system

Abstract

Provide a system. The system includes a means for predicting the probability of a disaster occurring in each region based on multiple disaster data collected; a means for optimally arranging a plurality of evacuation sites based on the disaster occurrence probability; means for displaying the evacuation locations and evacuation routes on a map; means for notifying a user of information on the map; A system including:

Description

[Technical Field]

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

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

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

[0004] Currently, many local governments face the challenge of issuing quick and accurate evacuation instructions when a disaster occurs. In particular, they are unable to quickly determine where to evacuate and where to open evacuation shelters, which can result in the safety of residents being compromised. Furthermore, the efficiency of evacuations is reduced because optimal evacuation routes that take into account traffic congestion and geographical constraints are not provided. To solve these problems, a comprehensive system is needed that can predict the probability of disaster occurrence, optimally locate evacuation shelters, and optimize evacuation routes. [Means for solving the problem]

[0005] The disaster prediction and evacuation support system of the present invention includes the following means.

[0006] 1. A method for predicting the probability of disaster occurrence in each region based on collected data on multiple disasters

[0007] 2. A means for optimally arranging multiple evacuation sites based on the probability of disaster occurrence.

[0008] 3. Means for displaying the evacuation locations and evacuation routes on a map

[0009] 4. Means for notifying the user of the information on the map

[0010] First, multiple disaster data, such as weather data, earthquake data, and flood data, are collected, and the probability of a disaster occurring is predicted based on this data. Next, multiple safe and effective evacuation sites are optimally located based on the predicted disaster probability. Furthermore, evacuation routes are optimized, taking into account road congestion information and geographical constraints. This information is then displayed on a map so that residents can intuitively understand it. Notification methods are also used to quickly communicate evacuation instructions and disaster information to residents. This enables local governments to issue evacuation instructions quickly and accurately, effectively ensuring the safety of residents.

[0011] "Disaster data" refers to data related to the occurrence and prediction of disasters, such as weather data, earthquake data, and flood data.

[0012] "Probability of disaster occurrence" is a numerical representation of the possibility of a disaster occurring in a specific area based on collected disaster data.

[0013] An "evacuation site" is a place where residents can safely escape in the event of a disaster, and includes evacuation shelters and public facilities.

[0014] "Optimal deployment" refers to the most effective and efficient deployment within limited resources and conditions, and in particular, deployment that maximizes safety.

[0015] An "evacuation route" refers to the route that residents should take to reach an evacuation site in the event of a disaster.

[0016] "Displaying on a map" means visually showing related information in the form of a map using a geographic information system (GIS) or similar.

[0017] "Notification" means transmitting system-generated information to users via means such as SMS or email. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

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

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] The present invention is a system for disaster prediction for local governments, which supports the proposal of evacuation sites and the establishment of evacuation shelters. This system includes multiple means for collecting disaster data, predicting the probability of disaster occurrence, optimizing evacuation sites, and displaying and notifying the results.

[0040] 1. Data Collection

[0041] The server periodically obtains disaster-related data such as weather data, earthquake data, and flood data from external information providers (e.g., the Japan Meteorological Agency) and stores it in a database. The terminals are used by local government officials to collect information on the geographical information of each region (topography, rivers, population density, etc.), the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (road conditions, bridge strength, etc.), and upload it to the server. Users enter this information into the system, and the collected data is updated daily.

[0042] 2. Creating a disaster prediction model

[0043] The server preprocesses the collected data and formats it into a format suitable for machine learning models. It then trains a model that calculates the probability of disaster occurrence using pre-defined algorithms (e.g., random forests, neural networks). This model predicts the probability of disaster occurrence for each region.

[0044] 3. Optimizing evacuation locations

[0045] The server executes a method to optimally locate multiple evacuation sites based on the predicted probability of disaster occurrence. Evacuation sites are determined based on their capacity, safety, and accessibility. It also calculates the optimal evacuation route. This evacuation route is designed to allow residents to evacuate most efficiently and safely, taking into account road congestion information and geographical constraints.

[0046] 4. Display and notification of results

[0047] The server generates a digital disaster prevention map that displays optimized evacuation locations and evacuation routes on a map. This disaster prevention map is displayed on the dashboard of the device used by local government officials. The system is also equipped with a notification function to quickly communicate evacuation instructions and disaster information to residents. This allows the device to deliver necessary information to residents via SMS and email.

[0048] Examples:

[0049] For example, if a typhoon is approaching a certain municipality, the following process can be carried out using this system.

[0050] 1. The server obtains the latest typhoon data from the Japan Meteorological Agency and stores it in a database.

[0051] 2. Local government officials operating the terminals input and update local geographical information, resident information, building earthquake resistance, and evacuation shelter information into the system.

[0052] 3. The server predicts the probability of a typhoon-related disaster occurring based on the collected data.

[0053] 4. The server selects a safe evacuation location based on the prediction results and displays that information on the device.

[0054] 5. The server calculates a safe and efficient evacuation route and displays it on a map.

[0055] 6. The person using the terminal checks the disaster prevention map, makes any necessary corrections, and then issues the final evacuation instructions.

[0056] 7. The server notifies residents of evacuation information via SMS or email.

[0057] This system will enable local governments to issue quick and accurate evacuation instructions to ensure the safety of residents.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] The server automatically obtains the latest disaster data (e.g., typhoon data, flood data, earthquake data, etc.) from the Japan Meteorological Agency and seismic observation stations, and stores it in a database. This includes the process of periodically obtaining data using an API.

[0061] Step 2:

[0062] Local government officials operating the terminals input geographical information for each region (topography, river locations, population density, etc.) and upload it to the server. This involves manually entering data using a dedicated input form.

[0063] Step 3:

[0064] Local government officials operating the terminals collect data on the earthquake resistance of buildings in the area, the capacity of evacuation shelters, and the state of infrastructure (strength of roads and bridges, etc.), and enter this data into the system, again using a dedicated input form.

[0065] Step 4:

[0066] The server preprocesses the collected data, which includes imputing missing data, standardizing data, and treating outliers.

[0067] Step 5:

[0068] The server uses machine learning algorithms to predict the probability of disaster occurrence. At this stage, a model is trained based on the preprocessed data and the model is used to calculate the probability of disaster occurrence for each region.

[0069] Step 6:

[0070] The server selects safe evacuation sites based on the predicted probability of disaster occurrence, taking into account factors such as the shelter's capacity, safety, and ease of physical access.

[0071] Step 7:

[0072] The server calculates the optimal evacuation route from the evacuation site to the residents' residence, taking into account road congestion information and geographical constraints (e.g., obstacles such as rivers and mountains).

[0073] Step 8:

[0074] To visualize the results of the calculations, the server displays evacuation locations and routes on a map, which is digitally generated and displayed on a dashboard.

[0075] Step 9:

[0076] The local government official operating the device checks the displayed disaster prevention map and, if necessary, modifies and confirms the contents. Once the modifications are complete, the final evacuation plan is confirmed.

[0077] Step 10:

[0078] The server will then send evacuation information to residents via SMS or email based on the finalized evacuation plan, including evacuation locations, evacuation routes, and other important disaster information.

[0079] Step 11:

[0080] The user promptly begins evacuation based on the evacuation information received. The user heads to the evacuation site and stays there until safety is confirmed.

[0081] Step 12:

[0082] Local government officials using the devices will monitor the evacuation status of residents in real time and issue additional evacuation orders or rescue operations as necessary. This includes collecting and displaying real-time information.

[0083] The above are the detailed processing steps of the disaster prediction and evacuation support system of the present invention. This system enables local governments to respond quickly and appropriately when a disaster occurs, thereby ensuring the safety of residents.

[0084] Example 1

[0085] 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."

[0086] In modern society, disasters are difficult to predict, and selecting evacuation sites and ensuring efficient evacuation routes are major challenges, especially for local governments. Furthermore, if it is not possible to properly predict the probability of disaster occurrence or locate optimal evacuation sites, it becomes difficult to ensure the safety of residents. To address this situation, a system is needed that can accurately predict the probability of disaster occurrence, optimally locate evacuation sites, and quickly notify residents.

[0087] 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.

[0088] In this invention, the server includes means for predicting the probability of disaster occurrence in each region based on multiple disaster-related data collected, means for optimally locating multiple evacuation sites based on the disaster occurrence probability, means for displaying the evacuation sites and evacuation routes on a map, means for notifying users of the information on the map, means for formatting the collected data into a format suitable for a machine learning model, means for calculating the disaster occurrence probability using the machine learning model, and means for calculating evacuation routes taking into account the status of infrastructure. This enables accurate prediction of the disaster occurrence probability, optimal location of evacuation sites, efficient calculation of evacuation routes, and rapid information notification.

[0089] "Disaster-related data" refers to weather data, earthquake data, flood data and other disaster-related information.

[0090] "Means for predicting the probability of disaster occurrence" refers to algorithms and tools that calculate and predict the possibility of disasters occurring in each region based on collected disaster-related data.

[0091] "Methods for optimally locating evacuation shelters" refers to algorithms and methods for safely and efficiently locating evacuation shelters based on collected data and the predicted probability of disaster occurrence.

[0092] "Means for displaying on a map" refers to a graphical interface or digital map that visually displays calculated evacuation locations and evacuation routes.

[0093] "Means of notifying users of information" refers to the function of quickly conveying important evacuation and disaster information to users using communication methods such as SMS and email.

[0094] "Means of formatting data suitable for machine learning models" refers to procedures and methods for converting collected disaster-related data into a format that can be processed by machine learning algorithms.

[0095] "Means for calculating the probability of disaster occurrence" refers to models and algorithms that use data science techniques to calculate the probability of a disaster occurring.

[0096] "Means for calculating evacuation routes taking into account infrastructure conditions" refers to algorithms and tools for calculating safe and quick evacuation routes based on road congestion information and geographical constraints.

[0097] The present invention provides a disaster prediction system for local governments, and supports them in proposing evacuation sites and opening evacuation shelters. Detailed embodiments for carrying out the present invention will be described below.

[0098] This system involves a series of processing steps performed by a server, terminals, and users, including data collection, data processing, disaster prediction, evacuation site optimization, and result display and notification.

[0099] 1. Hardware and Software Used

[0100] The servers use cloud computing services (e.g., Amazon Web Services and Google Cloud Platform) to handle large amounts of data, and the databases use database management systems that support SQL and NoSQL formats.

[0101] The terminals are devices such as computers and tablets used by local government officials, and they access the dashboard via a browser. The system is designed as a web application, and JavaScript (registered trademark) frameworks such as React and Vue.js are used for the front end.

[0102] Users are local government officials and residents who access the system through terminals and input or receive the necessary information. The user interface is designed to be intuitive and easy to operate.

[0103] 2. Data Collection and Processing

[0104] The server periodically obtains weather data, earthquake data, flood data, and other data from external information providers such as the Japan Meteorological Agency via API and stores it in a database, which is updated in real time.

[0105] Local government officials operating the terminals input detailed information such as the area's geographical location, the earthquake resistance of buildings, the capacity of evacuation shelters, the condition of roads and bridges, etc. The collected data is then instantly uploaded to a server.

[0106] The server preprocesses the collected data and formats it into a format suitable for machine learning models, such as converting text data into numerical data and imputing missing values.

[0107] 3. Disaster Prediction Using Machine Learning

[0108] The server uses the preprocessed data to train machine learning models, including algorithms such as random forests and neural networks (e.g., Tensorflow® and PyTorch), which predict the probability of disasters occurring in each region.

[0109] 4. Optimization and display of evacuation locations

[0110] The server then executes a method to optimally locate evacuation sites based on the predicted probability of disaster occurrence. It also calculates optimal evacuation routes, taking into account infrastructure conditions (road congestion and geographical constraints). This allows the most efficient and safe evacuation route for residents to be designed.

[0111] The generated evacuation location and route information is compiled into a digital disaster prevention map and displayed on a dashboard on the device, allowing local government officials to intuitively check the information and make corrections if necessary.

[0112] 5. Notification of Results

[0113] The server notifies residents of the final evacuation location and evacuation route via SMS or email, enabling quick and accurate information transmission in the event of a disaster.

[0114] Specific examples

[0115] For example, if a typhoon is approaching, the following process will be executed:

[0116] 1. The server retrieves the latest typhoon data from the Japan Meteorological Agency's API and stores it in a database.

[0117] 2. Local government officials operate the terminals to input and update information such as local geographical information, resident information, building earthquake resistance, and evacuation shelter information.

[0118] 3. The server preprocesses the collected data and trains the disaster prediction model.

[0119] 4. The server uses the trained model to predict the probability of typhoon disasters.

[0120] 5. The server calculates the optimal evacuation location and evacuation route, and generates a digital disaster prevention map.

[0121] 6. Local government officials check the disaster prevention map on the terminal, make any necessary corrections, and issue final evacuation instructions.

[0122] 7. The server notifies residents of evacuation information via SMS or email.

[0123] Prompt Sentence Examples

[0124] "Use this system to select the best evacuation location for an approaching typhoon and calculate an efficient evacuation route."

[0125] The above describes a specific embodiment of the present invention. By implementing the invention in accordance with this embodiment, it is possible to accurately predict the probability of a disaster occurring, optimally locate evacuation sites, calculate efficient evacuation routes, and quickly notify users of the information.

[0126] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0127] Step 1: Data collection

[0128] The server periodically retrieves disaster-related data such as weather data, earthquake data, and flood data from external information providers (e.g., the Japan Meteorological Agency) through APIs and stores it in a database. This input data includes the latest weather information, earthquake occurrence status, river water level data, etc. In the process of retrieving this data, the server sends requests and parses and stores the data received as a response. As an output, a consistent storage of disaster-related data is formed in the database.

[0129] Step 2: Enter region data

[0130] Local government officials operating the terminals use a dedicated input form to input local geographic information (e.g., topography, rivers, population density, etc.), the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (e.g., road conditions, bridge strength, etc.). The input data covers detailed information about the area and the current state of infrastructure. The input information is uploaded to a server in real time and stored in a database. As a result, a rich dataset specific to the area is created.

[0131] Step 3: Preprocessing the data

[0132] The server preprocesses the collected disaster-related and local data. The input data undergoes processes such as missing value imputation, data normalization, and encoding of categorical variables. For example, it converts text data to numerical data and handles outliers. The output is a consistent dataset in a format suitable for machine learning models.

[0133] Step 4: Train the machine learning model

[0134] The server uses the preprocessed dataset to train a machine learning model. Algorithms used include random forests and neural networks (e.g., TensorFlow, PyTorch). The input data includes past disaster data and regional characteristics. The model can predict the probability of disaster occurrence for each region. The output is a trained disaster prediction model.

