System

Abstract

A system is provided.SOLUTION: This system includes a means for collecting data in real time, a means for analyzing the collected data and predicting a disaster, a means for analyzing a state of damage, a means for proposing an optimum countermeasure plan for relief and restoration, a means for providing necessary information, and a means for proposing an optimum moving route.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] Conventional disaster response systems have difficulty collecting and analyzing data in real time, making it difficult to respond quickly and effectively. It is also extremely difficult to accurately grasp the extent of damage and plan optimal rescue and recovery measures. A system that can solve these issues and ensure a rapid and accurate response in the event of a disaster is needed. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for collecting data in real time, a means for analyzing the collected data to make disaster predictions, a means for analyzing the damage situation, a means for proposing optimal response plans for rescue and recovery, a means for providing necessary information, and a means for proposing optimal travel routes. Specifically, the system collects satellite and drone data to make disaster predictions and grasp detailed damage situations. It also includes a means for collecting traffic and damage information and calculating optimal travel routes based on the collected data. This enables a system that enables victims, rescue teams, government agencies, and local governments to act quickly and effectively.

[0006] "Real-time" means processing the latest information at the moment and providing results instantly.

[0007] "Data collection means" refers to devices and systems that acquire information from sensors, drones, satellites, external APIs, etc.

[0008] "Data analysis means" refers to algorithms and computer programs that model collected information and make predictions and judgments.

[0009] "Disaster prediction" refers to predicting the timing and extent of impact of natural disasters such as earthquakes, floods, and typhoons.

[0010] "Damage analysis" involves assessing the damage and impact caused by a disaster and accurately understanding the situation in the affected areas.

[0011] The "response plan proposal means" is a system and device for proposing optimal rescue and recovery measures based on the damage situation.

[0012] "Information provision means" refers to notification systems, dashboards, alert functions, etc. that provide necessary information to users and related organizations.

[0013] The "travel route suggestion method" is an algorithm and system that takes into account traffic conditions and damage information to calculate and present the optimal travel route.

[0014] "Satellite data" means images and information of the Earth's surface and atmosphere obtained from artificial satellites.

[0015] "Drone data" refers to images and sensor information collected from unmanned aerial vehicles (drones).

[0016] "Traffic information" refers to data that affects travel, such as road closures, congestion, and traffic volume.

[0017] "Damage information" refers to data such as damage to buildings and damage to infrastructure caused by disasters. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] This invention relates to a system for implementing rapid and effective countermeasures in the event of a disaster, including the collection and analysis of real-time data, damage prediction, response plan proposal, information provision, and optimal travel route proposal. Specific embodiments for implementing the invention are described below.

[0040] System configuration

[0041] 1. Data Collection Module

[0042] The server collects data in real time from sensors, drones, satellites, external APIs, etc. For example, it uses data from seismometers and weather sensors, image data from drones and satellites, and API data from the Japan Meteorological Agency and traffic information services.

[0043] 2. Data storage module

[0044] The server stores the collected data in a database, which can handle both structured and unstructured data.

[0045] 3. Data Analysis Module

[0046] The server then performs analysis on the stored data, using AI algorithms to run disaster prediction and damage situation models, which can predict, for example, the epicenter and intensity of an earthquake, as well as areas susceptible to flooding.

[0047] 4. Aid Response Proposal Module

[0048] The server will create optimal aid and recovery plans based on the damage situation, for example, calculating the type, quantity and priority of supplies needed and creating a personnel deployment plan.

[0049] 5. Information System

[0050] The server sends the latest information to the dashboard API, which the device receives and visually displays, providing users with easy-to-understand, real-time updated data and recommendations.

[0051] 6. Optimal Route Proposal Module

[0052] The server calculates optimal routes based on the latest traffic information, taking into account the extent of damage and traffic conditions, and optimizes routes for delivering relief supplies and moving personnel.

[0053] Program processing explanation

[0054] Disaster prediction and damage analysis

[0055] The server stores data collected from sensors, drones, and satellites in a database. It then analyzes the stored data using AI algorithms and runs disaster prediction models. These models identify predicted earthquake centers and areas prone to flooding. The analysis results are stored in the database as they are processed and sent to devices via the dashboard API.

[0056] Aid response proposal

[0057] The server calculates the necessary relief supplies and personnel based on the damage information and generates an optimal relief plan. For example, it calculates the required amounts of food, water, medicine, etc. and plans the deployment of rescue teams. The generated relief plan is sent to the device via the dashboard API, where the user can confirm it.

[0058] Providing information

[0059] The server continuously updates the collected and analyzed data in real time and notifies the user of important information. For example, it sends push notifications in response to the expansion of the affected area or changes in traffic conditions. The device receives these notifications and displays them to the user, prompting them to take action as necessary.

[0060] Optimal route suggestions

[0061] The server calculates the optimal travel route based on traffic and damage information. The calculation uses Dijkstra's algorithm and A algorithm to calculate the shortest distance and fastest route. The calculation results are sent to the device, allowing the user to check the optimal route.

[0062] Specific examples

[0063] Example 1: Processing when an earthquake occurs

[0064] 1. The server receives earthquake data from the seismometer and stores it in a database.

[0065] 2. The server analyzes the stored data and runs models to predict the epicenter and intensity of the earthquake.

[0066] 3. The server sends the analysis results to the device via the dashboard API, and the device visually displays the prediction results.

[0067] 4. Users can check the damage situation and forecast information via their devices and take appropriate evacuation actions.

[0068] Example 2: Flood forecasting and response planning

[0069] 1. The server receives rainfall data from weather sensors and stores it in a database.

[0070] 2. The server analyzes the stored data and runs flood forecasting models, which identify areas that are likely to flood.

[0071] 3. The server calculates the necessary relief supplies based on the damage situation and generates the optimal relief plan.

[0072] 4. The terminal displays the support plan to the user, enabling them to quickly allocate the necessary resources.

[0073] In this way, this system enables rapid and effective response in the event of a disaster through the collection and analysis of real-time data.

[0074] The processing flow will be explained below.

[0075] Disaster prediction and damage analysis

[0076] Step 1:

[0077] The server receives information from sensors (seismometers, weather sensors), drones, satellite data, and external APIs.

[0078] Step 2:

[0079] The server stores the received data in a temporary memory, then normalizes the data and stores it in a database.

[0080] Step 3:

[0081] The server applies pre-trained AI models to the stored data to perform disaster predictions, such as predicting the epicenter and intensity of an earthquake, or the risk of flooding based on rainfall.

[0082] Step 4:

[0083] The server analyzes the prediction results to determine the extent of damage, and uses image analysis technology to process data from drones and satellites to assess the extent of damage to buildings.

[0084] Step 5:

[0085] The server stores the analysis results back in a database and notifies you of relevant information via email alerts and dashboard APIs.

[0086] Step 6:

[0087] The device receives data from the server and visually displays it on a dashboard, providing users with an easy-to-read view. Damage forecasts and response plans are highlighted on a map.

[0088] Processing of assistance response proposals

[0089] Step 1:

[0090] Based on the damage prediction results, the server evaluates the extent and distribution of the damage and calculates the necessary relief resources.

[0091] Step 2:

[0092] The server lists the required supplies (food, water, medicine, etc.) and personnel (emergency medical team, construction team) by type and calculates their quantities.

[0093] Step 3:

[0094] The server sets priorities for supplies and personnel and draws up plans for how much resource to allocate to each area.

[0095] Step 4:

[0096] The server generates a document with the optimal support and recovery plan and sends it to the device via the dashboard API.

[0097] Step 5:

[0098] The terminal receives the proposed assistance plan and visually displays it on the user interface, which the user can review and decide on specific actions to take.

[0099] Processing of information provided

[0100] Step 1:

[0101] The server collects new data in real time and continuously updates the database with the collected data.

[0102] Step 2:

[0103] When the server detects important updates (new disaster predictions, changes in the damage situation), it generates a push notification based on that information.

[0104] Step 3:

[0105] The device receives a push notification from the server and immediately alerts the user, providing a link to additional information if necessary.

[0106] Step 4:

[0107] Users can check the notifications and take necessary actions, such as checking evacuation locations or preparing to distribute relief supplies.

[0108] Processing optimal route suggestions

[0109] Step 1:

[0110] The server collects traffic and damage information in real time and stores it in a database.

[0111] Step 2:

[0112] The server runs an algorithm (such as Dijkstra's algorithm or A algorithm) to calculate the optimal travel route based on the latest data.

[0113] Step 3:

[0114] The server sends the calculated optimal route to the device via the dashboard API.

[0115] Step 4:

[0116] The terminal displays the optimal route information received from the server on a map, helping the user travel efficiently.

[0117] Step 5:

[0118] The user checks the presented route and gives instructions for the transportation of relief supplies and the movement of the rescue team.

[0119] Example 1

[0120] 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."

[0121] In modern society, rapid and accurate countermeasures are required when natural disasters occur. However, conventional systems have problems with insufficient real-time data collection and the time it takes to analyze the data, making it difficult to take prompt action. Furthermore, it is difficult to simultaneously solve multiple issues, such as assessing the damage situation, optimally distributing relief supplies, and proposing evacuation routes. This increases the risk of putting many lives and property at risk.

[0122] 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.

[0123] In this invention, the server includes means for collecting data in real time using sensors, unmanned aerial vehicles, satellites, and external APIs, means for storing the collected data in structured and unstructured databases, means for analyzing the stored data using an AI algorithm and running a disaster prediction model and a damage situation model, means for calculating relief supplies and personnel based on damage information and generating an optimal support plan, means for notifying users of important data and displaying the latest information through a dashboard API, and means for calculating optimal travel routes based on traffic and damage information and providing them to users, thereby enabling rapid and accurate disaster response.

[0124] A "sensor" is a device that measures environmental conditions or physical quantities and converts that information into an electrical signal.

[0125] An "unmanned aerial vehicle" is an aircraft that moves through the air by remote control or autonomous flight, collecting data and making observations.

[0126] A "satellite" is a spacecraft placed in orbit around the Earth that collects data such as meteorological observations and Earth remote sensing.

[0127] An "external API" is a programmatic interface for obtaining information from other systems or services.

[0128] A "database" is a system for efficiently storing, retrieving, and analyzing data. Both structured and unstructured databases exist.

[0129] An "AI algorithm" is a method of analyzing data using machine learning and data mining techniques to make predictions and classifications.

[0130] A "disaster prediction model" is a mathematical model for predicting the occurrence and impact of disasters based on collected data.

[0131] A "damage situation model" is a mathematical model used to analyze the scope and extent of damage when a disaster occurs.

[0132] A "support plan" is a specific proposal for optimally planning the types and quantities of relief supplies, the deployment of personnel, etc.

[0133] "Dashboard API" means a programmatic interface for visually displaying collected and analyzed data.

[0134] The "optimal route" is the most efficient travel route calculated based on traffic and damage information.

[0135] MODE FOR CARRYING OUT THE INVENTION

[0136] This invention is a system for realizing a rapid and effective response in the event of a disaster, and includes the collection and analysis of real-time data, damage prediction, response plan proposal, information provision, and optimal travel route proposal. Specific embodiments for implementing the invention are described below.

[0137] System configuration

[0138] Data collection

[0139] The server collects data in real time using sensors, drones, satellites, and external APIs. Specific examples include earthquake data from seismometers, weather data from weather sensors, image data from drones and satellites, and traffic data from traffic information APIs. All data is time-stamped, making it easier to analyze later.

[0140] Data storage

[0141] The server stores the collected data in structured and unstructured databases. Databases such as MySQL (registered trademark) and MongoDB are used. For example, earthquake data is stored in a table called "seismic_data," and meteorological data is stored in a table called "weather_data."

[0142] Data analysis

[0143] The server uses AI algorithms to analyze the stored data. Specifically, it uses tools such as TENSORFLOW (registered trademark) to run disaster prediction and damage situation models. This allows it to predict the epicenter and areas prone to flooding. The analysis results are stored in a new table called "prediction_results."

[0144] Aid response proposal

[0145] The server generates a relief plan based on the analysis results. Python is used to calculate the type and quantity of relief supplies and the deployment of personnel. The generated relief plan is converted into JSON format and sent to the device via the dashboard API. For example, the calculated relief plan may include information such as "Area A needs 500 sets of food, 100 liters of water, and five relief team members."

[0146] Providing information

[0147] The server notifies users of important information in real time based on the collected data and analysis results. For example, if it detects an expansion of the affected area or a change in traffic conditions, it sends a push notification to the device via the dashboard API. The device receives this and displays it as an alert to the user.

[0148] Optimal route suggestions

[0149] The server calculates the optimal travel route based on traffic and damage information. The algorithms used are Dijkstra's algorithm and A algorithm, which calculate the most efficient travel route. The calculation results are sent in JSON format to the device via the dashboard API, allowing the user to check the optimal route.

[0150] Specific examples

[0151] Example 1: Processing when an earthquake occurs

[0152] 1. The server receives earthquake data from the seismometer and stores it in a database.

[0153] 2. The server analyzes the stored data and runs models to predict the epicenter and intensity of the earthquake.

[0154] 3. The server sends the analysis results to the device via the dashboard API, and the device visually displays the prediction results.

[0155] 4. Users can check the damage situation and forecast information via their devices and take appropriate evacuation actions.

[0156] Example 2: Flood forecasting and response planning

[0157] 1. The server receives rainfall data from weather sensors and stores it in a database.

[0158] 2. The server analyzes the stored data and runs flood forecasting models, which identify areas that are likely to flood.

[0159] 3. The server calculates the necessary relief supplies based on the damage situation and generates the optimal relief plan.

[0160] 4. The terminal displays the support plan to the user, enabling them to quickly allocate the necessary resources.

[0161] Prompt Sentence Examples

[0162] "Please tell me the procedure for processing the damage prediction model in the event of an earthquake."

[0163] "Please give us some concrete examples of flood forecasts and response plans based on current rainfall data."

[0164] In this way, the present invention enables rapid and effective response in the event of a disaster through real-time data collection and analysis, enabling optimal measures to minimize damage and save lives.

[0165] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0166] Step 1: Data collection

[0167] The server collects data in real time using sensors, drones, satellites, and external APIs. For example, it acquires earthquake data from seismometers, weather data from weather sensors, image data from drones and satellites, and traffic data from traffic information APIs. The collected data is stored as a time-stamped log.

[0168] Inputs: Data from seismometers, weather sensors, drones, satellites, and external APIs

[0169] Output: Raw data log with timestamps

[0170] Specific operation:

[0171] Earthquake data is obtained from the seismometer every 10 seconds.

[0172] Traffic information updated every minute via API.

[0173] Step 2: Save data

[0174] The server stores the collected data in structured and unstructured databases, such as MySQL or MongoDB.

[0175] Input: Raw data log with timestamps

[0176] Output: Structured and unstructured data stored in a database

[0177] Specific operation:

[0178] Seismic data is stored using the SQL query "INSERT INTO seismic_data (timestamp, magnitude) VALUES (timestamp, magnitude)".

[0179] Weather data is stored using the SQL query "INSERT INTO weather_data (timestamp, temperature) VALUES (timestamp, temperature)".

[0180] Step 3: Data analysis

[0181] The server analyzes the stored data using AI algorithms, and runs disaster prediction models and damage situation models using TensorFlow and other tools.

[0182] Input: Structured and unstructured data stored in a database

[0183] Output: Analysis results (epicenter, seismic intensity, damage prediction area)

[0184] Specific operation:

[0185] TensorFlow is used to analyze earthquake data and predict the epicenter and intensity.

[0186] The analysis results are saved in a new table called "prediction_results".

[0187] Step 4: Propose an aid response

[0188] The server generates an aid plan based on the analysis results. It uses Python to calculate the type and quantity of needed relief supplies and personnel deployment. The generated aid plan is converted into JSON format and sent to the device via the dashboard API.

[0189] Input: Analysis results (epicenter, seismic intensity, predicted damage area)

[0190] Output: Support plan in JSON format

[0191] Specific operation:

[0192] Run a script to generate a support plan and calculate the required supplies and personnel allocation.

[0193] The generated support plan is saved as a "relief supplies JSON file."

[0194] Step 5: Provide information

[0195] The server notifies users of important information in real time based on the collected data and analysis results. Push notifications are sent to the device via the dashboard API, which receives them and displays them as alerts to the user.

[0196] Input: Important analytical results and newly collected data

[0197] Output: Push notification to the user

[0198] Specific operation:

[0199] If an expansion of the affected area or changes in traffic information are detected, a push notification will be generated.

[0200] Send notifications to devices via the Dashboard API.

[0201] Step 6: Optimal route proposal

[0202] The server calculates the optimal travel route based on traffic and damage information. The Dijkstra algorithm and A algorithm are used to calculate the most efficient travel route. The calculation results are sent in JSON format to the device via the dashboard API, allowing the user to check the optimal route.

[0203] Input: Traffic information, damage information

[0204] Output: Optimal route in JSON format

[0205] Specific operation:

[0206] Calculates the optimal route from the current location to the destination using Dijkstra's algorithm.

[0207] The calculation results are saved as an "optimal route JSON file" and sent to the device via the dashboard API.

[0208] (Application example 1)

[0209] 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."

[0210] Existing disaster prevention systems lack real-time data collection and analysis, making it difficult to develop rapid and effective response plans. They also lack the necessary information and optimal travel route suggestions required during a disaster, leaving users highly confused. Furthermore, notification functions on mobile devices such as smartphones are inadequate, making it difficult to provide important information immediately in an emergency.

[0211] 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.

[0212] In this invention, the server includes means for collecting data in real time, means for analyzing the collected data and making disaster predictions, means for analyzing the damage situation, means for proposing an optimal response plan for rescue and recovery, means for providing necessary information, means for proposing an optimal travel route, means for notifying the user using an application installed on the smartphone, and means for proposing assistance using data stored in the database. This enables a quick and effective response in the event of a disaster, and makes it possible to provide users with important information and optimal evacuation routes in real time.

[0213] "Real-time data collection means" refers to the system's ability to continuously acquire new data through sensors, drones, satellites, and external APIs.

[0214] "Means of analyzing collected data and making disaster predictions" refers to the system's function of using AI algorithms to predict the likelihood of disasters occurring and the extent of damage based on the acquired data.

[0215] "Means for analyzing the damage situation" refers to the system's function of using collected and analyzed data to assess the extent and severity of damage caused by a disaster.

[0216] "Means for proposing optimal response plans for rescue and recovery" refers to the system's function of planning the deployment of necessary supplies and personnel based on analyzed damage information, and determining the optimal means of assistance and recovery.

[0217] "Means of providing necessary information" refers to the system's functions for notifying users of important information in real time and encouraging appropriate action.

[0218] "Means for suggesting optimal travel routes" refers to the system's function of calculating the safest and quickest evacuation route based on traffic and damage information and presenting it to the user.

[0219] "Means of notifying users using an application installed on a smartphone" refers to a system function that notifies users of disaster information and evacuation routes in real time via an application.

[0220] "Means for proposing assistance responses using data stored in the database" refers to a system function that analyzes stored past and current data and proposes optimal assistance responses.

[0221] This invention is a system for providing rapid and effective countermeasures in the event of a disaster, and is implemented in the following steps.

[0222] Data collection

[0223] The server collects data in real time from sensors (such as seismometers and weather sensors), drones, satellites, and external APIs (such as the Japan Meteorological Agency and traffic information services). This allows for a constant accumulation of up-to-date information on earthquakes and weather. Specific hardware used includes seismometers, weather sensors, drones, and satellites. Software uses libraries (such as Requests) to access external APIs.

[0224] Data storage

[0225] The collected data is stored in a database by the server. Databases can handle both structured and unstructured data. Examples of databases used include SQLite and MySQL.

[0226] Data analysis

[0227] The server uses AI algorithms based on the stored data to perform disaster predictions. This analysis identifies, for example, the epicenter and intensity of an earthquake, as well as areas expected to be flooded. The AI ​​algorithms utilize machine learning libraries such as Scikit-learn and TensorFlow.

[0228] Damage analysis

[0229] The server evaluates the damage situation based on the analyzed data, allowing the extent of the disaster's impact and severity to be determined. The analysis results are stored in a database and updated as needed.

[0230] Aid response proposal

[0231] The server calculates the necessary relief supplies and personnel allocation based on damage information, and generates an optimal aid and recovery plan, which calculates the necessary amounts of food, water, medicine, etc., enabling the rapid deployment of rescue teams.

[0232] Providing information

[0233] The server notifies users of important information based on data collected and analyzed in real time. Information such as damage forecasts, assistance response plans, and optimal evacuation routes is provided via push notifications using an application installed on a smartphone. Notification services such as Firebase Cloud Messaging are used.

[0234] Optimal route suggestions

[0235] The server calculates the optimal travel route based on traffic and damage information. The calculation uses Dijkstra's algorithm and A algorithm to calculate the shortest distance and fastest route. The calculation results are sent to devices such as smartphones, allowing users to evacuate safely.

[0236] Specific examples

[0237] For example, when an earthquake occurs, the server receives earthquake data from a seismometer and predicts the epicenter and seismic intensity. Based on this information, the damage situation is analyzed and appropriate relief supplies and personnel deployment plans are made. Ultimately, the epicenter, seismic intensity, and evacuation routes are notified to the user's smartphone. As another example, in flood prediction, rainfall data is collected and areas with a high probability of flooding are identified. This makes it possible to quickly deliver necessary relief supplies to areas where disasters are predicted.

[0238] Prompt Sentence Examples

[0239] "Based on the latest earthquake and meteorological data, please estimate the epicenter and damage, and suggest evacuation routes."

[0240] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0241] Step 1: Data collection

[0242] The server collects real-time data from seismometers, weather sensors, drones, satellites, and external APIs. Input data includes earthquake data, meteorological data, and image data. The server obtains the latest data from each data source and passes it on to the next processing step. This allows the latest disaster information to be collected at all times.

[0243] Step 2: Save data

[0244] The server stores the collected data in a database. The input data is earthquake and weather data collected in real time, and is stored in the database as structured or unstructured data. This data is efficiently managed using a database management system such as SQLite or MySQL.

[0245] Step 3: Data analysis

[0246] The server uses AI algorithms based on the stored data to make disaster predictions. The input data is stored earthquake and weather data. The AI ​​algorithm analyzes the earthquake's epicenter, seismic intensity, predicted flood areas, etc., and outputs the results. Machine learning libraries such as Scikit-learn and TensorFlow are used here.

[0247] Step 4: Damage analysis

[0248] The server assesses the damage situation based on the analyzed data. The input data is the analysis results. The impact scope and severity of the disaster are assessed, and the damage situation is understood in detail. This information is used to plan the next aid response.

[0249] Step 5: Propose an aid response

[0250] The server creates optimal rescue and recovery plans based on the damage situation. The input data is a detailed description of the damage situation, and it calculates the necessary supplies and personnel to generate an optimal support plan. This determines the required amounts of supplies such as food, water, and medicine, as well as the deployment of rescue teams.

