Step 6:

[0565] The device's emotion engine acquires and analyzes emotional data from the user's facial expressions, tone of voice, text input, etc. The analysis results in information such as the user's stress level and degree of impatience.

[0566] Step 7:

[0567] The device then transmits the acquired emotional data, including the level of stress and impatience, to the server.

[0568] Step 8:

[0569] The server generates optimal evacuation routes and instructions based on risk analysis results and emotional data. If the user's stress level is high, the server prioritizes simpler and more reassuring routes.

[0570] Step 9:

[0571] The server then sends the generated evacuation route and instructions to the device, such as "head to the nearest high ground" or "evacuate to a designated evacuation shelter."

[0572] Step 10:

[0573] The user follows the instructions displayed on the device and begins the designated evacuation action, using the device's GPS function to check their current location and evacuation destination as they move.

[0574] Step 11:

[0575] The device transmits the user's location information and movement trajectory to the server in real time, allowing the server to track the user's evacuation status.

[0576] Step 12:

[0577] When the user completes evacuation, they press the "Evacuation Complete" button on their device. The evacuation completion information is sent to the server and recorded.

[0578] Step 13:

[0579] The server collects user behavior data and evacuation success rates, and uses feedback to improve the accuracy of risk analysis and behavioral instructions for future events, thereby continuously improving the effectiveness of the system.

[0580] Example 2

[0581] 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."

[0582] Conventional disaster prevention systems are limited to analyzing earthquake disaster risks and suggesting evacuation routes, and do not consider the user's emotional state, which can increase panic and stress during an emergency. Furthermore, evacuation route instructions are generalized, making it difficult to provide optimal instructions tailored to the user's individual situation and emotions. This can lead to ineffective evacuation behavior and reduced safety.

[0583] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a data collection means for collecting and learning past earthquake data, a risk analysis means for analyzing risks in real time based on the learned earthquake data, an emotion recognition means for acquiring user emotion data, an evacuation route generation means for analyzing the emotion data and integrating it with the risk analysis results to generate an evacuation route and action instructions, and an instruction transmission means for transmitting the generated evacuation route and action instructions to the user terminal. This makes it possible to provide an appropriate and effective evacuation route and action instructions that take into account the user's emotional state, thereby reducing stress in an emergency and improving evacuation safety.

[0584] "Data collection means" refers to the means for collecting past earthquake data and formatting it into a format suitable for analysis and learning.

[0585] "Risk analysis means" refers to a means for analyzing the risk of an earthquake occurring in real time based on collected and learned earthquake data.

[0586] The "emotion recognition means" is a means for analyzing the user's facial expression, tone of voice, text input, etc., and acquiring the user's emotional data.

[0587] The "evacuation route generation means" is a means for generating the optimal evacuation route and action instructions for the user based on the risk analysis results and emotion data.

[0588] The "instruction transmission means" is a means for transmitting the generated evacuation route and action instructions to the user terminal.

[0589] The "location tracking means" is a means for receiving real-time location information from the user terminal and tracking the evacuation status of the user.

[0590] The "feedback means" is a means for collecting user behavior data and evacuation success rates, and using the data for future risk analysis and generation of behavioral instructions.

[0591] This invention is a disaster prevention system that analyzes risks and suggests evacuation actions for earthquake disasters, and provides optimal evacuation routes and action instructions in real time based on past earthquake data and user emotion data. This system is composed of three parties: a server, a terminal, and a user, each of which plays a specific role.

[0592] First, the server has a data collection tool for collecting past earthquake data. This tool collects earthquake data using APIs from the Japan Meteorological Agency and other earthquake information providers. The collected data is cleansed and formatted for analysis using data processing libraries such as Pandas and NumPy. Then, a machine learning model is trained using TensorFlow and PyTorch. This model is used to identify risk patterns and make predictions when earthquakes occur.

[0593] Next, when a device (smartphone or tablet) detects an earthquake with its sensor or receives an earthquake warning from the Japan Meteorological Agency, earthquake information is sent to a server. The information sent includes the epicenter, seismic intensity, and time of occurrence. The server compares this information with past data and performs real-time risk analysis using cloud analysis services such as Google Cloud and Azure AI.

[0594] The device is also equipped with an emotion engine that recognizes the user's emotions. The emotion engine uses tools such as OpenCV, Emotion API, and Watson Tone Analyzer to acquire and analyze emotional data from the user's facial expressions, tone of voice, and text input. The resulting data, such as the user's stress level and degree of impatience, is sent to the server.

[0595] The server integrates the risk analysis results with the emotion data to generate the optimal evacuation route and behavioral instructions. For example, if the user is in a high-stress state, an evacuation route that prioritizes a sense of security will be selected, and instructions such as "proceed slowly and safely." These instructions are then sent to the device and provided to the user.

[0596] The user follows instructions from the device to carry out evacuation. Using the device's GPS function, the user moves while checking their current location and evacuation destination. The device sends the user's location information and movement trajectory to the server in real time, and the user's evacuation status is tracked.

[0597] As a concrete example, consider the case where a magnitude 7 earthquake occurs in a certain area and is detected by a device. At this time, earthquake information is sent to the server, and risk analysis is performed in real time. At the same time, the device's emotion engine collects the user's emotional data and detects that the user is in a high-stress state. Based on this, the server generates an instruction to "select an evacuation route that prioritizes a sense of security" and sends this to the device. The user begins evacuation in accordance with this instruction, and once the evacuation is complete, they press the "Evacuation Complete" button on the device, sending feedback to the server that the evacuation was successful.

[0598] An example of a prompt sentence is, "Please explain the real-time processing of a system that takes into account the user's emotions and suggests the optimal evacuation route when an earthquake occurs."

[0599] In this way, the present invention not only supports quick and appropriate evacuation behavior in the event of an earthquake disaster, but also realizes more effective evacuation by taking into account the user's emotional state.

[0600] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0601] Step 1:

[0602] The server retrieves past earthquake data.

[0603] Input: Collect earthquake data from the APIs of earthquake information providers. Specifically, access the APIs of the Japan Meteorological Agency and earthquake information providers.

[0604] Data processing: Receive collected data in JSON format and use the Pandas library to format it appropriately. Cleanse unnecessary information and missing data.

[0605] Output: A database of cleansed seismic data is generated.

[0606] Step 2:

[0607] The server trains a machine learning model based on the data.

[0608] Input: Formatted historical earthquake data. Specifically, features such as epicenter, seismic intensity, and damage status are used.

[0609] Data Computing: Using TensorFlow and PyTorch, we train an earthquake risk prediction model and identify risk patterns in the event of an earthquake based on historical earthquake data.

[0610] Output: A trained earthquake risk prediction model.

[0611] Step 3:

[0612] The device detects an earthquake or receives an earthquake alert.

[0613] Input: Data detecting earthquake vibrations from device sensors or notifications from earthquake warning systems.

[0614] Data processing: Obtain earthquake information (epicenter, seismic intensity, time of occurrence).

[0615] Output: Earthquake information is sent from the device to the server.

[0616] Step 4:

[0617] The server performs real-time risk analysis.

[0618] Input: Earthquake information sent from the device, specifically, data on the epicenter, seismic intensity, and occurrence time.

[0619] Data calculation: Analyze received earthquake information in real time and compare it with past data. Analyze risks using cloud analysis services from Google Cloud and Azure AI.

[0620] Output: Real-time risk analysis results are obtained.

[0621] Step 5:

[0622] The device collects the user's emotional data.

[0623] Input: Facial expression data from the camera, tone of voice from the microphone, and text input.

[0624] Data processing: Analyze these data using OpenCV, Emotion API, and Watson Tone Analyzer to obtain emotion data.

[0625] Output: Emotion data is obtained and sent to the server.

[0626] Step 6:

[0627] The server generates evacuation routes and action instructions taking into account emotion data.

[0628] Input: Real-time risk analysis results and sentiment data.

[0629] Data calculation: By integrating risk analysis results with emotional data, the system uses the Google Maps API to generate the optimal evacuation route based on the user's emotional state. For example, if the user is in a high-stress state, the system will select a simple and reassuring route.

[0630] Output: Optimal evacuation routes and action instructions are generated.

[0631] Step 7:

[0632] The server sends the generated evacuation route and action instructions to the terminal.

[0633] Input: Optimal evacuation route and action instructions.

[0634] Data processing: Format the data into JSON format and send it to the terminal via an HTTP request.

[0635] Output: The device receives the required information.

[0636] Step 8:

[0637] The user performs evacuation actions.

[0638] Input: Evacuation route and action instructions received from the terminal.

[0639] Specific actions: Use the GPS function to check your current location and follow a safe evacuation route.

[0640] Output: The user safely completes the evacuation.

[0641] Step 9:

[0642] The device tracks the user's evacuation status in real time.

[0643] Input: User location and movement trajectory.

[0644] Data processing: GPS data is acquired in real time and sent to the server.

[0645] Output: Evacuation status is tracked on the server.

[0646] Step 10:

[0647] When the user has completed the evacuation, he or she presses the "Evacuation Complete" button on the terminal.

[0648] Input: User presses the "Evacuation Complete" button.

[0649] Data processing: Send information about the completion of evacuation to the server.

[0650] Output: The server records a successful evacuation.

[0651] These are the specific processing steps of the program for this system, which makes it possible to support effective evacuation while taking into consideration the user's emotions.

[0652] (Application example 2)

[0653] 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."

[0654] Although systems already exist to support quick and appropriate evacuation behavior during earthquake disasters, previous systems did not take into account the user's emotional state, which can result in increased stress and anxiety. Furthermore, evacuation routes are provided based on a general approach, which does not provide appropriate instructions tailored to the user's individual emotional state. Therefore, there is a need for a system that allows users to evacuate with peace of mind.

[0655] The identification process by the identification 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 a data collection means for collecting and learning past earthquake disaster data, a risk analysis means for analyzing risks in real time based on the learned earthquake disaster data, an evacuation route generation means for generating evacuation routes and action instructions based on the analysis results, and an emotion analysis means for collecting user emotion data and reflecting it in the generation of evacuation routes. This makes it possible to provide an optimal evacuation route that takes the user's emotional state into consideration, realizing a system that allows users to evacuate quickly and safely.

[0656] "Data collection means" is a function that collects data on past earthquake disasters and formats the data for learning purposes.

[0657] The "risk analysis means" is a function that analyzes the risk in the event of an earthquake in real time based on learned earthquake disaster data.

[0658] The "evacuation route generation means" is a function that generates an optimal evacuation route and action instructions for the user based on the results of risk analysis.

[0659] The "instruction sending means" is a function that sends the generated evacuation route and action instructions to the user terminal.

[0660] The "emotion analysis means" is a function that collects the user's emotional data (stress level and degree of anxiety) and reflects that data in generating an evacuation route.

[0661] The "location tracking means" is a function that receives real-time location information from the user terminal and tracks the evacuation status of the user.

[0662] The "feedback means" is a function that collects user behavior data and evacuation success rates, and uses them for future risk analysis and generation of behavioral instructions.

[0663] The "emotion data analysis means" is a function that uses an emotion recognition engine installed on the user's terminal to analyze the user's stress level and degree of anxiety, and reflects this in generating an evacuation route.

[0664] This invention is a system that takes into consideration the emotional state of a user in the event of an earthquake disaster and provides optimal evacuation routes and action instructions. Specific embodiments of this system will be described below.

[0665] 1. Data collection and learning

[0666] The server first collects data on past earthquake disasters. This data includes information such as epicenters, seismic intensity, damage status, and the impact of tsunamis and fires. The collected data is then cleansed and formatted for analysis. It then uses machine learning algorithms and deep learning models to identify risk patterns in the event of an earthquake and build a predictive model. This process uses programming languages ​​and libraries such as Python and TensorFlow.

[0667] 2. Real-time risk prediction

[0668] When the user's device (smart glasses) detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency, it sends the information to a server. The information sent includes the earthquake's seismic intensity, epicenter, and time of occurrence. The server compares the received earthquake information with past data and analyzes the risk in the relevant area in real time.

[0669] 3. Emotion Recognition and Evaluation

[0670] The user device is equipped with an emotion recognition engine that recognizes the user's emotions. The emotion engine acquires and analyzes emotion data from the user's facial expressions, tone of voice, text input, etc., and sends the results to the server. Emotion data includes stress level and degree of impatience. This process utilizes the Emotion Recognition library.

[0671] 4. Emotion-based evacuation route and behavior suggestions

[0672] The server generates optimal evacuation routes and instructions based on the risk analysis results and emotional data from the emotion engine. If the user is in a high-stress state, the server prioritizes routes that provide a sense of security and simple instructions. The server then transmits the generated evacuation routes and instructions to the user's device.

[0673] 5. User Behavior and Feedback

[0674] The user carries out evacuation actions instructed by the device. Using the device's GPS function, the user moves while checking their current location and evacuation destination. The device sends the user's location information and movement trajectory to the server in real time, and the user's evacuation status is tracked.