[0135] Step 5: Predict the probability of disaster occurrence

[0136] The server uses a trained machine learning model to predict the probability of disasters occurring in each region, taking the latest collected data as input. The input data includes current weather data and local information. The output is a predicted probability of disaster occurrence for each region, which is then stored in a database.

[0137] Step 6: Optimize evacuation locations

[0138] The server runs a mathematical optimization algorithm to optimally locate multiple evacuation sites based on the predicted probability of disaster occurrence. Input data includes the predicted probability of disaster occurrence, the capacity of the evacuation site, safety, accessibility, etc. The output is the calculation of the optimal evacuation site and evacuation route.

[0139] Step 7: Creating a digital disaster prevention map

[0140] The server generates a digital disaster prevention map based on the optimized evacuation location and evacuation route information. This digital disaster prevention map is designed to be easily referenced in the event of a disaster. The input data includes information on evacuation locations and routes. The output is a visually easy-to-understand map display.

[0141] Step 8: View the dashboard

[0142] Local government officials using the terminals can check the generated digital disaster prevention map on a dedicated dashboard. The input includes the generated disaster prevention map information. The output is the disaster prevention map displayed on the terminal screen.

[0143] Step 9: Notifications

[0144] The server notifies residents of optimized evacuation locations and routes via SMS and email. This process is done quickly, before a disaster occurs. Input data includes evacuation information and residents' contact information. The output is evacuation information sent to residents via SMS and email.

[0145] (Application example 1)

[0146] 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."

[0147] Conventional disaster prediction and evacuation systems often fail to predict the probability of disaster occurrence and suggest evacuation locations in sufficient real time, or provide insufficient optimal evacuation routes based on the user's location information. Furthermore, they lack a means to utilize generative AI models to instantly predict the probability of disaster occurrence and effectively notify users. This creates challenges in ensuring the safety of residents by preventing rapid and accurate evacuation in the event of a disaster.

[0148] 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.

[0149] In this invention, the server includes means for predicting the probability of disaster occurrence in each region based on multiple disaster data collected, means for optimally locating multiple evacuation sites based on the disaster occurrence probability, means for displaying the evacuation sites and evacuation routes on a map, means for notifying the user of the information on the map, means for calculating the disaster occurrence probability and evacuation site information in real time and proposing optimal evacuation sites and evacuation routes based on the user's location information, and means for receiving and notifying the disaster prediction results using a generative AI model in response to input of a prompt sentence. This makes it possible to provide the user with optimal evacuation information in real time and support rapid and accurate evacuation.

[0150] "Probability of disaster occurrence" is a probability value that represents the possibility of a disaster occurring in a specific area based on collected disaster data.

[0151] An "evacuation site" is a designated location for residents to evacuate safely in the event of a disaster.

[0152] An "evacuation route" is a route that allows residents to safely travel to an evacuation site.

[0153] "Means for displaying on a map" refers to the technology and methods for visually displaying evacuation locations and evacuation routes on a map.

[0154] The "means for notifying the user" is a method for promptly notifying the user of evacuation information.

[0155] "Real-time calculation" means that calculations are made instantly based on the current situation.

[0156] "User location information" is geographic information about the location where the user is currently located.

[0157] "Using a generative AI model" means using a model that uses artificial intelligence to make predictions and perform data analysis.

[0158] A "prompt" refers to an instruction or question that is input into a generative AI model.

[0159] "Disaster prediction results" are the predicted results of the probability and circumstances of disaster occurrence calculated by the generative AI model.

[0160] This invention is a system for predicting the probability of disaster occurrence in real time and proposing optimal evacuation sites and evacuation routes. This system includes multiple means for collecting disaster data, predicting the probability of disaster occurrence, optimizing evacuation sites, and displaying and notifying the results. This allows for rapid and accurate evacuation support in the event of a disaster.

[0161] The server periodically obtains disaster-related data, such as weather data, earthquake data, and flood data, from external information providers and stores it in a database. This data is used as training data for a model to predict the probability of disaster occurrence. The collected data is then preprocessed and formatted into a format suitable for the machine learning model. The machine learning model uses algorithms such as random forests and neural networks. This model calculates the probability of disaster occurrence and predicts the probability of disaster occurrence for each region.

[0162] The server also generates optimal evacuation locations and routes based on the predicted probability of disaster. Evacuation locations are determined based on their capacity, safety, and accessibility. Evacuation routes are designed to allow users to evacuate most efficiently and safely, taking into account road congestion information and geographical constraints.

[0163] The devices are used by local government officials to collect information on the area's geographical location, the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (road conditions and bridge strength), and upload it to a server. They also display real-time disaster information and evacuation instructions and notify residents. The device's dashboard displays optimized evacuation locations and evacuation routes on a map. Necessary information is also quickly delivered to residents via SMS and email.

[0164] Using a mobile device such as a smartphone, users can receive real-time information on optimal evacuation locations and routes based on their location. By entering a prompt, the user receives disaster prediction results from a generative AI model and obtains appropriate evacuation instructions in real time.

[0165] As a concrete example, if a typhoon is approaching a certain area, the system operates as follows: The server acquires weather data and predicts the probability of a typhoon-related disaster occurring. Based on the collected local information, it proposes optimal evacuation locations and calculates evacuation routes, displaying them on a map. The device displays the disaster prevention map to local government officials, who then issue evacuation instructions, and the server notifies residents via SMS or email. At this time, the user can obtain the disaster prediction results and evacuation information using the following prompt text:

[0166] Example prompt sentence:

[0167] "Use the latest weather data to predict the probability of a disaster occurring near my current location, suggest the safest evacuation location and evacuation route, and notify me of evacuation instructions in real time if necessary."

[0168] This system allows users to quickly and accurately obtain evacuation information and ensure their safety.

[0169] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0170] Step 1:

[0171] The server periodically obtains disaster-related information such as weather data, earthquake data, and flood data from external information providers (e.g., the Japan Meteorological Agency) and stores it in a database. The input is data obtained from external information providers, and the output is data stored in the server's database. This ensures that the latest disaster information is always available.

[0172] Step 2:

[0173] The terminal collects information from local government officials about the geographical information for each region (topography, rivers, population density, etc.), the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (road conditions, bridge strength, etc.), and uploads it to a server. The input is the regional information entered by the local government officials, and the output is the regional information uploaded to the server. This allows detailed data for each region to be collected.

[0174] Step 3:

[0175] The server preprocesses the collected disaster data and local information and formats it into a format suitable for machine learning models. The input is the collected raw data, and the output is the preprocessed data. Preprocessing such as data cleaning and normalization is performed to create data suitable for model training.

[0176] Step 4:

[0177] The server uses a machine learning model to predict the probability of a disaster occurring. The input is preprocessed data, and the output is the predicted probability of a disaster occurring. Specifically, the prediction is made by applying algorithms such as random forests and neural networks.

[0178] Step 5:

[0179] The server calculates the optimal evacuation site and evacuation route based on the predicted probability of disaster occurrence. The input is the predicted probability of disaster occurrence and collected local information, and the output is the optimal evacuation site and evacuation route. The optimal route is calculated taking into account the capacity, safety, and accessibility of the evacuation site.

[0180] Step 6:

[0181] The terminal displays the optimal evacuation locations and evacuation routes received from the server on a map and generates a disaster prevention map. The input is evacuation information from the server, and the output is a disaster prevention map displayed on a map. This makes it easier for local government officials to understand the current situation.

[0182] Step 7:

[0183] The server notifies residents of evacuation instructions and disaster information via SMS and email. The input is the generated evacuation instructions, and the output is the notification sent to residents, allowing residents to take evacuation action quickly.

[0184] Step 8:

[0185] The user inputs a prompt using a smartphone, receives the disaster prediction results from the generative AI model, and obtains evacuation information in real time. The input is the prompt and the user's location information, and the output is the disaster prediction results from the generative AI model. The following example prompt can be used:

[0186] Example prompt sentence:

[0187] "Use the latest weather data to predict the probability of a disaster occurring near my current location, suggest the safest evacuation location and evacuation route, and notify me of evacuation instructions in real time if necessary."

[0188] Through the above processing steps, this system can provide users with optimal evacuation information in real time, supporting quick and accurate evacuation.

[0189] 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.

[0190] The present invention combines a system for disaster prediction, evacuation site proposals, and shelter establishment support for local governments with an emotion engine that recognizes user emotions. This system includes multiple means for collecting disaster data, predicting the probability of disaster occurrence, optimizing evacuation sites, and displaying and notifying the results, as well as an emotion engine that recognizes user emotions and adjusts the information display content and notification method.

[0191] 1. Data Collection

[0192] The server periodically obtains disaster-related data such as weather data, earthquake data, and flood data from external information providers (e.g., the Japan Meteorological Agency) and stores it in a database. The terminals are used by local government officials to collect information on the geographical information of each region (topography, rivers, population density, etc.), the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (road conditions, bridge strength, etc.), and upload it to the server. Users enter this information into the system, and the collected data is updated daily.

[0193] 2. Creating a disaster prediction model

[0194] The server preprocesses the collected data and formats it into a format suitable for machine learning models. It then trains a model that calculates the probability of disaster occurrence using pre-defined algorithms (e.g., random forests, neural networks). This model predicts the probability of disaster occurrence for each region.

[0195] 3. Optimizing evacuation locations

[0196] The server executes a method to optimally locate multiple evacuation sites based on the predicted probability of disaster occurrence. Evacuation sites are determined based on their capacity, safety, and accessibility. It also calculates the optimal evacuation route. This evacuation route is designed to allow residents to evacuate most efficiently and safely, taking into account road congestion information and geographical constraints.

[0197] 4. Information adjustment by emotion engine

[0198] The server analyzes the user's emotional state using an emotion engine. The emotion engine recognizes the user's emotions based on multiple factors, such as voice, facial expression, and input speed. If the user's stress level is high, the system simplifies notification information or adds encouraging messages to reduce the user's stress.

[0199] 5. Display and notification of results

[0200] The server generates a digital disaster prevention map that displays optimized information on evacuation locations and evacuation routes. This disaster prevention map is displayed on the dashboard of the device used by local government officials. It also has a notification function to quickly convey evacuation instructions and disaster information to residents. The display content and notification method of the information are adjusted according to the analysis results of the emotion engine, providing appropriate evacuation information to residents.

[0201] Examples:

[0202] For example, if a typhoon is approaching a certain municipality, the following process can be carried out using this system.

[0203] 1. The server obtains the latest typhoon data from the Japan Meteorological Agency and stores it in a database.

[0204] 2. Local government officials operating the terminals input and update local geographical information, resident information, building earthquake resistance, and evacuation shelter information into the system.

[0205] 3. The server predicts the probability of a typhoon-related disaster occurring based on the collected data.

[0206] 4. The server selects a safe evacuation location based on the prediction results and displays that information on the device.

[0207] 5. The server calculates a safe and efficient evacuation route and displays it on a map.

[0208] 6. The emotion engine analyzes the user's emotional state and displays brief evacuation information and adds encouraging messages to users with high stress levels.

[0209] 7. The person using the terminal checks the disaster prevention map, corrects the contents if necessary, and then finalizes the evacuation plan.

[0210] 8. The server will notify residents of evacuation information via SMS or email based on the confirmed evacuation plan.

[0211] This system enables local governments to issue quick and accurate evacuation instructions and ensure the safety of residents. In addition, the introduction of an emotion engine makes it possible to provide appropriate information according to the emotional state of each user, making evacuation support more effective.

[0212] The processing flow will be explained below.

[0213] Step 1:

[0214] The server automatically obtains the latest disaster data (e.g., typhoon data, flood data, earthquake data, etc.) from the Japan Meteorological Agency and seismic observation stations, and stores it in a database. This includes the process of periodically obtaining data using an API.

[0215] Step 2:

[0216] Local government officials operating the terminals input geographical information for each region (topography, river locations, population density, etc.) and upload it to the server. This involves manually entering data using a dedicated input form.

[0217] Step 3:

[0218] Local government officials operating the terminals collect data on the earthquake resistance of buildings in the area, the capacity of evacuation shelters, and the state of infrastructure (strength of roads and bridges, etc.), and enter this data into the system, again using a dedicated input form.

[0219] Step 4:

[0220] The server preprocesses the collected data, which includes imputing missing data, standardizing data, and treating outliers.

[0221] Step 5:

[0222] The server uses machine learning algorithms to predict the probability of disaster occurrence. At this stage, a model is trained based on the preprocessed data and the model is used to calculate the probability of disaster occurrence for each region.

[0223] Step 6:

[0224] The server selects safe evacuation sites based on the predicted probability of disaster occurrence, taking into account factors such as the evacuation site's capacity, safety, and physical accessibility.

[0225] Step 7:

[0226] The server calculates the optimal evacuation route from the evacuation site to the residents' residence, taking into account road congestion information and geographical constraints (e.g., obstacles such as rivers and mountains).

[0227] Step 8:

[0228] To visualize the results of the calculations, the server displays evacuation locations and routes on a map, which is digitally generated and displayed on a dashboard.

[0229] Step 9:

[0230] The emotion engine analyzes the user's emotional state and recognizes the user's emotions based on multiple factors such as the user's voice, facial expression, and input speed.

[0231] Step 10:

[0232] The server adjusts the information display and notification method according to the user's emotional state as recognized by the emotion engine. For example, a user with a high stress level will be shown simple information and an encouraging message will be added.

[0233] Step 11:

[0234] The local government official operating the device will check the displayed disaster prevention map, revise the content if necessary, and then finalize the evacuation plan.

[0235] Step 12:

[0236] The server will then send evacuation information to residents via SMS or email based on the finalized evacuation plan, including evacuation locations, evacuation routes, and other important disaster information.

[0237] Step 13:

[0238] The user promptly begins evacuation based on the evacuation information received. The user heads to the evacuation site and stays there until safety is confirmed.

[0239] Step 14:

[0240] Local government officials using the devices will monitor the evacuation status of residents in real time and issue additional evacuation orders or rescue operations as necessary. This includes collecting and displaying real-time information.

[0241] The above are the detailed processing steps of the disaster prediction and evacuation support system of the present invention. This system enables local governments to respond quickly and appropriately when a disaster occurs, ensuring the safety of residents. The introduction of an emotion engine enables the provision of appropriate information according to each user's emotional state, making evacuation support even more effective.

[0242] Example 2

[0243] 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."

[0244] In recent years, the risk of disasters due to weather changes and seismic activity has increased, making it necessary for local governments to evacuate residents quickly and accurately. However, current disaster prediction and evacuation systems provide uniform information without taking into account the emotional state of individual residents, which can lead to stress and confusion and reduce the effectiveness of evacuation. Furthermore, optimization of evacuation locations and provision of evacuation routes may not fully take into account real-time traffic information or geographical constraints. This poses a challenge in ensuring the safety of residents.

