System

Abstract

A system is provided.SOLUTION: A system including means for collecting weather data and earthquake data in the past and analyzing these data, means for analyzing videos and photographs transmitted in real time and specifying a damage range and a damage pattern, means for analyzing images acquired from a satellite and a drone and grasping a situation of a disaster area, means for analyzing rescue activities and evacuation guidance data in the past and proposing an optimal countermeasure, means for analyzing a health state and a psychological state of a disaster victim and determining care and evacuation place arrangement, and means for providing appropriate information and measures to a user on the basis of these means.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] When a disaster occurs, delayed warning actions, a lack of accurate information, and a lack of clarity about appropriate countermeasures can lead to greater damage. Furthermore, current systems, which lack the ability to predict disasters in real time or quickly share information, make it difficult to carry out appropriate evacuation and rescue operations. Therefore, there is a need for a system that can effectively predict disaster risks and quickly and accurately propose countermeasures. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system that includes a means for collecting and analyzing past weather and earthquake data, a means for analyzing video and photographs transmitted in real time to identify the extent and pattern of damage, a means for analyzing images acquired from satellites and drones to grasp the situation in the disaster-stricken area, a means for analyzing past rescue operations and evacuation guidance data to propose optimal countermeasures, and a means for analyzing the health and psychological state of disaster victims to determine care and evacuation shelter placement.This system uses an analysis means that uses generative AI to predict the occurrence of disasters in advance and quickly provide appropriate countermeasures, providing users with real-time information and enabling safe evacuation and rapid rescue operations.

[0006] "Weather data" refers to observational data related to weather, such as temperature, precipitation, wind speed, and humidity.

[0007] "Earthquake data" refers to observational data related to earthquakes, such as the date and time of the earthquake, the location of the epicenter, the seismic intensity, and the depth of the epicenter.

[0008] "Analytical tools" are techniques or methods that analyze collected data and reveal specific trends or patterns.

[0009] "Generative AI" refers to algorithms and models that use artificial intelligence technology to generate and analyze data and generate new insights and predictions.

[0010] "Video and photos transmitted in real time" refers to videos and still images transmitted in real time from drones, surveillance cameras, etc.

[0011] "Affected area" refers to the extent of the area or location affected by a disaster.

[0012] A "damage pattern" refers to the specific form or tendency of damage or impact that occurs when a disaster occurs.

[0013] "Images obtained from satellites and drones" refers to images of the earth's surface and disaster-stricken areas taken by satellites or drones.

[0014] "Rescue operations" refers to activities such as saving lives, providing supplies, and providing medical support during disasters.

[0015] "Evacuation guidance data" refers to information for carrying out effective evacuation, such as evacuation routes and the location of evacuation shelters.

[0016] "Health status" refers to information about the physical condition and medical condition of the disaster victims.

[0017] "Psychological status" refers to information about the mental health and stress levels of disaster victims.

[0018] "Care" refers to medical and psychological support to improve and maintain the health and psychological state of disaster victims.

[0019] "Shelter arrangement" refers to the planning and implementation of the arrangement and establishment of places for disaster victims to evacuate. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] As an embodiment of the present invention, the operation of the system is explained step by step below. This system collects and analyzes a wide range of data, such as weather data, earthquake data, real-time video and photos, satellite and drone images, rescue operation and evacuation guidance data, and the health and psychological state of disaster victims, and provides users with appropriate information and countermeasures.

[0042] Data collection and analysis

[0043] First, the server collects historical weather and earthquake data from various data sources (weather observation satellites and government agencies). The collected data is converted into an easy-to-analyze format, and data cleaning is performed to fill in missing data and remove noise. A generative AI model analyzes this historical data and predicts future disaster risk. After the analysis is complete, a predictive model is generated.

[0044] Real-time data collection and analysis

[0045] The device then transfers real-time video and photos from devices such as drones and fixed cameras to a server. The server uses this real-time data to identify the extent and pattern of damage. For example, the server analyzes the depth and spread of flooding and generates optimal evacuation routes.

[0046] The server also analyzes images acquired from satellites and drones in real time to obtain the latest information on the situation in the affected areas, including the traffic status of major roads and the extent of damage in the affected areas.

[0047] Rescue operations and evacuation guidance suggestions

[0048] The server analyzes a database of past rescue operations and evacuation guidance, proposing optimal rescue methods and evacuation guidance measures. This analysis is based on past successful cases, enabling a swift and effective response tailored to the current situation in the disaster area.

[0049] Analysis of the health and psychological status of disaster victims

[0050] Users enter their own health and psychological state into the device through the application. The device then sends this data to a server, which then analyzes it using generative AI. Based on this analysis, appropriate care for disaster victims and the location of evacuation shelters are determined.

[0051] Providing information and advice

[0052] Based on all of the above analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. The device displays this information in an easy-to-understand manner, supporting rapid evacuation and appropriate action. Additionally, depending on changes in the user's health or psychological state, the device prioritizes users who require appropriate medical assistance and guides them to evacuation shelters.

[0053] Specific examples

[0054] For example, if flooding due to heavy rain is predicted in a certain area, the server analyzes past weather data to make a highly accurate flood forecast. At the same time, it analyzes drone images received in real time to identify areas that have already been flooded. Based on the analysis results, the server provides residents of the area with specific evacuation routes and shelter information in the event that evacuation is necessary. Furthermore, residents can enter their own health and psychological state into the application, and the server will adjust care and assistance accordingly, providing appropriate medical support.

[0055] As described above, this system is an advanced information system that handles a wide variety of data in an integrated manner and is capable of predicting disasters and providing appropriate countermeasures promptly.

[0056] The processing flow will be explained below.

[0057] Step 1:

[0058] The server collects historical weather and earthquake data, including connections to weather satellites and government databases, and periodically retrieves the latest data using communication protocols (e.g., HTTP, API).

[0059] Step 2:

[0060] The server converts the collected weather and earthquake data into a format that is easy to analyze. Specifically, it standardizes the data (e.g., standardizing temperature, precipitation, wind speed, etc.), fills in missing data, and removes noise.

[0061] Step 3:

[0062] The server uses a generative AI model to analyze weather and earthquake data and predict future disaster risks. The AI ​​model performs pattern recognition based on past data and updates the prediction model.

[0063] Step 4:

[0064] The device transmits real-time video and photos from drones and fixed cameras to a server, where the video is uploaded via the Internet.

[0065] Step 5:

[0066] The server analyzes the video and photos sent in real time, and uses generative AI to identify the extent and pattern of damage. For example, it analyzes the depth and spread of flooding to grasp the extent of damage in the relevant area.

[0067] Step 6:

[0068] The server analyzes real-time images acquired from satellites and drones, which allows for a grasp of road conditions and the extent of damage in affected areas. Satellite images are analyzed using high-resolution image analysis technology.

[0069] Step 7:

[0070] The server analyzes a database of past rescue operations and evacuation guidance, and proposes optimal rescue methods and evacuation guidance measures. Based on past success stories, a plan tailored to the local situation is generated.

[0071] Step 8:

[0072] Through the application, users input their own health and psychological conditions, such as headache, fever, and stress, into input fields.

[0073] Step 9:

[0074] The device transmits health and psychological data from the user to a server, where the data is securely transferred using end-to-end encryption technology.

[0075] Step 10:

[0076] The server analyzes the received health and psychological status data to determine appropriate care for the victims and the placement of evacuation shelters. The generating AI analyzes the data and prioritizes support for users with high urgency.

[0077] Step 11:

[0078] Based on the analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. This information is then sent to the user's device and displayed in an easy-to-understand manner.

[0079] Step 12:

[0080] The device displays the information sent from the server, including maps of safe evacuation routes, detailed information on evacuation shelters, and emergency measures. Users can evacuate safely based on this information.

[0081] Step 13:

[0082] The server records all data and feedback and uses it to improve the accuracy of the generative AI model. The model is retrained based on analysis results and user behavior data, continuously improving the accuracy of disaster prediction and response.

[0083] Example 1

[0084] 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."

[0085] When a natural disaster occurs, there is a need to provide fast and accurate information and propose countermeasures, but conventional systems take time to collect and analyze data, making it difficult to respond in real time. Furthermore, there was a lack of systems that could adequately provide appropriate care and arrange evacuation shelters taking into account the health and psychological state of victims. Furthermore, there were limited means to effectively integrate and analyze past disaster data and real-time video footage, making it difficult to propose optimal rescue operations and evacuation guidance measures.

[0086] 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.

[0087] In this invention, the server includes means for collecting and analyzing past weather and earthquake data, means for analyzing video and photos transmitted in real time to identify the extent and pattern of damage, means for analyzing images acquired from satellites and drones to grasp the situation in the disaster-stricken area, means for analyzing past rescue operation and evacuation guidance data to propose optimal countermeasures, means for analyzing the health and psychological state of disaster victims and determining care and evacuation shelter placement, means for preprocessing the collected data, filling in missing data, and removing noise, means for generating a predictive model using the collected data with a generative AI model, means for analyzing the collected video in real time to generate evacuation routes, means for providing real-time disaster information, evacuation routes, and countermeasures to users based on the analysis results, and means for displaying appropriate information and countermeasures on a terminal based on these means. This enables the provision of rapid and accurate disaster information, appropriate care for disaster victims, and the proposal of optimal rescue operations and evacuation guidance measures.

[0088] "Historical weather data" is information about past weather conditions collected from data sources such as weather observation satellites and government agencies.

[0089] "Earthquake Data" means information about past and present earthquake activity collected by seismic monitoring agencies and seismic instruments.

[0090] "Means for analysis" refers to a processing method for converting collected data into a format that is easy to analyze, cleaning the data as necessary, and then analyzing the data using a generative AI model to generate a predictive model.

[0091] "Video and photographs transmitted in real time" refers to video and photographic data that records the disaster situation and is transmitted in real time from devices such as drones and fixed cameras.

[0092] "Means for identifying the extent and pattern of damage" refers to an analytical method for analyzing video and photographs transmitted in real time to identify the extent and pattern of damage caused by a disaster.

[0093] "Images obtained from satellites and drones" are visual data taken from the sky, and are image data collected by satellites and drones that show the latest situation in the disaster-stricken areas.

[0094] "Means for understanding the situation in the disaster-stricken areas" refers to a method for analyzing images obtained from satellites and drones to understand the current situation in the disaster-stricken areas and the extent of the damage.

[0095] "Rescue operation and evacuation guidance data" refers to records of rescue operations and evacuation guidance that have been carried out in the past, and includes information on successful cases and countermeasures.

[0096] The "means of proposing optimal response measures" is a method for analyzing past rescue operations and evacuation guidance data, and proposing the most effective rescue methods and evacuation guidance measures based on the current situation.

[0097] "Health and psychological conditions of disaster victims" refers to data on the physical health and psychological conditions of disaster victims at the time of the disaster.

[0098] "Measures for determining care and shelter placement" refers to methods for analyzing the health and psychological state of disaster victims and determining the type of care needed and appropriate shelter placement.

[0099] "Preprocessing of collected data" refers to a processing method for converting data into a format that is easy to analyze, filling in missing data, and removing noise.

[0100] "Means for filling in missing data and removing noise" refers to cleaning techniques for filling in missing parts of collected data and eliminating unnecessary noise.

[0101] A "generative AI model" is a model trained using artificial intelligence, an algorithm that analyzes collected data and performs predictions and pattern recognition.

[0102] "Means for generating a predictive model" refers to a method for using a generative AI model to predict future disaster risks and predictions based on collected data.

[0103] The "means for generating evacuation routes" is a method for analyzing video footage collected in real time and determining the optimal evacuation route based on the extent of damage and road conditions.

[0104] The "means for providing disaster information, evacuation routes, and countermeasures" is a system for providing users with necessary disaster information, evacuation routes, and necessary countermeasures based on the analysis results.

[0105] MODE FOR CARRYING OUT THE INVENTION

[0106] To implement this invention, the following specific procedures and details of the hardware and software used are required. This system integrates a wide range of data, including weather data, earthquake data, real-time video, photographs, satellite and drone images, rescue operation and evacuation guidance data, and the health and psychological state of disaster victims, and quickly provides users with appropriate information and countermeasures.

[0107] Data collection and analysis

[0108] The server collects historical weather and earthquake data from data sources such as weather observation satellites and government agencies. The collected data is then converted into a format that is easy to analyze using an ETL (Extract, Transform, Load) process. Specifically, the data is converted from JSON format to CSV format and measurement units are standardized. Data cleaning is also performed, including filling in missing data and removing noise.

[0109] The generative AI model is trained using a machine learning framework (such as TENSORFLOW® or PyTorch) and analyzes past data to predict future disaster risks. A predictive model is generated based on the prediction results, and disaster risk maps and statistical data are created.

[0110] Real-time data collection and analysis

[0111] The terminal transfers real-time video and photos sent from devices such as drones and fixed cameras to a server using real-time communication protocols such as MQTT and WebSocket.

[0112] The server uses the transferred real-time data to identify the extent and pattern of damage. It uses computer vision technologies (such as OpenCV and TensorFlow) to analyze the depth and extent of flooding and generate optimal evacuation routes. Furthermore, the server analyzes images acquired from satellites and drones to obtain the latest information on the situation in the affected areas.

[0113] Rescue operations and evacuation guidance suggestions

[0114] The server manages a database of past rescue operations and evacuation guidance, which is stored using a relational database such as an SQL server. This data is analyzed and optimal rescue methods and evacuation guidance measures are proposed based on past success stories.

[0115] Analysis of the health and psychological status of disaster victims

[0116] Users input their health and psychological status into the device through the application. The input data is collected through the smartphone application and sent to the server via HTTP requests. The server then analyzes this data using a generative AI model to determine the appropriate care provision and shelter placement.

[0117] Providing information and advice

[0118] The server provides users with real-time disaster information, evacuation routes, and countermeasures based on all analysis results. The device displays this information in an easy-to-understand manner, supporting rapid evacuation and appropriate action. It also prioritizes users who require appropriate medical assistance and guides them to evacuation shelters based on their health and psychological state.

[0119] Specific examples

[0120] For example, if a certain area is predicted to be flooded due to heavy rain, the server uses an API to collect historical weather data and preprocesses the data using an ETL process. A generative AI model is used to make highly accurate flood predictions, while simultaneously analyzing real-time drone images to identify areas that have already been flooded. Based on the analysis results, the system provides residents with specific evacuation routes and shelter information. Users enter their own health and psychological state into the application, and the server analyzes this data to provide appropriate medical support.

[0121] Prompt Sentence Examples

[0122] "For the next natural disaster, please provide information on the best evacuation routes and shelters. Also, please provide procedures for special assistance for residents with illnesses or mental health issues."

[0123] As described above, this invention is an advanced information system that handles a wide variety of data in an integrated manner and quickly provides disaster prediction and appropriate countermeasures.

[0124] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0125] Step 1:

[0126] The server collects historical weather and earthquake data from data sources such as weather observation satellites and government agencies. Specifically, it periodically retrieves this data through an API and stores it in a database. The input data is in JSON or XML format, and is converted into a standardized format. The output is a dataset that can be analyzed.

[0127] Step 2:

[0128] The server preprocesses the collected data using the ETL (Extract, Transform, Load) process. It converts the data into CSV, fills in missing values, and removes noise. Specifically, it fills in missing data by averaging the preceding and following values, and removes anomalous data points. The input is the data before transformation, and the output is the preprocessed data.

[0129] Step 3:

[0130] The server inputs the preprocessed data into a generative AI model for analysis. It uses a machine learning framework (e.g., TensorFlow or PyTorch) to predict the risk of future disasters. The input is the preprocessed data, and the output is a risk prediction model and a probability map of disaster occurrence.

[0131] Step 4:

[0132] The terminal transfers real-time video and photo data from devices such as drones and fixed cameras to a server using real-time communication protocols such as MQTT and WebSocket. The input is video and photo data, and the output is real-time data transfer to the server.

[0133] Step 5:

[0134] The server analyzes the video and photos received in real time and uses computer vision technology (such as OpenCV and TensorFlow) to identify the depth and extent of flooding. The input is real-time data, and the output is the identification of the extent and pattern of damage.

[0135] Step 6:

[0136] The server analyzes images acquired from satellites and drones in real time to grasp the latest situation in the disaster-stricken areas. Image analysis is performed to quantify road traffic conditions and the extent of damage. The input is image data from satellites and drones, and the output is a report of the latest situation in the disaster-stricken areas.

[0137] Step 7:

[0138] The server manages a database of past rescue operations and evacuation guidance using a relational database such as an SQL server, analyzes this data, and proposes optimal rescue methods and evacuation guidance measures. The input is past data, and the output is the proposed rescue methods and evacuation guidance measures.

[0139] Step 8:

[0140] Users input their own health and psychological status into the device through the application. This data is sent to the server via HTTPS. The input is the user's health and psychological status data, and the output is the data sent to the server.

[0141] Step 9:

[0142] The server uses a generative AI model to analyze the user's health and psychological state data and determine the appropriate care provision and shelter placement. The input is the user's health and psychological data, and the output is the decision on care provision and shelter placement.

[0143] Step 10:

[0144] The server provides users with real-time disaster information, evacuation routes, and countermeasures based on all analysis results. This information is sent to the terminal and visually presented to the user. The input is the analysis results, and the output is the information provided to the user.

[0145] Step 11:

[0146] The device displays disaster information and evacuation routes in an easy-to-understand format for users, supporting rapid evacuation and appropriate action. The input is notification data from the server, and the output is information displayed to the user. In addition, if the user needs appropriate medical assistance based on their health and psychological state, the device will guide them to an evacuation shelter with priority.

[0147] The above is the specific flow of operation of this system.

[0148] (Application example 1)

[0149] 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."

[0150] It is difficult to provide prompt and accurate information and evacuation guidance during disasters. There is also a lack of appropriate care and shelter locations based on the psychological and physical health status of disaster victims. This often results in an inability to respond appropriately when a disaster occurs, which can lead to the spread of damage and delays in providing appropriate assistance.

[0151] 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.

[0152] In this invention, the server includes means for collecting and analyzing past weather and earthquake data, means for analyzing video and photographs transmitted in real time to identify the extent and pattern of damage, means for analyzing images acquired from satellites and drones to grasp the situation in the disaster-stricken area, means for analyzing past rescue operations and evacuation guidance data to propose optimal countermeasures, means for analyzing the health and psychological state of disaster victims and determining care and evacuation shelter placement, means for providing appropriate information and countermeasures to users based on these means, means for analyzing weather, satellite, and drone data using generation AI to propose optimal evacuation routes, and means for providing real-time navigation to evacuation shelters based on the user's location information. This enables rapid and effective disaster response and appropriate evacuation guidance based on advanced information processing.

[0153] "Historical weather data" refers to historical weather information, including weather elements such as temperature, precipitation, and wind speed.

[0154] "Earthquake data" refers to observational information about earthquakes, including details such as the epicenter, seismic intensity, and date and time of occurrence.

[0155] "Video and photos transmitted in real time" refers to visual data that captures the current situation in real time, and includes video and still images.

[0156] "Damage scope and damage pattern" refers to the physical extent of the impact of a disaster and the specific form of that impact.

[0157] "Satellite and drone-derived imagery" refers to high-resolution visual data taken from the air, such as satellites or drones.

[0158] "The situation in the affected areas" refers to the current state of the areas where the disaster occurred, including the extent of the damage and the area affected.

[0159] "Rescue operation and evacuation guidance data" refers to information on past rescue operations and evacuation cases, including both successful and unsuccessful cases.

[0160] "Optimal response" refers to the action or measure that is most appropriate for the current situation.

[0161] "The health and psychological state of the disaster victims" refers to the physical health and psychological state of the people affected by the disaster.

[0162] "Care and shelter placement" refers to the necessary support for disaster victims and the appropriate placement of shelters.

[0163] "Appropriate information and measures" refers to the correct information and guidelines for action that should be provided to users.

[0164] "Weather data, satellite data, and drone data" refers collectively to weather information and visual data taken from the air.

[0165] "Generative AI" refers to artificial intelligence technology that analyzes and predicts based on input data.

[0166] An "evacuation route" refers to a route for evacuation in the event of a disaster.

[0167] "Real-time navigation" refers to a system that provides real-time directions based on your current location.

[0168] A system that specifically embodies the present invention is configured as follows.

[0169] Hardware and software used

[0170] The system uses hardware such as servers, smartphones, drones, and satellites, as well as the following software:

[0171] 1. Python

[0172] 2. OpenCV (Drone video analysis)

[0173] 3. scikit-learn (data analysis and predictive models)

[0174] 4. TensorFlow (generative AI models)

[0175] 5. geopy (distance calculation)

[0176] Data collection and analysis

[0177] First, the server collects weather and earthquake data from various data sources (weather observation satellites and government agencies). The collected data is cleaned and converted into a format that is easy to analyze. The server then uses a generative AI model to analyze this past data and predict future disaster risks.

[0178] Real-time data collection and analysis

[0179] The terminal then transfers real-time video and photos sent from devices such as drones and fixed cameras to a server. The server uses this real-time data to identify the extent and pattern of damage. The server also analyzes images acquired from satellites and drones in real time to grasp the latest situation in the affected area.

[0180] Rescue operations and evacuation guidance suggestions

[0181] The server analyzes a database of past rescue operations and evacuation guidance, proposing optimal rescue methods and evacuation guidance measures. This analysis is based on past successful cases, enabling a swift and effective response tailored to the current situation in the disaster area.

[0182] Analysis of the health and psychological status of disaster victims

[0183] Users enter their own health and psychological state into the device through the application. The device then sends this data to a server, which then analyzes it using generative AI. Based on this analysis, appropriate care for disaster victims and the placement of evacuation shelters are determined.

[0184] Information and navigation

[0185] Based on all of the above analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. The device displays this information in an easy-to-understand manner, supporting rapid evacuation and appropriate action. Real-time navigation to evacuation shelters is also provided based on the user's location information.

[0186] Specific examples

[0187] For example, in this application, named "Emergency Guardian," if a user is in an area where flooding due to heavy rain is predicted, the server analyzes past weather data to make highly accurate flood predictions. At the same time, it analyzes drone images received in real time to identify areas that have already been flooded. Based on the analysis results, the server provides residents in the area with specific evacuation routes and shelter information in the event that evacuation is necessary. Furthermore, residents can enter their own health and psychological state into the application, and the server will adjust care and assistance accordingly, providing appropriate medical support.

[0188] Prompt Sentence Examples

[0189] Weather data: {weather_data}, Satellite data: {satellite_data}, Drone data: {drone_data}

[0190] Please analyze the above data and provide the best evacuation route."

[0191] This will enable rapid and effective disaster response and appropriate evacuation guidance based on advanced information processing.

[0192] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0193] Step 1:

[0194] The server collects historical weather and earthquake data. The input is data provided by weather observation satellites and government agencies, and the output is raw data stored on the server for analysis. Specifically, the server retrieves data through an API and stores it in a database.

[0195] Step 2:

[0196] The server analyzes the collected weather and earthquake data. The input is the past weather and earthquake data saved in step 1, and the output is the result of predicting future disaster risk based on the generative AI model. Specific operations include data cleaning, noise removal, and application of analysis algorithms.