[0675] Specific examples

[0676] For example, if an earthquake occurs in a certain area and is detected by a device, the earthquake information is sent to a server, where risk analysis is performed in real time. At the same time, the device's emotion engine collects the user's emotional data, which is also sent to the server. If the server determines that the user is in a high-stress state, it selects an evacuation route that prioritizes a sense of security, generates instructions to "proceed slowly and safely," and sends these instructions to the device. The user begins evacuation according to the instructions, and once the evacuation is complete, presses the "Evacuation Complete" button on the device. This information is also sent to the server, and the success or failure of the evacuation is recorded.

[0677] Prompt Sentence Examples

[0678] "Analyze the user's emotional state and suggest evacuation routes based on that data."

[0679] "Consider the user's current location when generating evacuation routes."

[0680] "To address high stress levels in users, prioritize escape routes that provide a sense of security."

[0681] This system not only supports quick and appropriate evacuation behavior during earthquake disasters, but also enables more effective evacuation by taking into account the user's emotional state.

[0682] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0683] Step 1:

[0684] The server collects data on past earthquake disasters. Specifically, it collects data on the epicenter, seismic intensity, damage status, and the impact of tsunamis and fires, and stores it in a database. It then prepares this data for analysis using machine learning algorithms and deep learning models. The input is disaster data from external data sources (such as the Japan Meteorological Agency or disaster databases), and the output is cleansed, formatted, and analyzable data.

[0685] Step 2:

[0686] The server uses machine learning algorithms and deep learning models to learn from the collected earthquake disaster data, identify risk patterns when an earthquake occurs, and build a predictive model. Specifically, the model is trained using programming languages ​​and libraries such as Python and TensorFlow. The input is formatted disaster data, and the output is a risk prediction model when an earthquake occurs.

[0687] Step 3:

[0688] When the device (smart glasses) detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency, it sends that information to the server. The input is the warning data from the earthquake detection device or the Japan Meteorological Agency, and the output is the earthquake information (seismic intensity, epicenter, and time of occurrence) sent to the server.

[0689] Step 4:

[0690] The server compares the received earthquake information with past data and analyzes the risk in the relevant area in real time. The input is earthquake information sent from the terminal, and the output is the real-time risk assessment result. This process uses a deep learning model.

[0691] Step 5:

[0692] The device is equipped with an emotion recognition engine that recognizes the user's emotions. The emotion engine acquires and analyzes emotion data from the user's facial expressions, tone of voice, text input, etc., and sends the results to a server. The input is the user's facial expression data and voice data, and the output is analyzed emotion data (stress level and degree of impatience).

[0693] Step 6:

[0694] The server generates optimal evacuation routes and action instructions by taking into account the risk analysis results as well as emotional data from the emotion engine. If the user is in a high-stress state, the system adjusts to prioritize routes that provide a sense of security and simple instructions. The inputs are real-time risk assessment results and emotional data, and the output is the optimal evacuation route and action instructions.

[0695] Step 7:

[0696] The server sends the generated evacuation route and action instructions to the terminal. The input is the optimal evacuation route and action instructions, and the output is the evacuation route and action instructions sent to the terminal.

[0697] Step 8:

[0698] The user carries out evacuation actions instructed by the device. They move while checking their current location and evacuation destination using the device's GPS function. The device sends the user's location information and movement trajectory to the server in real time, and tracks the user's evacuation status. The input is the user's current location and movement trajectory, and the output is evacuation status data sent to the server.

[0699] Step 9:

[0700] The server checks whether the user has completed evacuation and sends additional instructions or alerts as necessary. The input is real-time evacuation status data and feedback data, and the output is evacuation completion notification and additional instructions.

[0701] 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.

[0702] 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.

[0703] 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.

[0704] [Third embodiment]

[0705] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0706] 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.

[0707] 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).

[0708] 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.

[0709] 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.

[0710] 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).

[0711] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0712] 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.

[0713] 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.

[0714] 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.

[0715] 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.

[0716] 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."

[0717] This invention is a disaster prevention system that analyzes risks in the event of an earthquake and proposes evacuation actions, and provides optimal evacuation routes and action instructions in real time based on past earthquake disaster data. This system is composed of three parties: a server, a terminal, and a user, each of which plays a specific role.

[0718] 1. Data collection and learning

[0719] The server first collects data on past earthquake disasters. This data includes information such as epicenters, seismic intensity, damage status, and the impact of tsunamis and fires. This data is then cleansed and formatted for analysis, after which it is trained using machine learning algorithms and deep learning models. This allows the system to identify various risk patterns in the event of an earthquake and build a predictive model.

[0720] 2. Real-time risk prediction

[0721] When a device (such as a smartphone or tablet) detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency, it sends that information to a server. The server then compares the received earthquake information with past data and analyzes the risk in the relevant area. The analysis takes into account factors such as distance from the epicenter, topographical information, and population density.

[0722] 3. Evacuation routes and suggested actions

[0723] Based on the analysis results, the server calculates the optimal evacuation route. This calculation uses current topographical information and traffic conditions (e.g., traffic congestion information, road closure information). The server then generates specific instructions along with the evacuation route. For example, specific instructions such as "head to the nearest high ground" or "evacuate to a specific evacuation shelter" are generated and sent to the device.

[0724] 4. User Behavior and Feedback

[0725] The user carries out the evacuation actions instructed from the device. Once the evacuation is complete, the user presses the "Evacuation Complete" button on the device, which sends the information to the server. The server receives the user's location information and movement trajectory in real time and tracks the evacuation status. The server also collects user behavior data and evacuation success rate, and uses this information as feedback to improve the accuracy of the system in future risk analysis and the generation of behavioral instructions.

[0726] Examples:

[0727] For example, suppose an earthquake occurs in a certain area and is detected by a device. This information is sent to a server, which compares it with past data and analyzes the risk in that area. If the server determines that there is a risk of a tsunami, it calculates an evacuation route and instructs the user to evacuate to higher ground. This instruction is sent to the device, and the user begins evacuating to higher ground. After completing the evacuation, the user presses the "Evacuation Complete" button on the device, and the information is sent to the server. In this way, quick and specific evacuation instructions can be provided.

[0728] This system aims to support quick and specific evacuation actions in the event of an earthquake disaster, thereby minimizing damage.

[0729] The processing flow will be explained below.

[0730] Step 1:

[0731] The server collects data on past earthquake disasters, including epicenters, seismic intensity, damage, and the impact of tsunamis and fires. This data is obtained from government agencies, university research institutes, disaster-related organizations, and other sources.

[0732] Step 2:

[0733] The server cleanses the collected data, removing irrelevant data, processing missing values, standardizing data formats, and otherwise formatting it into a format that is easy to analyze.

[0734] Step 3:

[0735] The server inputs the formatted data into machine learning algorithms and deep learning models to learn risk patterns in the event of an earthquake, thereby building a predictive model.

[0736] Step 4:

[0737] When a device (such as a smartphone or tablet) receives an earthquake warning from an earthquake detection sensor or the Japan Meteorological Agency, it sends the information to a server, including the earthquake's seismic intensity, epicenter, and time of occurrence.

[0738] Step 5:

[0739] The server compares the received earthquake information with past data and performs real-time risk analysis, taking into account factors such as distance from the epicenter, topographical information, and population density.

[0740] Step 6:

[0741] The server calculates the optimal evacuation route based on the analysis results, taking into account current terrain information and traffic conditions (e.g., traffic congestion, road closures).

[0742] Step 7:

[0743] The server generates specific instructions along with evacuation routes, such as "head to the nearest high ground" or "evacuate to a specific shelter."

[0744] Step 8:

[0745] The server then sends the generated evacuation route and action instructions to the terminal, allowing the user to receive specific evacuation instructions.

[0746] Step 9:

[0747] The user follows the instructions displayed on the device and begins the designated evacuation action, using the device's GPS function to check their current location and evacuation destination as they move.

[0748] Step 10:

[0749] The device transmits the user's location information and movement trajectory to the server in real time, allowing the server to track the user's evacuation status.

[0750] Step 11:

[0751] When the user completes evacuation, they press the "Evacuation Complete" button on their device. The evacuation completion information is sent to the server and recorded.

[0752] Step 12:

[0753] The server collects user behavior data and evacuation success rates, and uses feedback to improve the accuracy of risk analysis and behavioral instructions for future events, thereby continuously improving the effectiveness of the system.

[0754] Example 1

[0755] 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."

[0756] Current earthquake disaster prevention systems do not fully utilize past data, resulting in issues with the accuracy of real-time risk predictions and evacuation instructions. They also lack the functionality to track users' location information and evacuation status, making it difficult to support appropriate evacuation behavior. Furthermore, they lack a mechanism for feeding back evacuation behavior data to improve the accuracy of the system.

[0757] 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.

[0758] In this invention, the server includes a data collection means for collecting and learning past earthquake disaster data, a risk analysis means for analyzing risks in real time based on the learned earthquake disaster data, an evacuation route generation means for generating evacuation routes and action instructions based on the analysis results, and an instruction transmission means for transmitting the generated evacuation routes and action instructions to the communication device. This enables real-time risk prediction and provision of specific and optimal evacuation instructions to the user, thereby improving the accuracy and effectiveness of evacuation actions.

[0759] "Data collection means" refers to the function of collecting and learning from past earthquake disaster data.

[0760] "Risk analysis means" refers to the function of analyzing risk in real time based on learned earthquake disaster data.

[0761] "Evacuation route generation means" refers to a function that generates an evacuation route and action instructions based on the analysis results.

[0762] The "instruction sending means" refers to a function that sends the generated evacuation route and action instructions to the communication device.

[0763] "Location tracking means" refers to the function of receiving real-time location signals and tracking evacuation status.

[0764] "Feedback means" refers to the function of collecting behavioral data and evacuation success rates and using them for future risk analysis and generation of behavioral instructions.

[0765] "Server" refers to a central processing unit that manages and operates functions such as data collection, risk analysis, evacuation route generation, instruction transmission, location tracking, and feedback.

[0766] "Communication device" refers to a user terminal that receives evacuation routes and action instructions sent from the server.

[0767] The present invention is a disaster prevention system that performs risk analysis and evacuation instructions using past earthquake disaster data. This system is composed of a server, terminals, and users, each of which plays a specific role.

[0768] Server Roles and Functions

[0769] The server plays a central role in this system and performs the following functions:

[0770] Data collection methods

[0771] The server collects past earthquake disaster data from public databases on the Internet, earthquake research institutes, the Japan Meteorological Agency, etc. This data includes information such as the epicenter, seismic intensity, damage status, and the impact of tsunamis and fires. Specifically, the server automatically collects data using an API and stores it in an internal database.

[0772] Risk Analysis Tools

[0773] The server cleanses the collected earthquake disaster data and formats it into a format suitable for analysis. It removes duplicates, missing values, and inappropriate values ​​to create a dataset. It then uses machine learning algorithms and deep learning models (e.g., TensorFlow and PyTorch) to train this dataset and build a predictive model for real-time risk forecasting in the event of an earthquake.

[0774] Evacuation route generation method

[0775] The server uses machine learning models to analyze risk in the event of an earthquake and generates optimal evacuation routes based on that risk. It references current topographical information and traffic conditions (e.g., traffic congestion and road closures) using Google Maps API and OpenStreetMap. Along with the evacuation route, it generates specific instructions, such as "head to the nearest high ground" or "evacuate to a specific evacuation shelter."

[0776] Instruction sending means

[0777] The server sends the generated evacuation route and instructions to the device via push notification or SMS, helping users to quickly begin evacuation actions.

[0778] Location Tracking Methods

[0779] The server tracks the user's evacuation status based on real-time location information received from the device, allowing it to check whether the user is evacuating as instructed and send further instructions if necessary.

[0780] Feedback Methods

[0781] The server collects data on users' evacuation behavior and the success rate of evacuation, and uses this information for future risk analysis and generation of action instructions, thereby enabling the system's accuracy to be continually improved.

[0782] Device roles and functions

[0783] The device (smartphone, tablet, etc.) is responsible for the following functions:

[0784] earthquake sensing

[0785] The device detects earthquakes using its built-in acceleration sensor or receives earthquake warnings from the Japan Meteorological Agency.

[0786] Sending information to the server

[0787] If an earthquake is detected, the device immediately sends that information and its current location to the server.

[0788] Receiving and displaying instructions

[0789] The system receives evacuation routes and instructions sent from the server and displays them to the user. It also notifies the user via push notifications and alarm sounds, encouraging them to take prompt action.

[0790] User Roles and Capabilities

[0791] The user takes evacuation action based on the information provided by the terminal.

[0792] Implementing evacuation actions

[0793] The user follows the evacuation instructions from the device and begins evacuating along the designated evacuation route, for example, heading to the nearest high ground or to a specific evacuation shelter.

[0794] Reporting completion of evacuation

[0795] Once the evacuation is complete, press the "Evacuation Complete" button on the device to send the information to the server.