[0251] Step 6: Provide information

[0252] The server provides users with important information in real time. The input data is assistance response plans and damage situation information, and the information is sent to users via an application installed on their smartphone. Push notification services such as Firebase Cloud Messaging are used to prompt users to take appropriate action.

[0253] Step 7: Optimal route proposal

[0254] The server calculates the optimal travel route based on traffic and damage information. The input data is real-time traffic and damage information, and the shortest distance and fastest route are calculated using Dijkstra's algorithm and A algorithm. The results are sent to the user's smartphone, helping them evacuate safely.

[0255] Step 8: User's appropriate evacuation behavior

[0256] The user takes appropriate evacuation action based on the information received on their smartphone. The input data is a notification sent from the server, and the user confirms it and follows the indicated evacuation route. This allows the user to evacuate quickly and safely.

[0257] 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.

[0258] This invention relates to a system that reduces the psychological burden on users during disasters and realizes more effective countermeasures by combining real-time data collection, analysis, damage prediction, response plan proposals, information provision, and optimal travel route proposals with an emotion engine that recognizes the user's emotions. Specific embodiments for implementing this invention are described below.

[0259] System configuration

[0260] 1. Data Collection Module

[0261] The server collects data in real time from sensors, drones, satellites, and external APIs. Specifically, it uses data from seismometers and weather sensors, image data from drones and satellites, and API data from the Japan Meteorological Agency and traffic information services.

[0262] 2. Data storage module

[0263] The server stores the collected data in a database, which can handle both structured and unstructured data.

[0264] 3. Data Analysis Module

[0265] The server applies AI models to the stored data to predict disasters and analyze damage situations, for example, predicting the epicenter and seismic intensity of an earthquake and areas susceptible to flooding.

[0266] 4. Aid Response Proposal Module

[0267] Based on the damage situation, the server calculates the type, quantity, and priority of supplies needed and draws up a personnel deployment plan.

[0268] 5. Information System

[0269] The server sends the latest information to the dashboard API, which the device receives and visually displays, providing users with easy-to-understand, real-time updated data and recommendations.

[0270] 6. Optimal Route Proposal Module

[0271] The server calculates optimal routes based on the latest traffic information, taking into account the extent of damage and traffic conditions, and optimizes routes for delivering relief supplies and moving personnel.

[0272] 7. Emotion Engine

[0273] The server uses an emotion engine to recognize the user's emotions in real time. Emotion data is collected and analyzed from cameras and microphones.

[0274] Program processing explanation

[0275] User Emotion Recognition

[0276] The server collects image and audio data from the camera and microphone connected to the device.

[0277] The server uses an emotion engine to analyze the collected data and recognize emotions (fear, stress, relief, etc.) from the user's facial expressions and voice tone.

[0278] The server stores the recognized emotion data in a database and triggers actions as needed.

[0279] Customized information provision

[0280] The server analyzes the user's stress and anxiety levels based on the emotional data. For example, if the user is in a high-stress state, it provides reassuring notifications and evacuation information.

[0281] The server sends the analysis results to the dashboard API, which the device receives and displays in real time, along with reassuring messages and alerts.

[0282] Reflecting priorities

[0283] The server then uses the emotional data to prioritize rescue and recovery plans, for example by quickly dispatching relief supplies and rescue teams to areas with a high number of users experiencing high levels of stress.

[0284] The server reconstructs the support plan based on the priority and allocates resources optimally.

[0285] Specific examples

[0286] Example 1: Processing when an earthquake occurs

[0287] 1. The server receives earthquake data from the seismometer and stores it in a database.

[0288] 2. The server analyzes the stored data and predicts the epicenter and intensity of the earthquake.

[0289] 3. The server collects the user's emotional data from the device's camera and microphone and analyzes it using an emotion engine.

[0290] 4. The server identifies areas with a high number of users experiencing high stress and develops a plan to quickly send relief supplies to those areas.

[0291] Example 2: Flood forecasting and response planning

[0292] 1. The server receives rainfall data from weather sensors and stores it in a database.

[0293] 2. The server analyzes the rainfall data and runs flood forecasting models, which identify areas that are likely to flood.

[0294] 3. The server calculates the necessary relief supplies based on the damage situation and generates the optimal relief plan.

[0295] 4. The server analyzes the user's emotional state and provides priority support to areas with a high number of users in high stress states.

[0296] 5. The terminal displays the support plan to the user, enabling them to quickly allocate the necessary resources.

[0297] In this way, by combining emotion engines, it is possible to reduce the psychological burden on users and enable more effective responses in the event of a disaster.

[0298] The processing flow will be explained below.

[0299] User emotion recognition processing

[0300] Step 1:

[0301] The terminal activates the camera and microphone on the device operated by the user.

[0302] Step 2:

[0303] The device captures a picture of the user's face with a camera and collects audio data with a microphone.

[0304] Step 3:

[0305] The terminal transmits the acquired image data and audio data to the server in real time.

[0306] Step 4:

[0307] The server inputs the received data into the emotion engine and analyzes the user's facial expressions and voice.

[0308] Step 5:

[0309] The server stores the analysis results of the emotion engine in a database and records the user's emotional state in real time.

[0310] Processing of customized communications

[0311] Step 1:

[0312] The server uses the analysis results from the emotion engine to evaluate the user's level of stress and anxiety.

[0313] Step 2:

[0314] The server selects appropriate information based on the evaluation results. For example, if a high stress state is detected, it will provide a reassuring message or evacuation information.

[0315] Step 3:

[0316] The server sends the selected information to the terminal via the dashboard API.

[0317] Step 4:

[0318] The device visually displays the received information to the user, encouraging safe behavior, and can also play audible messages to reduce stress.

[0319] Priority reflection processing

[0320] Step 1:

[0321] The server analyzes the damage situation information, including the emotion data, stored in the database.

[0322] Step 2:

[0323] Based on the emotional data, the server assesses the level of stress and anxiety in each affected area and sets priorities.

[0324] Step 3:

[0325] The server reconstructs the allocation plan for relief supplies and personnel based on priorities, and prioritizes areas where high stress levels are detected.

[0326] Step 4:

[0327] The server sends the recalculated support plan to the device via the dashboard API.

[0328] Step 5:

[0329] The device will display the new plan to the user and provide instructions on how to receive relief supplies and guidelines for action.

[0330] Specific examples

[0331] Example 1: Processing when an earthquake occurs

[0332] Step 1:

[0333] The server receives earthquake data from the seismometer and stores it in a database.

[0334] Step 2:

[0335] The server analyzes earthquake data and predicts the epicenter and intensity of the earthquake.

[0336] Step 3:

[0337] The device activates the camera and microphone and transmits the user's facial expressions and voice to the server in real time.

[0338] Step 4:

[0339] The server uses an emotion engine to analyze the user's emotional state.

[0340] Step 5:

[0341] The server identifies areas with a large number of users experiencing high stress levels and develops a plan to prioritize sending relief supplies to those areas.

[0342] Step 6:

[0343] The server sends the plan to the device via the dashboard API, and the device provides the information to the user.

[0344] Example 2: Flood forecasting and response planning

[0345] Step 1:

[0346] The server receives rainfall data from weather sensors and stores it in a database.

[0347] Step 2:

[0348] The server analyzes rainfall data and runs flood forecasting models.

[0349] Step 3:

[0350] The server identifies areas that are likely to be flooded and predicts damage.

[0351] Step 4:

[0352] The device activates the camera and microphone to collect the user's emotional data and send it to the server.

[0353] Step 5:

[0354] The server analyzes the emotional data and identifies areas where there are many users with high stress levels.

[0355] Step 6:

[0356] The server calculates the necessary relief supplies based on the priority and generates the optimal relief plan.

[0357] Step 7:

[0358] The server sends the support plan to the device via the dashboard API, and the device visually displays it to the user.

[0359] In this way, the system of the present invention combines real-time data collection, analysis, and user emotion recognition to enable rapid and effective responses in the event of a disaster and reduce the psychological burden on users.

[0360] Example 2

[0361] 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."

[0362] With the increasing frequency of natural disasters, there is a need for real-time data collection and analysis, damage analysis, and optimal response plans. However, conventional systems lacked functionality to address the psychological burden placed on users, making it difficult to maintain psychological stability during disasters. Furthermore, they were also inadequate in formulating quick and effective support plans based on collected data and proposing optimal travel routes.

[0363] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0364] In this invention, the server includes means for collecting data in real time, means for saving the collected data, means for analyzing the saved data and making disaster predictions, means for analyzing the damage situation, means for collecting and analyzing user emotion data, means for providing information for reducing psychological burden based on the collected emotion data, means for proposing an optimal response plan for rescue and recovery, means for providing necessary information, and means for proposing an optimal travel route. This enables effective disaster response in real time, and makes it possible to propose optimal support plans and travel routes while reducing the psychological burden on users.

[0365] "Means for collecting data in real time" refers to devices or systems that acquire disaster and environmental data in real time using sensors, unmanned aerial vehicles, satellites, external APIs, etc.

[0366] "Means for storing collected data" refers to a database or storage system for temporarily or permanently storing acquired data.

[0367] "Means for analyzing stored data and making disaster predictions" refers to a system that analyzes stored data and uses algorithms and AI models to predict the occurrence of earthquakes, floods, and other disasters in advance.

[0368] "Means for analyzing the damage situation" refers to a system that analyzes the scale and extent of the damage after a disaster occurs, and determines the exact extent of the damage.

[0369] The "means for collecting and analyzing user emotional data" refers to a system that uses devices such as a camera and microphone to collect the user's facial expressions and tone of voice, and analyzes them using an emotion recognition engine.

[0370] The "means for providing information that reduces psychological burden based on collected emotional data" is a system that provides notifications and evacuation information that give users a sense of security based on analyzed emotional data.

[0371] The "means of proposing optimal response plans for rescue and recovery" is a system that draws up plans for the allocation of damage, necessary supplies, and personnel, and provides optimal support and recovery methods.

[0372] "Means for providing necessary information" refers to a system that provides users with breaking news and updated information via a dashboard or the like.

[0373] The "means for proposing optimal travel routes" is a system that calculates and proposes optimal travel routes for relief supplies and personnel based on traffic and damage information.

[0374] This invention is realized by combining the following elements in the system: The roles of the server, terminal, and user are specifically shown, and the corresponding hardware and software configurations, data processing, and data calculations are explained in detail.

[0375] System Overview

[0376] This system collects data in real time, analyzes it, predicts damage, proposes optimal response plans, provides information, and recognizes emotions, enabling effective responses in the event of a disaster. In particular, it is equipped with an emotion recognition function to reduce the psychological burden on users.

[0377] Data collection

[0378] The server uses sensors (seismometers, weather sensors), unmanned aerial vehicles, satellites, external APIs, etc. to collect earthquake data, rainfall data, image data, weather data, traffic information, etc. in real time. Specific devices used include seismometers (e.g., Seismometer-X100), weather sensors (e.g., WeatherSensor-Y200), and unmanned aerial vehicles (e.g., DJI Phantom 4). Data is obtained using APIs from the Japan Meteorological Agency and traffic information providers.

[0379] Data storage

[0380] The server stores the collected data in a database. Structured data (e.g., numerical data) is stored in a relational database (e.g., MySQL), and unstructured data (e.g., image data) is stored in a non-relational database (e.g., MongoDB). A timestamp is assigned to each entry of the data, and it is managed to make it easy to search and analyze.

[0381] Data analysis

[0382] The server analyzes the stored data using AI models (e.g., TensorFlow, PyTorch) to predict disasters such as earthquakes and floods. The analysis results are stored in a database and used to develop subsequent response plans.

[0383] Damage response proposals

[0384] The server calculates the type, quantity, and priority of needed relief supplies based on disaster prediction and damage data. It also creates a personnel deployment plan and formulates optimal relief and recovery plans. In this process, the results of the AI ​​model's calculations are utilized to enable a fast and efficient response.

[0385] Providing information

[0386] The server sends the latest analysis results and support plans to a dashboard API (e.g., Grafana, Tableau), which then receives and displays the information on the device. Users can visually check the information updated in real time through their device.

[0387] Optimal route suggestions

[0388] The server calculates the optimal route using the Google® Maps API based on the collected traffic information. The calculation results are sent to the dashboard API, which is then received and displayed on the device. This allows for the efficient movement of relief supplies and personnel.

[0389] emotion recognition

[0390] The server analyzes the user's image and voice data collected from the device's connected camera (e.g., Logitech C920) and microphone (e.g., Blue Yeti) in real time using an emotion engine (e.g., Affectiva, Microsoft® Azure® Emotion API). The analyzed emotion data is stored in a database, and information to reduce psychological stress is provided as needed.

[0391] Specific examples

[0392] Example 1: Processing when an earthquake occurs

[0393] 1. The server receives earthquake data from a seismometer (e.g., Seismometer-X100) and stores it in a database.

[0394] 2. The server analyzes the earthquake data and predicts the epicenter and intensity of the earthquake.

[0395] 3. The server analyzes the emotional data collected from the device's camera and microphone and identifies areas with a high number of users experiencing high levels of stress.

[0396] 4. The server will develop a plan to quickly send relief supplies to the identified area.

[0397] 5. The device receives the assistance plan and visually displays it to the user.

[0398] Prompt for the generative AI model in this example:

[0399] "Generate a scenario for the next earthquake. Explain in detail how you would predict damage based on data collected from sensors and how you would collect and analyze user emotion data. Then, describe the steps to propose an optimal assistance plan."

[0400] Example 2: Flood forecasting and response planning

[0401] 1. The server receives rainfall data from a weather sensor (e.g., WeatherSensor-Y200) and stores it in a database.

[0402] 2. The server analyzes the rainfall data and runs flood forecasting models.

[0403] 3. The server identifies areas at high risk of flooding and calculates the amount of relief supplies needed.

[0404] 4. The server creates a support plan and prioritizes sending support to areas with a large number of users in high stress.

[0405] 5. The device receives the support plan and displays it to the user.

[0406] Prompt for the generative AI model in this example:

[0407] "Generate the following flood scenario. Explain in detail how you would use data collected from sensors to perform flood predictions, identify damage, and collect and analyze user sentiment data. Then, detail the steps to propose an optimal assistance plan."

[0408] In this way, the system executes each processing step in detail, realizing effective disaster response while reducing the psychological burden on the user.

[0409] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0410] Step 1: Data collection

[0411] The server collects various data in real time using sensors, unmanned aerial vehicles, satellites, external APIs, etc. Specifically, it obtains earthquake data from seismometers (e.g., Seismometer-X100), rainfall data from weather sensors (e.g., WeatherSensor-Y200), and image data from unmanned aerial vehicles (e.g., DJI Phantom 4). It also obtains the latest weather and traffic information from the APIs of the Japan Meteorological Agency and traffic information services. The server receives input data from each device and API and converts it into a format that can be used in the next step.

[0412] Step 2: Save data

[0413] The server stores the collected data in a database. The input is various data collected in real time, which the server stores as structured data (e.g., numerical data stored in MySQL) and unstructured data (e.g., image data stored in MongoDB). Each piece of data is assigned a timestamp and managed to make it easy to search and analyze. The output is the various saved data stored in the database.

[0414] Step 3: Data analysis

[0415] The server inputs the stored data into an AI model (e.g., TensorFlow, PyTorch) for analysis. The inputs include stored earthquake data, meteorological data, and image data, and the server analyzes these to predict earthquakes and floods. Specifically, it predicts the epicenter and seismic intensity from the earthquake data, and identifies flood risk areas from the meteorological data. The analysis results are output and stored in a database for use in the next step.

[0416] Step 4: Damage response proposal

[0417] The server calculates the type, quantity, and priority of the necessary relief supplies based on the disaster prediction data obtained as a result of the analysis. The inputs are the disaster prediction data and collected damage situation data, and the server uses this to formulate a relief plan. Specifically, it uses an AI model to create optimal personnel deployment plans and supply distribution plans. The output is an optimal relief and recovery plan.

[0418] Step 5: Provide information

[0419] The server sends the latest analysis results and support plans to a dashboard API (e.g., Grafana, Tableau), and the terminal receives and displays the information. The input includes analysis results and support plan data, which the server sends to the terminal via the dashboard API. The terminal receives this information and displays it visually to the user. As an output, the user can view information that is updated in real time.

[0420] Step 6: Optimal route proposal

[0421] The server uses the Google Maps API to calculate the optimal travel route based on the collected traffic information. The server inputs the latest traffic and damage information into a route calculation algorithm. The calculation results are sent to the dashboard API and received and displayed on the device. The output is optimal travel route information, enabling the efficient movement of relief supplies and personnel.

[0422] Step 7: Emotion Recognition

[0423] The server uses an emotion engine (e.g., Affectiva, Microsoft Azure Emotion API) to analyze in real time the user's image and voice data collected from the camera (e.g., Logitech C920) or microphone (e.g., Blue Yeti) connected to the device. The input is the collected image and voice data, which the server analyzes to recognize the user's emotions (fear, stress, relief, etc.). The analysis results are stored in a database, and notifications or evacuation information are provided to reduce psychological stress as needed. The output is the recognized emotion data and actions based on it.

[0424] (Application example 2)

[0425] 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."

[0426] Conventional disaster response systems collect and analyze data in real time, predicting disasters, analyzing damage situations, and proposing rescue and recovery plans, but they do not adequately consider reducing the psychological burden on users. Furthermore, they lack the ability to provide customized information that takes into account people's emotional changes during a disaster, making it difficult for users to take appropriate action. This limits the effectiveness of disaster response and makes it difficult to prevent the damage from spreading.

[0427] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data in real time, means for analyzing the collected data and making disaster predictions, means for analyzing the damage situation, means for proposing an optimal response plan for rescue and recovery, means for providing necessary information, means for proposing an optimal travel route, means for recognizing the user's emotions in real time using an emotion recognition engine, and means for providing information customized based on the user's emotion data. This makes it possible to improve the efficiency and effectiveness of disaster response while reducing the psychological burden on the user.

[0428] "Means of collecting data in real time" refers to devices and methods that collect current information from sensors, external APIs, drones, satellites, etc.

[0429] "Means for analyzing collected data and making disaster predictions" refers to devices or methods that use AI models or algorithms based on acquired information to predict the possibility and scope of a disaster.

[0430] "Means for analyzing the damage situation" refers to devices and methods for assessing and analyzing the scope of impact and the extent of damage when a disaster occurs.

[0431] "Means for proposing optimal response plans for rescue and recovery" refers to devices and methods for creating plans to efficiently provide the types and quantities of supplies needed, deploy personnel, etc., based on the damage situation.

[0432] The "means for providing necessary information" refers to a device or method that visually or audibly provides the user with situation information and evacuation information that is updated in real time.

[0433] "Means for proposing optimal travel routes" refers to devices or methods that calculate and present the most suitable travel routes for evacuation, delivery of relief supplies, etc. based on damage status and traffic information.

[0434] "Means for recognizing a user's emotions in real time using an emotion recognition engine" refers to a device or method that analyzes image and audio data from a camera or microphone and determines the user's emotional state in real time.

[0435] "Means for providing information customized based on user emotional data" refers to a device or method that provides information adjusted to reduce the user's psychological burden based on recognized emotional data.

[0436] This invention is a system for reducing the psychological burden on users during disasters and realizing more effective countermeasures. The system provides comprehensive support to users by combining real-time data collection, analysis, disaster prediction, damage analysis, optimal response plan proposal, information provision, optimal travel route proposal, and an emotion engine that recognizes the user's emotions.

[0437] System Configuration

[0438] 1. Data Collection Module

[0439] The server collects real-time data from sensors, drones, satellites, and external APIs, including data from seismometers and weather sensors, image data from drones and satellites, and API data from meteorological agencies and traffic information services.

[0440] 2. Data storage module

[0441] The server stores the collected data in a database, which can manage both structured and unstructured data.

[0442] 3. Data Analysis Module

[0443] The server applies machine learning and AI models to the stored data to predict disasters and analyze damage situations, thereby predicting the epicenter and intensity of earthquakes and flood areas in the event of an earthquake.

[0444] 4. Aid Response Proposal Module

[0445] The server calculates the type, quantity, and priority of supplies needed based on the damage situation, and creates a personnel deployment plan, which is optimized based on data updated in real time.

[0446] 5. Information System

[0447] The server sends the latest information to the dashboard via API, which the device receives and displays visually, providing users with easy-to-understand, real-time updates and recommendations.

[0448] 6. Optimal Route Proposal Module

[0449] The server calculates optimal routes based on the latest traffic information, taking into account the extent of damage and traffic conditions, optimizing routes for delivering relief supplies and moving personnel.

[0450] 7. Emotion Engine

[0451] The server collects image and audio data from the camera and microphone and analyzes it using an emotion engine, which recognizes emotions (fear, stress, relief, etc.) from the user's facial expressions and tone of voice in real time.

[0452] Program processing explanation

[0453] Hardware: Cameras, microphones, and GPS sensors built into devices such as smartphones, tablets, and computers.

[0454] Software: The application is developed using Python and utilizes machine learning libraries (TensorFlow and PyTorch), and API communication involves HTTP requests and JSON data exchange.

[0455] Data processing and calculation: Data collected from sensors and external APIs is stored in a database and analyzed by machine learning models. The emotion engine analyzes data obtained from the camera and microphone to recognize the user's emotional state.

[0456] Example: When an earthquake occurs, the server immediately acquires and analyzes seismograph data and predicts the epicenter. The user's device uses a camera and microphone to analyze the user's emotions and presents a "safe evacuation route."

[0457] Example prompt sentence:

[0458] Analyze the video and audio data to recognize the user's current emotions. If the result is "high stress," generate a message saying, "According to the analysis results, the current situation has a low risk of disaster. However, please secure the optimal evacuation route just in case."

[0459] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0460] Step 1:

[0461] Real-time data collection

[0462] The server collects seismograph data, weather data, and traffic information in real time from sensors, drones, satellites, and external APIs. Specifically, it retrieves data from APIs using HTTP requests. The input is data streams from various sensors and APIs, which are received and stored in a database as structured and unstructured data. The output is the latest disaster-related data stored in the database.

[0463] Step 2:

[0464] Data storage

[0465] The server stores the collected data in a database. This database can be an RDBMS or NoSQL database. The input is sensor data or API data collected in real time, and the output is the stored data. Specific operations include data format conversion, normalization, and index creation.

[0466] Step 3:

[0467] Data analysis and disaster prediction

[0468] The server analyzes the stored data and uses AI models to make disaster predictions. The input is the latest disaster-related data stored in the database, and the output is a prediction of the likelihood of a disaster occurring and the damage it will cause. Specific operations include applying machine learning models and running prediction algorithms.

[0469] Step 4:

[0470] Analysis of the damage situation

[0471] The server analyzes the damage situation in real time after a disaster occurs. The input is the disaster prediction results and additional sensor data, and the output is the analysis results of the damage range and extent. Specific operations include image analysis, text analysis, and data aggregation.

[0472] Step 5:

[0473] Proposed relief and recovery plan

[0474] The server calculates the type, quantity, and priority of supplies needed based on the results of the damage analysis, and then creates a personnel deployment plan. The input is the results of the damage analysis and existing rescue resource data, and the output is a detailed rescue and recovery plan. The specific operation involves applying a resource optimization algorithm.