[0245] 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 predicting the probability of disaster occurrence in each area based on collected disaster data, a means for optimally arranging multiple evacuation sites based on the disaster occurrence probability, and an emotion recognition means for analyzing the emotional state of the user and adjusting the notification content. This makes it possible to quickly identify areas with a high probability of disaster occurrence, provide appropriate evacuation sites and evacuation routes, and provide information to reduce stress according to the user's emotional state.

[0246] "Disaster data" refers to information about natural disasters such as weather, earthquakes, and floods.

[0247] "Probability of disaster occurrence" is an indicator that shows the possibility of a disaster occurring in a specific area based on collected disaster data and past cases.

[0248] An "evacuation site" is a safe place designated for temporary evacuation of residents in the event of a disaster.

[0249] "Optimal location" means effectively locating evacuation shelters and evacuation routes, taking into account given conditions and constraints, such as capacity, ease of access, and safety.

[0250] "Emotion recognition" is a technology that analyzes a user's emotional state based on their voice, facial expressions, input speed, etc., and adjusts information and notifications based on the results.

[0251] "Displaying on a map" means using visual information such as digital maps to display evacuation locations and evacuation routes geographically in an easy-to-understand manner.

[0252] "Notifying" means transmitting important information or warnings from the system to the user. This notification can be done by various means such as SMS, email, or application notification.

[0253] The present invention combines a system for disaster prediction, evacuation site proposals, and shelter establishment support for local governments with an emotion engine that recognizes user emotions. This system includes multiple means for collecting disaster data, predicting the probability of disaster occurrence, optimizing evacuation sites, and displaying and notifying the results, as well as an emotion engine that recognizes user emotions and adjusts the information display content and notification method.

[0254] The server periodically obtains data on disasters, such as weather data, earthquake data, and flood data, from external information providers and stores it in a database. The server preprocesses the collected data, performs data cleaning to fill in outliers and missing values, and then generates a model that calculates the probability of disaster occurrence using machine learning algorithms (e.g., random forests and neural networks).

[0255] The terminals will be used by local government officials to collect information on each region's geographical information (topography, rivers, population density, etc.), the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (road conditions, bridge strength, etc.), and upload it to a server. The terminals will also be used to check information on evacuation locations and evacuation routes needed in the event of a disaster.

[0256] Users are responsible for inputting the location, capacity, and seismic performance data of evacuation shelters into the system and receiving notifications from the system in the event of an emergency. The system utilizes emotion recognition to analyze the user's emotional state and, if stress levels are high, provides simplified information and encouraging messages to support evacuation behavior.

[0257] For example, if a typhoon is approaching a certain municipality, this system will execute the following specific processes: The server retrieves typhoon data from the Japan Meteorological Agency API and stores it in a database. The person operating the device enters local topographical and demographic data, and the user updates evacuation shelter location and capacity data. The server inputs the collected data into a machine learning model to predict the probability of a typhoon-related disaster. The server then optimizes evacuation sites and routes, and displays them on a map using the Google Maps API. The emotion engine analyzes the user's emotions, and simplified information and encouraging messages are sent to users in a highly stressed state.

[0258] An example of a prompt sentence to be input to the generative AI model is, "Please provide a detailed explanation of the disaster prediction system for local governments, including countermeasures that combine an emotion engine."

[0259] The above is an embodiment of the present invention, showing specific methods for processing collected disaster data, predicting the probability of disaster occurrence, optimizing evacuation sites, displaying the results, and recognizing user emotions. This system enables local governments to issue evacuation instructions quickly and accurately, ensuring the safety of residents.

[0260] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0261] Step 1: Data collection

[0262] The server periodically obtains weather data (temperature, precipitation, wind speed, etc.) from the Japan Meteorological Agency via API and stores it in its own database. The input is weather data obtained from an external API. The output is that data is stored in the server's database. Specifically, the server runs a scheduled job, fetches data from the API, and performs an INSERT operation on the database.

[0263] Step 2: Enter geographic information

[0264] Local government officials using the terminals manually input geographic information for each region (topography, river locations, flood risk areas, etc.) and upload it to the server. The input is geographic information collected by the officials using GIS software such as ArcGIS. The output is that information is uploaded to the server. Specifically, the officials input the geographic information, and the terminals call an API that uploads it to the server.

[0265] Step 3: Enter shelter information

[0266] Users input information about shelters, such as their capacity, earthquake resistance, and contact information for residents, into the system. The input includes detailed shelter information provided by users. The output is stored in a database on the server. Specifically, users enter data through a web interface, which is then sent as a POST request to the server and stored in the database.

[0267] Step 4: Data Preprocessing

[0268] The server preprocesses the collected weather data, geographic information, and evacuation shelter information, and fills in outliers and missing values. The input is the collected raw data. The output is a clean and complete dataset. Specifically, the server uses Python's Pandas library to clean the data, correct outliers, and fill in missing values ​​with the mean or median.

[0269] Step 5: Disaster prediction

[0270] The server inputs the preprocessed data into a machine learning algorithm (such as a random forest or neural network) to generate a model that calculates the probability of a disaster occurring. The input is a clean dataset. The output is the probability of a disaster occurring for each region. Specifically, the server trains the model using Scikit-learn or TensorFlow and calculates the prediction results.

[0271] Step 6: Optimize evacuation locations and routes

[0272] The server calculates the optimal evacuation locations and evacuation routes based on the predicted disaster occurrence probability and local geographic information. The inputs are the disaster occurrence probability and geographic information. The output is a list of optimal evacuation locations and evacuation routes. Specifically, the server uses the Google Maps API to calculate the optimal route taking into account real-time traffic information and stores the results in a database.

[0273] Step 7: Emotion Recognition

[0274] The server uses an emotion engine to analyze the user's emotional state. The inputs include the user's voice data and facial expression data. The output is the analyzed emotional state. Specifically, the server analyzes emotions using voice recognition software (e.g., voice recognition API) and facial expression recognition software (e.g., face API), and stores the results in a list.

[0275] Step 8: View and notify results

[0276] The server creates a digital disaster prevention map that displays optimized information on evacuation locations and evacuation routes on a map and notifies residents. The input is data on evacuation locations and evacuation routes. The output is a digital map and notification content. Specifically, the server generates the map using the Google Maps API and sends information to residents via SMS or email via the notification system.

[0277] The above is a description of the specific processing steps of this system.

[0278] (Application example 2)

[0279] 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."

[0280] The main function of conventional disaster prediction systems is to predict the probability of disaster occurrence based on collected data and optimize evacuation sites and evacuation routes, but these systems do not take into account the emotional state of each user, and have the problem of not being able to provide appropriate information if the user is in a high-stress state during an emergency.In particular, in situations where users may panic during a disaster, it is necessary to display information and notifications that correspond to the user's emotional state, but there was a lack of a mechanism to achieve this.

[0281] 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.

[0282] In this invention, the server includes means for predicting the probability of disaster occurrence in each area based on multiple disaster data collected, means for optimally locating multiple evacuation sites based on the disaster occurrence probability, means for displaying the evacuation sites and evacuation routes on a map, means for notifying the user of information on the map, and emotion analysis means for analyzing the emotional state of the user based on multiple factors such as voice, facial expression, and input speed, and adjusting the display content and notification method. This makes it possible to provide appropriate information that takes the emotional state of the user into consideration when a disaster occurs.

[0283] "Disaster data" refers to any information related to disasters, such as weather data, earthquake data, and flood data.

[0284] "Probability of disaster occurrence" is a prediction of the possibility of a disaster occurring in each region based on collected disaster data.

[0285] An "evacuation site" refers to a safe place where residents can temporarily take refuge in the event of a disaster.

[0286] An "evacuation route" refers to a route or path that allows a user to reach an evacuation site safely and efficiently.

[0287] "Means of displaying on a map" refers to a method for visually showing information such as the probability of disaster occurrence, evacuation locations, and evacuation routes in map format.

[0288] "Means of notification" refers to the method for providing disaster information and evacuation instructions to users, including email, SMS, and in-app notifications.

[0289] "Emotion analysis means" refers to a method for analyzing the user's emotional state based on multiple elements such as voice, facial expression, and input speed, and adjusting the display content and notification method.

[0290] "User" refers to an individual or local government official who uses this system.

[0291] "Server" refers to a computer system for collecting, storing, and processing disaster data.

[0292] This invention combines a system that predicts disasters, suggests evacuation sites, and supports the establishment of evacuation shelters with an emotion engine that recognizes the user's emotions. This system collects disaster data, predicts the probability of disaster occurrence, optimizes evacuation sites, and displays and notifies the results. It also analyzes the user's emotional state based on multiple factors such as voice, facial expression, and input speed, and adjusts the information displayed and the notification method accordingly.

[0293] Overall system configuration

[0294] Hardware and Software

[0295] 1. Server:

[0296] The server is a computer system for collecting, storing, and processing disaster data. Specific software includes Python and machine learning libraries (e.g., scikit-learn and TensorFlow) to train and run a disaster probability prediction model.

[0297] 2. Terminal:

[0298] The terminals are computers or tablets used by local government officials to input and update data such as geographical information for each region, building information, and infrastructure status. A browser-based dashboard is displayed on the terminals.

[0299] 3. User Device:

[0300] The user device is a smartphone used by residents. An application for receiving notifications is installed on the device. This application uses hardware such as a camera (facial expression recognition), microphone (voice recognition), and touch point detection (input speed) for emotion analysis.

[0301] Processing Details

[0302] The server operates as follows:

[0303] 1. Data Collection:

[0304] The server periodically obtains the latest weather, earthquake, and flood data from external information providers such as the Japan Meteorological Agency and stores it in a database. Local government officials also use terminals to input and update geographical information for each region, the earthquake resistance of buildings, the capacity of evacuation shelters, and the status of infrastructure.

[0305] 2. Disaster prediction model:

[0306] The server preprocesses the collected data and formats it into a format suitable for machine learning models. It then uses algorithms such as random forests and neural networks to train a model that can predict the probability of a disaster occurring. This makes it possible to predict the probability of a disaster occurring in each region.

[0307] 3. Optimizing evacuation locations:

[0308] Based on the predicted probability of disaster occurrence, the server optimally allocates multiple evacuation sites, taking into consideration the safety, capacity, and accessibility of each site. It also calculates the optimal evacuation route and displays it on a map.

[0309] 4. Emotion analysis:

[0310] The server analyzes the user's emotional state based on voice, facial expression, and input data collected from the user's device. The analysis engine uses OpenCV, Google Cloud Speech-to-Text, and touch data analysis algorithms. If the user's emotional state is tense, the notification information is simplified and an encouraging message is added.

[0311] 5. Display and notification of results:

[0312] The server displays optimized evacuation locations and evacuation routes on a map, which is then displayed on the device dashboard as a digital disaster prevention map. It also notifies residents of evacuation instructions and disaster information on their smartphones, adjusting the content and display method of the notifications based on the results of emotion analysis.

[0313] Examples:

[0314] For example, if a municipality experiences prolonged heavy rain and is at risk of flooding, the system can perform the following operations:

[0315] The server obtains the latest heavy rain data from the Japan Meteorological Agency and stores it in a database.

[0316] Local government officials operating the terminals input and update local geographical information, resident information, building earthquake resistance, and evacuation shelter information into the system.

[0317] The server predicts the probability of flood disasters occurring based on the collected data.

[0318] The server selects a safe evacuation location based on the prediction results and displays that information on the device.

[0319] The server calculates safe and efficient evacuation routes and displays them on a map.

[0320] The emotion engine analyzes the user's emotional state and displays brief evacuation information and adds encouraging messages to users with high stress levels.

[0321] The person in charge using the terminal will check the disaster prevention map, revise the contents if necessary, and then finalize the evacuation plan.

[0322] Based on the confirmed evacuation plan, the server will notify residents of evacuation information via SMS or email.

[0323] Example prompt sentence:

[0324] "It suggests optimal evacuation routes based on current weather conditions and adjusts notifications based on the user's emotional state."

[0325] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0326] Step 1:

[0327] The server obtains the latest weather data, earthquake data, flood data, etc. from external information providers such as the Japan Meteorological Agency. The input is disaster data obtained from external APIs, and the output is disaster data stored on the server. Specifically, it periodically sends API requests and stores the responses in a database.

[0328] Step 2:

[0329] Local government officials operating the terminals input and update local geographic information, building seismic performance, evacuation shelter capacity, and infrastructure status for each region. The input is manual entry of local information, and the output is updated local information that is uploaded to the server. Specific operations include entering information through a browser-based dashboard and pressing the submit button to upload the data.

[0330] Step 3:

[0331] The server preprocesses the collected disaster data and area information and formats it into a format suitable for the machine learning model. The input is the collected disaster data and area information, and the output is a formatted dataset. Specific operations include filling in missing values, removing outliers, and normalizing the data.

[0332] Step 4:

[0333] The server uses the shaped dataset to train a model that predicts the probability of disaster occurrence using algorithms such as random forests and neural networks. The input is the shaped dataset, and the output is a trained model that predicts the probability of disaster occurrence. Specifically, the server inputs the training data into the algorithm and optimizes the model parameters.

[0334] Step 5:

[0335] The server uses the trained model to predict the probability of disaster occurrence for each region in real time. The input is the latest disaster data, and the output is the probability of disaster occurrence for each region. Specifically, new data is input into the model, and the prediction results are obtained and stored in the database.

[0336] Step 6:

[0337] The server selects safe evacuation sites and calculates optimal evacuation routes based on the predicted probability of disaster occurrence. The inputs are the probability of disaster occurrence, local geographic information, and infrastructure information, and the output is information on evacuation sites and evacuation routes. Specifically, the server selects evacuation sites taking into account each site's capacity, safety, and accessibility, and calculates optimal evacuation routes based on traffic information.

[0338] Step 7:

[0339] The server displays information on evacuation locations and evacuation routes on a map and generates a digital disaster prevention map. The input is information on evacuation locations and evacuation routes, and the output is a digital disaster prevention map that is displayed on the device's dashboard. Specifically, the server visually displays evacuation locations and routes by overlaying them on the map data.

[0340] Step 8:

[0341] The user device acquires voice data, facial expression data, and input data and performs emotion analysis. The input is data acquired from the user device, and the output is the analyzed emotional state of the user. Specifically, data is collected using a camera and microphone and processed by an emotion analysis engine.

[0342] Step 9:

[0343] The server adjusts the display content and notification method based on the results of emotion analysis. The input is the analyzed emotional state and evacuation information, and the output is the adjusted notification information. Specifically, for users with high stress, the system simplifies the information and adds an encouraging message.

[0344] Step 10:

[0345] The server notifies residents of evacuation information via SMS or email based on the finalized evacuation plan. The input is the final evacuation plan, and the output is the notification sent to residents. Specifically, the server generates disaster information and evacuation instructions in text format and sends them using the communication system.