[0796] Specific examples

[0797] For example, if an earthquake occurs in a certain area, the device will detect the earthquake and send that information along with the user's current location to the server. The server will compare this information with past data and analyze the risk in that area. If the server determines that there is a risk of a tsunami, it will calculate the optimal evacuation route and instruct the user to "evacuate to higher ground." This instruction is sent to the device, and the user begins evacuation accordingly. After completing the evacuation, the user presses the "evacuation complete" button on the device, and the information is sent to the server. This series of steps allows for quick and specific evacuation actions to be taken.

[0798] Prompt Sentence Examples

[0799] The following is an example of a prompt sentence that uses a generative AI model to specifically explain the operation of this system:

[0800] "Please explain how the earthquake disaster prevention system works. The system collects data on past earthquake disasters, performs risk predictions in real time, and provides optimal evacuation routes and action instructions. Please explain each processing step in detail."

[0801] The system aims to support quick and specific evacuation actions in the event of an earthquake disaster, thereby minimizing damage.

[0802] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0803] Step 1: Data collection

[0804] The server collects data on past earthquake disasters from public databases on the Internet, earthquake research institutes, the Japan Meteorological Agency, and other sources. This data includes information such as the epicenter, seismic intensity, damage status, and the impact of tsunamis and fires. The collected data is stored in the server's internal database. Specifically, it is automatically collected using an API and obtains data in JSON format. The input data is raw data on earthquake disasters, and the output data is the raw data file before cleansing.

[0805] Step 2: Data cleansing

[0806] The server cleanses the collected data. Specifically, it removes duplicate data and corrects missing or inappropriate values. For example, data showing a seismic intensity of "upper 6" is converted to the numerical value "6." This process converts the data into a format suitable for analysis. The input data is a raw data file, and the output data is a cleansed dataset.

[0807] Step 3: Training the machine learning model

[0808] The server uses the cleansed data to train machine learning algorithms and deep learning models. Libraries used include TensorFlow and PyTorch. The learning algorithms used are random forests and neural networks for risk prediction. This process builds a predictive model for real-time risk forecasting in the event of an earthquake. The input data is the cleansed dataset, and the output data is the trained predictive model.

[0809] Step 4: Earthquake detection and information transmission

[0810] A device (such as a smartphone or tablet) detects an earthquake using its built-in acceleration sensor or receives an earthquake warning from the Japan Meteorological Agency. When an earthquake is detected, the device sends this detection information along with its current location information to a server. The input data is the earthquake detection data and location information, and the output data is the data sent to the server.

[0811] Step 5: Risk analysis

[0812] The server compares the received earthquake information and location information with past data and analyzes the risk of the relevant area. Specifically, it takes into account factors such as distance from the epicenter, topographical information, and population density. This risk analysis uses a trained predictive model. The input data is earthquake information and location information, and the output data is the risk analysis results.

[0813] Step 6: Evacuation route generation and behavior instructions

[0814] The server generates the optimal evacuation route based on the risk analysis results. This generation uses geographic information services such as Google Maps API and OpenStreetMap. It also generates specific action instructions (e.g., "head to the nearest high ground" or "evacuate to a specific evacuation shelter"). The input data are the risk analysis results and current terrain and traffic information, and the output data are the evacuation route and action instructions.

[0815] Step 7: Sending instructions

[0816] The server sends the generated evacuation route and action instructions to the device. This is done using push notifications or SMS. The input data is the evacuation route and action instructions, and the output data is the data sent to the device.

[0817] Step 8: User evacuation behavior

[0818] The user follows the instructions received from the device and begins evacuation along the specified evacuation route. For example, they may head to the nearest high ground or evacuate to a specific evacuation shelter. The input data are instructions from the device, and the output is the actual evacuation behavior.

[0819] Step 9: Evacuation completion report

[0820] When the user completes evacuation, they press the "Evacuation Complete" button on their device to send evacuation completion information to the server. The input data is the evacuation completion information, and the output data is the data to be sent to the server.

[0821] Step 10: Evacuation status tracking and feedback

[0822] The server tracks the user's evacuation status based on the received evacuation completion information and user location information. It also uses the collected evacuation behavior data and evacuation success rate for future risk analysis and the generation of behavioral instructions. The input data are evacuation behavior data and completion information, and the output data is learning data used as feedback.

[0823] The above is a specific operation of each processing step in the disaster recovery system.

[0824] (Application example 1)

[0825] 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."

[0826] During earthquake disasters, it is important to provide routes and instructions for quick and safe evacuation, but current technology makes it difficult to provide optimal evacuation routes and specific instructions for action in real time according to the individual circumstances of each evacuee.In addition, there is no system in place to efficiently support evacuation using autonomous vehicles, which can result in delays in evacuation.To solve this problem, there is a need for a system that can perform risk analysis in real time during earthquake disasters and provide evacuation routes and instructions for action to autonomous vehicles.

[0827] 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.

[0828] In this invention, the server includes a data collection means for collecting and learning past earthquake disaster data, a risk analysis means for analyzing risks in real time based on the learned earthquake disaster data, an evacuation route generation means for generating evacuation routes and action instructions based on the analysis results, an instruction transmission means for transmitting the generated evacuation routes and action instructions to a user terminal, a vehicle control means for controlling an autonomous vehicle to move along the evacuation route when an earthquake occurs, and an information provision means for providing information to users via an in-vehicle display or audio guidance. This makes it possible to provide optimal evacuation routes and specific action instructions according to the individual circumstances of evacuees in the event of an earthquake disaster, and to support quick and safe evacuation using autonomous vehicles.

[0829] The "data collection means" is a system component that collects past earthquake disaster data and uses it for learning.

[0830] The "risk analysis means" is a system component for analyzing earthquake risk in real time based on collected data.

[0831] The "evacuation route generation means" is a system component that generates an optimal evacuation route and specific action instructions based on the results of risk analysis.

[0832] The "instruction transmitting means" is a system component for transmitting the generated evacuation route and action instructions to the user terminal.

[0833] The "vehicle control means" is a system component that controls autonomous vehicles in the event of an earthquake and moves them along evacuation routes.

[0834] The "information provision means" is a system component that provides evacuation information to users using in-vehicle displays, voice guidance, etc.

[0835] The "location tracking means" is a system component for receiving real-time location information from user terminals and tracking the evacuation situation.

[0836] The "feedback means" is a system component that collects user behavior data and evacuation success rates and uses them for future risk analysis and generation of behavioral instructions.

[0837] System Configuration

[0838] This invention is a system that collects past earthquake disaster data, performs risk analysis in real time, and provides optimal evacuation routes and action instructions. This system consists of three parties: a server, a terminal, and a user. In particular, we focus on an application example realized by a dedicated application installed in an autonomous vehicle.

[0839] Server Roles

[0840] The server first collects data on past earthquake disasters, cleansing the data, and then uses machine learning algorithms and deep learning models to learn from it. This allows it to identify risk patterns when an earthquake occurs and build a predictive model. Next, when it receives information from a device that detected an earthquake, it compares that information with past data to analyze the risk in the relevant area. The analysis takes into account data such as distance from the epicenter, topographical information, and population density. It then calculates the optimal evacuation route based on the risk analysis results and sends it to the device.

[0841] Device Role

[0842] The terminals consist of common mobile devices such as smartphones and tablets, but in this case they also include on-board computers installed in self-driving vehicles. When an earthquake is detected or an earthquake warning is received from the Japan Meteorological Agency, the information is sent to a server. When evacuation routes and specific instructions for action are sent from the server, the terminal communicates these to the user via the in-vehicle display and voice guidance system. Furthermore, the terminal also has the function of controlling the self-driving vehicle along the evacuation route using vehicle control means.

[0843] User Roles

[0844] The user begins and executes evacuation actions according to instructions from the device. When the evacuation is complete, the user presses the "Evacuation Complete" button on the device, and the information is sent to the server. The server collects the user's behavioral data and evacuation success rate, and uses this data for future risk analysis and the generation of behavioral instructions.

[0845] Hardware and Software Used

[0846] Server: Python, machine learning libraries (Scikit-Learn, TensorFlow, etc.), database (PostgreSQL)

[0847] Devices: Smartphones, tablets, in-vehicle computers for autonomous vehicles, displays, voice guidance systems

[0848] Data collection: Japan Meteorological Agency Earthquake Alert API, USGS Earthquake API

[0849] Specific examples

[0850] For example, suppose an earthquake occurs in a certain area and is detected by a device in an autonomous vehicle. This information is sent to a server, where it is compared with past data to analyze the risk in that area. If it determines that there is a risk of a tsunami, the server calculates an evacuation route and automatically guides the vehicle to higher ground, allowing the user to complete the evacuation safely.

[0851] Prompt Sentence Examples

[0852] An earthquake has occurred. Your current location is longitude 139.70, latitude 35.69. Please calculate the safest evacuation route and guide you to your destination.

[0853] In this way, the form for implementing the invention can provide optimal evacuation routes and specific instructions for actions in real time according to the individual circumstances of evacuees during earthquake disasters, and can also support quick and safe evacuation using autonomous vehicles.

[0854] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0855] Step 1:

[0856] The server collects data on past earthquake disasters. The input is earthquake data obtained from various APIs, and the output is a cleansed dataset. Data processing includes filling in incomplete data and processing outliers.

[0857] Step 2:

[0858] The server uses the cleansed data to train machine learning algorithms or deep learning models. The input is the cleansed dataset and the output is the trained model. Data operations include feature extraction and pattern identification.

[0859] Step 3:

[0860] The device detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency. The input is sensor data and earthquake warnings from the Japan Meteorological Agency API, and the output is a notification of an earthquake occurrence. Specific operations are triggered by sensors and communication modules on the device.

[0861] Step 4:

[0862] The terminal sends earthquake information to the server. The input is a notification of the earthquake occurrence, and the output is a transmission request to the server. Here, the terminal's network communication function is used.

[0863] Step 5:

[0864] The server compares the received earthquake information with past data and analyzes the risk in the relevant area. The input is earthquake information and a trained model, and the output is the risk analysis results. Data calculations take into account the distance from the epicenter and topographical information.

[0865] Step 6:

[0866] The server calculates the optimal evacuation route based on the risk analysis results and generates action instructions. The input is the risk analysis results, and the output is the evacuation route and action instructions. Specific operations include real-time traffic situation analysis using an algorithm.

[0867] Step 7:

[0868] The server sends the generated evacuation route and action instructions to the terminal. The input is the evacuation route and action instructions, and the output is a transmission request. The terminal's communication module is used again.

[0869] Step 8:

[0870] The terminal receives the evacuation route and action instructions from the server and provides them to the user via an in-car display or voice guidance. The input is the evacuation route and action instructions, and the output is the display and voice guidance. The in-car system plays an important role here.

[0871] Step 9:

[0872] The terminal controls the autonomous vehicle according to the evacuation route. The input is evacuation route information, and the output is vehicle control commands. Specific operations include route optimization by the navigation system and control of the drive-by-wire system.

[0873] Step 10:

[0874] The user presses the "Evacuation Complete" button on the device to notify that the evacuation is complete. The input is the user's touch operation, and the output is a notification of evacuation completion to the server.

[0875] Step 11:

[0876] The server receives evacuation completion notifications from users and records the user's behavioral data and evacuation success rate. The input is the evacuation completion notification, and the output is a record in the database. This will be used as a feedback tool for the next risk analysis.

[0877] Step 12:

[0878] The server uses feedback mechanisms to generate future risk analyses and action instructions. The input is the previous evacuation data, and the output is an updated predictive model. Generative AI models and prompts are used here.

[0879] 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.

[0880] This invention is a disaster prevention system that analyzes risks and suggests evacuation actions for earthquake disasters, providing optimal evacuation routes and action instructions in real time based on past earthquake disaster data. By combining this system with an emotion engine, it is possible to take the user's emotions into consideration and provide more accurate and effective evacuation instructions. This system consists of three parties: a server, a terminal, and a user, each of which plays a specific role.

[0881] 1. Data collection and learning

[0882] The server first collects data on past earthquake disasters. This data includes information such as epicenters, seismic intensity, damage status, and the impact of tsunamis and fires. This data is then cleansed and formatted for analysis. It is then trained using machine learning algorithms and deep learning models to identify risk patterns in the event of an earthquake and build a predictive model.

[0883] 2. Real-time risk prediction

[0884] When a device (such as a smartphone or tablet) detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency, it sends that information to a server. The information sent includes the earthquake's seismic intensity, epicenter, and time of occurrence. The server compares the received earthquake information with past data and analyzes the risk in the relevant area in real time.

[0885] 3. Emotion Recognition and Evaluation

[0886] The device is equipped with an emotion engine that recognizes the user's emotions. The emotion engine acquires and analyzes emotion data from the user's facial expressions, tone of voice, text input, etc., and sends the results to a server. Emotion data includes stress levels and levels of impatience.

[0887] 4. Emotion-based evacuation route and behavior suggestions

[0888] The server generates optimal evacuation routes and instructions based on the risk analysis results and emotional data from the emotion engine. If the user is in a high-stress state, the server prioritizes routes that provide a sense of security and simple instructions. The server then transmits the generated evacuation routes and instructions to the device.

