System

Abstract

A system is provided.SOLUTION: A means for generating a list of necessary supplies and personnel on the basis of a result of the estimation, a means for making the list known to related parties, and a means for estimating traffic and road conditions from the satellite data, the method comprising: a means for generating a list of necessary supplies and personnel on the basis of a result of the estimation, a means for generating a list of necessary supplies and personnel on the basis of a result of the estimation, and a means for estimating traffic and road conditions from the satellite data, the method comprising: AI, the system includes a means for generating a passable route, a means for distributing the information to a digital signage or a smartphone, and a means for continuously monitoring the data or information and redistributing an instruction as necessary.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In the past, it was difficult to quickly and accurately collect and share information on disaster damage after a disaster occurred. This meant that it was difficult to quickly grasp the situation in the affected areas, especially immediately after the disaster, which led to delays in providing necessary supplies and personnel. Furthermore, fragmented information made it difficult to prioritize support and provide appropriate instructions. Furthermore, grasping the status of transportation infrastructure in the affected areas and proposing passable routes also hindered efficient support activities on the ground. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. It provides a means for acquiring satellite data, meteorological data, and crustal data, which are centrally stored and preprocessed. The preprocessed data is then passed to a generation AI to quickly and accurately estimate the damage situation. It provides a means for generating a list of supplies and personnel needed in the disaster area based on the estimation results and automatically disseminating this information to relevant parties. It also provides a means for using satellite data to estimate traffic and road conditions, generating passable routes, and optimizing on-site support activities. This realizes a system that enables fast and accurate information collection, appropriate support instructions, and efficient support activities immediately after a disaster occurs.

[0006] "Satellite data" refers to observation data obtained from artificial satellites deployed in outer space.

[0007] "Weather data" refers to data that includes information related to weather, such as rainfall, temperature, wind speed, wind direction, humidity, and atmospheric pressure.

[0008] "Crustal data" is data that includes information related to the Earth's crust, such as seismic activity, crustal movements, and volcanic activity.

[0009] "SNS data" refers to data that includes information such as text, images, and videos posted by users on social networking services.

[0010] "Digital signage" is a device that uses electronic displays to display information, typically installed in public places.

[0011] "Generative AI" is an artificial intelligence technology that estimates the damage situation based on collected data and performs advanced analysis.

[0012] "Preprocessing" refers to processing to remove noise from collected data and standardize the format.

[0013] "Disaster situation" is information that indicates the extent and severity of damage caused by a disaster.

[0014] "Supplies" refer to supplies such as drinking water, food, and medicine that are needed by disaster victims and for relief efforts when a disaster occurs.

[0015] "Personnel" refers to the people needed to carry out relief and recovery efforts in the event of a disaster, such as medical staff and rescue teams.

[0016] "Traffic and road conditions" refers to information about transportation infrastructure, such as current traffic flow, road conditions, and passability.

[0017] "Passable routes" is information indicating road routes that can be traveled safely in the disaster area.

[0018] "Stakeholders" refers to agencies and organizations, such as government agencies and non-governmental organizations, that receive information necessary to provide assistance in the event of a disaster. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] The present invention is a system for quickly and accurately collecting and analyzing disaster information when a disaster occurs, and disseminating the information to relevant parties. An embodiment of this system will now be described in detail.

[0041] 1. Data Collection Methods

[0042] The server acquires satellite data, meteorological data, and crustal data in real time. Satellite data is high-resolution image data observed by artificial satellites in space, which allows for extensive visual information on the disaster-stricken area. Meteorological data includes meteorological information such as rainfall, temperature, wind speed, wind direction, humidity, and air pressure. Meanwhile, crustal data is data acquired from seismometers and devices that monitor crustal movements. The server also collects social media data and acquires disaster-related information posted by users on social networking services.

[0043] 2. Data storage and preprocessing methods

[0044] The server stores the collected data in a centralized database. The stored data is preprocessed to remove noise and standardize its format. For example, unnecessary hashtags and emojis are removed from social media posts, and satellite image data is optimized for image analysis.

[0045] 3. Data Analysis Methods

[0046] The preprocessed data is passed from the server to the generation AI. The generation AI analyzes satellite images to visually grasp the extent of damage in the affected areas. For example, it identifies collapsed buildings and flooded areas. It then analyzes social media data using text mining techniques to identify the location and status of victims with high urgency. By integrating meteorological data and crustal data and applying a damage prediction model, it estimates the demand for supplies and personnel in the affected areas.

[0047] 4. How to create a list of supplies and personnel needed

[0048] Based on the analysis results of the generative AI, the server generates a list of supplies (e.g., drinking water, food, medicine) and personnel (e.g., medical staff, rescue teams) needed in the disaster area, allowing users to quickly determine what is needed where.

[0049] 5. How to inform relevant parties

[0050] The generated list is automatically sent from the server to the relevant parties via email, SMS, and the disaster prevention radio system, and includes details of the supplies and personnel needed, allowing the relevant parties to immediately begin responding.

[0051] 6. Traffic and road condition estimation methods

[0052] The server analyzes the state of transportation infrastructure in the disaster area based on satellite data, and the generating AI uses this information to calculate the optimal route for safe and fast movement of support vehicles and proposes it to the support team.

[0053] 7. Means of information distribution

[0054] For residents in the affected areas, safety instructions and evacuation information are sent from the server to digital signage and smartphones. The terminal (digital signage) notifies people in the vicinity of the received information visually and audibly, urging them to take emergency action. The user (smartphone) then uses the received information to ensure their own safety and the safety of those around them.

[0055] Specific examples

[0056] For example, when a major earthquake occurs, the server immediately collects satellite data and seismograph data. It also obtains posts from social media such as "Shaking" and "Collapse," and the generation AI estimates the extent of damage in the affected area. Based on this, it generates a list of necessary supplies and personnel and automatically disseminates this information to relevant parties. It also calculates passable routes and suggests them to support vehicles. At the same time, it distributes evacuation information to digital signage and smartphones, helping to ensure the safety of victims.

[0057] In this way, this system enables prompt and appropriate support activities in the event of a disaster.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] The server periodically acquires satellite data, meteorological data, and crustal data. Satellite data is recorded at specified intervals, and meteorological data is acquired in real time from the Meteorological Agency's API. Crustal data is automatically collected from observation data from seismometers.

[0061] Step 2:

[0062] The server also simultaneously acquires social media data, using public APIs such as Twitter and Facebook to collect posts filtered by keywords such as "disaster," "earthquake," and "rescue."

[0063] Step 3:

[0064] The server stores the acquired data in a centralized database, which has an intermediate format for integrating different data formats, making all data immediately accessible.

[0065] Step 4:

[0066] The server pre-processes the stored data, for example removing noise from social media data and cleaning up text data, and adjusts the resolution of satellite image data to prepare it for image analysis.

[0067] Step 5:

[0068] The server passes the preprocessed data to the generation AI, which then uses this data to begin estimating the extent of the damage. First, it analyzes satellite images to identify collapsed buildings and the extent of flooding.

[0069] Step 6:

[0070] The generative AI analyzes text from social media data to extract the location information of disaster victims with high urgency, using natural language processing technology to identify location information by analyzing the frequency and importance of related keywords.

[0071] Step 7:

[0072] The generative AI integrates meteorological and crustal data and applies damage prediction models to estimate supply shortages and personnel needs in affected areas.

[0073] Step 8:

[0074] The server generates a list of required supplies and personnel based on the estimation results of the generation AI. The generated list is saved in XML or JSON format.

[0075] Step 9:

[0076] The server sends the generated list to the relevant parties via email, SMS, and the disaster prevention radio system. It also checks whether the relevant parties have received the information, and if not, resends it.

[0077] Step 10:

[0078] The server then acquires satellite data again and analyzes the current traffic and road conditions, thereby identifying passable and impassable roads.

[0079] Step 11:

[0080] The generation AI calculates the optimal route for the support vehicle to travel quickly, and the calculated route is updated in real time.

[0081] Step 12:

[0082] The server distributes safety instructions and evacuation information to digital signage and smartphones, and the digital signage notifies those in the vicinity with audio and visual information.

[0083] Step 13:

[0084] The user (smartphone) receives information from the server and takes action based on the instructions to ensure the safety of themselves and those around them.

[0085] Step 14:

[0086] The server continuously collects data and monitors changes in the situation in the affected area, then re-distributes necessary instructions according to the new situation.

[0087] Example 1

[0088] 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."

[0089] When a disaster occurs, it is necessary to quickly and accurately collect and analyze damage information and disseminate it to all relevant parties. However, with conventional systems, data collection and analysis are often carried out as separate processes, making it difficult to centralize information management and analyze it in real time. In addition, there is a time lag when estimating traffic conditions in disaster-stricken areas and proposing passable routes, which hinders rapid relief efforts.

[0090] 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.

[0091] In this invention, the server includes: means for acquiring satellite data, means for acquiring meteorological and crustal data, means for acquiring social networking service data, means for centrally storing and preprocessing these data; means for passing the preprocessed data to a generation AI and estimating the damage situation; means for generating a list of necessary supplies and personnel based on the estimation results; means for disseminating the list to relevant parties; means for estimating traffic and road conditions from satellite data and generating passable routes; means for distributing this information to digital information display devices and mobile communication devices; and means for continuously monitoring this data and information and redistributing instructions as necessary. This enables centralized data management and real-time information analysis and dissemination. Furthermore, traffic condition estimation and route suggestions enable rapid relief activities.

[0092] "Satellite data" refers to high-resolution image data obtained from satellites in space, providing a wide range of visual information.

[0093] "Weather data" refers to data including meteorological information such as rainfall, temperature, wind speed, wind direction, humidity, and atmospheric pressure.

[0094] "Crustal data" refers to data obtained from seismometers and devices that monitor crustal movements, and includes information such as the magnitude and epicenter of an earthquake.

[0095] "Social networking service data" refers to data that includes disaster-related information posted by users on social networking services.

[0096] "Means of centralized storage" refers to a means of storing collected data in a single database.

[0097] "Preprocessing means" refers to a means for removing noise from the stored data and standardizing it into a format that is easy to analyze.

[0098] "Generative AI" is an artificial intelligence model that analyzes preprocessed data and estimates the damage situation.

[0099] "Means for estimating the damage situation" refers to a means of using generative AI to identify the damage situation in the affected areas and the location and condition of victims with high urgency.

[0100] The "means for generating a list of necessary supplies and personnel" is a means for creating a list of supplies and personnel required in the disaster-stricken area based on the estimated damage situation.

[0101] "Means of informing relevant parties" refers to the means of notifying relevant parties of the generated lists of supplies and personnel via email, SMS, and disaster prevention radio systems.

[0102] "Means for estimating traffic and road conditions" refers to analyzing the state of transportation infrastructure based on satellite data and calculating passable routes.

[0103] A "digital information display device" is an electronic public sign that displays disaster information and evacuation instructions visually and audibly.

[0104] A "mobile communication terminal" is a portable communication device such as a smartphone, and is a terminal for receiving disaster information.

[0105] "Continuous monitoring measures" are measures that constantly check collected data and information and redeliver instructions if the situation changes.

[0106] This invention is a system for collecting and analyzing disaster information quickly and accurately when a disaster occurs, and disseminating it to relevant parties. Specific embodiments of this system will be described in detail below.

[0107] First, the hardware and software that provide the foundation for the entire system consists of servers, mobile communication terminals, digital information display devices, etc. These devices work together to provide the infrastructure for centrally managing and analyzing collected data.

[0108] Data collection methods

[0109] The server collects the following data in real time:

[0110] 1. Satellite data collection: Receiving high-resolution image data from satellites in space. This image data is crucial for visually understanding the overall situation of the affected area.

[0111] 2. Meteorological Data Collection: Meteorological data such as rainfall, temperature, wind speed, wind direction, humidity, and air pressure are obtained from weather observation stations.

[0112] 3. Collecting crustal data: Receive crustal data from seismometers and other devices that monitor crustal movements, including information on the magnitude and epicenter of earthquakes.

[0113] 4. Social networking service data collection: We collect disaster-related information posted by users on social networking services. Specifically, we collect posts such as "Shaking" and "Collapse" in real time.

[0114] Data storage and preprocessing methods

[0115] The server stores the collected data in a centralized database, and then performs the following pre-processing:

[0116] 1. Noise removal: Remove unnecessary information from the stored data. For example, remove hashtags and emojis from social media data.

[0117] 2. Format unification: Data formats are standardized for analysis. For example, text data is converted into a fixed format, and image data is adjusted to a format that is easy to analyze.

[0118] Data Analysis Methods

[0119] The pre-processed data is passed from the server to the generative AI:

[0120] 1. Satellite image analysis: Generative AI analyzes satellite images to visually grasp the extent of damage in the affected area, specifically identifying collapsed buildings and flooded areas.

[0121] 2. Social media data analysis: Using text mining techniques, we analyze social media data to identify the location and condition of disaster victims with the highest urgency.

[0122] 3. Application of damage prediction models: By integrating meteorological and crustal data and using damage prediction models, we estimate the demand for supplies and personnel in the affected areas.

[0123] A means of creating a list of required supplies and personnel

[0124] The server generates the following list based on the analysis results of the generation AI:

[0125] 1. Supplies list: A list of supplies needed in the disaster area, such as drinking water, food, and medicine.

[0126] 2. Personnel list: A list of medical staff, rescue teams, and other personnel needed in the disaster area.

[0127] Methods of informing relevant parties

[0128] The generated list is sent from the server to the relevant parties in the following way:

[0129] 1. Email: Email a list to relevant parties with details of the supplies and personnel needed.

[0130] 2. SMS sending: Send information that requires immediate action via SMS.

[0131] 3. Disaster Prevention Radio System: Some important information is transmitted through the disaster prevention radio system.

[0132] Traffic and road condition estimation tools

[0133] The server analyzes the state of transportation infrastructure in the affected area based on satellite data, and the generating AI does the following:

[0134] 1. Traffic situation analysis: Identifying the damage status of major roads and bridges based on satellite images.

[0135] 2. Optimal route calculation: Calculate the optimal route for the support vehicle to travel safely and quickly, and propose it to the support team in real time.

[0136] Information delivery method

[0137] Information will be distributed to residents in the affected areas from the server in the following ways:

[0138] 1. Distribution to digital information display devices: Evacuation information and safety instructions are transmitted and displayed visually and audibly.

[0139] 2. Delivery to smartphones: Push notifications are sent to residents' smartphones, which users can receive to ensure their own safety and that of their surroundings.

[0140] Specific examples

[0141] For example, in the event of a major earthquake:

[0142] 1. The server instantly collects satellite data, seismometer data, and social media data.

[0143] 2. The server stores these data in a database, removes noise, and standardizes the format.

[0144] 3. The generative AI model analyzes the preprocessed data and identifies the extent of damage in the affected area and the most urgent victims.

[0145] 4. Based on the results of the generation AI, the server creates a list of necessary supplies and personnel and disseminates it to all relevant parties.

[0146] 5. The generative AI model analyzes traffic conditions and suggests optimal travel routes to the support team.

[0147] 6. The server distributes evacuation information to digital information display devices and smartphones, helping to ensure the safety of residents.

[0148] Prompt Sentence Examples

[0149] "When a major earthquake occurs, please analyze the situation in the affected area using satellite data and social media data, and generate a list of supplies that will be needed."

[0150] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0151] Step 1: Data collection

[0152] The server receives satellite data, meteorological data, crustal data, and social networking service data in real time.

[0153] Input: Image data from satellites, data from weather stations and seismometers, and posted data from social networking services.

[0154] Data processing: Obtain satellite images, collect meteorological and crustal data from sensors, and filter related posts using SNS APIs.

[0155] Output: Unified dataset (satellite image files, meteorological data files, crustal data files, SNS post dataset).

[0156] Step 2: Save data

[0157] The server stores the collected data in a centralized database.

[0158] Input: A centralized dataset.

[0159] Data processing: Based on the database design, each data is stored in the corresponding table.

[0160] Output: The saved database with noise.

[0161] Step 3: Data Preprocessing

[0162] The server performs pre-processing of the stored data.

[0163] Input: A noisy stored database.

[0164] Data processing: Unnecessary hashtags and emojis are removed from the social media dataset, and image data is resized and filtered for analysis.

[0165] Output: A denoised and uniformly formatted dataset.

[0166] Step 4: Data analysis

[0167] The server passes the preprocessed data to the generation AI, which analyzes the damage situation.

[0168] Input: A denoised and uniformly formatted dataset.

[0169] Data processing: Generative AI performs image analysis, text mining, and applies predictive models.

[0170] Output: Damage status of affected areas, location and condition of highly urgent victims, and forecast of demand for supplies and personnel.

[0171] Step 5: List Generation

[0172] The server creates a list of required supplies and personnel based on the analysis results of the generation AI.

[0173] Input: Damage situation in the affected area, location and condition of victims with high urgency, predicted demand for supplies and personnel.

[0174] Data processing: Prepare a list of supplies (drinking water, food, medicine, etc.) and personnel (medical staff, rescue teams, etc.).

[0175] Output: List of supplies and personnel needed.

[0176] Step 6: Notify all parties involved

[0177] The server sends the created list to the relevant parties.

[0178] Input: List of supplies and personnel needed.

[0179] Data processing: The list will be sent via email, SMS, and disaster prevention radio system.

[0180] Output: List sent to all parties.

[0181] Step 7: Estimate traffic and road conditions

[0182] The server analyzes the state of the transportation infrastructure, and the generation AI calculates a passable route.

[0183] Input: Satellite data.

[0184] Data processing: Applying algorithms to analyze damage to transportation infrastructure and calculate safe travel routes.

[0185] Output: Optimal travel route for support vehicles.

[0186] Step 8: Distributing information

[0187] The server distributes evacuation information to digital information display devices and mobile communication terminals.

[0188] Input: Evacuation instructions and safety information.

[0189] Data processing: Generate data for push notifications and visual display.

[0190] Output: Evacuation information delivered to digital information display devices and smartphones.

[0191] (Application example 1)

[0192] 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."

[0193] When a disaster occurs, it is necessary to quickly and accurately collect and analyze damage information and disseminate it to all relevant parties, but in the current system, these processes are often not carried out efficiently. In addition, there is a lack of means to appropriately deliver relief supplies and personnel to affected areas and to flexibly respond to changes in traffic conditions. This leads to delays in relief activities and the rescue of victims.

[0194] 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.

[0195] In this invention, the server includes: means for acquiring satellite data, means for acquiring meteorological data and crustal data, means for acquiring social media data, means for centrally storing and preprocessing these data, means for passing the preprocessed data to a generation AI and estimating the damage situation, means for generating a list of necessary supplies and personnel based on the estimation results, means for disseminating the list to relevant parties, means for estimating traffic and road conditions from satellite data and generating passable routes, means for distributing this information to digital signage and mobile information terminal devices, means for continuously monitoring this data and information and redistributing instructions as needed, and means for remotely monitoring the location information and progress of autonomous vehicles and executing operations as needed. This enables the rapid and accurate collection, analysis, and dissemination of information in the event of a disaster, enabling the appropriate delivery of relief supplies and personnel to disaster-stricken areas and flexible response to changes in traffic conditions.

[0196] "Satellite data" refers to high-resolution image data observed by artificial satellites placed in outer space, which can provide extensive visual information on the affected areas.

[0197] "Weather data" refers to data including meteorological information such as rainfall, temperature, wind speed, wind direction, humidity, and atmospheric pressure.

[0198] "Crustal data" refers to data obtained from seismometers and devices that monitor crustal movements, and includes information on crustal movements such as earthquakes and volcanic activity.

[0199] "SNS data" refers to data that includes information such as text, images, and videos posted by users on social networking services, and is used to obtain information about the location and condition of disaster victims.

[0200] "Centralized storage" refers to a method of integrating data collected from multiple data sources into a single database and managing it efficiently.

[0201] The "preprocessing means" is a processing method for removing noise from the collected data and standardizing the format.

[0202] "Generative AI" is an artificial intelligence technology that analyzes collected data and estimates the extent of damage.

[0203] "Means for generating a list of necessary supplies and personnel" refers to a method for creating a specific list of supplies and personnel needed in disaster-stricken areas based on the analysis results of the generation AI.

[0204] "Means of informing relevant parties" refers to distributing the generated list to relevant organizations and individuals via email, SMS, or disaster prevention radio systems.

[0205] "Means for estimating traffic and road conditions" refers to a method of analyzing the state of transportation infrastructure in disaster-stricken areas based on satellite data and calculating passable routes.

[0206] "Digital signage" is a device that uses a digital display to display information in real time.

[0207] A "portable information terminal device" is a portable information processing device such as a smartphone or tablet.

[0208] "Means for remote monitoring" refers to a method of remotely monitoring the location information and progress of autonomous vehicles, etc., using a communication network such as the Internet.

[0209] "Means for performing operations" refers to a method for remotely controlling the operation of an autonomous vehicle.

[0210] The present invention provides a system that enables the rapid and accurate collection, analysis, and dissemination of disaster information when a disaster occurs, and enables efficient relief activities using autonomous vehicles. Specific embodiments for carrying out the present invention will be described below.

[0211] 1. Data Collection Methods

[0212] The server acquires satellite data, meteorological data, crustal data, and SNS data in real time. Satellite data is high-resolution image data acquired from artificial satellites in space, and meteorological data includes information such as rainfall, temperature, wind speed, wind direction, humidity, and air pressure. Crustal data is data acquired from seismometers and crustal movement monitoring devices. SNS data includes disaster-related information posted by users on social networking services.

[0213] 2. Data storage and preprocessing methods

[0214] The server stores the collected data in a centralized database and performs preprocessing such as noise removal using Python and Pandas. Unnecessary hashtags and emojis are removed from social media posts, and satellite image data is optimized for image analysis using OpenCV.

[0215] 3. Data Analysis Methods

[0216] The preprocessed data is passed from the server to a generation AI (using TensorFlow and Scikit-Learn). The generation AI analyzes satellite images to identify collapsed buildings and flooded areas. It also uses text mining techniques to analyze social media data to identify the location and status of victims with high urgency. It also integrates meteorological and crustal data and applies a damage prediction model to estimate the demand for supplies and personnel in the affected area.

[0217] 4. How to create a list of supplies and personnel needed

[0218] Based on the analysis results of the generative AI, the server registers a list of supplies (e.g., drinking water, food, medicine) and personnel (e.g., medical staff, rescue teams) needed in the disaster area in a MySQL database, allowing for a quick understanding of the assistance needed.

[0219] 5. How to inform relevant parties

[0220] The generated list is automatically sent from the server to the relevant parties via email, SMS, and the disaster prevention radio system, allowing them to immediately begin responding.

[0221] 6. Traffic and road condition estimation methods

[0222] The server analyzes the status of the transportation infrastructure in the affected area based on satellite data, and the generation AI uses Google Maps API and Dijkstra's algorithm to calculate the optimal route for support vehicles and instruct the autonomous vehicles on which to take it.

[0223] 7. Means of information distribution

[0224] For residents in the affected areas, safety instructions and evacuation information are sent from the server to digital signage and mobile information terminal devices. The digital signage notifies people in the vicinity of the received information visually and audibly, urging them to take emergency action. The mobile information terminal devices then ensure safety based on the received information.

[0225] 8. Autonomous Vehicle Monitoring and Operational Methods

[0226] The server remotely monitors the location and progress of the autonomous vehicle via WebSocket, and performs operations using Flask and React as needed to streamline support activities.