[0475] Step 6:

[0476] Providing information

[0477] The server sends the latest information to the dashboard API, which the device receives and visually displays. The input is disaster prediction results and rescue plans, and the output is real-time information displayed to the user. Specific operations include data format conversion and UI updates.

[0478] Step 7:

[0479] Proposing optimal travel routes

[0480] The server calculates the optimal travel route based on the latest traffic information and sends it to the terminal. The input is real-time traffic data and disaster information, and the output is a proposal for the optimal travel route. Specifically, the route calculation is performed using Dijkstra's algorithm or the A algorithm.

[0481] Step 8:

[0482] emotion recognition

[0483] The device collects image and audio data from the camera and microphone, and the server analyzes it using an emotion engine. The input is the image and audio data sent from the device, and the output is the recognition result of the user's emotional state (high stress, relief, etc.). Specific operations include applying facial expression recognition algorithms and voice analysis algorithms.

[0484] Step 9:

[0485] Customized information provision

[0486] Based on the recognized emotion data, the server sends customized information to the device to reduce the user's psychological burden. The input is the recognized emotion data and disaster information, and the output is a customized message or notification. For example, a message such as "According to the analysis results, the current situation has a low risk of disaster. However, please secure the optimal evacuation route just in case" may be generated.

[0487] 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.

[0488] 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.

[0489] 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.

[0490] [Second embodiment]

[0491] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0492] 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.

[0493] 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).

[0494] 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.

[0495] 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.

[0496] 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).

[0497] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0498] 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.

[0499] 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.

[0500] 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.

[0501] 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.

[0502] 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."

[0503] This invention relates to a system for implementing rapid and effective countermeasures in the event of a disaster, including the collection and analysis of real-time data, damage prediction, response plan proposal, information provision, and optimal travel route proposal. Specific embodiments for implementing the invention are described below.

[0504] System configuration

[0505] 1. Data Collection Module

[0506] The server collects data in real time from sensors, drones, satellites, external APIs, etc. For example, it uses data from seismometers and weather sensors, image data from drones and satellites, and API data from the Japan Meteorological Agency and traffic information services.

[0507] 2. Data storage module

[0508] The server stores the collected data in a database, which can handle both structured and unstructured data.

[0509] 3. Data Analysis Module

[0510] The server then performs analysis on the stored data, using AI algorithms to run disaster prediction and damage situation models, which can predict, for example, the epicenter and intensity of an earthquake, as well as areas susceptible to flooding.

[0511] 4. Aid Response Proposal Module

[0512] The server will create optimal aid and recovery plans based on the damage situation, for example, calculating the type, quantity and priority of supplies needed and creating a personnel deployment plan.

[0513] 5. Information System

[0514] The server sends the latest information to the dashboard API, which the device receives and visually displays, providing users with easy-to-understand, real-time updated data and recommendations.

[0515] 6. Optimal Route Proposal Module

[0516] The server calculates optimal routes based on the latest traffic information, taking into account the extent of damage and traffic conditions, and optimizes routes for delivering relief supplies and moving personnel.

[0517] Program processing explanation

[0518] Disaster prediction and damage analysis

[0519] The server stores data collected from sensors, drones, and satellites in a database. It then analyzes the stored data using AI algorithms and runs disaster prediction models. These models identify predicted earthquake centers and areas prone to flooding. The analysis results are stored in the database as they are processed and sent to devices via the dashboard API.

[0520] Aid response proposal

[0521] The server calculates the necessary relief supplies and personnel based on the damage information and generates an optimal relief plan. For example, it calculates the required amounts of food, water, medicine, etc. and plans the deployment of rescue teams. The generated relief plan is sent to the device via the dashboard API, where the user can confirm it.

[0522] Providing information

[0523] The server continuously updates the collected and analyzed data in real time and notifies the user of important information. For example, it sends push notifications in response to the expansion of the affected area or changes in traffic conditions. The device receives these notifications and displays them to the user, prompting them to take action as necessary.

[0524] Optimal route suggestions

[0525] The server calculates the optimal travel route based on traffic and damage information. The calculation uses Dijkstra's algorithm and A algorithm to calculate the shortest distance and fastest route. The calculation results are sent to the device, allowing the user to check the optimal route.

[0526] Specific examples

[0527] Example 1: Processing when an earthquake occurs

[0528] 1. The server receives earthquake data from the seismometer and stores it in a database.

[0529] 2. The server analyzes the stored data and runs models to predict the epicenter and intensity of the earthquake.

[0530] 3. The server sends the analysis results to the device via the dashboard API, and the device visually displays the prediction results.

[0531] 4. Users can check the damage situation and forecast information via their devices and take appropriate evacuation actions.

[0532] Example 2: Flood forecasting and response planning

[0533] 1. The server receives rainfall data from weather sensors and stores it in a database.

[0534] 2. The server analyzes the stored data and runs flood forecasting models, which identify areas that are likely to flood.

[0535] 3. The server calculates the necessary relief supplies based on the damage situation and generates the optimal relief plan.

[0536] 4. The terminal displays the support plan to the user, enabling them to quickly allocate the necessary resources.

[0537] In this way, this system enables rapid and effective response in the event of a disaster through the collection and analysis of real-time data.

[0538] The processing flow will be explained below.

[0539] Disaster prediction and damage analysis

[0540] Step 1:

[0541] The server receives information from sensors (seismometers, weather sensors), drones, satellite data, and external APIs.

[0542] Step 2:

[0543] The server stores the received data in a temporary memory, then normalizes the data and stores it in a database.

[0544] Step 3:

[0545] The server applies pre-trained AI models to the stored data to perform disaster predictions, such as predicting the epicenter and intensity of an earthquake, or the risk of flooding based on rainfall.

[0546] Step 4:

[0547] The server analyzes the prediction results to determine the extent of damage, and uses image analysis technology to process data from drones and satellites to assess the extent of damage to buildings.

[0548] Step 5:

[0549] The server stores the analysis results back in a database and notifies you of relevant information via email alerts and dashboard APIs.

[0550] Step 6:

[0551] The device receives data from the server and visually displays it on a dashboard, providing users with an easy-to-read view. Damage forecasts and response plans are highlighted on a map.

[0552] Processing of assistance response proposals

[0553] Step 1:

[0554] Based on the damage prediction results, the server evaluates the extent and distribution of the damage and calculates the necessary relief resources.

[0555] Step 2:

[0556] The server lists the required supplies (food, water, medicine, etc.) and personnel (emergency medical team, construction team) by type and calculates their quantities.

[0557] Step 3:

[0558] The server sets priorities for supplies and personnel and draws up plans for how much resource to allocate to each area.

[0559] Step 4:

[0560] The server generates a document with the optimal support and recovery plan and sends it to the device via the dashboard API.

[0561] Step 5:

[0562] The terminal receives the proposed assistance plan and visually displays it on the user interface, which the user can review and decide on specific actions to take.

[0563] Processing of information provided

[0564] Step 1:

[0565] The server collects new data in real time and continuously updates the database with the collected data.

[0566] Step 2:

[0567] When the server detects important updates (new disaster predictions, changes in the damage situation), it generates a push notification based on that information.

[0568] Step 3:

[0569] The device receives a push notification from the server and immediately alerts the user, providing a link to additional information if necessary.

[0570] Step 4:

[0571] Users can check the notifications and take necessary actions, such as checking evacuation locations or preparing to distribute relief supplies.

[0572] Processing optimal route suggestions

[0573] Step 1:

[0574] The server collects traffic and damage information in real time and stores it in a database.

[0575] Step 2:

[0576] The server runs an algorithm (such as Dijkstra's algorithm or A algorithm) to calculate the optimal travel route based on the latest data.

[0577] Step 3:

[0578] The server sends the calculated optimal route to the device via the dashboard API.

[0579] Step 4:

[0580] The terminal displays the optimal route information received from the server on a map, helping the user travel efficiently.

[0581] Step 5:

[0582] The user checks the presented route and gives instructions for the transportation of relief supplies and the movement of the rescue team.

[0583] Example 1

[0584] 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."

[0585] In modern society, rapid and accurate countermeasures are required when natural disasters occur. However, conventional systems have problems with insufficient real-time data collection and the time it takes to analyze the data, making it difficult to take prompt action. Furthermore, it is difficult to simultaneously solve multiple issues, such as assessing the damage situation, optimally distributing relief supplies, and proposing evacuation routes. This increases the risk of putting many lives and property at risk.

[0586] 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.

[0587] In this invention, the server includes means for collecting data in real time using sensors, unmanned aerial vehicles, satellites, and external APIs, means for storing the collected data in structured and unstructured databases, means for analyzing the stored data using an AI algorithm and running a disaster prediction model and a damage situation model, means for calculating relief supplies and personnel based on damage information and generating an optimal support plan, means for notifying users of important data and displaying the latest information through a dashboard API, and means for calculating optimal travel routes based on traffic and damage information and providing them to users, thereby enabling rapid and accurate disaster response.

[0588] A "sensor" is a device that measures environmental conditions or physical quantities and converts that information into an electrical signal.

[0589] An "unmanned aerial vehicle" is an aircraft that moves through the air by remote control or autonomous flight, collecting data and making observations.

[0590] A "satellite" is a spacecraft placed in orbit around the Earth that collects data such as meteorological observations and Earth remote sensing.

[0591] An "external API" is a programmatic interface for obtaining information from other systems or services.

[0592] A "database" is a system for efficiently storing, retrieving, and analyzing data. Both structured and unstructured databases exist.

[0593] An "AI algorithm" is a method of analyzing data using machine learning and data mining techniques to make predictions and classifications.

[0594] A "disaster prediction model" is a mathematical model for predicting the occurrence and impact of disasters based on collected data.

[0595] A "damage situation model" is a mathematical model used to analyze the scope and extent of damage when a disaster occurs.

[0596] A "support plan" is a specific proposal for optimally planning the types and quantities of relief supplies, the deployment of personnel, etc.

[0597] "Dashboard API" means a programmatic interface for visually displaying collected and analyzed data.

[0598] The "optimal route" is the most efficient travel route calculated based on traffic and damage information.

[0599] MODE FOR CARRYING OUT THE INVENTION

[0600] This invention is a system for realizing a rapid and effective response in the event of a disaster, and includes the collection and analysis of real-time data, damage prediction, response plan proposal, information provision, and optimal travel route proposal. Specific embodiments for implementing the invention are described below.

[0601] System configuration

[0602] Data collection

[0603] The server collects data in real time using sensors, drones, satellites, and external APIs. Specific examples include earthquake data from seismometers, weather data from weather sensors, image data from drones and satellites, and traffic data from traffic information APIs. All data is time-stamped, making it easier to analyze later.

[0604] Data storage

[0605] The server stores the collected data in structured and unstructured databases, using databases such as MySQL or MongoDB. For example, earthquake data is stored in a table called "seismic_data," and meteorological data is stored in a table called "weather_data."

[0606] Data analysis

[0607] The server uses AI algorithms to analyze the stored data. Specifically, it uses TensorFlow and other tools to run disaster prediction and damage situation models. This allows it to predict the epicenter and areas prone to flooding. The analysis results are stored in a new table called "prediction_results."

[0608] Aid response proposal

[0609] The server generates a relief plan based on the analysis results. Python is used to calculate the type and quantity of relief supplies and the deployment of personnel. The generated relief plan is converted into JSON format and sent to the device via the dashboard API. For example, the calculated relief plan may include information such as "Area A needs 500 sets of food, 100 liters of water, and five relief team members."

[0610] Providing information

[0611] The server notifies users of important information in real time based on the collected data and analysis results. For example, if it detects an expansion of the affected area or a change in traffic conditions, it sends a push notification to the device via the dashboard API. The device receives this and displays it as an alert to the user.

[0612] Optimal route suggestions

[0613] The server calculates the optimal travel route based on traffic and damage information. The algorithms used are Dijkstra's algorithm and A algorithm, which calculate the most efficient travel route. The calculation results are sent in JSON format to the device via the dashboard API, allowing the user to check the optimal route.

[0614] Specific examples

[0615] Example 1: Processing when an earthquake occurs

[0616] 1. The server receives earthquake data from the seismometer and stores it in a database.

[0617] 2. The server analyzes the stored data and runs models to predict the epicenter and intensity of the earthquake.

[0618] 3. The server sends the analysis results to the device via the dashboard API, and the device visually displays the prediction results.

[0619] 4. Users can check the damage situation and forecast information via their devices and take appropriate evacuation actions.

[0620] Example 2: Flood forecasting and response planning

[0621] 1. The server receives rainfall data from weather sensors and stores it in a database.

[0622] 2. The server analyzes the stored data and runs flood forecasting models, which identify areas that are likely to flood.

[0623] 3. The server calculates the necessary relief supplies based on the damage situation and generates the optimal relief plan.

[0624] 4. The terminal displays the support plan to the user, enabling them to quickly allocate the necessary resources.

[0625] Prompt Sentence Examples

[0626] "Please tell me the procedure for processing the damage prediction model in the event of an earthquake."

[0627] "Please give us some concrete examples of flood forecasts and response plans based on current rainfall data."

[0628] In this way, the present invention enables rapid and effective response in the event of a disaster through real-time data collection and analysis, enabling optimal measures to minimize damage and save lives.

[0629] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0630] Step 1: Data collection

[0631] The server collects data in real time using sensors, drones, satellites, and external APIs. For example, it acquires earthquake data from seismometers, weather data from weather sensors, image data from drones and satellites, and traffic data from traffic information APIs. The collected data is stored as a time-stamped log.

[0632] Inputs: Data from seismometers, weather sensors, drones, satellites, and external APIs

[0633] Output: Raw data log with timestamps

[0634] Specific operation:

[0635] Earthquake data is obtained from the seismometer every 10 seconds.

[0636] Traffic information updated every minute via API.

[0637] Step 2: Save data

[0638] The server stores the collected data in structured and unstructured databases, such as MySQL or MongoDB.

[0639] Input: Raw data log with timestamps

[0640] Output: Structured and unstructured data stored in a database

[0641] Specific operation:

[0642] Seismic data is stored using the SQL query "INSERT INTO seismic_data (timestamp, magnitude) VALUES (timestamp, magnitude)".

[0643] Weather data is stored using the SQL query "INSERT INTO weather_data (timestamp, temperature) VALUES (timestamp, temperature)".

[0644] Step 3: Data analysis

[0645] The server analyzes the stored data using AI algorithms, and runs disaster prediction models and damage situation models using TensorFlow and other tools.

[0646] Input: Structured and unstructured data stored in a database

[0647] Output: Analysis results (epicenter, seismic intensity, damage prediction area)

[0648] Specific operation:

[0649] TensorFlow is used to analyze earthquake data and predict the epicenter and intensity.

[0650] The analysis results are saved in a new table called "prediction_results".

[0651] Step 4: Propose an aid response

[0652] The server generates an aid plan based on the analysis results. It uses Python to calculate the type and quantity of needed relief supplies and personnel deployment. The generated aid plan is converted into JSON format and sent to the device via the dashboard API.

[0653] Input: Analysis results (epicenter, seismic intensity, predicted damage area)

[0654] Output: Support plan in JSON format

[0655] Specific operation:

[0656] Run a script to generate a support plan and calculate the required supplies and personnel allocation.

[0657] The generated support plan is saved as a "relief supplies JSON file."

[0658] Step 5: Provide information

[0659] The server notifies users of important information in real time based on the collected data and analysis results. Push notifications are sent to the device via the dashboard API, which receives them and displays them as alerts to the user.

[0660] Input: Important analytical results and newly collected data

[0661] Output: Push notification to the user

[0662] Specific operation:

[0663] If an expansion of the affected area or changes in traffic information are detected, a push notification will be generated.

[0664] Send notifications to devices via the Dashboard API.

[0665] Step 6: Optimal route proposal

[0666] The server calculates the optimal travel route based on traffic and damage information. The Dijkstra algorithm and A algorithm are used to calculate the most efficient travel route. The calculation results are sent in JSON format to the device via the dashboard API, allowing the user to check the optimal route.

[0667] Input: Traffic information, damage information

[0668] Output: Optimal route in JSON format

[0669] Specific operation:

[0670] Calculates the optimal route from the current location to the destination using Dijkstra's algorithm.

[0671] The calculation results are saved as an "optimal route JSON file" and sent to the device via the dashboard API.

[0672] (Application example 1)

[0673] 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."

[0674] Existing disaster prevention systems lack real-time data collection and analysis, making it difficult to develop rapid and effective response plans. They also lack the necessary information and optimal travel route suggestions required during a disaster, leaving users highly confused. Furthermore, notification functions on mobile devices such as smartphones are inadequate, making it difficult to provide important information immediately in an emergency.

[0675] 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.

[0676] In this invention, the server includes means for collecting data in real time, means for analyzing the collected data and making disaster predictions, means for analyzing the damage situation, means for proposing an optimal response plan for rescue and recovery, means for providing necessary information, means for proposing an optimal travel route, means for notifying the user using an application installed on the smartphone, and means for proposing assistance using data stored in the database. This enables a quick and effective response in the event of a disaster, and makes it possible to provide users with important information and optimal evacuation routes in real time.

[0677] "Real-time data collection means" refers to the system's ability to continuously acquire new data through sensors, drones, satellites, and external APIs.

[0678] "Means of analyzing collected data and making disaster predictions" refers to the system's function of using AI algorithms to predict the likelihood of disasters occurring and the extent of damage based on the acquired data.

[0679] "Means for analyzing the damage situation" refers to the system's function of using collected and analyzed data to assess the extent and severity of damage caused by a disaster.

[0680] "Means for proposing optimal response plans for rescue and recovery" refers to the system's function of planning the deployment of necessary supplies and personnel based on analyzed damage information, and determining the optimal means of assistance and recovery.

[0681] "Means of providing necessary information" refers to the system's functions for notifying users of important information in real time and encouraging appropriate action.

[0682] "Means for suggesting optimal travel routes" refers to the system's function of calculating the safest and quickest evacuation route based on traffic and damage information and presenting it to the user.

[0683] "Means of notifying users using an application installed on a smartphone" refers to a system function that notifies users of disaster information and evacuation routes in real time via an application.

[0684] "Means for proposing assistance responses using data stored in the database" refers to a system function that analyzes stored past and current data and proposes optimal assistance responses.

[0685] This invention is a system for providing rapid and effective countermeasures in the event of a disaster, and is implemented in the following steps.

[0686] Data collection

[0687] The server collects data in real time from sensors (such as seismometers and weather sensors), drones, satellites, and external APIs (such as the Japan Meteorological Agency and traffic information services). This allows for a constant accumulation of up-to-date information on earthquakes and weather. Specific hardware used includes seismometers, weather sensors, drones, and satellites. Software uses libraries (such as Requests) to access external APIs.

[0688] Data storage

[0689] The collected data is stored in a database by the server. Databases can handle both structured and unstructured data. Examples of databases used include SQLite and MySQL.

[0690] Data analysis

[0691] The server uses AI algorithms based on the stored data to perform disaster predictions. This analysis identifies, for example, the epicenter and intensity of an earthquake, as well as areas expected to be flooded. The AI ​​algorithms utilize machine learning libraries such as Scikit-learn and TensorFlow.

[0692] Damage analysis

[0693] The server evaluates the damage situation based on the analyzed data, allowing the extent of the disaster's impact and severity to be determined. The analysis results are stored in a database and updated as needed.

[0694] Aid response proposal

[0695] The server calculates the necessary relief supplies and personnel allocation based on damage information, and generates an optimal aid and recovery plan, which calculates the necessary amounts of food, water, medicine, etc., enabling the rapid deployment of rescue teams.

[0696] Providing information

[0697] The server notifies users of important information based on data collected and analyzed in real time. Information such as damage forecasts, assistance response plans, and optimal evacuation routes is provided via push notifications using an application installed on a smartphone. Notification services such as Firebase Cloud Messaging are used.

[0698] Optimal route suggestions

[0699] The server calculates the optimal travel route based on traffic and damage information. The calculation uses Dijkstra's algorithm and A algorithm to calculate the shortest distance and fastest route. The calculation results are sent to devices such as smartphones, allowing users to evacuate safely.

[0700] Specific examples

[0701] For example, when an earthquake occurs, the server receives earthquake data from a seismometer and predicts the epicenter and seismic intensity. Based on this information, the damage situation is analyzed and appropriate relief supplies and personnel deployment plans are made. Ultimately, the epicenter, seismic intensity, and evacuation routes are notified to the user's smartphone. As another example, in flood prediction, rainfall data is collected and areas with a high probability of flooding are identified. This makes it possible to quickly deliver necessary relief supplies to areas where disasters are predicted.

[0702] Prompt Sentence Examples

[0703] "Based on the latest earthquake and meteorological data, please estimate the epicenter and damage, and suggest evacuation routes."

[0704] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0705] Step 1: Data collection

[0706] The server collects real-time data from seismometers, weather sensors, drones, satellites, and external APIs. Input data includes earthquake data, meteorological data, and image data. The server obtains the latest data from each data source and passes it on to the next processing step. This allows the latest disaster information to be collected at all times.

[0707] Step 2: Save data

[0708] The server stores the collected data in a database. The input data is earthquake and weather data collected in real time, and is stored in the database as structured or unstructured data. This data is efficiently managed using a database management system such as SQLite or MySQL.

[0709] Step 3: Data analysis

[0710] The server uses AI algorithms based on the stored data to make disaster predictions. The input data is stored earthquake and weather data. The AI ​​algorithm analyzes the earthquake's epicenter, seismic intensity, predicted flood areas, etc., and outputs the results. Machine learning libraries such as Scikit-learn and TensorFlow are used here.

[0711] Step 4: Damage analysis

[0712] The server assesses the damage situation based on the analyzed data. The input data is the analysis results. The impact scope and severity of the disaster are assessed, and the damage situation is understood in detail. This information is used to plan the next aid response.

[0713] Step 5: Propose an aid response

[0714] The server creates optimal rescue and recovery plans based on the damage situation. The input data is a detailed description of the damage situation, and it calculates the necessary supplies and personnel to generate an optimal support plan. This determines the required amounts of supplies such as food, water, and medicine, as well as the deployment of rescue teams.

[0715] Step 6: Provide information

[0716] The server provides users with important information in real time. The input data is assistance response plans and damage situation information, and the information is sent to users via an application installed on their smartphone. Push notification services such as Firebase Cloud Messaging are used to prompt users to take appropriate action.

[0717] Step 7: Optimal route proposal

[0718] The server calculates the optimal travel route based on traffic and damage information. The input data is real-time traffic and damage information, and the shortest distance and fastest route are calculated using Dijkstra's algorithm and A algorithm. The results are sent to the user's smartphone, helping them evacuate safely.

[0719] Step 8: User's appropriate evacuation behavior

[0720] The user takes appropriate evacuation action based on the information received on their smartphone. The input data is a notification sent from the server, and the user confirms it and follows the indicated evacuation route. This allows the user to evacuate quickly and safely.