[0889] 5. User Behavior and Feedback

[0890] The user carries out evacuation actions instructed by the device. They move while checking their current location and evacuation destination using the device's GPS function. The device sends the user's location information and movement trajectory to the server in real time, and the user's evacuation status is tracked.

[0891] Examples:

[0892] For example, if an earthquake occurs in a certain area and is detected by a device, the earthquake information is sent to a server, where risk analysis is performed in real time. At the same time, the device's emotion engine collects the user's emotional data, which is also sent to the server. If the server determines that the user is in a high-stress state, it selects an evacuation route that prioritizes a sense of security, generates instructions to "proceed slowly and safely," and sends these instructions to the device. The user begins evacuation according to the instructions, and once the evacuation is complete, presses the "Evacuation Complete" button on the device. This information is also sent to the server, and the success or failure of the evacuation is recorded.

[0893] This system not only supports quick and appropriate evacuation behavior during earthquake disasters, but also enables more effective evacuation by taking into account the user's emotional state.

[0894] The processing flow will be explained below.

[0895] Step 1:

[0896] The server collects data on past earthquake disasters, including epicenters, seismic intensity, damage, and the impact of tsunamis and fires. This data is obtained from government agencies, university research institutes, disaster-related organizations, and other sources.

[0897] Step 2:

[0898] The server cleanses the collected data and formats it in a format suitable for analysis, removing irrelevant data, handling missing values, and standardizing data formats.

[0899] Step 3:

[0900] The server uses the formatted data to train machine learning algorithms and deep learning models, identifying risk patterns in the event of an earthquake and building a predictive model.

[0901] Step 4:

[0902] When a device (smartphone or tablet) detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency, it sends that information, including the earthquake's magnitude, epicenter, and time of occurrence, to a server.

[0903] Step 5:

[0904] The server compares the received earthquake information with past data and performs real-time risk analysis, taking into account factors such as distance from the epicenter, topographical information, and population density.

[0905] Step 6:

[0906] The device's emotion engine acquires and analyzes emotional data from the user's facial expressions, tone of voice, text input, etc. The analysis results in information such as the user's stress level and degree of impatience.

[0907] Step 7:

[0908] The device then transmits the acquired emotional data, including the level of stress and impatience, to the server.

[0909] Step 8:

[0910] The server generates optimal evacuation routes and instructions based on risk analysis results and emotional data. If the user's stress level is high, the server prioritizes simpler and more reassuring routes.

[0911] Step 9:

[0912] The server then sends the generated evacuation route and instructions to the device, such as "head to the nearest high ground" or "evacuate to a designated evacuation shelter."

[0913] Step 10:

[0914] The user follows the instructions displayed on the device and begins the designated evacuation action, using the device's GPS function to check their current location and evacuation destination as they move.

[0915] Step 11:

[0916] The device transmits the user's location information and movement trajectory to the server in real time, allowing the server to track the user's evacuation status.

[0917] Step 12:

[0918] When the user completes evacuation, they press the "Evacuation Complete" button on their device. The evacuation completion information is sent to the server and recorded.

[0919] Step 13:

[0920] The server collects user behavior data and evacuation success rates, and uses feedback to improve the accuracy of risk analysis and behavioral instructions for future events, thereby continuously improving the effectiveness of the system.

[0921] Example 2

[0922] 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."

[0923] Conventional disaster prevention systems are limited to analyzing earthquake disaster risks and suggesting evacuation routes, and do not consider the user's emotional state, which can increase panic and stress during an emergency. Furthermore, evacuation route instructions are generalized, making it difficult to provide optimal instructions tailored to the user's individual situation and emotions. This can lead to ineffective evacuation behavior and reduced safety.

[0924] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a data collection means for collecting and learning past earthquake data, a risk analysis means for analyzing risks in real time based on the learned earthquake data, an emotion recognition means for acquiring user emotion data, an evacuation route generation means for analyzing the emotion data and integrating it with the risk analysis results to generate an evacuation route and action instructions, and an instruction transmission means for transmitting the generated evacuation route and action instructions to the user terminal. This makes it possible to provide an appropriate and effective evacuation route and action instructions that take into account the user's emotional state, thereby reducing stress in an emergency and improving evacuation safety.

[0925] "Data collection means" refers to the means for collecting past earthquake data and formatting it into a format suitable for analysis and learning.

[0926] "Risk analysis means" refers to a means for analyzing the risk of an earthquake occurring in real time based on collected and learned earthquake data.

[0927] The "emotion recognition means" is a means for analyzing the user's facial expression, tone of voice, text input, etc., and acquiring the user's emotional data.

[0928] The "evacuation route generation means" is a means for generating the optimal evacuation route and action instructions for the user based on the risk analysis results and emotion data.

[0929] The "instruction transmission means" is a means for transmitting the generated evacuation route and action instructions to the user terminal.

[0930] The "location tracking means" is a means for receiving real-time location information from the user terminal and tracking the evacuation status of the user.

[0931] The "feedback means" is a means for collecting user behavior data and evacuation success rates, and using the data for future risk analysis and generation of behavioral instructions.

[0932] This invention is a disaster prevention system that analyzes risks and suggests evacuation actions for earthquake disasters, and provides optimal evacuation routes and action instructions in real time based on past earthquake data and user emotion data. This system is composed of three parties: a server, a terminal, and a user, each of which plays a specific role.

[0933] First, the server has a data collection tool for collecting past earthquake data. This tool collects earthquake data using APIs from the Japan Meteorological Agency and other earthquake information providers. The collected data is cleansed and formatted for analysis using data processing libraries such as Pandas and NumPy. Then, a machine learning model is trained using TensorFlow and PyTorch. This model is used to identify risk patterns and make predictions when earthquakes occur.

[0934] Next, when a device (smartphone or tablet) detects an earthquake with its sensor or receives an earthquake warning from the Japan Meteorological Agency, earthquake information is sent to a server. The information sent includes the epicenter, seismic intensity, and time of occurrence. The server compares this information with past data and performs real-time risk analysis using cloud analysis services such as Google Cloud and Azure AI.

[0935] The device is also equipped with an emotion engine that recognizes the user's emotions. The emotion engine uses tools such as OpenCV, Emotion API, and Watson Tone Analyzer to acquire and analyze emotional data from the user's facial expressions, tone of voice, and text input. The resulting data, such as the user's stress level and degree of impatience, is sent to the server.

[0936] The server integrates the risk analysis results with the emotion data to generate the optimal evacuation route and behavioral instructions. For example, if the user is in a high-stress state, an evacuation route that prioritizes a sense of security will be selected, and instructions such as "proceed slowly and safely." These instructions are then sent to the device and provided to the user.

[0937] The user follows instructions from the device to carry out evacuation. Using the device's GPS function, the user moves while checking their current location and evacuation destination. The device sends the user's location information and movement trajectory to the server in real time, and the user's evacuation status is tracked.

[0938] As a concrete example, consider the case where a magnitude 7 earthquake occurs in a certain area and is detected by a device. At this time, earthquake information is sent to the server, and risk analysis is performed in real time. At the same time, the device's emotion engine collects the user's emotional data and detects that the user is in a high-stress state. Based on this, the server generates an instruction to "select an evacuation route that prioritizes a sense of security" and sends this to the device. The user begins evacuation in accordance with this instruction, and once the evacuation is complete, they press the "Evacuation Complete" button on the device, sending feedback to the server that the evacuation was successful.

[0939] An example of a prompt sentence is, "Please explain the real-time processing of a system that takes into account the user's emotions and suggests the optimal evacuation route when an earthquake occurs."

[0940] In this way, the present invention not only supports quick and appropriate evacuation behavior in the event of an earthquake disaster, but also realizes more effective evacuation by taking into account the user's emotional state.

[0941] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0942] Step 1:

[0943] The server retrieves past earthquake data.

[0944] Input: Collect earthquake data from the APIs of earthquake information providers. Specifically, access the APIs of the Japan Meteorological Agency and earthquake information providers.

[0945] Data processing: Receive collected data in JSON format and use the Pandas library to format it appropriately. Cleanse unnecessary information and missing data.

[0946] Output: A database of cleansed seismic data is generated.

[0947] Step 2:

[0948] The server trains a machine learning model based on the data.

[0949] Input: Formatted historical earthquake data. Specifically, features such as epicenter, seismic intensity, and damage status are used.

[0950] Data Computing: Using TensorFlow and PyTorch, we train an earthquake risk prediction model and identify risk patterns in the event of an earthquake based on historical earthquake data.

[0951] Output: A trained earthquake risk prediction model.

[0952] Step 3:

[0953] The device detects an earthquake or receives an earthquake alert.

[0954] Input: Data detecting earthquake vibrations from device sensors or notifications from earthquake warning systems.

[0955] Data processing: Obtain earthquake information (epicenter, seismic intensity, time of occurrence).

[0956] Output: Earthquake information is sent from the device to the server.

[0957] Step 4:

[0958] The server performs real-time risk analysis.

[0959] Input: Earthquake information sent from the device, specifically, data on the epicenter, seismic intensity, and occurrence time.

[0960] Data calculation: Analyze received earthquake information in real time and compare it with past data. Analyze risks using cloud analysis services from Google Cloud and Azure AI.

[0961] Output: Real-time risk analysis results are obtained.

[0962] Step 5:

[0963] The device collects the user's emotional data.

[0964] Input: Facial expression data from the camera, tone of voice from the microphone, and text input.

[0965] Data processing: Analyze these data using OpenCV, Emotion API, and Watson Tone Analyzer to obtain emotion data.

[0966] Output: Emotion data is obtained and sent to the server.

[0967] Step 6:

[0968] The server generates evacuation routes and action instructions taking into account emotion data.

[0969] Input: Real-time risk analysis results and sentiment data.

[0970] Data calculation: By integrating risk analysis results with emotional data, the system uses the Google Maps API to generate the optimal evacuation route based on the user's emotional state. For example, if the user is in a high-stress state, the system will select a simple and reassuring route.

[0971] Output: Optimal evacuation routes and action instructions are generated.

[0972] Step 7:

[0973] The server sends the generated evacuation route and action instructions to the terminal.

[0974] Input: Optimal evacuation route and action instructions.

[0975] Data processing: Format the data into JSON format and send it to the terminal via an HTTP request.

[0976] Output: The device receives the required information.

[0977] Step 8:

[0978] The user performs evacuation actions.

[0979] Input: Evacuation route and action instructions received from the terminal.

[0980] Specific actions: Use the GPS function to check your current location and follow a safe evacuation route.

[0981] Output: The user safely completes the evacuation.

[0982] Step 9:

[0983] The device tracks the user's evacuation status in real time.

[0984] Input: User location and movement trajectory.

[0985] Data processing: GPS data is acquired in real time and sent to the server.

[0986] Output: Evacuation status is tracked on the server.

[0987] Step 10:

[0988] When the user has completed the evacuation, he or she presses the "Evacuation Complete" button on the terminal.

[0989] Input: User presses the "Evacuation Complete" button.

[0990] Data processing: Send information about the completion of evacuation to the server.

[0991] Output: The server records a successful evacuation.

[0992] These are the specific processing steps of the program for this system, which makes it possible to support effective evacuation while taking into consideration the user's emotions.

[0993] (Application example 2)

[0994] 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."

[0995] Although systems already exist to support quick and appropriate evacuation behavior during earthquake disasters, previous systems did not take into account the user's emotional state, which can result in increased stress and anxiety. Furthermore, evacuation routes are provided based on a general approach, which does not provide appropriate instructions tailored to the user's individual emotional state. Therefore, there is a need for a system that allows users to evacuate with peace of mind.

[0996] The identification process by the identification 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 a data collection means for collecting and learning past earthquake disaster data, a risk analysis means for analyzing risks in real time based on the learned earthquake disaster data, an evacuation route generation means for generating evacuation routes and action instructions based on the analysis results, and an emotion analysis means for collecting user emotion data and reflecting it in the generation of evacuation routes. This makes it possible to provide an optimal evacuation route that takes the user's emotional state into consideration, realizing a system that allows users to evacuate quickly and safely.

[0997] "Data collection means" is a function that collects data on past earthquake disasters and formats the data for learning purposes.

[0998] The "risk analysis means" is a function that analyzes the risk in the event of an earthquake in real time based on learned earthquake disaster data.

[0999] The "evacuation route generation means" is a function that generates an optimal evacuation route and action instructions for the user based on the results of risk analysis.

[1000] The "instruction sending means" is a function that sends the generated evacuation route and action instructions to the user terminal.

[1001] The "emotion analysis means" is a function that collects the user's emotional data (stress level and degree of anxiety) and reflects that data in generating an evacuation route.

[1002] The "location tracking means" is a function that receives real-time location information from the user terminal and tracks the evacuation status of the user.

[1003] The "feedback means" is a function that collects user behavior data and evacuation success rates, and uses them for future risk analysis and generation of behavioral instructions.

[1004] The "emotion data analysis means" is a function that uses an emotion recognition engine installed on the user's terminal to analyze the user's stress level and degree of anxiety, and reflects this in generating an evacuation route.