[0227] Specific examples

[0228] For example, if a large-scale earthquake occurs in Tokyo, the server will immediately collect satellite data and seismograph data. It will also obtain posts from social media and estimate the severity of the damage based on information such as "shaking" and "collapse." The generation AI will analyze this data to grasp the situation in the affected area and generate a list of necessary supplies and personnel. It will also calculate passable routes and provide instructions to autonomous vehicles. At the same time, it will distribute evacuation information to digital signage and mobile information terminal devices, helping to ensure the safety of victims.

[0229] Example prompts for generative AI models

[0230] "Based on satellite image data, seismometer data, and data posted on social media by Shinjuku Ward, please analyze the damage situation in the affected areas and assess the need for supplies. Also, calculate the optimal route and make a plan to deliver relief supplies using autonomous vehicles."

[0231] In this way, this system enables prompt and appropriate support activities when a disaster occurs.

[0232] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0233] Step 1:

[0234] Data collection

[0235] The server collects satellite data, meteorological data, crustal data, and social media data. Specifically, the server obtains high-resolution image data from satellite APIs, receives information such as rainfall and temperature from weather sensors, and acquires seismic motion from seismometers. It also collects disaster-related posts from social networking services via APIs. The input is data from various data sources, and the output is raw data stored centrally.

[0236] Step 2:

[0237] Data storage and preprocessing

[0238] The server stores the collected data in a centralized database. Python and Pandas are used to perform preprocessing to remove noise and standardize the format. Unnecessary hashtags and emojis are removed from social media data, and satellite image data is optimized for analysis using OpenCV. The input is raw, centralized data, and the output is preprocessed, clean data.

[0239] Step 3:

[0240] Data analysis

[0241] The server passes the preprocessed data to the generation AI for analysis. The generation AI (using TensorFlow and Scikit-Learn) analyzes satellite images to identify collapsed buildings and flooded areas. It also uses text mining techniques to analyze social media data to identify the location and status of highly urgent victims. It integrates meteorological data and crustal data and applies a damage prediction model to estimate the demand for supplies and personnel in the affected area. The input is the preprocessed data, and the output is the analysis results of the damage situation and the need for assistance.

[0242] Step 4:

[0243] Creating a list of supplies and personnel

[0244] Based on the analysis results of the generative AI, the server registers a list of supplies and personnel needed in the disaster area in a MySQL database. The supply list includes drinking water, food, medicine, etc., while the personnel list includes medical staff and rescue teams. The input is the analysis results of the disaster situation and the need for assistance, and the output is the generated list of supplies and personnel.

[0245] Step 5:

[0246] Informing all parties concerned

[0247] The server automatically sends the generated list to the relevant parties via email, SMS, and the disaster prevention radio system, allowing them to immediately begin responding. The input is the generated list of supplies and personnel, and the output is notifications to the relevant parties.

[0248] Step 6:

[0249] Traffic and road condition estimates

[0250] The server analyzes the status of the transportation infrastructure in the affected area based on satellite data. The generation AI uses the Google Maps API and Dijkstra's algorithm to calculate the optimal route for support vehicles. The input is satellite data and information on traffic conditions, and the output is the optimal route.

[0251] Step 7:

[0252] Information distribution

[0253] For residents in the affected areas, safety instructions and evacuation information are sent from the server to digital signage and mobile information terminal devices. The digital signage notifies nearby people of the received information visually and audibly, urging them to take emergency action. The mobile information terminal devices ensure safety based on the received information. The input is the analysis results of the generative AI, and the output is the distribution of emergency information to the digital signage and mobile information terminal devices.

[0254] Step 8:

[0255] Autonomous vehicle monitoring and operation

[0256] The server remotely monitors the location and progress of the autonomous vehicle via WebSocket. If necessary, it executes operations using Flask and React to streamline support activities. The input is the real-time location and progress of the autonomous vehicle, and the output is operation instructions as needed.

[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] The present invention is a system that not only quickly and accurately collects and analyzes disaster information when a disaster occurs and disseminates it to relevant parties, but also recognizes the user's emotions and provides appropriate information. An embodiment of this system will be specifically described below.

[0259] 1. Data Collection Methods

[0260] The server periodically acquires satellite data, meteorological data, and crustal data. Satellite data is collected at specified intervals, and meteorological data is acquired in real time from the meteorological bureau's API. Crustal data is automatically collected from seismometers. The server also acquires SNS data from social networking services, collecting posts filtered by related keywords such as "disaster," "earthquake," and "rescue."

[0261] 2. Data storage and preprocessing methods

[0262] The server stores the acquired data in a centralized database. The stored data is pre-processed to remove noise and standardize the format. For example, unnecessary hashtags and emojis are removed from social media posts, and satellite image data is optimized for image analysis.

[0263] 3. Data Analysis Methods

[0264] The preprocessed data is passed from the server to the generation AI, which uses this data to estimate the extent of the damage. It analyzes satellite images to identify collapsed buildings and the extent of flooding. It also uses text mining techniques to analyze social media data to identify the location and status of victims with high urgency. It integrates meteorological data and crustal data and applies a damage prediction model to estimate the demand for supplies and personnel in the affected area.

[0265] 4. How to create a list of supplies and personnel needed

[0266] Based on the analysis results of the generative AI, the server generates a list of supplies (e.g., drinking water, food, medicine) and personnel (e.g., medical staff, rescue teams) needed in the disaster area. This list is saved in XML or JSON format.

[0267] 5. How to inform relevant parties

[0268] The server automatically sends the generated list to the relevant parties via email, SMS, and the disaster prevention radio system. It also has a mechanism to check whether the relevant parties have received the information, and if not, resend it.

[0269] 6. Traffic and road condition estimation methods

[0270] The server analyzes the state of transportation infrastructure in the disaster area based on satellite data, and the AI ​​generator uses this information to calculate the optimal route for relief vehicles to travel safely and quickly.

[0271] 7. Means of information distribution

[0272] For residents in the affected areas, safety instructions and evacuation information are sent from the server to digital signage and smartphones. The terminal (digital signage) notifies people in the vicinity of the received information through audio and visual means, urging them to take emergency action. The user (smartphone) then uses the received information to ensure their own safety and the safety of those around them.

[0273] 8. Emotion Recognition Engine Means

[0274] The server runs an emotion engine to recognize the user's emotions. This emotion engine analyzes social media data and other interactions to identify the user's emotional state. The recognized emotions are analyzed by the generative AI, which then provides the user with appropriate evacuation instructions and reassurance information. For example, if the user is feeling anxious or scared, reassuring messages and support information will be delivered first.

[0275] Specific examples

[0276] For example, if a large-scale earthquake occurs, the server immediately collects and preprocesses satellite data, meteorological data, crustal data, and social media data. The generation AI estimates the damage situation in the affected area and generates a list of needed supplies and personnel. This list is automatically disseminated to relevant parties. Furthermore, the system analyzes traffic conditions based on satellite data and provides optimal routes for support vehicles. The emotion engine also analyzes user emotions and prioritizes the delivery of reassuring information to users who are feeling anxious. For example, if a resident of a disaster-stricken area posts on social media that they are "scared," the emotion engine recognizes this information and provides specific instructions for remaining calm and acting accordingly.

[0277] In this way, this system not only enables rapid and accurate information gathering and support provision in the event of a disaster, but also enables more effective support activities by delivering appropriate information that takes into account the user's emotions.

[0278] The processing flow will be explained below.

[0279] Step 1:

[0280] The server periodically acquires satellite data, meteorological data, and crustal data. Satellite data is high-resolution images and observation data delivered from artificial satellites. Meteorological data is obtained in real time from the Japan Meteorological Agency's API. Crustal data is acquired from seismometers and crustal movement monitoring devices.

[0281] Step 2:

[0282] The server also retrieves social media data, collecting posts from social media platforms such as Twitter and Facebook filtered by disaster-related keywords (e.g., "shaking" and "collapse").

[0283] Step 3:

[0284] The server stores all acquired data in a centralized database, which has the ability to manage data in various formats and make it instantly accessible.

[0285] Step 4:

[0286] The server preprocesses the stored data, for example, removing noise from social media data and normalizing text, and converting satellite image data into a format that is easier to apply to image analysis by adjusting the resolution.

[0287] Step 5:

[0288] The server passes the preprocessed data to the generation AI, which uses this data to estimate the extent of the damage. It identifies the extent of building collapse and flooding through satellite image analysis. It also integrates meteorological and crustal data to assess the situation in the affected area based on a damage prediction model.

[0289] Step 6:

[0290] The generative AI analyzes text from social media data to identify the locations of disaster victims with high urgency, and uses natural language processing technology to analyze the sentiment of posts and determine whether users are feeling anxious or scared.

[0291] Step 7:

[0292] The server generates a list of required supplies and personnel based on the analysis results of the generation AI. This list is created in XML or JSON format and is ready to be sent immediately.

[0293] Step 8:

[0294] The server sends the generated list to the relevant parties via email, SMS, and the disaster prevention radio system. It also checks the status of the transmission and resends if the list has not been received.

[0295] Step 9:

[0296] The server again acquires satellite data and analyzes the state of the transportation infrastructure in the affected area. Passable and impassable routes are identified, and the generation AI calculates the optimal support route.

[0297] Step 10:

[0298] The server runs an emotion engine to recognize the user's emotions, analyzing social media data and other interaction data to identify the user's emotional state.

[0299] Step 11:

[0300] The AI ​​then generates appropriate evacuation instructions and reassurance information based on the user's emotions. For example, if the user expresses emotions such as "fear" or "anxiety," it will prioritize providing messages that promote reassurance.

[0301] Step 12:

[0302] The server distributes the generated evacuation instructions and safety information to digital signage and smartphones, which then display the information in real time using audio and visual displays to notify people in the vicinity.

[0303] Step 13:

[0304] The user (smartphone) receives information from the server and takes action based on the instructions to ensure the safety of themselves and those around them.

[0305] Step 14:

[0306] The server continuously collects data and monitors changes in the situation in the disaster area, redistributing necessary instructions according to the new situation and optimizing relief efforts.

[0307] Example 2

[0308] 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."

[0309] Conventional disaster response systems often had difficulty accurately grasping the extent of the damage, resulting in delays in arranging necessary supplies and personnel. Furthermore, the state of transportation infrastructure was unclear, making it difficult to efficiently move support vehicles. Furthermore, information provided did not take into account the emotions of disaster victims, resulting in a lack of psychological support. The present invention aims to solve these problems.

[0310] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for acquiring satellite data, a means for acquiring meteorological data and crustal data, and a means for acquiring social networking service (SNS) data. This allows data to be centrally stored, and preprocessed data to be passed to the generation AI to estimate the damage situation. Based on the estimation results, a list of necessary supplies and personnel can be generated and disseminated to relevant parties. In addition, the status of transportation infrastructure can be estimated and passable routes can be generated. Furthermore, psychological support can be provided by analyzing the user's emotions and providing appropriate information.

[0311] "Satellite data" refers to image data and remote sensing data obtained from artificial satellites.

[0312] "Weather data" refers to weather observation data obtained from the Japan Meteorological Agency and various meteorological organizations.

[0313] "Crustal data" refers to observational data on crustal movements and seismic activity obtained from seismometers and related equipment.

[0314] "SNS data" refers to the content of posts and user interaction data obtained from social networking services.

[0315] "Centralized storage" means consolidating and storing data obtained from multiple data sources in a single database or data storage.

[0316] "Preprocessing" refers to processing of acquired data to remove noise and standardize the format.

[0317] "Generative AI" refers to artificial intelligence that uses machine learning models and deep learning to analyze data and make inferences.

[0318] "Estimating the damage situation" means predicting the scale and scope of damage caused by a disaster based on collected data.

[0319] "List of supplies and personnel" refers to a list of supplies and personnel required for disaster response.

[0320] "Relevant parties" refers to government agencies, relief organizations, and other related organizations involved in disaster response.

[0321] "Status of transportation infrastructure" refers to information showing the extent to which transportation facilities such as roads and bridges have been affected by the disaster.

[0322] A "passable route" is a route along which support vehicles can travel safely and quickly.

[0323] "Display device" refers to a screen or monitor such as digital signage, and is a device that displays information visually.

[0324] A "communication terminal" is a device for sending and receiving information via wireless communication, such as a smartphone or tablet.

[0325] "Analyzing user emotions" means identifying a user's emotional state based on social media data and other user interaction data.

[0326] "Providing appropriate information" means delivering information such as reassuring messages and evacuation instructions to users based on the analyzed user emotions.

[0327] The present invention is a system that uses data collected from multiple data sources to quickly and accurately analyze the damage situation during a disaster and provide necessary support. This system operates in cooperation with each element: a server, a terminal, and a user.

[0328] First, the server obtains satellite data, meteorological data, and crustal data. Satellite data is collected periodically using remote sensing technology from artificial satellites. Meteorological data is obtained in real time through APIs provided by meteorological agencies, and crustal data is automatically collected from seismometers. The server also obtains related posts from social networking services (SNS). This includes data filtered by keywords such as "disaster," "earthquake," and "rescue."

[0329] The acquired data is stored in a centralized database on a server. This database uses a relational database management system (RDBMS) such as MySQL or PostgreSQL. The stored data is then preprocessed. Specifically, hashtags and emojis that cause noise are removed from social media data, and the resolution and size of the satellite image data are optimized for analysis.

[0330] The preprocessed data is passed to the generation AI, which uses text mining techniques to analyze the social media data and extract posts with high urgency. It also uses satellite image analysis to identify collapsed buildings and flooded areas in the affected areas. It also integrates meteorological and crustal data and applies a damage prediction model to estimate the demand for supplies and personnel in the affected areas.

[0331] Based on the estimation results, the server generates a list of necessary supplies (e.g., drinking water, food, medicine) and personnel (e.g., medical staff, rescue teams). This list is disseminated to relevant parties in JSON or XML format. The server automatically sends this list via email, short message service (SMS), or disaster prevention radio system. It also checks whether the information has been received and resends it if it has not.

[0332] The server then analyzes satellite data to understand the status of the transportation infrastructure and generates routes that support vehicles can take. The AI ​​uses this information to calculate the optimal route and notifies the device from the server.

[0333] The device (digital signage) notifies people in the vicinity with audio and visual information, urging them to take action in the event of an emergency. Users (smartphones) also receive notifications from the device and can take action to ensure their own safety and the safety of those around them.

[0334] Finally, the server runs an emotion engine to recognize the user's emotions. This emotion engine analyzes social media data and other interaction data to identify the user's emotional state. The recognized emotions are analyzed by the generative AI and provide the user with appropriate evacuation instructions and reassurance information. For example, if a user posts on social media expressing the emotion "fear," the emotion engine recognizes this information and provides specific instructions for calm behavior.

[0335] As a concrete example, when a large-scale earthquake occurs, the server immediately collects and preprocesses satellite, meteorological, crustal, and social media data. The generation AI then estimates the extent of damage in the affected area, generates a list of needed supplies and personnel, and automatically notifies relevant parties. It analyzes traffic conditions based on satellite data and provides optimal routes for support vehicles. If the emotion engine recognizes the user's anxiety, it prioritizes the distribution of reassuring information.

[0336] An example prompt is:

[0337] "A large earthquake will occur on October 17, 2023. Please provide the following information about the area affected by this earthquake: a map of the affected area, the number of collapsed buildings, the location and condition of the victims, a list of needed supplies and personnel, the best route for relief vehicles, and specific evacuation instructions based on the emotional state of the victims."

[0338] As described above, the present invention is a system that realizes rapid and accurate information collection and support provision when a disaster occurs, and further provides support that takes into consideration the user's emotions.

[0339] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0340] Step 1: Data collection

[0341] The server collects information from the following data sources. First, remote sensing data and image data are obtained from satellites at specific time intervals. This data is automatically downloaded via API. Next, real-time weather data is collected using the API of meteorological agencies. This includes observational data such as temperature, precipitation, and wind speed. Crustal data is also automatically collected from seismometers, and includes information such as the epicenter, intensity, and time of occurrence of earthquakes. The server also obtains posted data from social networking services, filtered by keywords such as "disaster," "earthquake," and "rescue." This allows the server to obtain a wide range of information and obtain input data to proceed to the next step.

[0342] Step 2: Storing and Preprocessing Data

[0343] The server stores the collected data in a centralized database. The database used is a relational database management system (RDBMS) such as MySQL or PostgreSQL. This stored data is preprocessed. Specifically, unnecessary hashtags and emojis are removed from the social media data and the format is standardized. The resolution and size of the satellite image data are optimized for analysis. As a result of preprocessing, data is obtained in an easy-to-handle format and is used for analysis in the next step.

[0344] Step 3: Data analysis

[0345] The server passes the preprocessed data to the generation AI. The generation AI first analyzes satellite image data to identify collapsed buildings and the extent of flooding. Next, it uses text mining technology to analyze social media data and extract important posts, including the location and status of highly urgent victims. It then integrates meteorological and crustal data and applies a damage prediction model. This allows it to estimate the demand for supplies and personnel in the affected area. The results of this analysis are used in the next step.

[0346] Step 4: Make a list of supplies and personnel needed

[0347] The server generates a list of necessary supplies and personnel based on the analysis results of the generation AI. Specifically, it lists drinking water, food, medicine, medical staff, rescue teams, etc. These lists are saved in XML or JSON format and disseminated to relevant parties in the next step.

[0348] Step 5: Notify all parties involved

[0349] The server automatically sends the generated list to relevant parties via email, SMS, and the disaster prevention radio system. Destinations include government agencies and relief organizations. The server checks whether the information has been received, and if not, resends it. This ensures that the necessary information is delivered to relevant parties quickly and reliably.

[0350] Step 6: Estimate traffic and road conditions

[0351] The server analyzes satellite data to understand the status of transportation infrastructure. The generation AI uses this information to calculate passable routes for support vehicles. Specifically, it detects road closures and bridge damage and generates safe travel routes. This information is used in the next step.

[0352] Step 7: Distributing information

[0353] The server distributes safety instructions and evacuation information to residents in the affected area via digital signage and smartphones. The devices then notify nearby people of the received information via audio and visual means, urging them to take emergency action. Users can then ensure their own safety and that of those around them based on the information they receive, enabling rapid response.

[0354] Step 8: Emotion Recognition

[0355] The server runs an emotion engine to recognize the user's emotions. The emotion engine analyzes social media data and other interaction data to identify the user's emotional state. The recognized emotions are analyzed by the generative AI, which then provides the user with appropriate evacuation instructions and reassurance information. For example, if the user is feeling anxious or scared, reassuring messages and support information will be delivered first.

[0356] In this way, by carrying out specific processing for each step, this system is able to quickly and accurately collect information and provide support when a disaster occurs, and can also provide support that takes into account the user's emotions.

[0357] (Application example 2)

[0358] 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."

[0359] There are existing systems that quickly and accurately collect and analyze disaster information when a disaster occurs and disseminate it to relevant parties, but many of them do not take into account the emotional state of the user, making it difficult to provide appropriate evacuation instructions or reassurance information. In particular, when users are feeling anxious or scared, simply providing information makes it difficult to evacuate or respond effectively. Furthermore, there are only a limited number of systems that can adequately provide optimal routes for support vehicles or continuously monitor and redistribute data. There is a need to solve these issues.

[0360] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0361] In this invention, the server includes a means for acquiring satellite data, a means for acquiring meteorological data and crustal data, and a means for acquiring SNS data, which enables rapid and accurate information collection and provision of information that takes into account the user's feelings when a disaster occurs.

[0362] "Satellite Data" refers to image data and information obtained from satellites to monitor conditions on Earth.

[0363] "Weather Data" means data relating to weather and weather conditions obtained from meteorological agencies or other weather observation agencies.

[0364] "Crustal data" refers to data about the movement and vibration of the Earth's crust obtained from seismometers and geological observation equipment.

[0365] "SNS data" refers to information such as user posts and messages obtained from social networking services.

[0366] "Preprocessing" refers to processing to remove noise from acquired data and standardize the data format.

[0367] "Generative AI" refers to artificial intelligence systems that use machine learning models to generate new information and inferences.

[0368] "Estimating the damage situation" refers to the process of analyzing data to estimate the scope and extent of damage caused by a disaster.

[0369] "List of supplies and personnel" refers to a list of supplies (drinking water, food, medicine, etc.) and personnel (medical staff, rescue teams, etc.) needed for disaster response.

[0370] "Publicizing" refers to the act of notifying and sharing important information with relevant parties.

[0371] "Traffic and road condition estimation" refers to the analysis of satellite data to assess road passability and the presence of obstacles.

[0372] A "passable route" refers to the optimal route along which support vehicles can travel safely and quickly.

[0373] "Information distribution" refers to the act of sending emergency information and evacuation instructions to devices such as digital signage and smartphones.

[0374] "Emotion recognition" refers to the process of analyzing and determining a user's emotional state from their posts and messages.

[0375] "Re-delivery of instructions" refers to the act of sending information again if the initial delivery is not successful or if necessary.

[0376] This invention is a system that not only quickly and accurately collects and analyzes disaster information when a disaster occurs and disseminates it to relevant parties, but also recognizes the user's emotions and provides appropriate information. Specific embodiments are shown below.

[0377] 1. Data Collection Methods

[0378] The server periodically acquires satellite data, meteorological data, and crustal data. Satellite data is collected at specified intervals, and meteorological data is acquired in real time from the meteorological bureau's API. Crustal data is automatically collected from seismometers. The server also acquires SNS data from social networking services, collecting posts filtered by related keywords such as "disaster," "earthquake," and "rescue."

[0379] 2. Data storage and preprocessing methods

[0380] The server stores the acquired data in a centralized database. The stored data is pre-processed to remove noise and standardize the format. For example, unnecessary hashtags and emojis are removed from social media posts, and satellite image data is optimized for image analysis.

[0381] 3. Data Analysis Methods

[0382] The preprocessed data is passed from the server to the generation AI, which uses this data to estimate the extent of the damage. It analyzes satellite images to identify collapsed buildings and the extent of flooding. It also uses text mining techniques to analyze social media data to identify the location and status of victims with high urgency. It integrates meteorological data and crustal data and applies a damage prediction model to estimate the demand for supplies and personnel in the affected area.

[0383] 4. How to create a list of supplies and personnel needed

[0384] Based on the analysis results of the generative AI, the server generates a list of supplies (e.g., drinking water, food, medicine) and personnel (e.g., medical staff, rescue teams) needed in the disaster area. This list is saved in XML or JSON format.

[0385] 5. How to inform relevant parties

[0386] The server automatically sends the generated list to the relevant parties via email, SMS, and the disaster prevention radio system. It also has a mechanism to check whether the relevant parties have received the information, and if not, resend it.

[0387] 6. Traffic and road condition estimation methods

[0388] The server analyzes the state of transportation infrastructure in the disaster area based on satellite data, and the AI ​​generator uses this information to calculate the optimal route for relief vehicles to travel safely and quickly.

[0389] 7. Means of information distribution

[0390] For residents in the affected areas, safety instructions and evacuation information are sent from the server to digital signage and smartphones. The terminal (digital signage) notifies people in the vicinity of the received information through audio and visual means, urging them to take emergency action. The user (smartphone) then uses the received information to ensure their own safety and the safety of those around them.

[0391] 8. Emotion Recognition Engine Means

[0392] The server runs an emotion engine to recognize the user's emotions. This emotion engine analyzes social media data and other interactions to identify the user's emotional state. The recognized emotions are analyzed by the generative AI, which then provides the user with appropriate evacuation instructions and reassurance information. For example, if the user is feeling anxious or scared, reassuring messages and support information will be delivered first.