[0346] Example prompt sentence:

[0347] "It suggests optimal evacuation routes based on current weather conditions and adjusts notifications based on the user's emotional state."

[0348] 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.

[0349] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0350] 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.

[0351] [Second embodiment]

[0352] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0353] 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.

[0354] 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).

[0355] 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.

[0356] 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.

[0357] 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).

[0358] 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.

[0359] 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.

[0360] 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.

[0361] 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.

[0362] 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.

[0363] 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."

[0364] The present invention is a system for disaster prediction for local governments, which supports the proposal of evacuation sites and the establishment of evacuation shelters. This system includes multiple means for collecting disaster data, predicting the probability of disaster occurrence, optimizing evacuation sites, and displaying and notifying the results.

[0365] 1. Data Collection

[0366] The server periodically obtains disaster-related data such as weather data, earthquake data, and flood data from external information providers (e.g., the Japan Meteorological Agency) and stores it in a database. The terminals are used by local government officials to collect information on the geographical information of each region (topography, rivers, population density, etc.), the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (road conditions, bridge strength, etc.), and upload it to the server. Users enter this information into the system, and the collected data is updated daily.

[0367] 2. Creating a disaster prediction model

[0368] The server preprocesses the collected data and formats it into a format suitable for machine learning models. It then trains a model that calculates the probability of disaster occurrence using pre-defined algorithms (e.g., random forests, neural networks). This model predicts the probability of disaster occurrence for each region.

[0369] 3. Optimizing evacuation locations

[0370] The server executes a method to optimally locate multiple evacuation sites based on the predicted probability of disaster occurrence. Evacuation sites are determined based on their capacity, safety, and accessibility. It also calculates the optimal evacuation route. This evacuation route is designed to allow residents to evacuate most efficiently and safely, taking into account road congestion information and geographical constraints.

[0371] 4. Display and notification of results

[0372] The server generates a digital disaster prevention map that displays optimized evacuation locations and evacuation routes on a map. This disaster prevention map is displayed on the dashboard of the device used by local government officials. The system is also equipped with a notification function to quickly communicate evacuation instructions and disaster information to residents. This allows the device to deliver necessary information to residents via SMS and email.

[0373] Examples:

[0374] For example, if a typhoon is approaching a certain municipality, the following process can be carried out using this system.

[0375] 1. The server obtains the latest typhoon data from the Japan Meteorological Agency and stores it in a database.

[0376] 2. Local government officials operating the terminals input and update local geographical information, resident information, building earthquake resistance, and evacuation shelter information into the system.

[0377] 3. The server predicts the probability of a typhoon-related disaster occurring based on the collected data.

[0378] 4. The server selects a safe evacuation location based on the prediction results and displays that information on the device.

[0379] 5. The server calculates a safe and efficient evacuation route and displays it on a map.

[0380] 6. The person using the terminal checks the disaster prevention map, makes any necessary corrections, and then issues the final evacuation instructions.

[0381] 7. The server notifies residents of evacuation information via SMS or email.

[0382] This system will enable local governments to issue quick and accurate evacuation instructions to ensure the safety of residents.

[0383] The processing flow will be explained below.

[0384] Step 1:

[0385] The server automatically obtains the latest disaster data (e.g., typhoon data, flood data, earthquake data, etc.) from the Japan Meteorological Agency and seismic observation stations, and stores it in a database. This includes the process of periodically obtaining data using an API.

[0386] Step 2:

[0387] Local government officials operating the terminals input geographical information for each region (topography, river locations, population density, etc.) and upload it to the server. This involves manually entering data using a dedicated input form.

[0388] Step 3:

[0389] Local government officials operating the terminals collect data on the earthquake resistance of buildings in the area, the capacity of evacuation shelters, and the state of infrastructure (strength of roads and bridges, etc.), and enter this data into the system, again using a dedicated input form.

[0390] Step 4:

[0391] The server preprocesses the collected data, which includes imputing missing data, standardizing data, and treating outliers.

[0392] Step 5:

[0393] The server uses machine learning algorithms to predict the probability of disaster occurrence. At this stage, a model is trained based on the preprocessed data and the model is used to calculate the probability of disaster occurrence for each region.

[0394] Step 6:

[0395] The server selects safe evacuation sites based on the predicted probability of disaster occurrence, taking into account factors such as the shelter's capacity, safety, and ease of physical access.

[0396] Step 7:

[0397] The server calculates the optimal evacuation route from the evacuation site to the residents' residence, taking into account road congestion information and geographical constraints (e.g., obstacles such as rivers and mountains).

[0398] Step 8:

[0399] To visualize the results of the calculations, the server displays evacuation locations and routes on a map, which is digitally generated and displayed on a dashboard.

[0400] Step 9:

[0401] The local government official operating the device checks the displayed disaster prevention map and, if necessary, modifies and confirms the contents. Once the modifications are complete, the final evacuation plan is confirmed.

[0402] Step 10:

[0403] The server will then send evacuation information to residents via SMS or email based on the finalized evacuation plan, including evacuation locations, evacuation routes, and other important disaster information.

[0404] Step 11:

[0405] The user promptly begins evacuation based on the evacuation information received. The user heads to the evacuation site and stays there until safety is confirmed.

[0406] Step 12:

[0407] Local government officials using the devices will monitor the evacuation status of residents in real time and issue additional evacuation orders or rescue operations as necessary. This includes collecting and displaying real-time information.

[0408] The above are the detailed processing steps of the disaster prediction and evacuation support system of the present invention. This system enables local governments to respond quickly and appropriately when a disaster occurs, thereby ensuring the safety of residents.

[0409] Example 1

[0410] 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."

[0411] In modern society, disasters are difficult to predict, and selecting evacuation sites and ensuring efficient evacuation routes are major challenges, especially for local governments. Furthermore, if it is not possible to properly predict the probability of disaster occurrence or locate optimal evacuation sites, it becomes difficult to ensure the safety of residents. To address this situation, a system is needed that can accurately predict the probability of disaster occurrence, optimally locate evacuation sites, and quickly notify residents.

[0412] 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.

[0413] In this invention, the server includes means for predicting the probability of disaster occurrence in each region based on multiple disaster-related data collected, means for optimally locating multiple evacuation sites based on the disaster occurrence probability, means for displaying the evacuation sites and evacuation routes on a map, means for notifying users of the information on the map, means for formatting the collected data into a format suitable for a machine learning model, means for calculating the disaster occurrence probability using the machine learning model, and means for calculating evacuation routes taking into account the status of infrastructure. This enables accurate prediction of the disaster occurrence probability, optimal location of evacuation sites, efficient calculation of evacuation routes, and rapid information notification.

[0414] "Disaster-related data" refers to weather data, earthquake data, flood data and other disaster-related information.

[0415] "Means for predicting the probability of disaster occurrence" refers to algorithms and tools that calculate and predict the possibility of disasters occurring in each region based on collected disaster-related data.

[0416] "Methods for optimally locating evacuation shelters" refers to algorithms and methods for safely and efficiently locating evacuation shelters based on collected data and the predicted probability of disaster occurrence.

[0417] "Means for displaying on a map" refers to a graphical interface or digital map that visually displays calculated evacuation locations and evacuation routes.

[0418] "Means of notifying users of information" refers to the function of quickly conveying important evacuation and disaster information to users using communication methods such as SMS and email.

[0419] "Means of formatting data suitable for machine learning models" refers to procedures and methods for converting collected disaster-related data into a format that can be processed by machine learning algorithms.

[0420] "Means for calculating the probability of disaster occurrence" refers to models and algorithms that use data science techniques to calculate the probability of a disaster occurring.

[0421] "Means for calculating evacuation routes taking into account infrastructure conditions" refers to algorithms and tools for calculating safe and quick evacuation routes based on road congestion information and geographical constraints.

[0422] The present invention provides a disaster prediction system for local governments, and supports them in proposing evacuation sites and opening evacuation shelters. Detailed embodiments for carrying out the present invention will be described below.

[0423] This system involves a series of processing steps performed by a server, terminals, and users, including data collection, data processing, disaster prediction, evacuation site optimization, and result display and notification.

[0424] 1. Hardware and Software Used

[0425] The servers use cloud computing services (e.g., Amazon Web Services and Google Cloud Platform) to handle large amounts of data, and the database uses a database management system that supports SQL and NoSQL formats.

[0426] The terminals are devices such as computers and tablets used by local government officials, and they access the dashboard via a browser. The system is designed as a web application, and the front end uses JavaScript frameworks such as React and Vue.js.

[0427] Users are local government officials and residents who access the system through terminals and input or receive the necessary information. The user interface is designed to be intuitive and easy to operate.

[0428] 2. Data Collection and Processing

[0429] The server periodically obtains weather data, earthquake data, flood data, and other data from external information providers such as the Japan Meteorological Agency via API and stores it in a database, which is updated in real time.

[0430] Local government officials operating the terminals input detailed information such as the area's geographical location, the earthquake resistance of buildings, the capacity of evacuation shelters, the condition of roads and bridges, etc. The collected data is then instantly uploaded to a server.

[0431] The server preprocesses the collected data and formats it into a format suitable for machine learning models, such as converting text data into numerical data and imputing missing values.

[0432] 3. Disaster Prediction Using Machine Learning

[0433] The server uses the preprocessed data to train machine learning models, including algorithms such as random forests and neural networks (e.g., TensorFlow and PyTorch), which predict the probability of disasters occurring in each region.

[0434] 4. Optimization and display of evacuation locations

[0435] The server then executes a method to optimally locate evacuation sites based on the predicted probability of disaster occurrence. It also calculates optimal evacuation routes, taking into account infrastructure conditions (road congestion and geographical constraints). This allows the most efficient and safe evacuation route for residents to be designed.

[0436] The generated evacuation location and route information is compiled into a digital disaster prevention map and displayed on a dashboard on the device, allowing local government officials to intuitively check the information and make corrections if necessary.

[0437] 5. Notification of Results

[0438] The server notifies residents of the final evacuation location and evacuation route via SMS or email, enabling quick and accurate information transmission in the event of a disaster.

[0439] Specific examples

[0440] For example, if a typhoon is approaching, the following process will be executed:

[0441] 1. The server retrieves the latest typhoon data from the Japan Meteorological Agency's API and stores it in a database.

[0442] 2. Local government officials operate the terminals to input and update information such as local geographical information, resident information, building earthquake resistance, and evacuation shelter information.

[0443] 3. The server preprocesses the collected data and trains the disaster prediction model.

[0444] 4. The server uses the trained model to predict the probability of typhoon disasters.

[0445] 5. The server calculates the optimal evacuation location and evacuation route, and generates a digital disaster prevention map.

[0446] 6. Local government officials check the disaster prevention map on the terminal, make any necessary corrections, and issue final evacuation instructions.

[0447] 7. The server notifies residents of evacuation information via SMS or email.

[0448] Prompt Sentence Examples

[0449] "Use this system to select the best evacuation location for an approaching typhoon and calculate an efficient evacuation route."

[0450] The above describes a specific embodiment of the present invention. By implementing the invention in accordance with this embodiment, it is possible to accurately predict the probability of a disaster occurring, optimally locate evacuation sites, calculate efficient evacuation routes, and quickly notify users of the information.

[0451] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0452] Step 1: Data collection

[0453] The server periodically retrieves disaster-related data such as weather data, earthquake data, and flood data from external information providers (e.g., the Japan Meteorological Agency) through APIs and stores it in a database. This input data includes the latest weather information, earthquake occurrence status, river water level data, etc. In the process of retrieving this data, the server sends requests and parses and stores the data received as a response. As an output, a consistent storage of disaster-related data is formed in the database.

[0454] Step 2: Enter region data

[0455] Local government officials operating the terminals use a dedicated input form to input local geographic information (e.g., topography, rivers, population density, etc.), the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (e.g., road conditions, bridge strength, etc.). The input data covers detailed information about the area and the current state of infrastructure. The input information is uploaded to a server in real time and stored in a database. As a result, a rich dataset specific to the area is created.

[0456] Step 3: Preprocessing the data

[0457] The server preprocesses the collected disaster-related and local data. The input data undergoes processes such as missing value imputation, data normalization, and encoding of categorical variables. For example, it converts text data to numerical data and handles outliers. The output is a consistent dataset in a format suitable for machine learning models.

[0458] Step 4: Train the machine learning model

[0459] The server uses the preprocessed dataset to train a machine learning model. Algorithms used include random forests and neural networks (e.g., TensorFlow, PyTorch). The input data includes past disaster data and regional characteristics. The model can predict the probability of disaster occurrence for each region. The output is a trained disaster prediction model.

[0460] Step 5: Predict the probability of disaster occurrence

[0461] The server uses a trained machine learning model to predict the probability of disasters occurring in each region, taking the latest collected data as input. The input data includes current weather data and local information. The output is a predicted probability of disaster occurrence for each region, which is then stored in a database.

[0462] Step 6: Optimize evacuation locations

[0463] The server runs a mathematical optimization algorithm to optimally locate multiple evacuation sites based on the predicted probability of disaster occurrence. Input data includes the predicted probability of disaster occurrence, the capacity of the evacuation site, safety, accessibility, etc. The output is the calculation of the optimal evacuation site and evacuation route.

[0464] Step 7: Creating a digital disaster prevention map

[0465] The server generates a digital disaster prevention map based on the optimized evacuation location and evacuation route information. This digital disaster prevention map is designed to be easily referenced in the event of a disaster. The input data includes information on evacuation locations and routes. The output is a visually easy-to-understand map display.

[0466] Step 8: View the dashboard

[0467] Local government officials using the terminals can check the generated digital disaster prevention map on a dedicated dashboard. The input includes the generated disaster prevention map information. The output is the disaster prevention map displayed on the terminal screen.

[0468] Step 9: Notifications

[0469] The server notifies residents of optimized evacuation locations and routes via SMS and email. This process is done quickly, before a disaster occurs. Input data includes evacuation information and residents' contact information. The output is evacuation information sent to residents via SMS and email.

[0470] (Application example 1)

[0471] 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."

[0472] Conventional disaster prediction and evacuation systems often fail to predict the probability of disaster occurrence and suggest evacuation locations in sufficient real time, or provide insufficient optimal evacuation routes based on the user's location information. Furthermore, they lack a means to utilize generative AI models to instantly predict the probability of disaster occurrence and effectively notify users. This creates challenges in ensuring the safety of residents by preventing rapid and accurate evacuation in the event of a disaster.

[0473] 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.