[1005] This invention is a system that takes into consideration the emotional state of a user in the event of an earthquake disaster and provides optimal evacuation routes and action instructions. Specific embodiments of this system will be described below.

[1006] 1. Data collection and learning

[1007] The server first collects data on past earthquake disasters. This data includes information such as epicenters, seismic intensity, damage status, and the impact of tsunamis and fires. The collected data is then cleansed and formatted for analysis. It then uses machine learning algorithms and deep learning models to identify risk patterns in the event of an earthquake and build a predictive model. This process uses programming languages ​​and libraries such as Python and TensorFlow.

[1008] 2. Real-time risk prediction

[1009] When the user's device (smart glasses) detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency, it sends the information to a server. The information sent includes the earthquake's seismic intensity, epicenter, and time of occurrence. The server compares the received earthquake information with past data and analyzes the risk in the relevant area in real time.

[1010] 3. Emotion Recognition and Evaluation

[1011] The user device is equipped with an emotion recognition engine that recognizes the user's emotions. The emotion engine acquires and analyzes emotion data from the user's facial expressions, tone of voice, text input, etc., and sends the results to the server. Emotion data includes stress level and degree of impatience. This process utilizes the Emotion Recognition library.

[1012] 4. Emotion-based evacuation route and behavior suggestions

[1013] The server generates optimal evacuation routes and instructions based on the risk analysis results and emotional data from the emotion engine. If the user is in a high-stress state, the server prioritizes routes that provide a sense of security and simple instructions. The server then transmits the generated evacuation routes and instructions to the user's device.

[1014] 5. User Behavior and Feedback

[1015] The user carries out evacuation actions instructed by the device. Using the device's GPS function, the user moves while checking their current location and evacuation destination. The device sends the user's location information and movement trajectory to the server in real time, and the user's evacuation status is tracked.

[1016] Specific examples

[1017] For example, if an earthquake occurs in a certain area and is detected by a device, the earthquake information is sent to a server, where risk analysis is performed in real time. At the same time, the device's emotion engine collects the user's emotional data, which is also sent to the server. If the server determines that the user is in a high-stress state, it selects an evacuation route that prioritizes a sense of security, generates instructions to "proceed slowly and safely," and sends these instructions to the device. The user begins evacuation according to the instructions, and once the evacuation is complete, presses the "Evacuation Complete" button on the device. This information is also sent to the server, and the success or failure of the evacuation is recorded.

[1018] Prompt Sentence Examples

[1019] "Analyze the user's emotional state and suggest evacuation routes based on that data."

[1020] "Consider the user's current location when generating evacuation routes."

[1021] "To address high stress levels in users, prioritize escape routes that provide a sense of security."

[1022] This system not only supports quick and appropriate evacuation behavior during earthquake disasters, but also enables more effective evacuation by taking into account the user's emotional state.

[1023] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1024] Step 1:

[1025] The server collects data on past earthquake disasters. Specifically, it collects data on the epicenter, seismic intensity, damage status, and the impact of tsunamis and fires, and stores it in a database. It then prepares this data for analysis using machine learning algorithms and deep learning models. The input is disaster data from external data sources (such as the Japan Meteorological Agency or disaster databases), and the output is cleansed, formatted, and analyzable data.

[1026] Step 2:

[1027] The server uses machine learning algorithms and deep learning models to learn from the collected earthquake disaster data, identify risk patterns when an earthquake occurs, and build a predictive model. Specifically, the model is trained using programming languages ​​and libraries such as Python and TensorFlow. The input is formatted disaster data, and the output is a risk prediction model when an earthquake occurs.

[1028] Step 3:

[1029] When the device (smart glasses) detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency, it sends that information to the server. The input is the warning data from the earthquake detection device or the Japan Meteorological Agency, and the output is the earthquake information (seismic intensity, epicenter, and time of occurrence) sent to the server.

[1030] Step 4:

[1031] The server compares the received earthquake information with past data and analyzes the risk in the relevant area in real time. The input is earthquake information sent from the terminal, and the output is the real-time risk assessment result. This process uses a deep learning model.

[1032] Step 5:

[1033] The device is equipped with an emotion recognition engine that recognizes the user's emotions. The emotion engine acquires and analyzes emotion data from the user's facial expressions, tone of voice, text input, etc., and sends the results to a server. The input is the user's facial expression data and voice data, and the output is analyzed emotion data (stress level and degree of impatience).

[1034] Step 6:

[1035] The server generates optimal evacuation routes and action instructions by taking into account the risk analysis results as well as emotional data from the emotion engine. If the user is in a high-stress state, the system adjusts to prioritize routes that provide a sense of security and simple instructions. The inputs are real-time risk assessment results and emotional data, and the output is the optimal evacuation route and action instructions.

[1036] Step 7:

[1037] The server sends the generated evacuation route and action instructions to the terminal. The input is the optimal evacuation route and action instructions, and the output is the evacuation route and action instructions sent to the terminal.

[1038] Step 8:

[1039] The user carries out evacuation actions instructed by the device. They move while checking their current location and evacuation destination using the device's GPS function. The device sends the user's location information and movement trajectory to the server in real time, and tracks the user's evacuation status. The input is the user's current location and movement trajectory, and the output is evacuation status data sent to the server.

[1040] Step 9:

[1041] The server checks whether the user has completed evacuation and sends additional instructions or alerts as necessary. The input is real-time evacuation status data and feedback data, and the output is evacuation completion notification and additional instructions.

[1042] 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.

[1043] 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.

[1044] 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.

[1045] [Fourth embodiment]

[1046] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1047] 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.

[1048] 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).

[1049] 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.

[1050] 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.

[1051] 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).

[1052] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1053] 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.

[1054] 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.

[1055] 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.

[1056] 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.

[1057] 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.

[1058] 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."

[1059] This invention is a disaster prevention system that analyzes risks in the event of an earthquake and proposes evacuation actions, and provides optimal evacuation routes and action instructions in real time based on past earthquake disaster data. This system is composed of three parties: a server, a terminal, and a user, each of which plays a specific role.

[1060] 1. Data collection and learning

[1061] The server first collects data on past earthquake disasters. This data includes information such as epicenters, seismic intensity, damage status, and the impact of tsunamis and fires. This data is then cleansed and formatted for analysis, after which it is trained using machine learning algorithms and deep learning models. This allows the system to identify various risk patterns in the event of an earthquake and build a predictive model.

[1062] 2. Real-time risk prediction

[1063] When a device (such as a smartphone or tablet) detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency, it sends that information to a server. The server then compares the received earthquake information with past data and analyzes the risk in the relevant area. The analysis takes into account factors such as distance from the epicenter, topographical information, and population density.

[1064] 3. Evacuation routes and suggested actions

[1065] Based on the analysis results, the server calculates the optimal evacuation route. This calculation uses current topographical information and traffic conditions (e.g., traffic congestion information, road closure information). The server then generates specific instructions along with the evacuation route. For example, specific instructions such as "head to the nearest high ground" or "evacuate to a specific evacuation shelter" are generated and sent to the device.

[1066] 4. User Behavior and Feedback

[1067] The user carries out the evacuation actions instructed from the device. Once the evacuation is complete, the user presses the "Evacuation Complete" button on the device, which sends the information to the server. The server receives the user's location information and movement trajectory in real time and tracks the evacuation status. The server also collects user behavior data and evacuation success rate, and uses this information as feedback to improve the accuracy of the system in future risk analysis and the generation of behavioral instructions.

[1068] Examples:

[1069] For example, suppose an earthquake occurs in a certain area and is detected by a device. This information is sent to a server, which compares it with past data and analyzes the risk in that area. If the server determines that there is a risk of a tsunami, it calculates an evacuation route and instructs the user to evacuate to higher ground. This instruction is sent to the device, and the user begins evacuating to higher ground. After completing the evacuation, the user presses the "Evacuation Complete" button on the device, and the information is sent to the server. In this way, quick and specific evacuation instructions can be provided.

[1070] This system aims to support quick and specific evacuation actions in the event of an earthquake disaster, thereby minimizing damage.

[1071] The processing flow will be explained below.

[1072] Step 1:

[1073] The server collects data on past earthquake disasters, including epicenters, seismic intensity, damage, and the impact of tsunamis and fires. This data is obtained from government agencies, university research institutes, disaster-related organizations, and other sources.

[1074] Step 2:

[1075] The server cleanses the collected data, removing irrelevant data, processing missing values, standardizing data formats, and otherwise formatting it into a format that is easy to analyze.

[1076] Step 3:

[1077] The server inputs the formatted data into machine learning algorithms and deep learning models to learn risk patterns in the event of an earthquake, thereby building a predictive model.

[1078] Step 4:

[1079] When a device (such as a smartphone or tablet) receives an earthquake warning from an earthquake detection sensor or the Japan Meteorological Agency, it sends the information to a server, including the earthquake's seismic intensity, epicenter, and time of occurrence.

[1080] Step 5:

[1081] The server compares the received earthquake information with past data and performs real-time risk analysis, taking into account factors such as distance from the epicenter, topographical information, and population density.

[1082] Step 6:

[1083] The server calculates the optimal evacuation route based on the analysis results, taking into account current terrain information and traffic conditions (e.g., traffic congestion, road closures).

[1084] Step 7:

[1085] The server generates specific instructions along with evacuation routes, such as "head to the nearest high ground" or "evacuate to a specific shelter."

[1086] Step 8:

[1087] The server then sends the generated evacuation route and action instructions to the terminal, allowing the user to receive specific evacuation instructions.

[1088] Step 9:

[1089] The user follows the instructions displayed on the device and begins the designated evacuation action, using the device's GPS function to check their current location and evacuation destination as they move.

[1090] Step 10:

[1091] The device transmits the user's location information and movement trajectory to the server in real time, allowing the server to track the user's evacuation status.

[1092] Step 11:

[1093] When the user completes evacuation, they press the "Evacuation Complete" button on their device. The evacuation completion information is sent to the server and recorded.

[1094] Step 12:

[1095] The server collects user behavior data and evacuation success rates, and uses feedback to improve the accuracy of risk analysis and behavioral instructions for future events, thereby continuously improving the effectiveness of the system.

[1096] Example 1

[1097] 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."

[1098] Current earthquake disaster prevention systems do not fully utilize past data, resulting in issues with the accuracy of real-time risk predictions and evacuation instructions. They also lack the functionality to track users' location information and evacuation status, making it difficult to support appropriate evacuation behavior. Furthermore, they lack a mechanism for feeding back evacuation behavior data to improve the accuracy of the system.

[1099] 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.

[1100] In this invention, the server includes a data collection means for collecting and learning past earthquake disaster data, a risk analysis means for analyzing risks in real time based on the learned earthquake disaster data, an evacuation route generation means for generating evacuation routes and action instructions based on the analysis results, and an instruction transmission means for transmitting the generated evacuation routes and action instructions to the communication device. This enables real-time risk prediction and provision of specific and optimal evacuation instructions to the user, thereby improving the accuracy and effectiveness of evacuation actions.

[1101] "Data collection means" refers to the function of collecting and learning from past earthquake disaster data.

[1102] "Risk analysis means" refers to the function of analyzing risk in real time based on learned earthquake disaster data.

[1103] "Evacuation route generation means" refers to a function that generates an evacuation route and action instructions based on the analysis results.

[1104] The "instruction sending means" refers to a function that sends the generated evacuation route and action instructions to the communication device.

[1105] "Location tracking means" refers to the function of receiving real-time location signals and tracking evacuation status.

[1106] "Feedback means" refers to the function of collecting behavioral data and evacuation success rates and using them for future risk analysis and generation of behavioral instructions.

[1107] "Server" refers to a central processing unit that manages and operates functions such as data collection, risk analysis, evacuation route generation, instruction transmission, location tracking, and feedback.

[1108] "Communication device" refers to a user terminal that receives evacuation routes and action instructions sent from the server.

[1109] The present invention is a disaster prevention system that performs risk analysis and evacuation instructions using past earthquake disaster data. This system is composed of a server, terminals, and users, each of which plays a specific role.

[1110] Server Roles and Functions

[1111] The server plays a central role in this system and performs the following functions:

[1112] Data collection methods

[1113] The server collects past earthquake disaster data from public databases on the Internet, earthquake research institutes, the Japan Meteorological Agency, etc. This data includes information such as the epicenter, seismic intensity, damage status, and the impact of tsunamis and fires. Specifically, the server automatically collects data using an API and stores it in an internal database.

[1114] Risk Analysis Tools

[1115] The server cleanses the collected earthquake disaster data and formats it into a format suitable for analysis. It removes duplicates, missing values, and inappropriate values ​​to create a dataset. It then uses machine learning algorithms and deep learning models (e.g., TensorFlow and PyTorch) to train this dataset and build a predictive model for real-time risk forecasting in the event of an earthquake.