[0393] Hardware and software used

[0394] Hardware: Servers, smartphones, digital signage

[0395] Software: TensorFlow (generative AI model), OpenCV (image analysis), NLTK (text mining), Flask (backend API construction)

[0396] Specific examples

[0397] For example, if a large-scale earthquake occurs, the server immediately collects and preprocesses satellite data, meteorological data, crustal data, and social media data. The generation AI estimates the damage situation in the affected area and generates a list of needed supplies and personnel. This list is automatically disseminated to relevant parties. Furthermore, the AI ​​analyzes traffic conditions based on satellite data and provides optimal routes for support vehicles. The emotion engine also analyzes user emotions and prioritizes the delivery of reassuring information to users who are feeling anxious. For example, if a resident of a disaster-stricken area posts on social media that they are "scared," the emotion engine recognizes this information and provides specific instructions for calm action.

[0398] Prompt Sentence Examples

[0399] The generative AI model is sent the following prompt:

[0400] Satellite image path: / path / to / satellite_image.jpg

[0401] Text data: "I'm scared, the earthquake was really strong!"

[0402] When this prompt is sent, the application returns the damage situation and emotion recognition results, and provides the user with appropriate evacuation instructions and reassurance information.

[0403] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0404] Step 1:

[0405] The server acquires satellite data, meteorological data, crustal data, and social media data. When the server acquires these data, satellite data is collected at specified intervals, and meteorological data is acquired in real time from the meteorological agency's API. Crustal data is collected as observation data from seismometers, and social media data is acquired by filtering posts by related keywords. The input is data from each data source, and the output is the acquired dataset.

[0406] Step 2:

[0407] The server stores the acquired data in a centralized database and performs preprocessing, which includes removing unnecessary hashtags and emojis from social media data and optimizing satellite image data for image analysis. The input is the acquired dataset, and the output is the preprocessed dataset.

[0408] Step 3:

[0409] The server passes the preprocessed data to the generation AI, which estimates the damage situation. The generation AI analyzes satellite images to identify collapsed buildings and flooded areas, and uses text mining to identify the location and status of victims with high urgency from social media data. The input is the preprocessed dataset, and the output is estimated damage situation data.

[0410] Step 4:

[0411] The server generates a list of necessary supplies and personnel based on the results of the AI's estimations. The list includes items such as drinking water, food, and medicine, and is saved in XML or JSON format. The input is estimated damage data, and the output is a list of supplies and personnel.

[0412] Step 5:

[0413] The server automatically sends the generated list to relevant parties via email, SMS, and the disaster prevention radio system. It also checks whether the information has been received, and resends it if not. The input is a list of supplies and personnel, and the output is notification confirmation data.

[0414] Step 6:

[0415] The server analyzes the state of the transportation infrastructure in the disaster area based on satellite data, and the generating AI calculates the optimal route for support vehicles to travel safely and quickly. The input is satellite data, and the output is passable route information.

[0416] Step 7:

[0417] Safety instructions and evacuation information are delivered to digital signage and smartphones. The terminal (digital signage) notifies people in the vicinity with audio and visual information, and the user (smartphone) ensures their own safety and the safety of those around them based on the information received. The input is evacuation information, and the output is the user's actions.

[0418] Step 8:

[0419] The server runs an emotion engine that analyzes social media data and other interactions to identify the user's emotional state. The emotion engine passes the recognized emotion to a generative AI, which then provides the user with appropriate evacuation instructions and reassurance information. The input is social media data, and the output is the user's emotional state and appropriate instructions and information.

[0420] 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.

[0421] 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.

[0422] 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.

[0423] [Second embodiment]

[0424] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0425] 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.

[0426] 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).

[0427] 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.

[0428] 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.

[0429] 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).

[0430] 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.

[0431] 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.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] 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."

[0436] The present invention is a system for quickly and accurately collecting and analyzing disaster information when a disaster occurs, and disseminating the information to relevant parties. An embodiment of this system will now be described in detail.

[0437] 1. Data Collection Methods

[0438] The server acquires satellite data, meteorological data, and crustal data in real time. Satellite data is high-resolution image data observed by artificial satellites in space, which allows for extensive visual information on the disaster-stricken area. Meteorological data includes meteorological information such as rainfall, temperature, wind speed, wind direction, humidity, and air pressure. Meanwhile, crustal data is data acquired from seismometers and devices that monitor crustal movements. The server also collects social media data and acquires disaster-related information posted by users on social networking services.

[0439] 2. Data storage and preprocessing methods

[0440] The server stores the collected data in a centralized database. The stored data is preprocessed to remove noise and standardize its format. For example, unnecessary hashtags and emojis are removed from social media posts, and satellite image data is optimized for image analysis.

[0441] 3. Data Analysis Methods

[0442] The preprocessed data is passed from the server to the generation AI. The generation AI analyzes satellite images to visually grasp the extent of damage in the affected areas. For example, it identifies collapsed buildings and flooded areas. It then analyzes social media data using text mining techniques to identify the location and status of victims with high urgency. By integrating meteorological data and crustal data and applying a damage prediction model, it estimates the demand for supplies and personnel in the affected areas.

[0443] 4. How to create a list of supplies and personnel needed

[0444] Based on the analysis results of the generative AI, the server generates a list of supplies (e.g., drinking water, food, medicine) and personnel (e.g., medical staff, rescue teams) needed in the disaster area, allowing users to quickly determine what is needed where.

[0445] 5. How to inform relevant parties

[0446] The generated list is automatically sent from the server to the relevant parties via email, SMS, and the disaster prevention radio system, and includes details of the supplies and personnel needed, allowing the relevant parties to immediately begin responding.

[0447] 6. Traffic and road condition estimation methods

[0448] The server analyzes the state of transportation infrastructure in the disaster area based on satellite data, and the generating AI uses this information to calculate the optimal route for safe and fast movement of support vehicles and proposes it to the support team.

[0449] 7. Means of information distribution

[0450] For residents in the affected areas, safety instructions and evacuation information are sent from the server to digital signage and smartphones. The terminal (digital signage) notifies people in the vicinity of the received information visually and audibly, urging them to take emergency action. The user (smartphone) then uses the received information to ensure their own safety and the safety of those around them.

[0451] Specific examples

[0452] For example, when a major earthquake occurs, the server immediately collects satellite data and seismograph data. It also obtains posts from social media such as "Shaking" and "Collapse," and the generation AI estimates the extent of damage in the affected area. Based on this, it generates a list of necessary supplies and personnel and automatically disseminates this information to relevant parties. It also calculates passable routes and suggests them to support vehicles. At the same time, it distributes evacuation information to digital signage and smartphones, helping to ensure the safety of victims.

[0453] In this way, this system enables prompt and appropriate support activities in the event of a disaster.

[0454] The processing flow will be explained below.

[0455] Step 1:

[0456] The server periodically acquires satellite data, meteorological data, and crustal data. Satellite data is recorded at specified intervals, and meteorological data is acquired in real time from the Meteorological Agency's API. Crustal data is automatically collected from observation data from seismometers.

[0457] Step 2:

[0458] The server also simultaneously acquires social media data, using public APIs such as Twitter and Facebook to collect posts filtered by keywords such as "disaster," "earthquake," and "rescue."

[0459] Step 3:

[0460] The server stores the acquired data in a centralized database, which has an intermediate format for integrating different data formats, making all data immediately accessible.

[0461] Step 4:

[0462] The server pre-processes the stored data, for example removing noise from social media data and cleaning up text data, and adjusts the resolution of satellite image data to prepare it for image analysis.

[0463] Step 5:

[0464] The server passes the preprocessed data to the generation AI, which then uses this data to begin estimating the extent of the damage. First, it analyzes satellite images to identify collapsed buildings and the extent of flooding.

[0465] Step 6:

[0466] The generative AI analyzes text from social media data to extract the location information of disaster victims with high urgency, using natural language processing technology to identify location information by analyzing the frequency and importance of related keywords.

[0467] Step 7:

[0468] The generative AI integrates meteorological and crustal data and applies damage prediction models to estimate supply shortages and personnel needs in affected areas.

[0469] Step 8:

[0470] The server generates a list of required supplies and personnel based on the estimation results of the generation AI. The generated list is saved in XML or JSON format.

[0471] Step 9:

[0472] The server sends the generated list to the relevant parties via email, SMS, and the disaster prevention radio system. It also checks whether the relevant parties have received the information, and if not, resends it.

[0473] Step 10:

[0474] The server then acquires satellite data again and analyzes the current traffic and road conditions, thereby identifying passable and impassable roads.

[0475] Step 11:

[0476] The generation AI calculates the optimal route for the support vehicle to travel quickly, and the calculated route is updated in real time.

[0477] Step 12:

[0478] The server distributes safety instructions and evacuation information to digital signage and smartphones, and the digital signage notifies those in the vicinity with audio and visual information.

[0479] Step 13:

[0480] The user (smartphone) receives information from the server and takes action based on the instructions to ensure the safety of themselves and those around them.

[0481] Step 14:

[0482] The server continuously collects data and monitors changes in the situation in the affected area, then re-distributes necessary instructions according to the new situation.

[0483] Example 1

[0484] 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."

[0485] When a disaster occurs, it is necessary to quickly and accurately collect and analyze damage information and disseminate it to all relevant parties. However, with conventional systems, data collection and analysis are often carried out as separate processes, making it difficult to centralize information management and analyze it in real time. In addition, there is a time lag when estimating traffic conditions in disaster-stricken areas and proposing passable routes, which hinders rapid relief efforts.

[0486] 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.

[0487] In this invention, the server includes: means for acquiring satellite data, means for acquiring meteorological and crustal data, means for acquiring social networking service data, means for centrally storing and preprocessing these data; means for passing the preprocessed data to a generation AI and estimating the damage situation; means for generating a list of necessary supplies and personnel based on the estimation results; means for disseminating the list to relevant parties; means for estimating traffic and road conditions from satellite data and generating passable routes; means for distributing this information to digital information display devices and mobile communication devices; and means for continuously monitoring this data and information and redistributing instructions as necessary. This enables centralized data management and real-time information analysis and dissemination. Furthermore, traffic condition estimation and route suggestions enable rapid relief activities.

[0488] "Satellite data" refers to high-resolution image data obtained from satellites in space, providing a wide range of visual information.

[0489] "Weather data" refers to data including meteorological information such as rainfall, temperature, wind speed, wind direction, humidity, and atmospheric pressure.

[0490] "Crustal data" refers to data obtained from seismometers and devices that monitor crustal movements, and includes information such as the magnitude and epicenter of an earthquake.

[0491] "Social networking service data" refers to data that includes disaster-related information posted by users on social networking services.

[0492] "Means of centralized storage" refers to a means of storing collected data in a single database.

[0493] "Preprocessing means" refers to a means for removing noise from the stored data and standardizing it into a format that is easy to analyze.

[0494] "Generative AI" is an artificial intelligence model that analyzes preprocessed data and estimates the damage situation.

[0495] "Means for estimating the damage situation" refers to a means of using generative AI to identify the damage situation in the affected areas and the location and condition of victims with high urgency.

[0496] The "means for generating a list of necessary supplies and personnel" is a means for creating a list of supplies and personnel required in the disaster-stricken area based on the estimated damage situation.

[0497] "Means of informing relevant parties" refers to the means of notifying relevant parties of the generated lists of supplies and personnel via email, SMS, and disaster prevention radio systems.

[0498] "Means for estimating traffic and road conditions" refers to analyzing the state of transportation infrastructure based on satellite data and calculating passable routes.

[0499] A "digital information display device" is an electronic public sign that displays disaster information and evacuation instructions visually and audibly.

[0500] A "mobile communication terminal" is a portable communication device such as a smartphone, and is a terminal for receiving disaster information.

[0501] "Continuous monitoring measures" are measures that constantly check collected data and information and redeliver instructions if the situation changes.

[0502] This invention is a system for collecting and analyzing disaster information quickly and accurately when a disaster occurs, and disseminating it to relevant parties. Specific embodiments of this system will be described in detail below.

[0503] First, the hardware and software that provide the foundation for the entire system consists of servers, mobile communication terminals, digital information display devices, etc. These devices work together to provide the infrastructure for centrally managing and analyzing collected data.

[0504] Data collection methods

[0505] The server collects the following data in real time:

[0506] 1. Satellite data collection: Receiving high-resolution image data from satellites in space. This image data is crucial for visually understanding the overall situation of the affected area.

[0507] 2. Meteorological Data Collection: Meteorological data such as rainfall, temperature, wind speed, wind direction, humidity, and air pressure are obtained from weather observation stations.

[0508] 3. Collecting crustal data: Receive crustal data from seismometers and other devices that monitor crustal movements, including information on the magnitude and epicenter of earthquakes.

[0509] 4. Social networking service data collection: We collect disaster-related information posted by users on social networking services. Specifically, we collect posts such as "Shaking" and "Collapse" in real time.

[0510] Data storage and preprocessing methods

[0511] The server stores the collected data in a centralized database, and then performs the following pre-processing:

[0512] 1. Noise removal: Remove unnecessary information from the stored data. For example, remove hashtags and emojis from social media data.

[0513] 2. Format unification: Data formats are standardized for analysis. For example, text data is converted into a fixed format, and image data is adjusted to a format that is easy to analyze.

[0514] Data Analysis Methods

[0515] The pre-processed data is passed from the server to the generative AI:

[0516] 1. Satellite image analysis: Generative AI analyzes satellite images to visually grasp the extent of damage in the affected area, specifically identifying collapsed buildings and flooded areas.

[0517] 2. Social media data analysis: Using text mining techniques, we analyze social media data to identify the location and condition of disaster victims with the highest urgency.

[0518] 3. Application of damage prediction models: By integrating meteorological and crustal data and using damage prediction models, we estimate the demand for supplies and personnel in the affected areas.

[0519] A means of creating a list of required supplies and personnel

[0520] The server generates the following list based on the analysis results of the generation AI:

[0521] 1. Supplies list: A list of supplies needed in the disaster area, such as drinking water, food, and medicine.

[0522] 2. Personnel list: A list of medical staff, rescue teams, and other personnel needed in the disaster area.

[0523] Methods of informing relevant parties

[0524] The generated list is sent from the server to the relevant parties in the following way:

[0525] 1. Email: Email a list to relevant parties with details of the supplies and personnel needed.

[0526] 2. SMS sending: Send information that requires immediate action via SMS.

[0527] 3. Disaster Prevention Radio System: Some important information is transmitted through the disaster prevention radio system.

[0528] Traffic and road condition estimation tools

[0529] The server analyzes the state of transportation infrastructure in the affected area based on satellite data, and the generating AI does the following:

[0530] 1. Traffic situation analysis: Identifying the damage status of major roads and bridges based on satellite images.

[0531] 2. Optimal route calculation: Calculate the optimal route for the support vehicle to travel safely and quickly, and propose it to the support team in real time.

[0532] Information delivery method

[0533] Information will be distributed to residents in the affected areas from the server in the following ways:

[0534] 1. Distribution to digital information display devices: Evacuation information and safety instructions are transmitted and displayed visually and audibly.

[0535] 2. Delivery to smartphones: Push notifications are sent to residents' smartphones, which users can receive to ensure their own safety and that of their surroundings.

[0536] Specific examples

[0537] For example, in the event of a major earthquake:

[0538] 1. The server instantly collects satellite data, seismometer data, and social media data.

[0539] 2. The server stores these data in a database, removes noise, and standardizes the format.

[0540] 3. The generative AI model analyzes the preprocessed data and identifies the extent of damage in the affected area and the most urgent victims.

[0541] 4. Based on the results of the generation AI, the server creates a list of necessary supplies and personnel and disseminates it to all relevant parties.

[0542] 5. The generative AI model analyzes traffic conditions and suggests optimal travel routes to the support team.

[0543] 6. The server distributes evacuation information to digital information display devices and smartphones, helping to ensure the safety of residents.

[0544] Prompt Sentence Examples

[0545] "When a major earthquake occurs, please analyze the situation in the affected area using satellite data and social media data, and generate a list of supplies that will be needed."

[0546] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0547] Step 1: Data collection

[0548] The server receives satellite data, meteorological data, crustal data, and social networking service data in real time.

[0549] Input: Image data from satellites, data from weather stations and seismometers, and posted data from social networking services.

[0550] Data processing: Obtain satellite images, collect meteorological and crustal data from sensors, and filter related posts using SNS APIs.

[0551] Output: Unified dataset (satellite image files, meteorological data files, crustal data files, SNS post dataset).

[0552] Step 2: Save data

[0553] The server stores the collected data in a centralized database.

[0554] Input: A centralized dataset.

[0555] Data processing: Based on the database design, each data is stored in the corresponding table.

[0556] Output: The saved database with noise.

[0557] Step 3: Data Preprocessing

[0558] The server performs pre-processing of the stored data.

[0559] Input: A noisy stored database.

[0560] Data processing: Unnecessary hashtags and emojis are removed from the social media dataset, and image data is resized and filtered for analysis.

[0561] Output: A denoised and uniformly formatted dataset.

[0562] Step 4: Data analysis

[0563] The server passes the preprocessed data to the generation AI, which analyzes the damage situation.

[0564] Input: A denoised and uniformly formatted dataset.

[0565] Data processing: Generative AI performs image analysis, text mining, and applies predictive models.

[0566] Output: Damage status of affected areas, location and condition of highly urgent victims, and forecast of demand for supplies and personnel.

[0567] Step 5: List Generation

[0568] The server creates a list of required supplies and personnel based on the analysis results of the generation AI.

[0569] Input: Damage situation in the affected area, location and condition of victims with high urgency, predicted demand for supplies and personnel.

[0570] Data processing: Prepare a list of supplies (drinking water, food, medicine, etc.) and personnel (medical staff, rescue teams, etc.).

[0571] Output: List of supplies and personnel needed.

[0572] Step 6: Notify all parties involved

[0573] The server sends the created list to the relevant parties.

[0574] Input: List of supplies and personnel needed.

[0575] Data processing: The list will be sent via email, SMS, and disaster prevention radio system.

[0576] Output: List sent to all parties.

[0577] Step 7: Estimate traffic and road conditions

[0578] The server analyzes the state of the transportation infrastructure, and the generation AI calculates a passable route.

[0579] Input: Satellite data.

[0580] Data processing: Applying algorithms to analyze damage to transportation infrastructure and calculate safe travel routes.

[0581] Output: Optimal travel route for support vehicles.

[0582] Step 8: Distributing information

[0583] The server distributes evacuation information to digital information display devices and mobile communication terminals.

[0584] Input: Evacuation instructions and safety information.

[0585] Data processing: Generate data for push notifications and visual display.

[0586] Output: Evacuation information delivered to digital information display devices and smartphones.

[0587] (Application example 1)

[0588] 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."

[0589] When a disaster occurs, it is necessary to quickly and accurately collect and analyze damage information and disseminate it to all relevant parties, but in the current system, these processes are often not carried out efficiently. In addition, there is a lack of means to appropriately deliver relief supplies and personnel to affected areas and to flexibly respond to changes in traffic conditions. This leads to delays in relief activities and the rescue of victims.

[0590] 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.

[0591] In this invention, the server includes: means for acquiring satellite data, means for acquiring meteorological data and crustal data, means for acquiring social media data, means for centrally storing and preprocessing these data, means for passing the preprocessed data to a generation AI and estimating the damage situation, means for generating a list of necessary supplies and personnel based on the estimation results, means for disseminating the list to relevant parties, means for estimating traffic and road conditions from satellite data and generating passable routes, means for distributing this information to digital signage and mobile information terminal devices, means for continuously monitoring this data and information and redistributing instructions as needed, and means for remotely monitoring the location information and progress of autonomous vehicles and executing operations as needed. This enables the rapid and accurate collection, analysis, and dissemination of information in the event of a disaster, enabling the appropriate delivery of relief supplies and personnel to disaster-stricken areas and flexible response to changes in traffic conditions.

[0592] "Satellite data" refers to high-resolution image data observed by artificial satellites placed in outer space, which can provide extensive visual information on the affected areas.

[0593] "Weather data" refers to data including meteorological information such as rainfall, temperature, wind speed, wind direction, humidity, and atmospheric pressure.

[0594] "Crustal data" refers to data obtained from seismometers and devices that monitor crustal movements, and includes information on crustal movements such as earthquakes and volcanic activity.

[0595] "SNS data" refers to data that includes information such as text, images, and videos posted by users on social networking services, and is used to obtain information about the location and condition of disaster victims.

[0596] "Centralized storage" refers to a method of integrating data collected from multiple data sources into a single database and managing it efficiently.

[0597] The "preprocessing means" is a processing method for removing noise from the collected data and standardizing the format.

[0598] "Generative AI" is an artificial intelligence technology that analyzes collected data and estimates the extent of damage.

[0599] "Means for generating a list of necessary supplies and personnel" refers to a method for creating a specific list of supplies and personnel needed in disaster-stricken areas based on the analysis results of the generation AI.

[0600] "Means of informing relevant parties" refers to distributing the generated list to relevant organizations and individuals via email, SMS, or disaster prevention radio systems.

[0601] "Means for estimating traffic and road conditions" refers to a method of analyzing the state of transportation infrastructure in disaster-stricken areas based on satellite data and calculating passable routes.

[0602] "Digital signage" is a device that uses a digital display to display information in real time.

[0603] A "portable information terminal device" is a portable information processing device such as a smartphone or tablet.

[0604] "Means for remote monitoring" refers to a method of remotely monitoring the location information and progress of autonomous vehicles, etc., using a communication network such as the Internet.

[0605] "Means for performing operations" refers to a method for remotely controlling the operation of an autonomous vehicle.

[0606] The present invention provides a system that enables the rapid and accurate collection, analysis, and dissemination of disaster information when a disaster occurs, and enables efficient relief activities using autonomous vehicles. Specific embodiments for carrying out the present invention will be described below.

[0607] 1. Data Collection Methods

[0608] The server acquires satellite data, meteorological data, crustal data, and SNS data in real time. Satellite data is high-resolution image data acquired from artificial satellites in space, and meteorological data includes information such as rainfall, temperature, wind speed, wind direction, humidity, and air pressure. Crustal data is data acquired from seismometers and crustal movement monitoring devices. SNS data includes disaster-related information posted by users on social networking services.

[0609] 2. Data storage and preprocessing methods

[0610] The server stores the collected data in a centralized database and performs preprocessing such as noise removal using Python and Pandas. Unnecessary hashtags and emojis are removed from social media posts, and satellite image data is optimized for image analysis using OpenCV.

[0611] 3. Data Analysis Methods

[0612] The preprocessed data is passed from the server to a generation AI (using TensorFlow and Scikit-Learn). The generation AI analyzes satellite images to identify collapsed buildings and flooded areas. It also uses text mining techniques to analyze social media data to identify the location and status of victims with high urgency. It also integrates meteorological and crustal data and applies a damage prediction model to estimate the demand for supplies and personnel in the affected area.

[0613] 4. How to create a list of supplies and personnel needed

[0614] Based on the analysis results of the generative AI, the server registers a list of supplies (e.g., drinking water, food, medicine) and personnel (e.g., medical staff, rescue teams) needed in the disaster area in a MySQL database, allowing for a quick understanding of the assistance needed.

[0615] 5. How to inform relevant parties

[0616] The generated list is automatically sent from the server to the relevant parties via email, SMS, and the disaster prevention radio system, allowing them to immediately begin responding.

[0617] 6. Traffic and road condition estimation methods

[0618] The server analyzes the status of the transportation infrastructure in the affected area based on satellite data, and the generation AI uses Google Maps API and Dijkstra's algorithm to calculate the optimal route for support vehicles and instruct the autonomous vehicles on which to take it.

[0619] 7. Means of information distribution

[0620] For residents in the affected areas, safety instructions and evacuation information are sent from the server to digital signage and mobile information terminal devices. The digital signage notifies people in the vicinity of the received information visually and audibly, urging them to take emergency action. The mobile information terminal devices then ensure safety based on the received information.