[0474] In this invention, the server includes means for predicting the probability of disaster occurrence in each region based on multiple disaster data collected, means for optimally locating multiple evacuation sites based on the disaster occurrence probability, means for displaying the evacuation sites and evacuation routes on a map, means for notifying the user of the information on the map, means for calculating the disaster occurrence probability and evacuation site information in real time and proposing optimal evacuation sites and evacuation routes based on the user's location information, and means for receiving and notifying the disaster prediction results using a generative AI model in response to input of a prompt sentence. This makes it possible to provide the user with optimal evacuation information in real time and support rapid and accurate evacuation.

[0475] "Probability of disaster occurrence" is a probability value that represents the possibility of a disaster occurring in a specific area based on collected disaster data.

[0476] An "evacuation site" is a designated location for residents to evacuate safely in the event of a disaster.

[0477] An "evacuation route" is a route that allows residents to safely travel to an evacuation site.

[0478] "Means for displaying on a map" refers to the technology and methods for visually displaying evacuation locations and evacuation routes on a map.

[0479] The "means for notifying the user" is a method for promptly notifying the user of evacuation information.

[0480] "Real-time calculation" means that calculations are made instantly based on the current situation.

[0481] "User location information" is geographic information about the location where the user is currently located.

[0482] "Using a generative AI model" means using a model that uses artificial intelligence to make predictions and perform data analysis.

[0483] A "prompt" refers to an instruction or question that is input into a generative AI model.

[0484] "Disaster prediction results" are the predicted results of the probability and circumstances of disaster occurrence calculated by the generative AI model.

[0485] This invention is a system for predicting the probability of disaster occurrence in real time and proposing optimal evacuation sites and evacuation routes. This system includes multiple means for collecting disaster data, predicting the probability of disaster occurrence, optimizing evacuation sites, and displaying and notifying the results. This allows for rapid and accurate evacuation support in the event of a disaster.

[0486] The server periodically obtains disaster-related data, such as weather data, earthquake data, and flood data, from external information providers and stores it in a database. This data is used as training data for a model to predict the probability of disaster occurrence. The collected data is then preprocessed and formatted into a format suitable for the machine learning model. The machine learning model uses algorithms such as random forests and neural networks. This model calculates the probability of disaster occurrence and predicts the probability of disaster occurrence for each region.

[0487] The server also generates optimal evacuation locations and routes based on the predicted probability of disaster. Evacuation locations are determined based on their capacity, safety, and accessibility. Evacuation routes are designed to allow users to evacuate most efficiently and safely, taking into account road congestion information and geographical constraints.

[0488] The devices are used by local government officials to collect information on the area's geographical location, the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (road conditions and bridge strength), and upload it to a server. They also display real-time disaster information and evacuation instructions and notify residents. The device's dashboard displays optimized evacuation locations and evacuation routes on a map. Necessary information is also quickly delivered to residents via SMS and email.

[0489] Using a mobile device such as a smartphone, users can receive real-time information on optimal evacuation locations and routes based on their location. By entering a prompt, the user receives disaster prediction results from a generative AI model and obtains appropriate evacuation instructions in real time.

[0490] As a concrete example, if a typhoon is approaching a certain area, the system operates as follows: The server acquires weather data and predicts the probability of a typhoon-related disaster occurring. Based on the collected local information, it proposes optimal evacuation locations and calculates evacuation routes, displaying them on a map. The device displays the disaster prevention map to local government officials, who then issue evacuation instructions, and the server notifies residents via SMS or email. At this time, the user can obtain the disaster prediction results and evacuation information using the following prompt text:

[0491] Example prompt sentence:

[0492] "Use the latest weather data to predict the probability of a disaster occurring near my current location, suggest the safest evacuation location and evacuation route, and notify me of evacuation instructions in real time if necessary."

[0493] This system allows users to quickly and accurately obtain evacuation information and ensure their safety.

[0494] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0495] Step 1:

[0496] The server periodically obtains disaster-related information such as weather data, earthquake data, and flood data from external information providers (e.g., the Japan Meteorological Agency) and stores it in a database. The input is data obtained from external information providers, and the output is data stored in the server's database. This ensures that the latest disaster information is always available.

[0497] Step 2:

[0498] The terminal collects information from local government officials about the geographical information for each region (topography, rivers, population density, etc.), the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (road conditions, bridge strength, etc.), and uploads it to a server. The input is the regional information entered by the local government officials, and the output is the regional information uploaded to the server. This allows detailed data for each region to be collected.

[0499] Step 3:

[0500] The server preprocesses the collected disaster data and local information and formats it into a format suitable for machine learning models. The input is the collected raw data, and the output is the preprocessed data. Preprocessing such as data cleaning and normalization is performed to create data suitable for model training.

[0501] Step 4:

[0502] The server uses a machine learning model to predict the probability of a disaster occurring. The input is preprocessed data, and the output is the predicted probability of a disaster occurring. Specifically, the prediction is made by applying algorithms such as random forests and neural networks.

[0503] Step 5:

[0504] The server calculates the optimal evacuation site and evacuation route based on the predicted probability of disaster occurrence. The input is the predicted probability of disaster occurrence and collected local information, and the output is the optimal evacuation site and evacuation route. The optimal route is calculated taking into account the capacity, safety, and accessibility of the evacuation site.

[0505] Step 6:

[0506] The terminal displays the optimal evacuation locations and evacuation routes received from the server on a map and generates a disaster prevention map. The input is evacuation information from the server, and the output is a disaster prevention map displayed on a map. This makes it easier for local government officials to understand the current situation.

[0507] Step 7:

[0508] The server notifies residents of evacuation instructions and disaster information via SMS and email. The input is the generated evacuation instructions, and the output is the notification sent to residents, allowing residents to take evacuation action quickly.

[0509] Step 8:

[0510] The user inputs a prompt using a smartphone, receives the disaster prediction results from the generative AI model, and obtains evacuation information in real time. The input is the prompt and the user's location information, and the output is the disaster prediction results from the generative AI model. The following example prompt can be used:

[0511] Example prompt sentence:

[0512] "Use the latest weather data to predict the probability of a disaster occurring near my current location, suggest the safest evacuation location and evacuation route, and notify me of evacuation instructions in real time if necessary."

[0513] Through the above processing steps, this system can provide users with optimal evacuation information in real time, supporting quick and accurate evacuation.

[0514] 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.

[0515] The present invention combines a system for disaster prediction, evacuation site proposals, and shelter establishment support for local governments with an emotion engine that recognizes user emotions. This system includes multiple means for collecting disaster data, predicting the probability of disaster occurrence, optimizing evacuation sites, and displaying and notifying the results, as well as an emotion engine that recognizes user emotions and adjusts the information display content and notification method.

[0516] 1. Data Collection

[0517] The server periodically obtains disaster-related data such as weather data, earthquake data, and flood data from external information providers (e.g., the Japan Meteorological Agency) and stores it in a database. The terminals are used by local government officials to collect information on the geographical information of each region (topography, rivers, population density, etc.), the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (road conditions, bridge strength, etc.), and upload it to the server. Users enter this information into the system, and the collected data is updated daily.

[0518] 2. Creating a disaster prediction model

[0519] The server preprocesses the collected data and formats it into a format suitable for machine learning models. It then trains a model that calculates the probability of disaster occurrence using pre-defined algorithms (e.g., random forests, neural networks). This model predicts the probability of disaster occurrence for each region.

[0520] 3. Optimizing evacuation locations

[0521] The server executes a method to optimally locate multiple evacuation sites based on the predicted probability of disaster occurrence. Evacuation sites are determined based on their capacity, safety, and accessibility. It also calculates the optimal evacuation route. This evacuation route is designed to allow residents to evacuate most efficiently and safely, taking into account road congestion information and geographical constraints.

[0522] 4. Information adjustment by emotion engine

[0523] The server analyzes the user's emotional state using an emotion engine. The emotion engine recognizes the user's emotions based on multiple factors, such as voice, facial expression, and input speed. If the user's stress level is high, the system simplifies notification information or adds encouraging messages to reduce the user's stress.

[0524] 5. Display and notification of results

[0525] The server generates a digital disaster prevention map that displays optimized information on evacuation locations and evacuation routes. This disaster prevention map is displayed on the dashboard of the device used by local government officials. It also has a notification function to quickly convey evacuation instructions and disaster information to residents. The display content and notification method of the information are adjusted according to the analysis results of the emotion engine, providing appropriate evacuation information to residents.

[0526] Examples:

[0527] For example, if a typhoon is approaching a certain municipality, the following process can be carried out using this system.

[0528] 1. The server obtains the latest typhoon data from the Japan Meteorological Agency and stores it in a database.

[0529] 2. Local government officials operating the terminals input and update local geographical information, resident information, building earthquake resistance, and evacuation shelter information into the system.

[0530] 3. The server predicts the probability of a typhoon-related disaster occurring based on the collected data.

[0531] 4. The server selects a safe evacuation location based on the prediction results and displays that information on the device.

[0532] 5. The server calculates a safe and efficient evacuation route and displays it on a map.

[0533] 6. The emotion engine analyzes the user's emotional state and displays brief evacuation information and adds encouraging messages to users with high stress levels.

[0534] 7. The person using the terminal checks the disaster prevention map, corrects the contents if necessary, and then finalizes the evacuation plan.

[0535] 8. The server will notify residents of evacuation information via SMS or email based on the confirmed evacuation plan.

[0536] This system enables local governments to issue quick and accurate evacuation instructions and ensure the safety of residents. In addition, the introduction of an emotion engine makes it possible to provide appropriate information according to the emotional state of each user, making evacuation support more effective.

[0537] The processing flow will be explained below.

[0538] Step 1:

[0539] The server automatically obtains the latest disaster data (e.g., typhoon data, flood data, earthquake data, etc.) from the Japan Meteorological Agency and seismic observation stations, and stores it in a database. This includes the process of periodically obtaining data using an API.

[0540] Step 2:

[0541] Local government officials operating the terminals input geographical information for each region (topography, river locations, population density, etc.) and upload it to the server. This involves manually entering data using a dedicated input form.

[0542] Step 3:

[0543] Local government officials operating the terminals collect data on the earthquake resistance of buildings in the area, the capacity of evacuation shelters, and the state of infrastructure (strength of roads and bridges, etc.), and enter this data into the system, again using a dedicated input form.

[0544] Step 4:

[0545] The server preprocesses the collected data, which includes imputing missing data, standardizing data, and treating outliers.

[0546] Step 5:

[0547] The server uses machine learning algorithms to predict the probability of disaster occurrence. At this stage, a model is trained based on the preprocessed data and the model is used to calculate the probability of disaster occurrence for each region.

[0548] Step 6:

[0549] The server selects safe evacuation sites based on the predicted probability of disaster occurrence, taking into account factors such as the evacuation site's capacity, safety, and physical accessibility.

[0550] Step 7:

[0551] The server calculates the optimal evacuation route from the evacuation site to the residents' residence, taking into account road congestion information and geographical constraints (e.g., obstacles such as rivers and mountains).

[0552] Step 8:

[0553] To visualize the results of the calculations, the server displays evacuation locations and routes on a map, which is digitally generated and displayed on a dashboard.

[0554] Step 9:

[0555] The emotion engine analyzes the user's emotional state and recognizes the user's emotions based on multiple factors such as the user's voice, facial expression, and input speed.

[0556] Step 10:

[0557] The server adjusts the information display and notification method according to the user's emotional state as recognized by the emotion engine. For example, a user with a high stress level will be shown simple information and an encouraging message will be added.

[0558] Step 11:

[0559] The local government official operating the device will check the displayed disaster prevention map, revise the content if necessary, and then finalize the evacuation plan.

[0560] Step 12:

[0561] The server will then send evacuation information to residents via SMS or email based on the finalized evacuation plan, including evacuation locations, evacuation routes, and other important disaster information.

[0562] Step 13:

[0563] The user promptly begins evacuation based on the evacuation information received. The user heads to the evacuation site and stays there until safety is confirmed.

[0564] Step 14:

[0565] Local government officials using the devices will monitor the evacuation status of residents in real time and issue additional evacuation orders or rescue operations as necessary. This includes collecting and displaying real-time information.

[0566] The above are the detailed processing steps of the disaster prediction and evacuation support system of the present invention. This system enables local governments to respond quickly and appropriately when a disaster occurs, ensuring the safety of residents. The introduction of an emotion engine enables the provision of appropriate information according to each user's emotional state, making evacuation support even more effective.

[0567] Example 2

[0568] 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."

[0569] In recent years, the risk of disasters due to weather changes and seismic activity has increased, making it necessary for local governments to evacuate residents quickly and accurately. However, current disaster prediction and evacuation systems provide uniform information without taking into account the emotional state of individual residents, which can lead to stress and confusion and reduce the effectiveness of evacuation. Furthermore, optimization of evacuation locations and provision of evacuation routes may not fully take into account real-time traffic information or geographical constraints. This poses a challenge in ensuring the safety of residents.

[0570] 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 predicting the probability of disaster occurrence in each area based on collected disaster data, a means for optimally arranging multiple evacuation sites based on the disaster occurrence probability, and an emotion recognition means for analyzing the emotional state of the user and adjusting the notification content. This makes it possible to quickly identify areas with a high probability of disaster occurrence, provide appropriate evacuation sites and evacuation routes, and provide information to reduce stress according to the user's emotional state.

[0571] "Disaster data" refers to information about natural disasters such as weather, earthquakes, and floods.

[0572] "Probability of disaster occurrence" is an indicator that shows the possibility of a disaster occurring in a specific area based on collected disaster data and past cases.

[0573] An "evacuation site" is a safe place designated for temporary evacuation of residents in the event of a disaster.

[0574] "Optimal location" means effectively locating evacuation shelters and evacuation routes, taking into account given conditions and constraints, such as capacity, ease of access, and safety.

[0575] "Emotion recognition" is a technology that analyzes a user's emotional state based on their voice, facial expressions, input speed, etc., and adjusts information and notifications based on the results.

[0576] "Displaying on a map" means using visual information such as digital maps to display evacuation locations and evacuation routes geographically in an easy-to-understand manner.

[0577] "Notifying" means transmitting important information or warnings from the system to the user. This notification can be done by various means such as SMS, email, or application notification.

[0578] The present invention combines a system for disaster prediction, evacuation site proposals, and shelter establishment support for local governments with an emotion engine that recognizes user emotions. This system includes multiple means for collecting disaster data, predicting the probability of disaster occurrence, optimizing evacuation sites, and displaying and notifying the results, as well as an emotion engine that recognizes user emotions and adjusts the information display content and notification method.

[0579] The server periodically obtains data on disasters, such as weather data, earthquake data, and flood data, from external information providers and stores it in a database. The server preprocesses the collected data, performs data cleaning to fill in outliers and missing values, and then generates a model that calculates the probability of disaster occurrence using machine learning algorithms (e.g., random forests and neural networks).