[0197] Step 3:

[0198] The terminal transfers the video and photos sent in real time from drones, fixed cameras, etc. to the server. The input is the real-time video and photos sent from the drones or fixed cameras, and the output is the data transferred to the server. Specifically, the terminal receives the data, converts it into an appropriate format, and sends it to the server.

[0199] Step 4:

[0200] The server uses real-time data to identify the extent and pattern of damage. The input is the video and photos received in step 3, and the output is the analysis results that identify the extent and pattern of damage. Specifically, it applies an image analysis algorithm to identify the depth and spread of flooding.

[0201] Step 5:

[0202] The server analyzes images acquired from satellites and drones in real time. The input is images acquired from satellites and drones, and the output is the latest status of the affected areas. Specifically, image analysis technology is used to identify traffic conditions on major roads and the extent of damage.

[0203] Step 6:

[0204] The server analyzes data on past rescue operations and evacuation guidance, and proposes optimal countermeasures. The input is past rescue operation and evacuation guidance data, and the output is the results of proposing optimal rescue methods and evacuation guidance measures. Specifically, it performs data analysis based on past successful cases.

[0205] Step 7:

[0206] The user inputs their own health and psychological state into the device through the application. The input is the user's health and psychological state data, and the output is data that is saved on the device and sent to the server. Specifically, the data input from the device is sent to the server.

[0207] Step 8:

[0208] The server analyzes the health and psychological status data using a generative AI model. The input is the data sent in step 7, and the output is the results of determining the appropriate care provision and shelter location. Specifically, the server uses generative AI to analyze the data and propose appropriate countermeasures.

[0209] Step 9:

[0210] The server provides the user with appropriate information and countermeasures based on the analysis results. The input is the analysis results mentioned above, and the output is specific evacuation route and shelter information notified to the user. Specifically, the server calculates evacuation routes in real time and sends the information to the terminal.

[0211] Step 10:

[0212] The terminal provides real-time navigation to evacuation shelters based on the user's location information. The input is the user's location information from GPS etc. and evacuation route information received from the server, and the output is navigation information displayed in a format that is easy for the user to view. Specifically, the terminal integrates GPS data and evacuation route information and displays it on the screen.

[0213] 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.

[0214] As an embodiment of this invention, the operation of the system is explained step by step below. This system incorporates weather data, earthquake data, real-time video and photos, satellite and drone images, rescue operation and evacuation guidance data, the health and psychological state of disaster victims, and an emotion engine that recognizes the user's emotions. This allows the system to provide the user with optimal information and countermeasures.

[0215] Data collection and analysis

[0216] First, the server collects historical weather and earthquake data from various data sources (weather observation satellites and government agencies). The collected data is converted into an easy-to-analyze format, and data cleaning is performed to fill in missing data and remove noise. A generative AI model analyzes this historical data and predicts future disaster risk. After the analysis is complete, a predictive model is generated.

[0217] Real-time data collection and analysis

[0218] The device then transfers real-time video and photos from devices such as drones and fixed cameras to a server. The server uses this real-time data to identify the extent and pattern of damage. For example, the server analyzes the depth and spread of flooding and generates optimal evacuation routes.

[0219] The server also analyzes images acquired from satellites and drones in real time to obtain the latest information on the situation in the affected areas, including the traffic status of major roads and the extent of damage in the affected areas.

[0220] Rescue operations and evacuation guidance suggestions

[0221] The server analyzes a database of past rescue operations and evacuation guidance, proposing optimal rescue methods and evacuation guidance measures. This analysis is based on past successful cases, enabling a swift and effective response tailored to the current situation in the disaster area.

[0222] Analysis of the health and psychological status of disaster victims

[0223] Users enter their own health and psychological state into the device through the application. The device then sends this data to a server, which then analyzes it using generative AI. Based on this analysis, appropriate care for disaster victims and the location of evacuation shelters are determined.

[0224] Emotion recognition by emotion engine

[0225] When the user inputs their health status, the device captures their voice and facial expressions and analyzes them using an emotion engine. The emotion engine analyzes their voice and facial expressions to recognize the user's emotions. For example, it can determine whether the user is feeling stressed or calm.

[0226] Providing information and advice

[0227] Based on all of the above analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. The device displays this information in an easy-to-understand manner, supporting rapid evacuation and appropriate action. Additionally, depending on changes in the user's health or psychological state, the device prioritizes users who require appropriate medical assistance and guides them to evacuation shelters.

[0228] Furthermore, based on the emotion recognition results of the emotion engine, stress management and psychological support information is provided to users, allowing them to receive psychological support even in times of disaster.

[0229] Specific examples

[0230] For example, if a certain area is predicted to be flooded due to heavy rain, the server will analyze past weather data to generate a highly accurate flood forecast. At the same time, it will analyze drone images received in real time to identify areas that are already flooded. Based on the analysis results, the server will provide residents of the area with specific evacuation routes and shelter information in the event that evacuation is necessary.

[0231] Residents enter their physical and psychological state into the application, and the emotion engine measures their stress levels. The server then analyzes the information and provides medical assistance as needed. As a result, residents can evacuate with peace of mind and be quickly guided to a safe location.

[0232] As described above, this system is an advanced information system that makes integrated use of a wide variety of data and an emotion engine to quickly predict disasters and provide appropriate countermeasures, thereby ensuring the safety and psychological support of users.

[0233] The processing flow will be explained below.

[0234] Step 1:

[0235] The server collects historical weather and earthquake data from various sources, including weather satellites and government databases, and periodically retrieves the latest data using communication protocols (e.g., HTTP, API).

[0236] Step 2:

[0237] The server converts the collected weather and earthquake data into a format that is easy to analyze. Specifically, it standardizes the data (e.g., standardizing temperature, precipitation, wind speed, etc.), fills in missing data, and removes noise.

[0238] Step 3:

[0239] The server uses a generative AI model to analyze weather and earthquake data and predict future disaster risks. The AI ​​model performs pattern recognition based on past data and updates the prediction model.

[0240] Step 4:

[0241] The device collects data on the user's health and psychological state, and the user inputs their physical condition, stress level, etc. using a dedicated application.

[0242] Step 5:

[0243] The device captures the user's voice and facial expressions and sends them to the emotion engine, which then understands the user's emotions.

[0244] Step 6:

[0245] The emotion engine uses voice and facial expression analysis to recognize the user's emotions, for example, determining whether the user is feeling stressed or relieved.

[0246] Step 7:

[0247] The device transmits the collected health, psychological, and emotional data to a server, where the data is securely transferred using end-to-end encryption technology.

[0248] Step 8:

[0249] The server analyzes the received data using a generative AI model to assess the user's health and psychological state, and makes decisions about providing care and locating evacuation shelters based on this.

[0250] Step 9:

[0251] The device transmits real-time video and photos from drones and fixed cameras to a server, where the video is uploaded via the Internet.

[0252] Step 10:

[0253] The server analyzes the video and photos sent in real time, and uses generative AI to identify the extent and pattern of damage. For example, it analyzes the depth and spread of flooding to grasp the extent of damage in the relevant area.

[0254] Step 11:

[0255] The server analyzes real-time images acquired from satellites and drones, providing an up-to-date understanding of the situation in the affected areas, including the passability of major roads and the extent of damage in the affected areas.

[0256] Step 12:

[0257] The server analyzes a database of past rescue operations and evacuation guidance, and proposes optimal rescue methods and evacuation guidance measures. Based on past success stories, a plan tailored to the local situation is generated.

[0258] Step 13:

[0259] Based on all of the above analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. This information is then sent to the user's device and displayed in an easy-to-understand format.

[0260] Step 14:

[0261] The device displays the information sent from the server, including maps of safe evacuation routes, detailed information on evacuation shelters, and emergency measures. Users can evacuate safely based on this information.

[0262] Step 15:

[0263] Based on the recognition results of the emotion engine, the server provides users with information on stress management and psychological support, which helps users to evacuate safely while receiving psychological support.

[0264] Step 16:

[0265] The server records all data and feedback and uses it to improve the accuracy of the generative AI model. The model is retrained based on analysis results and user behavior data, continuously improving the accuracy of disaster prediction and response.

[0266] Example 2

[0267] 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."

[0268] In order to carry out appropriate evacuation and rescue operations quickly and effectively during disasters, it is necessary to collect and analyze a wide variety of data in real time and provide users with appropriate information and countermeasures. However, conventional systems have limitations in the accuracy of data collection and analysis, making it difficult to respond quickly. Furthermore, they do not adequately provide support that takes into account the health, psychological state, and emotions of disaster victims. For these reasons, improving safety and psychological support during disasters is a challenge.

[0269] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting past weather data and earthquake data and analyzing this data, means for analyzing videos and photos transmitted in real time to identify the extent and pattern of damage, means for analyzing images acquired from satellites and drones to grasp the situation in the disaster-stricken area, means for analyzing past rescue operations and evacuation guidance data to propose optimal countermeasures, means for analyzing the health and psychological states of disaster victims and determining care and shelter placement, and means for analyzing the user's voice and facial expressions using an emotion engine to recognize the user's emotional state. This enables rapid analysis of various data and provision of appropriate information taking into account the user's health and emotional state.

[0270] "Weather data" refers to weather observation results and forecast information such as temperature, precipitation, wind speed, wind direction, and humidity.

[0271] "Earthquake data" refers to observation results related to earthquakes, including data such as the earthquake's seismic intensity, epicenter, and date and time of occurrence.

[0272] "Analysis means" refers to devices or software that perform calculations and statistical processing on collected data to extract and interpret specific information.

[0273] "Real-time data" refers to data that can be immediately acquired and analyzed based on the current situation.

[0274] "Footage and photographs" refers to visual data captured by photographic equipment such as cameras and drones.

[0275] "Affected area" refers to the geographic area affected by a disaster.

[0276] "Damage pattern" refers to the type and distribution of specific impacts and damage caused by a disaster.

[0277] "Satellite imagery" refers to image data of the Earth captured by sensors mounted on artificial satellites.

[0278] "Drone imagery" refers to image data captured by an unmanned aerial vehicle.

[0279] "Situational awareness" refers to the act of understanding the current situation or state based on collected data.

[0280] "Rescue activities" refers to activities such as saving lives, distributing supplies, and providing medical support during disasters.

[0281] "Evacuation guidance" refers to the act of instructing and guiding people to a safe place during a disaster.

[0282] "Health status" refers to information about physical health, such as the state of each bodily function and tissue, and the presence or absence of disease.

[0283] "Psychological state" refers to information about mental states such as stress, anxiety, and mental well-being.

[0284] An "emotion engine" refers to an algorithm or system that analyzes and identifies emotions from a user's voice, facial expressions, etc.

[0285] A "generative AI model" refers to an artificial intelligence model that learns from large amounts of data and makes highly accurate predictions and analyses of new data.

[0286] "Appropriate information and measures" refers to information and measures that will enable users to evacuate safely and obtain the necessary support in the event of a disaster.

[0287] The present invention is a system that collects and analyzes a variety of data and provides prompt and appropriate information and countermeasures in the event of a disaster. A specific example of this system will be described below.

[0288] Data collection and analysis

[0289] The server collects historical weather and earthquake data from weather observation satellites and government agencies. This data is converted into an easy-to-analyze format and cleaned to fill in missing data and remove noise. A suitable tool for this is the Python pandas library.

[0290] Analysis using generative AI models

[0291] The server analyzes the collected and cleaned data using a generative AI model, specifically using deep learning frameworks such as TensorFlow and PyTorch to build a disaster risk prediction model.

[0292] Real-time data collection

[0293] The device transfers real-time video and photos from drones and fixed cameras to a server, and can transmit data over Wi-Fi or 5G networks.

[0294] Real-time data analysis

[0295] The server uses the received real-time data to identify the extent and pattern of damage. For example, it can use OpenCV to perform image analysis to identify the depth and spread of flooding. It can also use object detection algorithms to check the traffic status of major roads.

[0296] Rescue operations and evacuation guidance suggestions

[0297] The server analyzes past rescue operations and evacuation guidance data and proposes optimal rescue methods and evacuation guidance measures. This is achieved by searching for and analyzing the necessary information from the database using SQL queries.

[0298] Analysis of the health and psychological status of disaster victims

[0299] Users input their own health and psychological status through the application. The device then sends this data to a server, which then uses generative AI to analyze the data. For example, NLP (natural language processing) technology can be used to analyze the user's input text and determine the priority of medical assistance.

[0300] Emotion recognition by emotion engine

[0301] When a user enters their health status, the device captures the user's voice and facial expressions and analyzes them using an emotion engine. The emotion engine uses deep learning models to analyze the voice and facial expressions and recognize the user's emotions. For example, a model built using the Keras library can be used to determine whether the user is feeling stressed.

[0302] Providing information and advice

[0303] Based on all of the above analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. The device uses HTML5 and JavaScript (registered trademark) to display this information in an easy-to-understand manner. For example, evacuation routes can be displayed on a map using the Google (registered trademark) Maps API.

[0304] Specific examples

[0305] For example, if heavy rain is predicted to cause flooding in a certain area, the server will use past weather data to generate highly accurate flood predictions. At the same time, it will analyze drone images received in real time to identify areas that are already flooded. Based on this information, the server will provide specific evacuation routes and shelter information to residents in the area.

[0306] Prompt Sentence Examples

[0307] "Please suggest evacuation measures for areas predicted to be flooded by heavy rain. Based on the analysis results of historical weather data and drone imagery, please tell us how to provide specific evacuation routes and necessary medical assistance."

[0308] As described above, this system is an advanced information system that makes integrated use of a wide variety of data and an emotion engine to quickly predict disasters and provide appropriate countermeasures, thereby ensuring the safety and psychological support of users.

[0309] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0310] Step 1:

[0311] The server collects past weather and earthquake data from weather observation satellites and government agencies. Specifically, it acquires the data using the API of the Japan Meteorological Agency and the API of satellite data providers and stores it in a database. The input is a dataset from each API, and the output is a dataset for preparation for analysis.

[0312] Step 2:

[0313] The server converts the acquired data into a format suitable for analysis. It uses the Python pandas library to convert the data into CSV format, imputes missing data, and removes noise. The input is the collected raw data, and the output is the cleaned and formatted data.

[0314] Step 3:

[0315] The server feeds the cleaned data into a generative AI model to build a model that predicts future disaster risk. It uses TensorFlow and PyTorch to train the deep learning model and output the prediction results. The input is the cleaned dataset, and the output is a disaster risk prediction model and the prediction results.

[0316] Step 4:

[0317] The terminal transfers real-time video and photos sent from drones and fixed cameras to a server. The device transmits data using Wi-Fi or 5G. The input is real-time video and photos from the device, and the output is data transferred to the server.

[0318] Step 5:

[0319] The server analyzes the received real-time data to identify the extent and pattern of damage. It uses OpenCV to perform image analysis to determine the depth and extent of flooding and the traffic situation on major roads. The input is real-time video and photos, and the output is the results of identifying the extent and pattern of damage.

[0320] Step 6:

[0321] The server analyzes past rescue operation and evacuation guidance data and proposes optimal rescue methods and evacuation guidance measures. It searches the database using SQL queries and creates rescue plans based on the analysis results. The input is past rescue operation data, and the output is the proposed rescue method and evacuation guidance measures.

[0322] Step 7:

[0323] Users input their own health and psychological state through the application. The device sends this to the server, which analyzes it using generative AI. NLP technology is used to analyze the input text and determine the priority of medical assistance. The input is the user's health and psychological state data, and the output is the analysis results and the priority of medical assistance.

[0324] Step 8:

[0325] The device captures the user's voice and facial expressions and analyzes them using an emotion engine. The emotion engine uses a deep learning model to analyze the voice and facial expressions and recognize the user's emotions. The input is the user's voice and facial expression data, and the output is the recognized emotional state.

[0326] Step 9:

[0327] The server provides users with real-time disaster information, evacuation routes, and countermeasures based on all analysis results. The device displays this information in an easy-to-understand manner and prioritizes the provision of necessary medical assistance. Information is visualized using HTML5 and JavaScript, and evacuation routes are displayed using the Google Maps API. The input is various analysis results, and the output is specific disaster information and evacuation routes that are displayed to the user.

[0328] (Application example 2)

[0329] 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."

[0330] When a disaster occurs, it is difficult to grasp the situation in the affected area and provide victims with prompt and appropriate information. At the same time, there is a need to provide food and other necessities quickly, accurately grasp the health and psychological state of victims, and provide psychological care. To solve these problems, a system is needed that can collect and analyze information from multiple data sources in real time and quickly propose countermeasures.

[0331] The identification processing 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 means for collecting past weather data and earthquake data and analyzing this data, means for analyzing videos and photos transmitted in real time to identify the extent and pattern of damage, means for analyzing images acquired from satellites and drones to grasp the situation in the disaster-stricken area, means for analyzing past rescue operations and evacuation guidance data to propose optimal countermeasures, means for analyzing the health and psychological states of disaster victims and determining care and shelter placement, means for providing food to disaster-stricken areas using drones and autonomous mobile devices, means for understanding the psychological states of disaster victims using emotion recognition technology and providing stress management information, and means for providing appropriate information and countermeasures to users based on these means. This enables accurate and rapid understanding of the situation in the disaster-stricken area, rapid provision of supplies including food, and appropriate information and psychological support to disaster victims.

[0332] "Past weather data" refers to data relating to weather observed in the past, including information such as temperature, precipitation, wind speed, wind direction, and humidity.

[0333] "Earthquake data" refers to data that includes information on the epicenter, seismic intensity, and waveforms of shaking at the time of an earthquake, and is the basis for analyzing the scale and extent of an earthquake's impact.

[0334] "Video and photos transmitted in real time" refers to video and still image data obtained by instantly photographing and recording the current situation and then instantly transmitting that data.

[0335] "Damage range and damage pattern" is pattern information that indicates the range of the area affected by the disaster and the type and scale of the damage.

[0336] "Imagery obtained from satellites and drones" refers to image data taken from the air, including images of the earth's surface taken by satellites or unmanned aerial vehicles.

[0337] "Status of the affected areas" refers to data showing the current state of the affected areas at the time of the disaster and afterwards, including the scale, scope and detailed information of the damage.

[0338] "Past rescue operation and evacuation guidance data" refers to data on rescue and evacuation operations that have been carried out in the past, including success stories, failure stories, and information on the processes involved.

[0339] "Optimal response measures" are proposals based on analyzed data that propose optimal guidelines for action, evacuation routes, rescue methods, etc. for affected areas and victims.

[0340] "The health and psychological state of the disaster victims" is data indicating the physical health and psychological state of the disaster victims.

[0341] "Care and sheltering" refers to providing medical and psychological support to disaster victims, as well as the provision and arrangement of appropriate shelter.

[0342] "Drones and autonomous mobile devices" refers to unmanned aerial vehicles and ground mobile devices that use autonomous driving technology, which can be used to transport supplies and food.

[0343] "Emotion recognition technology" is a technology that identifies human emotions through voice analysis and facial expression analysis, and evaluates psychological states such as stress and a sense of security.

[0344] This invention is a system for collecting and analyzing information in the event of a disaster, and providing appropriate countermeasures. The system collects various data, analyzes it, and provides information to users in real time. It also uses drones and autonomous mobile devices to quickly provide food and relief supplies.

[0345] Hardware Configuration

[0346] Server: Processes data and analyzes the generated AI model.

[0347] Cloud server: Data storage and big data analysis are performed using AWS (registered trademark).

[0348] Drones: Collect images of disaster areas and deliver supplies.

[0349] Autonomous mobile devices: Distribute food and relief supplies on the ground.

[0350] Smartphone: Used as a device for users to input their health and psychological status.

[0351] Fixed cameras: Providing real-time footage of the affected areas.

[0352] Software Configuration

[0353] Python: A programming language for data analysis, specifically using Scikit-learn and TensorFlow.

[0354] OpenCV: A library for performing image analysis.

[0355] AWS Lambda: An AWS service for serverless data processing.

[0356] Emotion Engine API: Technology that recognizes emotions through voice and facial expression analysis.

[0357] Data collection and analysis process

[0358] 1. Historical data collection and analysis:

[0359] The server collects historical weather and earthquake data from government agencies and weather observation satellites, which is then analyzed using a generative AI model to predict future disaster risks.

[0360] 2. Real-time data collection:

[0361] Real-time video and photos from drones and fixed cameras are sent to a server, which analyzes the data to identify the extent and pattern of damage.

[0362] 3. Understanding the situation in the affected areas:

[0363] Images acquired from satellites and drones will be analyzed to provide an up-to-date picture of the situation in the affected areas, including road conditions and the extent of damage.

[0364] 4. Suggestions for rescue operations and evacuation:

[0365] The server analyzes past rescue operations and evacuation guidance data and proposes the optimal response measures.

[0366] 5. Health and Psychological Analysis:

[0367] Users input their health and psychological state using their smartphones, which is then analyzed by the server. An emotion engine is used to recognize the user's emotions and provide stress management information.

[0368] 6. Information provision and implementation of measures:

[0369] Based on all the above analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. It also uses drones and autonomous mobile devices to quickly deliver food to disaster-stricken areas.

[0370] Specific examples

[0371] For example, if a flood is predicted in a certain area, the server analyzes past weather data to generate a highly accurate flood forecast. At the same time, it analyzes drone images received in real time to identify flooded areas. As a result, it provides information on optimal evacuation routes and evacuation shelters. It also provides necessary medical assistance and psychological support based on the individual's health and psychological state.

[0372] Prompt Sentence Examples

[0373] Below are some example prompts to input to the generative AI model:

[0374] Based on the information below, please suggest appropriate evacuation routes and food distribution methods for the affected areas.

[0375] Weather data: {Weather data details}

[0376] Satellite image: {satellite image URL}

[0377] Real-time imagery from drone: {drone image URL}

[0378] Victim's health status: {health status data}

[0379] Victim's psychological state: {Psychological state data}

[0380] Emotion analysis result: {Emotion analysis result}

[0381] This system is capable of quickly analyzing huge amounts of data and providing appropriate information and assistance in real time.

[0382] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0383] Step 1:

[0384] The server collects historical weather and earthquake data.

[0385] Input: Data from weather satellites and government agencies

[0386] How it works: The server queries these data sources through APIs to retrieve weather and earthquake data.

[0387] Output: Data obtained in the form of historical weather and earthquake data

[0388] Step 2:

[0389] The server analyzes the collected historical data and uses a generative AI model to predict the risk of future disasters.

[0390] Input: Weather and earthquake data collected in Step 1

[0391] How it works: Cleans data and converts it into an analyzable format. Enters prompts into a generative AI model to perform predictive calculations.

[0392] Output: Prediction data of future disaster risk

[0393] Step 3:

[0394] Video and photos are transmitted in real time to identify the extent and pattern of damage.

[0395] Input: Real-time video and photos from drones and fixed cameras

[0396] Operation: The server receives the video data and analyzes it using OpenCV. It identifies the extent and pattern of damage and analyzes the image data.