[0721] 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.

[0722] This invention relates to a system that reduces the psychological burden on users during disasters and realizes more effective countermeasures by combining real-time data collection, analysis, damage prediction, response plan proposals, information provision, and optimal travel route proposals with an emotion engine that recognizes the user's emotions. Specific embodiments for implementing this invention are described below.

[0723] System configuration

[0724] 1. Data Collection Module

[0725] The server collects data in real time from sensors, drones, satellites, and external APIs. Specifically, it uses data from seismometers and weather sensors, image data from drones and satellites, and API data from the Japan Meteorological Agency and traffic information services.

[0726] 2. Data storage module

[0727] The server stores the collected data in a database, which can handle both structured and unstructured data.

[0728] 3. Data Analysis Module

[0729] The server applies AI models to the stored data to predict disasters and analyze damage situations, for example, predicting the epicenter and seismic intensity of an earthquake and areas susceptible to flooding.

[0730] 4. Aid Response Proposal Module

[0731] Based on the damage situation, the server calculates the type, quantity, and priority of supplies needed and draws up a personnel deployment plan.

[0732] 5. Information System

[0733] The server sends the latest information to the dashboard API, which the device receives and visually displays, providing users with easy-to-understand, real-time updated data and recommendations.

[0734] 6. Optimal Route Proposal Module

[0735] The server calculates optimal routes based on the latest traffic information, taking into account the extent of damage and traffic conditions, and optimizes routes for delivering relief supplies and moving personnel.

[0736] 7. Emotion Engine

[0737] The server uses an emotion engine to recognize the user's emotions in real time. Emotion data is collected and analyzed from cameras and microphones.

[0738] Program processing explanation

[0739] User Emotion Recognition

[0740] The server collects image and audio data from the camera and microphone connected to the device.

[0741] The server uses an emotion engine to analyze the collected data and recognize emotions (fear, stress, relief, etc.) from the user's facial expressions and voice tone.

[0742] The server stores the recognized emotion data in a database and triggers actions as needed.

[0743] Customized information provision

[0744] The server analyzes the user's stress and anxiety levels based on the emotional data. For example, if the user is in a high-stress state, it provides reassuring notifications and evacuation information.

[0745] The server sends the analysis results to the dashboard API, which the device receives and displays in real time, along with reassuring messages and alerts.

[0746] Reflecting priorities

[0747] The server then uses the emotional data to prioritize rescue and recovery plans, for example by quickly dispatching relief supplies and rescue teams to areas with a high number of users experiencing high levels of stress.

[0748] The server reconstructs the support plan based on the priority and allocates resources optimally.

[0749] Specific examples

[0750] Example 1: Processing when an earthquake occurs

[0751] 1. The server receives earthquake data from the seismometer and stores it in a database.

[0752] 2. The server analyzes the stored data and predicts the epicenter and intensity of the earthquake.

[0753] 3. The server collects the user's emotional data from the device's camera and microphone and analyzes it using an emotion engine.

[0754] 4. The server identifies areas with a high number of users experiencing high stress and develops a plan to quickly send relief supplies to those areas.

[0755] Example 2: Flood forecasting and response planning

[0756] 1. The server receives rainfall data from weather sensors and stores it in a database.

[0757] 2. The server analyzes the rainfall data and runs flood forecasting models, which identify areas that are likely to flood.

[0758] 3. The server calculates the necessary relief supplies based on the damage situation and generates the optimal relief plan.

[0759] 4. The server analyzes the user's emotional state and provides priority support to areas with a high number of users in high stress states.

[0760] 5. The terminal displays the support plan to the user, enabling them to quickly allocate the necessary resources.

[0761] In this way, by combining emotion engines, it is possible to reduce the psychological burden on users and enable more effective responses in the event of a disaster.

[0762] The processing flow will be explained below.

[0763] User emotion recognition processing

[0764] Step 1:

[0765] The terminal activates the camera and microphone on the device operated by the user.

[0766] Step 2:

[0767] The device captures a picture of the user's face with a camera and collects audio data with a microphone.

[0768] Step 3:

[0769] The terminal transmits the acquired image data and audio data to the server in real time.

[0770] Step 4:

[0771] The server inputs the received data into the emotion engine and analyzes the user's facial expressions and voice.

[0772] Step 5:

[0773] The server stores the analysis results of the emotion engine in a database and records the user's emotional state in real time.

[0774] Processing of customized communications

[0775] Step 1:

[0776] The server uses the analysis results from the emotion engine to evaluate the user's level of stress and anxiety.

[0777] Step 2:

[0778] The server selects appropriate information based on the evaluation results. For example, if a high stress state is detected, it will provide a reassuring message or evacuation information.

[0779] Step 3:

[0780] The server sends the selected information to the terminal via the dashboard API.

[0781] Step 4:

[0782] The device visually displays the received information to the user, encouraging safe behavior, and can also play audible messages to reduce stress.

[0783] Priority reflection processing

[0784] Step 1:

[0785] The server analyzes the damage situation information, including the emotion data, stored in the database.

[0786] Step 2:

[0787] Based on the emotional data, the server assesses the level of stress and anxiety in each affected area and sets priorities.

[0788] Step 3:

[0789] The server reconstructs the allocation plan for relief supplies and personnel based on priorities, and prioritizes areas where high stress levels are detected.

[0790] Step 4:

[0791] The server sends the recalculated support plan to the device via the dashboard API.

[0792] Step 5:

[0793] The device will display the new plan to the user and provide instructions on how to receive relief supplies and guidelines for action.

[0794] Specific examples

[0795] Example 1: Processing when an earthquake occurs

[0796] Step 1:

[0797] The server receives earthquake data from the seismometer and stores it in a database.

[0798] Step 2:

[0799] The server analyzes earthquake data and predicts the epicenter and intensity of the earthquake.

[0800] Step 3:

[0801] The device activates the camera and microphone and transmits the user's facial expressions and voice to the server in real time.

[0802] Step 4:

[0803] The server uses an emotion engine to analyze the user's emotional state.

[0804] Step 5:

[0805] The server identifies areas with a large number of users experiencing high stress levels and develops a plan to prioritize sending relief supplies to those areas.

[0806] Step 6:

[0807] The server sends the plan to the device via the dashboard API, and the device provides the information to the user.

[0808] Example 2: Flood forecasting and response planning

[0809] Step 1:

[0810] The server receives rainfall data from weather sensors and stores it in a database.

[0811] Step 2:

[0812] The server analyzes rainfall data and runs flood forecasting models.

[0813] Step 3:

[0814] The server identifies areas that are likely to be flooded and predicts damage.

[0815] Step 4:

[0816] The device activates the camera and microphone to collect the user's emotional data and send it to the server.

[0817] Step 5:

[0818] The server analyzes the emotional data and identifies areas where there are many users with high stress levels.

[0819] Step 6:

[0820] The server calculates the necessary relief supplies based on the priority and generates the optimal relief plan.

[0821] Step 7:

[0822] The server sends the support plan to the device via the dashboard API, and the device visually displays it to the user.

[0823] In this way, the system of the present invention combines real-time data collection, analysis, and user emotion recognition to enable rapid and effective responses in the event of a disaster and reduce the psychological burden on users.

[0824] Example 2

[0825] 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."

[0826] With the increasing frequency of natural disasters, there is a need for real-time data collection and analysis, damage analysis, and optimal response plans. However, conventional systems lacked functionality to address the psychological burden placed on users, making it difficult to maintain psychological stability during disasters. Furthermore, they were also inadequate in formulating quick and effective support plans based on collected data and proposing optimal travel routes.

[0827] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0828] In this invention, the server includes means for collecting data in real time, means for saving the collected data, means for analyzing the saved data and making disaster predictions, means for analyzing the damage situation, means for collecting and analyzing user emotion data, means for providing information for reducing psychological burden based on the collected emotion data, means for proposing an optimal response plan for rescue and recovery, means for providing necessary information, and means for proposing an optimal travel route. This enables effective disaster response in real time, and makes it possible to propose optimal support plans and travel routes while reducing the psychological burden on users.

[0829] "Means for collecting data in real time" refers to devices or systems that acquire disaster and environmental data in real time using sensors, unmanned aerial vehicles, satellites, external APIs, etc.

[0830] "Means for storing collected data" refers to a database or storage system for temporarily or permanently storing acquired data.

[0831] "Means for analyzing stored data and making disaster predictions" refers to a system that analyzes stored data and uses algorithms and AI models to predict the occurrence of earthquakes, floods, and other disasters in advance.

[0832] "Means for analyzing the damage situation" refers to a system that analyzes the scale and extent of the damage after a disaster occurs, and determines the exact extent of the damage.

[0833] The "means for collecting and analyzing user emotional data" refers to a system that uses devices such as a camera and microphone to collect the user's facial expressions and tone of voice, and analyzes them using an emotion recognition engine.

[0834] The "means for providing information that reduces psychological burden based on collected emotional data" is a system that provides notifications and evacuation information that give users a sense of security based on analyzed emotional data.

[0835] The "means of proposing optimal response plans for rescue and recovery" is a system that draws up plans for the allocation of damage, necessary supplies, and personnel, and provides optimal support and recovery methods.

[0836] "Means for providing necessary information" refers to a system that provides users with breaking news and updated information via a dashboard or the like.

[0837] The "means for proposing optimal travel routes" is a system that calculates and proposes optimal travel routes for relief supplies and personnel based on traffic and damage information.

[0838] This invention is realized by combining the following elements in the system: The roles of the server, terminal, and user are specifically shown, and the corresponding hardware and software configurations, data processing, and data calculations are explained in detail.

[0839] System Overview

[0840] This system collects data in real time, analyzes it, predicts damage, proposes optimal response plans, provides information, and recognizes emotions, enabling effective responses in the event of a disaster. In particular, it is equipped with an emotion recognition function to reduce the psychological burden on users.

[0841] Data collection

[0842] The server uses sensors (seismometers, weather sensors), unmanned aerial vehicles, satellites, external APIs, etc. to collect earthquake data, rainfall data, image data, weather data, traffic information, etc. in real time. Specific devices used include seismometers (e.g., Seismometer-X100), weather sensors (e.g., WeatherSensor-Y200), and unmanned aerial vehicles (e.g., DJI Phantom 4). Data is obtained using APIs from the Japan Meteorological Agency and traffic information providers.

[0843] Data storage

[0844] The server stores the collected data in a database. Structured data (e.g., numerical data) is stored in a relational database (e.g., MySQL), and unstructured data (e.g., image data) is stored in a non-relational database (e.g., MongoDB). A timestamp is assigned to each entry of the data, and it is managed to make it easy to search and analyze.

[0845] Data analysis

[0846] The server analyzes the stored data using AI models (e.g., TensorFlow, PyTorch) to predict disasters such as earthquakes and floods. The analysis results are stored in a database and used to develop subsequent response plans.

[0847] Damage response proposals

[0848] The server calculates the type, quantity, and priority of needed relief supplies based on disaster prediction and damage data. It also creates a personnel deployment plan and formulates optimal relief and recovery plans. In this process, the results of the AI ​​model's calculations are utilized to enable a fast and efficient response.

[0849] Providing information

[0850] The server sends the latest analysis results and support plans to a dashboard API (e.g., Grafana, Tableau), which then receives and displays the information on the device. Users can visually check the information updated in real time through their device.

[0851] Optimal route suggestions

[0852] The server uses the Google Maps API to calculate the optimal route based on the collected traffic information. The calculation results are sent to the dashboard API, which is then received and displayed on the device. This allows for the efficient movement of relief supplies and personnel.

[0853] emotion recognition

[0854] The server analyzes the user's image and voice data collected from the device's connected camera (e.g., Logitech C920) and microphone (e.g., Blue Yeti) in real time using an emotion engine (e.g., Affectiva, Microsoft Azure Emotion API). The analyzed emotion data is stored in a database, and information is provided to reduce psychological stress as needed.

[0855] Specific examples

[0856] Example 1: Processing when an earthquake occurs

[0857] 1. The server receives earthquake data from a seismometer (e.g., Seismometer-X100) and stores it in a database.

[0858] 2. The server analyzes the earthquake data and predicts the epicenter and intensity of the earthquake.

[0859] 3. The server analyzes the emotional data collected from the device's camera and microphone and identifies areas with a high number of users experiencing high levels of stress.

[0860] 4. The server will develop a plan to quickly send relief supplies to the identified area.

[0861] 5. The device receives the assistance plan and visually displays it to the user.

[0862] Prompt for the generative AI model in this example:

[0863] "Generate a scenario for the next earthquake. Explain in detail how you would predict damage based on data collected from sensors and how you would collect and analyze user emotion data. Then, describe the steps to propose an optimal assistance plan."

[0864] Example 2: Flood forecasting and response planning

[0865] 1. The server receives rainfall data from a weather sensor (e.g., WeatherSensor-Y200) and stores it in a database.

[0866] 2. The server analyzes the rainfall data and runs flood forecasting models.

[0867] 3. The server identifies areas at high risk of flooding and calculates the amount of relief supplies needed.

[0868] 4. The server creates a support plan and prioritizes sending support to areas with a large number of users in high stress.

[0869] 5. The device receives the support plan and displays it to the user.

[0870] Prompt for the generative AI model in this example:

[0871] "Generate the following flood scenario. Explain in detail how you would use data collected from sensors to perform flood predictions, identify damage, and collect and analyze user sentiment data. Then, detail the steps to propose an optimal assistance plan."

[0872] In this way, the system executes each processing step in detail, realizing effective disaster response while reducing the psychological burden on the user.

[0873] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0874] Step 1: Data collection

[0875] The server collects various data in real time using sensors, unmanned aerial vehicles, satellites, external APIs, etc. Specifically, it obtains earthquake data from seismometers (e.g., Seismometer-X100), rainfall data from weather sensors (e.g., WeatherSensor-Y200), and image data from unmanned aerial vehicles (e.g., DJI Phantom 4). It also obtains the latest weather and traffic information from the APIs of the Japan Meteorological Agency and traffic information services. The server receives input data from each device and API and converts it into a format that can be used in the next step.

[0876] Step 2: Save data

[0877] The server stores the collected data in a database. The input is various data collected in real time, which the server stores as structured data (e.g., numerical data stored in MySQL) and unstructured data (e.g., image data stored in MongoDB). Each piece of data is assigned a timestamp and managed to make it easy to search and analyze. The output is the various saved data stored in the database.

[0878] Step 3: Data analysis

[0879] The server inputs the stored data into an AI model (e.g., TensorFlow, PyTorch) for analysis. The inputs include stored earthquake data, meteorological data, and image data, and the server analyzes these to predict earthquakes and floods. Specifically, it predicts the epicenter and seismic intensity from the earthquake data, and identifies flood risk areas from the meteorological data. The analysis results are output and stored in a database for use in the next step.

[0880] Step 4: Damage response proposal

[0881] The server calculates the type, quantity, and priority of the necessary relief supplies based on the disaster prediction data obtained as a result of the analysis. The inputs are the disaster prediction data and collected damage situation data, and the server uses this to formulate a relief plan. Specifically, it uses an AI model to create optimal personnel deployment plans and supply distribution plans. The output is an optimal relief and recovery plan.

[0882] Step 5: Provide information

[0883] The server sends the latest analysis results and support plans to a dashboard API (e.g., Grafana, Tableau), and the terminal receives and displays the information. The input includes analysis results and support plan data, which the server sends to the terminal via the dashboard API. The terminal receives this information and displays it visually to the user. As an output, the user can view information that is updated in real time.

[0884] Step 6: Optimal route proposal

[0885] The server uses the Google Maps API to calculate the optimal travel route based on the collected traffic information. The server inputs the latest traffic and damage information into a route calculation algorithm. The calculation results are sent to the dashboard API and received and displayed on the device. The output is optimal travel route information, enabling the efficient movement of relief supplies and personnel.

[0886] Step 7: Emotion Recognition

[0887] The server uses an emotion engine (e.g., Affectiva, Microsoft Azure Emotion API) to analyze in real time the user's image and voice data collected from the camera (e.g., Logitech C920) or microphone (e.g., Blue Yeti) connected to the device. The input is the collected image and voice data, which the server analyzes to recognize the user's emotions (fear, stress, relief, etc.). The analysis results are stored in a database, and notifications or evacuation information are provided to reduce psychological stress as needed. The output is the recognized emotion data and actions based on it.

[0888] (Application example 2)

[0889] 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."

[0890] Conventional disaster response systems collect and analyze data in real time, predicting disasters, analyzing damage situations, and proposing rescue and recovery plans, but they do not adequately consider reducing the psychological burden on users. Furthermore, they lack the ability to provide customized information that takes into account people's emotional changes during a disaster, making it difficult for users to take appropriate action. This limits the effectiveness of disaster response and makes it difficult to prevent the damage from spreading.

[0891] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data in real time, means for analyzing the collected data and making disaster predictions, means for analyzing the damage situation, means for proposing an optimal response plan for rescue and recovery, means for providing necessary information, means for proposing an optimal travel route, means for recognizing the user's emotions in real time using an emotion recognition engine, and means for providing information customized based on the user's emotion data. This makes it possible to improve the efficiency and effectiveness of disaster response while reducing the psychological burden on the user.

[0892] "Means of collecting data in real time" refers to devices and methods that collect current information from sensors, external APIs, drones, satellites, etc.

[0893] "Means for analyzing collected data and making disaster predictions" refers to devices or methods that use AI models or algorithms based on acquired information to predict the possibility and scope of a disaster.

[0894] "Means for analyzing the damage situation" refers to devices and methods for assessing and analyzing the scope of impact and the extent of damage when a disaster occurs.

[0895] "Means for proposing optimal response plans for rescue and recovery" refers to devices and methods for creating plans to efficiently provide the types and quantities of supplies needed, deploy personnel, etc., based on the damage situation.

[0896] The "means for providing necessary information" refers to a device or method that visually or audibly provides the user with situation information and evacuation information that is updated in real time.

[0897] "Means for proposing optimal travel routes" refers to devices or methods that calculate and present the most suitable travel routes for evacuation, delivery of relief supplies, etc. based on damage status and traffic information.

[0898] "Means for recognizing a user's emotions in real time using an emotion recognition engine" refers to a device or method that analyzes image and audio data from a camera or microphone and determines the user's emotional state in real time.

[0899] "Means for providing information customized based on user emotional data" refers to a device or method that provides information adjusted to reduce the user's psychological burden based on recognized emotional data.

[0900] This invention is a system for reducing the psychological burden on users during disasters and realizing more effective countermeasures. The system provides comprehensive support to users by combining real-time data collection, analysis, disaster prediction, damage analysis, optimal response plan proposal, information provision, optimal travel route proposal, and an emotion engine that recognizes the user's emotions.

[0901] System Configuration

[0902] 1. Data Collection Module

[0903] The server collects real-time data from sensors, drones, satellites, and external APIs, including data from seismometers and weather sensors, image data from drones and satellites, and API data from meteorological agencies and traffic information services.

[0904] 2. Data storage module

[0905] The server stores the collected data in a database, which can manage both structured and unstructured data.

[0906] 3. Data Analysis Module

[0907] The server applies machine learning and AI models to the stored data to predict disasters and analyze damage situations, thereby predicting the epicenter and intensity of earthquakes and flood areas in the event of an earthquake.

[0908] 4. Aid Response Proposal Module

[0909] The server calculates the type, quantity, and priority of supplies needed based on the damage situation, and creates a personnel deployment plan, which is optimized based on data updated in real time.

[0910] 5. Information System

[0911] The server sends the latest information to the dashboard via API, which the device receives and displays visually, providing users with easy-to-understand, real-time updates and recommendations.

[0912] 6. Optimal Route Proposal Module

[0913] The server calculates optimal routes based on the latest traffic information, taking into account the extent of damage and traffic conditions, optimizing routes for delivering relief supplies and moving personnel.

[0914] 7. Emotion Engine

[0915] The server collects image and audio data from the camera and microphone and analyzes it using an emotion engine, which recognizes emotions (fear, stress, relief, etc.) from the user's facial expressions and tone of voice in real time.

[0916] Program processing explanation

[0917] Hardware: Cameras, microphones, and GPS sensors built into devices such as smartphones, tablets, and computers.

[0918] Software: The application is developed using Python and utilizes machine learning libraries (TensorFlow and PyTorch), and API communication involves HTTP requests and JSON data exchange.

[0919] Data processing and calculation: Data collected from sensors and external APIs is stored in a database and analyzed by machine learning models. The emotion engine analyzes data obtained from the camera and microphone to recognize the user's emotional state.

[0920] Example: When an earthquake occurs, the server immediately acquires and analyzes seismograph data and predicts the epicenter. The user's device uses a camera and microphone to analyze the user's emotions and presents a "safe evacuation route."

[0921] Example prompt sentence:

[0922] Analyze the video and audio data to recognize the user's current emotions. If the result is "high stress," generate a message saying, "According to the analysis results, the current situation has a low risk of disaster. However, please secure the optimal evacuation route just in case."

[0923] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0924] Step 1:

[0925] Real-time data collection

[0926] The server collects seismograph data, weather data, and traffic information in real time from sensors, drones, satellites, and external APIs. Specifically, it retrieves data from APIs using HTTP requests. The input is data streams from various sensors and APIs, which are received and stored in a database as structured and unstructured data. The output is the latest disaster-related data stored in the database.

[0927] Step 2:

[0928] Data storage

[0929] The server stores the collected data in a database. This database can be an RDBMS or NoSQL database. The input is sensor data or API data collected in real time, and the output is the stored data. Specific operations include data format conversion, normalization, and index creation.

[0930] Step 3:

[0931] Data analysis and disaster prediction

[0932] The server analyzes the stored data and uses AI models to make disaster predictions. The input is the latest disaster-related data stored in the database, and the output is a prediction of the likelihood of a disaster occurring and the damage it will cause. Specific operations include applying machine learning models and running prediction algorithms.

[0933] Step 4:

[0934] Analysis of the damage situation

[0935] The server analyzes the damage situation in real time after a disaster occurs. The input is the disaster prediction results and additional sensor data, and the output is the analysis results of the damage range and extent. Specific operations include image analysis, text analysis, and data aggregation.

[0936] Step 5:

[0937] Proposed relief and recovery plan

[0938] The server calculates the type, quantity, and priority of supplies needed based on the results of the damage analysis, and then creates a personnel deployment plan. The input is the results of the damage analysis and existing rescue resource data, and the output is a detailed rescue and recovery plan. The specific operation involves applying a resource optimization algorithm.

[0939] Step 6:

[0940] Providing information

[0941] The server sends the latest information to the dashboard API, which the device receives and visually displays. The input is disaster prediction results and rescue plans, and the output is real-time information displayed to the user. Specific operations include data format conversion and UI updates.

[0942] Step 7:

[0943] Proposing optimal travel routes

[0944] The server calculates the optimal travel route based on the latest traffic information and sends it to the terminal. The input is real-time traffic data and disaster information, and the output is a proposal for the optimal travel route. Specifically, the route calculation is performed using Dijkstra's algorithm or the A algorithm.