[1116] Evacuation route generation method

[1117] The server uses machine learning models to analyze risk in the event of an earthquake and generates optimal evacuation routes based on that risk. It references current topographical information and traffic conditions (e.g., traffic congestion and road closures) using Google Maps API and OpenStreetMap. Along with the evacuation route, it generates specific instructions, such as "head to the nearest high ground" or "evacuate to a specific evacuation shelter."

[1118] Instruction sending means

[1119] The server sends the generated evacuation route and instructions to the device via push notification or SMS, helping users to quickly begin evacuation actions.

[1120] Location Tracking Methods

[1121] The server tracks the user's evacuation status based on real-time location information received from the device, allowing it to check whether the user is evacuating as instructed and send further instructions if necessary.

[1122] Feedback Methods

[1123] The server collects data on users' evacuation behavior and the success rate of evacuation, and uses this information for future risk analysis and generation of action instructions, thereby enabling the system's accuracy to be continually improved.

[1124] Device roles and functions

[1125] The device (smartphone, tablet, etc.) is responsible for the following functions:

[1126] earthquake sensing

[1127] The device detects earthquakes using its built-in acceleration sensor or receives earthquake warnings from the Japan Meteorological Agency.

[1128] Sending information to the server

[1129] If an earthquake is detected, the device immediately sends that information and its current location to the server.

[1130] Receiving and displaying instructions

[1131] The system receives evacuation routes and instructions sent from the server and displays them to the user. It also notifies the user via push notifications and alarm sounds, encouraging them to take prompt action.

[1132] User Roles and Capabilities

[1133] The user takes evacuation action based on the information provided by the terminal.

[1134] Implementing evacuation actions

[1135] The user follows the evacuation instructions from the device and begins evacuating along the designated evacuation route, for example, heading to the nearest high ground or to a specific evacuation shelter.

[1136] Reporting completion of evacuation

[1137] Once the evacuation is complete, press the "Evacuation Complete" button on the device to send the information to the server.

[1138] Specific examples

[1139] For example, if an earthquake occurs in a certain area, the device will detect the earthquake and send that information along with the user's current location to the server. The server will compare this information with past data and analyze the risk in that area. If the server determines that there is a risk of a tsunami, it will calculate the optimal evacuation route and instruct the user to "evacuate to higher ground." This instruction is sent to the device, and the user begins evacuation accordingly. After completing the evacuation, the user presses the "evacuation complete" button on the device, and the information is sent to the server. This series of steps allows for quick and specific evacuation actions to be taken.

[1140] Prompt Sentence Examples

[1141] The following is an example of a prompt sentence that uses a generative AI model to specifically explain the operation of this system:

[1142] "Please explain how the earthquake disaster prevention system works. The system collects data on past earthquake disasters, performs risk predictions in real time, and provides optimal evacuation routes and action instructions. Please explain each processing step in detail."

[1143] The system aims to support quick and specific evacuation actions in the event of an earthquake disaster, thereby minimizing damage.

[1144] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1145] Step 1: Data collection

[1146] The server collects data on past earthquake disasters from public databases on the Internet, earthquake research institutes, the Japan Meteorological Agency, and other sources. This data includes information such as the epicenter, seismic intensity, damage status, and the impact of tsunamis and fires. The collected data is stored in the server's internal database. Specifically, it is automatically collected using an API and obtains data in JSON format. The input data is raw data on earthquake disasters, and the output data is the raw data file before cleansing.

[1147] Step 2: Data cleansing

[1148] The server cleanses the collected data. Specifically, it removes duplicate data and corrects missing or inappropriate values. For example, data showing a seismic intensity of "upper 6" is converted to the numerical value "6." This process converts the data into a format suitable for analysis. The input data is a raw data file, and the output data is a cleansed dataset.

[1149] Step 3: Training the machine learning model

[1150] The server uses the cleansed data to train machine learning algorithms and deep learning models. Libraries used include TensorFlow and PyTorch. The learning algorithms used are random forests and neural networks for risk prediction. This process builds a predictive model for real-time risk forecasting in the event of an earthquake. The input data is the cleansed dataset, and the output data is the trained predictive model.

[1151] Step 4: Earthquake detection and information transmission

[1152] A device (such as a smartphone or tablet) detects an earthquake using its built-in acceleration sensor or receives an earthquake warning from the Japan Meteorological Agency. When an earthquake is detected, the device sends this detection information along with its current location information to a server. The input data is the earthquake detection data and location information, and the output data is the data sent to the server.

[1153] Step 5: Risk analysis

[1154] The server compares the received earthquake information and location information with past data and analyzes the risk of the relevant area. Specifically, it takes into account factors such as distance from the epicenter, topographical information, and population density. This risk analysis uses a trained predictive model. The input data is earthquake information and location information, and the output data is the risk analysis results.

[1155] Step 6: Evacuation route generation and behavior instructions

[1156] The server generates the optimal evacuation route based on the risk analysis results. This generation uses geographic information services such as Google Maps API and OpenStreetMap. It also generates specific action instructions (e.g., "head to the nearest high ground" or "evacuate to a specific evacuation shelter"). The input data are the risk analysis results and current terrain and traffic information, and the output data are the evacuation route and action instructions.

[1157] Step 7: Sending instructions

[1158] The server sends the generated evacuation route and action instructions to the device. This is done using push notifications or SMS. The input data is the evacuation route and action instructions, and the output data is the data sent to the device.

[1159] Step 8: User evacuation behavior

[1160] The user follows the instructions received from the device and begins evacuation along the specified evacuation route. For example, they may head to the nearest high ground or evacuate to a specific evacuation shelter. The input data are instructions from the device, and the output is the actual evacuation behavior.

[1161] Step 9: Evacuation completion report

[1162] When the user completes evacuation, they press the "Evacuation Complete" button on their device to send evacuation completion information to the server. The input data is the evacuation completion information, and the output data is the data to be sent to the server.

[1163] Step 10: Evacuation status tracking and feedback

[1164] The server tracks the user's evacuation status based on the received evacuation completion information and user location information. It also uses the collected evacuation behavior data and evacuation success rate for future risk analysis and the generation of behavioral instructions. The input data are evacuation behavior data and completion information, and the output data is learning data used as feedback.

[1165] The above is a specific operation of each processing step in the disaster recovery system.

[1166] (Application example 1)

[1167] 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."

[1168] During earthquake disasters, it is important to provide routes and instructions for quick and safe evacuation, but current technology makes it difficult to provide optimal evacuation routes and specific instructions for action in real time according to the individual circumstances of each evacuee.In addition, there is no system in place to efficiently support evacuation using autonomous vehicles, which can result in delays in evacuation.To solve this problem, there is a need for a system that can perform risk analysis in real time during earthquake disasters and provide evacuation routes and instructions for action to autonomous vehicles.

[1169] 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.

[1170] In this invention, the server includes a data collection means for collecting and learning past earthquake disaster data, a risk analysis means for analyzing risks in real time based on the learned earthquake disaster data, an evacuation route generation means for generating evacuation routes and action instructions based on the analysis results, an instruction transmission means for transmitting the generated evacuation routes and action instructions to a user terminal, a vehicle control means for controlling an autonomous vehicle to move along the evacuation route when an earthquake occurs, and an information provision means for providing information to users via an in-vehicle display or audio guidance. This makes it possible to provide optimal evacuation routes and specific action instructions according to the individual circumstances of evacuees in the event of an earthquake disaster, and to support quick and safe evacuation using autonomous vehicles.

[1171] The "data collection means" is a system component that collects past earthquake disaster data and uses it for learning.

[1172] The "risk analysis means" is a system component for analyzing earthquake risk in real time based on collected data.

[1173] The "evacuation route generation means" is a system component that generates an optimal evacuation route and specific action instructions based on the results of risk analysis.

[1174] The "instruction transmitting means" is a system component for transmitting the generated evacuation route and action instructions to the user terminal.

[1175] The "vehicle control means" is a system component that controls autonomous vehicles in the event of an earthquake and moves them along evacuation routes.

[1176] The "information provision means" is a system component that provides evacuation information to users using in-vehicle displays, voice guidance, etc.

[1177] The "location tracking means" is a system component for receiving real-time location information from user terminals and tracking the evacuation situation.

[1178] The "feedback means" is a system component that collects user behavior data and evacuation success rates and uses them for future risk analysis and generation of behavioral instructions.

[1179] System Configuration

[1180] This invention is a system that collects past earthquake disaster data, performs risk analysis in real time, and provides optimal evacuation routes and action instructions. This system consists of three parties: a server, a terminal, and a user. In particular, we focus on an application example realized by a dedicated application installed in an autonomous vehicle.

[1181] Server Roles

[1182] The server first collects data on past earthquake disasters, cleansing the data, and then uses machine learning algorithms and deep learning models to learn from it. This allows it to identify risk patterns when an earthquake occurs and build a predictive model. Next, when it receives information from a device that detected an earthquake, it compares that information with past data to analyze the risk in the relevant area. The analysis takes into account data such as distance from the epicenter, topographical information, and population density. It then calculates the optimal evacuation route based on the risk analysis results and sends it to the device.

[1183] Device Role

[1184] The terminals consist of common mobile devices such as smartphones and tablets, but in this case they also include on-board computers installed in self-driving vehicles. When an earthquake is detected or an earthquake warning is received from the Japan Meteorological Agency, the information is sent to a server. When evacuation routes and specific instructions for action are sent from the server, the terminal communicates these to the user via the in-vehicle display and voice guidance system. Furthermore, the terminal also has the function of controlling the self-driving vehicle along the evacuation route using vehicle control means.

[1185] User Roles

[1186] The user begins and executes evacuation actions according to instructions from the device. When the evacuation is complete, the user presses the "Evacuation Complete" button on the device, and the information is sent to the server. The server collects the user's behavioral data and evacuation success rate, and uses this data for future risk analysis and the generation of behavioral instructions.

[1187] Hardware and Software Used

[1188] Server: Python, machine learning libraries (Scikit-Learn, TensorFlow, etc.), database (PostgreSQL)

[1189] Devices: Smartphones, tablets, in-vehicle computers for autonomous vehicles, displays, voice guidance systems

[1190] Data collection: Japan Meteorological Agency Earthquake Alert API, USGS Earthquake API

[1191] Specific examples

[1192] For example, suppose an earthquake occurs in a certain area and is detected by a device in an autonomous vehicle. This information is sent to a server, where it is compared with past data to analyze the risk in that area. If it determines that there is a risk of a tsunami, the server calculates an evacuation route and automatically guides the vehicle to higher ground, allowing the user to complete the evacuation safely.

[1193] Prompt Sentence Examples

[1194] An earthquake has occurred. Your current location is longitude 139.70, latitude 35.69. Please calculate the safest evacuation route and guide you to your destination.

[1195] In this way, the form for implementing the invention can provide optimal evacuation routes and specific instructions for actions in real time according to the individual circumstances of evacuees during earthquake disasters, and can also support quick and safe evacuation using autonomous vehicles.

[1196] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1197] Step 1:

[1198] The server collects data on past earthquake disasters. The input is earthquake data obtained from various APIs, and the output is a cleansed dataset. Data processing includes filling in incomplete data and processing outliers.

[1199] Step 2:

[1200] The server uses the cleansed data to train machine learning algorithms or deep learning models. The input is the cleansed dataset and the output is the trained model. Data operations include feature extraction and pattern identification.

[1201] Step 3:

[1202] The device detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency. The input is sensor data and earthquake warnings from the Japan Meteorological Agency API, and the output is a notification of an earthquake occurrence. Specific operations are triggered by sensors and communication modules on the device.

[1203] Step 4:

[1204] The terminal sends earthquake information to the server. The input is a notification of the earthquake occurrence, and the output is a transmission request to the server. Here, the terminal's network communication function is used.

[1205] Step 5:

[1206] The server compares the received earthquake information with past data and analyzes the risk in the relevant area. The input is earthquake information and a trained model, and the output is the risk analysis results. Data calculations take into account the distance from the epicenter and topographical information.

[1207] Step 6:

[1208] The server calculates the optimal evacuation route based on the risk analysis results and generates action instructions. The input is the risk analysis results, and the output is the evacuation route and action instructions. Specific operations include real-time traffic situation analysis using an algorithm.

[1209] Step 7:

[1210] The server sends the generated evacuation route and action instructions to the terminal. The input is the evacuation route and action instructions, and the output is a transmission request. The terminal's communication module is used again.

[1211] Step 8:

[1212] The terminal receives the evacuation route and action instructions from the server and provides them to the user via an in-car display or voice guidance. The input is the evacuation route and action instructions, and the output is the display and voice guidance. The in-car system plays an important role here.

[1213] Step 9:

[1214] The terminal controls the autonomous vehicle according to the evacuation route. The input is evacuation route information, and the output is vehicle control commands. Specific operations include route optimization by the navigation system and control of the drive-by-wire system.

[1215] Step 10:

[1216] The user presses the "Evacuation Complete" button on the device to notify that the evacuation is complete. The input is the user's touch operation, and the output is a notification of evacuation completion to the server.

[1217] Step 11:

[1218] The server receives evacuation completion notifications from users and records the user's behavioral data and evacuation success rate. The input is the evacuation completion notification, and the output is a record in the database. This will be used as a feedback tool for the next risk analysis.