[0397] Output: Specific information on the extent and pattern of damage

[0398] Step 4:

[0399] Images obtained from satellites and drones are analyzed to understand the situation in the affected areas.

[0400] Input: Satellite and drone imagery

[0401] Operation: The server receives images acquired from satellites and drones and analyzes them using OpenCV to grasp the current situation in the affected areas, determine road traffic conditions, and the extent of damage.

[0402] Output: Situation data of the affected area

[0403] Step 5:

[0404] We analyze past rescue operations and evacuation guidance data to propose optimal response measures.

[0405] Input: Past rescue operations and evacuation guidance data stored in the database

[0406] How it works: The server analyzes historical data and uses generative AI models to generate optimal rescue operations and evacuation guidance prompts.

[0407] Output: Proposal data for optimal countermeasures

[0408] Step 6:

[0409] Analyze the health and psychological state of disaster victims to determine care and evacuation placement.

[0410] Input: Health and psychological data entered by the user into the device, and analysis results by the emotion engine

[0411] How it works: The server uses generative AI models to analyze data and determine appropriate care and shelter placement. It also uses an emotion engine to provide stress management information.

[0412] Output: Care and shelter placement proposal data

[0413] Step 7:

[0414] Delivering food to disaster-stricken areas using drones and autonomous mobile devices.

[0415] Input: Situation data of the affected area, location information of the victims

[0416] How it works: The server analyzes the optimal route and sends instructions to drones and autonomous mobile devices, which then deliver food to disaster-stricken areas.

[0417] Output: Data on completed delivery of supplies and food

[0418] Step 8:

[0419] Provide users with appropriate information and measures.

[0420] Input: Analysis results from the above steps and proposed data

[0421] How it works: The server compiles this data and sends it to the user's device. The user receives the appropriate information on their smartphone and can take action.

[0422] Output: Appropriate information and measures to be sent to the user's device

[0423] In this way, data collection, analysis, and execution are performed in coordination at each step, enabling rapid response and support for disaster victims.

[0424] 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.

[0425] 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.

[0426] 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.

[0427] [Second embodiment]

[0428] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0429] 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.

[0430] 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).

[0431] 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.

[0432] 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.

[0433] 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).

[0434] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] 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."

[0440] As an embodiment of the present invention, the operation of the system is explained step by step below. This system collects and analyzes a wide range of data, such as weather data, earthquake data, real-time video and photos, satellite and drone images, rescue operation and evacuation guidance data, and the health and psychological state of disaster victims, and provides users with appropriate information and countermeasures.

[0441] Data collection and analysis

[0442] First, the server collects historical weather and earthquake data from various data sources (weather observation satellites and government agencies). The collected data is converted into an easy-to-analyze format, and data cleaning is performed to fill in missing data and remove noise. A generative AI model analyzes this historical data and predicts future disaster risk. After the analysis is complete, a predictive model is generated.

[0443] Real-time data collection and analysis

[0444] The device then transfers real-time video and photos from devices such as drones and fixed cameras to a server. The server uses this real-time data to identify the extent and pattern of damage. For example, the server analyzes the depth and spread of flooding and generates optimal evacuation routes.

[0445] The server also analyzes images acquired from satellites and drones in real time to obtain the latest information on the situation in the affected areas, including the traffic status of major roads and the extent of damage in the affected areas.

[0446] Rescue operations and evacuation guidance suggestions

[0447] The server analyzes a database of past rescue operations and evacuation guidance, proposing optimal rescue methods and evacuation guidance measures. This analysis is based on past successful cases, enabling a swift and effective response tailored to the current situation in the disaster area.

[0448] Analysis of the health and psychological status of disaster victims

[0449] Users enter their own health and psychological state into the device through the application. The device then sends this data to a server, which then analyzes it using generative AI. Based on this analysis, appropriate care for disaster victims and the location of evacuation shelters are determined.

[0450] Providing information and advice

[0451] Based on all of the above analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. The device displays this information in an easy-to-understand manner, supporting rapid evacuation and appropriate action. Additionally, depending on changes in the user's health or psychological state, the device prioritizes users who require appropriate medical assistance and guides them to evacuation shelters.

[0452] Specific examples

[0453] For example, if flooding due to heavy rain is predicted in a certain area, the server analyzes past weather data to make a highly accurate flood forecast. At the same time, it analyzes drone images received in real time to identify areas that have already been flooded. Based on the analysis results, the server provides residents of the area with specific evacuation routes and shelter information in the event that evacuation is necessary. Furthermore, residents can enter their own health and psychological state into the application, and the server will adjust care and assistance accordingly, providing appropriate medical support.

[0454] As described above, this system is an advanced information system that handles a wide variety of data in an integrated manner and is capable of predicting disasters and providing appropriate countermeasures promptly.

[0455] The processing flow will be explained below.

[0456] Step 1:

[0457] The server collects historical weather and earthquake data, including connections to weather satellites and government databases, and periodically retrieves the latest data using communication protocols (e.g., HTTP, API).

[0458] Step 2:

[0459] The server converts the collected weather and earthquake data into a format that is easy to analyze. Specifically, it standardizes the data (e.g., standardizing temperature, precipitation, wind speed, etc.), fills in missing data, and removes noise.

[0460] Step 3:

[0461] The server uses a generative AI model to analyze weather and earthquake data and predict future disaster risks. The AI ​​model performs pattern recognition based on past data and updates the prediction model.

[0462] Step 4:

[0463] The device transmits real-time video and photos from drones and fixed cameras to a server, where the video is uploaded via the Internet.

[0464] Step 5:

[0465] The server analyzes the video and photos sent in real time, and uses generative AI to identify the extent and pattern of damage. For example, it analyzes the depth and spread of flooding to grasp the extent of damage in the relevant area.

[0466] Step 6:

[0467] The server analyzes real-time images acquired from satellites and drones, which allows for a grasp of road conditions and the extent of damage in affected areas. Satellite images are analyzed using high-resolution image analysis technology.

[0468] Step 7:

[0469] The server analyzes a database of past rescue operations and evacuation guidance, and proposes optimal rescue methods and evacuation guidance measures. Based on past success stories, a plan tailored to the local situation is generated.

[0470] Step 8:

[0471] Through the application, users input their own health and psychological conditions, such as headache, fever, and stress, into input fields.

[0472] Step 9:

[0473] The device transmits health and psychological data from the user to a server, where the data is securely transferred using end-to-end encryption technology.

[0474] Step 10:

[0475] The server analyzes the received health and psychological status data to determine appropriate care for the victims and the placement of evacuation shelters. The generating AI analyzes the data and prioritizes support for users with high urgency.

[0476] Step 11:

[0477] Based on the analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. This information is then sent to the user's device and displayed in an easy-to-understand manner.

[0478] Step 12:

[0479] The device displays the information sent from the server, including maps of safe evacuation routes, detailed information on evacuation shelters, and emergency measures. Users can evacuate safely based on this information.

[0480] Step 13:

[0481] The server records all data and feedback and uses it to improve the accuracy of the generative AI model. The model is retrained based on analysis results and user behavior data, continuously improving the accuracy of disaster prediction and response.

[0482] Example 1

[0483] 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."

[0484] When a natural disaster occurs, there is a need to provide fast and accurate information and propose countermeasures, but conventional systems take time to collect and analyze data, making it difficult to respond in real time. Furthermore, there was a lack of systems that could adequately provide appropriate care and arrange evacuation shelters taking into account the health and psychological state of victims. Furthermore, there were limited means to effectively integrate and analyze past disaster data and real-time video footage, making it difficult to propose optimal rescue operations and evacuation guidance measures.

[0485] 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.

[0486] In this invention, the server includes means for collecting and analyzing past weather and earthquake data, means for analyzing video and photos transmitted in real time to identify the extent and pattern of damage, means for analyzing images acquired from satellites and drones to grasp the situation in the disaster-stricken area, means for analyzing past rescue operation and evacuation guidance data to propose optimal countermeasures, means for analyzing the health and psychological state of disaster victims and determining care and evacuation shelter placement, means for preprocessing the collected data, filling in missing data, and removing noise, means for generating a predictive model using the collected data with a generative AI model, means for analyzing the collected video in real time to generate evacuation routes, means for providing real-time disaster information, evacuation routes, and countermeasures to users based on the analysis results, and means for displaying appropriate information and countermeasures on a terminal based on these means. This enables the provision of rapid and accurate disaster information, appropriate care for disaster victims, and the proposal of optimal rescue operations and evacuation guidance measures.

[0487] "Historical weather data" is information about past weather conditions collected from data sources such as weather observation satellites and government agencies.

[0488] "Earthquake Data" means information about past and present earthquake activity collected by seismic monitoring agencies and seismic instruments.

[0489] "Means for analysis" refers to a processing method for converting collected data into a format that is easy to analyze, cleaning the data as necessary, and then analyzing the data using a generative AI model to generate a predictive model.

[0490] "Video and photographs transmitted in real time" refers to video and photographic data that records the disaster situation and is transmitted in real time from devices such as drones and fixed cameras.

[0491] "Means for identifying the extent and pattern of damage" refers to an analytical method for analyzing video and photographs transmitted in real time to identify the extent and pattern of damage caused by a disaster.

[0492] "Images obtained from satellites and drones" are visual data taken from the sky, and are image data collected by satellites and drones that show the latest situation in the disaster-stricken areas.

[0493] "Means for understanding the situation in the disaster-stricken areas" refers to a method for analyzing images obtained from satellites and drones to understand the current situation in the disaster-stricken areas and the extent of the damage.

[0494] "Rescue operation and evacuation guidance data" refers to records of rescue operations and evacuation guidance that have been carried out in the past, and includes information on successful cases and countermeasures.

[0495] The "means of proposing optimal response measures" is a method for analyzing past rescue operations and evacuation guidance data, and proposing the most effective rescue methods and evacuation guidance measures based on the current situation.

[0496] "Health and psychological conditions of disaster victims" refers to data on the physical health and psychological conditions of disaster victims at the time of the disaster.

[0497] "Measures for determining care and shelter placement" refers to methods for analyzing the health and psychological state of disaster victims and determining the type of care needed and appropriate shelter placement.

[0498] "Preprocessing of collected data" refers to a processing method for converting data into a format that is easy to analyze, filling in missing data, and removing noise.

[0499] "Means for filling in missing data and removing noise" refers to cleaning techniques for filling in missing parts of collected data and eliminating unnecessary noise.

[0500] A "generative AI model" is a model trained using artificial intelligence, an algorithm that analyzes collected data and performs predictions and pattern recognition.

[0501] "Means for generating a predictive model" refers to a method for using a generative AI model to predict future disaster risks and predictions based on collected data.

[0502] The "means for generating evacuation routes" is a method for analyzing video footage collected in real time and determining the optimal evacuation route based on the extent of damage and road conditions.

[0503] The "means for providing disaster information, evacuation routes, and countermeasures" is a system for providing users with necessary disaster information, evacuation routes, and necessary countermeasures based on the analysis results.

[0504] MODE FOR CARRYING OUT THE INVENTION

[0505] To implement this invention, the following specific procedures and details of the hardware and software used are required. This system integrates a wide range of data, including weather data, earthquake data, real-time video, photographs, satellite and drone images, rescue operation and evacuation guidance data, and the health and psychological state of disaster victims, and quickly provides users with appropriate information and countermeasures.

[0506] Data collection and analysis

[0507] The server collects historical weather and earthquake data from data sources such as weather observation satellites and government agencies. The collected data is then converted into a format that is easy to analyze using an ETL (Extract, Transform, Load) process. Specifically, the data is converted from JSON format to CSV format and measurement units are standardized. Data cleaning is also performed, including filling in missing data and removing noise.

[0508] The generative AI model is trained using a machine learning framework (such as TensorFlow or PyTorch) to analyze past data and predict future disaster risk. Based on the prediction results, a predictive model is generated, and disaster risk maps and statistical data are created.

[0509] Real-time data collection and analysis

[0510] The terminal transfers real-time video and photos sent from devices such as drones and fixed cameras to a server using real-time communication protocols such as MQTT and WebSocket.

[0511] The server uses the transferred real-time data to identify the extent and pattern of damage. It uses computer vision technologies (such as OpenCV and TensorFlow) to analyze the depth and extent of flooding and generate optimal evacuation routes. Furthermore, the server analyzes images acquired from satellites and drones to obtain the latest information on the situation in the affected areas.

[0512] Rescue operations and evacuation guidance suggestions

[0513] The server manages a database of past rescue operations and evacuation guidance, which is stored using a relational database such as an SQL server. This data is analyzed and optimal rescue methods and evacuation guidance measures are proposed based on past success stories.

[0514] Analysis of the health and psychological status of disaster victims

[0515] Users input their health and psychological status into the device through the application. The input data is collected through the smartphone application and sent to the server via HTTP requests. The server then analyzes this data using a generative AI model to determine the appropriate care provision and shelter placement.

[0516] Providing information and advice

[0517] The server provides users with real-time disaster information, evacuation routes, and countermeasures based on all analysis results. The device displays this information in an easy-to-understand manner, supporting rapid evacuation and appropriate action. It also prioritizes users who require appropriate medical assistance and guides them to evacuation shelters based on their health and psychological state.

[0518] Specific examples

[0519] For example, if a certain area is predicted to be flooded due to heavy rain, the server uses an API to collect historical weather data and preprocesses the data using an ETL process. A generative AI model is used to make highly accurate flood predictions, while simultaneously analyzing real-time drone images to identify areas that have already been flooded. Based on the analysis results, the system provides residents with specific evacuation routes and shelter information. Users enter their own health and psychological state into the application, and the server analyzes this data to provide appropriate medical support.

[0520] Prompt Sentence Examples

[0521] "For the next natural disaster, please provide information on the best evacuation routes and shelters. Also, please provide procedures for special assistance for residents with illnesses or mental health issues."

[0522] As described above, this invention is an advanced information system that handles a wide variety of data in an integrated manner and quickly provides disaster prediction and appropriate countermeasures.

[0523] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0524] Step 1:

[0525] The server collects historical weather and earthquake data from data sources such as weather observation satellites and government agencies. Specifically, it periodically retrieves this data through an API and stores it in a database. The input data is in JSON or XML format, and is converted into a standardized format. The output is a dataset that can be analyzed.

[0526] Step 2:

[0527] The server preprocesses the collected data using the ETL (Extract, Transform, Load) process. It converts the data into CSV, fills in missing values, and removes noise. Specifically, it fills in missing data by averaging the preceding and following values, and removes anomalous data points. The input is the data before transformation, and the output is the preprocessed data.

[0528] Step 3:

[0529] The server inputs the preprocessed data into a generative AI model for analysis. It uses a machine learning framework (e.g., TensorFlow or PyTorch) to predict the risk of future disasters. The input is the preprocessed data, and the output is a risk prediction model and a probability map of disaster occurrence.

[0530] Step 4:

[0531] The terminal transfers real-time video and photo data from devices such as drones and fixed cameras to a server using real-time communication protocols such as MQTT and WebSocket. The input is video and photo data, and the output is real-time data transfer to the server.

[0532] Step 5:

[0533] The server analyzes the video and photos received in real time and uses computer vision technology (such as OpenCV and TensorFlow) to identify the depth and extent of flooding. The input is real-time data, and the output is the identification of the extent and pattern of damage.

[0534] Step 6:

[0535] The server analyzes images acquired from satellites and drones in real time to grasp the latest situation in the disaster-stricken areas. Image analysis is performed to quantify road traffic conditions and the extent of damage. The input is image data from satellites and drones, and the output is a report of the latest situation in the disaster-stricken areas.

[0536] Step 7:

[0537] The server manages a database of past rescue operations and evacuation guidance using a relational database such as an SQL server, analyzes this data, and proposes optimal rescue methods and evacuation guidance measures. The input is past data, and the output is the proposed rescue methods and evacuation guidance measures.

[0538] Step 8:

[0539] Users input their own health and psychological status into the device through the application. This data is sent to the server via HTTPS. The input is the user's health and psychological status data, and the output is the data sent to the server.

[0540] Step 9:

[0541] The server uses a generative AI model to analyze the user's health and psychological state data and determine the appropriate care provision and shelter placement. The input is the user's health and psychological data, and the output is the decision on care provision and shelter placement.

[0542] Step 10:

[0543] The server provides users with real-time disaster information, evacuation routes, and countermeasures based on all analysis results. This information is sent to the terminal and visually presented to the user. The input is the analysis results, and the output is the information provided to the user.

[0544] Step 11:

[0545] The device displays disaster information and evacuation routes in an easy-to-understand format for users, supporting rapid evacuation and appropriate action. The input is notification data from the server, and the output is information displayed to the user. In addition, if the user needs appropriate medical assistance based on their health and psychological state, the device will guide them to an evacuation shelter with priority.

[0546] The above is the specific flow of operation of this system.

[0547] (Application example 1)

[0548] 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."

[0549] It is difficult to provide prompt and accurate information and evacuation guidance during disasters. There is also a lack of appropriate care and shelter locations based on the psychological and physical health status of disaster victims. This often results in an inability to respond appropriately when a disaster occurs, which can lead to the spread of damage and delays in providing appropriate assistance.

[0550] 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.

[0551] In this invention, the server includes means for collecting and analyzing past weather and earthquake data, means for analyzing video and photographs transmitted in real time to identify the extent and pattern of damage, means for analyzing images acquired from satellites and drones to grasp the situation in the disaster-stricken area, means for analyzing past rescue operations and evacuation guidance data to propose optimal countermeasures, means for analyzing the health and psychological state of disaster victims and determining care and evacuation shelter placement, means for providing appropriate information and countermeasures to users based on these means, means for analyzing weather, satellite, and drone data using generation AI to propose optimal evacuation routes, and means for providing real-time navigation to evacuation shelters based on the user's location information. This enables rapid and effective disaster response and appropriate evacuation guidance based on advanced information processing.

[0552] "Historical weather data" refers to historical weather information, including weather elements such as temperature, precipitation, and wind speed.

[0553] "Earthquake data" refers to observational information about earthquakes, including details such as the epicenter, seismic intensity, and date and time of occurrence.

[0554] "Video and photos transmitted in real time" refers to visual data that captures the current situation in real time, and includes video and still images.

[0555] "Damage scope and damage pattern" refers to the physical extent of the impact of a disaster and the specific form of that impact.

[0556] "Satellite and drone-derived imagery" refers to high-resolution visual data taken from the air, such as satellites or drones.

[0557] "The situation in the affected areas" refers to the current state of the areas where the disaster occurred, including the extent of the damage and the area affected.

[0558] "Rescue operation and evacuation guidance data" refers to information on past rescue operations and evacuation cases, including both successful and unsuccessful cases.

[0559] "Optimal response" refers to the action or measure that is most appropriate for the current situation.

[0560] "The health and psychological state of the disaster victims" refers to the physical health and psychological state of the people affected by the disaster.

[0561] "Care and shelter placement" refers to the necessary support for disaster victims and the appropriate placement of shelters.

[0562] "Appropriate information and measures" refers to the correct information and guidelines for action that should be provided to users.

[0563] "Weather data, satellite data, and drone data" refers collectively to weather information and visual data taken from the air.

[0564] "Generative AI" refers to artificial intelligence technology that analyzes and predicts based on input data.

[0565] An "evacuation route" refers to a route for evacuation in the event of a disaster.

[0566] "Real-time navigation" refers to a system that provides real-time directions based on your current location.

[0567] A system that specifically embodies the present invention is configured as follows.

[0568] Hardware and software used

[0569] The system uses hardware such as servers, smartphones, drones, and satellites, as well as the following software:

[0570] 1. Python

[0571] 2. OpenCV (Drone video analysis)

[0572] 3. scikit-learn (data analysis and predictive models)

[0573] 4. TensorFlow (generative AI models)

[0574] 5. geopy (distance calculation)

[0575] Data collection and analysis

[0576] First, the server collects weather and earthquake data from various data sources (weather observation satellites and government agencies). The collected data is cleaned and converted into a format that is easy to analyze. The server then uses a generative AI model to analyze this past data and predict future disaster risks.

[0577] Real-time data collection and analysis

[0578] The terminal then transfers real-time video and photos sent from devices such as drones and fixed cameras to a server. The server uses this real-time data to identify the extent and pattern of damage. The server also analyzes images acquired from satellites and drones in real time to grasp the latest situation in the affected area.

[0579] Rescue operations and evacuation guidance suggestions

[0580] The server analyzes a database of past rescue operations and evacuation guidance, proposing optimal rescue methods and evacuation guidance measures. This analysis is based on past successful cases, enabling a swift and effective response tailored to the current situation in the disaster area.

[0581] Analysis of the health and psychological status of disaster victims

[0582] Users enter their own health and psychological state into the device through the application. The device then sends this data to a server, which then analyzes it using generative AI. Based on this analysis, appropriate care for disaster victims and the placement of evacuation shelters are determined.

[0583] Information and navigation

[0584] Based on all of the above analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. The device displays this information in an easy-to-understand manner, supporting rapid evacuation and appropriate action. Real-time navigation to evacuation shelters is also provided based on the user's location information.

[0585] Specific examples

[0586] For example, in this application, named "Emergency Guardian," if a user is in an area where flooding due to heavy rain is predicted, the server analyzes past weather data to make highly accurate flood predictions. At the same time, it analyzes drone images received in real time to identify areas that have already been flooded. Based on the analysis results, the server provides residents in the area with specific evacuation routes and shelter information in the event that evacuation is necessary. Furthermore, residents can enter their own health and psychological state into the application, and the server will adjust care and assistance accordingly, providing appropriate medical support.

[0587] Prompt Sentence Examples

[0588] Weather data: {weather_data}, Satellite data: {satellite_data}, Drone data: {drone_data}

[0589] Please analyze the above data and provide the best evacuation route."

[0590] This will enable rapid and effective disaster response and appropriate evacuation guidance based on advanced information processing.

[0591] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0592] Step 1:

[0593] The server collects historical weather and earthquake data. The input is data provided by weather observation satellites and government agencies, and the output is raw data stored on the server for analysis. Specifically, the server retrieves data through an API and stores it in a database.

[0594] Step 2:

[0595] The server analyzes the collected weather and earthquake data. The input is the past weather and earthquake data saved in step 1, and the output is the result of predicting future disaster risk based on the generative AI model. Specific operations include data cleaning, noise removal, and application of analysis algorithms.

[0596] Step 3:

[0597] The terminal transfers the video and photos sent in real time from drones, fixed cameras, etc. to the server. The input is the real-time video and photos sent from the drones or fixed cameras, and the output is the data transferred to the server. Specifically, the terminal receives the data, converts it into an appropriate format, and sends it to the server.

[0598] Step 4:

[0599] The server uses real-time data to identify the extent and pattern of damage. The input is the video and photos received in step 3, and the output is the analysis results that identify the extent and pattern of damage. Specifically, it applies an image analysis algorithm to identify the depth and spread of flooding.

[0600] Step 5:

[0601] The server analyzes images acquired from satellites and drones in real time. The input is images acquired from satellites and drones, and the output is the latest status of the affected areas. Specifically, image analysis technology is used to identify traffic conditions on major roads and the extent of damage.