[0945] Step 8:

[0946] emotion recognition

[0947] The device collects image and audio data from the camera and microphone, and the server analyzes it using an emotion engine. The input is the image and audio data sent from the device, and the output is the recognition result of the user's emotional state (high stress, relief, etc.). Specific operations include applying facial expression recognition algorithms and voice analysis algorithms.

[0948] Step 9:

[0949] Customized information provision

[0950] Based on the recognized emotion data, the server sends customized information to the device to reduce the user's psychological burden. The input is the recognized emotion data and disaster information, and the output is a customized message or notification. For example, a message such as "According to the analysis results, the current situation has a low risk of disaster. However, please secure the optimal evacuation route just in case" may be generated.

[0951] 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.

[0952] 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.

[0953] 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.

[0954] [Third embodiment]

[0955] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0956] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0957] 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).

[0958] 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.

[0959] 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.

[0960] 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).

[0961] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0962] 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.

[0963] 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.

[0964] 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.

[0965] 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.

[0966] 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."

[0967] This invention relates to a system for implementing rapid and effective countermeasures in the event of a disaster, including the collection and analysis of real-time data, damage prediction, response plan proposal, information provision, and optimal travel route proposal. Specific embodiments for implementing the invention are described below.

[0968] System configuration

[0969] 1. Data Collection Module

[0970] The server collects data in real time from sensors, drones, satellites, external APIs, etc. For example, it uses data from seismometers and weather sensors, image data from drones and satellites, and API data from the Japan Meteorological Agency and traffic information services.

[0971] 2. Data storage module

[0972] The server stores the collected data in a database, which can handle both structured and unstructured data.

[0973] 3. Data Analysis Module

[0974] The server then performs analysis on the stored data, using AI algorithms to run disaster prediction and damage situation models, which can predict, for example, the epicenter and intensity of an earthquake, as well as areas susceptible to flooding.

[0975] 4. Aid Response Proposal Module

[0976] The server will create optimal aid and recovery plans based on the damage situation, for example, calculating the type, quantity and priority of supplies needed and creating a personnel deployment plan.

[0977] 5. Information System

[0978] The server sends the latest information to the dashboard API, which the device receives and visually displays, providing users with easy-to-understand, real-time updated data and recommendations.

[0979] 6. Optimal Route Proposal Module

[0980] The server calculates optimal routes based on the latest traffic information, taking into account the extent of damage and traffic conditions, and optimizes routes for delivering relief supplies and moving personnel.

[0981] Program processing explanation

[0982] Disaster prediction and damage analysis

[0983] The server stores data collected from sensors, drones, and satellites in a database. It then analyzes the stored data using AI algorithms and runs disaster prediction models. These models identify predicted earthquake centers and areas prone to flooding. The analysis results are stored in the database as they are processed and sent to devices via the dashboard API.

[0984] Aid response proposal

[0985] The server calculates the necessary relief supplies and personnel based on the damage information and generates an optimal relief plan. For example, it calculates the required amounts of food, water, medicine, etc. and plans the deployment of rescue teams. The generated relief plan is sent to the device via the dashboard API, where the user can confirm it.

[0986] Providing information

[0987] The server continuously updates the collected and analyzed data in real time and notifies the user of important information. For example, it sends push notifications in response to the expansion of the affected area or changes in traffic conditions. The device receives these notifications and displays them to the user, prompting them to take action as necessary.

[0988] Optimal route suggestions

[0989] The server calculates the optimal travel route based on traffic and damage information. The calculation uses Dijkstra's algorithm and A algorithm to calculate the shortest distance and fastest route. The calculation results are sent to the device, allowing the user to check the optimal route.

[0990] Specific examples

[0991] Example 1: Processing when an earthquake occurs

[0992] 1. The server receives earthquake data from the seismometer and stores it in a database.

[0993] 2. The server analyzes the stored data and runs models to predict the epicenter and intensity of the earthquake.

[0994] 3. The server sends the analysis results to the device via the dashboard API, and the device visually displays the prediction results.

[0995] 4. Users can check the damage situation and forecast information via their devices and take appropriate evacuation actions.

[0996] Example 2: Flood forecasting and response planning

[0997] 1. The server receives rainfall data from weather sensors and stores it in a database.

[0998] 2. The server analyzes the stored data and runs flood forecasting models, which identify areas that are likely to flood.

[0999] 3. The server calculates the necessary relief supplies based on the damage situation and generates the optimal relief plan.

[1000] 4. The terminal displays the support plan to the user, enabling them to quickly allocate the necessary resources.

[1001] In this way, this system enables rapid and effective response in the event of a disaster through the collection and analysis of real-time data.

[1002] The processing flow will be explained below.

[1003] Disaster prediction and damage analysis

[1004] Step 1:

[1005] The server receives information from sensors (seismometers, weather sensors), drones, satellite data, and external APIs.

[1006] Step 2:

[1007] The server stores the received data in a temporary memory, then normalizes the data and stores it in a database.

[1008] Step 3:

[1009] The server applies pre-trained AI models to the stored data to perform disaster predictions, such as predicting the epicenter and intensity of an earthquake, or the risk of flooding based on rainfall.

[1010] Step 4:

[1011] The server analyzes the prediction results to determine the extent of damage, and uses image analysis technology to process data from drones and satellites to assess the extent of damage to buildings.

[1012] Step 5:

[1013] The server stores the analysis results back in a database and notifies you of relevant information via email alerts and dashboard APIs.

[1014] Step 6:

[1015] The device receives data from the server and visually displays it on a dashboard, providing users with an easy-to-read view. Damage forecasts and response plans are highlighted on a map.

[1016] Processing of assistance response proposals

[1017] Step 1:

[1018] Based on the damage prediction results, the server evaluates the extent and distribution of the damage and calculates the necessary relief resources.

[1019] Step 2:

[1020] The server lists the required supplies (food, water, medicine, etc.) and personnel (emergency medical team, construction team) by type and calculates their quantities.

[1021] Step 3:

[1022] The server sets priorities for supplies and personnel and draws up plans for how much resource to allocate to each area.

[1023] Step 4:

[1024] The server generates a document with the optimal support and recovery plan and sends it to the device via the dashboard API.

[1025] Step 5:

[1026] The terminal receives the proposed assistance plan and visually displays it on the user interface, which the user can review and decide on specific actions to take.

[1027] Processing of information provided

[1028] Step 1:

[1029] The server collects new data in real time and continuously updates the database with the collected data.

[1030] Step 2:

[1031] When the server detects important updates (new disaster predictions, changes in the damage situation), it generates a push notification based on that information.

[1032] Step 3:

[1033] The device receives a push notification from the server and immediately alerts the user, providing a link to additional information if necessary.

[1034] Step 4:

[1035] Users can check the notifications and take necessary actions, such as checking evacuation locations or preparing to distribute relief supplies.

[1036] Processing optimal route suggestions

[1037] Step 1:

[1038] The server collects traffic and damage information in real time and stores it in a database.

[1039] Step 2:

[1040] The server runs an algorithm (such as Dijkstra's algorithm or A algorithm) to calculate the optimal travel route based on the latest data.

[1041] Step 3:

[1042] The server sends the calculated optimal route to the device via the dashboard API.

[1043] Step 4:

[1044] The terminal displays the optimal route information received from the server on a map, helping the user travel efficiently.

[1045] Step 5:

[1046] The user checks the presented route and gives instructions for the transportation of relief supplies and the movement of the rescue team.

[1047] Example 1

[1048] 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."

[1049] In modern society, rapid and accurate countermeasures are required when natural disasters occur. However, conventional systems have problems with insufficient real-time data collection and the time it takes to analyze the data, making it difficult to take prompt action. Furthermore, it is difficult to simultaneously solve multiple issues, such as assessing the damage situation, optimally distributing relief supplies, and proposing evacuation routes. This increases the risk of putting many lives and property at risk.

[1050] 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.

[1051] In this invention, the server includes means for collecting data in real time using sensors, unmanned aerial vehicles, satellites, and external APIs, means for storing the collected data in structured and unstructured databases, means for analyzing the stored data using an AI algorithm and running a disaster prediction model and a damage situation model, means for calculating relief supplies and personnel based on damage information and generating an optimal support plan, means for notifying users of important data and displaying the latest information through a dashboard API, and means for calculating optimal travel routes based on traffic and damage information and providing them to users, thereby enabling rapid and accurate disaster response.

[1052] A "sensor" is a device that measures environmental conditions or physical quantities and converts that information into an electrical signal.

[1053] An "unmanned aerial vehicle" is an aircraft that moves through the air by remote control or autonomous flight, collecting data and making observations.

[1054] A "satellite" is a spacecraft placed in orbit around the Earth that collects data such as meteorological observations and Earth remote sensing.

[1055] An "external API" is a programmatic interface for obtaining information from other systems or services.

[1056] A "database" is a system for efficiently storing, retrieving, and analyzing data. Both structured and unstructured databases exist.

[1057] An "AI algorithm" is a method of analyzing data using machine learning and data mining techniques to make predictions and classifications.

[1058] A "disaster prediction model" is a mathematical model for predicting the occurrence and impact of disasters based on collected data.

[1059] A "damage situation model" is a mathematical model used to analyze the scope and extent of damage when a disaster occurs.

[1060] A "support plan" is a specific proposal for optimally planning the types and quantities of relief supplies, the deployment of personnel, etc.

[1061] "Dashboard API" means a programmatic interface for visually displaying collected and analyzed data.

[1062] The "optimal route" is the most efficient travel route calculated based on traffic and damage information.

[1063] MODE FOR CARRYING OUT THE INVENTION

[1064] This invention is a system for realizing a rapid and effective response in the event of a disaster, and includes the collection and analysis of real-time data, damage prediction, response plan proposal, information provision, and optimal travel route proposal. Specific embodiments for implementing the invention are described below.

[1065] System configuration

[1066] Data collection

[1067] The server collects data in real time using sensors, drones, satellites, and external APIs. Specific examples include earthquake data from seismometers, weather data from weather sensors, image data from drones and satellites, and traffic data from traffic information APIs. All data is time-stamped, making it easier to analyze later.

[1068] Data storage

[1069] The server stores the collected data in structured and unstructured databases, using databases such as MySQL or MongoDB. For example, earthquake data is stored in a table called "seismic_data," and meteorological data is stored in a table called "weather_data."

[1070] Data analysis

[1071] The server uses AI algorithms to analyze the stored data. Specifically, it uses TensorFlow and other tools to run disaster prediction and damage situation models. This allows it to predict the epicenter and areas prone to flooding. The analysis results are stored in a new table called "prediction_results."

[1072] Aid response proposal

[1073] The server generates a relief plan based on the analysis results. Python is used to calculate the type and quantity of relief supplies and the deployment of personnel. The generated relief plan is converted into JSON format and sent to the device via the dashboard API. For example, the calculated relief plan may include information such as "Area A needs 500 sets of food, 100 liters of water, and five relief team members."

[1074] Providing information

[1075] The server notifies users of important information in real time based on the collected data and analysis results. For example, if it detects an expansion of the affected area or a change in traffic conditions, it sends a push notification to the device via the dashboard API. The device receives this and displays it as an alert to the user.

[1076] Optimal route suggestions

[1077] The server calculates the optimal travel route based on traffic and damage information. The algorithms used are Dijkstra's algorithm and A algorithm, which calculate the most efficient travel route. The calculation results are sent in JSON format to the device via the dashboard API, allowing the user to check the optimal route.

[1078] Specific examples

[1079] Example 1: Processing when an earthquake occurs

[1080] 1. The server receives earthquake data from the seismometer and stores it in a database.

[1081] 2. The server analyzes the stored data and runs models to predict the epicenter and intensity of the earthquake.

[1082] 3. The server sends the analysis results to the device via the dashboard API, and the device visually displays the prediction results.

[1083] 4. Users can check the damage situation and forecast information via their devices and take appropriate evacuation actions.

[1084] Example 2: Flood forecasting and response planning

[1085] 1. The server receives rainfall data from weather sensors and stores it in a database.

[1086] 2. The server analyzes the stored data and runs flood forecasting models, which identify areas that are likely to flood.

[1087] 3. The server calculates the necessary relief supplies based on the damage situation and generates the optimal relief plan.

[1088] 4. The terminal displays the support plan to the user, enabling them to quickly allocate the necessary resources.

[1089] Prompt Sentence Examples

[1090] "Please tell me the procedure for processing the damage prediction model in the event of an earthquake."

[1091] "Please give us some concrete examples of flood forecasts and response plans based on current rainfall data."

[1092] In this way, the present invention enables rapid and effective response in the event of a disaster through real-time data collection and analysis, enabling optimal measures to minimize damage and save lives.

[1093] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1094] Step 1: Data collection

[1095] The server collects data in real time using sensors, drones, satellites, and external APIs. For example, it acquires earthquake data from seismometers, weather data from weather sensors, image data from drones and satellites, and traffic data from traffic information APIs. The collected data is stored as a time-stamped log.

[1096] Inputs: Data from seismometers, weather sensors, drones, satellites, and external APIs

[1097] Output: Raw data log with timestamps

[1098] Specific operation:

[1099] Earthquake data is obtained from the seismometer every 10 seconds.

[1100] Traffic information updated every minute via API.

[1101] Step 2: Save data

[1102] The server stores the collected data in structured and unstructured databases, such as MySQL or MongoDB.

[1103] Input: Raw data log with timestamps

[1104] Output: Structured and unstructured data stored in a database

[1105] Specific operation:

[1106] Seismic data is stored using the SQL query "INSERT INTO seismic_data (timestamp, magnitude) VALUES (timestamp, magnitude)".

[1107] Weather data is stored using the SQL query "INSERT INTO weather_data (timestamp, temperature) VALUES (timestamp, temperature)".

[1108] Step 3: Data analysis

[1109] The server analyzes the stored data using AI algorithms, and runs disaster prediction models and damage situation models using TensorFlow and other tools.

[1110] Input: Structured and unstructured data stored in a database

[1111] Output: Analysis results (epicenter, seismic intensity, damage prediction area)

[1112] Specific operation:

[1113] TensorFlow is used to analyze earthquake data and predict the epicenter and intensity.

[1114] The analysis results are saved in a new table called "prediction_results".

[1115] Step 4: Propose an aid response

[1116] The server generates an aid plan based on the analysis results. It uses Python to calculate the type and quantity of needed relief supplies and personnel deployment. The generated aid plan is converted into JSON format and sent to the device via the dashboard API.

[1117] Input: Analysis results (epicenter, seismic intensity, predicted damage area)

[1118] Output: Support plan in JSON format

[1119] Specific operation:

[1120] Run a script to generate a support plan and calculate the required supplies and personnel allocation.

[1121] The generated support plan is saved as a "relief supplies JSON file."

[1122] Step 5: Provide information

[1123] The server notifies users of important information in real time based on the collected data and analysis results. Push notifications are sent to the device via the dashboard API, which receives them and displays them as alerts to the user.

[1124] Input: Important analytical results and newly collected data

[1125] Output: Push notification to the user

[1126] Specific operation:

[1127] If an expansion of the affected area or changes in traffic information are detected, a push notification will be generated.

[1128] Send notifications to devices via the Dashboard API.

[1129] Step 6: Optimal route proposal

[1130] The server calculates the optimal travel route based on traffic and damage information. The Dijkstra algorithm and A algorithm are used to calculate the most efficient travel route. The calculation results are sent in JSON format to the device via the dashboard API, allowing the user to check the optimal route.

[1131] Input: Traffic information, damage information

[1132] Output: Optimal route in JSON format

[1133] Specific operation:

[1134] Calculates the optimal route from the current location to the destination using Dijkstra's algorithm.

[1135] The calculation results are saved as an "optimal route JSON file" and sent to the device via the dashboard API.

[1136] (Application example 1)

[1137] 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."

[1138] Existing disaster prevention systems lack real-time data collection and analysis, making it difficult to develop rapid and effective response plans. They also lack the necessary information and optimal travel route suggestions required during a disaster, leaving users highly confused. Furthermore, notification functions on mobile devices such as smartphones are inadequate, making it difficult to provide important information immediately in an emergency.

[1139] 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.

[1140] In this invention, the server includes means for collecting data in real time, means for analyzing the collected data and making disaster predictions, means for analyzing the damage situation, means for proposing an optimal response plan for rescue and recovery, means for providing necessary information, means for proposing an optimal travel route, means for notifying the user using an application installed on the smartphone, and means for proposing assistance using data stored in the database. This enables a quick and effective response in the event of a disaster, and makes it possible to provide users with important information and optimal evacuation routes in real time.

[1141] "Real-time data collection means" refers to the system's ability to continuously acquire new data through sensors, drones, satellites, and external APIs.

[1142] "Means of analyzing collected data and making disaster predictions" refers to the system's function of using AI algorithms to predict the likelihood of disasters occurring and the extent of damage based on the acquired data.

[1143] "Means for analyzing the damage situation" refers to the system's function of using collected and analyzed data to assess the extent and severity of damage caused by a disaster.

[1144] "Means for proposing optimal response plans for rescue and recovery" refers to the system's function of planning the deployment of necessary supplies and personnel based on analyzed damage information, and determining the optimal means of assistance and recovery.

[1145] "Means of providing necessary information" refers to the system's functions for notifying users of important information in real time and encouraging appropriate action.

[1146] "Means for suggesting optimal travel routes" refers to the system's function of calculating the safest and quickest evacuation route based on traffic and damage information and presenting it to the user.

[1147] "Means of notifying users using an application installed on a smartphone" refers to a system function that notifies users of disaster information and evacuation routes in real time via an application.

[1148] "Means for proposing assistance responses using data stored in the database" refers to a system function that analyzes stored past and current data and proposes optimal assistance responses.

[1149] This invention is a system for providing rapid and effective countermeasures in the event of a disaster, and is implemented in the following steps.

[1150] Data collection

[1151] The server collects data in real time from sensors (such as seismometers and weather sensors), drones, satellites, and external APIs (such as the Japan Meteorological Agency and traffic information services). This allows for a constant accumulation of up-to-date information on earthquakes and weather. Specific hardware used includes seismometers, weather sensors, drones, and satellites. Software uses libraries (such as Requests) to access external APIs.

[1152] Data storage

[1153] The collected data is stored in a database by the server. Databases can handle both structured and unstructured data. Examples of databases used include SQLite and MySQL.

[1154] Data analysis

[1155] The server uses AI algorithms based on the stored data to perform disaster predictions. This analysis identifies, for example, the epicenter and intensity of an earthquake, as well as areas expected to be flooded. The AI ​​algorithms utilize machine learning libraries such as Scikit-learn and TensorFlow.

[1156] Damage analysis

[1157] The server evaluates the damage situation based on the analyzed data, allowing the extent of the disaster's impact and severity to be determined. The analysis results are stored in a database and updated as needed.

[1158] Aid response proposal

[1159] The server calculates the necessary relief supplies and personnel allocation based on damage information, and generates an optimal aid and recovery plan, which calculates the necessary amounts of food, water, medicine, etc., enabling the rapid deployment of rescue teams.

[1160] Providing information

[1161] The server notifies users of important information based on data collected and analyzed in real time. Information such as damage forecasts, assistance response plans, and optimal evacuation routes is provided via push notifications using an application installed on a smartphone. Notification services such as Firebase Cloud Messaging are used.

[1162] Optimal route suggestions

[1163] The server calculates the optimal travel route based on traffic and damage information. The calculation uses Dijkstra's algorithm and A algorithm to calculate the shortest distance and fastest route. The calculation results are sent to devices such as smartphones, allowing users to evacuate safely.

[1164] Specific examples

[1165] For example, when an earthquake occurs, the server receives earthquake data from a seismometer and predicts the epicenter and seismic intensity. Based on this information, the damage situation is analyzed and appropriate relief supplies and personnel deployment plans are made. Ultimately, the epicenter, seismic intensity, and evacuation routes are notified to the user's smartphone. As another example, in flood prediction, rainfall data is collected and areas with a high probability of flooding are identified. This makes it possible to quickly deliver necessary relief supplies to areas where disasters are predicted.

[1166] Prompt Sentence Examples

[1167] "Based on the latest earthquake and meteorological data, please estimate the epicenter and damage, and suggest evacuation routes."

[1168] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1169] Step 1: Data collection

[1170] The server collects real-time data from seismometers, weather sensors, drones, satellites, and external APIs. Input data includes earthquake data, meteorological data, and image data. The server obtains the latest data from each data source and passes it on to the next processing step. This allows the latest disaster information to be collected at all times.

[1171] Step 2: Save data

[1172] The server stores the collected data in a database. The input data is earthquake and weather data collected in real time, and is stored in the database as structured or unstructured data. This data is efficiently managed using a database management system such as SQLite or MySQL.

[1173] Step 3: Data analysis

[1174] The server uses AI algorithms based on the stored data to make disaster predictions. The input data is stored earthquake and weather data. The AI ​​algorithm analyzes the earthquake's epicenter, seismic intensity, predicted flood areas, etc., and outputs the results. Machine learning libraries such as Scikit-learn and TensorFlow are used here.

[1175] Step 4: Damage analysis

[1176] The server assesses the damage situation based on the analyzed data. The input data is the analysis results. The impact scope and severity of the disaster are assessed, and the damage situation is understood in detail. This information is used to plan the next aid response.

[1177] Step 5: Propose an aid response

[1178] The server creates optimal rescue and recovery plans based on the damage situation. The input data is a detailed description of the damage situation, and it calculates the necessary supplies and personnel to generate an optimal support plan. This determines the required amounts of supplies such as food, water, and medicine, as well as the deployment of rescue teams.

[1179] Step 6: Provide information

[1180] The server provides users with important information in real time. The input data is assistance response plans and damage situation information, and the information is sent to users via an application installed on their smartphone. Push notification services such as Firebase Cloud Messaging are used to prompt users to take appropriate action.

[1181] Step 7: Optimal route proposal

[1182] The server calculates the optimal travel route based on traffic and damage information. The input data is real-time traffic and damage information, and the shortest distance and fastest route are calculated using Dijkstra's algorithm and A algorithm. The results are sent to the user's smartphone, helping them evacuate safely.

[1183] Step 8: User's appropriate evacuation behavior

[1184] The user takes appropriate evacuation action based on the information received on their smartphone. The input data is a notification sent from the server, and the user confirms it and follows the indicated evacuation route. This allows the user to evacuate quickly and safely.

[1185] 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.

[1186] This invention relates to a system that reduces the psychological burden on users during disasters and realizes more effective countermeasures by combining real-time data collection, analysis, damage prediction, response plan proposals, information provision, and optimal travel route proposals with an emotion engine that recognizes the user's emotions. Specific embodiments for implementing this invention are described below.

[1187] System configuration

[1188] 1. Data Collection Module

[1189] The server collects data in real time from sensors, drones, satellites, and external APIs. Specifically, it uses data from seismometers and weather sensors, image data from drones and satellites, and API data from the Japan Meteorological Agency and traffic information services.

[1190] 2. Data storage module

[1191] The server stores the collected data in a database, which can handle both structured and unstructured data.