[1219] Step 12:

[1220] The server uses feedback mechanisms to generate future risk analyses and action instructions. The input is the previous evacuation data, and the output is an updated predictive model. Generative AI models and prompts are used here.

[1221] 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.

[1222] This invention is a disaster prevention system that analyzes risks and suggests evacuation actions for earthquake disasters, providing optimal evacuation routes and action instructions in real time based on past earthquake disaster data. By combining this system with an emotion engine, it is possible to take the user's emotions into consideration and provide more accurate and effective evacuation instructions. This system consists of three parties: a server, a terminal, and a user, each of which plays a specific role.

[1223] 1. Data collection and learning

[1224] The server first collects data on past earthquake disasters. This data includes information such as epicenters, seismic intensity, damage status, and the impact of tsunamis and fires. This data is then cleansed and formatted for analysis. It is then trained using machine learning algorithms and deep learning models to identify risk patterns in the event of an earthquake and build a predictive model.

[1225] 2. Real-time risk prediction

[1226] When a device (such as a smartphone or tablet) detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency, it sends that information to a server. The information sent includes the earthquake's seismic intensity, epicenter, and time of occurrence. The server compares the received earthquake information with past data and analyzes the risk in the relevant area in real time.

[1227] 3. Emotion Recognition and Evaluation

[1228] The device is equipped with an emotion engine that recognizes the user's emotions. The emotion engine acquires and analyzes emotion data from the user's facial expressions, tone of voice, text input, etc., and sends the results to a server. Emotion data includes stress levels and levels of impatience.

[1229] 4. Emotion-based evacuation route and behavior suggestions

[1230] The server generates optimal evacuation routes and instructions based on the risk analysis results and emotional data from the emotion engine. If the user is in a high-stress state, the server prioritizes routes that provide a sense of security and simple instructions. The server then transmits the generated evacuation routes and instructions to the device.

[1231] 5. User Behavior and Feedback

[1232] The user carries out evacuation actions instructed by the device. They move while checking their current location and evacuation destination using the device's GPS function. The device sends the user's location information and movement trajectory to the server in real time, and the user's evacuation status is tracked.

[1233] Examples:

[1234] For example, if an earthquake occurs in a certain area and is detected by a device, the earthquake information is sent to a server, where risk analysis is performed in real time. At the same time, the device's emotion engine collects the user's emotional data, which is also sent to the server. If the server determines that the user is in a high-stress state, it selects an evacuation route that prioritizes a sense of security, generates instructions to "proceed slowly and safely," and sends these instructions to the device. The user begins evacuation according to the instructions, and once the evacuation is complete, presses the "Evacuation Complete" button on the device. This information is also sent to the server, and the success or failure of the evacuation is recorded.

[1235] This system not only supports quick and appropriate evacuation behavior during earthquake disasters, but also enables more effective evacuation by taking into account the user's emotional state.

[1236] The processing flow will be explained below.

[1237] Step 1:

[1238] The server collects data on past earthquake disasters, including epicenters, seismic intensity, damage, and the impact of tsunamis and fires. This data is obtained from government agencies, university research institutes, disaster-related organizations, and other sources.

[1239] Step 2:

[1240] The server cleanses the collected data and formats it in a format suitable for analysis, removing irrelevant data, handling missing values, and standardizing data formats.

[1241] Step 3:

[1242] The server uses the formatted data to train machine learning algorithms and deep learning models, identifying risk patterns in the event of an earthquake and building a predictive model.

[1243] Step 4:

[1244] When a device (smartphone or tablet) detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency, it sends that information, including the earthquake's magnitude, epicenter, and time of occurrence, to a server.

[1245] Step 5:

[1246] The server compares the received earthquake information with past data and performs real-time risk analysis, taking into account factors such as distance from the epicenter, topographical information, and population density.

[1247] Step 6:

[1248] The device's emotion engine acquires and analyzes emotional data from the user's facial expressions, tone of voice, text input, etc. The analysis results in information such as the user's stress level and degree of impatience.

[1249] Step 7:

[1250] The device then transmits the acquired emotional data, including the level of stress and impatience, to the server.

[1251] Step 8:

[1252] The server generates optimal evacuation routes and instructions based on risk analysis results and emotional data. If the user's stress level is high, the server prioritizes simpler and more reassuring routes.

[1253] Step 9:

[1254] The server then sends the generated evacuation route and instructions to the device, such as "head to the nearest high ground" or "evacuate to a designated evacuation shelter."

[1255] Step 10:

[1256] The user follows the instructions displayed on the device and begins the designated evacuation action, using the device's GPS function to check their current location and evacuation destination as they move.

[1257] Step 11:

[1258] The device transmits the user's location information and movement trajectory to the server in real time, allowing the server to track the user's evacuation status.

[1259] Step 12:

[1260] When the user completes evacuation, they press the "Evacuation Complete" button on their device. The evacuation completion information is sent to the server and recorded.

[1261] Step 13:

[1262] The server collects user behavior data and evacuation success rates, and uses feedback to improve the accuracy of risk analysis and behavioral instructions for future events, thereby continuously improving the effectiveness of the system.

[1263] Example 2

[1264] 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."

[1265] Conventional disaster prevention systems are limited to analyzing earthquake disaster risks and suggesting evacuation routes, and do not consider the user's emotional state, which can increase panic and stress during an emergency. Furthermore, evacuation route instructions are generalized, making it difficult to provide optimal instructions tailored to the user's individual situation and emotions. This can lead to ineffective evacuation behavior and reduced safety.

[1266] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a data collection means for collecting and learning past earthquake data, a risk analysis means for analyzing risks in real time based on the learned earthquake data, an emotion recognition means for acquiring user emotion data, an evacuation route generation means for analyzing the emotion data and integrating it with the risk analysis results to generate an evacuation route and action instructions, and an instruction transmission means for transmitting the generated evacuation route and action instructions to the user terminal. This makes it possible to provide an appropriate and effective evacuation route and action instructions that take into account the user's emotional state, thereby reducing stress in an emergency and improving evacuation safety.

[1267] "Data collection means" refers to the means for collecting past earthquake data and formatting it into a format suitable for analysis and learning.

[1268] "Risk analysis means" refers to a means for analyzing the risk of an earthquake occurring in real time based on collected and learned earthquake data.

[1269] The "emotion recognition means" is a means for analyzing the user's facial expression, tone of voice, text input, etc., and acquiring the user's emotional data.

[1270] The "evacuation route generation means" is a means for generating the optimal evacuation route and action instructions for the user based on the risk analysis results and emotion data.

[1271] The "instruction transmission means" is a means for transmitting the generated evacuation route and action instructions to the user terminal.

[1272] The "location tracking means" is a means for receiving real-time location information from the user terminal and tracking the evacuation status of the user.

[1273] The "feedback means" is a means for collecting user behavior data and evacuation success rates, and using the data for future risk analysis and generation of behavioral instructions.

[1274] This invention is a disaster prevention system that analyzes risks and suggests evacuation actions for earthquake disasters, and provides optimal evacuation routes and action instructions in real time based on past earthquake data and user emotion data. This system is composed of three parties: a server, a terminal, and a user, each of which plays a specific role.

[1275] First, the server has a data collection tool for collecting past earthquake data. This tool collects earthquake data using APIs from the Japan Meteorological Agency and other earthquake information providers. The collected data is cleansed and formatted for analysis using data processing libraries such as Pandas and NumPy. Then, a machine learning model is trained using TensorFlow and PyTorch. This model is used to identify risk patterns and make predictions when earthquakes occur.

[1276] Next, when a device (smartphone or tablet) detects an earthquake with its sensor or receives an earthquake warning from the Japan Meteorological Agency, earthquake information is sent to a server. The information sent includes the epicenter, seismic intensity, and time of occurrence. The server compares this information with past data and performs real-time risk analysis using cloud analysis services such as Google Cloud and Azure AI.

[1277] The device is also equipped with an emotion engine that recognizes the user's emotions. The emotion engine uses tools such as OpenCV, Emotion API, and Watson Tone Analyzer to acquire and analyze emotional data from the user's facial expressions, tone of voice, and text input. The resulting data, such as the user's stress level and degree of impatience, is sent to the server.

[1278] The server integrates the risk analysis results with the emotion data to generate the optimal evacuation route and behavioral instructions. For example, if the user is in a high-stress state, an evacuation route that prioritizes a sense of security will be selected, and instructions such as "proceed slowly and safely." These instructions are then sent to the device and provided to the user.

[1279] The user follows instructions from the device to carry out evacuation. Using the device's GPS function, the user moves while checking their current location and evacuation destination. The device sends the user's location information and movement trajectory to the server in real time, and the user's evacuation status is tracked.

[1280] As a concrete example, consider the case where a magnitude 7 earthquake occurs in a certain area and is detected by a device. At this time, earthquake information is sent to the server, and risk analysis is performed in real time. At the same time, the device's emotion engine collects the user's emotional data and detects that the user is in a high-stress state. Based on this, the server generates an instruction to "select an evacuation route that prioritizes a sense of security" and sends this to the device. The user begins evacuation in accordance with this instruction, and once the evacuation is complete, they press the "Evacuation Complete" button on the device, sending feedback to the server that the evacuation was successful.

[1281] An example of a prompt sentence is, "Please explain the real-time processing of a system that takes into account the user's emotions and suggests the optimal evacuation route when an earthquake occurs."

[1282] In this way, the present invention not only supports quick and appropriate evacuation behavior in the event of an earthquake disaster, but also realizes more effective evacuation by taking into account the user's emotional state.

[1283] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1284] Step 1:

[1285] The server retrieves past earthquake data.

[1286] Input: Collect earthquake data from the APIs of earthquake information providers. Specifically, access the APIs of the Japan Meteorological Agency and earthquake information providers.

[1287] Data processing: Receive collected data in JSON format and use the Pandas library to format it appropriately. Cleanse unnecessary information and missing data.

[1288] Output: A database of cleansed seismic data is generated.

[1289] Step 2:

[1290] The server trains a machine learning model based on the data.

[1291] Input: Formatted historical earthquake data. Specifically, features such as epicenter, seismic intensity, and damage status are used.

[1292] Data Computing: Using TensorFlow and PyTorch, we train an earthquake risk prediction model and identify risk patterns in the event of an earthquake based on historical earthquake data.

[1293] Output: A trained earthquake risk prediction model.

[1294] Step 3:

[1295] The device detects an earthquake or receives an earthquake alert.

[1296] Input: Data detecting earthquake vibrations from device sensors or notifications from earthquake warning systems.

[1297] Data processing: Obtain earthquake information (epicenter, seismic intensity, time of occurrence).

[1298] Output: Earthquake information is sent from the device to the server.

[1299] Step 4:

[1300] The server performs real-time risk analysis.

[1301] Input: Earthquake information sent from the device, specifically, data on the epicenter, seismic intensity, and occurrence time.

[1302] Data calculation: Analyze received earthquake information in real time and compare it with past data. Analyze risks using cloud analysis services from Google Cloud and Azure AI.

[1303] Output: Real-time risk analysis results are obtained.

[1304] Step 5:

[1305] The device collects the user's emotional data.

[1306] Input: Facial expression data from the camera, tone of voice from the microphone, and text input.

[1307] Data processing: Analyze these data using OpenCV, Emotion API, and Watson Tone Analyzer to obtain emotion data.

[1308] Output: Emotion data is obtained and sent to the server.

[1309] Step 6:

[1310] The server generates evacuation routes and action instructions taking into account emotion data.

[1311] Input: Real-time risk analysis results and sentiment data.

[1312] Data calculation: By integrating risk analysis results with emotional data, the system uses the Google Maps API to generate the optimal evacuation route based on the user's emotional state. For example, if the user is in a high-stress state, the system will select a simple and reassuring route.

[1313] Output: Optimal evacuation routes and action instructions are generated.

[1314] Step 7:

[1315] The server sends the generated evacuation route and action instructions to the terminal.

[1316] Input: Optimal evacuation route and action instructions.

[1317] Data processing: Format the data into JSON format and send it to the terminal via an HTTP request.

[1318] Output: The device receives the required information.

[1319] Step 8:

[1320] The user performs evacuation actions.

[1321] Input: Evacuation route and action instructions received from the terminal.

[1322] Specific actions: Use the GPS function to check your current location and follow a safe evacuation route.

[1323] Output: The user safely completes the evacuation.

[1324] Step 9:

[1325] The device tracks the user's evacuation status in real time.

[1326] Input: User location and movement trajectory.

[1327] Data processing: GPS data is acquired in real time and sent to the server.

[1328] Output: Evacuation status is tracked on the server.

[1329] Step 10:

[1330] When the user has completed the evacuation, he or she presses the "Evacuation Complete" button on the terminal.

[1331] Input: User presses the "Evacuation Complete" button.

[1332] Data processing: Send information about the completion of evacuation to the server.

[1333] Output: The server records a successful evacuation.