[0602] Step 6:

[0603] The server analyzes data on past rescue operations and evacuation guidance, and proposes optimal countermeasures. The input is past rescue operation and evacuation guidance data, and the output is the results of proposing optimal rescue methods and evacuation guidance measures. Specifically, it performs data analysis based on past successful cases.

[0604] Step 7:

[0605] The user inputs their own health and psychological state into the device through the application. The input is the user's health and psychological state data, and the output is data that is saved on the device and sent to the server. Specifically, the data input from the device is sent to the server.

[0606] Step 8:

[0607] The server analyzes the health and psychological status data using a generative AI model. The input is the data sent in step 7, and the output is the results of determining the appropriate care provision and shelter location. Specifically, the server uses generative AI to analyze the data and propose appropriate countermeasures.

[0608] Step 9:

[0609] The server provides the user with appropriate information and countermeasures based on the analysis results. The input is the analysis results mentioned above, and the output is specific evacuation route and shelter information notified to the user. Specifically, the server calculates evacuation routes in real time and sends the information to the terminal.

[0610] Step 10:

[0611] The terminal provides real-time navigation to evacuation shelters based on the user's location information. The input is the user's location information from GPS etc. and evacuation route information received from the server, and the output is navigation information displayed in a format that is easy for the user to view. Specifically, the terminal integrates GPS data and evacuation route information and displays it on the screen.

[0612] 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.

[0613] As an embodiment of this invention, the operation of the system is explained step by step below. This system incorporates weather data, earthquake data, real-time video and photos, satellite and drone images, rescue operation and evacuation guidance data, the health and psychological state of disaster victims, and an emotion engine that recognizes the user's emotions. This allows the system to provide the user with optimal information and countermeasures.

[0614] Data collection and analysis

[0615] First, the server collects historical weather and earthquake data from various data sources (weather observation satellites and government agencies). The collected data is converted into an easy-to-analyze format, and data cleaning is performed to fill in missing data and remove noise. A generative AI model analyzes this historical data and predicts future disaster risk. After the analysis is complete, a predictive model is generated.

[0616] Real-time data collection and analysis

[0617] The device then transfers real-time video and photos from devices such as drones and fixed cameras to a server. The server uses this real-time data to identify the extent and pattern of damage. For example, the server analyzes the depth and spread of flooding and generates optimal evacuation routes.

[0618] The server also analyzes images acquired from satellites and drones in real time to obtain the latest information on the situation in the affected areas, including the traffic status of major roads and the extent of damage in the affected areas.

[0619] Rescue operations and evacuation guidance suggestions

[0620] The server analyzes a database of past rescue operations and evacuation guidance, proposing optimal rescue methods and evacuation guidance measures. This analysis is based on past successful cases, enabling a swift and effective response tailored to the current situation in the disaster area.

[0621] Analysis of the health and psychological status of disaster victims

[0622] Users enter their own health and psychological state into the device through the application. The device then sends this data to a server, which then analyzes it using generative AI. Based on this analysis, appropriate care for disaster victims and the location of evacuation shelters are determined.

[0623] Emotion recognition by emotion engine

[0624] When the user inputs their health status, the device captures their voice and facial expressions and analyzes them using an emotion engine. The emotion engine analyzes their voice and facial expressions to recognize the user's emotions. For example, it can determine whether the user is feeling stressed or calm.

[0625] Providing information and advice

[0626] Based on all of the above analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. The device displays this information in an easy-to-understand manner, supporting rapid evacuation and appropriate action. Additionally, depending on changes in the user's health or psychological state, the device prioritizes users who require appropriate medical assistance and guides them to evacuation shelters.

[0627] Furthermore, based on the emotion recognition results of the emotion engine, stress management and psychological support information is provided to users, allowing them to receive psychological support even in times of disaster.

[0628] Specific examples

[0629] For example, if a certain area is predicted to be flooded due to heavy rain, the server will analyze past weather data to generate a highly accurate flood forecast. At the same time, it will analyze drone images received in real time to identify areas that are already flooded. Based on the analysis results, the server will provide residents of the area with specific evacuation routes and shelter information in the event that evacuation is necessary.

[0630] Residents enter their physical and psychological state into the application, and the emotion engine measures their stress levels. The server then analyzes the information and provides medical assistance as needed. As a result, residents can evacuate with peace of mind and be quickly guided to a safe location.

[0631] As described above, this system is an advanced information system that makes integrated use of a wide variety of data and an emotion engine to quickly predict disasters and provide appropriate countermeasures, thereby ensuring the safety and psychological support of users.

[0632] The processing flow will be explained below.

[0633] Step 1:

[0634] The server collects historical weather and earthquake data from various sources, including weather satellites and government databases, and periodically retrieves the latest data using communication protocols (e.g., HTTP, API).

[0635] Step 2:

[0636] The server converts the collected weather and earthquake data into a format that is easy to analyze. Specifically, it standardizes the data (e.g., standardizing temperature, precipitation, wind speed, etc.), fills in missing data, and removes noise.

[0637] Step 3:

[0638] The server uses a generative AI model to analyze weather and earthquake data and predict future disaster risks. The AI ​​model performs pattern recognition based on past data and updates the prediction model.

[0639] Step 4:

[0640] The device collects data on the user's health and psychological state, and the user inputs their physical condition, stress level, etc. using a dedicated application.

[0641] Step 5:

[0642] The device captures the user's voice and facial expressions and sends them to the emotion engine, which then understands the user's emotions.

[0643] Step 6:

[0644] The emotion engine uses voice and facial expression analysis to recognize the user's emotions, for example, determining whether the user is feeling stressed or relieved.

[0645] Step 7:

[0646] The device transmits the collected health, psychological, and emotional data to a server, where the data is securely transferred using end-to-end encryption technology.

[0647] Step 8:

[0648] The server analyzes the received data using a generative AI model to assess the user's health and psychological state, and makes decisions about providing care and locating evacuation shelters based on this.

[0649] Step 9:

[0650] The device transmits real-time video and photos from drones and fixed cameras to a server, where the video is uploaded via the Internet.

[0651] Step 10:

[0652] The server analyzes the video and photos sent in real time, and uses generative AI to identify the extent and pattern of damage. For example, it analyzes the depth and spread of flooding to grasp the extent of damage in the relevant area.

[0653] Step 11:

[0654] The server analyzes real-time images acquired from satellites and drones, providing an up-to-date understanding of the situation in the affected areas, including the passability of major roads and the extent of damage in the affected areas.

[0655] Step 12:

[0656] The server analyzes a database of past rescue operations and evacuation guidance, and proposes optimal rescue methods and evacuation guidance measures. Based on past success stories, a plan tailored to the local situation is generated.

[0657] Step 13:

[0658] Based on all of the above analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. This information is then sent to the user's device and displayed in an easy-to-understand format.

[0659] Step 14:

[0660] The device displays the information sent from the server, including maps of safe evacuation routes, detailed information on evacuation shelters, and emergency measures. Users can evacuate safely based on this information.

[0661] Step 15:

[0662] Based on the recognition results of the emotion engine, the server provides users with information on stress management and psychological support, which helps users to evacuate safely while receiving psychological support.

[0663] Step 16:

[0664] The server records all data and feedback and uses it to improve the accuracy of the generative AI model. The model is retrained based on analysis results and user behavior data, continuously improving the accuracy of disaster prediction and response.

[0665] Example 2

[0666] 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."

[0667] In order to carry out appropriate evacuation and rescue operations quickly and effectively during disasters, it is necessary to collect and analyze a wide variety of data in real time and provide users with appropriate information and countermeasures. However, conventional systems have limitations in the accuracy of data collection and analysis, making it difficult to respond quickly. Furthermore, they do not adequately provide support that takes into account the health, psychological state, and emotions of disaster victims. For these reasons, improving safety and psychological support during disasters is a challenge.

[0668] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting past weather data and earthquake data and analyzing this data, means for analyzing videos and photos transmitted in real time to identify the extent and pattern of damage, means for analyzing images acquired from satellites and drones to grasp the situation in the disaster-stricken area, means for analyzing past rescue operations and evacuation guidance data to propose optimal countermeasures, means for analyzing the health and psychological states of disaster victims and determining care and shelter placement, and means for analyzing the user's voice and facial expressions using an emotion engine to recognize the user's emotional state. This enables rapid analysis of various data and provision of appropriate information taking into account the user's health and emotional state.

[0669] "Weather data" refers to weather observation results and forecast information such as temperature, precipitation, wind speed, wind direction, and humidity.

[0670] "Earthquake data" refers to observation results related to earthquakes, including data such as the earthquake's seismic intensity, epicenter, and date and time of occurrence.

[0671] "Analysis means" refers to devices or software that perform calculations and statistical processing on collected data to extract and interpret specific information.

[0672] "Real-time data" refers to data that can be immediately acquired and analyzed based on the current situation.

[0673] "Footage and photographs" refers to visual data captured by photographic equipment such as cameras and drones.

[0674] "Affected area" refers to the geographic area affected by a disaster.

[0675] "Damage pattern" refers to the type and distribution of specific impacts and damage caused by a disaster.

[0676] "Satellite imagery" refers to image data of the Earth captured by sensors mounted on artificial satellites.

[0677] "Drone imagery" refers to image data captured by an unmanned aerial vehicle.

[0678] "Situational awareness" refers to the act of understanding the current situation or state based on collected data.

[0679] "Rescue activities" refers to activities such as saving lives, distributing supplies, and providing medical support during disasters.

[0680] "Evacuation guidance" refers to the act of instructing and guiding people to a safe place during a disaster.

[0681] "Health status" refers to information about physical health, such as the state of each bodily function and tissue, and the presence or absence of disease.

[0682] "Psychological state" refers to information about mental states such as stress, anxiety, and mental well-being.

[0683] An "emotion engine" refers to an algorithm or system that analyzes and identifies emotions from a user's voice, facial expressions, etc.

[0684] A "generative AI model" refers to an artificial intelligence model that learns from large amounts of data and makes highly accurate predictions and analyses of new data.

[0685] "Appropriate information and measures" refers to information and measures that will enable users to evacuate safely and obtain the necessary support in the event of a disaster.

[0686] The present invention is a system that collects and analyzes a variety of data and provides prompt and appropriate information and countermeasures in the event of a disaster. A specific example of this system will be described below.

[0687] Data collection and analysis

[0688] The server collects historical weather and earthquake data from weather observation satellites and government agencies. This data is converted into an easy-to-analyze format and cleaned to fill in missing data and remove noise. A suitable tool for this is the Python pandas library.

[0689] Analysis using generative AI models

[0690] The server analyzes the collected and cleaned data using a generative AI model, specifically using deep learning frameworks such as TensorFlow and PyTorch to build a disaster risk prediction model.

[0691] Real-time data collection

[0692] The device transfers real-time video and photos from drones and fixed cameras to a server, and can transmit data over Wi-Fi or 5G networks.

[0693] Real-time data analysis

[0694] The server uses the received real-time data to identify the extent and pattern of damage. For example, it can use OpenCV to perform image analysis to identify the depth and spread of flooding. It can also use object detection algorithms to check the traffic status of major roads.

[0695] Rescue operations and evacuation guidance suggestions

[0696] The server analyzes past rescue operations and evacuation guidance data and proposes optimal rescue methods and evacuation guidance measures. This is achieved by searching for and analyzing the necessary information from the database using SQL queries.

[0697] Analysis of the health and psychological status of disaster victims

[0698] Users input their own health and psychological status through the application. The device then sends this data to a server, which then uses generative AI to analyze the data. For example, NLP (natural language processing) technology can be used to analyze the user's input text and determine the priority of medical assistance.

[0699] Emotion recognition by emotion engine

[0700] When a user enters their health status, the device captures the user's voice and facial expressions and analyzes them using an emotion engine. The emotion engine uses deep learning models to analyze the voice and facial expressions and recognize the user's emotions. For example, a model built using the Keras library can be used to determine whether the user is feeling stressed.

[0701] Providing information and advice

[0702] The server provides users with real-time disaster information, evacuation routes, and countermeasures based on all of the above analysis results. The device uses HTML5 and JavaScript to display this information in an easy-to-understand manner. For example, evacuation routes can be displayed on a map using the Google Maps API.

[0703] Specific examples

[0704] For example, if heavy rain is predicted to cause flooding in a certain area, the server will use past weather data to generate highly accurate flood predictions. At the same time, it will analyze drone images received in real time to identify areas that are already flooded. Based on this information, the server will provide specific evacuation routes and shelter information to residents in the area.

[0705] Prompt Sentence Examples

[0706] "Please suggest evacuation measures for areas predicted to be flooded by heavy rain. Based on the analysis results of historical weather data and drone imagery, please tell us how to provide specific evacuation routes and necessary medical assistance."

[0707] As described above, this system is an advanced information system that makes integrated use of a wide variety of data and an emotion engine to quickly predict disasters and provide appropriate countermeasures, thereby ensuring the safety and psychological support of users.

[0708] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0709] Step 1:

[0710] The server collects past weather and earthquake data from weather observation satellites and government agencies. Specifically, it acquires the data using the API of the Japan Meteorological Agency and the API of satellite data providers and stores it in a database. The input is a dataset from each API, and the output is a dataset for preparation for analysis.

[0711] Step 2:

[0712] The server converts the acquired data into a format suitable for analysis. It uses the Python pandas library to convert the data into CSV format, imputes missing data, and removes noise. The input is the collected raw data, and the output is the cleaned and formatted data.

[0713] Step 3:

[0714] The server feeds the cleaned data into a generative AI model to build a model that predicts future disaster risk. It uses TensorFlow and PyTorch to train the deep learning model and output the prediction results. The input is the cleaned dataset, and the output is a disaster risk prediction model and the prediction results.

[0715] Step 4:

[0716] The terminal transfers real-time video and photos sent from drones and fixed cameras to a server. The device transmits data using Wi-Fi or 5G. The input is real-time video and photos from the device, and the output is data transferred to the server.

[0717] Step 5:

[0718] The server analyzes the received real-time data to identify the extent and pattern of damage. It uses OpenCV to perform image analysis to determine the depth and extent of flooding and the traffic situation on major roads. The input is real-time video and photos, and the output is the results of identifying the extent and pattern of damage.

[0719] Step 6:

[0720] The server analyzes past rescue operation and evacuation guidance data and proposes optimal rescue methods and evacuation guidance measures. It searches the database using SQL queries and creates rescue plans based on the analysis results. The input is past rescue operation data, and the output is the proposed rescue method and evacuation guidance measures.

[0721] Step 7:

[0722] Users input their own health and psychological state through the application. The device sends this to the server, which analyzes it using generative AI. NLP technology is used to analyze the input text and determine the priority of medical assistance. The input is the user's health and psychological state data, and the output is the analysis results and the priority of medical assistance.

[0723] Step 8:

[0724] The device captures the user's voice and facial expressions and analyzes them using an emotion engine. The emotion engine uses a deep learning model to analyze the voice and facial expressions and recognize the user's emotions. The input is the user's voice and facial expression data, and the output is the recognized emotional state.

[0725] Step 9:

[0726] The server provides users with real-time disaster information, evacuation routes, and countermeasures based on all analysis results. The device displays this information in an easy-to-understand manner and prioritizes the provision of necessary medical assistance. Information is visualized using HTML5 and JavaScript, and evacuation routes are displayed using the Google Maps API. The input is various analysis results, and the output is specific disaster information and evacuation routes that are displayed to the user.

[0727] (Application example 2)

[0728] 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."

[0729] When a disaster occurs, it is difficult to grasp the situation in the affected area and provide victims with prompt and appropriate information. At the same time, there is a need to provide food and other necessities quickly, accurately grasp the health and psychological state of victims, and provide psychological care. To solve these problems, a system is needed that can collect and analyze information from multiple data sources in real time and quickly propose countermeasures.

[0730] The identification processing 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 means for collecting past weather data and earthquake data and analyzing this data, means for analyzing videos and photos transmitted in real time to identify the extent and pattern of damage, means for analyzing images acquired from satellites and drones to grasp the situation in the disaster-stricken area, means for analyzing past rescue operations and evacuation guidance data to propose optimal countermeasures, means for analyzing the health and psychological states of disaster victims and determining care and shelter placement, means for providing food to disaster-stricken areas using drones and autonomous mobile devices, means for understanding the psychological states of disaster victims using emotion recognition technology and providing stress management information, and means for providing appropriate information and countermeasures to users based on these means. This enables accurate and rapid understanding of the situation in the disaster-stricken area, rapid provision of supplies including food, and appropriate information and psychological support to disaster victims.

[0731] "Past weather data" refers to data relating to weather observed in the past, including information such as temperature, precipitation, wind speed, wind direction, and humidity.

[0732] "Earthquake data" refers to data that includes information on the epicenter, seismic intensity, and waveforms of shaking at the time of an earthquake, and is the basis for analyzing the scale and extent of an earthquake's impact.

[0733] "Video and photos transmitted in real time" refers to video and still image data obtained by instantly photographing and recording the current situation and then instantly transmitting that data.

[0734] "Damage range and damage pattern" is pattern information that indicates the range of the area affected by the disaster and the type and scale of the damage.

[0735] "Imagery obtained from satellites and drones" refers to image data taken from the air, including images of the earth's surface taken by satellites or unmanned aerial vehicles.

[0736] "Status of the affected areas" refers to data showing the current state of the affected areas at the time of the disaster and afterwards, including the scale, scope and detailed information of the damage.

[0737] "Past rescue operation and evacuation guidance data" refers to data on rescue and evacuation operations that have been carried out in the past, including success stories, failure stories, and information on the processes involved.

[0738] "Optimal response measures" are proposals based on analyzed data that propose optimal guidelines for action, evacuation routes, rescue methods, etc. for affected areas and victims.

[0739] "The health and psychological state of the disaster victims" is data indicating the physical health and psychological state of the disaster victims.

[0740] "Care and sheltering" refers to providing medical and psychological support to disaster victims, as well as the provision and arrangement of appropriate shelter.

[0741] "Drones and autonomous mobile devices" refers to unmanned aerial vehicles and ground mobile devices that use autonomous driving technology, which can be used to transport supplies and food.

[0742] "Emotion recognition technology" is a technology that identifies human emotions through voice analysis and facial expression analysis, and evaluates psychological states such as stress and a sense of security.

[0743] This invention is a system for collecting and analyzing information in the event of a disaster, and providing appropriate countermeasures. The system collects various data, analyzes it, and provides information to users in real time. It also uses drones and autonomous mobile devices to quickly provide food and relief supplies.

[0744] Hardware Configuration

[0745] Server: Processes data and analyzes the generated AI model.

[0746] Cloud server: Data storage and big data analysis are performed using AWS.

[0747] Drones: Collect images of disaster areas and deliver supplies.

[0748] Autonomous mobile devices: Distribute food and relief supplies on the ground.

[0749] Smartphone: Used as a device for users to input their health and psychological status.

[0750] Fixed cameras: Providing real-time footage of the affected areas.

[0751] Software Configuration

[0752] Python: A programming language for data analysis, specifically using Scikit-learn and TensorFlow.

[0753] OpenCV: A library for performing image analysis.

[0754] AWS Lambda: An AWS service for serverless data processing.

[0755] Emotion Engine API: Technology that recognizes emotions through voice and facial expression analysis.

[0756] Data collection and analysis process

[0757] 1. Historical data collection and analysis:

[0758] The server collects historical weather and earthquake data from government agencies and weather observation satellites, which is then analyzed using a generative AI model to predict future disaster risks.

[0759] 2. Real-time data collection:

[0760] Real-time video and photos from drones and fixed cameras are sent to a server, which analyzes the data to identify the extent and pattern of damage.

[0761] 3. Understanding the situation in the affected areas:

[0762] Images acquired from satellites and drones will be analyzed to provide an up-to-date picture of the situation in the affected areas, including road conditions and the extent of damage.

[0763] 4. Suggestions for rescue operations and evacuation:

[0764] The server analyzes past rescue operations and evacuation guidance data and proposes the optimal response measures.

[0765] 5. Health and Psychological Analysis:

[0766] Users input their health and psychological state using their smartphones, which is then analyzed by the server. An emotion engine is used to recognize the user's emotions and provide stress management information.

[0767] 6. Information provision and implementation of measures:

[0768] Based on all the above analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. It also uses drones and autonomous mobile devices to quickly deliver food to disaster-stricken areas.

[0769] Specific examples

[0770] For example, if a flood is predicted in a certain area, the server analyzes past weather data to generate a highly accurate flood forecast. At the same time, it analyzes drone images received in real time to identify flooded areas. As a result, it provides information on optimal evacuation routes and evacuation shelters. It also provides necessary medical assistance and psychological support based on the individual's health and psychological state.

[0771] Prompt Sentence Examples

[0772] Below are some example prompts to input to the generative AI model:

[0773] Based on the information below, please suggest appropriate evacuation routes and food distribution methods for the affected areas.

[0774] Weather data: {Weather data details}

[0775] Satellite image: {satellite image URL}

[0776] Real-time imagery from drone: {drone image URL}

[0777] Victim's health status: {health status data}

[0778] Victim's psychological state: {Psychological state data}

[0779] Emotion analysis result: {Emotion analysis result}

[0780] This system is capable of quickly analyzing huge amounts of data and providing appropriate information and assistance in real time.

[0781] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0782] Step 1:

[0783] The server collects historical weather and earthquake data.

[0784] Input: Data from weather satellites and government agencies

[0785] How it works: The server queries these data sources through APIs to retrieve weather and earthquake data.

[0786] Output: Data obtained in the form of historical weather and earthquake data

[0787] Step 2:

[0788] The server analyzes the collected historical data and uses a generative AI model to predict the risk of future disasters.

[0789] Input: Weather and earthquake data collected in Step 1

[0790] How it works: Cleans data and converts it into an analyzable format. Enters prompts into a generative AI model to perform predictive calculations.

[0791] Output: Prediction data of future disaster risk

[0792] Step 3:

[0793] Video and photos are transmitted in real time to identify the extent and pattern of damage.

[0794] Input: Real-time video and photos from drones and fixed cameras

[0795] Operation: The server receives the video data and analyzes it using OpenCV. It identifies the extent and pattern of damage and analyzes the image data.

[0796] Output: Specific information on the extent and pattern of damage

[0797] Step 4:

[0798] Images obtained from satellites and drones are analyzed to understand the situation in the affected areas.

[0799] Input: Satellite and drone imagery

[0800] Operation: The server receives images acquired from satellites and drones and analyzes them using OpenCV to grasp the current situation in the affected areas, determine road traffic conditions, and the extent of damage.

[0801] Output: Situation data of the affected area

[0802] Step 5:

[0803] We analyze past rescue operations and evacuation guidance data to propose optimal response measures.

[0804] Input: Past rescue operations and evacuation guidance data stored in the database

[0805] How it works: The server analyzes historical data and uses generative AI models to generate optimal rescue operations and evacuation guidance prompts.

[0806] Output: Proposal data for optimal countermeasures

[0807] Step 6:

[0808] Analyze the health and psychological state of disaster victims to determine care and evacuation placement.