[0621] 8. Autonomous Vehicle Monitoring and Operational Methods

[0622] The server remotely monitors the location and progress of the autonomous vehicle via WebSocket, and performs operations using Flask and React as needed to streamline support activities.

[0623] Specific examples

[0624] For example, if a large-scale earthquake occurs in Tokyo, the server will immediately collect satellite data and seismograph data. It will also obtain posts from social media and estimate the severity of the damage based on information such as "shaking" and "collapse." The generation AI will analyze this data to grasp the situation in the affected area and generate a list of necessary supplies and personnel. It will also calculate passable routes and provide instructions to autonomous vehicles. At the same time, it will distribute evacuation information to digital signage and mobile information terminal devices, helping to ensure the safety of victims.

[0625] Example prompts for generative AI models

[0626] "Based on satellite image data, seismometer data, and data posted on social media by Shinjuku Ward, please analyze the damage situation in the affected areas and assess the need for supplies. Also, calculate the optimal route and make a plan to deliver relief supplies using autonomous vehicles."

[0627] In this way, this system enables prompt and appropriate support activities when a disaster occurs.

[0628] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0629] Step 1:

[0630] Data collection

[0631] The server collects satellite data, meteorological data, crustal data, and social media data. Specifically, the server obtains high-resolution image data from satellite APIs, receives information such as rainfall and temperature from weather sensors, and acquires seismic motion from seismometers. It also collects disaster-related posts from social networking services via APIs. The input is data from various data sources, and the output is raw data stored centrally.

[0632] Step 2:

[0633] Data storage and preprocessing

[0634] The server stores the collected data in a centralized database. Python and Pandas are used to perform preprocessing to remove noise and standardize the format. Unnecessary hashtags and emojis are removed from social media data, and satellite image data is optimized for analysis using OpenCV. The input is raw, centralized data, and the output is preprocessed, clean data.

[0635] Step 3:

[0636] Data analysis

[0637] The server passes the preprocessed data to the generation AI for analysis. The generation AI (using TensorFlow and Scikit-Learn) analyzes satellite images to identify collapsed buildings and flooded areas. It also uses text mining techniques to analyze social media data to identify the location and status of highly urgent victims. It integrates meteorological data and crustal data and applies a damage prediction model to estimate the demand for supplies and personnel in the affected area. The input is the preprocessed data, and the output is the analysis results of the damage situation and the need for assistance.

[0638] Step 4:

[0639] Creating a list of supplies and personnel

[0640] Based on the analysis results of the generative AI, the server registers a list of supplies and personnel needed in the disaster area in a MySQL database. The supply list includes drinking water, food, medicine, etc., while the personnel list includes medical staff and rescue teams. The input is the analysis results of the disaster situation and the need for assistance, and the output is the generated list of supplies and personnel.

[0641] Step 5:

[0642] Informing all parties concerned

[0643] The server automatically sends the generated list to the relevant parties via email, SMS, and the disaster prevention radio system, allowing them to immediately begin responding. The input is the generated list of supplies and personnel, and the output is notifications to the relevant parties.

[0644] Step 6:

[0645] Traffic and road condition estimates

[0646] The server analyzes the status of the transportation infrastructure in the affected area based on satellite data. The generation AI uses the Google Maps API and Dijkstra's algorithm to calculate the optimal route for support vehicles. The input is satellite data and information on traffic conditions, and the output is the optimal route.

[0647] Step 7:

[0648] Information distribution

[0649] For residents in the affected areas, safety instructions and evacuation information are sent from the server to digital signage and mobile information terminal devices. The digital signage notifies nearby people of the received information visually and audibly, urging them to take emergency action. The mobile information terminal devices ensure safety based on the received information. The input is the analysis results of the generative AI, and the output is the distribution of emergency information to the digital signage and mobile information terminal devices.

[0650] Step 8:

[0651] Autonomous vehicle monitoring and operation

[0652] The server remotely monitors the location and progress of the autonomous vehicle via WebSocket. If necessary, it executes operations using Flask and React to streamline support activities. The input is the real-time location and progress of the autonomous vehicle, and the output is operation instructions as needed.

[0653] 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.

[0654] The present invention is a system that not only quickly and accurately collects and analyzes disaster information when a disaster occurs and disseminates it to relevant parties, but also recognizes the user's emotions and provides appropriate information. An embodiment of this system will be specifically described below.

[0655] 1. Data Collection Methods

[0656] The server periodically acquires satellite data, meteorological data, and crustal data. Satellite data is collected at specified intervals, and meteorological data is acquired in real time from the meteorological bureau's API. Crustal data is automatically collected from seismometers. The server also acquires SNS data from social networking services, collecting posts filtered by related keywords such as "disaster," "earthquake," and "rescue."

[0657] 2. Data storage and preprocessing methods

[0658] The server stores the acquired data in a centralized database. The stored data is pre-processed to remove noise and standardize the format. For example, unnecessary hashtags and emojis are removed from social media posts, and satellite image data is optimized for image analysis.

[0659] 3. Data Analysis Methods

[0660] The preprocessed data is passed from the server to the generation AI, which uses this data to estimate the extent of the damage. It analyzes satellite images to identify collapsed buildings and the extent of flooding. It also uses text mining techniques to analyze social media data to identify the location and status of victims with high urgency. It integrates meteorological data and crustal data and applies a damage prediction model to estimate the demand for supplies and personnel in the affected area.

[0661] 4. How to create a list of supplies and personnel needed

[0662] Based on the analysis results of the generative AI, the server generates a list of supplies (e.g., drinking water, food, medicine) and personnel (e.g., medical staff, rescue teams) needed in the disaster area. This list is saved in XML or JSON format.

[0663] 5. How to inform relevant parties

[0664] The server automatically sends the generated list to the relevant parties via email, SMS, and the disaster prevention radio system. It also has a mechanism to check whether the relevant parties have received the information, and if not, resend it.

[0665] 6. Traffic and road condition estimation methods

[0666] The server analyzes the state of transportation infrastructure in the disaster area based on satellite data, and the AI ​​generator uses this information to calculate the optimal route for relief vehicles to travel safely and quickly.

[0667] 7. Means of information distribution

[0668] For residents in the affected areas, safety instructions and evacuation information are sent from the server to digital signage and smartphones. The terminal (digital signage) notifies people in the vicinity of the received information through audio and visual means, urging them to take emergency action. The user (smartphone) then uses the received information to ensure their own safety and the safety of those around them.

[0669] 8. Emotion Recognition Engine Means

[0670] The server runs an emotion engine to recognize the user's emotions. This emotion engine analyzes social media data and other interactions to identify the user's emotional state. The recognized emotions are analyzed by the generative AI, which then provides the user with appropriate evacuation instructions and reassurance information. For example, if the user is feeling anxious or scared, reassuring messages and support information will be delivered first.

[0671] Specific examples

[0672] For example, if a large-scale earthquake occurs, the server immediately collects and preprocesses satellite data, meteorological data, crustal data, and social media data. The generation AI estimates the damage situation in the affected area and generates a list of needed supplies and personnel. This list is automatically disseminated to relevant parties. Furthermore, the system analyzes traffic conditions based on satellite data and provides optimal routes for support vehicles. The emotion engine also analyzes user emotions and prioritizes the delivery of reassuring information to users who are feeling anxious. For example, if a resident of a disaster-stricken area posts on social media that they are "scared," the emotion engine recognizes this information and provides specific instructions for remaining calm and acting accordingly.

[0673] In this way, this system not only enables rapid and accurate information gathering and support provision in the event of a disaster, but also enables more effective support activities by delivering appropriate information that takes into account the user's emotions.

[0674] The processing flow will be explained below.

[0675] Step 1:

[0676] The server periodically acquires satellite data, meteorological data, and crustal data. Satellite data is high-resolution images and observation data delivered from artificial satellites. Meteorological data is obtained in real time from the Japan Meteorological Agency's API. Crustal data is acquired from seismometers and crustal movement monitoring devices.

[0677] Step 2:

[0678] The server also retrieves social media data, collecting posts from social media platforms such as Twitter and Facebook filtered by disaster-related keywords (e.g., "shaking" and "collapse").

[0679] Step 3:

[0680] The server stores all acquired data in a centralized database, which has the ability to manage data in various formats and make it instantly accessible.

[0681] Step 4:

[0682] The server preprocesses the stored data, for example, removing noise from social media data and normalizing text, and converting satellite image data into a format that is easier to apply to image analysis by adjusting the resolution.

[0683] Step 5:

[0684] The server passes the preprocessed data to the generation AI, which uses this data to estimate the extent of the damage. It identifies the extent of building collapse and flooding through satellite image analysis. It also integrates meteorological and crustal data to assess the situation in the affected area based on a damage prediction model.

[0685] Step 6:

[0686] The generative AI analyzes text from social media data to identify the locations of disaster victims with high urgency, and uses natural language processing technology to analyze the sentiment of posts and determine whether users are feeling anxious or scared.

[0687] Step 7:

[0688] The server generates a list of required supplies and personnel based on the analysis results of the generation AI. This list is created in XML or JSON format and is ready to be sent immediately.

[0689] Step 8:

[0690] The server sends the generated list to the relevant parties via email, SMS, and the disaster prevention radio system. It also checks the status of the transmission and resends if the list has not been received.

[0691] Step 9:

[0692] The server again acquires satellite data and analyzes the state of the transportation infrastructure in the affected area. Passable and impassable routes are identified, and the generation AI calculates the optimal support route.

[0693] Step 10:

[0694] The server runs an emotion engine to recognize the user's emotions, analyzing social media data and other interaction data to identify the user's emotional state.

[0695] Step 11:

[0696] The AI ​​then generates appropriate evacuation instructions and reassurance information based on the user's emotions. For example, if the user expresses emotions such as "fear" or "anxiety," it will prioritize providing messages that promote reassurance.

[0697] Step 12:

[0698] The server distributes the generated evacuation instructions and safety information to digital signage and smartphones, which then display the information in real time using audio and visual displays to notify people in the vicinity.

[0699] Step 13:

[0700] The user (smartphone) receives information from the server and takes action based on the instructions to ensure the safety of themselves and those around them.

[0701] Step 14:

[0702] The server continuously collects data and monitors changes in the situation in the disaster area, redistributing necessary instructions according to the new situation and optimizing relief efforts.

[0703] Example 2

[0704] 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."

[0705] Conventional disaster response systems often had difficulty accurately grasping the extent of the damage, resulting in delays in arranging necessary supplies and personnel. Furthermore, the state of transportation infrastructure was unclear, making it difficult to efficiently move support vehicles. Furthermore, information provided did not take into account the emotions of disaster victims, resulting in a lack of psychological support. The present invention aims to solve these problems.

[0706] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for acquiring satellite data, a means for acquiring meteorological data and crustal data, and a means for acquiring social networking service (SNS) data. This allows data to be centrally stored, and preprocessed data to be passed to the generation AI to estimate the damage situation. Based on the estimation results, a list of necessary supplies and personnel can be generated and disseminated to relevant parties. In addition, the status of transportation infrastructure can be estimated and passable routes can be generated. Furthermore, psychological support can be provided by analyzing the user's emotions and providing appropriate information.

[0707] "Satellite data" refers to image data and remote sensing data obtained from artificial satellites.

[0708] "Weather data" refers to weather observation data obtained from the Japan Meteorological Agency and various meteorological organizations.

[0709] "Crustal data" refers to observational data on crustal movements and seismic activity obtained from seismometers and related equipment.

[0710] "SNS data" refers to the content of posts and user interaction data obtained from social networking services.

[0711] "Centralized storage" means consolidating and storing data obtained from multiple data sources in a single database or data storage.

[0712] "Preprocessing" refers to processing of acquired data to remove noise and standardize the format.

[0713] "Generative AI" refers to artificial intelligence that uses machine learning models and deep learning to analyze data and make inferences.

[0714] "Estimating the damage situation" means predicting the scale and scope of damage caused by a disaster based on collected data.

[0715] "List of supplies and personnel" refers to a list of supplies and personnel required for disaster response.

[0716] "Relevant parties" refers to government agencies, relief organizations, and other related organizations involved in disaster response.

[0717] "Status of transportation infrastructure" refers to information showing the extent to which transportation facilities such as roads and bridges have been affected by the disaster.

[0718] A "passable route" is a route along which support vehicles can travel safely and quickly.

[0719] "Display device" refers to a screen or monitor such as digital signage, and is a device that displays information visually.

[0720] A "communication terminal" is a device for sending and receiving information via wireless communication, such as a smartphone or tablet.

[0721] "Analyzing user emotions" means identifying a user's emotional state based on social media data and other user interaction data.

[0722] "Providing appropriate information" means delivering information such as reassuring messages and evacuation instructions to users based on the analyzed user emotions.

[0723] The present invention is a system that uses data collected from multiple data sources to quickly and accurately analyze the damage situation during a disaster and provide necessary support. This system operates in cooperation with each element: a server, a terminal, and a user.

[0724] First, the server obtains satellite data, meteorological data, and crustal data. Satellite data is collected periodically using remote sensing technology from artificial satellites. Meteorological data is obtained in real time through APIs provided by meteorological agencies, and crustal data is automatically collected from seismometers. The server also obtains related posts from social networking services (SNS). This includes data filtered by keywords such as "disaster," "earthquake," and "rescue."

[0725] The acquired data is stored in a centralized database on a server. This database uses a relational database management system (RDBMS) such as MySQL or PostgreSQL. The stored data is then preprocessed. Specifically, hashtags and emojis that cause noise are removed from social media data, and the resolution and size of the satellite image data are optimized for analysis.

[0726] The preprocessed data is passed to the generation AI, which uses text mining techniques to analyze the social media data and extract posts with high urgency. It also uses satellite image analysis to identify collapsed buildings and flooded areas in the affected areas. It also integrates meteorological and crustal data and applies a damage prediction model to estimate the demand for supplies and personnel in the affected areas.

[0727] Based on the estimation results, the server generates a list of necessary supplies (e.g., drinking water, food, medicine) and personnel (e.g., medical staff, rescue teams). This list is disseminated to relevant parties in JSON or XML format. The server automatically sends this list via email, short message service (SMS), or disaster prevention radio system. It also checks whether the information has been received and resends it if it has not.

[0728] The server then analyzes satellite data to understand the status of the transportation infrastructure and generates routes that support vehicles can take. The AI ​​uses this information to calculate the optimal route and notifies the device from the server.

[0729] The device (digital signage) notifies people in the vicinity with audio and visual information, urging them to take action in the event of an emergency. Users (smartphones) also receive notifications from the device and can take action to ensure their own safety and the safety of those around them.

[0730] Finally, the server runs an emotion engine to recognize the user's emotions. This emotion engine analyzes social media data and other interaction data to identify the user's emotional state. The recognized emotions are analyzed by the generative AI and provide the user with appropriate evacuation instructions and reassurance information. For example, if a user posts on social media expressing the emotion "fear," the emotion engine recognizes this information and provides specific instructions for calm behavior.

[0731] As a concrete example, when a large-scale earthquake occurs, the server immediately collects and preprocesses satellite, meteorological, crustal, and social media data. The generation AI then estimates the extent of damage in the affected area, generates a list of needed supplies and personnel, and automatically notifies relevant parties. It analyzes traffic conditions based on satellite data and provides optimal routes for support vehicles. If the emotion engine recognizes the user's anxiety, it prioritizes the distribution of reassuring information.

[0732] An example prompt is:

[0733] "A large earthquake will occur on October 17, 2023. Please provide the following information about the area affected by this earthquake: a map of the affected area, the number of collapsed buildings, the location and condition of the victims, a list of needed supplies and personnel, the best route for relief vehicles, and specific evacuation instructions based on the emotional state of the victims."

[0734] As described above, the present invention is a system that realizes rapid and accurate information collection and support provision when a disaster occurs, and further provides support that takes into consideration the user's emotions.

[0735] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0736] Step 1: Data collection

[0737] The server collects information from the following data sources. First, remote sensing data and image data are obtained from satellites at specific time intervals. This data is automatically downloaded via API. Next, real-time weather data is collected using the API of meteorological agencies. This includes observational data such as temperature, precipitation, and wind speed. Crustal data is also automatically collected from seismometers, and includes information such as the epicenter, intensity, and time of occurrence of earthquakes. The server also obtains posted data from social networking services, filtered by keywords such as "disaster," "earthquake," and "rescue." This allows the server to obtain a wide range of information and obtain input data to proceed to the next step.

[0738] Step 2: Storing and Preprocessing Data

[0739] The server stores the collected data in a centralized database. The database used is a relational database management system (RDBMS) such as MySQL or PostgreSQL. This stored data is preprocessed. Specifically, unnecessary hashtags and emojis are removed from the social media data and the format is standardized. The resolution and size of the satellite image data are optimized for analysis. As a result of preprocessing, data is obtained in an easy-to-handle format and is used for analysis in the next step.

[0740] Step 3: Data analysis

[0741] The server passes the preprocessed data to the generation AI. The generation AI first analyzes satellite image data to identify collapsed buildings and the extent of flooding. Next, it uses text mining technology to analyze social media data and extract important posts, including the location and status of highly urgent victims. It then integrates meteorological and crustal data and applies a damage prediction model. This allows it to estimate the demand for supplies and personnel in the affected area. The results of this analysis are used in the next step.

[0742] Step 4: Make a list of supplies and personnel needed

[0743] The server generates a list of necessary supplies and personnel based on the analysis results of the generation AI. Specifically, it lists drinking water, food, medicine, medical staff, rescue teams, etc. These lists are saved in XML or JSON format and disseminated to relevant parties in the next step.

[0744] Step 5: Notify all parties involved

[0745] The server automatically sends the generated list to relevant parties via email, SMS, and the disaster prevention radio system. Destinations include government agencies and relief organizations. The server checks whether the information has been received, and if not, resends it. This ensures that the necessary information is delivered to relevant parties quickly and reliably.

[0746] Step 6: Estimate traffic and road conditions

[0747] The server analyzes satellite data to understand the status of transportation infrastructure. The generation AI uses this information to calculate passable routes for support vehicles. Specifically, it detects road closures and bridge damage and generates safe travel routes. This information is used in the next step.

[0748] Step 7: Distributing information

[0749] The server distributes safety instructions and evacuation information to residents in the affected area via digital signage and smartphones. The devices then notify nearby people of the received information via audio and visual means, urging them to take emergency action. Users can then ensure their own safety and that of those around them based on the information they receive, enabling rapid response.

[0750] Step 8: Emotion Recognition

[0751] The server runs an emotion engine to recognize the user's emotions. The emotion engine analyzes social media data and other interaction data to identify the user's emotional state. The recognized emotions are analyzed by the generative AI, which then provides the user with appropriate evacuation instructions and reassurance information. For example, if the user is feeling anxious or scared, reassuring messages and support information will be delivered first.

[0752] In this way, by carrying out specific processing for each step, this system is able to quickly and accurately collect information and provide support when a disaster occurs, and can also provide support that takes into account the user's emotions.

[0753] (Application example 2)

[0754] 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."

[0755] There are existing systems that quickly and accurately collect and analyze disaster information when a disaster occurs and disseminate it to relevant parties, but many of them do not take into account the emotional state of the user, making it difficult to provide appropriate evacuation instructions or reassurance information. In particular, when users are feeling anxious or scared, simply providing information makes it difficult to evacuate or respond effectively. Furthermore, there are only a limited number of systems that can adequately provide optimal routes for support vehicles or continuously monitor and redistribute data. There is a need to solve these issues.

[0756] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0757] In this invention, the server includes a means for acquiring satellite data, a means for acquiring meteorological data and crustal data, and a means for acquiring SNS data, which enables rapid and accurate information collection and provision of information that takes into account the user's feelings when a disaster occurs.

[0758] "Satellite Data" refers to image data and information obtained from satellites to monitor conditions on Earth.

[0759] "Weather Data" means data relating to weather and weather conditions obtained from meteorological agencies or other weather observation agencies.

[0760] "Crustal data" refers to data about the movement and vibration of the Earth's crust obtained from seismometers and geological observation equipment.

[0761] "SNS data" refers to information such as user posts and messages obtained from social networking services.

[0762] "Preprocessing" refers to processing to remove noise from acquired data and standardize the data format.

[0763] "Generative AI" refers to artificial intelligence systems that use machine learning models to generate new information and inferences.

[0764] "Estimating the damage situation" refers to the process of analyzing data to estimate the scope and extent of damage caused by a disaster.

[0765] "List of supplies and personnel" refers to a list of supplies (drinking water, food, medicine, etc.) and personnel (medical staff, rescue teams, etc.) needed for disaster response.

[0766] "Publicizing" refers to the act of notifying and sharing important information with relevant parties.

[0767] "Traffic and road condition estimation" refers to the analysis of satellite data to assess road passability and the presence of obstacles.

[0768] A "passable route" refers to the optimal route along which support vehicles can travel safely and quickly.

[0769] "Information distribution" refers to the act of sending emergency information and evacuation instructions to devices such as digital signage and smartphones.

[0770] "Emotion recognition" refers to the process of analyzing and determining a user's emotional state from their posts and messages.

[0771] "Re-delivery of instructions" refers to the act of sending information again if the initial delivery is not successful or if necessary.

[0772] This invention is a system that not only quickly and accurately collects and analyzes disaster information when a disaster occurs and disseminates it to relevant parties, but also recognizes the user's emotions and provides appropriate information. Specific embodiments are shown below.

[0773] 1. Data Collection Methods

[0774] The server periodically acquires satellite data, meteorological data, and crustal data. Satellite data is collected at specified intervals, and meteorological data is acquired in real time from the meteorological bureau's API. Crustal data is automatically collected from seismometers. The server also acquires SNS data from social networking services, collecting posts filtered by related keywords such as "disaster," "earthquake," and "rescue."

[0775] 2. Data storage and preprocessing methods

[0776] The server stores the acquired data in a centralized database. The stored data is pre-processed to remove noise and standardize the format. For example, unnecessary hashtags and emojis are removed from social media posts, and satellite image data is optimized for image analysis.

[0777] 3. Data Analysis Methods

[0778] The preprocessed data is passed from the server to the generation AI, which uses this data to estimate the extent of the damage. It analyzes satellite images to identify collapsed buildings and the extent of flooding. It also uses text mining techniques to analyze social media data to identify the location and status of victims with high urgency. It integrates meteorological data and crustal data and applies a damage prediction model to estimate the demand for supplies and personnel in the affected area.

[0779] 4. How to create a list of supplies and personnel needed

[0780] Based on the analysis results of the generative AI, the server generates a list of supplies (e.g., drinking water, food, medicine) and personnel (e.g., medical staff, rescue teams) needed in the disaster area. This list is saved in XML or JSON format.

[0781] 5. How to inform relevant parties

[0782] The server automatically sends the generated list to the relevant parties via email, SMS, and the disaster prevention radio system. It also has a mechanism to check whether the relevant parties have received the information, and if not, resend it.

[0783] 6. Traffic and road condition estimation methods

[0784] The server analyzes the state of transportation infrastructure in the disaster area based on satellite data, and the AI ​​generator uses this information to calculate the optimal route for relief vehicles to travel safely and quickly.

[0785] 7. Means of information distribution

[0786] For residents in the affected areas, safety instructions and evacuation information are sent from the server to digital signage and smartphones. The terminal (digital signage) notifies people in the vicinity of the received information through audio and visual means, urging them to take emergency action. The user (smartphone) then uses the received information to ensure their own safety and the safety of those around them.

[0787] 8. Emotion Recognition Engine Means

[0788] The server runs an emotion engine to recognize the user's emotions. This emotion engine analyzes social media data and other interactions to identify the user's emotional state. The recognized emotions are analyzed by the generative AI, which then provides the user with appropriate evacuation instructions and reassurance information. For example, if the user is feeling anxious or scared, reassuring messages and support information will be delivered first.