[1192] 3. Data Analysis Module

[1193] The server applies AI models to the stored data to predict disasters and analyze damage situations, for example, predicting the epicenter and seismic intensity of an earthquake and areas susceptible to flooding.

[1194] 4. Aid Response Proposal Module

[1195] Based on the damage situation, the server calculates the type, quantity, and priority of supplies needed and draws up a personnel deployment plan.

[1196] 5. Information System

[1197] The server sends the latest information to the dashboard API, which the device receives and visually displays, providing users with easy-to-understand, real-time updated data and recommendations.

[1198] 6. Optimal Route Proposal Module

[1199] The server calculates optimal routes based on the latest traffic information, taking into account the extent of damage and traffic conditions, and optimizes routes for delivering relief supplies and moving personnel.

[1200] 7. Emotion Engine

[1201] The server uses an emotion engine to recognize the user's emotions in real time. Emotion data is collected and analyzed from cameras and microphones.

[1202] Program processing explanation

[1203] User Emotion Recognition

[1204] The server collects image and audio data from the camera and microphone connected to the device.

[1205] The server uses an emotion engine to analyze the collected data and recognize emotions (fear, stress, relief, etc.) from the user's facial expressions and voice tone.

[1206] The server stores the recognized emotion data in a database and triggers actions as needed.

[1207] Customized information provision

[1208] The server analyzes the user's stress and anxiety levels based on the emotional data. For example, if the user is in a high-stress state, it provides reassuring notifications and evacuation information.

[1209] The server sends the analysis results to the dashboard API, which the device receives and displays in real time, along with reassuring messages and alerts.

[1210] Reflecting priorities

[1211] The server then uses the emotional data to prioritize rescue and recovery plans, for example by quickly dispatching relief supplies and rescue teams to areas with a high number of users experiencing high levels of stress.

[1212] The server reconstructs the support plan based on the priority and allocates resources optimally.

[1213] Specific examples

[1214] Example 1: Processing when an earthquake occurs

[1215] 1. The server receives earthquake data from the seismometer and stores it in a database.

[1216] 2. The server analyzes the stored data and predicts the epicenter and intensity of the earthquake.

[1217] 3. The server collects the user's emotional data from the device's camera and microphone and analyzes it using an emotion engine.

[1218] 4. The server identifies areas with a high number of users experiencing high stress and develops a plan to quickly send relief supplies to those areas.

[1219] Example 2: Flood forecasting and response planning

[1220] 1. The server receives rainfall data from weather sensors and stores it in a database.

[1221] 2. The server analyzes the rainfall data and runs flood forecasting models, which identify areas that are likely to flood.

[1222] 3. The server calculates the necessary relief supplies based on the damage situation and generates the optimal relief plan.

[1223] 4. The server analyzes the user's emotional state and provides priority support to areas with a high number of users in high stress states.

[1224] 5. The terminal displays the support plan to the user, enabling them to quickly allocate the necessary resources.

[1225] In this way, by combining emotion engines, it is possible to reduce the psychological burden on users and enable more effective responses in the event of a disaster.

[1226] The processing flow will be explained below.

[1227] User emotion recognition processing

[1228] Step 1:

[1229] The terminal activates the camera and microphone on the device operated by the user.

[1230] Step 2:

[1231] The device captures a picture of the user's face with a camera and collects audio data with a microphone.

[1232] Step 3:

[1233] The terminal transmits the acquired image data and audio data to the server in real time.

[1234] Step 4:

[1235] The server inputs the received data into the emotion engine and analyzes the user's facial expressions and voice.

[1236] Step 5:

[1237] The server stores the analysis results of the emotion engine in a database and records the user's emotional state in real time.

[1238] Processing of customized communications

[1239] Step 1:

[1240] The server uses the analysis results from the emotion engine to evaluate the user's level of stress and anxiety.

[1241] Step 2:

[1242] The server selects appropriate information based on the evaluation results. For example, if a high stress state is detected, it will provide a reassuring message or evacuation information.

[1243] Step 3:

[1244] The server sends the selected information to the terminal via the dashboard API.

[1245] Step 4:

[1246] The device visually displays the received information to the user, encouraging safe behavior, and can also play audible messages to reduce stress.

[1247] Priority reflection processing

[1248] Step 1:

[1249] The server analyzes the damage situation information, including the emotion data, stored in the database.

[1250] Step 2:

[1251] Based on the emotional data, the server assesses the level of stress and anxiety in each affected area and sets priorities.

[1252] Step 3:

[1253] The server reconstructs the allocation plan for relief supplies and personnel based on priorities, and prioritizes areas where high stress levels are detected.

[1254] Step 4:

[1255] The server sends the recalculated support plan to the device via the dashboard API.

[1256] Step 5:

[1257] The device will display the new plan to the user and provide instructions on how to receive relief supplies and guidelines for action.

[1258] Specific examples

[1259] Example 1: Processing when an earthquake occurs

[1260] Step 1:

[1261] The server receives earthquake data from the seismometer and stores it in a database.

[1262] Step 2:

[1263] The server analyzes earthquake data and predicts the epicenter and intensity of the earthquake.

[1264] Step 3:

[1265] The device activates the camera and microphone and transmits the user's facial expressions and voice to the server in real time.

[1266] Step 4:

[1267] The server uses an emotion engine to analyze the user's emotional state.

[1268] Step 5:

[1269] The server identifies areas with a large number of users experiencing high stress levels and develops a plan to prioritize sending relief supplies to those areas.

[1270] Step 6:

[1271] The server sends the plan to the device via the dashboard API, and the device provides the information to the user.

[1272] Example 2: Flood forecasting and response planning

[1273] Step 1:

[1274] The server receives rainfall data from weather sensors and stores it in a database.

[1275] Step 2:

[1276] The server analyzes rainfall data and runs flood forecasting models.

[1277] Step 3:

[1278] The server identifies areas that are likely to be flooded and predicts damage.

[1279] Step 4:

[1280] The device activates the camera and microphone to collect the user's emotional data and send it to the server.

[1281] Step 5:

[1282] The server analyzes the emotional data and identifies areas where there are many users with high stress levels.

[1283] Step 6:

[1284] The server calculates the necessary relief supplies based on the priority and generates the optimal relief plan.

[1285] Step 7:

[1286] The server sends the support plan to the device via the dashboard API, and the device visually displays it to the user.

[1287] In this way, the system of the present invention combines real-time data collection, analysis, and user emotion recognition to enable rapid and effective responses in the event of a disaster and reduce the psychological burden on users.

[1288] Example 2

[1289] 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."

[1290] With the increasing frequency of natural disasters, there is a need for real-time data collection and analysis, damage analysis, and optimal response plans. However, conventional systems lacked functionality to address the psychological burden placed on users, making it difficult to maintain psychological stability during disasters. Furthermore, they were also inadequate in formulating quick and effective support plans based on collected data and proposing optimal travel routes.

[1291] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1292] In this invention, the server includes means for collecting data in real time, means for saving the collected data, means for analyzing the saved data and making disaster predictions, means for analyzing the damage situation, means for collecting and analyzing user emotion data, means for providing information for reducing psychological burden based on the collected emotion data, means for proposing an optimal response plan for rescue and recovery, means for providing necessary information, and means for proposing an optimal travel route. This enables effective disaster response in real time, and makes it possible to propose optimal support plans and travel routes while reducing the psychological burden on users.

[1293] "Means for collecting data in real time" refers to devices or systems that acquire disaster and environmental data in real time using sensors, unmanned aerial vehicles, satellites, external APIs, etc.

[1294] "Means for storing collected data" refers to a database or storage system for temporarily or permanently storing acquired data.

[1295] "Means for analyzing stored data and making disaster predictions" refers to a system that analyzes stored data and uses algorithms and AI models to predict the occurrence of earthquakes, floods, and other disasters in advance.

[1296] "Means for analyzing the damage situation" refers to a system that analyzes the scale and extent of the damage after a disaster occurs, and determines the exact extent of the damage.

[1297] The "means for collecting and analyzing user emotional data" refers to a system that uses devices such as a camera and microphone to collect the user's facial expressions and tone of voice, and analyzes them using an emotion recognition engine.

[1298] The "means for providing information that reduces psychological burden based on collected emotional data" is a system that provides notifications and evacuation information that give users a sense of security based on analyzed emotional data.

[1299] The "means of proposing optimal response plans for rescue and recovery" is a system that draws up plans for the allocation of damage, necessary supplies, and personnel, and provides optimal support and recovery methods.

[1300] "Means for providing necessary information" refers to a system that provides users with breaking news and updated information via a dashboard or the like.

[1301] The "means for proposing optimal travel routes" is a system that calculates and proposes optimal travel routes for relief supplies and personnel based on traffic and damage information.

[1302] This invention is realized by combining the following elements in the system: The roles of the server, terminal, and user are specifically shown, and the corresponding hardware and software configurations, data processing, and data calculations are explained in detail.

[1303] System Overview

[1304] This system collects data in real time, analyzes it, predicts damage, proposes optimal response plans, provides information, and recognizes emotions, enabling effective responses in the event of a disaster. In particular, it is equipped with an emotion recognition function to reduce the psychological burden on users.

[1305] Data collection

[1306] The server uses sensors (seismometers, weather sensors), unmanned aerial vehicles, satellites, external APIs, etc. to collect earthquake data, rainfall data, image data, weather data, traffic information, etc. in real time. Specific devices used include seismometers (e.g., Seismometer-X100), weather sensors (e.g., WeatherSensor-Y200), and unmanned aerial vehicles (e.g., DJI Phantom 4). Data is obtained using APIs from the Japan Meteorological Agency and traffic information providers.

[1307] Data storage

[1308] The server stores the collected data in a database. Structured data (e.g., numerical data) is stored in a relational database (e.g., MySQL), and unstructured data (e.g., image data) is stored in a non-relational database (e.g., MongoDB). A timestamp is assigned to each entry of the data, and it is managed to make it easy to search and analyze.

[1309] Data analysis

[1310] The server analyzes the stored data using AI models (e.g., TensorFlow, PyTorch) to predict disasters such as earthquakes and floods. The analysis results are stored in a database and used to develop subsequent response plans.

[1311] Damage response proposals

[1312] The server calculates the type, quantity, and priority of needed relief supplies based on disaster prediction and damage data. It also creates a personnel deployment plan and formulates optimal relief and recovery plans. In this process, the results of the AI ​​model's calculations are utilized to enable a fast and efficient response.

[1313] Providing information

[1314] The server sends the latest analysis results and support plans to a dashboard API (e.g., Grafana, Tableau), which then receives and displays the information on the device. Users can visually check the information updated in real time through their device.

[1315] Optimal route suggestions

[1316] The server uses the Google Maps API to calculate the optimal route based on the collected traffic information. The calculation results are sent to the dashboard API, which is then received and displayed on the device. This allows for the efficient movement of relief supplies and personnel.

[1317] emotion recognition

[1318] The server analyzes the user's image and voice data collected from the device's connected camera (e.g., Logitech C920) and microphone (e.g., Blue Yeti) in real time using an emotion engine (e.g., Affectiva, Microsoft Azure Emotion API). The analyzed emotion data is stored in a database, and information is provided to reduce psychological stress as needed.

[1319] Specific examples

[1320] Example 1: Processing when an earthquake occurs

[1321] 1. The server receives earthquake data from a seismometer (e.g., Seismometer-X100) and stores it in a database.

[1322] 2. The server analyzes the earthquake data and predicts the epicenter and intensity of the earthquake.

[1323] 3. The server analyzes the emotional data collected from the device's camera and microphone and identifies areas with a high number of users experiencing high levels of stress.

[1324] 4. The server will develop a plan to quickly send relief supplies to the identified area.

[1325] 5. The device receives the assistance plan and visually displays it to the user.

[1326] Prompt for the generative AI model in this example:

[1327] "Generate a scenario for the next earthquake. Explain in detail how you would predict damage based on data collected from sensors and how you would collect and analyze user emotion data. Then, describe the steps to propose an optimal assistance plan."

[1328] Example 2: Flood forecasting and response planning

[1329] 1. The server receives rainfall data from a weather sensor (e.g., WeatherSensor-Y200) and stores it in a database.

[1330] 2. The server analyzes the rainfall data and runs flood forecasting models.

[1331] 3. The server identifies areas at high risk of flooding and calculates the amount of relief supplies needed.

[1332] 4. The server creates a support plan and prioritizes sending support to areas with a large number of users in high stress.

[1333] 5. The device receives the support plan and displays it to the user.

[1334] Prompt for the generative AI model in this example:

[1335] "Generate the following flood scenario. Explain in detail how you would use data collected from sensors to perform flood predictions, identify damage, and collect and analyze user sentiment data. Then, detail the steps to propose an optimal assistance plan."

[1336] In this way, the system executes each processing step in detail, realizing effective disaster response while reducing the psychological burden on the user.

[1337] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1338] Step 1: Data collection

[1339] The server collects various data in real time using sensors, unmanned aerial vehicles, satellites, external APIs, etc. Specifically, it obtains earthquake data from seismometers (e.g., Seismometer-X100), rainfall data from weather sensors (e.g., WeatherSensor-Y200), and image data from unmanned aerial vehicles (e.g., DJI Phantom 4). It also obtains the latest weather and traffic information from the APIs of the Japan Meteorological Agency and traffic information services. The server receives input data from each device and API and converts it into a format that can be used in the next step.

[1340] Step 2: Save data

[1341] The server stores the collected data in a database. The input is various data collected in real time, which the server stores as structured data (e.g., numerical data stored in MySQL) and unstructured data (e.g., image data stored in MongoDB). Each piece of data is assigned a timestamp and managed to make it easy to search and analyze. The output is the various saved data stored in the database.

[1342] Step 3: Data analysis

[1343] The server inputs the stored data into an AI model (e.g., TensorFlow, PyTorch) for analysis. The inputs include stored earthquake data, meteorological data, and image data, and the server analyzes these to predict earthquakes and floods. Specifically, it predicts the epicenter and seismic intensity from the earthquake data, and identifies flood risk areas from the meteorological data. The analysis results are output and stored in a database for use in the next step.

[1344] Step 4: Damage response proposal

[1345] The server calculates the type, quantity, and priority of the necessary relief supplies based on the disaster prediction data obtained as a result of the analysis. The inputs are the disaster prediction data and collected damage situation data, and the server uses this to formulate a relief plan. Specifically, it uses an AI model to create optimal personnel deployment plans and supply distribution plans. The output is an optimal relief and recovery plan.

[1346] Step 5: Provide information

[1347] The server sends the latest analysis results and support plans to a dashboard API (e.g., Grafana, Tableau), and the terminal receives and displays the information. The input includes analysis results and support plan data, which the server sends to the terminal via the dashboard API. The terminal receives this information and displays it visually to the user. As an output, the user can view information that is updated in real time.

[1348] Step 6: Optimal route proposal

[1349] The server uses the Google Maps API to calculate the optimal travel route based on the collected traffic information. The server inputs the latest traffic and damage information into a route calculation algorithm. The calculation results are sent to the dashboard API and received and displayed on the device. The output is optimal travel route information, enabling the efficient movement of relief supplies and personnel.

[1350] Step 7: Emotion Recognition

[1351] The server uses an emotion engine (e.g., Affectiva, Microsoft Azure Emotion API) to analyze in real time the user's image and voice data collected from the camera (e.g., Logitech C920) or microphone (e.g., Blue Yeti) connected to the device. The input is the collected image and voice data, which the server analyzes to recognize the user's emotions (fear, stress, relief, etc.). The analysis results are stored in a database, and notifications or evacuation information are provided to reduce psychological stress as needed. The output is the recognized emotion data and actions based on it.

[1352] (Application example 2)

[1353] 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."

[1354] Conventional disaster response systems collect and analyze data in real time, predicting disasters, analyzing damage situations, and proposing rescue and recovery plans, but they do not adequately consider reducing the psychological burden on users. Furthermore, they lack the ability to provide customized information that takes into account people's emotional changes during a disaster, making it difficult for users to take appropriate action. This limits the effectiveness of disaster response and makes it difficult to prevent the damage from spreading.

[1355] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data in real time, means for analyzing the collected data and making disaster predictions, means for analyzing the damage situation, means for proposing an optimal response plan for rescue and recovery, means for providing necessary information, means for proposing an optimal travel route, means for recognizing the user's emotions in real time using an emotion recognition engine, and means for providing information customized based on the user's emotion data. This makes it possible to improve the efficiency and effectiveness of disaster response while reducing the psychological burden on the user.

[1356] "Means of collecting data in real time" refers to devices and methods that collect current information from sensors, external APIs, drones, satellites, etc.

[1357] "Means for analyzing collected data and making disaster predictions" refers to devices or methods that use AI models or algorithms based on acquired information to predict the possibility and scope of a disaster.

[1358] "Means for analyzing the damage situation" refers to devices and methods for assessing and analyzing the scope of impact and the extent of damage when a disaster occurs.

[1359] "Means for proposing optimal response plans for rescue and recovery" refers to devices and methods for creating plans to efficiently provide the types and quantities of supplies needed, deploy personnel, etc., based on the damage situation.

[1360] The "means for providing necessary information" refers to a device or method that visually or audibly provides the user with situation information and evacuation information that is updated in real time.

[1361] "Means for proposing optimal travel routes" refers to devices or methods that calculate and present the most suitable travel routes for evacuation, delivery of relief supplies, etc. based on damage status and traffic information.

[1362] "Means for recognizing a user's emotions in real time using an emotion recognition engine" refers to a device or method that analyzes image and audio data from a camera or microphone and determines the user's emotional state in real time.

[1363] "Means for providing information customized based on user emotional data" refers to a device or method that provides information adjusted to reduce the user's psychological burden based on recognized emotional data.

[1364] This invention is a system for reducing the psychological burden on users during disasters and realizing more effective countermeasures. The system provides comprehensive support to users by combining real-time data collection, analysis, disaster prediction, damage analysis, optimal response plan proposal, information provision, optimal travel route proposal, and an emotion engine that recognizes the user's emotions.

[1365] System Configuration

[1366] 1. Data Collection Module

[1367] The server collects real-time data from sensors, drones, satellites, and external APIs, including data from seismometers and weather sensors, image data from drones and satellites, and API data from meteorological agencies and traffic information services.

[1368] 2. Data storage module

[1369] The server stores the collected data in a database, which can manage both structured and unstructured data.

[1370] 3. Data Analysis Module

[1371] The server applies machine learning and AI models to the stored data to predict disasters and analyze damage situations, thereby predicting the epicenter and intensity of earthquakes and flood areas in the event of an earthquake.

[1372] 4. Aid Response Proposal Module

[1373] The server calculates the type, quantity, and priority of supplies needed based on the damage situation, and creates a personnel deployment plan, which is optimized based on data updated in real time.

[1374] 5. Information System

[1375] The server sends the latest information to the dashboard via API, which the device receives and displays visually, providing users with easy-to-understand, real-time updates and recommendations.

[1376] 6. Optimal Route Proposal Module

[1377] The server calculates optimal routes based on the latest traffic information, taking into account the extent of damage and traffic conditions, optimizing routes for delivering relief supplies and moving personnel.

[1378] 7. Emotion Engine

[1379] The server collects image and audio data from the camera and microphone and analyzes it using an emotion engine, which recognizes emotions (fear, stress, relief, etc.) from the user's facial expressions and tone of voice in real time.

[1380] Program processing explanation

[1381] Hardware: Cameras, microphones, and GPS sensors built into devices such as smartphones, tablets, and computers.

[1382] Software: The application is developed using Python and utilizes machine learning libraries (TensorFlow and PyTorch), and API communication involves HTTP requests and JSON data exchange.

[1383] Data processing and calculation: Data collected from sensors and external APIs is stored in a database and analyzed by machine learning models. The emotion engine analyzes data obtained from the camera and microphone to recognize the user's emotional state.

[1384] Example: When an earthquake occurs, the server immediately acquires and analyzes seismograph data and predicts the epicenter. The user's device uses a camera and microphone to analyze the user's emotions and presents a "safe evacuation route."

[1385] Example prompt sentence:

[1386] Analyze the video and audio data to recognize the user's current emotions. If the result is "high stress," generate a message saying, "According to the analysis results, the current situation has a low risk of disaster. However, please secure the optimal evacuation route just in case."

[1387] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1388] Step 1:

[1389] Real-time data collection

[1390] The server collects seismograph data, weather data, and traffic information in real time from sensors, drones, satellites, and external APIs. Specifically, it retrieves data from APIs using HTTP requests. The input is data streams from various sensors and APIs, which are received and stored in a database as structured and unstructured data. The output is the latest disaster-related data stored in the database.

[1391] Step 2:

[1392] Data storage

[1393] The server stores the collected data in a database. This database can be an RDBMS or NoSQL database. The input is sensor data or API data collected in real time, and the output is the stored data. Specific operations include data format conversion, normalization, and index creation.

[1394] Step 3:

[1395] Data analysis and disaster prediction

[1396] The server analyzes the stored data and uses AI models to make disaster predictions. The input is the latest disaster-related data stored in the database, and the output is a prediction of the likelihood of a disaster occurring and the damage it will cause. Specific operations include applying machine learning models and running prediction algorithms.

[1397] Step 4:

[1398] Analysis of the damage situation

[1399] The server analyzes the damage situation in real time after a disaster occurs. The input is the disaster prediction results and additional sensor data, and the output is the analysis results of the damage range and extent. Specific operations include image analysis, text analysis, and data aggregation.

[1400] Step 5:

[1401] Proposed relief and recovery plan

[1402] The server calculates the type, quantity, and priority of supplies needed based on the results of the damage analysis, and then creates a personnel deployment plan. The input is the results of the damage analysis and existing rescue resource data, and the output is a detailed rescue and recovery plan. The specific operation involves applying a resource optimization algorithm.

[1403] Step 6:

[1404] Providing information

[1405] The server sends the latest information to the dashboard API, which the device receives and visually displays. The input is disaster prediction results and rescue plans, and the output is real-time information displayed to the user. Specific operations include data format conversion and UI updates.

[1406] Step 7:

[1407] Proposing optimal travel routes

[1408] The server calculates the optimal travel route based on the latest traffic information and sends it to the terminal. The input is real-time traffic data and disaster information, and the output is a proposal for the optimal travel route. Specifically, the route calculation is performed using Dijkstra's algorithm or the A algorithm.

[1409] Step 8:

[1410] emotion recognition

[1411] The device collects image and audio data from the camera and microphone, and the server analyzes it using an emotion engine. The input is the image and audio data sent from the device, and the output is the recognition result of the user's emotional state (high stress, relief, etc.). Specific operations include applying facial expression recognition algorithms and voice analysis algorithms.

[1412] Step 9:

[1413] Customized information provision

[1414] Based on the recognized emotion data, the server sends customized information to the device to reduce the user's psychological burden. The input is the recognized emotion data and disaster information, and the output is a customized message or notification. For example, a message such as "According to the analysis results, the current situation has a low risk of disaster. However, please secure the optimal evacuation route just in case" may be generated.

[1415] 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.