[0809] Input: Health and psychological data entered by the user into the device, and analysis results by the emotion engine

[0810] How it works: The server uses generative AI models to analyze data and determine appropriate care and shelter placement. It also uses an emotion engine to provide stress management information.

[0811] Output: Care and shelter placement proposal data

[0812] Step 7:

[0813] Delivering food to disaster-stricken areas using drones and autonomous mobile devices.

[0814] Input: Situation data of the affected area, location information of the victims

[0815] How it works: The server analyzes the optimal route and sends instructions to drones and autonomous mobile devices, which then deliver food to disaster-stricken areas.

[0816] Output: Data on completed delivery of supplies and food

[0817] Step 8:

[0818] Provide users with appropriate information and measures.

[0819] Input: Analysis results from the above steps and proposed data

[0820] How it works: The server compiles this data and sends it to the user's device. The user receives the appropriate information on their smartphone and can take action.

[0821] Output: Appropriate information and measures to be sent to the user's device

[0822] In this way, data collection, analysis, and execution are performed in coordination at each step, enabling rapid response and support for disaster victims.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] [Third embodiment]

[0827] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0828] 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.

[0829] 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).

[0830] 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.

[0831] 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.

[0832] 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).

[0833] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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."

[0839] As an embodiment of the present invention, the operation of the system is explained step by step below. This system collects and analyzes a wide range of data, such as weather data, earthquake data, real-time video and photos, satellite and drone images, rescue operation and evacuation guidance data, and the health and psychological state of disaster victims, and provides users with appropriate information and countermeasures.

[0840] Data collection and analysis

[0841] First, the server collects historical weather and earthquake data from various data sources (weather observation satellites and government agencies). The collected data is converted into an easy-to-analyze format, and data cleaning is performed to fill in missing data and remove noise. A generative AI model analyzes this historical data and predicts future disaster risk. After the analysis is complete, a predictive model is generated.

[0842] Real-time data collection and analysis

[0843] The device then transfers real-time video and photos from devices such as drones and fixed cameras to a server. The server uses this real-time data to identify the extent and pattern of damage. For example, the server analyzes the depth and spread of flooding and generates optimal evacuation routes.

[0844] The server also analyzes images acquired from satellites and drones in real time to obtain the latest information on the situation in the affected areas, including the traffic status of major roads and the extent of damage in the affected areas.

[0845] Rescue operations and evacuation guidance suggestions

[0846] The server analyzes a database of past rescue operations and evacuation guidance, proposing optimal rescue methods and evacuation guidance measures. This analysis is based on past successful cases, enabling a swift and effective response tailored to the current situation in the disaster area.

[0847] Analysis of the health and psychological status of disaster victims

[0848] Users enter their own health and psychological state into the device through the application. The device then sends this data to a server, which then analyzes it using generative AI. Based on this analysis, appropriate care for disaster victims and the location of evacuation shelters are determined.

[0849] Providing information and advice

[0850] Based on all of the above analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. The device displays this information in an easy-to-understand manner, supporting rapid evacuation and appropriate action. Additionally, depending on changes in the user's health or psychological state, the device prioritizes users who require appropriate medical assistance and guides them to evacuation shelters.

[0851] Specific examples

[0852] For example, if flooding due to heavy rain is predicted in a certain area, the server analyzes past weather data to make a highly accurate flood forecast. At the same time, it analyzes drone images received in real time to identify areas that have already been flooded. Based on the analysis results, the server provides residents of the area with specific evacuation routes and shelter information in the event that evacuation is necessary. Furthermore, residents can enter their own health and psychological state into the application, and the server will adjust care and assistance accordingly, providing appropriate medical support.

[0853] As described above, this system is an advanced information system that handles a wide variety of data in an integrated manner and is capable of predicting disasters and providing appropriate countermeasures promptly.

[0854] The processing flow will be explained below.

[0855] Step 1:

[0856] The server collects historical weather and earthquake data, including connections to weather satellites and government databases, and periodically retrieves the latest data using communication protocols (e.g., HTTP, API).

[0857] Step 2:

[0858] The server converts the collected weather and earthquake data into a format that is easy to analyze. Specifically, it standardizes the data (e.g., standardizing temperature, precipitation, wind speed, etc.), fills in missing data, and removes noise.

[0859] Step 3:

[0860] The server uses a generative AI model to analyze weather and earthquake data and predict future disaster risks. The AI ​​model performs pattern recognition based on past data and updates the prediction model.

[0861] Step 4:

[0862] The device transmits real-time video and photos from drones and fixed cameras to a server, where the video is uploaded via the Internet.

[0863] Step 5:

[0864] The server analyzes the video and photos sent in real time, and uses generative AI to identify the extent and pattern of damage. For example, it analyzes the depth and spread of flooding to grasp the extent of damage in the relevant area.

[0865] Step 6:

[0866] The server analyzes real-time images acquired from satellites and drones, which allows for a grasp of road conditions and the extent of damage in affected areas. Satellite images are analyzed using high-resolution image analysis technology.

[0867] Step 7:

[0868] The server analyzes a database of past rescue operations and evacuation guidance, and proposes optimal rescue methods and evacuation guidance measures. Based on past success stories, a plan tailored to the local situation is generated.

[0869] Step 8:

[0870] Through the application, users input their own health and psychological conditions, such as headache, fever, and stress, into input fields.

[0871] Step 9:

[0872] The device transmits health and psychological data from the user to a server, where the data is securely transferred using end-to-end encryption technology.

[0873] Step 10:

[0874] The server analyzes the received health and psychological status data to determine appropriate care for the victims and the placement of evacuation shelters. The generating AI analyzes the data and prioritizes support for users with high urgency.

[0875] Step 11:

[0876] Based on the analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. This information is then sent to the user's device and displayed in an easy-to-understand manner.

[0877] Step 12:

[0878] The device displays the information sent from the server, including maps of safe evacuation routes, detailed information on evacuation shelters, and emergency measures. Users can evacuate safely based on this information.

[0879] Step 13:

[0880] The server records all data and feedback and uses it to improve the accuracy of the generative AI model. The model is retrained based on analysis results and user behavior data, continuously improving the accuracy of disaster prediction and response.

[0881] Example 1

[0882] 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."

[0883] When a natural disaster occurs, there is a need to provide fast and accurate information and propose countermeasures, but conventional systems take time to collect and analyze data, making it difficult to respond in real time. Furthermore, there was a lack of systems that could adequately provide appropriate care and arrange evacuation shelters taking into account the health and psychological state of victims. Furthermore, there were limited means to effectively integrate and analyze past disaster data and real-time video footage, making it difficult to propose optimal rescue operations and evacuation guidance measures.

[0884] 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.

[0885] In this invention, the server includes means for collecting and analyzing past weather and earthquake data, means for analyzing video and photos transmitted in real time to identify the extent and pattern of damage, means for analyzing images acquired from satellites and drones to grasp the situation in the disaster-stricken area, means for analyzing past rescue operation and evacuation guidance data to propose optimal countermeasures, means for analyzing the health and psychological state of disaster victims and determining care and evacuation shelter placement, means for preprocessing the collected data, filling in missing data, and removing noise, means for generating a predictive model using the collected data with a generative AI model, means for analyzing the collected video in real time to generate evacuation routes, means for providing real-time disaster information, evacuation routes, and countermeasures to users based on the analysis results, and means for displaying appropriate information and countermeasures on a terminal based on these means. This enables the provision of rapid and accurate disaster information, appropriate care for disaster victims, and the proposal of optimal rescue operations and evacuation guidance measures.

[0886] "Historical weather data" is information about past weather conditions collected from data sources such as weather observation satellites and government agencies.

[0887] "Earthquake Data" means information about past and present earthquake activity collected by seismic monitoring agencies and seismic instruments.

[0888] "Means for analysis" refers to a processing method for converting collected data into a format that is easy to analyze, cleaning the data as necessary, and then analyzing the data using a generative AI model to generate a predictive model.

[0889] "Video and photographs transmitted in real time" refers to video and photographic data that records the disaster situation and is transmitted in real time from devices such as drones and fixed cameras.

[0890] "Means for identifying the extent and pattern of damage" refers to an analytical method for analyzing video and photographs transmitted in real time to identify the extent and pattern of damage caused by a disaster.

[0891] "Images obtained from satellites and drones" are visual data taken from the sky, and are image data collected by satellites and drones that show the latest situation in the disaster-stricken areas.

[0892] "Means for understanding the situation in the disaster-stricken areas" refers to a method for analyzing images obtained from satellites and drones to understand the current situation in the disaster-stricken areas and the extent of the damage.

[0893] "Rescue operation and evacuation guidance data" refers to records of rescue operations and evacuation guidance that have been carried out in the past, and includes information on successful cases and countermeasures.

[0894] The "means of proposing optimal response measures" is a method for analyzing past rescue operations and evacuation guidance data, and proposing the most effective rescue methods and evacuation guidance measures based on the current situation.

[0895] "Health and psychological conditions of disaster victims" refers to data on the physical health and psychological conditions of disaster victims at the time of the disaster.

[0896] "Measures for determining care and shelter placement" refers to methods for analyzing the health and psychological state of disaster victims and determining the type of care needed and appropriate shelter placement.

[0897] "Preprocessing of collected data" refers to a processing method for converting data into a format that is easy to analyze, filling in missing data, and removing noise.

[0898] "Means for filling in missing data and removing noise" refers to cleaning techniques for filling in missing parts of collected data and eliminating unnecessary noise.

[0899] A "generative AI model" is a model trained using artificial intelligence, an algorithm that analyzes collected data and performs predictions and pattern recognition.

[0900] "Means for generating a predictive model" refers to a method for using a generative AI model to predict future disaster risks and predictions based on collected data.

[0901] The "means for generating evacuation routes" is a method for analyzing video footage collected in real time and determining the optimal evacuation route based on the extent of damage and road conditions.

[0902] The "means for providing disaster information, evacuation routes, and countermeasures" is a system for providing users with necessary disaster information, evacuation routes, and necessary countermeasures based on the analysis results.

[0903] MODE FOR CARRYING OUT THE INVENTION

[0904] To implement this invention, the following specific procedures and details of the hardware and software used are required. This system integrates a wide range of data, including weather data, earthquake data, real-time video, photographs, satellite and drone images, rescue operation and evacuation guidance data, and the health and psychological state of disaster victims, and quickly provides users with appropriate information and countermeasures.

[0905] Data collection and analysis

[0906] The server collects historical weather and earthquake data from data sources such as weather observation satellites and government agencies. The collected data is then converted into a format that is easy to analyze using an ETL (Extract, Transform, Load) process. Specifically, the data is converted from JSON format to CSV format and measurement units are standardized. Data cleaning is also performed, including filling in missing data and removing noise.

[0907] The generative AI model is trained using a machine learning framework (such as TensorFlow or PyTorch) to analyze past data and predict future disaster risk. Based on the prediction results, a predictive model is generated, and disaster risk maps and statistical data are created.

[0908] Real-time data collection and analysis

[0909] The terminal transfers real-time video and photos sent from devices such as drones and fixed cameras to a server using real-time communication protocols such as MQTT and WebSocket.

[0910] The server uses the transferred real-time data to identify the extent and pattern of damage. It uses computer vision technologies (such as OpenCV and TensorFlow) to analyze the depth and extent of flooding and generate optimal evacuation routes. Furthermore, the server analyzes images acquired from satellites and drones to obtain the latest information on the situation in the affected areas.

[0911] Rescue operations and evacuation guidance suggestions

[0912] The server manages a database of past rescue operations and evacuation guidance, which is stored using a relational database such as an SQL server. This data is analyzed and optimal rescue methods and evacuation guidance measures are proposed based on past success stories.

[0913] Analysis of the health and psychological status of disaster victims

[0914] Users input their health and psychological status into the device through the application. The input data is collected through the smartphone application and sent to the server via HTTP requests. The server then analyzes this data using a generative AI model to determine the appropriate care provision and shelter placement.

[0915] Providing information and advice

[0916] The server provides users with real-time disaster information, evacuation routes, and countermeasures based on all analysis results. The device displays this information in an easy-to-understand manner, supporting rapid evacuation and appropriate action. It also prioritizes users who require appropriate medical assistance and guides them to evacuation shelters based on their health and psychological state.

[0917] Specific examples

[0918] For example, if a certain area is predicted to be flooded due to heavy rain, the server uses an API to collect historical weather data and preprocesses the data using an ETL process. A generative AI model is used to make highly accurate flood predictions, while simultaneously analyzing real-time drone images to identify areas that have already been flooded. Based on the analysis results, the system provides residents with specific evacuation routes and shelter information. Users enter their own health and psychological state into the application, and the server analyzes this data to provide appropriate medical support.

[0919] Prompt Sentence Examples

[0920] "For the next natural disaster, please provide information on the best evacuation routes and shelters. Also, please provide procedures for special assistance for residents with illnesses or mental health issues."

[0921] As described above, this invention is an advanced information system that handles a wide variety of data in an integrated manner and quickly provides disaster prediction and appropriate countermeasures.

[0922] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0923] Step 1:

[0924] The server collects historical weather and earthquake data from data sources such as weather observation satellites and government agencies. Specifically, it periodically retrieves this data through an API and stores it in a database. The input data is in JSON or XML format, and is converted into a standardized format. The output is a dataset that can be analyzed.

[0925] Step 2:

[0926] The server preprocesses the collected data using the ETL (Extract, Transform, Load) process. It converts the data into CSV, fills in missing values, and removes noise. Specifically, it fills in missing data by averaging the preceding and following values, and removes anomalous data points. The input is the data before transformation, and the output is the preprocessed data.

[0927] Step 3:

[0928] The server inputs the preprocessed data into a generative AI model for analysis. It uses a machine learning framework (e.g., TensorFlow or PyTorch) to predict the risk of future disasters. The input is the preprocessed data, and the output is a risk prediction model and a probability map of disaster occurrence.

[0929] Step 4:

[0930] The terminal transfers real-time video and photo data from devices such as drones and fixed cameras to a server using real-time communication protocols such as MQTT and WebSocket. The input is video and photo data, and the output is real-time data transfer to the server.

[0931] Step 5:

[0932] The server analyzes the video and photos received in real time and uses computer vision technology (such as OpenCV and TensorFlow) to identify the depth and extent of flooding. The input is real-time data, and the output is the identification of the extent and pattern of damage.

[0933] Step 6:

[0934] The server analyzes images acquired from satellites and drones in real time to grasp the latest situation in the disaster-stricken areas. Image analysis is performed to quantify road traffic conditions and the extent of damage. The input is image data from satellites and drones, and the output is a report of the latest situation in the disaster-stricken areas.

[0935] Step 7:

[0936] The server manages a database of past rescue operations and evacuation guidance using a relational database such as an SQL server, analyzes this data, and proposes optimal rescue methods and evacuation guidance measures. The input is past data, and the output is the proposed rescue methods and evacuation guidance measures.

[0937] Step 8:

[0938] Users input their own health and psychological status into the device through the application. This data is sent to the server via HTTPS. The input is the user's health and psychological status data, and the output is the data sent to the server.

[0939] Step 9:

[0940] The server uses a generative AI model to analyze the user's health and psychological state data and determine the appropriate care provision and shelter placement. The input is the user's health and psychological data, and the output is the decision on care provision and shelter placement.

[0941] Step 10:

[0942] The server provides users with real-time disaster information, evacuation routes, and countermeasures based on all analysis results. This information is sent to the terminal and visually presented to the user. The input is the analysis results, and the output is the information provided to the user.

[0943] Step 11:

[0944] The device displays disaster information and evacuation routes in an easy-to-understand format for users, supporting rapid evacuation and appropriate action. The input is notification data from the server, and the output is information displayed to the user. In addition, if the user needs appropriate medical assistance based on their health and psychological state, the device will guide them to an evacuation shelter with priority.

[0945] The above is the specific flow of operation of this system.

[0946] (Application example 1)

[0947] 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."

[0948] It is difficult to provide prompt and accurate information and evacuation guidance during disasters. There is also a lack of appropriate care and shelter locations based on the psychological and physical health status of disaster victims. This often results in an inability to respond appropriately when a disaster occurs, which can lead to the spread of damage and delays in providing appropriate assistance.

[0949] 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.

[0950] In this invention, the server includes means for collecting and analyzing past weather and earthquake data, means for analyzing video and photographs transmitted in real time to identify the extent and pattern of damage, means for analyzing images acquired from satellites and drones to grasp the situation in the disaster-stricken area, means for analyzing past rescue operations and evacuation guidance data to propose optimal countermeasures, means for analyzing the health and psychological state of disaster victims and determining care and evacuation shelter placement, means for providing appropriate information and countermeasures to users based on these means, means for analyzing weather, satellite, and drone data using generation AI to propose optimal evacuation routes, and means for providing real-time navigation to evacuation shelters based on the user's location information. This enables rapid and effective disaster response and appropriate evacuation guidance based on advanced information processing.

[0951] "Historical weather data" refers to historical weather information, including weather elements such as temperature, precipitation, and wind speed.

[0952] "Earthquake data" refers to observational information about earthquakes, including details such as the epicenter, seismic intensity, and date and time of occurrence.

[0953] "Video and photos transmitted in real time" refers to visual data that captures the current situation in real time, and includes video and still images.

[0954] "Damage scope and damage pattern" refers to the physical extent of the impact of a disaster and the specific form of that impact.

[0955] "Satellite and drone-derived imagery" refers to high-resolution visual data taken from the air, such as satellites or drones.

[0956] "The situation in the affected areas" refers to the current state of the areas where the disaster occurred, including the extent of the damage and the area affected.

[0957] "Rescue operation and evacuation guidance data" refers to information on past rescue operations and evacuation cases, including both successful and unsuccessful cases.

[0958] "Optimal response" refers to the action or measure that is most appropriate for the current situation.

[0959] "The health and psychological state of the disaster victims" refers to the physical health and psychological state of the people affected by the disaster.

[0960] "Care and shelter placement" refers to the necessary support for disaster victims and the appropriate placement of shelters.

[0961] "Appropriate information and measures" refers to the correct information and guidelines for action that should be provided to users.

[0962] "Weather data, satellite data, and drone data" refers collectively to weather information and visual data taken from the air.

[0963] "Generative AI" refers to artificial intelligence technology that analyzes and predicts based on input data.

[0964] An "evacuation route" refers to a route for evacuation in the event of a disaster.

[0965] "Real-time navigation" refers to a system that provides real-time directions based on your current location.

[0966] A system that specifically embodies the present invention is configured as follows.

[0967] Hardware and software used

[0968] The system uses hardware such as servers, smartphones, drones, and satellites, as well as the following software:

[0969] 1. Python

[0970] 2. OpenCV (Drone video analysis)

[0971] 3. scikit-learn (data analysis and predictive models)

[0972] 4. TensorFlow (generative AI models)

[0973] 5. geopy (distance calculation)

[0974] Data collection and analysis

[0975] First, the server collects weather and earthquake data from various data sources (weather observation satellites and government agencies). The collected data is cleaned and converted into a format that is easy to analyze. The server then uses a generative AI model to analyze this past data and predict future disaster risks.

[0976] Real-time data collection and analysis

[0977] The terminal then transfers real-time video and photos sent from devices such as drones and fixed cameras to a server. The server uses this real-time data to identify the extent and pattern of damage. The server also analyzes images acquired from satellites and drones in real time to grasp the latest situation in the affected area.

[0978] Rescue operations and evacuation guidance suggestions

[0979] The server analyzes a database of past rescue operations and evacuation guidance, proposing optimal rescue methods and evacuation guidance measures. This analysis is based on past successful cases, enabling a swift and effective response tailored to the current situation in the disaster area.

[0980] Analysis of the health and psychological status of disaster victims

[0981] Users enter their own health and psychological state into the device through the application. The device then sends this data to a server, which then analyzes it using generative AI. Based on this analysis, appropriate care for disaster victims and the placement of evacuation shelters are determined.

[0982] Information and navigation

[0983] Based on all of the above analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. The device displays this information in an easy-to-understand manner, supporting rapid evacuation and appropriate action. Real-time navigation to evacuation shelters is also provided based on the user's location information.

[0984] Specific examples

[0985] For example, in this application, named "Emergency Guardian," if a user is in an area where flooding due to heavy rain is predicted, the server analyzes past weather data to make highly accurate flood predictions. At the same time, it analyzes drone images received in real time to identify areas that have already been flooded. Based on the analysis results, the server provides residents in the area with specific evacuation routes and shelter information in the event that evacuation is necessary. Furthermore, residents can enter their own health and psychological state into the application, and the server will adjust care and assistance accordingly, providing appropriate medical support.

[0986] Prompt Sentence Examples

[0987] Weather data: {weather_data}, Satellite data: {satellite_data}, Drone data: {drone_data}

[0988] Please analyze the above data and provide the best evacuation route."

[0989] This will enable rapid and effective disaster response and appropriate evacuation guidance based on advanced information processing.

[0990] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0991] Step 1:

[0992] The server collects historical weather and earthquake data. The input is data provided by weather observation satellites and government agencies, and the output is raw data stored on the server for analysis. Specifically, the server retrieves data through an API and stores it in a database.

[0993] Step 2:

[0994] The server analyzes the collected weather and earthquake data. The input is the past weather and earthquake data saved in step 1, and the output is the result of predicting future disaster risk based on the generative AI model. Specific operations include data cleaning, noise removal, and application of analysis algorithms.

[0995] Step 3:

[0996] The terminal transfers the video and photos sent in real time from drones, fixed cameras, etc. to the server. The input is the real-time video and photos sent from the drones or fixed cameras, and the output is the data transferred to the server. Specifically, the terminal receives the data, converts it into an appropriate format, and sends it to the server.

[0997] Step 4:

[0998] The server uses real-time data to identify the extent and pattern of damage. The input is the video and photos received in step 3, and the output is the analysis results that identify the extent and pattern of damage. Specifically, it applies an image analysis algorithm to identify the depth and spread of flooding.

[0999] Step 5:

[1000] The server analyzes images acquired from satellites and drones in real time. The input is images acquired from satellites and drones, and the output is the latest status of the affected areas. Specifically, image analysis technology is used to identify traffic conditions on major roads and the extent of damage.

[1001] Step 6:

[1002] The server analyzes data on past rescue operations and evacuation guidance, and proposes optimal countermeasures. The input is past rescue operation and evacuation guidance data, and the output is the results of proposing optimal rescue methods and evacuation guidance measures. Specifically, it performs data analysis based on past successful cases.

[1003] Step 7:

[1004] The user inputs their own health and psychological state into the device through the application. The input is the user's health and psychological state data, and the output is data that is saved on the device and sent to the server. Specifically, the data input from the device is sent to the server.

[1005] Step 8:

[1006] The server analyzes the health and psychological status data using a generative AI model. The input is the data sent in step 7, and the output is the results of determining the appropriate care provision and shelter location. Specifically, the server uses generative AI to analyze the data and propose appropriate countermeasures.

[1007] Step 9:

[1008] The server provides the user with appropriate information and countermeasures based on the analysis results. The input is the analysis results mentioned above, and the output is specific evacuation route and shelter information notified to the user. Specifically, the server calculates evacuation routes in real time and sends the information to the terminal.