[0789] Hardware and software used

[0790] Hardware: Servers, smartphones, digital signage

[0791] Software: TensorFlow (generative AI model), OpenCV (image analysis), NLTK (text mining), Flask (backend API construction)

[0792] Specific examples

[0793] For example, if a large-scale earthquake occurs, the server immediately collects and preprocesses satellite data, meteorological data, crustal data, and social media data. The generation AI estimates the damage situation in the affected area and generates a list of needed supplies and personnel. This list is automatically disseminated to relevant parties. Furthermore, the AI ​​analyzes traffic conditions based on satellite data and provides optimal routes for support vehicles. The emotion engine also analyzes user emotions and prioritizes the delivery of reassuring information to users who are feeling anxious. For example, if a resident of a disaster-stricken area posts on social media that they are "scared," the emotion engine recognizes this information and provides specific instructions for calm action.

[0794] Prompt Sentence Examples

[0795] The generative AI model is sent the following prompt:

[0796] Satellite image path: / path / to / satellite_image.jpg

[0797] Text data: "I'm scared, the earthquake was really strong!"

[0798] When this prompt is sent, the application returns the damage situation and emotion recognition results, and provides the user with appropriate evacuation instructions and reassurance information.

[0799] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0800] Step 1:

[0801] The server acquires satellite data, meteorological data, crustal data, and social media data. When the server acquires these data, satellite data is collected at specified intervals, and meteorological data is acquired in real time from the meteorological agency's API. Crustal data is collected as observation data from seismometers, and social media data is acquired by filtering posts by related keywords. The input is data from each data source, and the output is the acquired dataset.

[0802] Step 2:

[0803] The server stores the acquired data in a centralized database and performs preprocessing, which includes removing unnecessary hashtags and emojis from social media data and optimizing satellite image data for image analysis. The input is the acquired dataset, and the output is the preprocessed dataset.

[0804] Step 3:

[0805] The server passes the preprocessed data to the generation AI, which estimates the damage situation. The generation AI analyzes satellite images to identify collapsed buildings and flooded areas, and uses text mining to identify the location and status of victims with high urgency from social media data. The input is the preprocessed dataset, and the output is estimated damage situation data.

[0806] Step 4:

[0807] The server generates a list of necessary supplies and personnel based on the results of the AI's estimations. The list includes items such as drinking water, food, and medicine, and is saved in XML or JSON format. The input is estimated damage data, and the output is a list of supplies and personnel.

[0808] Step 5:

[0809] The server automatically sends the generated list to relevant parties via email, SMS, and the disaster prevention radio system. It also checks whether the information has been received, and resends it if not. The input is a list of supplies and personnel, and the output is notification confirmation data.

[0810] Step 6:

[0811] The server analyzes the state of the transportation infrastructure in the disaster area based on satellite data, and the generating AI calculates the optimal route for support vehicles to travel safely and quickly. The input is satellite data, and the output is passable route information.

[0812] Step 7:

[0813] Safety instructions and evacuation information are delivered to digital signage and smartphones. The terminal (digital signage) notifies people in the vicinity with audio and visual information, and the user (smartphone) ensures their own safety and the safety of those around them based on the information received. The input is evacuation information, and the output is the user's actions.

[0814] Step 8:

[0815] The server runs an emotion engine that analyzes social media data and other interactions to identify the user's emotional state. The emotion engine passes the recognized emotion to a generative AI, which then provides the user with appropriate evacuation instructions and reassurance information. The input is social media data, and the output is the user's emotional state and appropriate instructions and information.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] [Third embodiment]

[0820] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0821] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0822] 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).

[0823] 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.

[0824] 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.

[0825] 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).

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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."

[0832] The present invention is a system for quickly and accurately collecting and analyzing disaster information when a disaster occurs, and disseminating the information to relevant parties. An embodiment of this system will now be described in detail.

[0833] 1. Data Collection Methods

[0834] The server acquires satellite data, meteorological data, and crustal data in real time. Satellite data is high-resolution image data observed by artificial satellites in space, which allows for extensive visual information on the disaster-stricken area. Meteorological data includes meteorological information such as rainfall, temperature, wind speed, wind direction, humidity, and air pressure. Meanwhile, crustal data is data acquired from seismometers and devices that monitor crustal movements. The server also collects social media data and acquires disaster-related information posted by users on social networking services.

[0835] 2. Data storage and preprocessing methods

[0836] The server stores the collected data in a centralized database. The stored data is preprocessed to remove noise and standardize its format. For example, unnecessary hashtags and emojis are removed from social media posts, and satellite image data is optimized for image analysis.

[0837] 3. Data Analysis Methods

[0838] The preprocessed data is passed from the server to the generation AI. The generation AI analyzes satellite images to visually grasp the extent of damage in the affected areas. For example, it identifies collapsed buildings and flooded areas. It then analyzes social media data using text mining techniques to identify the location and status of victims with high urgency. By integrating meteorological data and crustal data and applying a damage prediction model, it estimates the demand for supplies and personnel in the affected areas.

[0839] 4. How to create a list of supplies and personnel needed

[0840] Based on the analysis results of the generative AI, the server generates a list of supplies (e.g., drinking water, food, medicine) and personnel (e.g., medical staff, rescue teams) needed in the disaster area, allowing users to quickly determine what is needed where.

[0841] 5. How to inform relevant parties

[0842] The generated list is automatically sent from the server to the relevant parties via email, SMS, and the disaster prevention radio system, and includes details of the supplies and personnel needed, allowing the relevant parties to immediately begin responding.

[0843] 6. Traffic and road condition estimation methods

[0844] The server analyzes the state of transportation infrastructure in the disaster area based on satellite data, and the generating AI uses this information to calculate the optimal route for safe and fast movement of support vehicles and proposes it to the support team.

[0845] 7. Means of information distribution

[0846] For residents in the affected areas, safety instructions and evacuation information are sent from the server to digital signage and smartphones. The terminal (digital signage) notifies people in the vicinity of the received information visually and audibly, urging them to take emergency action. The user (smartphone) then uses the received information to ensure their own safety and the safety of those around them.

[0847] Specific examples

[0848] For example, when a major earthquake occurs, the server immediately collects satellite data and seismograph data. It also obtains posts from social media such as "Shaking" and "Collapse," and the generation AI estimates the extent of damage in the affected area. Based on this, it generates a list of necessary supplies and personnel and automatically disseminates this information to relevant parties. It also calculates passable routes and suggests them to support vehicles. At the same time, it distributes evacuation information to digital signage and smartphones, helping to ensure the safety of victims.

[0849] In this way, this system enables prompt and appropriate support activities in the event of a disaster.

[0850] The processing flow will be explained below.

[0851] Step 1:

[0852] The server periodically acquires satellite data, meteorological data, and crustal data. Satellite data is recorded at specified intervals, and meteorological data is acquired in real time from the Meteorological Agency's API. Crustal data is automatically collected from observation data from seismometers.

[0853] Step 2:

[0854] The server also simultaneously acquires social media data, using public APIs such as Twitter and Facebook to collect posts filtered by keywords such as "disaster," "earthquake," and "rescue."

[0855] Step 3:

[0856] The server stores the acquired data in a centralized database, which has an intermediate format for integrating different data formats, making all data immediately accessible.

[0857] Step 4:

[0858] The server pre-processes the stored data, for example removing noise from social media data and cleaning up text data, and adjusts the resolution of satellite image data to prepare it for image analysis.

[0859] Step 5:

[0860] The server passes the preprocessed data to the generation AI, which then uses this data to begin estimating the extent of the damage. First, it analyzes satellite images to identify collapsed buildings and the extent of flooding.

[0861] Step 6:

[0862] The generative AI analyzes text from social media data to extract the location information of disaster victims with high urgency, using natural language processing technology to identify location information by analyzing the frequency and importance of related keywords.

[0863] Step 7:

[0864] The generative AI integrates meteorological and crustal data and applies damage prediction models to estimate supply shortages and personnel needs in affected areas.

[0865] Step 8:

[0866] The server generates a list of required supplies and personnel based on the estimation results of the generation AI. The generated list is saved in XML or JSON format.

[0867] Step 9:

[0868] The server sends the generated list to the relevant parties via email, SMS, and the disaster prevention radio system. It also checks whether the relevant parties have received the information, and if not, resends it.

[0869] Step 10:

[0870] The server then acquires satellite data again and analyzes the current traffic and road conditions, thereby identifying passable and impassable roads.

[0871] Step 11:

[0872] The generation AI calculates the optimal route for the support vehicle to travel quickly, and the calculated route is updated in real time.

[0873] Step 12:

[0874] The server distributes safety instructions and evacuation information to digital signage and smartphones, and the digital signage notifies those in the vicinity with audio and visual information.

[0875] Step 13:

[0876] The user (smartphone) receives information from the server and takes action based on the instructions to ensure the safety of themselves and those around them.

[0877] Step 14:

[0878] The server continuously collects data and monitors changes in the situation in the affected area, then re-distributes necessary instructions according to the new situation.

[0879] Example 1

[0880] 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."

[0881] When a disaster occurs, it is necessary to quickly and accurately collect and analyze damage information and disseminate it to all relevant parties. However, with conventional systems, data collection and analysis are often carried out as separate processes, making it difficult to centralize information management and analyze it in real time. In addition, there is a time lag when estimating traffic conditions in disaster-stricken areas and proposing passable routes, which hinders rapid relief efforts.

[0882] 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.

[0883] In this invention, the server includes: means for acquiring satellite data, means for acquiring meteorological and crustal data, means for acquiring social networking service data, means for centrally storing and preprocessing these data; means for passing the preprocessed data to a generation AI and estimating the damage situation; means for generating a list of necessary supplies and personnel based on the estimation results; means for disseminating the list to relevant parties; means for estimating traffic and road conditions from satellite data and generating passable routes; means for distributing this information to digital information display devices and mobile communication devices; and means for continuously monitoring this data and information and redistributing instructions as necessary. This enables centralized data management and real-time information analysis and dissemination. Furthermore, traffic condition estimation and route suggestions enable rapid relief activities.

[0884] "Satellite data" refers to high-resolution image data obtained from satellites in space, providing a wide range of visual information.

[0885] "Weather data" refers to data including meteorological information such as rainfall, temperature, wind speed, wind direction, humidity, and atmospheric pressure.

[0886] "Crustal data" refers to data obtained from seismometers and devices that monitor crustal movements, and includes information such as the magnitude and epicenter of an earthquake.

[0887] "Social networking service data" refers to data that includes disaster-related information posted by users on social networking services.

[0888] "Means of centralized storage" refers to a means of storing collected data in a single database.

[0889] "Preprocessing means" refers to a means for removing noise from the stored data and standardizing it into a format that is easy to analyze.

[0890] "Generative AI" is an artificial intelligence model that analyzes preprocessed data and estimates the damage situation.

[0891] "Means for estimating the damage situation" refers to a means of using generative AI to identify the damage situation in the affected areas and the location and condition of victims with high urgency.

[0892] The "means for generating a list of necessary supplies and personnel" is a means for creating a list of supplies and personnel required in the disaster-stricken area based on the estimated damage situation.

[0893] "Means of informing relevant parties" refers to the means of notifying relevant parties of the generated lists of supplies and personnel via email, SMS, and disaster prevention radio systems.

[0894] "Means for estimating traffic and road conditions" refers to analyzing the state of transportation infrastructure based on satellite data and calculating passable routes.

[0895] A "digital information display device" is an electronic public sign that displays disaster information and evacuation instructions visually and audibly.

[0896] A "mobile communication terminal" is a portable communication device such as a smartphone, and is a terminal for receiving disaster information.

[0897] "Continuous monitoring measures" are measures that constantly check collected data and information and redeliver instructions if the situation changes.

[0898] This invention is a system for collecting and analyzing disaster information quickly and accurately when a disaster occurs, and disseminating it to relevant parties. Specific embodiments of this system will be described in detail below.

[0899] First, the hardware and software that provide the foundation for the entire system consists of servers, mobile communication terminals, digital information display devices, etc. These devices work together to provide the infrastructure for centrally managing and analyzing collected data.

[0900] Data collection methods

[0901] The server collects the following data in real time:

[0902] 1. Satellite data collection: Receiving high-resolution image data from satellites in space. This image data is crucial for visually understanding the overall situation of the affected area.

[0903] 2. Meteorological Data Collection: Meteorological data such as rainfall, temperature, wind speed, wind direction, humidity, and air pressure are obtained from weather observation stations.

[0904] 3. Collecting crustal data: Receive crustal data from seismometers and other devices that monitor crustal movements, including information on the magnitude and epicenter of earthquakes.

[0905] 4. Social networking service data collection: We collect disaster-related information posted by users on social networking services. Specifically, we collect posts such as "Shaking" and "Collapse" in real time.

[0906] Data storage and preprocessing methods

[0907] The server stores the collected data in a centralized database, and then performs the following pre-processing:

[0908] 1. Noise removal: Remove unnecessary information from the stored data. For example, remove hashtags and emojis from social media data.

[0909] 2. Format unification: Data formats are standardized for analysis. For example, text data is converted into a fixed format, and image data is adjusted to a format that is easy to analyze.

[0910] Data Analysis Methods

[0911] The pre-processed data is passed from the server to the generative AI:

[0912] 1. Satellite image analysis: Generative AI analyzes satellite images to visually grasp the extent of damage in the affected area, specifically identifying collapsed buildings and flooded areas.

[0913] 2. Social media data analysis: Using text mining techniques, we analyze social media data to identify the location and condition of disaster victims with the highest urgency.

[0914] 3. Application of damage prediction models: By integrating meteorological and crustal data and using damage prediction models, we estimate the demand for supplies and personnel in the affected areas.

[0915] A means of creating a list of required supplies and personnel

[0916] The server generates the following list based on the analysis results of the generation AI:

[0917] 1. Supplies list: A list of supplies needed in the disaster area, such as drinking water, food, and medicine.

[0918] 2. Personnel list: A list of medical staff, rescue teams, and other personnel needed in the disaster area.

[0919] Methods of informing relevant parties

[0920] The generated list is sent from the server to the relevant parties in the following way:

[0921] 1. Email: Email a list to relevant parties with details of the supplies and personnel needed.

[0922] 2. SMS sending: Send information that requires immediate action via SMS.

[0923] 3. Disaster Prevention Radio System: Some important information is transmitted through the disaster prevention radio system.

[0924] Traffic and road condition estimation tools

[0925] The server analyzes the state of transportation infrastructure in the affected area based on satellite data, and the generating AI does the following:

[0926] 1. Traffic situation analysis: Identifying the damage status of major roads and bridges based on satellite images.

[0927] 2. Optimal route calculation: Calculate the optimal route for the support vehicle to travel safely and quickly, and propose it to the support team in real time.

[0928] Information delivery method

[0929] Information will be distributed to residents in the affected areas from the server in the following ways:

[0930] 1. Distribution to digital information display devices: Evacuation information and safety instructions are transmitted and displayed visually and audibly.

[0931] 2. Delivery to smartphones: Push notifications are sent to residents' smartphones, which users can receive to ensure their own safety and that of their surroundings.

[0932] Specific examples

[0933] For example, in the event of a major earthquake:

[0934] 1. The server instantly collects satellite data, seismometer data, and social media data.

[0935] 2. The server stores these data in a database, removes noise, and standardizes the format.

[0936] 3. The generative AI model analyzes the preprocessed data and identifies the extent of damage in the affected area and the most urgent victims.

[0937] 4. Based on the results of the generation AI, the server creates a list of necessary supplies and personnel and disseminates it to all relevant parties.

[0938] 5. The generative AI model analyzes traffic conditions and suggests optimal travel routes to the support team.

[0939] 6. The server distributes evacuation information to digital information display devices and smartphones, helping to ensure the safety of residents.

[0940] Prompt Sentence Examples

[0941] "When a major earthquake occurs, please analyze the situation in the affected area using satellite data and social media data, and generate a list of supplies that will be needed."

[0942] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0943] Step 1: Data collection

[0944] The server receives satellite data, meteorological data, crustal data, and social networking service data in real time.

[0945] Input: Image data from satellites, data from weather stations and seismometers, and posted data from social networking services.

[0946] Data processing: Obtain satellite images, collect meteorological and crustal data from sensors, and filter related posts using SNS APIs.

[0947] Output: Unified dataset (satellite image files, meteorological data files, crustal data files, SNS post dataset).

[0948] Step 2: Save data

[0949] The server stores the collected data in a centralized database.

[0950] Input: A centralized dataset.

[0951] Data processing: Based on the database design, each data is stored in the corresponding table.

[0952] Output: The saved database with noise.

[0953] Step 3: Data Preprocessing

[0954] The server performs pre-processing of the stored data.

[0955] Input: A noisy stored database.

[0956] Data processing: Unnecessary hashtags and emojis are removed from the social media dataset, and image data is resized and filtered for analysis.

[0957] Output: A denoised and uniformly formatted dataset.

[0958] Step 4: Data analysis

[0959] The server passes the preprocessed data to the generation AI, which analyzes the damage situation.

[0960] Input: A denoised and uniformly formatted dataset.

[0961] Data processing: Generative AI performs image analysis, text mining, and applies predictive models.

[0962] Output: Damage status of affected areas, location and condition of highly urgent victims, and forecast of demand for supplies and personnel.

[0963] Step 5: List Generation

[0964] The server creates a list of required supplies and personnel based on the analysis results of the generation AI.

[0965] Input: Damage situation in the affected area, location and condition of victims with high urgency, predicted demand for supplies and personnel.

[0966] Data processing: Prepare a list of supplies (drinking water, food, medicine, etc.) and personnel (medical staff, rescue teams, etc.).

[0967] Output: List of supplies and personnel needed.

[0968] Step 6: Notify all parties involved

[0969] The server sends the created list to the relevant parties.

[0970] Input: List of supplies and personnel needed.

[0971] Data processing: The list will be sent via email, SMS, and disaster prevention radio system.

[0972] Output: List sent to all parties.

[0973] Step 7: Estimate traffic and road conditions

[0974] The server analyzes the state of the transportation infrastructure, and the generation AI calculates a passable route.

[0975] Input: Satellite data.

[0976] Data processing: Applying algorithms to analyze damage to transportation infrastructure and calculate safe travel routes.

[0977] Output: Optimal travel route for support vehicles.

[0978] Step 8: Distributing information

[0979] The server distributes evacuation information to digital information display devices and mobile communication terminals.

[0980] Input: Evacuation instructions and safety information.

[0981] Data processing: Generate data for push notifications and visual display.

[0982] Output: Evacuation information delivered to digital information display devices and smartphones.

[0983] (Application example 1)

[0984] 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."

[0985] When a disaster occurs, it is necessary to quickly and accurately collect and analyze damage information and disseminate it to all relevant parties, but in the current system, these processes are often not carried out efficiently. In addition, there is a lack of means to appropriately deliver relief supplies and personnel to affected areas and to flexibly respond to changes in traffic conditions. This leads to delays in relief activities and the rescue of victims.

[0986] 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.

[0987] In this invention, the server includes: means for acquiring satellite data, means for acquiring meteorological data and crustal data, means for acquiring social media data, means for centrally storing and preprocessing these data, means for passing the preprocessed data to a generation AI and estimating the damage situation, means for generating a list of necessary supplies and personnel based on the estimation results, means for disseminating the list to relevant parties, means for estimating traffic and road conditions from satellite data and generating passable routes, means for distributing this information to digital signage and mobile information terminal devices, means for continuously monitoring this data and information and redistributing instructions as needed, and means for remotely monitoring the location information and progress of autonomous vehicles and executing operations as needed. This enables the rapid and accurate collection, analysis, and dissemination of information in the event of a disaster, enabling the appropriate delivery of relief supplies and personnel to disaster-stricken areas and flexible response to changes in traffic conditions.

[0988] "Satellite data" refers to high-resolution image data observed by artificial satellites placed in outer space, which can provide extensive visual information on the affected areas.

[0989] "Weather data" refers to data including meteorological information such as rainfall, temperature, wind speed, wind direction, humidity, and atmospheric pressure.

[0990] "Crustal data" refers to data obtained from seismometers and devices that monitor crustal movements, and includes information on crustal movements such as earthquakes and volcanic activity.

[0991] "SNS data" refers to data that includes information such as text, images, and videos posted by users on social networking services, and is used to obtain information about the location and condition of disaster victims.

[0992] "Centralized storage" refers to a method of integrating data collected from multiple data sources into a single database and managing it efficiently.

[0993] The "preprocessing means" is a processing method for removing noise from the collected data and standardizing the format.

[0994] "Generative AI" is an artificial intelligence technology that analyzes collected data and estimates the extent of damage.

[0995] "Means for generating a list of necessary supplies and personnel" refers to a method for creating a specific list of supplies and personnel needed in disaster-stricken areas based on the analysis results of the generation AI.

[0996] "Means of informing relevant parties" refers to distributing the generated list to relevant organizations and individuals via email, SMS, or disaster prevention radio systems.

[0997] "Means for estimating traffic and road conditions" refers to a method of analyzing the state of transportation infrastructure in disaster-stricken areas based on satellite data and calculating passable routes.

[0998] "Digital signage" is a device that uses a digital display to display information in real time.

[0999] A "portable information terminal device" is a portable information processing device such as a smartphone or tablet.

[1000] "Means for remote monitoring" refers to a method of remotely monitoring the location information and progress of autonomous vehicles, etc., using a communication network such as the Internet.

[1001] "Means for performing operations" refers to a method for remotely controlling the operation of an autonomous vehicle.

[1002] The present invention provides a system that enables the rapid and accurate collection, analysis, and dissemination of disaster information when a disaster occurs, and enables efficient relief activities using autonomous vehicles. Specific embodiments for carrying out the present invention will be described below.

[1003] 1. Data Collection Methods

[1004] The server acquires satellite data, meteorological data, crustal data, and SNS data in real time. Satellite data is high-resolution image data acquired from artificial satellites in space, and meteorological data includes information such as rainfall, temperature, wind speed, wind direction, humidity, and air pressure. Crustal data is data acquired from seismometers and crustal movement monitoring devices. SNS data includes disaster-related information posted by users on social networking services.

[1005] 2. Data storage and preprocessing methods

[1006] The server stores the collected data in a centralized database and performs preprocessing such as noise removal using Python and Pandas. Unnecessary hashtags and emojis are removed from social media posts, and satellite image data is optimized for image analysis using OpenCV.

[1007] 3. Data Analysis Methods

[1008] The preprocessed data is passed from the server to a generation AI (using TensorFlow and Scikit-Learn). The generation AI analyzes satellite images to identify collapsed buildings and flooded areas. It also uses text mining techniques to analyze social media data to identify the location and status of victims with high urgency. It also integrates meteorological and crustal data and applies a damage prediction model to estimate the demand for supplies and personnel in the affected area.

[1009] 4. How to create a list of supplies and personnel needed

[1010] Based on the analysis results of the generative AI, the server registers a list of supplies (e.g., drinking water, food, medicine) and personnel (e.g., medical staff, rescue teams) needed in the disaster area in a MySQL database, allowing for a quick understanding of the assistance needed.

[1011] 5. How to inform relevant parties

[1012] The generated list is automatically sent from the server to the relevant parties via email, SMS, and the disaster prevention radio system, allowing them to immediately begin responding.

[1013] 6. Traffic and road condition estimation methods

[1014] The server analyzes the status of the transportation infrastructure in the affected area based on satellite data, and the generation AI uses Google Maps API and Dijkstra's algorithm to calculate the optimal route for support vehicles and instruct the autonomous vehicles on which to take it.