[1334] These are the specific processing steps of the program for this system, which makes it possible to support effective evacuation while taking into consideration the user's emotions.

[1335] (Application example 2)

[1336] 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."

[1337] Although systems already exist to support quick and appropriate evacuation behavior during earthquake disasters, previous systems did not take into account the user's emotional state, which can result in increased stress and anxiety. Furthermore, evacuation routes are provided based on a general approach, which does not provide appropriate instructions tailored to the user's individual emotional state. Therefore, there is a need for a system that allows users to evacuate with peace of mind.

[1338] The identification process by the identification 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 a data collection means for collecting and learning past earthquake disaster data, a risk analysis means for analyzing risks in real time based on the learned earthquake disaster data, an evacuation route generation means for generating evacuation routes and action instructions based on the analysis results, and an emotion analysis means for collecting user emotion data and reflecting it in the generation of evacuation routes. This makes it possible to provide an optimal evacuation route that takes the user's emotional state into consideration, realizing a system that allows users to evacuate quickly and safely.

[1339] "Data collection means" is a function that collects data on past earthquake disasters and formats the data for learning purposes.

[1340] The "risk analysis means" is a function that analyzes the risk in the event of an earthquake in real time based on learned earthquake disaster data.

[1341] The "evacuation route generation means" is a function that generates an optimal evacuation route and action instructions for the user based on the results of risk analysis.

[1342] The "instruction sending means" is a function that sends the generated evacuation route and action instructions to the user terminal.

[1343] The "emotion analysis means" is a function that collects the user's emotional data (stress level and degree of anxiety) and reflects that data in generating an evacuation route.

[1344] The "location tracking means" is a function that receives real-time location information from the user terminal and tracks the evacuation status of the user.

[1345] The "feedback means" is a function that collects user behavior data and evacuation success rates, and uses them for future risk analysis and generation of behavioral instructions.

[1346] The "emotion data analysis means" is a function that uses an emotion recognition engine installed on the user's terminal to analyze the user's stress level and degree of anxiety, and reflects this in generating an evacuation route.

[1347] This invention is a system that takes into consideration the emotional state of a user in the event of an earthquake disaster and provides optimal evacuation routes and action instructions. Specific embodiments of this system will be described below.

[1348] 1. Data collection and learning

[1349] The server first collects data on past earthquake disasters. This data includes information such as epicenters, seismic intensity, damage status, and the impact of tsunamis and fires. The collected data is then cleansed and formatted for analysis. It then uses machine learning algorithms and deep learning models to identify risk patterns in the event of an earthquake and build a predictive model. This process uses programming languages ​​and libraries such as Python and TensorFlow.

[1350] 2. Real-time risk prediction

[1351] When the user's device (smart glasses) detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency, it sends the information to a server. The information sent includes the earthquake's seismic intensity, epicenter, and time of occurrence. The server compares the received earthquake information with past data and analyzes the risk in the relevant area in real time.

[1352] 3. Emotion Recognition and Evaluation

[1353] The user device is equipped with an emotion recognition engine that recognizes the user's emotions. The emotion engine acquires and analyzes emotion data from the user's facial expressions, tone of voice, text input, etc., and sends the results to the server. Emotion data includes stress level and degree of impatience. This process utilizes the Emotion Recognition library.

[1354] 4. Emotion-based evacuation route and behavior suggestions

[1355] The server generates optimal evacuation routes and instructions based on the risk analysis results and emotional data from the emotion engine. If the user is in a high-stress state, the server prioritizes routes that provide a sense of security and simple instructions. The server then transmits the generated evacuation routes and instructions to the user's device.

[1356] 5. User Behavior and Feedback

[1357] The user carries out evacuation actions instructed by the device. Using the device's GPS function, the user moves while checking their current location and evacuation destination. The device sends the user's location information and movement trajectory to the server in real time, and the user's evacuation status is tracked.

[1358] Specific examples

[1359] For example, if an earthquake occurs in a certain area and is detected by a device, the earthquake information is sent to a server, where risk analysis is performed in real time. At the same time, the device's emotion engine collects the user's emotional data, which is also sent to the server. If the server determines that the user is in a high-stress state, it selects an evacuation route that prioritizes a sense of security, generates instructions to "proceed slowly and safely," and sends these instructions to the device. The user begins evacuation according to the instructions, and once the evacuation is complete, presses the "Evacuation Complete" button on the device. This information is also sent to the server, and the success or failure of the evacuation is recorded.

[1360] Prompt Sentence Examples

[1361] "Analyze the user's emotional state and suggest evacuation routes based on that data."

[1362] "Consider the user's current location when generating evacuation routes."

[1363] "To address high stress levels in users, prioritize escape routes that provide a sense of security."

[1364] This system not only supports quick and appropriate evacuation behavior during earthquake disasters, but also enables more effective evacuation by taking into account the user's emotional state.

[1365] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1366] Step 1:

[1367] The server collects data on past earthquake disasters. Specifically, it collects data on the epicenter, seismic intensity, damage status, and the impact of tsunamis and fires, and stores it in a database. It then prepares this data for analysis using machine learning algorithms and deep learning models. The input is disaster data from external data sources (such as the Japan Meteorological Agency or disaster databases), and the output is cleansed, formatted, and analyzable data.

[1368] Step 2:

[1369] The server uses machine learning algorithms and deep learning models to learn from the collected earthquake disaster data, identify risk patterns when an earthquake occurs, and build a predictive model. Specifically, the model is trained using programming languages ​​and libraries such as Python and TensorFlow. The input is formatted disaster data, and the output is a risk prediction model when an earthquake occurs.

[1370] Step 3:

[1371] When the device (smart glasses) detects an earthquake or receives an earthquake warning from the Japan Meteorological Agency, it sends that information to the server. The input is the warning data from the earthquake detection device or the Japan Meteorological Agency, and the output is the earthquake information (seismic intensity, epicenter, and time of occurrence) sent to the server.

[1372] Step 4:

[1373] The server compares the received earthquake information with past data and analyzes the risk in the relevant area in real time. The input is earthquake information sent from the terminal, and the output is the real-time risk assessment result. This process uses a deep learning model.

[1374] Step 5:

[1375] The device is equipped with an emotion recognition engine that recognizes the user's emotions. The emotion engine acquires and analyzes emotion data from the user's facial expressions, tone of voice, text input, etc., and sends the results to a server. The input is the user's facial expression data and voice data, and the output is analyzed emotion data (stress level and degree of impatience).

[1376] Step 6:

[1377] The server generates optimal evacuation routes and action instructions by taking into account the risk analysis results as well as emotional data from the emotion engine. If the user is in a high-stress state, the system adjusts to prioritize routes that provide a sense of security and simple instructions. The inputs are real-time risk assessment results and emotional data, and the output is the optimal evacuation route and action instructions.

[1378] Step 7:

[1379] The server sends the generated evacuation route and action instructions to the terminal. The input is the optimal evacuation route and action instructions, and the output is the evacuation route and action instructions sent to the terminal.

[1380] Step 8:

[1381] The user carries out evacuation actions instructed by the device. They move while checking their current location and evacuation destination using the device's GPS function. The device sends the user's location information and movement trajectory to the server in real time, and tracks the user's evacuation status. The input is the user's current location and movement trajectory, and the output is evacuation status data sent to the server.

[1382] Step 9:

[1383] The server checks whether the user has completed evacuation and sends additional instructions or alerts as necessary. The input is real-time evacuation status data and feedback data, and the output is evacuation completion notification and additional instructions.

[1384] 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.

[1385] 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.

[1386] 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 robot 414.

[1387] 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.

[1388] FIG. 9 is a diagram illustrating 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 actions 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.

[1389] 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.

[1390] 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).

[1391] 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.

[1392] 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."

[1393] 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.

[1394] 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).

[1395] 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.

[1396] 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.

[1397] 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.

[1398] 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.

[1399] 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.

[1400] 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.

[1401] 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.

[1402] 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.

[1403] 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.

[1404] 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.

[1405] The following is further disclosed regarding the above embodiment.

[1406] (Claim 1)

[1407] A data collection means for collecting and learning from past earthquake disaster data;

[1408] A risk analysis method that analyzes risks in real time based on learned earthquake disaster data;

[1409] an evacuation route generation means for generating an evacuation route and action instructions based on the analysis results;

[1410] an instruction sending means for sending the generated evacuation route and action instructions to a user terminal;

[1411] A system including:

[1412] (Claim 2)

[1413] 10. The system of claim 1, further comprising a location tracking means for receiving real-time location information from the user terminal and tracking the evacuation situation.

[1414] (Claim 3)

[1415] 2. The system according to claim 1, further comprising a feedback means for collecting user behavior data and evacuation success rates and using the collected data for subsequent risk analysis and generation of behavioral instructions.

[1416] "Example 1"

[1417] (Claim 1)

[1418] A data collection means for collecting and learning from past earthquake disaster data;

[1419] A risk analysis method that analyzes risks in real time based on learned earthquake disaster data, and

[1420] an evacuation route generation means for generating an evacuation route and action instructions based on the analysis results;

[1421] an instruction sending means for sending the generated evacuation route and action instructions to a communication device;

[1422] A system including:

[1423] (Claim 2)

[1424] 10. The system of claim 1, further comprising a location tracking means for receiving real-time location signals and tracking evacuation situations.

[1425] (Claim 3)

[1426] 10. The system according to claim 1, further comprising a feedback means for collecting behavioral data and evacuation success rates and using the collected data for subsequent risk analysis and generation of behavioral instructions.

[1427] "Application Example 1"

[1428] (Claim 1)

[1429] A data collection means for collecting and learning from past earthquake disaster data;

[1430] A risk analysis method that analyzes risks in real time based on learned earthquake disaster data;

[1431] an evacuation route generation means for generating an evacuation route and action instructions based on the analysis results;

[1432] an instruction sending means for sending the generated evacuation route and action instructions to a user terminal;

[1433] a vehicle control means for controlling an autonomous vehicle to move along an evacuation route when an earthquake occurs;

[1434] An information providing means for providing information to users through an in-car display and voice guidance;

[1435] A system including:

[1436] (Claim 2)

[1437] 10. The system according to claim 1, further comprising a location tracking means for receiving real-time location information from the user terminal and tracking the evacuation situation.

[1438] (Claim 3)

[1439] 2. The system according to claim 1, further comprising a feedback means for collecting user behavior data and evacuation success rates and using the collected data for subsequent risk analysis and generation of behavioral instructions.

[1440] "Example 2: Combining Emotion Engines"

[1441] (Claim 1)

[1442] A data collection means for collecting and learning from past earthquake data;

[1443] A risk analysis method that analyzes risks in real time based on learned earthquake data;

[1444] emotion recognition means for acquiring emotion data of a user;

[1445] an evacuation route generation means for analyzing the emotion data and integrating it with a risk analysis result to generate an evacuation route and action instructions;

[1446] an instruction sending means for sending the generated evacuation route and action instructions to a user terminal;

[1447] A system including:

[1448] (Claim 2)

[1449] 10. The system of claim 1, further comprising a location tracking means for receiving real-time location information from the user terminal and tracking the evacuation situation.

[1450] (Claim 3)

[1451] 2. The system according to claim 1, further comprising a feedback means for collecting user behavior data and evacuation success rates and using the collected data for subsequent risk analysis and generation of behavioral instructions.

[1452] "Application example 2 when combining emotion engines"

[1453] (Claim 1)

[1454] A data collection means for collecting and learning from past earthquake disaster data;

[1455] A risk analysis method that analyzes risks in real time based on learned earthquake disaster data;

[1456] an evacuation route generation means for generating an evacuation route and action instructions based on the analysis results;

[1457] an instruction sending means for sending the generated evacuation route and action instructions to a user terminal;

[1458] An emotion analysis means for collecting user emotion data and reflecting the collected data in generating an evacuation route;

[1459] A system including:

[1460] (Claim 2)

[1461] 10. The system of claim 1, further comprising a location tracking means for receiving real-time location information from the user terminal and tracking the evacuation situation.

[1462] (Claim 3)

[1463] 2. The system according to claim 1, further comprising a feedback means for collecting user behavior data and evacuation success rates and using the collected data for subsequent risk analysis and generation of behavioral instructions.

[1464] (Claim 4)

[1465] 2. The system according to claim 1, further comprising emotion data analysis means for analyzing the stress level and degree of impatience of the user by an emotion recognition engine installed in the user terminal and reflecting the results in generating an evacuation route. [Explanation of symbols]

[1466] 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 data collection means for collecting and learning from past earthquake disaster data; A risk analysis method that analyzes risks in real time based on learned earthquake disaster data; an evacuation route generation means for generating an evacuation route and action instructions based on the analysis results; an instruction sending means for sending the generated evacuation route and action instructions to a user terminal; A system including:

2. 10. The system of claim 1, further comprising a location tracking means for receiving real-time location information from the user terminal and tracking the evacuation situation.

3. The system according to claim 1, further comprising a feedback means for collecting user behavior data and evacuation success rates and using the collected data for subsequent risk analysis and generation of behavioral instructions.

Images