[1416] 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.

[1417] 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.

[1418] [Fourth embodiment]

[1419] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1420] 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.

[1421] 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).

[1422] 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.

[1423] 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.

[1424] 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).

[1425] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1426] 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.

[1427] 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.

[1428] 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.

[1429] 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.

[1430] 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.

[1431] 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."

[1432] This invention relates to a system for implementing rapid and effective countermeasures in the event of a disaster, including the collection and analysis of real-time data, damage prediction, response plan proposal, information provision, and optimal travel route proposal. Specific embodiments for implementing the invention are described below.

[1433] System configuration

[1434] 1. Data Collection Module

[1435] The server collects data in real time from sensors, drones, satellites, external APIs, etc. For example, it uses data from seismometers and weather sensors, image data from drones and satellites, and API data from the Japan Meteorological Agency and traffic information services.

[1436] 2. Data storage module

[1437] The server stores the collected data in a database, which can handle both structured and unstructured data.

[1438] 3. Data Analysis Module

[1439] The server then performs analysis on the stored data, using AI algorithms to run disaster prediction and damage situation models, which can predict, for example, the epicenter and intensity of an earthquake, as well as areas susceptible to flooding.

[1440] 4. Aid Response Proposal Module

[1441] The server will create optimal aid and recovery plans based on the damage situation, for example, calculating the type, quantity and priority of supplies needed and creating a personnel deployment plan.

[1442] 5. Information System

[1443] The server sends the latest information to the dashboard API, which the device receives and visually displays, providing users with easy-to-understand, real-time updated data and recommendations.

[1444] 6. Optimal Route Proposal Module

[1445] The server calculates optimal routes based on the latest traffic information, taking into account the extent of damage and traffic conditions, and optimizes routes for delivering relief supplies and moving personnel.

[1446] Program processing explanation

[1447] Disaster prediction and damage analysis

[1448] The server stores data collected from sensors, drones, and satellites in a database. It then analyzes the stored data using AI algorithms and runs disaster prediction models. These models identify predicted earthquake centers and areas prone to flooding. The analysis results are stored in the database as they are processed and sent to devices via the dashboard API.

[1449] Aid response proposal

[1450] The server calculates the necessary relief supplies and personnel based on the damage information and generates an optimal relief plan. For example, it calculates the required amounts of food, water, medicine, etc. and plans the deployment of rescue teams. The generated relief plan is sent to the device via the dashboard API, where the user can confirm it.

[1451] Providing information

[1452] The server continuously updates the collected and analyzed data in real time and notifies the user of important information. For example, it sends push notifications in response to the expansion of the affected area or changes in traffic conditions. The device receives these notifications and displays them to the user, prompting them to take action as necessary.

[1453] Optimal route suggestions

[1454] The server calculates the optimal travel route based on traffic and damage information. The calculation uses Dijkstra's algorithm and A algorithm to calculate the shortest distance and fastest route. The calculation results are sent to the device, allowing the user to check the optimal route.

[1455] Specific examples

[1456] Example 1: Processing when an earthquake occurs

[1457] 1. The server receives earthquake data from the seismometer and stores it in a database.

[1458] 2. The server analyzes the stored data and runs models to predict the epicenter and intensity of the earthquake.

[1459] 3. The server sends the analysis results to the device via the dashboard API, and the device visually displays the prediction results.

[1460] 4. Users can check the damage situation and forecast information via their devices and take appropriate evacuation actions.

[1461] Example 2: Flood forecasting and response planning

[1462] 1. The server receives rainfall data from weather sensors and stores it in a database.

[1463] 2. The server analyzes the stored data and runs flood forecasting models, which identify areas that are likely to flood.

[1464] 3. The server calculates the necessary relief supplies based on the damage situation and generates the optimal relief plan.

[1465] 4. The terminal displays the support plan to the user, enabling them to quickly allocate the necessary resources.

[1466] In this way, this system enables rapid and effective response in the event of a disaster through the collection and analysis of real-time data.

[1467] The processing flow will be explained below.

[1468] Disaster prediction and damage analysis

[1469] Step 1:

[1470] The server receives information from sensors (seismometers, weather sensors), drones, satellite data, and external APIs.

[1471] Step 2:

[1472] The server stores the received data in a temporary memory, then normalizes the data and stores it in a database.

[1473] Step 3:

[1474] The server applies pre-trained AI models to the stored data to perform disaster predictions, such as predicting the epicenter and intensity of an earthquake, or the risk of flooding based on rainfall.

[1475] Step 4:

[1476] The server analyzes the prediction results to determine the extent of damage, and uses image analysis technology to process data from drones and satellites to assess the extent of damage to buildings.

[1477] Step 5:

[1478] The server stores the analysis results back in a database and notifies you of relevant information via email alerts and dashboard APIs.

[1479] Step 6:

[1480] The device receives data from the server and visually displays it on a dashboard, providing users with an easy-to-read view. Damage forecasts and response plans are highlighted on a map.

[1481] Processing of assistance response proposals

[1482] Step 1:

[1483] Based on the damage prediction results, the server evaluates the extent and distribution of the damage and calculates the necessary relief resources.

[1484] Step 2:

[1485] The server lists the required supplies (food, water, medicine, etc.) and personnel (emergency medical team, construction team) by type and calculates their quantities.

[1486] Step 3:

[1487] The server sets priorities for supplies and personnel and draws up plans for how much resource to allocate to each area.

[1488] Step 4:

[1489] The server generates a document with the optimal support and recovery plan and sends it to the device via the dashboard API.

[1490] Step 5:

[1491] The terminal receives the proposed assistance plan and visually displays it on the user interface, which the user can review and decide on specific actions to take.

[1492] Processing of information provided

[1493] Step 1:

[1494] The server collects new data in real time and continuously updates the database with the collected data.

[1495] Step 2:

[1496] When the server detects important updates (new disaster predictions, changes in the damage situation), it generates a push notification based on that information.

[1497] Step 3:

[1498] The device receives a push notification from the server and immediately alerts the user, providing a link to additional information if necessary.

[1499] Step 4:

[1500] Users can check the notifications and take necessary actions, such as checking evacuation locations or preparing to distribute relief supplies.

[1501] Processing optimal route suggestions

[1502] Step 1:

[1503] The server collects traffic and damage information in real time and stores it in a database.

[1504] Step 2:

[1505] The server runs an algorithm (such as Dijkstra's algorithm or A algorithm) to calculate the optimal travel route based on the latest data.

[1506] Step 3:

[1507] The server sends the calculated optimal route to the device via the dashboard API.

[1508] Step 4:

[1509] The terminal displays the optimal route information received from the server on a map, helping the user travel efficiently.

[1510] Step 5:

[1511] The user checks the presented route and gives instructions for the transportation of relief supplies and the movement of the rescue team.

[1512] Example 1

[1513] 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."

[1514] In modern society, rapid and accurate countermeasures are required when natural disasters occur. However, conventional systems have problems with insufficient real-time data collection and the time it takes to analyze the data, making it difficult to take prompt action. Furthermore, it is difficult to simultaneously solve multiple issues, such as assessing the damage situation, optimally distributing relief supplies, and proposing evacuation routes. This increases the risk of putting many lives and property at risk.

[1515] 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.

[1516] In this invention, the server includes means for collecting data in real time using sensors, unmanned aerial vehicles, satellites, and external APIs, means for storing the collected data in structured and unstructured databases, means for analyzing the stored data using an AI algorithm and running a disaster prediction model and a damage situation model, means for calculating relief supplies and personnel based on damage information and generating an optimal support plan, means for notifying users of important data and displaying the latest information through a dashboard API, and means for calculating optimal travel routes based on traffic and damage information and providing them to users, thereby enabling rapid and accurate disaster response.

[1517] A "sensor" is a device that measures environmental conditions or physical quantities and converts that information into an electrical signal.

[1518] An "unmanned aerial vehicle" is an aircraft that moves through the air by remote control or autonomous flight, collecting data and making observations.

[1519] A "satellite" is a spacecraft placed in orbit around the Earth that collects data such as meteorological observations and Earth remote sensing.

[1520] An "external API" is a programmatic interface for obtaining information from other systems or services.

[1521] A "database" is a system for efficiently storing, retrieving, and analyzing data. Both structured and unstructured databases exist.

[1522] An "AI algorithm" is a method of analyzing data using machine learning and data mining techniques to make predictions and classifications.

[1523] A "disaster prediction model" is a mathematical model for predicting the occurrence and impact of disasters based on collected data.

[1524] A "damage situation model" is a mathematical model used to analyze the scope and extent of damage when a disaster occurs.

[1525] A "support plan" is a specific proposal for optimally planning the types and quantities of relief supplies, the deployment of personnel, etc.

[1526] "Dashboard API" means a programmatic interface for visually displaying collected and analyzed data.

[1527] The "optimal route" is the most efficient travel route calculated based on traffic and damage information.

[1528] MODE FOR CARRYING OUT THE INVENTION

[1529] This invention is a system for realizing a rapid and effective response in the event of a disaster, and includes the collection and analysis of real-time data, damage prediction, response plan proposal, information provision, and optimal travel route proposal. Specific embodiments for implementing the invention are described below.

[1530] System configuration

[1531] Data collection

[1532] The server collects data in real time using sensors, drones, satellites, and external APIs. Specific examples include earthquake data from seismometers, weather data from weather sensors, image data from drones and satellites, and traffic data from traffic information APIs. All data is time-stamped, making it easier to analyze later.

[1533] Data storage

[1534] The server stores the collected data in structured and unstructured databases, using databases such as MySQL or MongoDB. For example, earthquake data is stored in a table called "seismic_data," and meteorological data is stored in a table called "weather_data."

[1535] Data analysis

[1536] The server uses AI algorithms to analyze the stored data. Specifically, it uses TensorFlow and other tools to run disaster prediction and damage situation models. This allows it to predict the epicenter and areas prone to flooding. The analysis results are stored in a new table called "prediction_results."

[1537] Aid response proposal

[1538] The server generates a relief plan based on the analysis results. Python is used to calculate the type and quantity of relief supplies and the deployment of personnel. The generated relief plan is converted into JSON format and sent to the device via the dashboard API. For example, the calculated relief plan may include information such as "Area A needs 500 sets of food, 100 liters of water, and five relief team members."

[1539] Providing information

[1540] The server notifies users of important information in real time based on the collected data and analysis results. For example, if it detects an expansion of the affected area or a change in traffic conditions, it sends a push notification to the device via the dashboard API. The device receives this and displays it as an alert to the user.

[1541] Optimal route suggestions

[1542] The server calculates the optimal travel route based on traffic and damage information. The algorithms used are Dijkstra's algorithm and A algorithm, which calculate the most efficient travel route. The calculation results are sent in JSON format to the device via the dashboard API, allowing the user to check the optimal route.

[1543] Specific examples

[1544] Example 1: Processing when an earthquake occurs

[1545] 1. The server receives earthquake data from the seismometer and stores it in a database.

[1546] 2. The server analyzes the stored data and runs models to predict the epicenter and intensity of the earthquake.

[1547] 3. The server sends the analysis results to the device via the dashboard API, and the device visually displays the prediction results.

[1548] 4. Users can check the damage situation and forecast information via their devices and take appropriate evacuation actions.

[1549] Example 2: Flood forecasting and response planning

[1550] 1. The server receives rainfall data from weather sensors and stores it in a database.

[1551] 2. The server analyzes the stored data and runs flood forecasting models, which identify areas that are likely to flood.

[1552] 3. The server calculates the necessary relief supplies based on the damage situation and generates the optimal relief plan.

[1553] 4. The terminal displays the support plan to the user, enabling them to quickly allocate the necessary resources.

[1554] Prompt Sentence Examples

[1555] "Please tell me the procedure for processing the damage prediction model in the event of an earthquake."

[1556] "Please give us some concrete examples of flood forecasts and response plans based on current rainfall data."

[1557] In this way, the present invention enables rapid and effective response in the event of a disaster through real-time data collection and analysis, enabling optimal measures to minimize damage and save lives.

[1558] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1559] Step 1: Data collection

[1560] The server collects data in real time using sensors, drones, satellites, and external APIs. For example, it acquires earthquake data from seismometers, weather data from weather sensors, image data from drones and satellites, and traffic data from traffic information APIs. The collected data is stored as a time-stamped log.

[1561] Inputs: Data from seismometers, weather sensors, drones, satellites, and external APIs

[1562] Output: Raw data log with timestamps

[1563] Specific operation:

[1564] Earthquake data is obtained from the seismometer every 10 seconds.

[1565] Traffic information updated every minute via API.

[1566] Step 2: Save data

[1567] The server stores the collected data in structured and unstructured databases, such as MySQL or MongoDB.

[1568] Input: Raw data log with timestamps

[1569] Output: Structured and unstructured data stored in a database

[1570] Specific operation:

[1571] Seismic data is stored using the SQL query "INSERT INTO seismic_data (timestamp, magnitude) VALUES (timestamp, magnitude)".

[1572] Weather data is stored using the SQL query "INSERT INTO weather_data (timestamp, temperature) VALUES (timestamp, temperature)".

[1573] Step 3: Data analysis

[1574] The server analyzes the stored data using AI algorithms, and runs disaster prediction models and damage situation models using TensorFlow and other tools.

[1575] Input: Structured and unstructured data stored in a database

[1576] Output: Analysis results (epicenter, seismic intensity, damage prediction area)

[1577] Specific operation:

[1578] TensorFlow is used to analyze earthquake data and predict the epicenter and intensity.

[1579] The analysis results are saved in a new table called "prediction_results".

[1580] Step 4: Propose an aid response

[1581] The server generates an aid plan based on the analysis results. It uses Python to calculate the type and quantity of needed relief supplies and personnel deployment. The generated aid plan is converted into JSON format and sent to the device via the dashboard API.

[1582] Input: Analysis results (epicenter, seismic intensity, predicted damage area)

[1583] Output: Support plan in JSON format

[1584] Specific operation:

[1585] Run a script to generate a support plan and calculate the required supplies and personnel allocation.

[1586] The generated support plan is saved as a "relief supplies JSON file."

[1587] Step 5: Provide information

[1588] The server notifies users of important information in real time based on the collected data and analysis results. Push notifications are sent to the device via the dashboard API, which receives them and displays them as alerts to the user.

[1589] Input: Important analytical results and newly collected data

[1590] Output: Push notification to the user

[1591] Specific operation:

[1592] If an expansion of the affected area or changes in traffic information are detected, a push notification will be generated.

[1593] Send notifications to devices via the Dashboard API.

[1594] Step 6: Optimal route proposal

[1595] The server calculates the optimal travel route based on traffic and damage information. The Dijkstra algorithm and A algorithm are used to calculate the most efficient travel route. The calculation results are sent in JSON format to the device via the dashboard API, allowing the user to check the optimal route.

[1596] Input: Traffic information, damage information

[1597] Output: Optimal route in JSON format

[1598] Specific operation:

[1599] Calculates the optimal route from the current location to the destination using Dijkstra's algorithm.

[1600] The calculation results are saved as an "optimal route JSON file" and sent to the device via the dashboard API.

[1601] (Application example 1)

[1602] 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."

[1603] Existing disaster prevention systems lack real-time data collection and analysis, making it difficult to develop rapid and effective response plans. They also lack the necessary information and optimal travel route suggestions required during a disaster, leaving users highly confused. Furthermore, notification functions on mobile devices such as smartphones are inadequate, making it difficult to provide important information immediately in an emergency.

[1604] 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.

[1605] In this invention, the server includes means for collecting data in real time, means for analyzing the collected data and making disaster predictions, means for analyzing the damage situation, means for proposing an optimal response plan for rescue and recovery, means for providing necessary information, means for proposing an optimal travel route, means for notifying the user using an application installed on the smartphone, and means for proposing assistance using data stored in the database. This enables a quick and effective response in the event of a disaster, and makes it possible to provide users with important information and optimal evacuation routes in real time.

[1606] "Real-time data collection means" refers to the system's ability to continuously acquire new data through sensors, drones, satellites, and external APIs.

[1607] "Means of analyzing collected data and making disaster predictions" refers to the system's function of using AI algorithms to predict the likelihood of disasters occurring and the extent of damage based on the acquired data.

[1608] "Means for analyzing the damage situation" refers to the system's function of using collected and analyzed data to assess the extent and severity of damage caused by a disaster.

[1609] "Means for proposing optimal response plans for rescue and recovery" refers to the system's function of planning the deployment of necessary supplies and personnel based on analyzed damage information, and determining the optimal means of assistance and recovery.

[1610] "Means of providing necessary information" refers to the system's functions for notifying users of important information in real time and encouraging appropriate action.

[1611] "Means for suggesting optimal travel routes" refers to the system's function of calculating the safest and quickest evacuation route based on traffic and damage information and presenting it to the user.

[1612] "Means of notifying users using an application installed on a smartphone" refers to a system function that notifies users of disaster information and evacuation routes in real time via an application.

[1613] "Means for proposing assistance responses using data stored in the database" refers to a system function that analyzes stored past and current data and proposes optimal assistance responses.

[1614] This invention is a system for providing rapid and effective countermeasures in the event of a disaster, and is implemented in the following steps.

[1615] Data collection

[1616] The server collects data in real time from sensors (such as seismometers and weather sensors), drones, satellites, and external APIs (such as the Japan Meteorological Agency and traffic information services). This allows for a constant accumulation of up-to-date information on earthquakes and weather. Specific hardware used includes seismometers, weather sensors, drones, and satellites. Software uses libraries (such as Requests) to access external APIs.

[1617] Data storage

[1618] The collected data is stored in a database by the server. Databases can handle both structured and unstructured data. Examples of databases used include SQLite and MySQL.

[1619] Data analysis

[1620] The server uses AI algorithms based on the stored data to perform disaster predictions. This analysis identifies, for example, the epicenter and intensity of an earthquake, as well as areas expected to be flooded. The AI ​​algorithms utilize machine learning libraries such as Scikit-learn and TensorFlow.

[1621] Damage analysis

[1622] The server evaluates the damage situation based on the analyzed data, allowing the extent of the disaster's impact and severity to be determined. The analysis results are stored in a database and updated as needed.

[1623] Aid response proposal

[1624] The server calculates the necessary relief supplies and personnel allocation based on damage information, and generates an optimal aid and recovery plan, which calculates the necessary amounts of food, water, medicine, etc., enabling the rapid deployment of rescue teams.

[1625] Providing information

[1626] The server notifies users of important information based on data collected and analyzed in real time. Information such as damage forecasts, assistance response plans, and optimal evacuation routes is provided via push notifications using an application installed on a smartphone. Notification services such as Firebase Cloud Messaging are used.

[1627] Optimal route suggestions

[1628] The server calculates the optimal travel route based on traffic and damage information. The calculation uses Dijkstra's algorithm and A algorithm to calculate the shortest distance and fastest route. The calculation results are sent to devices such as smartphones, allowing users to evacuate safely.

[1629] Specific examples

[1630] For example, when an earthquake occurs, the server receives earthquake data from a seismometer and predicts the epicenter and seismic intensity. Based on this information, the damage situation is analyzed and appropriate relief supplies and personnel deployment plans are made. Ultimately, the epicenter, seismic intensity, and evacuation routes are notified to the user's smartphone. As another example, in flood prediction, rainfall data is collected and areas with a high probability of flooding are identified. This makes it possible to quickly deliver necessary relief supplies to areas where disasters are predicted.

[1631] Prompt Sentence Examples

[1632] "Based on the latest earthquake and meteorological data, please estimate the epicenter and damage, and suggest evacuation routes."

[1633] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1634] Step 1: Data collection

[1635] The server collects real-time data from seismometers, weather sensors, drones, satellites, and external APIs. Input data includes earthquake data, meteorological data, and image data. The server obtains the latest data from each data source and passes it on to the next processing step. This allows the latest disaster information to be collected at all times.

[1636] Step 2: Save data

[1637] The server stores the collected data in a database. The input data is earthquake and weather data collected in real time, and is stored in the database as structured or unstructured data. This data is efficiently managed using a database management system such as SQLite or MySQL.

[1638] Step 3: Data analysis

[1639] The server uses AI algorithms based on the stored data to make disaster predictions. The input data is stored earthquake and weather data. The AI ​​algorithm analyzes the earthquake's epicenter, seismic intensity, predicted flood areas, etc., and outputs the results. Machine learning libraries such as Scikit-learn and TensorFlow are used here.

[1640] Step 4: Damage analysis

[1641] The server assesses the damage situation based on the analyzed data. The input data is the analysis results. The impact scope and severity of the disaster are assessed, and the damage situation is understood in detail. This information is used to plan the next aid response.

[1642] Step 5: Propose an aid response

[1643] The server creates optimal rescue and recovery plans based on the damage situation. The input data is a detailed description of the damage situation, and it calculates the necessary supplies and personnel to generate an optimal support plan. This determines the required amounts of supplies such as food, water, and medicine, as well as the deployment of rescue teams.

[1644] Step 6: Provide information

[1645] The server provides users with important information in real time. The input data is assistance response plans and damage situation information, and the information is sent to users via an application installed on their smartphone. Push notification services such as Firebase Cloud Messaging are used to prompt users to take appropriate action.

[1646] Step 7: Optimal route proposal

[1647] The server calculates the optimal travel route based on traffic and damage information. The input data is real-time traffic and damage information, and the shortest distance and fastest route are calculated using Dijkstra's algorithm and A algorithm. The results are sent to the user's smartphone, helping them evacuate safely.

[1648] Step 8: User's appropriate evacuation behavior

[1649] The user takes appropriate evacuation action based on the information received on their smartphone. The input data is a notification sent from the server, and the user confirms it and follows the indicated evacuation route. This allows the user to evacuate quickly and safely.

[1650] 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.

[1651] This invention relates to a system that reduces the psychological burden on users during disasters and realizes more effective countermeasures by combining real-time data collection, analysis, damage prediction, response plan proposals, information provision, and optimal travel route proposals with an emotion engine that recognizes the user's emotions. Specific embodiments for implementing this invention are described below.

[1652] System configuration

[1653] 1. Data Collection Module

[1654] The server collects data in real time from sensors, drones, satellites, and external APIs. Specifically, it uses data from seismometers and weather sensors, image data from drones and satellites, and API data from the Japan Meteorological Agency and traffic information services.

[1655] 2. Data storage module

[1656] The server stores the collected data in a database, which can handle both structured and unstructured data.

[1657] 3. Data Analysis Module

[1658] The server applies AI models to the stored data to predict disasters and analyze damage situations, for example, predicting the epicenter and seismic intensity of an earthquake and areas susceptible to flooding.

[1659] 4. Aid Response Proposal Module

[1660] Based on the damage situation, the server calculates the type, quantity, and priority of supplies needed and draws up a personnel deployment plan.

[1661] 5. Information System

[1662] The server sends the latest information to the dashboard API, which the device receives and visually displays, providing users with easy-to-understand, real-time updated data and recommendations.

[1663] 6. Optimal Route Proposal Module

[1664] The server calculates optimal routes based on the latest traffic information, taking into account the extent of damage and traffic conditions, and optimizes routes for delivering relief supplies and moving personnel.