[1015] 7. Means of information distribution

[1016] For residents in the affected areas, safety instructions and evacuation information are sent from the server to digital signage and mobile information terminal devices. The digital signage notifies people in the vicinity of the received information visually and audibly, urging them to take emergency action. The mobile information terminal devices then ensure safety based on the received information.

[1017] 8. Autonomous Vehicle Monitoring and Operational Methods

[1018] The server remotely monitors the location and progress of the autonomous vehicle via WebSocket, and performs operations using Flask and React as needed to streamline support activities.

[1019] Specific examples

[1020] For example, if a large-scale earthquake occurs in Tokyo, the server will immediately collect satellite data and seismograph data. It will also obtain posts from social media and estimate the severity of the damage based on information such as "shaking" and "collapse." The generation AI will analyze this data to grasp the situation in the affected area and generate a list of necessary supplies and personnel. It will also calculate passable routes and provide instructions to autonomous vehicles. At the same time, it will distribute evacuation information to digital signage and mobile information terminal devices, helping to ensure the safety of victims.

[1021] Example prompts for generative AI models

[1022] "Based on satellite image data, seismometer data, and data posted on social media by Shinjuku Ward, please analyze the damage situation in the affected areas and assess the need for supplies. Also, calculate the optimal route and make a plan to deliver relief supplies using autonomous vehicles."

[1023] In this way, this system enables prompt and appropriate support activities when a disaster occurs.

[1024] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1025] Step 1:

[1026] Data collection

[1027] The server collects satellite data, meteorological data, crustal data, and social media data. Specifically, the server obtains high-resolution image data from satellite APIs, receives information such as rainfall and temperature from weather sensors, and acquires seismic motion from seismometers. It also collects disaster-related posts from social networking services via APIs. The input is data from various data sources, and the output is raw data stored centrally.

[1028] Step 2:

[1029] Data storage and preprocessing

[1030] The server stores the collected data in a centralized database. Python and Pandas are used to perform preprocessing to remove noise and standardize the format. Unnecessary hashtags and emojis are removed from social media data, and satellite image data is optimized for analysis using OpenCV. The input is raw, centralized data, and the output is preprocessed, clean data.

[1031] Step 3:

[1032] Data analysis

[1033] The server passes the preprocessed data to the generation AI for analysis. The generation AI (using TensorFlow and Scikit-Learn) analyzes satellite images to identify collapsed buildings and flooded areas. It also uses text mining techniques to analyze social media data to identify the location and status of highly urgent victims. It integrates meteorological data and crustal data and applies a damage prediction model to estimate the demand for supplies and personnel in the affected area. The input is the preprocessed data, and the output is the analysis results of the damage situation and the need for assistance.

[1034] Step 4:

[1035] Creating a list of supplies and personnel

[1036] Based on the analysis results of the generative AI, the server registers a list of supplies and personnel needed in the disaster area in a MySQL database. The supply list includes drinking water, food, medicine, etc., while the personnel list includes medical staff and rescue teams. The input is the analysis results of the disaster situation and the need for assistance, and the output is the generated list of supplies and personnel.

[1037] Step 5:

[1038] Informing all parties concerned

[1039] The server automatically sends the generated list to the relevant parties via email, SMS, and the disaster prevention radio system, allowing them to immediately begin responding. The input is the generated list of supplies and personnel, and the output is notifications to the relevant parties.

[1040] Step 6:

[1041] Traffic and road condition estimates

[1042] The server analyzes the status of the transportation infrastructure in the affected area based on satellite data. The generation AI uses the Google Maps API and Dijkstra's algorithm to calculate the optimal route for support vehicles. The input is satellite data and information on traffic conditions, and the output is the optimal route.

[1043] Step 7:

[1044] Information distribution

[1045] For residents in the affected areas, safety instructions and evacuation information are sent from the server to digital signage and mobile information terminal devices. The digital signage notifies nearby people of the received information visually and audibly, urging them to take emergency action. The mobile information terminal devices ensure safety based on the received information. The input is the analysis results of the generative AI, and the output is the distribution of emergency information to the digital signage and mobile information terminal devices.

[1046] Step 8:

[1047] Autonomous vehicle monitoring and operation

[1048] The server remotely monitors the location and progress of the autonomous vehicle via WebSocket. If necessary, it executes operations using Flask and React to streamline support activities. The input is the real-time location and progress of the autonomous vehicle, and the output is operation instructions as needed.

[1049] 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.

[1050] The present invention is a system that not only quickly and accurately collects and analyzes disaster information when a disaster occurs and disseminates it to relevant parties, but also recognizes the user's emotions and provides appropriate information. An embodiment of this system will be specifically described below.

[1051] 1. Data Collection Methods

[1052] The server periodically acquires satellite data, meteorological data, and crustal data. Satellite data is collected at specified intervals, and meteorological data is acquired in real time from the meteorological bureau's API. Crustal data is automatically collected from seismometers. The server also acquires SNS data from social networking services, collecting posts filtered by related keywords such as "disaster," "earthquake," and "rescue."

[1053] 2. Data storage and preprocessing methods

[1054] The server stores the acquired data in a centralized database. The stored data is pre-processed to remove noise and standardize the format. For example, unnecessary hashtags and emojis are removed from social media posts, and satellite image data is optimized for image analysis.

[1055] 3. Data Analysis Methods

[1056] The preprocessed data is passed from the server to the generation AI, which uses this data to estimate the extent of the damage. It analyzes satellite images to identify collapsed buildings and the extent of flooding. It also uses text mining techniques to analyze social media data to identify the location and status of victims with high urgency. It integrates meteorological data and crustal data and applies a damage prediction model to estimate the demand for supplies and personnel in the affected area.

[1057] 4. How to create a list of supplies and personnel needed

[1058] Based on the analysis results of the generative AI, the server generates a list of supplies (e.g., drinking water, food, medicine) and personnel (e.g., medical staff, rescue teams) needed in the disaster area. This list is saved in XML or JSON format.

[1059] 5. How to inform relevant parties

[1060] The server automatically sends the generated list to the relevant parties via email, SMS, and the disaster prevention radio system. It also has a mechanism to check whether the relevant parties have received the information, and if not, resend it.

[1061] 6. Traffic and road condition estimation methods

[1062] The server analyzes the state of transportation infrastructure in the disaster area based on satellite data, and the AI ​​generator uses this information to calculate the optimal route for relief vehicles to travel safely and quickly.

[1063] 7. Means of information distribution

[1064] For residents in the affected areas, safety instructions and evacuation information are sent from the server to digital signage and smartphones. The terminal (digital signage) notifies people in the vicinity of the received information through audio and visual means, urging them to take emergency action. The user (smartphone) then uses the received information to ensure their own safety and the safety of those around them.

[1065] 8. Emotion Recognition Engine Means

[1066] The server runs an emotion engine to recognize the user's emotions. This emotion engine analyzes social media data and other interactions to identify the user's emotional state. The recognized emotions are analyzed by the generative AI, which then provides the user with appropriate evacuation instructions and reassurance information. For example, if the user is feeling anxious or scared, reassuring messages and support information will be delivered first.

[1067] Specific examples

[1068] For example, if a large-scale earthquake occurs, the server immediately collects and preprocesses satellite data, meteorological data, crustal data, and social media data. The generation AI estimates the damage situation in the affected area and generates a list of needed supplies and personnel. This list is automatically disseminated to relevant parties. Furthermore, the system analyzes traffic conditions based on satellite data and provides optimal routes for support vehicles. The emotion engine also analyzes user emotions and prioritizes the delivery of reassuring information to users who are feeling anxious. For example, if a resident of a disaster-stricken area posts on social media that they are "scared," the emotion engine recognizes this information and provides specific instructions for remaining calm and acting accordingly.

[1069] In this way, this system not only enables rapid and accurate information gathering and support provision in the event of a disaster, but also enables more effective support activities by delivering appropriate information that takes into account the user's emotions.

[1070] The processing flow will be explained below.

[1071] Step 1:

[1072] The server periodically acquires satellite data, meteorological data, and crustal data. Satellite data is high-resolution images and observation data delivered from artificial satellites. Meteorological data is obtained in real time from the Japan Meteorological Agency's API. Crustal data is acquired from seismometers and crustal movement monitoring devices.

[1073] Step 2:

[1074] The server also retrieves social media data, collecting posts from social media platforms such as Twitter and Facebook filtered by disaster-related keywords (e.g., "shaking" and "collapse").

[1075] Step 3:

[1076] The server stores all acquired data in a centralized database, which has the ability to manage data in various formats and make it instantly accessible.

[1077] Step 4:

[1078] The server preprocesses the stored data, for example, removing noise from social media data and normalizing text, and converting satellite image data into a format that is easier to apply to image analysis by adjusting the resolution.

[1079] Step 5:

[1080] The server passes the preprocessed data to the generation AI, which uses this data to estimate the extent of the damage. It identifies the extent of building collapse and flooding through satellite image analysis. It also integrates meteorological and crustal data to assess the situation in the affected area based on a damage prediction model.

[1081] Step 6:

[1082] The generative AI analyzes text from social media data to identify the locations of disaster victims with high urgency, and uses natural language processing technology to analyze the sentiment of posts and determine whether users are feeling anxious or scared.

[1083] Step 7:

[1084] The server generates a list of required supplies and personnel based on the analysis results of the generation AI. This list is created in XML or JSON format and is ready to be sent immediately.

[1085] Step 8:

[1086] The server sends the generated list to the relevant parties via email, SMS, and the disaster prevention radio system. It also checks the status of the transmission and resends if the list has not been received.

[1087] Step 9:

[1088] The server again acquires satellite data and analyzes the state of the transportation infrastructure in the affected area. Passable and impassable routes are identified, and the generation AI calculates the optimal support route.

[1089] Step 10:

[1090] The server runs an emotion engine to recognize the user's emotions, analyzing social media data and other interaction data to identify the user's emotional state.

[1091] Step 11:

[1092] The AI ​​then generates appropriate evacuation instructions and reassurance information based on the user's emotions. For example, if the user expresses emotions such as "fear" or "anxiety," it will prioritize providing messages that promote reassurance.

[1093] Step 12:

[1094] The server distributes the generated evacuation instructions and safety information to digital signage and smartphones, which then display the information in real time using audio and visual displays to notify people in the vicinity.

[1095] Step 13:

[1096] The user (smartphone) receives information from the server and takes action based on the instructions to ensure the safety of themselves and those around them.

[1097] Step 14:

[1098] The server continuously collects data and monitors changes in the situation in the disaster area, redistributing necessary instructions according to the new situation and optimizing relief efforts.

[1099] Example 2

[1100] 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."

[1101] Conventional disaster response systems often had difficulty accurately grasping the extent of the damage, resulting in delays in arranging necessary supplies and personnel. Furthermore, the state of transportation infrastructure was unclear, making it difficult to efficiently move support vehicles. Furthermore, information provided did not take into account the emotions of disaster victims, resulting in a lack of psychological support. The present invention aims to solve these problems.

[1102] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for acquiring satellite data, a means for acquiring meteorological data and crustal data, and a means for acquiring social networking service (SNS) data. This allows data to be centrally stored, and preprocessed data to be passed to the generation AI to estimate the damage situation. Based on the estimation results, a list of necessary supplies and personnel can be generated and disseminated to relevant parties. In addition, the status of transportation infrastructure can be estimated and passable routes can be generated. Furthermore, psychological support can be provided by analyzing the user's emotions and providing appropriate information.

[1103] "Satellite data" refers to image data and remote sensing data obtained from artificial satellites.

[1104] "Weather data" refers to weather observation data obtained from the Japan Meteorological Agency and various meteorological organizations.

[1105] "Crustal data" refers to observational data on crustal movements and seismic activity obtained from seismometers and related equipment.

[1106] "SNS data" refers to the content of posts and user interaction data obtained from social networking services.

[1107] "Centralized storage" means consolidating and storing data obtained from multiple data sources in a single database or data storage.

[1108] "Preprocessing" refers to processing of acquired data to remove noise and standardize the format.

[1109] "Generative AI" refers to artificial intelligence that uses machine learning models and deep learning to analyze data and make inferences.

[1110] "Estimating the damage situation" means predicting the scale and scope of damage caused by a disaster based on collected data.

[1111] "List of supplies and personnel" refers to a list of supplies and personnel required for disaster response.

[1112] "Relevant parties" refers to government agencies, relief organizations, and other related organizations involved in disaster response.

[1113] "Status of transportation infrastructure" refers to information showing the extent to which transportation facilities such as roads and bridges have been affected by the disaster.

[1114] A "passable route" is a route along which support vehicles can travel safely and quickly.

[1115] "Display device" refers to a screen or monitor such as digital signage, and is a device that displays information visually.

[1116] A "communication terminal" is a device for sending and receiving information via wireless communication, such as a smartphone or tablet.

[1117] "Analyzing user emotions" means identifying a user's emotional state based on social media data and other user interaction data.

[1118] "Providing appropriate information" means delivering information such as reassuring messages and evacuation instructions to users based on the analyzed user emotions.

[1119] The present invention is a system that uses data collected from multiple data sources to quickly and accurately analyze the damage situation during a disaster and provide necessary support. This system operates in cooperation with each element: a server, a terminal, and a user.

[1120] First, the server obtains satellite data, meteorological data, and crustal data. Satellite data is collected periodically using remote sensing technology from artificial satellites. Meteorological data is obtained in real time through APIs provided by meteorological agencies, and crustal data is automatically collected from seismometers. The server also obtains related posts from social networking services (SNS). This includes data filtered by keywords such as "disaster," "earthquake," and "rescue."

[1121] The acquired data is stored in a centralized database on a server. This database uses a relational database management system (RDBMS) such as MySQL or PostgreSQL. The stored data is then preprocessed. Specifically, hashtags and emojis that cause noise are removed from social media data, and the resolution and size of the satellite image data are optimized for analysis.

[1122] The preprocessed data is passed to the generation AI, which uses text mining techniques to analyze the social media data and extract posts with high urgency. It also uses satellite image analysis to identify collapsed buildings and flooded areas in the affected areas. It also integrates meteorological and crustal data and applies a damage prediction model to estimate the demand for supplies and personnel in the affected areas.

[1123] Based on the estimation results, the server generates a list of necessary supplies (e.g., drinking water, food, medicine) and personnel (e.g., medical staff, rescue teams). This list is disseminated to relevant parties in JSON or XML format. The server automatically sends this list via email, short message service (SMS), or disaster prevention radio system. It also checks whether the information has been received and resends it if it has not.

[1124] The server then analyzes satellite data to understand the status of the transportation infrastructure and generates routes that support vehicles can take. The AI ​​uses this information to calculate the optimal route and notifies the device from the server.

[1125] The device (digital signage) notifies people in the vicinity with audio and visual information, urging them to take action in the event of an emergency. Users (smartphones) also receive notifications from the device and can take action to ensure their own safety and the safety of those around them.

[1126] Finally, the server runs an emotion engine to recognize the user's emotions. This emotion engine analyzes social media data and other interaction data to identify the user's emotional state. The recognized emotions are analyzed by the generative AI and provide the user with appropriate evacuation instructions and reassurance information. For example, if a user posts on social media expressing the emotion "fear," the emotion engine recognizes this information and provides specific instructions for calm behavior.

[1127] As a concrete example, when a large-scale earthquake occurs, the server immediately collects and preprocesses satellite, meteorological, crustal, and social media data. The generation AI then estimates the extent of damage in the affected area, generates a list of needed supplies and personnel, and automatically notifies relevant parties. It analyzes traffic conditions based on satellite data and provides optimal routes for support vehicles. If the emotion engine recognizes the user's anxiety, it prioritizes the distribution of reassuring information.

[1128] An example prompt is:

[1129] "A large earthquake will occur on October 17, 2023. Please provide the following information about the area affected by this earthquake: a map of the affected area, the number of collapsed buildings, the location and condition of the victims, a list of needed supplies and personnel, the best route for relief vehicles, and specific evacuation instructions based on the emotional state of the victims."

[1130] As described above, the present invention is a system that realizes rapid and accurate information collection and support provision when a disaster occurs, and further provides support that takes into consideration the user's emotions.

[1131] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1132] Step 1: Data collection

[1133] The server collects information from the following data sources. First, remote sensing data and image data are obtained from satellites at specific time intervals. This data is automatically downloaded via API. Next, real-time weather data is collected using the API of meteorological agencies. This includes observational data such as temperature, precipitation, and wind speed. Crustal data is also automatically collected from seismometers, and includes information such as the epicenter, intensity, and time of occurrence of earthquakes. The server also obtains posted data from social networking services, filtered by keywords such as "disaster," "earthquake," and "rescue." This allows the server to obtain a wide range of information and obtain input data to proceed to the next step.

[1134] Step 2: Storing and Preprocessing Data

[1135] The server stores the collected data in a centralized database. The database used is a relational database management system (RDBMS) such as MySQL or PostgreSQL. This stored data is preprocessed. Specifically, unnecessary hashtags and emojis are removed from the social media data and the format is standardized. The resolution and size of the satellite image data are optimized for analysis. As a result of preprocessing, data is obtained in an easy-to-handle format and is used for analysis in the next step.

[1136] Step 3: Data analysis

[1137] The server passes the preprocessed data to the generation AI. The generation AI first analyzes satellite image data to identify collapsed buildings and the extent of flooding. Next, it uses text mining technology to analyze social media data and extract important posts, including the location and status of highly urgent victims. It then integrates meteorological and crustal data and applies a damage prediction model. This allows it to estimate the demand for supplies and personnel in the affected area. The results of this analysis are used in the next step.

[1138] Step 4: Make a list of supplies and personnel needed

[1139] The server generates a list of necessary supplies and personnel based on the analysis results of the generation AI. Specifically, it lists drinking water, food, medicine, medical staff, rescue teams, etc. These lists are saved in XML or JSON format and disseminated to relevant parties in the next step.

[1140] Step 5: Notify all parties involved

[1141] The server automatically sends the generated list to relevant parties via email, SMS, and the disaster prevention radio system. Destinations include government agencies and relief organizations. The server checks whether the information has been received, and if not, resends it. This ensures that the necessary information is delivered to relevant parties quickly and reliably.

[1142] Step 6: Estimate traffic and road conditions

[1143] The server analyzes satellite data to understand the status of transportation infrastructure. The generation AI uses this information to calculate passable routes for support vehicles. Specifically, it detects road closures and bridge damage and generates safe travel routes. This information is used in the next step.

[1144] Step 7: Distributing information

[1145] The server distributes safety instructions and evacuation information to residents in the affected area via digital signage and smartphones. The devices then notify nearby people of the received information via audio and visual means, urging them to take emergency action. Users can then ensure their own safety and that of those around them based on the information they receive, enabling rapid response.

[1146] Step 8: Emotion Recognition

[1147] The server runs an emotion engine to recognize the user's emotions. The emotion engine analyzes social media data and other interaction data to identify the user's emotional state. The recognized emotions are analyzed by the generative AI, which then provides the user with appropriate evacuation instructions and reassurance information. For example, if the user is feeling anxious or scared, reassuring messages and support information will be delivered first.

[1148] In this way, by carrying out specific processing for each step, this system is able to quickly and accurately collect information and provide support when a disaster occurs, and can also provide support that takes into account the user's emotions.

[1149] (Application example 2)

[1150] 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."

[1151] There are existing systems that quickly and accurately collect and analyze disaster information when a disaster occurs and disseminate it to relevant parties, but many of them do not take into account the emotional state of the user, making it difficult to provide appropriate evacuation instructions or reassurance information. In particular, when users are feeling anxious or scared, simply providing information makes it difficult to evacuate or respond effectively. Furthermore, there are only a limited number of systems that can adequately provide optimal routes for support vehicles or continuously monitor and redistribute data. There is a need to solve these issues.

[1152] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1153] In this invention, the server includes a means for acquiring satellite data, a means for acquiring meteorological data and crustal data, and a means for acquiring SNS data, which enables rapid and accurate information collection and provision of information that takes into account the user's feelings when a disaster occurs.

[1154] "Satellite Data" refers to image data and information obtained from satellites to monitor conditions on Earth.

[1155] "Weather Data" means data relating to weather and weather conditions obtained from meteorological agencies or other weather observation agencies.

[1156] "Crustal data" refers to data about the movement and vibration of the Earth's crust obtained from seismometers and geological observation equipment.

[1157] "SNS data" refers to information such as user posts and messages obtained from social networking services.

[1158] "Preprocessing" refers to processing to remove noise from acquired data and standardize the data format.

[1159] "Generative AI" refers to artificial intelligence systems that use machine learning models to generate new information and inferences.

[1160] "Estimating the damage situation" refers to the process of analyzing data to estimate the scope and extent of damage caused by a disaster.

[1161] "List of supplies and personnel" refers to a list of supplies (drinking water, food, medicine, etc.) and personnel (medical staff, rescue teams, etc.) needed for disaster response.

[1162] "Publicizing" refers to the act of notifying and sharing important information with relevant parties.

[1163] "Traffic and road condition estimation" refers to the analysis of satellite data to assess road passability and the presence of obstacles.

[1164] A "passable route" refers to the optimal route along which support vehicles can travel safely and quickly.

[1165] "Information distribution" refers to the act of sending emergency information and evacuation instructions to devices such as digital signage and smartphones.

[1166] "Emotion recognition" refers to the process of analyzing and determining a user's emotional state from their posts and messages.

[1167] "Re-delivery of instructions" refers to the act of sending information again if the initial delivery is not successful or if necessary.

[1168] This invention is a system that not only quickly and accurately collects and analyzes disaster information when a disaster occurs and disseminates it to relevant parties, but also recognizes the user's emotions and provides appropriate information. Specific embodiments are shown below.

[1169] 1. Data Collection Methods

[1170] The server periodically acquires satellite data, meteorological data, and crustal data. Satellite data is collected at specified intervals, and meteorological data is acquired in real time from the meteorological bureau's API. Crustal data is automatically collected from seismometers. The server also acquires SNS data from social networking services, collecting posts filtered by related keywords such as "disaster," "earthquake," and "rescue."

[1171] 2. Data storage and preprocessing methods

[1172] The server stores the acquired data in a centralized database. The stored data is pre-processed to remove noise and standardize the format. For example, unnecessary hashtags and emojis are removed from social media posts, and satellite image data is optimized for image analysis.

[1173] 3. Data Analysis Methods

[1174] The preprocessed data is passed from the server to the generation AI, which uses this data to estimate the extent of the damage. It analyzes satellite images to identify collapsed buildings and the extent of flooding. It also uses text mining techniques to analyze social media data to identify the location and status of victims with high urgency. It integrates meteorological data and crustal data and applies a damage prediction model to estimate the demand for supplies and personnel in the affected area.

[1175] 4. How to create a list of supplies and personnel needed

[1176] Based on the analysis results of the generative AI, the server generates a list of supplies (e.g., drinking water, food, medicine) and personnel (e.g., medical staff, rescue teams) needed in the disaster area. This list is saved in XML or JSON format.

[1177] 5. How to inform relevant parties

[1178] The server automatically sends the generated list to the relevant parties via email, SMS, and the disaster prevention radio system. It also has a mechanism to check whether the relevant parties have received the information, and if not, resend it.

[1179] 6. Traffic and road condition estimation methods

[1180] The server analyzes the state of transportation infrastructure in the disaster area based on satellite data, and the AI ​​generator uses this information to calculate the optimal route for relief vehicles to travel safely and quickly.

[1181] 7. Means of information distribution

[1182] For residents in the affected areas, safety instructions and evacuation information are sent from the server to digital signage and smartphones. The terminal (digital signage) notifies people in the vicinity of the received information through audio and visual means, urging them to take emergency action. The user (smartphone) then uses the received information to ensure their own safety and the safety of those around them.