[1009] Step 10:

[1010] The terminal provides real-time navigation to evacuation shelters based on the user's location information. The input is the user's location information from GPS etc. and evacuation route information received from the server, and the output is navigation information displayed in a format that is easy for the user to view. Specifically, the terminal integrates GPS data and evacuation route information and displays it on the screen.

[1011] 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.

[1012] As an embodiment of this invention, the operation of the system is explained step by step below. This system incorporates weather data, earthquake data, real-time video and photos, satellite and drone images, rescue operation and evacuation guidance data, the health and psychological state of disaster victims, and an emotion engine that recognizes the user's emotions. This allows the system to provide the user with optimal information and countermeasures.

[1013] Data collection and analysis

[1014] First, the server collects historical weather and earthquake data from various data sources (weather observation satellites and government agencies). The collected data is converted into an easy-to-analyze format, and data cleaning is performed to fill in missing data and remove noise. A generative AI model analyzes this historical data and predicts future disaster risk. After the analysis is complete, a predictive model is generated.

[1015] Real-time data collection and analysis

[1016] The device then transfers real-time video and photos from devices such as drones and fixed cameras to a server. The server uses this real-time data to identify the extent and pattern of damage. For example, the server analyzes the depth and spread of flooding and generates optimal evacuation routes.

[1017] The server also analyzes images acquired from satellites and drones in real time to obtain the latest information on the situation in the affected areas, including the traffic status of major roads and the extent of damage in the affected areas.

[1018] Rescue operations and evacuation guidance suggestions

[1019] The server analyzes a database of past rescue operations and evacuation guidance, proposing optimal rescue methods and evacuation guidance measures. This analysis is based on past successful cases, enabling a swift and effective response tailored to the current situation in the disaster area.

[1020] Analysis of the health and psychological status of disaster victims

[1021] Users enter their own health and psychological state into the device through the application. The device then sends this data to a server, which then analyzes it using generative AI. Based on this analysis, appropriate care for disaster victims and the location of evacuation shelters are determined.

[1022] Emotion recognition by emotion engine

[1023] When the user inputs their health status, the device captures their voice and facial expressions and analyzes them using an emotion engine. The emotion engine analyzes their voice and facial expressions to recognize the user's emotions. For example, it can determine whether the user is feeling stressed or calm.

[1024] Providing information and advice

[1025] Based on all of the above analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. The device displays this information in an easy-to-understand manner, supporting rapid evacuation and appropriate action. Additionally, depending on changes in the user's health or psychological state, the device prioritizes users who require appropriate medical assistance and guides them to evacuation shelters.

[1026] Furthermore, based on the emotion recognition results of the emotion engine, stress management and psychological support information is provided to users, allowing them to receive psychological support even in times of disaster.

[1027] Specific examples

[1028] For example, if a certain area is predicted to be flooded due to heavy rain, the server will analyze past weather data to generate a highly accurate flood forecast. At the same time, it will analyze drone images received in real time to identify areas that are already flooded. Based on the analysis results, the server will provide residents of the area with specific evacuation routes and shelter information in the event that evacuation is necessary.

[1029] Residents enter their physical and psychological state into the application, and the emotion engine measures their stress levels. The server then analyzes the information and provides medical assistance as needed. As a result, residents can evacuate with peace of mind and be quickly guided to a safe location.

[1030] As described above, this system is an advanced information system that makes integrated use of a wide variety of data and an emotion engine to quickly predict disasters and provide appropriate countermeasures, thereby ensuring the safety and psychological support of users.

[1031] The processing flow will be explained below.

[1032] Step 1:

[1033] The server collects historical weather and earthquake data from various sources, including weather satellites and government databases, and periodically retrieves the latest data using communication protocols (e.g., HTTP, API).

[1034] Step 2:

[1035] The server converts the collected weather and earthquake data into a format that is easy to analyze. Specifically, it standardizes the data (e.g., standardizing temperature, precipitation, wind speed, etc.), fills in missing data, and removes noise.

[1036] Step 3:

[1037] The server uses a generative AI model to analyze weather and earthquake data and predict future disaster risks. The AI ​​model performs pattern recognition based on past data and updates the prediction model.

[1038] Step 4:

[1039] The device collects data on the user's health and psychological state, and the user inputs their physical condition, stress level, etc. using a dedicated application.

[1040] Step 5:

[1041] The device captures the user's voice and facial expressions and sends them to the emotion engine, which then understands the user's emotions.

[1042] Step 6:

[1043] The emotion engine uses voice and facial expression analysis to recognize the user's emotions, for example, determining whether the user is feeling stressed or relieved.

[1044] Step 7:

[1045] The device transmits the collected health, psychological, and emotional data to a server, where the data is securely transferred using end-to-end encryption technology.

[1046] Step 8:

[1047] The server analyzes the received data using a generative AI model to assess the user's health and psychological state, and makes decisions about providing care and locating evacuation shelters based on this.

[1048] Step 9:

[1049] The device transmits real-time video and photos from drones and fixed cameras to a server, where the video is uploaded via the Internet.

[1050] Step 10:

[1051] The server analyzes the video and photos sent in real time, and uses generative AI to identify the extent and pattern of damage. For example, it analyzes the depth and spread of flooding to grasp the extent of damage in the relevant area.

[1052] Step 11:

[1053] The server analyzes real-time images acquired from satellites and drones, providing an up-to-date understanding of the situation in the affected areas, including the passability of major roads and the extent of damage in the affected areas.

[1054] Step 12:

[1055] The server analyzes a database of past rescue operations and evacuation guidance, and proposes optimal rescue methods and evacuation guidance measures. Based on past success stories, a plan tailored to the local situation is generated.

[1056] Step 13:

[1057] Based on all of the above analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. This information is then sent to the user's device and displayed in an easy-to-understand format.

[1058] Step 14:

[1059] The device displays the information sent from the server, including maps of safe evacuation routes, detailed information on evacuation shelters, and emergency measures. Users can evacuate safely based on this information.

[1060] Step 15:

[1061] Based on the recognition results of the emotion engine, the server provides users with information on stress management and psychological support, which helps users to evacuate safely while receiving psychological support.

[1062] Step 16:

[1063] The server records all data and feedback and uses it to improve the accuracy of the generative AI model. The model is retrained based on analysis results and user behavior data, continuously improving the accuracy of disaster prediction and response.

[1064] Example 2

[1065] 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."

[1066] In order to carry out appropriate evacuation and rescue operations quickly and effectively during disasters, it is necessary to collect and analyze a wide variety of data in real time and provide users with appropriate information and countermeasures. However, conventional systems have limitations in the accuracy of data collection and analysis, making it difficult to respond quickly. Furthermore, they do not adequately provide support that takes into account the health, psychological state, and emotions of disaster victims. For these reasons, improving safety and psychological support during disasters is a challenge.

[1067] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting past weather data and earthquake data and analyzing this data, means for analyzing videos and photos transmitted in real time to identify the extent and pattern of damage, means for analyzing images acquired from satellites and drones to grasp the situation in the disaster-stricken area, means for analyzing past rescue operations and evacuation guidance data to propose optimal countermeasures, means for analyzing the health and psychological states of disaster victims and determining care and shelter placement, and means for analyzing the user's voice and facial expressions using an emotion engine to recognize the user's emotional state. This enables rapid analysis of various data and provision of appropriate information taking into account the user's health and emotional state.

[1068] "Weather data" refers to weather observation results and forecast information such as temperature, precipitation, wind speed, wind direction, and humidity.

[1069] "Earthquake data" refers to observation results related to earthquakes, including data such as the earthquake's seismic intensity, epicenter, and date and time of occurrence.

[1070] "Analysis means" refers to devices or software that perform calculations and statistical processing on collected data to extract and interpret specific information.

[1071] "Real-time data" refers to data that can be immediately acquired and analyzed based on the current situation.

[1072] "Footage and photographs" refers to visual data captured by photographic equipment such as cameras and drones.

[1073] "Affected area" refers to the geographic area affected by a disaster.

[1074] "Damage pattern" refers to the type and distribution of specific impacts and damage caused by a disaster.

[1075] "Satellite imagery" refers to image data of the Earth captured by sensors mounted on artificial satellites.

[1076] "Drone imagery" refers to image data captured by an unmanned aerial vehicle.

[1077] "Situational awareness" refers to the act of understanding the current situation or state based on collected data.

[1078] "Rescue activities" refers to activities such as saving lives, distributing supplies, and providing medical support during disasters.

[1079] "Evacuation guidance" refers to the act of instructing and guiding people to a safe place during a disaster.

[1080] "Health status" refers to information about physical health, such as the state of each bodily function and tissue, and the presence or absence of disease.

[1081] "Psychological state" refers to information about mental states such as stress, anxiety, and mental well-being.

[1082] An "emotion engine" refers to an algorithm or system that analyzes and identifies emotions from a user's voice, facial expressions, etc.

[1083] A "generative AI model" refers to an artificial intelligence model that learns from large amounts of data and makes highly accurate predictions and analyses of new data.

[1084] "Appropriate information and measures" refers to information and measures that will enable users to evacuate safely and obtain the necessary support in the event of a disaster.

[1085] The present invention is a system that collects and analyzes a variety of data and provides prompt and appropriate information and countermeasures in the event of a disaster. A specific example of this system will be described below.

[1086] Data collection and analysis

[1087] The server collects historical weather and earthquake data from weather observation satellites and government agencies. This data is converted into an easy-to-analyze format and cleaned to fill in missing data and remove noise. A suitable tool for this is the Python pandas library.

[1088] Analysis using generative AI models

[1089] The server analyzes the collected and cleaned data using a generative AI model, specifically using deep learning frameworks such as TensorFlow and PyTorch to build a disaster risk prediction model.

[1090] Real-time data collection

[1091] The device transfers real-time video and photos from drones and fixed cameras to a server, and can transmit data over Wi-Fi or 5G networks.

[1092] Real-time data analysis

[1093] The server uses the received real-time data to identify the extent and pattern of damage. For example, it can use OpenCV to perform image analysis to identify the depth and spread of flooding. It can also use object detection algorithms to check the traffic status of major roads.

[1094] Rescue operations and evacuation guidance suggestions

[1095] The server analyzes past rescue operations and evacuation guidance data and proposes optimal rescue methods and evacuation guidance measures. This is achieved by searching for and analyzing the necessary information from the database using SQL queries.

[1096] Analysis of the health and psychological status of disaster victims

[1097] Users input their own health and psychological status through the application. The device then sends this data to a server, which then uses generative AI to analyze the data. For example, NLP (natural language processing) technology can be used to analyze the user's input text and determine the priority of medical assistance.

[1098] Emotion recognition by emotion engine

[1099] When a user enters their health status, the device captures the user's voice and facial expressions and analyzes them using an emotion engine. The emotion engine uses deep learning models to analyze the voice and facial expressions and recognize the user's emotions. For example, a model built using the Keras library can be used to determine whether the user is feeling stressed.

[1100] Providing information and advice

[1101] The server provides users with real-time disaster information, evacuation routes, and countermeasures based on all of the above analysis results. The device uses HTML5 and JavaScript to display this information in an easy-to-understand manner. For example, evacuation routes can be displayed on a map using the Google Maps API.

[1102] Specific examples

[1103] For example, if heavy rain is predicted to cause flooding in a certain area, the server will use past weather data to generate highly accurate flood predictions. At the same time, it will analyze drone images received in real time to identify areas that are already flooded. Based on this information, the server will provide specific evacuation routes and shelter information to residents in the area.

[1104] Prompt Sentence Examples

[1105] "Please suggest evacuation measures for areas predicted to be flooded by heavy rain. Based on the analysis results of historical weather data and drone imagery, please tell us how to provide specific evacuation routes and necessary medical assistance."

[1106] As described above, this system is an advanced information system that makes integrated use of a wide variety of data and an emotion engine to quickly predict disasters and provide appropriate countermeasures, thereby ensuring the safety and psychological support of users.

[1107] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1108] Step 1:

[1109] The server collects past weather and earthquake data from weather observation satellites and government agencies. Specifically, it acquires the data using the API of the Japan Meteorological Agency and the API of satellite data providers and stores it in a database. The input is a dataset from each API, and the output is a dataset for preparation for analysis.

[1110] Step 2:

[1111] The server converts the acquired data into a format suitable for analysis. It uses the Python pandas library to convert the data into CSV format, imputes missing data, and removes noise. The input is the collected raw data, and the output is the cleaned and formatted data.

[1112] Step 3:

[1113] The server feeds the cleaned data into a generative AI model to build a model that predicts future disaster risk. It uses TensorFlow and PyTorch to train the deep learning model and output the prediction results. The input is the cleaned dataset, and the output is a disaster risk prediction model and the prediction results.

[1114] Step 4:

[1115] The terminal transfers real-time video and photos sent from drones and fixed cameras to a server. The device transmits data using Wi-Fi or 5G. The input is real-time video and photos from the device, and the output is data transferred to the server.

[1116] Step 5:

[1117] The server analyzes the received real-time data to identify the extent and pattern of damage. It uses OpenCV to perform image analysis to determine the depth and extent of flooding and the traffic situation on major roads. The input is real-time video and photos, and the output is the results of identifying the extent and pattern of damage.

[1118] Step 6:

[1119] The server analyzes past rescue operation and evacuation guidance data and proposes optimal rescue methods and evacuation guidance measures. It searches the database using SQL queries and creates rescue plans based on the analysis results. The input is past rescue operation data, and the output is the proposed rescue method and evacuation guidance measures.

[1120] Step 7:

[1121] Users input their own health and psychological state through the application. The device sends this to the server, which analyzes it using generative AI. NLP technology is used to analyze the input text and determine the priority of medical assistance. The input is the user's health and psychological state data, and the output is the analysis results and the priority of medical assistance.

[1122] Step 8:

[1123] The device captures the user's voice and facial expressions and analyzes them using an emotion engine. The emotion engine uses a deep learning model to analyze the voice and facial expressions and recognize the user's emotions. The input is the user's voice and facial expression data, and the output is the recognized emotional state.

[1124] Step 9:

[1125] The server provides users with real-time disaster information, evacuation routes, and countermeasures based on all analysis results. The device displays this information in an easy-to-understand manner and prioritizes the provision of necessary medical assistance. Information is visualized using HTML5 and JavaScript, and evacuation routes are displayed using the Google Maps API. The input is various analysis results, and the output is specific disaster information and evacuation routes that are displayed to the user.

[1126] (Application example 2)

[1127] 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."

[1128] When a disaster occurs, it is difficult to grasp the situation in the affected area and provide victims with prompt and appropriate information. At the same time, there is a need to provide food and other necessities quickly, accurately grasp the health and psychological state of victims, and provide psychological care. To solve these problems, a system is needed that can collect and analyze information from multiple data sources in real time and quickly propose countermeasures.

[1129] The identification processing 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 means for collecting past weather data and earthquake data and analyzing this data, means for analyzing videos and photos transmitted in real time to identify the extent and pattern of damage, means for analyzing images acquired from satellites and drones to grasp the situation in the disaster-stricken area, means for analyzing past rescue operations and evacuation guidance data to propose optimal countermeasures, means for analyzing the health and psychological states of disaster victims and determining care and shelter placement, means for providing food to disaster-stricken areas using drones and autonomous mobile devices, means for understanding the psychological states of disaster victims using emotion recognition technology and providing stress management information, and means for providing appropriate information and countermeasures to users based on these means. This enables accurate and rapid understanding of the situation in the disaster-stricken area, rapid provision of supplies including food, and appropriate information and psychological support to disaster victims.

[1130] "Past weather data" refers to data relating to weather observed in the past, including information such as temperature, precipitation, wind speed, wind direction, and humidity.

[1131] "Earthquake data" refers to data that includes information on the epicenter, seismic intensity, and waveforms of shaking at the time of an earthquake, and is the basis for analyzing the scale and extent of an earthquake's impact.

[1132] "Video and photos transmitted in real time" refers to video and still image data obtained by instantly photographing and recording the current situation and then instantly transmitting that data.

[1133] "Damage range and damage pattern" is pattern information that indicates the range of the area affected by the disaster and the type and scale of the damage.

[1134] "Imagery obtained from satellites and drones" refers to image data taken from the air, including images of the earth's surface taken by satellites or unmanned aerial vehicles.

[1135] "Status of the affected areas" refers to data showing the current state of the affected areas at the time of the disaster and afterwards, including the scale, scope and detailed information of the damage.

[1136] "Past rescue operation and evacuation guidance data" refers to data on rescue and evacuation operations that have been carried out in the past, including success stories, failure stories, and information on the processes involved.

[1137] "Optimal response measures" are proposals based on analyzed data that propose optimal guidelines for action, evacuation routes, rescue methods, etc. for affected areas and victims.

[1138] "The health and psychological state of the disaster victims" is data indicating the physical health and psychological state of the disaster victims.

[1139] "Care and sheltering" refers to providing medical and psychological support to disaster victims, as well as the provision and arrangement of appropriate shelter.

[1140] "Drones and autonomous mobile devices" refers to unmanned aerial vehicles and ground mobile devices that use autonomous driving technology, which can be used to transport supplies and food.

[1141] "Emotion recognition technology" is a technology that identifies human emotions through voice analysis and facial expression analysis, and evaluates psychological states such as stress and a sense of security.

[1142] This invention is a system for collecting and analyzing information in the event of a disaster, and providing appropriate countermeasures. The system collects various data, analyzes it, and provides information to users in real time. It also uses drones and autonomous mobile devices to quickly provide food and relief supplies.

[1143] Hardware Configuration

[1144] Server: Processes data and analyzes the generated AI model.

[1145] Cloud server: Data storage and big data analysis are performed using AWS.

[1146] Drones: Collect images of disaster areas and deliver supplies.

[1147] Autonomous mobile devices: Distribute food and relief supplies on the ground.

[1148] Smartphone: Used as a device for users to input their health and psychological status.

[1149] Fixed cameras: Providing real-time footage of the affected areas.

[1150] Software Configuration

[1151] Python: A programming language for data analysis, specifically using Scikit-learn and TensorFlow.

[1152] OpenCV: A library for performing image analysis.

[1153] AWS Lambda: An AWS service for serverless data processing.

[1154] Emotion Engine API: Technology that recognizes emotions through voice and facial expression analysis.

[1155] Data collection and analysis process

[1156] 1. Historical data collection and analysis:

[1157] The server collects historical weather and earthquake data from government agencies and weather observation satellites, which is then analyzed using a generative AI model to predict future disaster risks.

[1158] 2. Real-time data collection:

[1159] Real-time video and photos from drones and fixed cameras are sent to a server, which analyzes the data to identify the extent and pattern of damage.

[1160] 3. Understanding the situation in the affected areas:

[1161] Images acquired from satellites and drones will be analyzed to provide an up-to-date picture of the situation in the affected areas, including road conditions and the extent of damage.

[1162] 4. Suggestions for rescue operations and evacuation:

[1163] The server analyzes past rescue operations and evacuation guidance data and proposes the optimal response measures.

[1164] 5. Health and Psychological Analysis:

[1165] Users input their health and psychological state using their smartphones, which is then analyzed by the server. An emotion engine is used to recognize the user's emotions and provide stress management information.

[1166] 6. Information provision and implementation of measures:

[1167] Based on all the above analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. It also uses drones and autonomous mobile devices to quickly deliver food to disaster-stricken areas.

[1168] Specific examples

[1169] For example, if a flood is predicted in a certain area, the server analyzes past weather data to generate a highly accurate flood forecast. At the same time, it analyzes drone images received in real time to identify flooded areas. As a result, it provides information on optimal evacuation routes and evacuation shelters. It also provides necessary medical assistance and psychological support based on the individual's health and psychological state.

[1170] Prompt Sentence Examples

[1171] Below are some example prompts to input to the generative AI model:

[1172] Based on the information below, please suggest appropriate evacuation routes and food distribution methods for the affected areas.

[1173] Weather data: {Weather data details}

[1174] Satellite image: {satellite image URL}

[1175] Real-time imagery from drone: {drone image URL}

[1176] Victim's health status: {health status data}

[1177] Victim's psychological state: {Psychological state data}

[1178] Emotion analysis result: {Emotion analysis result}

[1179] This system is capable of quickly analyzing huge amounts of data and providing appropriate information and assistance in real time.

[1180] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1181] Step 1:

[1182] The server collects historical weather and earthquake data.

[1183] Input: Data from weather satellites and government agencies

[1184] How it works: The server queries these data sources through APIs to retrieve weather and earthquake data.

[1185] Output: Data obtained in the form of historical weather and earthquake data

[1186] Step 2:

[1187] The server analyzes the collected historical data and uses a generative AI model to predict the risk of future disasters.

[1188] Input: Weather and earthquake data collected in Step 1

[1189] How it works: Cleans data and converts it into an analyzable format. Enters prompts into a generative AI model to perform predictive calculations.

[1190] Output: Prediction data of future disaster risk

[1191] Step 3:

[1192] Video and photos are transmitted in real time to identify the extent and pattern of damage.

[1193] Input: Real-time video and photos from drones and fixed cameras

[1194] Operation: The server receives the video data and analyzes it using OpenCV. It identifies the extent and pattern of damage and analyzes the image data.

[1195] Output: Specific information on the extent and pattern of damage

[1196] Step 4:

[1197] Images obtained from satellites and drones are analyzed to understand the situation in the affected areas.

[1198] Input: Satellite and drone imagery

[1199] Operation: The server receives images acquired from satellites and drones and analyzes them using OpenCV to grasp the current situation in the affected areas, determine road traffic conditions, and the extent of damage.

[1200] Output: Situation data of the affected area

[1201] Step 5:

[1202] We analyze past rescue operations and evacuation guidance data to propose optimal response measures.

[1203] Input: Past rescue operations and evacuation guidance data stored in the database

[1204] How it works: The server analyzes historical data and uses generative AI models to generate optimal rescue operations and evacuation guidance prompts.

[1205] Output: Proposal data for optimal countermeasures

[1206] Step 6:

[1207] Analyze the health and psychological state of disaster victims to determine care and evacuation placement.

[1208] Input: Health and psychological data entered by the user into the device, and analysis results by the emotion engine

[1209] How it works: The server uses generative AI models to analyze data and determine appropriate care and shelter placement. It also uses an emotion engine to provide stress management information.

[1210] Output: Care and shelter placement proposal data

[1211] Step 7:

[1212] Delivering food to disaster-stricken areas using drones and autonomous mobile devices.

[1213] Input: Situation data of the affected area, location information of the victims

[1214] How it works: The server analyzes the optimal route and sends instructions to drones and autonomous mobile devices, which then deliver food to disaster-stricken areas.

[1215] Output: Data on completed delivery of supplies and food

[1216] Step 8:

[1217] Provide users with appropriate information and measures.

[1218] Input: Analysis results from the above steps and proposed data

[1219] How it works: The server compiles this data and sends it to the user's device. The user receives the appropriate information on their smartphone and can take action.

[1220] Output: Appropriate information and measures to be sent to the user's device

[1221] In this way, data collection, analysis, and execution are performed in coordination at each step, enabling rapid response and support for disaster victims.