[0580] The terminals will be used by local government officials to collect information on each region's geographical information (topography, rivers, population density, etc.), the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (road conditions, bridge strength, etc.), and upload it to a server. The terminals will also be used to check information on evacuation locations and evacuation routes needed in the event of a disaster.

[0581] Users are responsible for inputting the location, capacity, and seismic performance data of evacuation shelters into the system and receiving notifications from the system in the event of an emergency. The system utilizes emotion recognition to analyze the user's emotional state and, if stress levels are high, provides simplified information and encouraging messages to support evacuation behavior.

[0582] For example, if a typhoon is approaching a certain municipality, this system will execute the following specific processes: The server retrieves typhoon data from the Japan Meteorological Agency API and stores it in a database. The person operating the device enters local topographical and demographic data, and the user updates evacuation shelter location and capacity data. The server inputs the collected data into a machine learning model to predict the probability of a typhoon-related disaster. The server then optimizes evacuation sites and routes, and displays them on a map using the Google Maps API. The emotion engine analyzes the user's emotions, and simplified information and encouraging messages are sent to users in a highly stressed state.

[0583] An example of a prompt sentence to be input to the generative AI model is, "Please provide a detailed explanation of the disaster prediction system for local governments, including countermeasures that combine an emotion engine."

[0584] The above is an embodiment of the present invention, showing specific methods for processing collected disaster data, predicting the probability of disaster occurrence, optimizing evacuation sites, displaying the results, and recognizing user emotions. This system enables local governments to issue evacuation instructions quickly and accurately, ensuring the safety of residents.

[0585] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0586] Step 1: Data collection

[0587] The server periodically obtains weather data (temperature, precipitation, wind speed, etc.) from the Japan Meteorological Agency via API and stores it in its own database. The input is weather data obtained from an external API. The output is that data is stored in the server's database. Specifically, the server runs a scheduled job, fetches data from the API, and performs an INSERT operation on the database.

[0588] Step 2: Enter geographic information

[0589] Local government officials using the terminals manually input geographic information for each region (topography, river locations, flood risk areas, etc.) and upload it to the server. The input is geographic information collected by the officials using GIS software such as ArcGIS. The output is that information is uploaded to the server. Specifically, the officials input the geographic information, and the terminals call an API that uploads it to the server.

[0590] Step 3: Enter shelter information

[0591] Users input information about shelters, such as their capacity, earthquake resistance, and contact information for residents, into the system. The input includes detailed shelter information provided by users. The output is stored in a database on the server. Specifically, users enter data through a web interface, which is then sent as a POST request to the server and stored in the database.

[0592] Step 4: Data Preprocessing

[0593] The server preprocesses the collected weather data, geographic information, and evacuation shelter information, and fills in outliers and missing values. The input is the collected raw data. The output is a clean and complete dataset. Specifically, the server uses Python's Pandas library to clean the data, correct outliers, and fill in missing values ​​with the mean or median.

[0594] Step 5: Disaster prediction

[0595] The server inputs the preprocessed data into a machine learning algorithm (such as a random forest or neural network) to generate a model that calculates the probability of a disaster occurring. The input is a clean dataset. The output is the probability of a disaster occurring for each region. Specifically, the server trains the model using Scikit-learn or TensorFlow and calculates the prediction results.

[0596] Step 6: Optimize evacuation locations and routes

[0597] The server calculates the optimal evacuation locations and evacuation routes based on the predicted disaster occurrence probability and local geographic information. The inputs are the disaster occurrence probability and geographic information. The output is a list of optimal evacuation locations and evacuation routes. Specifically, the server uses the Google Maps API to calculate the optimal route taking into account real-time traffic information and stores the results in a database.

[0598] Step 7: Emotion Recognition

[0599] The server uses an emotion engine to analyze the user's emotional state. The inputs include the user's voice data and facial expression data. The output is the analyzed emotional state. Specifically, the server analyzes emotions using voice recognition software (e.g., voice recognition API) and facial expression recognition software (e.g., face API), and stores the results in a list.

[0600] Step 8: View and notify results

[0601] The server creates a digital disaster prevention map that displays optimized information on evacuation locations and evacuation routes on a map and notifies residents. The input is data on evacuation locations and evacuation routes. The output is a digital map and notification content. Specifically, the server generates the map using the Google Maps API and sends information to residents via SMS or email via the notification system.

[0602] The above is a description of the specific processing steps of this system.

[0603] (Application example 2)

[0604] 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."

[0605] The main function of conventional disaster prediction systems is to predict the probability of disaster occurrence based on collected data and optimize evacuation sites and evacuation routes, but these systems do not take into account the emotional state of each user, and have the problem of not being able to provide appropriate information if the user is in a high-stress state during an emergency.In particular, in situations where users may panic during a disaster, it is necessary to display information and notifications that correspond to the user's emotional state, but there was a lack of a mechanism to achieve this.

[0606] 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.

[0607] In this invention, the server includes means for predicting the probability of disaster occurrence in each area based on multiple disaster data collected, means for optimally locating multiple evacuation sites based on the disaster occurrence probability, means for displaying the evacuation sites and evacuation routes on a map, means for notifying the user of information on the map, and emotion analysis means for analyzing the emotional state of the user based on multiple factors such as voice, facial expression, and input speed, and adjusting the display content and notification method. This makes it possible to provide appropriate information that takes the emotional state of the user into consideration when a disaster occurs.

[0608] "Disaster data" refers to any information related to disasters, such as weather data, earthquake data, and flood data.

[0609] "Probability of disaster occurrence" is a prediction of the possibility of a disaster occurring in each region based on collected disaster data.

[0610] An "evacuation site" refers to a safe place where residents can temporarily take refuge in the event of a disaster.

[0611] An "evacuation route" refers to a route or path that allows a user to reach an evacuation site safely and efficiently.

[0612] "Means of displaying on a map" refers to a method for visually showing information such as the probability of disaster occurrence, evacuation locations, and evacuation routes in map format.

[0613] "Means of notification" refers to the method for providing disaster information and evacuation instructions to users, including email, SMS, and in-app notifications.

[0614] "Emotion analysis means" refers to a method for analyzing the user's emotional state based on multiple elements such as voice, facial expression, and input speed, and adjusting the display content and notification method.

[0615] "User" refers to an individual or local government official who uses this system.

[0616] "Server" refers to a computer system for collecting, storing, and processing disaster data.

[0617] This invention combines a system that predicts disasters, suggests evacuation sites, and supports the establishment of evacuation shelters with an emotion engine that recognizes the user's emotions. This system collects disaster data, predicts the probability of disaster occurrence, optimizes evacuation sites, and displays and notifies the results. It also analyzes the user's emotional state based on multiple factors such as voice, facial expression, and input speed, and adjusts the information displayed and the notification method accordingly.

[0618] Overall system configuration

[0619] Hardware and Software

[0620] 1. Server:

[0621] The server is a computer system for collecting, storing, and processing disaster data. Specific software includes Python and machine learning libraries (e.g., scikit-learn and TensorFlow) to train and run a disaster probability prediction model.

[0622] 2. Terminal:

[0623] The terminals are computers or tablets used by local government officials to input and update data such as geographical information for each region, building information, and infrastructure status. A browser-based dashboard is displayed on the terminals.

[0624] 3. User Device:

[0625] The user device is a smartphone used by residents. An application for receiving notifications is installed on the device. This application uses hardware such as a camera (facial expression recognition), microphone (voice recognition), and touch point detection (input speed) for emotion analysis.

[0626] Processing Details

[0627] The server operates as follows:

[0628] 1. Data Collection:

[0629] The server periodically obtains the latest weather, earthquake, and flood data from external information providers such as the Japan Meteorological Agency and stores it in a database. Local government officials also use terminals to input and update geographical information for each region, the earthquake resistance of buildings, the capacity of evacuation shelters, and the status of infrastructure.

[0630] 2. Disaster prediction model:

[0631] The server preprocesses the collected data and formats it into a format suitable for machine learning models. It then uses algorithms such as random forests and neural networks to train a model that can predict the probability of a disaster occurring. This makes it possible to predict the probability of a disaster occurring in each region.

[0632] 3. Optimizing evacuation locations:

[0633] Based on the predicted probability of disaster occurrence, the server optimally allocates multiple evacuation sites, taking into consideration the safety, capacity, and accessibility of each site. It also calculates the optimal evacuation route and displays it on a map.

[0634] 4. Emotion analysis:

[0635] The server analyzes the user's emotional state based on voice, facial expression, and input data collected from the user's device. The analysis engine uses OpenCV, Google Cloud Speech-to-Text, and touch data analysis algorithms. If the user's emotional state is tense, the notification information is simplified and an encouraging message is added.

[0636] 5. Display and notification of results:

[0637] The server displays optimized evacuation locations and evacuation routes on a map, which is then displayed on the device dashboard as a digital disaster prevention map. It also notifies residents of evacuation instructions and disaster information on their smartphones, adjusting the content and display method of the notifications based on the results of emotion analysis.

[0638] Examples:

[0639] For example, if a municipality experiences prolonged heavy rain and is at risk of flooding, the system can perform the following operations:

[0640] The server obtains the latest heavy rain data from the Japan Meteorological Agency and stores it in a database.

[0641] Local government officials operating the terminals input and update local geographical information, resident information, building earthquake resistance, and evacuation shelter information into the system.

[0642] The server predicts the probability of flood disasters occurring based on the collected data.

[0643] The server selects a safe evacuation location based on the prediction results and displays that information on the device.

[0644] The server calculates safe and efficient evacuation routes and displays them on a map.

[0645] The emotion engine analyzes the user's emotional state and displays brief evacuation information and adds encouraging messages to users with high stress levels.

[0646] The person in charge using the terminal will check the disaster prevention map, revise the contents if necessary, and then finalize the evacuation plan.

[0647] Based on the confirmed evacuation plan, the server will notify residents of evacuation information via SMS or email.

[0648] Example prompt sentence:

[0649] "It suggests optimal evacuation routes based on current weather conditions and adjusts notifications based on the user's emotional state."

[0650] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0651] Step 1:

[0652] The server obtains the latest weather data, earthquake data, flood data, etc. from external information providers such as the Japan Meteorological Agency. The input is disaster data obtained from external APIs, and the output is disaster data stored on the server. Specifically, it periodically sends API requests and stores the responses in a database.

[0653] Step 2:

[0654] Local government officials operating the terminals input and update local geographic information, building seismic performance, evacuation shelter capacity, and infrastructure status for each region. The input is manual entry of local information, and the output is updated local information that is uploaded to the server. Specific operations include entering information through a browser-based dashboard and pressing the submit button to upload the data.

[0655] Step 3:

[0656] The server preprocesses the collected disaster data and area information and formats it into a format suitable for the machine learning model. The input is the collected disaster data and area information, and the output is a formatted dataset. Specific operations include filling in missing values, removing outliers, and normalizing the data.

[0657] Step 4:

[0658] The server uses the shaped dataset to train a model that predicts the probability of disaster occurrence using algorithms such as random forests and neural networks. The input is the shaped dataset, and the output is a trained model that predicts the probability of disaster occurrence. Specifically, the server inputs the training data into the algorithm and optimizes the model parameters.

[0659] Step 5:

[0660] The server uses the trained model to predict the probability of disaster occurrence for each region in real time. The input is the latest disaster data, and the output is the probability of disaster occurrence for each region. Specifically, new data is input into the model, and the prediction results are obtained and stored in the database.

[0661] Step 6:

[0662] The server selects safe evacuation sites and calculates optimal evacuation routes based on the predicted probability of disaster occurrence. The inputs are the probability of disaster occurrence, local geographic information, and infrastructure information, and the output is information on evacuation sites and evacuation routes. Specifically, the server selects evacuation sites taking into account each site's capacity, safety, and accessibility, and calculates optimal evacuation routes based on traffic information.

[0663] Step 7:

[0664] The server displays information on evacuation locations and evacuation routes on a map and generates a digital disaster prevention map. The input is information on evacuation locations and evacuation routes, and the output is a digital disaster prevention map that is displayed on the device's dashboard. Specifically, the server visually displays evacuation locations and routes by overlaying them on the map data.

[0665] Step 8:

[0666] The user device acquires voice data, facial expression data, and input data and performs emotion analysis. The input is data acquired from the user device, and the output is the analyzed emotional state of the user. Specifically, data is collected using a camera and microphone and processed by an emotion analysis engine.

[0667] Step 9:

[0668] The server adjusts the display content and notification method based on the results of emotion analysis. The input is the analyzed emotional state and evacuation information, and the output is the adjusted notification information. Specifically, for users with high stress, the system simplifies the information and adds an encouraging message.

[0669] Step 10:

[0670] The server notifies residents of evacuation information via SMS or email based on the finalized evacuation plan. The input is the final evacuation plan, and the output is the notification sent to residents. Specifically, the server generates disaster information and evacuation instructions in text format and sends them using the communication system.

[0671] Example prompt sentence:

[0672] "It suggests optimal evacuation routes based on current weather conditions and adjusts notifications based on the user's emotional state."

[0673] 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.

[0674] 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.

[0675] 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.

[0676] [Third embodiment]

[0677] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0678] 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.

[0679] 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).

[0680] 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.

[0681] 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.

[0682] 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).

[0683] 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.

[0684] 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.

[0685] 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.

[0686] 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.

[0687] 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.

[0688] 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."

[0689] The present invention is a system for disaster prediction for local governments, which supports the proposal of evacuation sites and the establishment of evacuation shelters. This system includes multiple means for collecting disaster data, predicting the probability of disaster occurrence, optimizing evacuation sites, and displaying and notifying the results.

[0690] 1. Data Collection

[0691] The server periodically obtains disaster-related data such as weather data, earthquake data, and flood data from external information providers (e.g., the Japan Meteorological Agency) and stores it in a database. The terminals are used by local government officials to collect information on the geographical information of each region (topography, rivers, population density, etc.), the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (road conditions, bridge strength, etc.), and upload it to the server. Users enter this information into the system, and the collected data is updated daily.

[0692] 2. Creating a disaster prediction model

[0693] The server preprocesses the collected data and formats it into a format suitable for machine learning models. It then trains a model that calculates the probability of disaster occurrence using pre-defined algorithms (e.g., random forests, neural networks). This model predicts the probability of disaster occurrence for each region.

[0694] 3. Optimizing evacuation locations

[0695] The server executes a method to optimally locate multiple evacuation sites based on the predicted probability of disaster occurrence. Evacuation sites are determined based on their capacity, safety, and accessibility. It also calculates the optimal evacuation route. This evacuation route is designed to allow residents to evacuate most efficiently and safely, taking into account road congestion information and geographical constraints.