[1183] 8. Emotion Recognition Engine Means

[1184] The server runs an emotion engine to recognize the user's emotions. This emotion engine analyzes social media data and other interactions to identify the user's emotional state. The recognized emotions are analyzed by the generative AI, which then provides the user with appropriate evacuation instructions and reassurance information. For example, if the user is feeling anxious or scared, reassuring messages and support information will be delivered first.

[1185] Hardware and software used

[1186] Hardware: Servers, smartphones, digital signage

[1187] Software: TensorFlow (generative AI model), OpenCV (image analysis), NLTK (text mining), Flask (backend API construction)

[1188] Specific examples

[1189] For example, if a large-scale earthquake occurs, the server immediately collects and preprocesses satellite data, meteorological data, crustal data, and social media data. The generation AI estimates the damage situation in the affected area and generates a list of needed supplies and personnel. This list is automatically disseminated to relevant parties. Furthermore, the AI ​​analyzes traffic conditions based on satellite data and provides optimal routes for support vehicles. The emotion engine also analyzes user emotions and prioritizes the delivery of reassuring information to users who are feeling anxious. For example, if a resident of a disaster-stricken area posts on social media that they are "scared," the emotion engine recognizes this information and provides specific instructions for calm action.

[1190] Prompt Sentence Examples

[1191] The generative AI model is sent the following prompt:

[1192] Satellite image path: / path / to / satellite_image.jpg

[1193] Text data: "I'm scared, the earthquake was really strong!"

[1194] When this prompt is sent, the application returns the damage situation and emotion recognition results, and provides the user with appropriate evacuation instructions and reassurance information.

[1195] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1196] Step 1:

[1197] The server acquires satellite data, meteorological data, crustal data, and social media data. When the server acquires these data, satellite data is collected at specified intervals, and meteorological data is acquired in real time from the meteorological agency's API. Crustal data is collected as observation data from seismometers, and social media data is acquired by filtering posts by related keywords. The input is data from each data source, and the output is the acquired dataset.

[1198] Step 2:

[1199] The server stores the acquired data in a centralized database and performs preprocessing, which includes removing unnecessary hashtags and emojis from social media data and optimizing satellite image data for image analysis. The input is the acquired dataset, and the output is the preprocessed dataset.

[1200] Step 3:

[1201] The server passes the preprocessed data to the generation AI, which estimates the damage situation. The generation AI analyzes satellite images to identify collapsed buildings and flooded areas, and uses text mining to identify the location and status of victims with high urgency from social media data. The input is the preprocessed dataset, and the output is estimated damage situation data.

[1202] Step 4:

[1203] The server generates a list of necessary supplies and personnel based on the results of the AI's estimations. The list includes items such as drinking water, food, and medicine, and is saved in XML or JSON format. The input is estimated damage data, and the output is a list of supplies and personnel.

[1204] Step 5:

[1205] The server automatically sends the generated list to relevant parties via email, SMS, and the disaster prevention radio system. It also checks whether the information has been received, and resends it if not. The input is a list of supplies and personnel, and the output is notification confirmation data.

[1206] Step 6:

[1207] The server analyzes the state of the transportation infrastructure in the disaster area based on satellite data, and the generating AI calculates the optimal route for support vehicles to travel safely and quickly. The input is satellite data, and the output is passable route information.

[1208] Step 7:

[1209] Safety instructions and evacuation information are delivered to digital signage and smartphones. The terminal (digital signage) notifies people in the vicinity with audio and visual information, and the user (smartphone) ensures their own safety and the safety of those around them based on the information received. The input is evacuation information, and the output is the user's actions.

[1210] Step 8:

[1211] The server runs an emotion engine that analyzes social media data and other interactions to identify the user's emotional state. The emotion engine passes the recognized emotion to a generative AI, which then provides the user with appropriate evacuation instructions and reassurance information. The input is social media data, and the output is the user's emotional state and appropriate instructions and information.

[1212] 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.

[1213] 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.

[1214] 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.

[1215] [Fourth embodiment]

[1216] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1217] 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.

[1218] 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).

[1219] 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.

[1220] 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.

[1221] 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).

[1222] 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.

[1223] 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.

[1224] 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.

[1225] 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.

[1226] 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.

[1227] 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.

[1228] 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."

[1229] The present invention is a system for quickly and accurately collecting and analyzing disaster information when a disaster occurs, and disseminating the information to relevant parties. An embodiment of this system will now be described in detail.

[1230] 1. Data Collection Methods

[1231] The server acquires satellite data, meteorological data, and crustal data in real time. Satellite data is high-resolution image data observed by artificial satellites in space, which allows for extensive visual information on the disaster-stricken area. Meteorological data includes meteorological information such as rainfall, temperature, wind speed, wind direction, humidity, and air pressure. Meanwhile, crustal data is data acquired from seismometers and devices that monitor crustal movements. The server also collects social media data and acquires disaster-related information posted by users on social networking services.

[1232] 2. Data storage and preprocessing methods

[1233] The server stores the collected data in a centralized database. The stored data is preprocessed to remove noise and standardize its format. For example, unnecessary hashtags and emojis are removed from social media posts, and satellite image data is optimized for image analysis.

[1234] 3. Data Analysis Methods

[1235] The preprocessed data is passed from the server to the generation AI. The generation AI analyzes satellite images to visually grasp the extent of damage in the affected areas. For example, it identifies collapsed buildings and flooded areas. It then analyzes social media data using text mining techniques to identify the location and status of victims with high urgency. By integrating meteorological data and crustal data and applying a damage prediction model, it estimates the demand for supplies and personnel in the affected areas.

[1236] 4. How to create a list of supplies and personnel needed

[1237] Based on the analysis results of the generative AI, the server generates a list of supplies (e.g., drinking water, food, medicine) and personnel (e.g., medical staff, rescue teams) needed in the disaster area, allowing users to quickly determine what is needed where.

[1238] 5. How to inform relevant parties

[1239] The generated list is automatically sent from the server to the relevant parties via email, SMS, and the disaster prevention radio system, and includes details of the supplies and personnel needed, allowing the relevant parties to immediately begin responding.

[1240] 6. Traffic and road condition estimation methods

[1241] The server analyzes the state of transportation infrastructure in the disaster area based on satellite data, and the generating AI uses this information to calculate the optimal route for safe and fast movement of support vehicles and proposes it to the support team.

[1242] 7. Means of information distribution

[1243] For residents in the affected areas, safety instructions and evacuation information are sent from the server to digital signage and smartphones. The terminal (digital signage) notifies people in the vicinity of the received information visually and audibly, urging them to take emergency action. The user (smartphone) then uses the received information to ensure their own safety and the safety of those around them.

[1244] Specific examples

[1245] For example, when a major earthquake occurs, the server immediately collects satellite data and seismograph data. It also obtains posts from social media such as "Shaking" and "Collapse," and the generation AI estimates the extent of damage in the affected area. Based on this, it generates a list of necessary supplies and personnel and automatically disseminates this information to relevant parties. It also calculates passable routes and suggests them to support vehicles. At the same time, it distributes evacuation information to digital signage and smartphones, helping to ensure the safety of victims.

[1246] In this way, this system enables prompt and appropriate support activities in the event of a disaster.

[1247] The processing flow will be explained below.

[1248] Step 1:

[1249] The server periodically acquires satellite data, meteorological data, and crustal data. Satellite data is recorded at specified intervals, and meteorological data is acquired in real time from the Meteorological Agency's API. Crustal data is automatically collected from observation data from seismometers.

[1250] Step 2:

[1251] The server also simultaneously acquires social media data, using public APIs such as Twitter and Facebook to collect posts filtered by keywords such as "disaster," "earthquake," and "rescue."

[1252] Step 3:

[1253] The server stores the acquired data in a centralized database, which has an intermediate format for integrating different data formats, making all data immediately accessible.

[1254] Step 4:

[1255] The server pre-processes the stored data, for example removing noise from social media data and cleaning up text data, and adjusts the resolution of satellite image data to prepare it for image analysis.

[1256] Step 5:

[1257] The server passes the preprocessed data to the generation AI, which then uses this data to begin estimating the extent of the damage. First, it analyzes satellite images to identify collapsed buildings and the extent of flooding.

[1258] Step 6:

[1259] The generative AI analyzes text from social media data to extract the location information of disaster victims with high urgency, using natural language processing technology to identify location information by analyzing the frequency and importance of related keywords.

[1260] Step 7:

[1261] The generative AI integrates meteorological and crustal data and applies damage prediction models to estimate supply shortages and personnel needs in affected areas.

[1262] Step 8:

[1263] The server generates a list of required supplies and personnel based on the estimation results of the generation AI. The generated list is saved in XML or JSON format.

[1264] Step 9:

[1265] The server sends the generated list to the relevant parties via email, SMS, and the disaster prevention radio system. It also checks whether the relevant parties have received the information, and if not, resends it.

[1266] Step 10:

[1267] The server then acquires satellite data again and analyzes the current traffic and road conditions, thereby identifying passable and impassable roads.

[1268] Step 11:

[1269] The generation AI calculates the optimal route for the support vehicle to travel quickly, and the calculated route is updated in real time.

[1270] Step 12:

[1271] The server distributes safety instructions and evacuation information to digital signage and smartphones, and the digital signage notifies those in the vicinity with audio and visual information.

[1272] Step 13:

[1273] The user (smartphone) receives information from the server and takes action based on the instructions to ensure the safety of themselves and those around them.

[1274] Step 14:

[1275] The server continuously collects data and monitors changes in the situation in the affected area, then re-distributes necessary instructions according to the new situation.

[1276] Example 1

[1277] 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."

[1278] When a disaster occurs, it is necessary to quickly and accurately collect and analyze damage information and disseminate it to all relevant parties. However, with conventional systems, data collection and analysis are often carried out as separate processes, making it difficult to centralize information management and analyze it in real time. In addition, there is a time lag when estimating traffic conditions in disaster-stricken areas and proposing passable routes, which hinders rapid relief efforts.

[1279] 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.

[1280] In this invention, the server includes: means for acquiring satellite data, means for acquiring meteorological and crustal data, means for acquiring social networking service data, means for centrally storing and preprocessing these data; means for passing the preprocessed data to a generation AI and estimating the damage situation; means for generating a list of necessary supplies and personnel based on the estimation results; means for disseminating the list to relevant parties; means for estimating traffic and road conditions from satellite data and generating passable routes; means for distributing this information to digital information display devices and mobile communication devices; and means for continuously monitoring this data and information and redistributing instructions as necessary. This enables centralized data management and real-time information analysis and dissemination. Furthermore, traffic condition estimation and route suggestions enable rapid relief activities.

[1281] "Satellite data" refers to high-resolution image data obtained from satellites in space, providing a wide range of visual information.

[1282] "Weather data" refers to data including meteorological information such as rainfall, temperature, wind speed, wind direction, humidity, and atmospheric pressure.

[1283] "Crustal data" refers to data obtained from seismometers and devices that monitor crustal movements, and includes information such as the magnitude and epicenter of an earthquake.

[1284] "Social networking service data" refers to data that includes disaster-related information posted by users on social networking services.

[1285] "Means of centralized storage" refers to a means of storing collected data in a single database.

[1286] "Preprocessing means" refers to a means for removing noise from the stored data and standardizing it into a format that is easy to analyze.

[1287] "Generative AI" is an artificial intelligence model that analyzes preprocessed data and estimates the damage situation.

[1288] "Means for estimating the damage situation" refers to a means of using generative AI to identify the damage situation in the affected areas and the location and condition of victims with high urgency.

[1289] The "means for generating a list of necessary supplies and personnel" is a means for creating a list of supplies and personnel required in the disaster-stricken area based on the estimated damage situation.

[1290] "Means of informing relevant parties" refers to the means of notifying relevant parties of the generated lists of supplies and personnel via email, SMS, and disaster prevention radio systems.

[1291] "Means for estimating traffic and road conditions" refers to analyzing the state of transportation infrastructure based on satellite data and calculating passable routes.

[1292] A "digital information display device" is an electronic public sign that displays disaster information and evacuation instructions visually and audibly.

[1293] A "mobile communication terminal" is a portable communication device such as a smartphone, and is a terminal for receiving disaster information.

[1294] "Continuous monitoring measures" are measures that constantly check collected data and information and redeliver instructions if the situation changes.

[1295] This invention is a system for collecting and analyzing disaster information quickly and accurately when a disaster occurs, and disseminating it to relevant parties. Specific embodiments of this system will be described in detail below.

[1296] First, the hardware and software that provide the foundation for the entire system consists of servers, mobile communication terminals, digital information display devices, etc. These devices work together to provide the infrastructure for centrally managing and analyzing collected data.

[1297] Data collection methods

[1298] The server collects the following data in real time:

[1299] 1. Satellite data collection: Receiving high-resolution image data from satellites in space. This image data is crucial for visually understanding the overall situation of the affected area.

[1300] 2. Meteorological Data Collection: Meteorological data such as rainfall, temperature, wind speed, wind direction, humidity, and air pressure are obtained from weather observation stations.

[1301] 3. Collecting crustal data: Receive crustal data from seismometers and other devices that monitor crustal movements, including information on the magnitude and epicenter of earthquakes.

[1302] 4. Social networking service data collection: We collect disaster-related information posted by users on social networking services. Specifically, we collect posts such as "Shaking" and "Collapse" in real time.

[1303] Data storage and preprocessing methods

[1304] The server stores the collected data in a centralized database, and then performs the following pre-processing:

[1305] 1. Noise removal: Remove unnecessary information from the stored data. For example, remove hashtags and emojis from social media data.

[1306] 2. Format unification: Data formats are standardized for analysis. For example, text data is converted into a fixed format, and image data is adjusted to a format that is easy to analyze.

[1307] Data Analysis Methods

[1308] The pre-processed data is passed from the server to the generative AI:

[1309] 1. Satellite image analysis: Generative AI analyzes satellite images to visually grasp the extent of damage in the affected area, specifically identifying collapsed buildings and flooded areas.

[1310] 2. Social media data analysis: Using text mining techniques, we analyze social media data to identify the location and condition of disaster victims with the highest urgency.

[1311] 3. Application of damage prediction models: By integrating meteorological and crustal data and using damage prediction models, we estimate the demand for supplies and personnel in the affected areas.

[1312] A means of creating a list of required supplies and personnel

[1313] The server generates the following list based on the analysis results of the generation AI:

[1314] 1. Supplies list: A list of supplies needed in the disaster area, such as drinking water, food, and medicine.

[1315] 2. Personnel list: A list of medical staff, rescue teams, and other personnel needed in the disaster area.

[1316] Methods of informing relevant parties

[1317] The generated list is sent from the server to the relevant parties in the following way:

[1318] 1. Email: Email a list to relevant parties with details of the supplies and personnel needed.

[1319] 2. SMS sending: Send information that requires immediate action via SMS.

[1320] 3. Disaster Prevention Radio System: Some important information is transmitted through the disaster prevention radio system.

[1321] Traffic and road condition estimation tools

[1322] The server analyzes the state of transportation infrastructure in the affected area based on satellite data, and the generating AI does the following:

[1323] 1. Traffic situation analysis: Identifying the damage status of major roads and bridges based on satellite images.

[1324] 2. Optimal route calculation: Calculate the optimal route for the support vehicle to travel safely and quickly, and propose it to the support team in real time.

[1325] Information delivery method

[1326] Information will be distributed to residents in the affected areas from the server in the following ways:

[1327] 1. Distribution to digital information display devices: Evacuation information and safety instructions are transmitted and displayed visually and audibly.

[1328] 2. Delivery to smartphones: Push notifications are sent to residents' smartphones, which users can receive to ensure their own safety and that of their surroundings.

[1329] Specific examples

[1330] For example, in the event of a major earthquake:

[1331] 1. The server instantly collects satellite data, seismometer data, and social media data.

[1332] 2. The server stores these data in a database, removes noise, and standardizes the format.

[1333] 3. The generative AI model analyzes the preprocessed data and identifies the extent of damage in the affected area and the most urgent victims.

[1334] 4. Based on the results of the generation AI, the server creates a list of necessary supplies and personnel and disseminates it to all relevant parties.

[1335] 5. The generative AI model analyzes traffic conditions and suggests optimal travel routes to the support team.

[1336] 6. The server distributes evacuation information to digital information display devices and smartphones, helping to ensure the safety of residents.

[1337] Prompt Sentence Examples

[1338] "When a major earthquake occurs, please analyze the situation in the affected area using satellite data and social media data, and generate a list of supplies that will be needed."

[1339] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1340] Step 1: Data collection

[1341] The server receives satellite data, meteorological data, crustal data, and social networking service data in real time.

[1342] Input: Image data from satellites, data from weather stations and seismometers, and posted data from social networking services.

[1343] Data processing: Obtain satellite images, collect meteorological and crustal data from sensors, and filter related posts using SNS APIs.

[1344] Output: Unified dataset (satellite image files, meteorological data files, crustal data files, SNS post dataset).

[1345] Step 2: Save data

[1346] The server stores the collected data in a centralized database.

[1347] Input: A centralized dataset.

[1348] Data processing: Based on the database design, each data is stored in the corresponding table.

[1349] Output: The saved database with noise.

[1350] Step 3: Data Preprocessing

[1351] The server performs pre-processing of the stored data.

[1352] Input: A noisy stored database.

[1353] Data processing: Unnecessary hashtags and emojis are removed from the social media dataset, and image data is resized and filtered for analysis.

[1354] Output: A denoised and uniformly formatted dataset.

[1355] Step 4: Data analysis

[1356] The server passes the preprocessed data to the generation AI, which analyzes the damage situation.

[1357] Input: A denoised and uniformly formatted dataset.

[1358] Data processing: Generative AI performs image analysis, text mining, and applies predictive models.

[1359] Output: Damage status of affected areas, location and condition of highly urgent victims, and forecast of demand for supplies and personnel.

[1360] Step 5: List Generation

[1361] The server creates a list of required supplies and personnel based on the analysis results of the generation AI.

[1362] Input: Damage situation in the affected area, location and condition of victims with high urgency, predicted demand for supplies and personnel.

[1363] Data processing: Prepare a list of supplies (drinking water, food, medicine, etc.) and personnel (medical staff, rescue teams, etc.).

[1364] Output: List of supplies and personnel needed.

[1365] Step 6: Notify all parties involved

[1366] The server sends the created list to the relevant parties.

[1367] Input: List of supplies and personnel needed.

[1368] Data processing: The list will be sent via email, SMS, and disaster prevention radio system.

[1369] Output: List sent to all parties.

[1370] Step 7: Estimate traffic and road conditions

[1371] The server analyzes the state of the transportation infrastructure, and the generation AI calculates a passable route.

[1372] Input: Satellite data.

[1373] Data processing: Applying algorithms to analyze damage to transportation infrastructure and calculate safe travel routes.

[1374] Output: Optimal travel route for support vehicles.

[1375] Step 8: Distributing information

[1376] The server distributes evacuation information to digital information display devices and mobile communication terminals.

[1377] Input: Evacuation instructions and safety information.

[1378] Data processing: Generate data for push notifications and visual display.

[1379] Output: Evacuation information delivered to digital information display devices and smartphones.

[1380] (Application example 1)

[1381] 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."

[1382] When a disaster occurs, it is necessary to quickly and accurately collect and analyze damage information and disseminate it to all relevant parties, but in the current system, these processes are often not carried out efficiently. In addition, there is a lack of means to appropriately deliver relief supplies and personnel to affected areas and to flexibly respond to changes in traffic conditions. This leads to delays in relief activities and the rescue of victims.

[1383] 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.

[1384] In this invention, the server includes: means for acquiring satellite data, means for acquiring meteorological data and crustal data, means for acquiring social media data, means for centrally storing and preprocessing these data, means for passing the preprocessed data to a generation AI and estimating the damage situation, means for generating a list of necessary supplies and personnel based on the estimation results, means for disseminating the list to relevant parties, means for estimating traffic and road conditions from satellite data and generating passable routes, means for distributing this information to digital signage and mobile information terminal devices, means for continuously monitoring this data and information and redistributing instructions as needed, and means for remotely monitoring the location information and progress of autonomous vehicles and executing operations as needed. This enables the rapid and accurate collection, analysis, and dissemination of information in the event of a disaster, enabling the appropriate delivery of relief supplies and personnel to disaster-stricken areas and flexible response to changes in traffic conditions.

[1385] "Satellite data" refers to high-resolution image data observed by artificial satellites placed in outer space, which can provide extensive visual information on the affected areas.

[1386] "Weather data" refers to data including meteorological information such as rainfall, temperature, wind speed, wind direction, humidity, and atmospheric pressure.

[1387] "Crustal data" refers to data obtained from seismometers and devices that monitor crustal movements, and includes information on crustal movements such as earthquakes and volcanic activity.

[1388] "SNS data" refers to data that includes information such as text, images, and videos posted by users on social networking services, and is used to obtain information about the location and condition of disaster victims.

[1389] "Centralized storage" refers to a method of integrating data collected from multiple data sources into a single database and managing it efficiently.

[1390] The "preprocessing means" is a processing method for removing noise from the collected data and standardizing the format.

[1391] "Generative AI" is an artificial intelligence technology that analyzes collected data and estimates the extent of damage.

[1392] "Means for generating a list of necessary supplies and personnel" refers to a method for creating a specific list of supplies and personnel needed in disaster-stricken areas based on the analysis results of the generation AI.

[1393] "Means of informing relevant parties" refers to distributing the generated list to relevant organizations and individuals via email, SMS, or disaster prevention radio systems.

[1394] "Means for estimating traffic and road conditions" refers to a method of analyzing the state of transportation infrastructure in disaster-stricken areas based on satellite data and calculating passable routes.

[1395] "Digital signage" is a device that uses a digital display to display information in real time.

[1396] A "portable information terminal device" is a portable information processing device such as a smartphone or tablet.

[1397] "Means for remote monitoring" refers to a method of remotely monitoring the location information and progress of autonomous vehicles, etc., using a communication network such as the Internet.

[1398] "Means for performing operations" refers to a method for remotely controlling the operation of an autonomous vehicle.

[1399] The present invention provides a system that enables the rapid and accurate collection, analysis, and dissemination of disaster information when a disaster occurs, and enables efficient relief activities using autonomous vehicles. Specific embodiments for carrying out the present invention will be described below.

[1400] 1. Data Collection Methods

[1401] The server acquires satellite data, meteorological data, crustal data, and SNS data in real time. Satellite data is high-resolution image data acquired from artificial satellites in space, and meteorological data includes information such as rainfall, temperature, wind speed, wind direction, humidity, and air pressure. Crustal data is data acquired from seismometers and crustal movement monitoring devices. SNS data includes disaster-related information posted by users on social networking services.

[1402] 2. Data storage and preprocessing methods

[1403] The server stores the collected data in a centralized database and performs preprocessing such as noise removal using Python and Pandas. Unnecessary hashtags and emojis are removed from social media posts, and satellite image data is optimized for image analysis using OpenCV.

[1404] 3. Data Analysis Methods

[1405] The preprocessed data is passed from the server to a generation AI (using TensorFlow and Scikit-Learn). The generation AI analyzes satellite images to identify collapsed buildings and flooded areas. It also uses text mining techniques to analyze social media data to identify the location and status of victims with high urgency. It also integrates meteorological and crustal data and applies a damage prediction model to estimate the demand for supplies and personnel in the affected area.

[1406] 4. How to create a list of supplies and personnel needed

[1407] Based on the analysis results of the generative AI, the server registers a list of supplies (e.g., drinking water, food, medicine) and personnel (e.g., medical staff, rescue teams) needed in the disaster area in a MySQL database, allowing for a quick understanding of the assistance needed.