[1222] 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.

[1223] 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.

[1224] 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.

[1225] [Fourth embodiment]

[1226] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1227] 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.

[1228] 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).

[1229] 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.

[1230] 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.

[1231] 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).

[1232] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1233] 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.

[1234] 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.

[1235] 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.

[1236] 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.

[1237] 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.

[1238] 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."

[1239] As an embodiment of the present invention, the operation of the system is explained step by step below. This system collects and analyzes a wide range of data, such as weather data, earthquake data, real-time video and photos, satellite and drone images, rescue operation and evacuation guidance data, and the health and psychological state of disaster victims, and provides users with appropriate information and countermeasures.

[1240] Data collection and analysis

[1241] First, the server collects historical weather and earthquake data from various data sources (weather observation satellites and government agencies). The collected data is converted into an easy-to-analyze format, and data cleaning is performed to fill in missing data and remove noise. A generative AI model analyzes this historical data and predicts future disaster risk. After the analysis is complete, a predictive model is generated.

[1242] Real-time data collection and analysis

[1243] The device then transfers real-time video and photos from devices such as drones and fixed cameras to a server. The server uses this real-time data to identify the extent and pattern of damage. For example, the server analyzes the depth and spread of flooding and generates optimal evacuation routes.

[1244] The server also analyzes images acquired from satellites and drones in real time to obtain the latest information on the situation in the affected areas, including the traffic status of major roads and the extent of damage in the affected areas.

[1245] Rescue operations and evacuation guidance suggestions

[1246] The server analyzes a database of past rescue operations and evacuation guidance, proposing optimal rescue methods and evacuation guidance measures. This analysis is based on past successful cases, enabling a swift and effective response tailored to the current situation in the disaster area.

[1247] Analysis of the health and psychological status of disaster victims

[1248] Users enter their own health and psychological state into the device through the application. The device then sends this data to a server, which then analyzes it using generative AI. Based on this analysis, appropriate care for disaster victims and the location of evacuation shelters are determined.

[1249] Providing information and advice

[1250] Based on all of the above analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. The device displays this information in an easy-to-understand manner, supporting rapid evacuation and appropriate action. Additionally, depending on changes in the user's health or psychological state, the device prioritizes users who require appropriate medical assistance and guides them to evacuation shelters.

[1251] Specific examples

[1252] For example, if flooding due to heavy rain is predicted in a certain area, the server analyzes past weather data to make a highly accurate flood forecast. At the same time, it analyzes drone images received in real time to identify areas that have already been flooded. Based on the analysis results, the server provides residents of the area with specific evacuation routes and shelter information in the event that evacuation is necessary. Furthermore, residents can enter their own health and psychological state into the application, and the server will adjust care and assistance accordingly, providing appropriate medical support.

[1253] As described above, this system is an advanced information system that handles a wide variety of data in an integrated manner and is capable of predicting disasters and providing appropriate countermeasures promptly.

[1254] The processing flow will be explained below.

[1255] Step 1:

[1256] The server collects historical weather and earthquake data, including connections to weather satellites and government databases, and periodically retrieves the latest data using communication protocols (e.g., HTTP, API).

[1257] Step 2:

[1258] The server converts the collected weather and earthquake data into a format that is easy to analyze. Specifically, it standardizes the data (e.g., standardizing temperature, precipitation, wind speed, etc.), fills in missing data, and removes noise.

[1259] Step 3:

[1260] The server uses a generative AI model to analyze weather and earthquake data and predict future disaster risks. The AI ​​model performs pattern recognition based on past data and updates the prediction model.

[1261] Step 4:

[1262] The device transmits real-time video and photos from drones and fixed cameras to a server, where the video is uploaded via the Internet.

[1263] Step 5:

[1264] The server analyzes the video and photos sent in real time, and uses generative AI to identify the extent and pattern of damage. For example, it analyzes the depth and spread of flooding to grasp the extent of damage in the relevant area.

[1265] Step 6:

[1266] The server analyzes real-time images acquired from satellites and drones, which allows for a grasp of road conditions and the extent of damage in affected areas. Satellite images are analyzed using high-resolution image analysis technology.

[1267] Step 7:

[1268] The server analyzes a database of past rescue operations and evacuation guidance, and proposes optimal rescue methods and evacuation guidance measures. Based on past success stories, a plan tailored to the local situation is generated.

[1269] Step 8:

[1270] Through the application, users input their own health and psychological conditions, such as headache, fever, and stress, into input fields.

[1271] Step 9:

[1272] The device transmits health and psychological data from the user to a server, where the data is securely transferred using end-to-end encryption technology.

[1273] Step 10:

[1274] The server analyzes the received health and psychological status data to determine appropriate care for the victims and the placement of evacuation shelters. The generating AI analyzes the data and prioritizes support for users with high urgency.

[1275] Step 11:

[1276] Based on the analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. This information is then sent to the user's device and displayed in an easy-to-understand manner.

[1277] Step 12:

[1278] The device displays the information sent from the server, including maps of safe evacuation routes, detailed information on evacuation shelters, and emergency measures. Users can evacuate safely based on this information.

[1279] Step 13:

[1280] The server records all data and feedback and uses it to improve the accuracy of the generative AI model. The model is retrained based on analysis results and user behavior data, continuously improving the accuracy of disaster prediction and response.

[1281] Example 1

[1282] 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."

[1283] When a natural disaster occurs, there is a need to provide fast and accurate information and propose countermeasures, but conventional systems take time to collect and analyze data, making it difficult to respond in real time. Furthermore, there was a lack of systems that could adequately provide appropriate care and arrange evacuation shelters taking into account the health and psychological state of victims. Furthermore, there were limited means to effectively integrate and analyze past disaster data and real-time video footage, making it difficult to propose optimal rescue operations and evacuation guidance measures.

[1284] 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.

[1285] In this invention, the server includes means for collecting and analyzing past weather and earthquake data, means for analyzing video and photos transmitted in real time to identify the extent and pattern of damage, means for analyzing images acquired from satellites and drones to grasp the situation in the disaster-stricken area, means for analyzing past rescue operation and evacuation guidance data to propose optimal countermeasures, means for analyzing the health and psychological state of disaster victims and determining care and evacuation shelter placement, means for preprocessing the collected data, filling in missing data, and removing noise, means for generating a predictive model using the collected data with a generative AI model, means for analyzing the collected video in real time to generate evacuation routes, means for providing real-time disaster information, evacuation routes, and countermeasures to users based on the analysis results, and means for displaying appropriate information and countermeasures on a terminal based on these means. This enables the provision of rapid and accurate disaster information, appropriate care for disaster victims, and the proposal of optimal rescue operations and evacuation guidance measures.

[1286] "Historical weather data" is information about past weather conditions collected from data sources such as weather observation satellites and government agencies.

[1287] "Earthquake Data" means information about past and present earthquake activity collected by seismic monitoring agencies and seismic instruments.

[1288] "Means for analysis" refers to a processing method for converting collected data into a format that is easy to analyze, cleaning the data as necessary, and then analyzing the data using a generative AI model to generate a predictive model.

[1289] "Video and photographs transmitted in real time" refers to video and photographic data that records the disaster situation and is transmitted in real time from devices such as drones and fixed cameras.

[1290] "Means for identifying the extent and pattern of damage" refers to an analytical method for analyzing video and photographs transmitted in real time to identify the extent and pattern of damage caused by a disaster.

[1291] "Images obtained from satellites and drones" are visual data taken from the sky, and are image data collected by satellites and drones that show the latest situation in the disaster-stricken areas.

[1292] "Means for understanding the situation in the disaster-stricken areas" refers to a method for analyzing images obtained from satellites and drones to understand the current situation in the disaster-stricken areas and the extent of the damage.

[1293] "Rescue operation and evacuation guidance data" refers to records of rescue operations and evacuation guidance that have been carried out in the past, and includes information on successful cases and countermeasures.

[1294] The "means of proposing optimal response measures" is a method for analyzing past rescue operations and evacuation guidance data, and proposing the most effective rescue methods and evacuation guidance measures based on the current situation.

[1295] "Health and psychological conditions of disaster victims" refers to data on the physical health and psychological conditions of disaster victims at the time of the disaster.

[1296] "Measures for determining care and shelter placement" refers to methods for analyzing the health and psychological state of disaster victims and determining the type of care needed and appropriate shelter placement.

[1297] "Preprocessing of collected data" refers to a processing method for converting data into a format that is easy to analyze, filling in missing data, and removing noise.

[1298] "Means for filling in missing data and removing noise" refers to cleaning techniques for filling in missing parts of collected data and eliminating unnecessary noise.

[1299] A "generative AI model" is a model trained using artificial intelligence, an algorithm that analyzes collected data and performs predictions and pattern recognition.

[1300] "Means for generating a predictive model" refers to a method for using a generative AI model to predict future disaster risks and predictions based on collected data.

[1301] The "means for generating evacuation routes" is a method for analyzing video footage collected in real time and determining the optimal evacuation route based on the extent of damage and road conditions.

[1302] The "means for providing disaster information, evacuation routes, and countermeasures" is a system for providing users with necessary disaster information, evacuation routes, and necessary countermeasures based on the analysis results.

[1303] MODE FOR CARRYING OUT THE INVENTION

[1304] To implement this invention, the following specific procedures and details of the hardware and software used are required. This system integrates a wide range of data, including weather data, earthquake data, real-time video, photographs, satellite and drone images, rescue operation and evacuation guidance data, and the health and psychological state of disaster victims, and quickly provides users with appropriate information and countermeasures.

[1305] Data collection and analysis

[1306] The server collects historical weather and earthquake data from data sources such as weather observation satellites and government agencies. The collected data is then converted into a format that is easy to analyze using an ETL (Extract, Transform, Load) process. Specifically, the data is converted from JSON format to CSV format and measurement units are standardized. Data cleaning is also performed, including filling in missing data and removing noise.

[1307] The generative AI model is trained using a machine learning framework (such as TensorFlow or PyTorch) to analyze past data and predict future disaster risk. Based on the prediction results, a predictive model is generated, and disaster risk maps and statistical data are created.

[1308] Real-time data collection and analysis

[1309] The terminal transfers real-time video and photos sent from devices such as drones and fixed cameras to a server using real-time communication protocols such as MQTT and WebSocket.

[1310] The server uses the transferred real-time data to identify the extent and pattern of damage. It uses computer vision technologies (such as OpenCV and TensorFlow) to analyze the depth and extent of flooding and generate optimal evacuation routes. Furthermore, the server analyzes images acquired from satellites and drones to obtain the latest information on the situation in the affected areas.

[1311] Rescue operations and evacuation guidance suggestions

[1312] The server manages a database of past rescue operations and evacuation guidance, which is stored using a relational database such as an SQL server. This data is analyzed and optimal rescue methods and evacuation guidance measures are proposed based on past success stories.

[1313] Analysis of the health and psychological status of disaster victims

[1314] Users input their health and psychological status into the device through the application. The input data is collected through the smartphone application and sent to the server via HTTP requests. The server then analyzes this data using a generative AI model to determine the appropriate care provision and shelter placement.

[1315] Providing information and advice

[1316] The server provides users with real-time disaster information, evacuation routes, and countermeasures based on all analysis results. The device displays this information in an easy-to-understand manner, supporting rapid evacuation and appropriate action. It also prioritizes users who require appropriate medical assistance and guides them to evacuation shelters based on their health and psychological state.

[1317] Specific examples

[1318] For example, if a certain area is predicted to be flooded due to heavy rain, the server uses an API to collect historical weather data and preprocesses the data using an ETL process. A generative AI model is used to make highly accurate flood predictions, while simultaneously analyzing real-time drone images to identify areas that have already been flooded. Based on the analysis results, the system provides residents with specific evacuation routes and shelter information. Users enter their own health and psychological state into the application, and the server analyzes this data to provide appropriate medical support.

[1319] Prompt Sentence Examples

[1320] "For the next natural disaster, please provide information on the best evacuation routes and shelters. Also, please provide procedures for special assistance for residents with illnesses or mental health issues."

[1321] As described above, this invention is an advanced information system that handles a wide variety of data in an integrated manner and quickly provides disaster prediction and appropriate countermeasures.

[1322] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1323] Step 1:

[1324] The server collects historical weather and earthquake data from data sources such as weather observation satellites and government agencies. Specifically, it periodically retrieves this data through an API and stores it in a database. The input data is in JSON or XML format, and is converted into a standardized format. The output is a dataset that can be analyzed.

[1325] Step 2:

[1326] The server preprocesses the collected data using the ETL (Extract, Transform, Load) process. It converts the data into CSV, fills in missing values, and removes noise. Specifically, it fills in missing data by averaging the preceding and following values, and removes anomalous data points. The input is the data before transformation, and the output is the preprocessed data.

[1327] Step 3:

[1328] The server inputs the preprocessed data into a generative AI model for analysis. It uses a machine learning framework (e.g., TensorFlow or PyTorch) to predict the risk of future disasters. The input is the preprocessed data, and the output is a risk prediction model and a probability map of disaster occurrence.

[1329] Step 4:

[1330] The terminal transfers real-time video and photo data from devices such as drones and fixed cameras to a server using real-time communication protocols such as MQTT and WebSocket. The input is video and photo data, and the output is real-time data transfer to the server.

[1331] Step 5:

[1332] The server analyzes the video and photos received in real time and uses computer vision technology (such as OpenCV and TensorFlow) to identify the depth and extent of flooding. The input is real-time data, and the output is the identification of the extent and pattern of damage.

[1333] Step 6:

[1334] The server analyzes images acquired from satellites and drones in real time to grasp the latest situation in the disaster-stricken areas. Image analysis is performed to quantify road traffic conditions and the extent of damage. The input is image data from satellites and drones, and the output is a report of the latest situation in the disaster-stricken areas.

[1335] Step 7:

[1336] The server manages a database of past rescue operations and evacuation guidance using a relational database such as an SQL server, analyzes this data, and proposes optimal rescue methods and evacuation guidance measures. The input is past data, and the output is the proposed rescue methods and evacuation guidance measures.

[1337] Step 8:

[1338] Users input their own health and psychological status into the device through the application. This data is sent to the server via HTTPS. The input is the user's health and psychological status data, and the output is the data sent to the server.

[1339] Step 9:

[1340] The server uses a generative AI model to analyze the user's health and psychological state data and determine the appropriate care provision and shelter placement. The input is the user's health and psychological data, and the output is the decision on care provision and shelter placement.

[1341] Step 10:

[1342] The server provides users with real-time disaster information, evacuation routes, and countermeasures based on all analysis results. This information is sent to the terminal and visually presented to the user. The input is the analysis results, and the output is the information provided to the user.

[1343] Step 11:

[1344] The device displays disaster information and evacuation routes in an easy-to-understand format for users, supporting rapid evacuation and appropriate action. The input is notification data from the server, and the output is information displayed to the user. In addition, if the user needs appropriate medical assistance based on their health and psychological state, the device will guide them to an evacuation shelter with priority.

[1345] The above is the specific flow of operation of this system.

[1346] (Application example 1)

[1347] 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."

[1348] It is difficult to provide prompt and accurate information and evacuation guidance during disasters. There is also a lack of appropriate care and shelter locations based on the psychological and physical health status of disaster victims. This often results in an inability to respond appropriately when a disaster occurs, which can lead to the spread of damage and delays in providing appropriate assistance.

[1349] 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.

[1350] In this invention, the server includes means for collecting and analyzing past weather and earthquake data, means for analyzing video and photographs transmitted in real time to identify the extent and pattern of damage, means for analyzing images acquired from satellites and drones to grasp the situation in the disaster-stricken area, means for analyzing past rescue operations and evacuation guidance data to propose optimal countermeasures, means for analyzing the health and psychological state of disaster victims and determining care and evacuation shelter placement, means for providing appropriate information and countermeasures to users based on these means, means for analyzing weather, satellite, and drone data using generation AI to propose optimal evacuation routes, and means for providing real-time navigation to evacuation shelters based on the user's location information. This enables rapid and effective disaster response and appropriate evacuation guidance based on advanced information processing.

[1351] "Historical weather data" refers to historical weather information, including weather elements such as temperature, precipitation, and wind speed.

[1352] "Earthquake data" refers to observational information about earthquakes, including details such as the epicenter, seismic intensity, and date and time of occurrence.

[1353] "Video and photos transmitted in real time" refers to visual data that captures the current situation in real time, and includes video and still images.

[1354] "Damage scope and damage pattern" refers to the physical extent of the impact of a disaster and the specific form of that impact.

[1355] "Satellite and drone-derived imagery" refers to high-resolution visual data taken from the air, such as satellites or drones.

[1356] "The situation in the affected areas" refers to the current state of the areas where the disaster occurred, including the extent of the damage and the area affected.

[1357] "Rescue operation and evacuation guidance data" refers to information on past rescue operations and evacuation cases, including both successful and unsuccessful cases.

[1358] "Optimal response" refers to the action or measure that is most appropriate for the current situation.

[1359] "The health and psychological state of the disaster victims" refers to the physical health and psychological state of the people affected by the disaster.

[1360] "Care and shelter placement" refers to the necessary support for disaster victims and the appropriate placement of shelters.

[1361] "Appropriate information and measures" refers to the correct information and guidelines for action that should be provided to users.

[1362] "Weather data, satellite data, and drone data" refers collectively to weather information and visual data taken from the air.

[1363] "Generative AI" refers to artificial intelligence technology that analyzes and predicts based on input data.

[1364] An "evacuation route" refers to a route for evacuation in the event of a disaster.

[1365] "Real-time navigation" refers to a system that provides real-time directions based on your current location.

[1366] A system that specifically embodies the present invention is configured as follows.

[1367] Hardware and software used

[1368] The system uses hardware such as servers, smartphones, drones, and satellites, as well as the following software:

[1369] 1. Python

[1370] 2. OpenCV (Drone video analysis)

[1371] 3. scikit-learn (data analysis and predictive models)

[1372] 4. TensorFlow (generative AI models)

[1373] 5. geopy (distance calculation)

[1374] Data collection and analysis

[1375] First, the server collects weather and earthquake data from various data sources (weather observation satellites and government agencies). The collected data is cleaned and converted into a format that is easy to analyze. The server then uses a generative AI model to analyze this past data and predict future disaster risks.

[1376] Real-time data collection and analysis

[1377] The terminal then transfers real-time video and photos sent from devices such as drones and fixed cameras to a server. The server uses this real-time data to identify the extent and pattern of damage. The server also analyzes images acquired from satellites and drones in real time to grasp the latest situation in the affected area.

[1378] Rescue operations and evacuation guidance suggestions

[1379] The server analyzes a database of past rescue operations and evacuation guidance, proposing optimal rescue methods and evacuation guidance measures. This analysis is based on past successful cases, enabling a swift and effective response tailored to the current situation in the disaster area.

[1380] Analysis of the health and psychological status of disaster victims

[1381] Users enter their own health and psychological state into the device through the application. The device then sends this data to a server, which then analyzes it using generative AI. Based on this analysis, appropriate care for disaster victims and the placement of evacuation shelters are determined.

[1382] Information and navigation

[1383] Based on all of the above analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. The device displays this information in an easy-to-understand manner, supporting rapid evacuation and appropriate action. Real-time navigation to evacuation shelters is also provided based on the user's location information.

[1384] Specific examples

[1385] For example, in this application, named "Emergency Guardian," if a user is in an area where flooding due to heavy rain is predicted, the server analyzes past weather data to make highly accurate flood predictions. At the same time, it analyzes drone images received in real time to identify areas that have already been flooded. Based on the analysis results, the server provides residents in the area with specific evacuation routes and shelter information in the event that evacuation is necessary. Furthermore, residents can enter their own health and psychological state into the application, and the server will adjust care and assistance accordingly, providing appropriate medical support.

[1386] Prompt Sentence Examples

[1387] Weather data: {weather_data}, Satellite data: {satellite_data}, Drone data: {drone_data}

[1388] Please analyze the above data and provide the best evacuation route."

[1389] This will enable rapid and effective disaster response and appropriate evacuation guidance based on advanced information processing.

[1390] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1391] Step 1:

[1392] The server collects historical weather and earthquake data. The input is data provided by weather observation satellites and government agencies, and the output is raw data stored on the server for analysis. Specifically, the server retrieves data through an API and stores it in a database.

[1393] Step 2:

[1394] The server analyzes the collected weather and earthquake data. The input is the past weather and earthquake data saved in step 1, and the output is the result of predicting future disaster risk based on the generative AI model. Specific operations include data cleaning, noise removal, and application of analysis algorithms.

[1395] Step 3:

[1396] The terminal transfers the video and photos sent in real time from drones, fixed cameras, etc. to the server. The input is the real-time video and photos sent from the drones or fixed cameras, and the output is the data transferred to the server. Specifically, the terminal receives the data, converts it into an appropriate format, and sends it to the server.

[1397] Step 4:

[1398] The server uses real-time data to identify the extent and pattern of damage. The input is the video and photos received in step 3, and the output is the analysis results that identify the extent and pattern of damage. Specifically, it applies an image analysis algorithm to identify the depth and spread of flooding.

[1399] Step 5:

[1400] The server analyzes images acquired from satellites and drones in real time. The input is images acquired from satellites and drones, and the output is the latest status of the affected areas. Specifically, image analysis technology is used to identify traffic conditions on major roads and the extent of damage.

[1401] Step 6:

[1402] The server analyzes data on past rescue operations and evacuation guidance, and proposes optimal countermeasures. The input is past rescue operation and evacuation guidance data, and the output is the results of proposing optimal rescue methods and evacuation guidance measures. Specifically, it performs data analysis based on past successful cases.

[1403] Step 7:

[1404] The user inputs their own health and psychological state into the device through the application. The input is the user's health and psychological state data, and the output is data that is saved on the device and sent to the server. Specifically, the data input from the device is sent to the server.

[1405] Step 8:

[1406] The server analyzes the health and psychological status data using a generative AI model. The input is the data sent in step 7, and the output is the results of determining the appropriate care provision and shelter location. Specifically, the server uses generative AI to analyze the data and propose appropriate countermeasures.

[1407] Step 9:

[1408] The server provides the user with appropriate information and countermeasures based on the analysis results. The input is the analysis results mentioned above, and the output is specific evacuation route and shelter information notified to the user. Specifically, the server calculates evacuation routes in real time and sends the information to the terminal.

[1409] Step 10:

[1410] The terminal provides real-time navigation to evacuation shelters based on the user's location information. The input is the user's location information from GPS etc. and evacuation route information received from the server, and the output is navigation information displayed in a format that is easy for the user to view. Specifically, the terminal integrates GPS data and evacuation route information and displays it on the screen.

[1411] 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.

[1412] As an embodiment of this invention, the operation of the system is explained step by step below. This system incorporates weather data, earthquake data, real-time video and photos, satellite and drone images, rescue operation and evacuation guidance data, the health and psychological state of disaster victims, and an emotion engine that recognizes the user's emotions. This allows the system to provide the user with optimal information and countermeasures.