[0696] 4. Display and notification of results

[0697] The server generates a digital disaster prevention map that displays optimized evacuation locations and evacuation routes on a map. This disaster prevention map is displayed on the dashboard of the device used by local government officials. The system is also equipped with a notification function to quickly communicate evacuation instructions and disaster information to residents. This allows the device to deliver necessary information to residents via SMS and email.

[0698] Examples:

[0699] For example, if a typhoon is approaching a certain municipality, the following process can be carried out using this system.

[0700] 1. The server obtains the latest typhoon data from the Japan Meteorological Agency and stores it in a database.

[0701] 2. Local government officials operating the terminals input and update local geographical information, resident information, building earthquake resistance, and evacuation shelter information into the system.

[0702] 3. The server predicts the probability of a typhoon-related disaster occurring based on the collected data.

[0703] 4. The server selects a safe evacuation location based on the prediction results and displays that information on the device.

[0704] 5. The server calculates a safe and efficient evacuation route and displays it on a map.

[0705] 6. The person using the terminal checks the disaster prevention map, makes any necessary corrections, and then issues the final evacuation instructions.

[0706] 7. The server notifies residents of evacuation information via SMS or email.

[0707] This system will enable local governments to issue quick and accurate evacuation instructions to ensure the safety of residents.

[0708] The processing flow will be explained below.

[0709] Step 1:

[0710] The server automatically obtains the latest disaster data (e.g., typhoon data, flood data, earthquake data, etc.) from the Japan Meteorological Agency and seismic observation stations, and stores it in a database. This includes the process of periodically obtaining data using an API.

[0711] Step 2:

[0712] Local government officials operating the terminals input geographical information for each region (topography, river locations, population density, etc.) and upload it to the server. This involves manually entering data using a dedicated input form.

[0713] Step 3:

[0714] Local government officials operating the terminals collect data on the earthquake resistance of buildings in the area, the capacity of evacuation shelters, and the state of infrastructure (strength of roads and bridges, etc.), and enter this data into the system, again using a dedicated input form.

[0715] Step 4:

[0716] The server preprocesses the collected data, which includes imputing missing data, standardizing data, and treating outliers.

[0717] Step 5:

[0718] The server uses machine learning algorithms to predict the probability of disaster occurrence. At this stage, a model is trained based on the preprocessed data and the model is used to calculate the probability of disaster occurrence for each region.

[0719] Step 6:

[0720] The server selects safe evacuation sites based on the predicted probability of disaster occurrence, taking into account factors such as the shelter's capacity, safety, and ease of physical access.

[0721] Step 7:

[0722] The server calculates the optimal evacuation route from the evacuation site to the residents' residence, taking into account road congestion information and geographical constraints (e.g., obstacles such as rivers and mountains).

[0723] Step 8:

[0724] To visualize the results of the calculations, the server displays evacuation locations and routes on a map, which is digitally generated and displayed on a dashboard.

[0725] Step 9:

[0726] The local government official operating the device checks the displayed disaster prevention map and, if necessary, modifies and confirms the contents. Once the modifications are complete, the final evacuation plan is confirmed.

[0727] Step 10:

[0728] The server will then send evacuation information to residents via SMS or email based on the finalized evacuation plan, including evacuation locations, evacuation routes, and other important disaster information.

[0729] Step 11:

[0730] The user promptly begins evacuation based on the evacuation information received. The user heads to the evacuation site and stays there until safety is confirmed.

[0731] Step 12:

[0732] Local government officials using the devices will monitor the evacuation status of residents in real time and issue additional evacuation orders or rescue operations as necessary. This includes collecting and displaying real-time information.

[0733] The above are the detailed processing steps of the disaster prediction and evacuation support system of the present invention. This system enables local governments to respond quickly and appropriately when a disaster occurs, thereby ensuring the safety of residents.

[0734] Example 1

[0735] 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."

[0736] In modern society, disasters are difficult to predict, and selecting evacuation sites and ensuring efficient evacuation routes are major challenges, especially for local governments. Furthermore, if it is not possible to properly predict the probability of disaster occurrence or locate optimal evacuation sites, it becomes difficult to ensure the safety of residents. To address this situation, a system is needed that can accurately predict the probability of disaster occurrence, optimally locate evacuation sites, and quickly notify residents.

[0737] 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.

[0738] In this invention, the server includes means for predicting the probability of disaster occurrence in each region based on multiple disaster-related data collected, means for optimally locating multiple evacuation sites based on the disaster occurrence probability, means for displaying the evacuation sites and evacuation routes on a map, means for notifying users of the information on the map, means for formatting the collected data into a format suitable for a machine learning model, means for calculating the disaster occurrence probability using the machine learning model, and means for calculating evacuation routes taking into account the status of infrastructure. This enables accurate prediction of the disaster occurrence probability, optimal location of evacuation sites, efficient calculation of evacuation routes, and rapid information notification.

[0739] "Disaster-related data" refers to weather data, earthquake data, flood data and other disaster-related information.

[0740] "Means for predicting the probability of disaster occurrence" refers to algorithms and tools that calculate and predict the possibility of disasters occurring in each region based on collected disaster-related data.

[0741] "Methods for optimally locating evacuation shelters" refers to algorithms and methods for safely and efficiently locating evacuation shelters based on collected data and the predicted probability of disaster occurrence.

[0742] "Means for displaying on a map" refers to a graphical interface or digital map that visually displays calculated evacuation locations and evacuation routes.

[0743] "Means of notifying users of information" refers to the function of quickly conveying important evacuation and disaster information to users using communication methods such as SMS and email.

[0744] "Means of formatting data suitable for machine learning models" refers to procedures and methods for converting collected disaster-related data into a format that can be processed by machine learning algorithms.

[0745] "Means for calculating the probability of disaster occurrence" refers to models and algorithms that use data science techniques to calculate the probability of a disaster occurring.

[0746] "Means for calculating evacuation routes taking into account infrastructure conditions" refers to algorithms and tools for calculating safe and quick evacuation routes based on road congestion information and geographical constraints.

[0747] The present invention provides a disaster prediction system for local governments, and supports them in proposing evacuation sites and opening evacuation shelters. Detailed embodiments for carrying out the present invention will be described below.

[0748] This system involves a series of processing steps performed by a server, terminals, and users, including data collection, data processing, disaster prediction, evacuation site optimization, and result display and notification.

[0749] 1. Hardware and Software Used

[0750] The servers use cloud computing services (e.g., Amazon Web Services and Google Cloud Platform) to handle large amounts of data, and the database uses a database management system that supports SQL and NoSQL formats.

[0751] The terminals are devices such as computers and tablets used by local government officials, and they access the dashboard via a browser. The system is designed as a web application, and the front end uses JavaScript frameworks such as React and Vue.js.

[0752] Users are local government officials and residents who access the system through terminals and input or receive the necessary information. The user interface is designed to be intuitive and easy to operate.

[0753] 2. Data Collection and Processing

[0754] The server periodically obtains weather data, earthquake data, flood data, and other data from external information providers such as the Japan Meteorological Agency via API and stores it in a database, which is updated in real time.

[0755] Local government officials operating the terminals input detailed information such as the area's geographical location, the earthquake resistance of buildings, the capacity of evacuation shelters, the condition of roads and bridges, etc. The collected data is then instantly uploaded to a server.

[0756] The server preprocesses the collected data and formats it into a format suitable for machine learning models, such as converting text data into numerical data and imputing missing values.

[0757] 3. Disaster Prediction Using Machine Learning

[0758] The server uses the preprocessed data to train machine learning models, including algorithms such as random forests and neural networks (e.g., TensorFlow and PyTorch), which predict the probability of disasters occurring in each region.

[0759] 4. Optimization and display of evacuation locations

[0760] The server then executes a method to optimally locate evacuation sites based on the predicted probability of disaster occurrence. It also calculates optimal evacuation routes, taking into account infrastructure conditions (road congestion and geographical constraints). This allows the most efficient and safe evacuation route for residents to be designed.

[0761] The generated evacuation location and route information is compiled into a digital disaster prevention map and displayed on a dashboard on the device, allowing local government officials to intuitively check the information and make corrections if necessary.

[0762] 5. Notification of Results

[0763] The server notifies residents of the final evacuation location and evacuation route via SMS or email, enabling quick and accurate information transmission in the event of a disaster.

[0764] Specific examples

[0765] For example, if a typhoon is approaching, the following process will be executed:

[0766] 1. The server retrieves the latest typhoon data from the Japan Meteorological Agency's API and stores it in a database.

[0767] 2. Local government officials operate the terminals to input and update information such as local geographical information, resident information, building earthquake resistance, and evacuation shelter information.

[0768] 3. The server preprocesses the collected data and trains the disaster prediction model.

[0769] 4. The server uses the trained model to predict the probability of typhoon disasters.

[0770] 5. The server calculates the optimal evacuation location and evacuation route, and generates a digital disaster prevention map.

[0771] 6. Local government officials check the disaster prevention map on the terminal, make any necessary corrections, and issue final evacuation instructions.

[0772] 7. The server notifies residents of evacuation information via SMS or email.

[0773] Prompt Sentence Examples

[0774] "Use this system to select the best evacuation location for an approaching typhoon and calculate an efficient evacuation route."

[0775] The above describes a specific embodiment of the present invention. By implementing the invention in accordance with this embodiment, it is possible to accurately predict the probability of a disaster occurring, optimally locate evacuation sites, calculate efficient evacuation routes, and quickly notify users of the information.

[0776] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0777] Step 1: Data collection

[0778] The server periodically retrieves disaster-related data such as weather data, earthquake data, and flood data from external information providers (e.g., the Japan Meteorological Agency) through APIs and stores it in a database. This input data includes the latest weather information, earthquake occurrence status, river water level data, etc. In the process of retrieving this data, the server sends requests and parses and stores the data received as a response. As an output, a consistent storage of disaster-related data is formed in the database.

[0779] Step 2: Enter region data

[0780] Local government officials operating the terminals use a dedicated input form to input local geographic information (e.g., topography, rivers, population density, etc.), the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (e.g., road conditions, bridge strength, etc.). The input data covers detailed information about the area and the current state of infrastructure. The input information is uploaded to a server in real time and stored in a database. As a result, a rich dataset specific to the area is created.

[0781] Step 3: Preprocessing the data

[0782] The server preprocesses the collected disaster-related and local data. The input data undergoes processes such as missing value imputation, data normalization, and encoding of categorical variables. For example, it converts text data to numerical data and handles outliers. The output is a consistent dataset in a format suitable for machine learning models.

[0783] Step 4: Train the machine learning model

[0784] The server uses the preprocessed dataset to train a machine learning model. Algorithms used include random forests and neural networks (e.g., TensorFlow, PyTorch). The input data includes past disaster data and regional characteristics. The model can predict the probability of disaster occurrence for each region. The output is a trained disaster prediction model.

[0785] Step 5: Predict the probability of disaster occurrence

[0786] The server uses a trained machine learning model to predict the probability of disasters occurring in each region, taking the latest collected data as input. The input data includes current weather data and local information. The output is a predicted probability of disaster occurrence for each region, which is then stored in a database.

[0787] Step 6: Optimize evacuation locations

[0788] The server runs a mathematical optimization algorithm to optimally locate multiple evacuation sites based on the predicted probability of disaster occurrence. Input data includes the predicted probability of disaster occurrence, the capacity of the evacuation site, safety, accessibility, etc. The output is the calculation of the optimal evacuation site and evacuation route.

[0789] Step 7: Creating a digital disaster prevention map

[0790] The server generates a digital disaster prevention map based on the optimized evacuation location and evacuation route information. This digital disaster prevention map is designed to be easily referenced in the event of a disaster. The input data includes information on evacuation locations and routes. The output is a visually easy-to-understand map display.

[0791] Step 8: View the dashboard

[0792] Local government officials using the terminals can check the generated digital disaster prevention map on a dedicated dashboard. The input includes the generated disaster prevention map information. The output is the disaster prevention map displayed on the terminal screen.

[0793] Step 9: Notifications

[0794] The server notifies residents of optimized evacuation locations and routes via SMS and email. This process is done quickly, before a disaster occurs. Input data includes evacuation information and residents' contact information. The output is evacuation information sent to residents via SMS and email.

[0795] (Application example 1)

[0796] 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."

[0797] Conventional disaster prediction and evacuation systems often fail to predict the probability of disaster occurrence and suggest evacuation locations in sufficient real time, or provide insufficient optimal evacuation routes based on the user's location information. Furthermore, they lack a means to utilize generative AI models to instantly predict the probability of disaster occurrence and effectively notify users. This creates challenges in ensuring the safety of residents by preventing rapid and accurate evacuation in the event of a disaster.

[0798] 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.

[0799] In this invention, the server includes means for predicting the probability of disaster occurrence in each region based on multiple disaster data collected, means for optimally locating multiple evacuation sites based on the disaster occurrence probability, means for displaying the evacuation sites and evacuation routes on a map, means for notifying the user of the information on the map, means for calculating the disaster occurrence probability and evacuation site information in real time and proposing optimal evacuation sites and evacuation routes based on the user's location information, and means for receiving and notifying the disaster prediction results using a generative AI model in response to input of a prompt sentence. This makes it possible to provide the user with optimal evacuation information in real time and support rapid and accurate evacuation.

[0800] "Probability of disaster occurrence" is a probability value that represents the possibility of a disaster occurring in a specific area based on collected disaster data.

[0801] An "evacuation site" is a designated location for residents to evacuate safely in the event of a disaster.

[0802] An "evacuation route" is a route that allows residents to safely travel to an evacuation site.

[0803] "Means for displaying on a map" refers to the technology and methods for visually displaying evacuation locations and evacuation routes on a map.

[0804] The "means for notifying the user" is a method for promptly notifying the user of evacuation information.

[0805] "Real-time calculation" means that calculations are made instantly based on the current situation.

[0806] "User location information" is geographic information about the location where the user is currently located.

[0807] "Using a generative AI model" means using a model that uses artificial intelligence to make predictions and perform data analysis.

[0808] A "prompt" refers to an instruction or question that is input into a generative AI model.

[0809] "Disaster prediction results" are the predicted results of the probability and circumstances of disaster occurrence calculated by the generative AI model.

[0810] This invention is a system for predicting the probability of disaster occurrence in real time and proposing optimal evacuation sites and evacuation routes. This system includes multiple means for collecting disaster data, predicting the probability of disaster occurrence, optimizing evacuation sites, and displaying and notifying the results. This allows for rapid and accurate evacuation support in the event of a disaster.

[0811] The server periodically obtains disaster-related data, such as weather data, earthquake data, and flood data, from external information providers and stores it in a database. This data is used as training data for a model to predict the probability of disaster occurrence. The collected data is then preprocessed and formatted into a format suitable for the machine learning model. The machine learning model uses algorithms such as random forests and neural networks. This model calculates the probability of disaster occurrence and predicts the probability of disaster occurrence for each region.