[1665] 7. Emotion Engine

[1666] The server uses an emotion engine to recognize the user's emotions in real time. Emotion data is collected and analyzed from cameras and microphones.

[1667] Program processing explanation

[1668] User Emotion Recognition

[1669] The server collects image and audio data from the camera and microphone connected to the device.

[1670] The server uses an emotion engine to analyze the collected data and recognize emotions (fear, stress, relief, etc.) from the user's facial expressions and voice tone.

[1671] The server stores the recognized emotion data in a database and triggers actions as needed.

[1672] Customized information provision

[1673] The server analyzes the user's stress and anxiety levels based on the emotional data. For example, if the user is in a high-stress state, it provides reassuring notifications and evacuation information.

[1674] The server sends the analysis results to the dashboard API, which the device receives and displays in real time, along with reassuring messages and alerts.

[1675] Reflecting priorities

[1676] The server then uses the emotional data to prioritize rescue and recovery plans, for example by quickly dispatching relief supplies and rescue teams to areas with a high number of users experiencing high levels of stress.

[1677] The server reconstructs the support plan based on the priority and allocates resources optimally.

[1678] Specific examples

[1679] Example 1: Processing when an earthquake occurs

[1680] 1. The server receives earthquake data from the seismometer and stores it in a database.

[1681] 2. The server analyzes the stored data and predicts the epicenter and intensity of the earthquake.

[1682] 3. The server collects the user's emotional data from the device's camera and microphone and analyzes it using an emotion engine.

[1683] 4. The server identifies areas with a high number of users experiencing high stress and develops a plan to quickly send relief supplies to those areas.

[1684] Example 2: Flood forecasting and response planning

[1685] 1. The server receives rainfall data from weather sensors and stores it in a database.

[1686] 2. The server analyzes the rainfall data and runs flood forecasting models, which identify areas that are likely to flood.

[1687] 3. The server calculates the necessary relief supplies based on the damage situation and generates the optimal relief plan.

[1688] 4. The server analyzes the user's emotional state and provides priority support to areas with a high number of users in high stress states.

[1689] 5. The terminal displays the support plan to the user, enabling them to quickly allocate the necessary resources.

[1690] In this way, by combining emotion engines, it is possible to reduce the psychological burden on users and enable more effective responses in the event of a disaster.

[1691] The processing flow will be explained below.

[1692] User emotion recognition processing

[1693] Step 1:

[1694] The terminal activates the camera and microphone on the device operated by the user.

[1695] Step 2:

[1696] The device captures a picture of the user's face with a camera and collects audio data with a microphone.

[1697] Step 3:

[1698] The terminal transmits the acquired image data and audio data to the server in real time.

[1699] Step 4:

[1700] The server inputs the received data into the emotion engine and analyzes the user's facial expressions and voice.

[1701] Step 5:

[1702] The server stores the analysis results of the emotion engine in a database and records the user's emotional state in real time.

[1703] Processing of customized communications

[1704] Step 1:

[1705] The server uses the analysis results from the emotion engine to evaluate the user's level of stress and anxiety.

[1706] Step 2:

[1707] The server selects appropriate information based on the evaluation results. For example, if a high stress state is detected, it will provide a reassuring message or evacuation information.

[1708] Step 3:

[1709] The server sends the selected information to the terminal via the dashboard API.

[1710] Step 4:

[1711] The device visually displays the received information to the user, encouraging safe behavior, and can also play audible messages to reduce stress.

[1712] Priority reflection processing

[1713] Step 1:

[1714] The server analyzes the damage situation information, including the emotion data, stored in the database.

[1715] Step 2:

[1716] Based on the emotional data, the server assesses the level of stress and anxiety in each affected area and sets priorities.

[1717] Step 3:

[1718] The server reconstructs the allocation plan for relief supplies and personnel based on priorities, and prioritizes areas where high stress levels are detected.

[1719] Step 4:

[1720] The server sends the recalculated support plan to the device via the dashboard API.

[1721] Step 5:

[1722] The device will display the new plan to the user and provide instructions on how to receive relief supplies and guidelines for action.

[1723] Specific examples

[1724] Example 1: Processing when an earthquake occurs

[1725] Step 1:

[1726] The server receives earthquake data from the seismometer and stores it in a database.

[1727] Step 2:

[1728] The server analyzes earthquake data and predicts the epicenter and intensity of the earthquake.

[1729] Step 3:

[1730] The device activates the camera and microphone and transmits the user's facial expressions and voice to the server in real time.

[1731] Step 4:

[1732] The server uses an emotion engine to analyze the user's emotional state.

[1733] Step 5:

[1734] The server identifies areas with a large number of users experiencing high stress levels and develops a plan to prioritize sending relief supplies to those areas.

[1735] Step 6:

[1736] The server sends the plan to the device via the dashboard API, and the device provides the information to the user.

[1737] Example 2: Flood forecasting and response planning

[1738] Step 1:

[1739] The server receives rainfall data from weather sensors and stores it in a database.

[1740] Step 2:

[1741] The server analyzes rainfall data and runs flood forecasting models.

[1742] Step 3:

[1743] The server identifies areas that are likely to be flooded and predicts damage.

[1744] Step 4:

[1745] The device activates the camera and microphone to collect the user's emotional data and send it to the server.

[1746] Step 5:

[1747] The server analyzes the emotional data and identifies areas where there are many users with high stress levels.

[1748] Step 6:

[1749] The server calculates the necessary relief supplies based on the priority and generates the optimal relief plan.

[1750] Step 7:

[1751] The server sends the support plan to the device via the dashboard API, and the device visually displays it to the user.

[1752] In this way, the system of the present invention combines real-time data collection, analysis, and user emotion recognition to enable rapid and effective responses in the event of a disaster and reduce the psychological burden on users.

[1753] Example 2

[1754] 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."

[1755] With the increasing frequency of natural disasters, there is a need for real-time data collection and analysis, damage analysis, and optimal response plans. However, conventional systems lacked functionality to address the psychological burden placed on users, making it difficult to maintain psychological stability during disasters. Furthermore, they were also inadequate in formulating quick and effective support plans based on collected data and proposing optimal travel routes.

[1756] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1757] In this invention, the server includes means for collecting data in real time, means for saving the collected data, means for analyzing the saved data and making disaster predictions, means for analyzing the damage situation, means for collecting and analyzing user emotion data, means for providing information for reducing psychological burden based on the collected emotion data, means for proposing an optimal response plan for rescue and recovery, means for providing necessary information, and means for proposing an optimal travel route. This enables effective disaster response in real time, and makes it possible to propose optimal support plans and travel routes while reducing the psychological burden on users.

[1758] "Means for collecting data in real time" refers to devices or systems that acquire disaster and environmental data in real time using sensors, unmanned aerial vehicles, satellites, external APIs, etc.

[1759] "Means for storing collected data" refers to a database or storage system for temporarily or permanently storing acquired data.

[1760] "Means for analyzing stored data and making disaster predictions" refers to a system that analyzes stored data and uses algorithms and AI models to predict the occurrence of earthquakes, floods, and other disasters in advance.

[1761] "Means for analyzing the damage situation" refers to a system that analyzes the scale and extent of the damage after a disaster occurs, and determines the exact extent of the damage.

[1762] The "means for collecting and analyzing user emotional data" refers to a system that uses devices such as a camera and microphone to collect the user's facial expressions and tone of voice, and analyzes them using an emotion recognition engine.

[1763] The "means for providing information that reduces psychological burden based on collected emotional data" is a system that provides notifications and evacuation information that give users a sense of security based on analyzed emotional data.

[1764] The "means of proposing optimal response plans for rescue and recovery" is a system that draws up plans for the allocation of damage, necessary supplies, and personnel, and provides optimal support and recovery methods.

[1765] "Means for providing necessary information" refers to a system that provides users with breaking news and updated information via a dashboard or the like.

[1766] The "means for proposing optimal travel routes" is a system that calculates and proposes optimal travel routes for relief supplies and personnel based on traffic and damage information.

[1767] This invention is realized by combining the following elements in the system: The roles of the server, terminal, and user are specifically shown, and the corresponding hardware and software configurations, data processing, and data calculations are explained in detail.

[1768] System Overview

[1769] This system collects data in real time, analyzes it, predicts damage, proposes optimal response plans, provides information, and recognizes emotions, enabling effective responses in the event of a disaster. In particular, it is equipped with an emotion recognition function to reduce the psychological burden on users.

[1770] Data collection

[1771] The server uses sensors (seismometers, weather sensors), unmanned aerial vehicles, satellites, external APIs, etc. to collect earthquake data, rainfall data, image data, weather data, traffic information, etc. in real time. Specific devices used include seismometers (e.g., Seismometer-X100), weather sensors (e.g., WeatherSensor-Y200), and unmanned aerial vehicles (e.g., DJI Phantom 4). Data is obtained using APIs from the Japan Meteorological Agency and traffic information providers.

[1772] Data storage

[1773] The server stores the collected data in a database. Structured data (e.g., numerical data) is stored in a relational database (e.g., MySQL), and unstructured data (e.g., image data) is stored in a non-relational database (e.g., MongoDB). A timestamp is assigned to each entry of the data, and it is managed to make it easy to search and analyze.

[1774] Data analysis

[1775] The server analyzes the stored data using AI models (e.g., TensorFlow, PyTorch) to predict disasters such as earthquakes and floods. The analysis results are stored in a database and used to develop subsequent response plans.

[1776] Damage response proposals

[1777] The server calculates the type, quantity, and priority of needed relief supplies based on disaster prediction and damage data. It also creates a personnel deployment plan and formulates optimal relief and recovery plans. In this process, the results of the AI ​​model's calculations are utilized to enable a fast and efficient response.

[1778] Providing information

[1779] The server sends the latest analysis results and support plans to a dashboard API (e.g., Grafana, Tableau), which then receives and displays the information on the device. Users can visually check the information updated in real time through their device.

[1780] Optimal route suggestions

[1781] The server uses the Google Maps API to calculate the optimal route based on the collected traffic information. The calculation results are sent to the dashboard API, which is then received and displayed on the device. This allows for the efficient movement of relief supplies and personnel.

[1782] emotion recognition

[1783] The server analyzes the user's image and voice data collected from the device's connected camera (e.g., Logitech C920) and microphone (e.g., Blue Yeti) in real time using an emotion engine (e.g., Affectiva, Microsoft Azure Emotion API). The analyzed emotion data is stored in a database, and information is provided to reduce psychological stress as needed.

[1784] Specific examples

[1785] Example 1: Processing when an earthquake occurs

[1786] 1. The server receives earthquake data from a seismometer (e.g., Seismometer-X100) and stores it in a database.

[1787] 2. The server analyzes the earthquake data and predicts the epicenter and intensity of the earthquake.

[1788] 3. The server analyzes the emotional data collected from the device's camera and microphone and identifies areas with a high number of users experiencing high levels of stress.

[1789] 4. The server will develop a plan to quickly send relief supplies to the identified area.

[1790] 5. The device receives the assistance plan and visually displays it to the user.

[1791] Prompt for the generative AI model in this example:

[1792] "Generate a scenario for the next earthquake. Explain in detail how you would predict damage based on data collected from sensors and how you would collect and analyze user emotion data. Then, describe the steps to propose an optimal assistance plan."

[1793] Example 2: Flood forecasting and response planning

[1794] 1. The server receives rainfall data from a weather sensor (e.g., WeatherSensor-Y200) and stores it in a database.

[1795] 2. The server analyzes the rainfall data and runs flood forecasting models.

[1796] 3. The server identifies areas at high risk of flooding and calculates the amount of relief supplies needed.

[1797] 4. The server creates a support plan and prioritizes sending support to areas with a large number of users in high stress.

[1798] 5. The device receives the support plan and displays it to the user.

[1799] Prompt for the generative AI model in this example:

[1800] "Generate the following flood scenario. Explain in detail how you would use data collected from sensors to perform flood predictions, identify damage, and collect and analyze user sentiment data. Then, detail the steps to propose an optimal assistance plan."

[1801] In this way, the system executes each processing step in detail, realizing effective disaster response while reducing the psychological burden on the user.

[1802] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1803] Step 1: Data collection

[1804] The server collects various data in real time using sensors, unmanned aerial vehicles, satellites, external APIs, etc. Specifically, it obtains earthquake data from seismometers (e.g., Seismometer-X100), rainfall data from weather sensors (e.g., WeatherSensor-Y200), and image data from unmanned aerial vehicles (e.g., DJI Phantom 4). It also obtains the latest weather and traffic information from the APIs of the Japan Meteorological Agency and traffic information services. The server receives input data from each device and API and converts it into a format that can be used in the next step.

[1805] Step 2: Save data

[1806] The server stores the collected data in a database. The input is various data collected in real time, which the server stores as structured data (e.g., numerical data stored in MySQL) and unstructured data (e.g., image data stored in MongoDB). Each piece of data is assigned a timestamp and managed to make it easy to search and analyze. The output is the various saved data stored in the database.

[1807] Step 3: Data analysis

[1808] The server inputs the stored data into an AI model (e.g., TensorFlow, PyTorch) for analysis. The inputs include stored earthquake data, meteorological data, and image data, and the server analyzes these to predict earthquakes and floods. Specifically, it predicts the epicenter and seismic intensity from the earthquake data, and identifies flood risk areas from the meteorological data. The analysis results are output and stored in a database for use in the next step.

[1809] Step 4: Damage response proposal

[1810] The server calculates the type, quantity, and priority of the necessary relief supplies based on the disaster prediction data obtained as a result of the analysis. The inputs are the disaster prediction data and collected damage situation data, and the server uses this to formulate a relief plan. Specifically, it uses an AI model to create optimal personnel deployment plans and supply distribution plans. The output is an optimal relief and recovery plan.

[1811] Step 5: Provide information

[1812] The server sends the latest analysis results and support plans to a dashboard API (e.g., Grafana, Tableau), and the terminal receives and displays the information. The input includes analysis results and support plan data, which the server sends to the terminal via the dashboard API. The terminal receives this information and displays it visually to the user. As an output, the user can view information that is updated in real time.

[1813] Step 6: Optimal route proposal

[1814] The server uses the Google Maps API to calculate the optimal travel route based on the collected traffic information. The server inputs the latest traffic and damage information into a route calculation algorithm. The calculation results are sent to the dashboard API and received and displayed on the device. The output is optimal travel route information, enabling the efficient movement of relief supplies and personnel.

[1815] Step 7: Emotion Recognition

[1816] The server uses an emotion engine (e.g., Affectiva, Microsoft Azure Emotion API) to analyze in real time the user's image and voice data collected from the camera (e.g., Logitech C920) or microphone (e.g., Blue Yeti) connected to the device. The input is the collected image and voice data, which the server analyzes to recognize the user's emotions (fear, stress, relief, etc.). The analysis results are stored in a database, and notifications or evacuation information are provided to reduce psychological stress as needed. The output is the recognized emotion data and actions based on it.

[1817] (Application example 2)

[1818] 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."

[1819] Conventional disaster response systems collect and analyze data in real time, predicting disasters, analyzing damage situations, and proposing rescue and recovery plans, but they do not adequately consider reducing the psychological burden on users. Furthermore, they lack the ability to provide customized information that takes into account people's emotional changes during a disaster, making it difficult for users to take appropriate action. This limits the effectiveness of disaster response and makes it difficult to prevent the damage from spreading.

[1820] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data in real time, means for analyzing the collected data and making disaster predictions, means for analyzing the damage situation, means for proposing an optimal response plan for rescue and recovery, means for providing necessary information, means for proposing an optimal travel route, means for recognizing the user's emotions in real time using an emotion recognition engine, and means for providing information customized based on the user's emotion data. This makes it possible to improve the efficiency and effectiveness of disaster response while reducing the psychological burden on the user.

[1821] "Means of collecting data in real time" refers to devices and methods that collect current information from sensors, external APIs, drones, satellites, etc.

[1822] "Means for analyzing collected data and making disaster predictions" refers to devices or methods that use AI models or algorithms based on acquired information to predict the possibility and scope of a disaster.

[1823] "Means for analyzing the damage situation" refers to devices and methods for assessing and analyzing the scope of impact and the extent of damage when a disaster occurs.

[1824] "Means for proposing optimal response plans for rescue and recovery" refers to devices and methods for creating plans to efficiently provide the types and quantities of supplies needed, deploy personnel, etc., based on the damage situation.

[1825] The "means for providing necessary information" refers to a device or method that visually or audibly provides the user with situation information and evacuation information that is updated in real time.

[1826] "Means for proposing optimal travel routes" refers to devices or methods that calculate and present the most suitable travel routes for evacuation, delivery of relief supplies, etc. based on damage status and traffic information.

[1827] "Means for recognizing a user's emotions in real time using an emotion recognition engine" refers to a device or method that analyzes image and audio data from a camera or microphone and determines the user's emotional state in real time.

[1828] "Means for providing information customized based on user emotional data" refers to a device or method that provides information adjusted to reduce the user's psychological burden based on recognized emotional data.

[1829] This invention is a system for reducing the psychological burden on users during disasters and realizing more effective countermeasures. The system provides comprehensive support to users by combining real-time data collection, analysis, disaster prediction, damage analysis, optimal response plan proposal, information provision, optimal travel route proposal, and an emotion engine that recognizes the user's emotions.

[1830] System Configuration

[1831] 1. Data Collection Module

[1832] The server collects real-time data from sensors, drones, satellites, and external APIs, including data from seismometers and weather sensors, image data from drones and satellites, and API data from meteorological agencies and traffic information services.

[1833] 2. Data storage module

[1834] The server stores the collected data in a database, which can manage both structured and unstructured data.

[1835] 3. Data Analysis Module

[1836] The server applies machine learning and AI models to the stored data to predict disasters and analyze damage situations, thereby predicting the epicenter and intensity of earthquakes and flood areas in the event of an earthquake.

[1837] 4. Aid Response Proposal Module

[1838] The server calculates the type, quantity, and priority of supplies needed based on the damage situation, and creates a personnel deployment plan, which is optimized based on data updated in real time.

[1839] 5. Information System

[1840] The server sends the latest information to the dashboard via API, which the device receives and displays visually, providing users with easy-to-understand, real-time updates and recommendations.

[1841] 6. Optimal Route Proposal Module

[1842] The server calculates optimal routes based on the latest traffic information, taking into account the extent of damage and traffic conditions, optimizing routes for delivering relief supplies and moving personnel.

[1843] 7. Emotion Engine

[1844] The server collects image and audio data from the camera and microphone and analyzes it using an emotion engine, which recognizes emotions (fear, stress, relief, etc.) from the user's facial expressions and tone of voice in real time.

[1845] Program processing explanation

[1846] Hardware: Cameras, microphones, and GPS sensors built into devices such as smartphones, tablets, and computers.

[1847] Software: The application is developed using Python and utilizes machine learning libraries (TensorFlow and PyTorch), and API communication involves HTTP requests and JSON data exchange.

[1848] Data processing and calculation: Data collected from sensors and external APIs is stored in a database and analyzed by machine learning models. The emotion engine analyzes data obtained from the camera and microphone to recognize the user's emotional state.

[1849] Example: When an earthquake occurs, the server immediately acquires and analyzes seismograph data and predicts the epicenter. The user's device uses a camera and microphone to analyze the user's emotions and presents a "safe evacuation route."

[1850] Example prompt sentence:

[1851] Analyze the video and audio data to recognize the user's current emotions. If the result is "high stress," generate a message saying, "According to the analysis results, the current situation has a low risk of disaster. However, please secure the optimal evacuation route just in case."

[1852] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1853] Step 1:

[1854] Real-time data collection

[1855] The server collects seismograph data, weather data, and traffic information in real time from sensors, drones, satellites, and external APIs. Specifically, it retrieves data from APIs using HTTP requests. The input is data streams from various sensors and APIs, which are received and stored in a database as structured and unstructured data. The output is the latest disaster-related data stored in the database.

[1856] Step 2:

[1857] Data storage

[1858] The server stores the collected data in a database. This database can be an RDBMS or NoSQL database. The input is sensor data or API data collected in real time, and the output is the stored data. Specific operations include data format conversion, normalization, and index creation.

[1859] Step 3:

[1860] Data analysis and disaster prediction

[1861] The server analyzes the stored data and uses AI models to make disaster predictions. The input is the latest disaster-related data stored in the database, and the output is a prediction of the likelihood of a disaster occurring and the damage it will cause. Specific operations include applying machine learning models and running prediction algorithms.

[1862] Step 4:

[1863] Analysis of the damage situation

[1864] The server analyzes the damage situation in real time after a disaster occurs. The input is the disaster prediction results and additional sensor data, and the output is the analysis results of the damage range and extent. Specific operations include image analysis, text analysis, and data aggregation.

[1865] Step 5:

[1866] Proposed relief and recovery plan

[1867] The server calculates the type, quantity, and priority of supplies needed based on the results of the damage analysis, and then creates a personnel deployment plan. The input is the results of the damage analysis and existing rescue resource data, and the output is a detailed rescue and recovery plan. The specific operation involves applying a resource optimization algorithm.

[1868] Step 6:

[1869] Providing information

[1870] The server sends the latest information to the dashboard API, which the device receives and visually displays. The input is disaster prediction results and rescue plans, and the output is real-time information displayed to the user. Specific operations include data format conversion and UI updates.

[1871] Step 7:

[1872] Proposing optimal travel routes

[1873] The server calculates the optimal travel route based on the latest traffic information and sends it to the terminal. The input is real-time traffic data and disaster information, and the output is a proposal for the optimal travel route. Specifically, the route calculation is performed using Dijkstra's algorithm or the A algorithm.

[1874] Step 8:

[1875] emotion recognition

[1876] The device collects image and audio data from the camera and microphone, and the server analyzes it using an emotion engine. The input is the image and audio data sent from the device, and the output is the recognition result of the user's emotional state (high stress, relief, etc.). Specific operations include applying facial expression recognition algorithms and voice analysis algorithms.

[1877] Step 9:

[1878] Customized information provision

[1879] Based on the recognized emotion data, the server sends customized information to the device to reduce the user's psychological burden. The input is the recognized emotion data and disaster information, and the output is a customized message or notification. For example, a message such as "According to the analysis results, the current situation has a low risk of disaster. However, please secure the optimal evacuation route just in case" may be generated.

[1880] 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.

[1881] 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.

[1882] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1883] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1884] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1885] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1886] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1887] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1888] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1889] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1890] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1891] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1892] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1893] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1894] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1895] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1896] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1897] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1898] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1899] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of ...

Claims

1. a means of collecting data in real time; A means of analyzing the collected data and making disaster predictions; A means of analyzing the damage situation; a means of proposing optimal response plans for relief and recovery; the means to provide the necessary information; A system including a means for suggesting optimal travel routes.

2. The system according to claim 1, which collects satellite data and drone data to predict disasters and grasp detailed damage situations.

3. 2. The system according to claim 1, further comprising means for collecting traffic information and damage information and calculating an optimal travel route based thereon.

Images