[1413] Data collection and analysis

[1414] First, the server collects historical weather and earthquake data from various data sources (weather observation satellites and government agencies). The collected data is converted into an easy-to-analyze format, and data cleaning is performed to fill in missing data and remove noise. A generative AI model analyzes this historical data and predicts future disaster risk. After the analysis is complete, a predictive model is generated.

[1415] Real-time data collection and analysis

[1416] The device then transfers real-time video and photos from devices such as drones and fixed cameras to a server. The server uses this real-time data to identify the extent and pattern of damage. For example, the server analyzes the depth and spread of flooding and generates optimal evacuation routes.

[1417] The server also analyzes images acquired from satellites and drones in real time to obtain the latest information on the situation in the affected areas, including the traffic status of major roads and the extent of damage in the affected areas.

[1418] Rescue operations and evacuation guidance suggestions

[1419] The server analyzes a database of past rescue operations and evacuation guidance, proposing optimal rescue methods and evacuation guidance measures. This analysis is based on past successful cases, enabling a swift and effective response tailored to the current situation in the disaster area.

[1420] Analysis of the health and psychological status of disaster victims

[1421] Users enter their own health and psychological state into the device through the application. The device then sends this data to a server, which then analyzes it using generative AI. Based on this analysis, appropriate care for disaster victims and the location of evacuation shelters are determined.

[1422] Emotion recognition by emotion engine

[1423] When the user inputs their health status, the device captures their voice and facial expressions and analyzes them using an emotion engine. The emotion engine analyzes their voice and facial expressions to recognize the user's emotions. For example, it can determine whether the user is feeling stressed or calm.

[1424] Providing information and advice

[1425] Based on all of the above analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. The device displays this information in an easy-to-understand manner, supporting rapid evacuation and appropriate action. Additionally, depending on changes in the user's health or psychological state, the device prioritizes users who require appropriate medical assistance and guides them to evacuation shelters.

[1426] Furthermore, based on the emotion recognition results of the emotion engine, stress management and psychological support information is provided to users, allowing them to receive psychological support even in times of disaster.

[1427] Specific examples

[1428] For example, if a certain area is predicted to be flooded due to heavy rain, the server will analyze past weather data to generate a highly accurate flood forecast. At the same time, it will analyze drone images received in real time to identify areas that are already flooded. Based on the analysis results, the server will provide residents of the area with specific evacuation routes and shelter information in the event that evacuation is necessary.

[1429] Residents enter their physical and psychological state into the application, and the emotion engine measures their stress levels. The server then analyzes the information and provides medical assistance as needed. As a result, residents can evacuate with peace of mind and be quickly guided to a safe location.

[1430] As described above, this system is an advanced information system that makes integrated use of a wide variety of data and an emotion engine to quickly predict disasters and provide appropriate countermeasures, thereby ensuring the safety and psychological support of users.

[1431] The processing flow will be explained below.

[1432] Step 1:

[1433] The server collects historical weather and earthquake data from various sources, including weather satellites and government databases, and periodically retrieves the latest data using communication protocols (e.g., HTTP, API).

[1434] Step 2:

[1435] The server converts the collected weather and earthquake data into a format that is easy to analyze. Specifically, it standardizes the data (e.g., standardizing temperature, precipitation, wind speed, etc.), fills in missing data, and removes noise.

[1436] Step 3:

[1437] The server uses a generative AI model to analyze weather and earthquake data and predict future disaster risks. The AI ​​model performs pattern recognition based on past data and updates the prediction model.

[1438] Step 4:

[1439] The device collects data on the user's health and psychological state, and the user inputs their physical condition, stress level, etc. using a dedicated application.

[1440] Step 5:

[1441] The device captures the user's voice and facial expressions and sends them to the emotion engine, which then understands the user's emotions.

[1442] Step 6:

[1443] The emotion engine uses voice and facial expression analysis to recognize the user's emotions, for example, determining whether the user is feeling stressed or relieved.

[1444] Step 7:

[1445] The device transmits the collected health, psychological, and emotional data to a server, where the data is securely transferred using end-to-end encryption technology.

[1446] Step 8:

[1447] The server analyzes the received data using a generative AI model to assess the user's health and psychological state, and makes decisions about providing care and locating evacuation shelters based on this.

[1448] Step 9:

[1449] The device transmits real-time video and photos from drones and fixed cameras to a server, where the video is uploaded via the Internet.

[1450] Step 10:

[1451] The server analyzes the video and photos sent in real time, and uses generative AI to identify the extent and pattern of damage. For example, it analyzes the depth and spread of flooding to grasp the extent of damage in the relevant area.

[1452] Step 11:

[1453] The server analyzes real-time images acquired from satellites and drones, providing an up-to-date understanding of the situation in the affected areas, including the passability of major roads and the extent of damage in the affected areas.

[1454] Step 12:

[1455] The server analyzes a database of past rescue operations and evacuation guidance, and proposes optimal rescue methods and evacuation guidance measures. Based on past success stories, a plan tailored to the local situation is generated.

[1456] Step 13:

[1457] Based on all of the above analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. This information is then sent to the user's device and displayed in an easy-to-understand format.

[1458] Step 14:

[1459] The device displays the information sent from the server, including maps of safe evacuation routes, detailed information on evacuation shelters, and emergency measures. Users can evacuate safely based on this information.

[1460] Step 15:

[1461] Based on the recognition results of the emotion engine, the server provides users with information on stress management and psychological support, which helps users to evacuate safely while receiving psychological support.

[1462] Step 16:

[1463] The server records all data and feedback and uses it to improve the accuracy of the generative AI model. The model is retrained based on analysis results and user behavior data, continuously improving the accuracy of disaster prediction and response.

[1464] Example 2

[1465] 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."

[1466] In order to carry out appropriate evacuation and rescue operations quickly and effectively during disasters, it is necessary to collect and analyze a wide variety of data in real time and provide users with appropriate information and countermeasures. However, conventional systems have limitations in the accuracy of data collection and analysis, making it difficult to respond quickly. Furthermore, they do not adequately provide support that takes into account the health, psychological state, and emotions of disaster victims. For these reasons, improving safety and psychological support during disasters is a challenge.

[1467] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting past weather data and earthquake data and analyzing this data, means for analyzing videos and photos transmitted in real time to identify the extent and pattern of damage, means for analyzing images acquired from satellites and drones to grasp the situation in the disaster-stricken area, means for analyzing past rescue operations and evacuation guidance data to propose optimal countermeasures, means for analyzing the health and psychological states of disaster victims and determining care and shelter placement, and means for analyzing the user's voice and facial expressions using an emotion engine to recognize the user's emotional state. This enables rapid analysis of various data and provision of appropriate information taking into account the user's health and emotional state.

[1468] "Weather data" refers to weather observation results and forecast information such as temperature, precipitation, wind speed, wind direction, and humidity.

[1469] "Earthquake data" refers to observation results related to earthquakes, including data such as the earthquake's seismic intensity, epicenter, and date and time of occurrence.

[1470] "Analysis means" refers to devices or software that perform calculations and statistical processing on collected data to extract and interpret specific information.

[1471] "Real-time data" refers to data that can be immediately acquired and analyzed based on the current situation.

[1472] "Footage and photographs" refers to visual data captured by photographic equipment such as cameras and drones.

[1473] "Affected area" refers to the geographic area affected by a disaster.

[1474] "Damage pattern" refers to the type and distribution of specific impacts and damage caused by a disaster.

[1475] "Satellite imagery" refers to image data of the Earth captured by sensors mounted on artificial satellites.

[1476] "Drone imagery" refers to image data captured by an unmanned aerial vehicle.

[1477] "Situational awareness" refers to the act of understanding the current situation or state based on collected data.

[1478] "Rescue activities" refers to activities such as saving lives, distributing supplies, and providing medical support during disasters.

[1479] "Evacuation guidance" refers to the act of instructing and guiding people to a safe place during a disaster.

[1480] "Health status" refers to information about physical health, such as the state of each bodily function and tissue, and the presence or absence of disease.

[1481] "Psychological state" refers to information about mental states such as stress, anxiety, and mental well-being.

[1482] An "emotion engine" refers to an algorithm or system that analyzes and identifies emotions from a user's voice, facial expressions, etc.

[1483] A "generative AI model" refers to an artificial intelligence model that learns from large amounts of data and makes highly accurate predictions and analyses of new data.

[1484] "Appropriate information and measures" refers to information and measures that will enable users to evacuate safely and obtain the necessary support in the event of a disaster.

[1485] The present invention is a system that collects and analyzes a variety of data and provides prompt and appropriate information and countermeasures in the event of a disaster. A specific example of this system will be described below.

[1486] Data collection and analysis

[1487] The server collects historical weather and earthquake data from weather observation satellites and government agencies. This data is converted into an easy-to-analyze format and cleaned to fill in missing data and remove noise. A suitable tool for this is the Python pandas library.

[1488] Analysis using generative AI models

[1489] The server analyzes the collected and cleaned data using a generative AI model, specifically using deep learning frameworks such as TensorFlow and PyTorch to build a disaster risk prediction model.

[1490] Real-time data collection

[1491] The device transfers real-time video and photos from drones and fixed cameras to a server, and can transmit data over Wi-Fi or 5G networks.

[1492] Real-time data analysis

[1493] The server uses the received real-time data to identify the extent and pattern of damage. For example, it can use OpenCV to perform image analysis to identify the depth and spread of flooding. It can also use object detection algorithms to check the traffic status of major roads.

[1494] Rescue operations and evacuation guidance suggestions

[1495] The server analyzes past rescue operations and evacuation guidance data and proposes optimal rescue methods and evacuation guidance measures. This is achieved by searching for and analyzing the necessary information from the database using SQL queries.

[1496] Analysis of the health and psychological status of disaster victims

[1497] Users input their own health and psychological status through the application. The device then sends this data to a server, which then uses generative AI to analyze the data. For example, NLP (natural language processing) technology can be used to analyze the user's input text and determine the priority of medical assistance.

[1498] Emotion recognition by emotion engine

[1499] When a user enters their health status, the device captures the user's voice and facial expressions and analyzes them using an emotion engine. The emotion engine uses deep learning models to analyze the voice and facial expressions and recognize the user's emotions. For example, a model built using the Keras library can be used to determine whether the user is feeling stressed.

[1500] Providing information and advice

[1501] The server provides users with real-time disaster information, evacuation routes, and countermeasures based on all of the above analysis results. The device uses HTML5 and JavaScript to display this information in an easy-to-understand manner. For example, evacuation routes can be displayed on a map using the Google Maps API.

[1502] Specific examples

[1503] For example, if heavy rain is predicted to cause flooding in a certain area, the server will use past weather data to generate highly accurate flood predictions. At the same time, it will analyze drone images received in real time to identify areas that are already flooded. Based on this information, the server will provide specific evacuation routes and shelter information to residents in the area.

[1504] Prompt Sentence Examples

[1505] "Please suggest evacuation measures for areas predicted to be flooded by heavy rain. Based on the analysis results of historical weather data and drone imagery, please tell us how to provide specific evacuation routes and necessary medical assistance."

[1506] As described above, this system is an advanced information system that makes integrated use of a wide variety of data and an emotion engine to quickly predict disasters and provide appropriate countermeasures, thereby ensuring the safety and psychological support of users.

[1507] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1508] Step 1:

[1509] The server collects past weather and earthquake data from weather observation satellites and government agencies. Specifically, it acquires the data using the API of the Japan Meteorological Agency and the API of satellite data providers and stores it in a database. The input is a dataset from each API, and the output is a dataset for preparation for analysis.

[1510] Step 2:

[1511] The server converts the acquired data into a format suitable for analysis. It uses the Python pandas library to convert the data into CSV format, imputes missing data, and removes noise. The input is the collected raw data, and the output is the cleaned and formatted data.

[1512] Step 3:

[1513] The server feeds the cleaned data into a generative AI model to build a model that predicts future disaster risk. It uses TensorFlow and PyTorch to train the deep learning model and output the prediction results. The input is the cleaned dataset, and the output is a disaster risk prediction model and the prediction results.

[1514] Step 4:

[1515] The terminal transfers real-time video and photos sent from drones and fixed cameras to a server. The device transmits data using Wi-Fi or 5G. The input is real-time video and photos from the device, and the output is data transferred to the server.

[1516] Step 5:

[1517] The server analyzes the received real-time data to identify the extent and pattern of damage. It uses OpenCV to perform image analysis to determine the depth and extent of flooding and the traffic situation on major roads. The input is real-time video and photos, and the output is the results of identifying the extent and pattern of damage.

[1518] Step 6:

[1519] The server analyzes past rescue operation and evacuation guidance data and proposes optimal rescue methods and evacuation guidance measures. It searches the database using SQL queries and creates rescue plans based on the analysis results. The input is past rescue operation data, and the output is the proposed rescue method and evacuation guidance measures.

[1520] Step 7:

[1521] Users input their own health and psychological state through the application. The device sends this to the server, which analyzes it using generative AI. NLP technology is used to analyze the input text and determine the priority of medical assistance. The input is the user's health and psychological state data, and the output is the analysis results and the priority of medical assistance.

[1522] Step 8:

[1523] The device captures the user's voice and facial expressions and analyzes them using an emotion engine. The emotion engine uses a deep learning model to analyze the voice and facial expressions and recognize the user's emotions. The input is the user's voice and facial expression data, and the output is the recognized emotional state.

[1524] Step 9:

[1525] The server provides users with real-time disaster information, evacuation routes, and countermeasures based on all analysis results. The device displays this information in an easy-to-understand manner and prioritizes the provision of necessary medical assistance. Information is visualized using HTML5 and JavaScript, and evacuation routes are displayed using the Google Maps API. The input is various analysis results, and the output is specific disaster information and evacuation routes that are displayed to the user.

[1526] (Application example 2)

[1527] 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."

[1528] When a disaster occurs, it is difficult to grasp the situation in the affected area and provide victims with prompt and appropriate information. At the same time, there is a need to provide food and other necessities quickly, accurately grasp the health and psychological state of victims, and provide psychological care. To solve these problems, a system is needed that can collect and analyze information from multiple data sources in real time and quickly propose countermeasures.

[1529] The identification processing 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 means for collecting past weather data and earthquake data and analyzing this data, means for analyzing videos and photos transmitted in real time to identify the extent and pattern of damage, means for analyzing images acquired from satellites and drones to grasp the situation in the disaster-stricken area, means for analyzing past rescue operations and evacuation guidance data to propose optimal countermeasures, means for analyzing the health and psychological states of disaster victims and determining care and shelter placement, means for providing food to disaster-stricken areas using drones and autonomous mobile devices, means for understanding the psychological states of disaster victims using emotion recognition technology and providing stress management information, and means for providing appropriate information and countermeasures to users based on these means. This enables accurate and rapid understanding of the situation in the disaster-stricken area, rapid provision of supplies including food, and appropriate information and psychological support to disaster victims.

[1530] "Past weather data" refers to data relating to weather observed in the past, including information such as temperature, precipitation, wind speed, wind direction, and humidity.

[1531] "Earthquake data" refers to data that includes information on the epicenter, seismic intensity, and waveforms of shaking at the time of an earthquake, and is the basis for analyzing the scale and extent of an earthquake's impact.

[1532] "Video and photos transmitted in real time" refers to video and still image data obtained by instantly photographing and recording the current situation and then instantly transmitting that data.

[1533] "Damage range and damage pattern" is pattern information that indicates the range of the area affected by the disaster and the type and scale of the damage.

[1534] "Imagery obtained from satellites and drones" refers to image data taken from the air, including images of the earth's surface taken by satellites or unmanned aerial vehicles.

[1535] "Status of the affected areas" refers to data showing the current state of the affected areas at the time of the disaster and afterwards, including the scale, scope and detailed information of the damage.

[1536] "Past rescue operation and evacuation guidance data" refers to data on rescue and evacuation operations that have been carried out in the past, including success stories, failure stories, and information on the processes involved.

[1537] "Optimal response measures" are proposals based on analyzed data that propose optimal guidelines for action, evacuation routes, rescue methods, etc. for affected areas and victims.

[1538] "The health and psychological state of the disaster victims" is data indicating the physical health and psychological state of the disaster victims.

[1539] "Care and sheltering" refers to providing medical and psychological support to disaster victims, as well as the provision and arrangement of appropriate shelter.

[1540] "Drones and autonomous mobile devices" refers to unmanned aerial vehicles and ground mobile devices that use autonomous driving technology, which can be used to transport supplies and food.

[1541] "Emotion recognition technology" is a technology that identifies human emotions through voice analysis and facial expression analysis, and evaluates psychological states such as stress and a sense of security.

[1542] This invention is a system for collecting and analyzing information in the event of a disaster, and providing appropriate countermeasures. The system collects various data, analyzes it, and provides information to users in real time. It also uses drones and autonomous mobile devices to quickly provide food and relief supplies.

[1543] Hardware Configuration

[1544] Server: Processes data and analyzes the generated AI model.

[1545] Cloud server: Data storage and big data analysis are performed using AWS.

[1546] Drones: Collect images of disaster areas and deliver supplies.

[1547] Autonomous mobile devices: Distribute food and relief supplies on the ground.

[1548] Smartphone: Used as a device for users to input their health and psychological status.

[1549] Fixed cameras: Providing real-time footage of the affected areas.

[1550] Software Configuration

[1551] Python: A programming language for data analysis, specifically using Scikit-learn and TensorFlow.

[1552] OpenCV: A library for performing image analysis.

[1553] AWS Lambda: An AWS service for serverless data processing.

[1554] Emotion Engine API: Technology that recognizes emotions through voice and facial expression analysis.

[1555] Data collection and analysis process

[1556] 1. Historical data collection and analysis:

[1557] The server collects historical weather and earthquake data from government agencies and weather observation satellites, which is then analyzed using a generative AI model to predict future disaster risks.

[1558] 2. Real-time data collection:

[1559] Real-time video and photos from drones and fixed cameras are sent to a server, which analyzes the data to identify the extent and pattern of damage.

[1560] 3. Understanding the situation in the affected areas:

[1561] Images acquired from satellites and drones will be analyzed to provide an up-to-date picture of the situation in the affected areas, including road conditions and the extent of damage.

[1562] 4. Suggestions for rescue operations and evacuation:

[1563] The server analyzes past rescue operations and evacuation guidance data and proposes the optimal response measures.

[1564] 5. Health and Psychological Analysis:

[1565] Users input their health and psychological state using their smartphones, which is then analyzed by the server. An emotion engine is used to recognize the user's emotions and provide stress management information.

[1566] 6. Information provision and implementation of measures:

[1567] Based on all the above analysis results, the server provides users with real-time disaster information, evacuation routes, and countermeasures. It also uses drones and autonomous mobile devices to quickly deliver food to disaster-stricken areas.

[1568] Specific examples

[1569] For example, if a flood is predicted in a certain area, the server analyzes past weather data to generate a highly accurate flood forecast. At the same time, it analyzes drone images received in real time to identify flooded areas. As a result, it provides information on optimal evacuation routes and evacuation shelters. It also provides necessary medical assistance and psychological support based on the individual's health and psychological state.

[1570] Prompt Sentence Examples

[1571] Below are some example prompts to input to the generative AI model:

[1572] Based on the information below, please suggest appropriate evacuation routes and food distribution methods for the affected areas.

[1573] Weather data: {Weather data details}

[1574] Satellite image: {satellite image URL}

[1575] Real-time imagery from drone: {drone image URL}

[1576] Victim's health status: {health status data}

[1577] Victim's psychological state: {Psychological state data}

[1578] Emotion analysis result: {Emotion analysis result}

[1579] This system is capable of quickly analyzing huge amounts of data and providing appropriate information and assistance in real time.

[1580] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1581] Step 1:

[1582] The server collects historical weather and earthquake data.

[1583] Input: Data from weather satellites and government agencies

[1584] How it works: The server queries these data sources through APIs to retrieve weather and earthquake data.

[1585] Output: Data obtained in the form of historical weather and earthquake data

[1586] Step 2:

[1587] The server analyzes the collected historical data and uses a generative AI model to predict the risk of future disasters.

[1588] Input: Weather and earthquake data collected in Step 1

[1589] How it works: Cleans data and converts it into an analyzable format. Enters prompts into a generative AI model to perform predictive calculations.

[1590] Output: Prediction data of future disaster risk

[1591] Step 3:

[1592] Video and photos are transmitted in real time to identify the extent and pattern of damage.

[1593] Input: Real-time video and photos from drones and fixed cameras

[1594] Operation: The server receives the video data and analyzes it using OpenCV. It identifies the extent and pattern of damage and analyzes the image data.

[1595] Output: Specific information on the extent and pattern of damage

[1596] Step 4:

[1597] Images obtained from satellites and drones are analyzed to understand the situation in the affected areas.

[1598] Input: Satellite and drone imagery

[1599] Operation: The server receives images acquired from satellites and drones and analyzes them using OpenCV to grasp the current situation in the affected areas, determine road traffic conditions, and the extent of damage.

[1600] Output: Situation data of the affected area

[1601] Step 5:

[1602] We analyze past rescue operations and evacuation guidance data to propose optimal response measures.

[1603] Input: Past rescue operations and evacuation guidance data stored in the database

[1604] How it works: The server analyzes historical data and uses generative AI models to generate optimal rescue operations and evacuation guidance prompts.

[1605] Output: Proposal data for optimal countermeasures

[1606] Step 6:

[1607] Analyze the health and psychological state of disaster victims to determine care and evacuation placement.

[1608] Input: Health and psychological data entered by the user into the device, and analysis results by the emotion engine

[1609] How it works: The server uses generative AI models to analyze data and determine appropriate care and shelter placement. It also uses an emotion engine to provide stress management information.

[1610] Output: Care and shelter placement proposal data

[1611] Step 7:

[1612] Delivering food to disaster-stricken areas using drones and autonomous mobile devices.

[1613] Input: Situation data of the affected area, location information of the victims

[1614] How it works: The server analyzes the optimal route and sends instructions to drones and autonomous mobile devices, which then deliver food to disaster-stricken areas.

[1615] Output: Data on completed delivery of supplies and food

[1616] Step 8:

[1617] Provide users with appropriate information and measures.

[1618] Input: Analysis results from the above steps and proposed data

[1619] How it works: The server compiles this data and sends it to the user's device. The user receives the appropriate information on their smartphone and can take action.

[1620] Output: Appropriate information and measures to be sent to the user's device

[1621] In this way, data collection, analysis, and execution are performed in coordination at each step, enabling rapid response and support for disaster victims.

[1622] 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.

[1623] 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 d...

Claims

1. means for collecting and analyzing historical meteorological and earthquake data; A means for analyzing the video and photos transmitted in real time and identifying the extent and pattern of damage; A means of analyzing images obtained from satellites and drones to grasp the situation in the affected areas, A means of analyzing past rescue operations and evacuation guidance data to propose optimal countermeasures; A means for analyzing the health and psychological state of disaster victims and determining care and shelter placement; Based on these measures, means to provide users with appropriate information and measures; A system including:

2. The system of claim 1, wherein said analyzing means uses generative AI.

3. The system according to claim 1, wherein the information and measures are notified to a terminal.

Images