[1408] 5. How to inform relevant parties

[1409] The generated list is automatically sent from the server to the relevant parties via email, SMS, and the disaster prevention radio system, allowing them to immediately begin responding.

[1410] 6. Traffic and road condition estimation methods

[1411] The server analyzes the status of the transportation infrastructure in the affected area based on satellite data, and the generation AI uses Google Maps API and Dijkstra's algorithm to calculate the optimal route for support vehicles and instruct the autonomous vehicles on which to take it.

[1412] 7. Means of information distribution

[1413] For residents in the affected areas, safety instructions and evacuation information are sent from the server to digital signage and mobile information terminal devices. The digital signage notifies people in the vicinity of the received information visually and audibly, urging them to take emergency action. The mobile information terminal devices then ensure safety based on the received information.

[1414] 8. Autonomous Vehicle Monitoring and Operational Methods

[1415] The server remotely monitors the location and progress of the autonomous vehicle via WebSocket, and performs operations using Flask and React as needed to streamline support activities.

[1416] Specific examples

[1417] For example, if a large-scale earthquake occurs in Tokyo, the server will immediately collect satellite data and seismograph data. It will also obtain posts from social media and estimate the severity of the damage based on information such as "shaking" and "collapse." The generation AI will analyze this data to grasp the situation in the affected area and generate a list of necessary supplies and personnel. It will also calculate passable routes and provide instructions to autonomous vehicles. At the same time, it will distribute evacuation information to digital signage and mobile information terminal devices, helping to ensure the safety of victims.

[1418] Example prompts for generative AI models

[1419] "Based on satellite image data, seismometer data, and data posted on social media by Shinjuku Ward, please analyze the damage situation in the affected areas and assess the need for supplies. Also, calculate the optimal route and make a plan to deliver relief supplies using autonomous vehicles."

[1420] In this way, this system enables prompt and appropriate support activities when a disaster occurs.

[1421] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1422] Step 1:

[1423] Data collection

[1424] The server collects satellite data, meteorological data, crustal data, and social media data. Specifically, the server obtains high-resolution image data from satellite APIs, receives information such as rainfall and temperature from weather sensors, and acquires seismic motion from seismometers. It also collects disaster-related posts from social networking services via APIs. The input is data from various data sources, and the output is raw data stored centrally.

[1425] Step 2:

[1426] Data storage and preprocessing

[1427] The server stores the collected data in a centralized database. Python and Pandas are used to perform preprocessing to remove noise and standardize the format. Unnecessary hashtags and emojis are removed from social media data, and satellite image data is optimized for analysis using OpenCV. The input is raw, centralized data, and the output is preprocessed, clean data.

[1428] Step 3:

[1429] Data analysis

[1430] The server passes the preprocessed data to the generation AI for analysis. The generation AI (using TensorFlow and Scikit-Learn) analyzes satellite images to identify collapsed buildings and flooded areas. It also uses text mining techniques to analyze social media data to identify the location and status of highly urgent victims. It integrates meteorological data and crustal data and applies a damage prediction model to estimate the demand for supplies and personnel in the affected area. The input is the preprocessed data, and the output is the analysis results of the damage situation and the need for assistance.

[1431] Step 4:

[1432] Creating a list of supplies and personnel

[1433] Based on the analysis results of the generative AI, the server registers a list of supplies and personnel needed in the disaster area in a MySQL database. The supply list includes drinking water, food, medicine, etc., while the personnel list includes medical staff and rescue teams. The input is the analysis results of the disaster situation and the need for assistance, and the output is the generated list of supplies and personnel.

[1434] Step 5:

[1435] Informing all parties concerned

[1436] The server automatically sends the generated list to the relevant parties via email, SMS, and the disaster prevention radio system, allowing them to immediately begin responding. The input is the generated list of supplies and personnel, and the output is notifications to the relevant parties.

[1437] Step 6:

[1438] Traffic and road condition estimates

[1439] The server analyzes the status of the transportation infrastructure in the affected area based on satellite data. The generation AI uses the Google Maps API and Dijkstra's algorithm to calculate the optimal route for support vehicles. The input is satellite data and information on traffic conditions, and the output is the optimal route.

[1440] Step 7:

[1441] Information distribution

[1442] For residents in the affected areas, safety instructions and evacuation information are sent from the server to digital signage and mobile information terminal devices. The digital signage notifies nearby people of the received information visually and audibly, urging them to take emergency action. The mobile information terminal devices ensure safety based on the received information. The input is the analysis results of the generative AI, and the output is the distribution of emergency information to the digital signage and mobile information terminal devices.

[1443] Step 8:

[1444] Autonomous vehicle monitoring and operation

[1445] The server remotely monitors the location and progress of the autonomous vehicle via WebSocket. If necessary, it executes operations using Flask and React to streamline support activities. The input is the real-time location and progress of the autonomous vehicle, and the output is operation instructions as needed.

[1446] 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.

[1447] The present invention is a system that not only quickly and accurately collects and analyzes disaster information when a disaster occurs and disseminates it to relevant parties, but also recognizes the user's emotions and provides appropriate information. An embodiment of this system will be specifically described below.

[1448] 1. Data Collection Methods

[1449] The server periodically acquires satellite data, meteorological data, and crustal data. Satellite data is collected at specified intervals, and meteorological data is acquired in real time from the meteorological bureau's API. Crustal data is automatically collected from seismometers. The server also acquires SNS data from social networking services, collecting posts filtered by related keywords such as "disaster," "earthquake," and "rescue."

[1450] 2. Data storage and preprocessing methods

[1451] The server stores the acquired data in a centralized database. The stored data is pre-processed to remove noise and standardize the format. For example, unnecessary hashtags and emojis are removed from social media posts, and satellite image data is optimized for image analysis.

[1452] 3. Data Analysis Methods

[1453] The preprocessed data is passed from the server to the generation AI, which uses this data to estimate the extent of the damage. It analyzes satellite images to identify collapsed buildings and the extent of flooding. It also uses text mining techniques to analyze social media data to identify the location and status of victims with high urgency. It integrates meteorological data and crustal data and applies a damage prediction model to estimate the demand for supplies and personnel in the affected area.

[1454] 4. How to create a list of supplies and personnel needed

[1455] Based on the analysis results of the generative AI, the server generates a list of supplies (e.g., drinking water, food, medicine) and personnel (e.g., medical staff, rescue teams) needed in the disaster area. This list is saved in XML or JSON format.

[1456] 5. How to inform relevant parties

[1457] The server automatically sends the generated list to the relevant parties via email, SMS, and the disaster prevention radio system. It also has a mechanism to check whether the relevant parties have received the information, and if not, resend it.

[1458] 6. Traffic and road condition estimation methods

[1459] The server analyzes the state of transportation infrastructure in the disaster area based on satellite data, and the AI ​​generator uses this information to calculate the optimal route for relief vehicles to travel safely and quickly.

[1460] 7. Means of information distribution

[1461] For residents in the affected areas, safety instructions and evacuation information are sent from the server to digital signage and smartphones. The terminal (digital signage) notifies people in the vicinity of the received information through audio and visual means, urging them to take emergency action. The user (smartphone) then uses the received information to ensure their own safety and the safety of those around them.

[1462] 8. Emotion Recognition Engine Means

[1463] The server runs an emotion engine to recognize the user's emotions. This emotion engine analyzes social media data and other interactions to identify the user's emotional state. The recognized emotions are analyzed by the generative AI, which then provides the user with appropriate evacuation instructions and reassurance information. For example, if the user is feeling anxious or scared, reassuring messages and support information will be delivered first.

[1464] Specific examples

[1465] For example, if a large-scale earthquake occurs, the server immediately collects and preprocesses satellite data, meteorological data, crustal data, and social media data. The generation AI estimates the damage situation in the affected area and generates a list of needed supplies and personnel. This list is automatically disseminated to relevant parties. Furthermore, the system analyzes traffic conditions based on satellite data and provides optimal routes for support vehicles. The emotion engine also analyzes user emotions and prioritizes the delivery of reassuring information to users who are feeling anxious. For example, if a resident of a disaster-stricken area posts on social media that they are "scared," the emotion engine recognizes this information and provides specific instructions for remaining calm and acting accordingly.

[1466] In this way, this system not only enables rapid and accurate information gathering and support provision in the event of a disaster, but also enables more effective support activities by delivering appropriate information that takes into account the user's emotions.

[1467] The processing flow will be explained below.

[1468] Step 1:

[1469] The server periodically acquires satellite data, meteorological data, and crustal data. Satellite data is high-resolution images and observation data delivered from artificial satellites. Meteorological data is obtained in real time from the Japan Meteorological Agency's API. Crustal data is acquired from seismometers and crustal movement monitoring devices.

[1470] Step 2:

[1471] The server also retrieves social media data, collecting posts from social media platforms such as Twitter and Facebook filtered by disaster-related keywords (e.g., "shaking" and "collapse").

[1472] Step 3:

[1473] The server stores all acquired data in a centralized database, which has the ability to manage data in various formats and make it instantly accessible.

[1474] Step 4:

[1475] The server preprocesses the stored data, for example, removing noise from social media data and normalizing text, and converting satellite image data into a format that is easier to apply to image analysis by adjusting the resolution.

[1476] Step 5:

[1477] The server passes the preprocessed data to the generation AI, which uses this data to estimate the extent of the damage. It identifies the extent of building collapse and flooding through satellite image analysis. It also integrates meteorological and crustal data to assess the situation in the affected area based on a damage prediction model.

[1478] Step 6:

[1479] The generative AI analyzes text from social media data to identify the locations of disaster victims with high urgency, and uses natural language processing technology to analyze the sentiment of posts and determine whether users are feeling anxious or scared.

[1480] Step 7:

[1481] The server generates a list of required supplies and personnel based on the analysis results of the generation AI. This list is created in XML or JSON format and is ready to be sent immediately.

[1482] Step 8:

[1483] The server sends the generated list to the relevant parties via email, SMS, and the disaster prevention radio system. It also checks the status of the transmission and resends if the list has not been received.

[1484] Step 9:

[1485] The server again acquires satellite data and analyzes the state of the transportation infrastructure in the affected area. Passable and impassable routes are identified, and the generation AI calculates the optimal support route.

[1486] Step 10:

[1487] The server runs an emotion engine to recognize the user's emotions, analyzing social media data and other interaction data to identify the user's emotional state.

[1488] Step 11:

[1489] The AI ​​then generates appropriate evacuation instructions and reassurance information based on the user's emotions. For example, if the user expresses emotions such as "fear" or "anxiety," it will prioritize providing messages that promote reassurance.

[1490] Step 12:

[1491] The server distributes the generated evacuation instructions and safety information to digital signage and smartphones, which then display the information in real time using audio and visual displays to notify people in the vicinity.

[1492] Step 13:

[1493] The user (smartphone) receives information from the server and takes action based on the instructions to ensure the safety of themselves and those around them.

[1494] Step 14:

[1495] The server continuously collects data and monitors changes in the situation in the disaster area, redistributing necessary instructions according to the new situation and optimizing relief efforts.

[1496] Example 2

[1497] 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."

[1498] Conventional disaster response systems often had difficulty accurately grasping the extent of the damage, resulting in delays in arranging necessary supplies and personnel. Furthermore, the state of transportation infrastructure was unclear, making it difficult to efficiently move support vehicles. Furthermore, information provided did not take into account the emotions of disaster victims, resulting in a lack of psychological support. The present invention aims to solve these problems.

[1499] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for acquiring satellite data, a means for acquiring meteorological data and crustal data, and a means for acquiring social networking service (SNS) data. This allows data to be centrally stored, and preprocessed data to be passed to the generation AI to estimate the damage situation. Based on the estimation results, a list of necessary supplies and personnel can be generated and disseminated to relevant parties. In addition, the status of transportation infrastructure can be estimated and passable routes can be generated. Furthermore, psychological support can be provided by analyzing the user's emotions and providing appropriate information.

[1500] "Satellite data" refers to image data and remote sensing data obtained from artificial satellites.

[1501] "Weather data" refers to weather observation data obtained from the Japan Meteorological Agency and various meteorological organizations.

[1502] "Crustal data" refers to observational data on crustal movements and seismic activity obtained from seismometers and related equipment.

[1503] "SNS data" refers to the content of posts and user interaction data obtained from social networking services.

[1504] "Centralized storage" means consolidating and storing data obtained from multiple data sources in a single database or data storage.

[1505] "Preprocessing" refers to processing of acquired data to remove noise and standardize the format.

[1506] "Generative AI" refers to artificial intelligence that uses machine learning models and deep learning to analyze data and make inferences.

[1507] "Estimating the damage situation" means predicting the scale and scope of damage caused by a disaster based on collected data.

[1508] "List of supplies and personnel" refers to a list of supplies and personnel required for disaster response.

[1509] "Relevant parties" refers to government agencies, relief organizations, and other related organizations involved in disaster response.

[1510] "Status of transportation infrastructure" refers to information showing the extent to which transportation facilities such as roads and bridges have been affected by the disaster.

[1511] A "passable route" is a route along which support vehicles can travel safely and quickly.

[1512] "Display device" refers to a screen or monitor such as digital signage, and is a device that displays information visually.

[1513] A "communication terminal" is a device for sending and receiving information via wireless communication, such as a smartphone or tablet.

[1514] "Analyzing user emotions" means identifying a user's emotional state based on social media data and other user interaction data.

[1515] "Providing appropriate information" means delivering information such as reassuring messages and evacuation instructions to users based on the analyzed user emotions.

[1516] The present invention is a system that uses data collected from multiple data sources to quickly and accurately analyze the damage situation during a disaster and provide necessary support. This system operates in cooperation with each element: a server, a terminal, and a user.

[1517] First, the server obtains satellite data, meteorological data, and crustal data. Satellite data is collected periodically using remote sensing technology from artificial satellites. Meteorological data is obtained in real time through APIs provided by meteorological agencies, and crustal data is automatically collected from seismometers. The server also obtains related posts from social networking services (SNS). This includes data filtered by keywords such as "disaster," "earthquake," and "rescue."

[1518] The acquired data is stored in a centralized database on a server. This database uses a relational database management system (RDBMS) such as MySQL or PostgreSQL. The stored data is then preprocessed. Specifically, hashtags and emojis that cause noise are removed from social media data, and the resolution and size of the satellite image data are optimized for analysis.

[1519] The preprocessed data is passed to the generation AI, which uses text mining techniques to analyze the social media data and extract posts with high urgency. It also uses satellite image analysis to identify collapsed buildings and flooded areas in the affected areas. It also integrates meteorological and crustal data and applies a damage prediction model to estimate the demand for supplies and personnel in the affected areas.

[1520] Based on the estimation results, the server generates a list of necessary supplies (e.g., drinking water, food, medicine) and personnel (e.g., medical staff, rescue teams). This list is disseminated to relevant parties in JSON or XML format. The server automatically sends this list via email, short message service (SMS), or disaster prevention radio system. It also checks whether the information has been received and resends it if it has not.

[1521] The server then analyzes satellite data to understand the status of the transportation infrastructure and generates routes that support vehicles can take. The AI ​​uses this information to calculate the optimal route and notifies the device from the server.

[1522] The device (digital signage) notifies people in the vicinity with audio and visual information, urging them to take action in the event of an emergency. Users (smartphones) also receive notifications from the device and can take action to ensure their own safety and the safety of those around them.

[1523] Finally, the server runs an emotion engine to recognize the user's emotions. This emotion engine analyzes social media data and other interaction data to identify the user's emotional state. The recognized emotions are analyzed by the generative AI and provide the user with appropriate evacuation instructions and reassurance information. For example, if a user posts on social media expressing the emotion "fear," the emotion engine recognizes this information and provides specific instructions for calm behavior.

[1524] As a concrete example, when a large-scale earthquake occurs, the server immediately collects and preprocesses satellite, meteorological, crustal, and social media data. The generation AI then estimates the extent of damage in the affected area, generates a list of needed supplies and personnel, and automatically notifies relevant parties. It analyzes traffic conditions based on satellite data and provides optimal routes for support vehicles. If the emotion engine recognizes the user's anxiety, it prioritizes the distribution of reassuring information.

[1525] An example prompt is:

[1526] "A large earthquake will occur on October 17, 2023. Please provide the following information about the area affected by this earthquake: a map of the affected area, the number of collapsed buildings, the location and condition of the victims, a list of needed supplies and personnel, the best route for relief vehicles, and specific evacuation instructions based on the emotional state of the victims."

[1527] As described above, the present invention is a system that realizes rapid and accurate information collection and support provision when a disaster occurs, and further provides support that takes into consideration the user's emotions.

[1528] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1529] Step 1: Data collection

[1530] The server collects information from the following data sources. First, remote sensing data and image data are obtained from satellites at specific time intervals. This data is automatically downloaded via API. Next, real-time weather data is collected using the API of meteorological agencies. This includes observational data such as temperature, precipitation, and wind speed. Crustal data is also automatically collected from seismometers, and includes information such as the epicenter, intensity, and time of occurrence of earthquakes. The server also obtains posted data from social networking services, filtered by keywords such as "disaster," "earthquake," and "rescue." This allows the server to obtain a wide range of information and obtain input data to proceed to the next step.

[1531] Step 2: Storing and Preprocessing Data

[1532] The server stores the collected data in a centralized database. The database used is a relational database management system (RDBMS) such as MySQL or PostgreSQL. This stored data is preprocessed. Specifically, unnecessary hashtags and emojis are removed from the social media data and the format is standardized. The resolution and size of the satellite image data are optimized for analysis. As a result of preprocessing, data is obtained in an easy-to-handle format and is used for analysis in the next step.

[1533] Step 3: Data analysis

[1534] The server passes the preprocessed data to the generation AI. The generation AI first analyzes satellite image data to identify collapsed buildings and the extent of flooding. Next, it uses text mining technology to analyze social media data and extract important posts, including the location and status of highly urgent victims. It then integrates meteorological and crustal data and applies a damage prediction model. This allows it to estimate the demand for supplies and personnel in the affected area. The results of this analysis are used in the next step.

[1535] Step 4: Make a list of supplies and personnel needed

[1536] The server generates a list of necessary supplies and personnel based on the analysis results of the generation AI. Specifically, it lists drinking water, food, medicine, medical staff, rescue teams, etc. These lists are saved in XML or JSON format and disseminated to relevant parties in the next step.

[1537] Step 5: Notify all parties involved

[1538] The server automatically sends the generated list to relevant parties via email, SMS, and the disaster prevention radio system. Destinations include government agencies and relief organizations. The server checks whether the information has been received, and if not, resends it. This ensures that the necessary information is delivered to relevant parties quickly and reliably.

[1539] Step 6: Estimate traffic and road conditions

[1540] The server analyzes satellite data to understand the status of transportation infrastructure. The generation AI uses this information to calculate passable routes for support vehicles. Specifically, it detects road closures and bridge damage and generates safe travel routes. This information is used in the next step.

[1541] Step 7: Distributing information

[1542] The server distributes safety instructions and evacuation information to residents in the affected area via digital signage and smartphones. The devices then notify nearby people of the received information via audio and visual means, urging them to take emergency action. Users can then ensure their own safety and that of those around them based on the information they receive, enabling rapid response.

[1543] Step 8: Emotion Recognition

[1544] The server runs an emotion engine to recognize the user's emotions. The emotion engine analyzes social media data and other interaction data to identify the user's emotional state. The recognized emotions are analyzed by the generative AI, which then provides the user with appropriate evacuation instructions and reassurance information. For example, if the user is feeling anxious or scared, reassuring messages and support information will be delivered first.

[1545] In this way, by carrying out specific processing for each step, this system is able to quickly and accurately collect information and provide support when a disaster occurs, and can also provide support that takes into account the user's emotions.

[1546] (Application example 2)

[1547] 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."

[1548] There are existing systems that quickly and accurately collect and analyze disaster information when a disaster occurs and disseminate it to relevant parties, but many of them do not take into account the emotional state of the user, making it difficult to provide appropriate evacuation instructions or reassurance information. In particular, when users are feeling anxious or scared, simply providing information makes it difficult to evacuate or respond effectively. Furthermore, there are only a limited number of systems that can adequately provide optimal routes for support vehicles or continuously monitor and redistribute data. There is a need to solve these issues.

[1549] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1550] In this invention, the server includes a means for acquiring satellite data, a means for acquiring meteorological data and crustal data, and a means for acquiring SNS data, which enables rapid and accurate information collection and provision of information that takes into account the user's feelings when a disaster occurs.

[1551] "Satellite Data" refers to image data and information obtained from satellites to monitor conditions on Earth.

[1552] "Weather Data" means data relating to weather and weather conditions obtained from meteorological agencies or other weather observation agencies.

[1553] "Crustal data" refers to data about the movement and vibration of the Earth's crust obtained from seismometers and geological observation equipment.

[1554] "SNS data" refers to information such as user posts and messages obtained from social networking services.

[1555] "Preprocessing" refers to processing to remove noise from acquired data and standardize the data format.

[1556] "Generative AI" refers to artificial intelligence systems that use machine learning models to generate new information and inferences.

[1557] "Estimating the damage situation" refers to the process of analyzing data to estimate the scope and extent of damage caused by a disaster.

[1558] "List of supplies and personnel" refers to a list of supplies (drinking water, food, medicine, etc.) and personnel (medical staff, rescue teams, etc.) needed for disaster response.

[1559] "Publicizing" refers to the act of notifying and sharing important information with relevant parties.

[1560] "Traffic and road condition estimation" refers to the analysis of satellite data to assess road passability and the presence of obstacles.

[1561] A "passable route" refers to the optimal route along which support vehicles can travel safely and quickly.

[1562] "Information distribution" refers to the act of sending emergency information and evacuation instructions to devices such as digital signage and smartphones.

[1563] "Emotion recognition" refers to the process of analyzing and determining a user's emotional state from their posts and messages.

[1564] "Re-delivery of instructions" refers to the act of sending information again if the initial delivery is not successful or if necessary.

[1565] This invention is a system that not only quickly and accurately collects and analyzes disaster information when a disaster occurs and disseminates it to relevant parties, but also recognizes the user's emotions and provides appropriate information. Specific embodiments are shown below.

[1566] 1. Data Collection Methods

[1567] The server periodically acquires satellite data, meteorological data, and crustal data. Satellite data is collected at specified intervals, and meteorological data is acquired in real time from the meteorological bureau's API. Crustal data is automatically collected from seismometers. The server also acquires SNS data from social networking services, collecting posts filtered by related keywords such as "disaster," "earthquake," and "rescue."

[1568] 2. Data storage and preprocessing methods

[1569] The server stores the acquired data in a centralized database. The stored data is pre-processed to remove noise and standardize the format. For example, unnecessary hashtags and emojis are removed from social media posts, and satellite image data is optimized for image analysis.

[1570] 3. Data Analysis Methods

[1571] The preprocessed data is passed from the server to the generation AI, which uses this data to estimate the extent of the damage. It analyzes satellite images to ide...

Claims

1. a means for acquiring satellite data; means for acquiring meteorological and crustal data; A means of obtaining SNS data; a means for centrally storing and pre-processing this data; A means of passing preprocessed data to the generation AI to estimate the damage situation, and A means for generating a list of required supplies and personnel based on the results of the estimate; a means for disseminating said list to relevant parties; A means of estimating traffic and road conditions from satellite data and generating passable routes; A means to distribute this information to digital signage and smartphones, A means of continuously monitoring this data and information and redelivering instructions as necessary; and A system including:

2. 10. The system of claim 1, further comprising means for centrally storing and pre-processing acquired satellite, meteorological and crustal data.

3. The system according to claim 1, further comprising a means for passing preprocessed data to a generation AI and estimating the damage situation.

Images