[0812] The server also generates optimal evacuation locations and routes based on the predicted probability of disaster. Evacuation locations are determined based on their capacity, safety, and accessibility. Evacuation routes are designed to allow users to evacuate most efficiently and safely, taking into account road congestion information and geographical constraints.

[0813] The devices are used by local government officials to collect information on the area's geographical location, the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (road conditions and bridge strength), and upload it to a server. They also display real-time disaster information and evacuation instructions and notify residents. The device's dashboard displays optimized evacuation locations and evacuation routes on a map. Necessary information is also quickly delivered to residents via SMS and email.

[0814] Using a mobile device such as a smartphone, users can receive real-time information on optimal evacuation locations and routes based on their location. By entering a prompt, the user receives disaster prediction results from a generative AI model and obtains appropriate evacuation instructions in real time.

[0815] As a concrete example, if a typhoon is approaching a certain area, the system operates as follows: The server acquires weather data and predicts the probability of a typhoon-related disaster occurring. Based on the collected local information, it proposes optimal evacuation locations and calculates evacuation routes, displaying them on a map. The device displays the disaster prevention map to local government officials, who then issue evacuation instructions, and the server notifies residents via SMS or email. At this time, the user can obtain the disaster prediction results and evacuation information using the following prompt text:

[0816] Example prompt sentence:

[0817] "Use the latest weather data to predict the probability of a disaster occurring near my current location, suggest the safest evacuation location and evacuation route, and notify me of evacuation instructions in real time if necessary."

[0818] This system allows users to quickly and accurately obtain evacuation information and ensure their safety.

[0819] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0820] Step 1:

[0821] The server periodically obtains disaster-related information such as weather data, earthquake data, and flood data from external information providers (e.g., the Japan Meteorological Agency) and stores it in a database. The input is data obtained from external information providers, and the output is data stored in the server's database. This ensures that the latest disaster information is always available.

[0822] Step 2:

[0823] The terminal collects information from local government officials about the geographical information for each region (topography, rivers, population density, etc.), the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (road conditions, bridge strength, etc.), and uploads it to a server. The input is the regional information entered by the local government officials, and the output is the regional information uploaded to the server. This allows detailed data for each region to be collected.

[0824] Step 3:

[0825] The server preprocesses the collected disaster data and local information and formats it into a format suitable for machine learning models. The input is the collected raw data, and the output is the preprocessed data. Preprocessing such as data cleaning and normalization is performed to create data suitable for model training.

[0826] Step 4:

[0827] The server uses a machine learning model to predict the probability of a disaster occurring. The input is preprocessed data, and the output is the predicted probability of a disaster occurring. Specifically, the prediction is made by applying algorithms such as random forests and neural networks.

[0828] Step 5:

[0829] The server calculates the optimal evacuation site and evacuation route based on the predicted probability of disaster occurrence. The input is the predicted probability of disaster occurrence and collected local information, and the output is the optimal evacuation site and evacuation route. The optimal route is calculated taking into account the capacity, safety, and accessibility of the evacuation site.

[0830] Step 6:

[0831] The terminal displays the optimal evacuation locations and evacuation routes received from the server on a map and generates a disaster prevention map. The input is evacuation information from the server, and the output is a disaster prevention map displayed on a map. This makes it easier for local government officials to understand the current situation.

[0832] Step 7:

[0833] The server notifies residents of evacuation instructions and disaster information via SMS and email. The input is the generated evacuation instructions, and the output is the notification sent to residents, allowing residents to take evacuation action quickly.

[0834] Step 8:

[0835] The user inputs a prompt using a smartphone, receives the disaster prediction results from the generative AI model, and obtains evacuation information in real time. The input is the prompt and the user's location information, and the output is the disaster prediction results from the generative AI model. The following example prompt can be used:

[0836] Example prompt sentence:

[0837] "Use the latest weather data to predict the probability of a disaster occurring near my current location, suggest the safest evacuation location and evacuation route, and notify me of evacuation instructions in real time if necessary."

[0838] Through the above processing steps, this system can provide users with optimal evacuation information in real time, supporting quick and accurate evacuation.

[0839] 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.

[0840] The present invention combines a system for disaster prediction, evacuation site proposals, and shelter establishment support for local governments with an emotion engine that recognizes user emotions. This system includes multiple means for collecting disaster data, predicting the probability of disaster occurrence, optimizing evacuation sites, and displaying and notifying the results, as well as an emotion engine that recognizes user emotions and adjusts the information display content and notification method.

[0841] 1. Data Collection

[0842] The server periodically obtains disaster-related data such as weather data, earthquake data, and flood data from external information providers (e.g., the Japan Meteorological Agency) and stores it in a database. The terminals are used by local government officials to collect information on the geographical information of each region (topography, rivers, population density, etc.), the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (road conditions, bridge strength, etc.), and upload it to the server. Users enter this information into the system, and the collected data is updated daily.

[0843] 2. Creating a disaster prediction model

[0844] The server preprocesses the collected data and formats it into a format suitable for machine learning models. It then trains a model that calculates the probability of disaster occurrence using pre-defined algorithms (e.g., random forests, neural networks). This model predicts the probability of disaster occurrence for each region.

[0845] 3. Optimizing evacuation locations

[0846] The server executes a method to optimally locate multiple evacuation sites based on the predicted probability of disaster occurrence. Evacuation sites are determined based on their capacity, safety, and accessibility. It also calculates the optimal evacuation route. This evacuation route is designed to allow residents to evacuate most efficiently and safely, taking into account road congestion information and geographical constraints.

[0847] 4. Information adjustment by emotion engine

[0848] The server analyzes the user's emotional state using an emotion engine. The emotion engine recognizes the user's emotions based on multiple factors, such as voice, facial expression, and input speed. If the user's stress level is high, the system simplifies notification information or adds encouraging messages to reduce the user's stress.

[0849] 5. Display and notification of results

[0850] The server generates a digital disaster prevention map that displays optimized information on evacuation locations and evacuation routes. This disaster prevention map is displayed on the dashboard of the device used by local government officials. It also has a notification function to quickly convey evacuation instructions and disaster information to residents. The display content and notification method of the information are adjusted according to the analysis results of the emotion engine, providing appropriate evacuation information to residents.

[0851] Examples:

[0852] For example, if a typhoon is approaching a certain municipality, the following process can be carried out using this system.

[0853] 1. The server obtains the latest typhoon data from the Japan Meteorological Agency and stores it in a database.

[0854] 2. Local government officials operating the terminals input and update local geographical information, resident information, building earthquake resistance, and evacuation shelter information into the system.

[0855] 3. The server predicts the probability of a typhoon-related disaster occurring based on the collected data.

[0856] 4. The server selects a safe evacuation location based on the prediction results and displays that information on the device.

[0857] 5. The server calculates a safe and efficient evacuation route and displays it on a map.

[0858] 6. The emotion engine analyzes the user's emotional state and displays brief evacuation information and adds encouraging messages to users with high stress levels.

[0859] 7. The person using the terminal checks the disaster prevention map, corrects the contents if necessary, and then finalizes the evacuation plan.

[0860] 8. The server will notify residents of evacuation information via SMS or email based on the confirmed evacuation plan.

[0861] This system enables local governments to issue quick and accurate evacuation instructions and ensure the safety of residents. In addition, the introduction of an emotion engine makes it possible to provide appropriate information according to the emotional state of each user, making evacuation support more effective.

[0862] The processing flow will be explained below.

[0863] Step 1:

[0864] The server automatically obtains the latest disaster data (e.g., typhoon data, flood data, earthquake data, etc.) from the Japan Meteorological Agency and seismic observation stations, and stores it in a database. This includes the process of periodically obtaining data using an API.

[0865] Step 2:

[0866] Local government officials operating the terminals input geographical information for each region (topography, river locations, population density, etc.) and upload it to the server. This involves manually entering data using a dedicated input form.

[0867] Step 3:

[0868] Local government officials operating the terminals collect data on the earthquake resistance of buildings in the area, the capacity of evacuation shelters, and the state of infrastructure (strength of roads and bridges, etc.), and enter this data into the system, again using a dedicated input form.

[0869] Step 4:

[0870] The server preprocesses the collected data, which includes imputing missing data, standardizing data, and treating outliers.

[0871] Step 5:

[0872] The server uses machine learning algorithms to predict the probability of disaster occurrence. At this stage, a model is trained based on the preprocessed data and the model is used to calculate the probability of disaster occurrence for each region.

[0873] Step 6:

[0874] The server selects safe evacuation sites based on the predicted probability of disaster occurrence, taking into account factors such as the evacuation site's capacity, safety, and physical accessibility.

[0875] Step 7:

[0876] The server calculates the optimal evacuation route from the evacuation site to the residents' residence, taking into account road congestion information and geographical constraints (e.g., obstacles such as rivers and mountains).

[0877] Step 8:

[0878] To visualize the results of the calculations, the server displays evacuation locations and routes on a map, which is digitally generated and displayed on a dashboard.

[0879] Step 9:

[0880] The emotion engine analyzes the user's emotional state and recognizes the user's emotions based on multiple factors such as the user's voice, facial expression, and input speed.

[0881] Step 10:

[0882] The server adjusts the information display and notification method according to the user's emotional state as recognized by the emotion engine. For example, a user with a high stress level will be shown simple information and an encouraging message will be added.

[0883] Step 11:

[0884] The local government official operating the device will check the displayed disaster prevention map, revise the content if necessary, and then finalize the evacuation plan.

[0885] Step 12:

[0886] The server will then send evacuation information to residents via SMS or email based on the finalized evacuation plan, including evacuation locations, evacuation routes, and other important disaster information.

[0887] Step 13:

[0888] The user promptly begins evacuation based on the evacuation information received. The user heads to the evacuation site and stays there until safety is confirmed.

[0889] Step 14:

[0890] Local government officials using the devices will monitor the evacuation status of residents in real time and issue additional evacuation orders or rescue operations as necessary. This includes collecting and displaying real-time information.

[0891] The above are the detailed processing steps of the disaster prediction and evacuation support system of the present invention. This system enables local governments to respond quickly and appropriately when a disaster occurs, ensuring the safety of residents. The introduction of an emotion engine enables the provision of appropriate information according to each user's emotional state, making evacuation support even more effective.

[0892] Example 2

[0893] 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."

[0894] In recent years, the risk of disasters due to weather changes and seismic activity has increased, making it necessary for local governments to evacuate residents quickly and accurately. However, current disaster prediction and evacuation systems provide uniform information without taking into account the emotional state of individual residents, which can lead to stress and confusion and reduce the effectiveness of evacuation. Furthermore, optimization of evacuation locations and provision of evacuation routes may not fully take into account real-time traffic information or geographical constraints. This poses a challenge in ensuring the safety of residents.

[0895] 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 predicting the probability of disaster occurrence in each area based on collected disaster data, a means for optimally arranging multiple evacuation sites based on the disaster occurrence probability, and an emotion recognition means for analyzing the emotional state of the user and adjusting the notification content. This makes it possible to quickly identify areas with a high probability of disaster occurrence, provide appropriate evacuation sites and evacuation routes, and provide information to reduce stress according to the user's emotional state.

[0896] "Disaster data" refers to information about natural disasters such as weather, earthquakes, and floods.

[0897] "Probability of disaster occurrence" is an indicator that shows the possibility of a disaster occurring in a specific area based on collected disaster data and past cases.

[0898] An "evacuation site" is a safe place designated for temporary evacuation of residents in the event of a disaster.

[0899] "Optimal location" means effectively locating evacuation shelters and evacuation routes, taking into account given conditions and constraints, such as capacity, ease of access, and safety.

[0900] "Emotion recognition" is a technology that analyzes a user's emotional state based on their voice, facial expressions, input speed, etc., and adjusts information and notifications based on the results.

[0901] "Displaying on a map" means using visual information such as digital maps to display evacuation locations and evacuation routes geographically in an easy-to-understand manner.

[0902] "Notifying" means transmitting important information or warnings from the system to the user. This notification can be done by various means such as SMS, email, or application notification.

[0903] The present invention combines a system for disaster prediction, evacuation site proposals, and shelter establishment support for local governments with an emotion engine that recognizes user emotions. This system includes multiple means for collecting disaster data, predicting the probability of disaster occurrence, optimizing evacuation sites, and displaying and notifying the results, as well as an emotion engine that recognizes user emotions and adjusts the information display content and notification method.

[0904] The server periodically obtains data on disasters, such as weather data, earthquake data, and flood data, from external information providers and stores it in a database. The server preprocesses the collected data, performs data cleaning to fill in outliers and missing values, and then generates a model that calculates the probability of disaster occurrence using machine learning algorithms (e.g., random forests and neural networks).

[0905] The terminals will be used by local government officials to collect information on each region's geographical information (topography, rivers, population density, etc.), the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (road conditions, bridge strength, etc.), and upload it to a server. The terminals will also be used to check information on evacuation locations and evacuation routes needed in the event of a disaster.

[0906] Users are responsible for inputting the location, capacity, and seismic performance data of evacuation shelters into the system and receiving notifications from the system in the event of an emergency. The system utilizes emotion recognition to analyze the user's emotional state and, if stress levels are high, provides simplified information and encouraging messages to support evacuation behavior.

[0907] For example, if a typhoon is approaching a certain municipality, this system will execute the following specific processes: The server retrieves typhoon data from the Japan Meteorological Agency API and stores it in a database. The person operating the device enters local topographical and demographic data, and the user updates evacuation shelter location and capacity data. The server inputs the collected data into a machine learning model to predict the probability of a typhoon-related disaster. The server then optimizes evacuation sites and routes, and displays them on a map using the Google Maps API. The emotion engine analyzes the user's emotions, and simplified information and encouraging messages are sent to users in a highly stressed state.

[0908] An example of a prompt sentence to be input to the generative AI model is, "Please provide a detailed explanation of the disaster prediction system for local governments, including countermeasures that combine an emotion engine."

[0909] The above is an embodiment of the present invention, showing specific methods for processing collected disaster data, predicting the probability of disaster occurrence, optimizing evacuation sites, displaying the results, and recognizing user emotions. This system enables local governments to issue evacuation instructions quickly and accurately, ensuring the safety of residents.

[0910] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0911] Step 1: Data collection

[0912] The server periodically obtains weather data (temperature, precipitation, wind speed, etc.) from the Japan Meteorological Agency via API and stores it in its own database. The input is weather data obtained from an external API. The output is that data is stored in the server's database. Specifically, the server runs a scheduled job, fetches data from the API, and performs an INSERT operation on the database.

[0913] Step 2: Enter geographic information

[0914] Local government officials using the terminals manually input geographic information for each region (topography, river locations, flood risk areas, etc.) and upload it to the server. The input is geographic information collected by the officials using GIS software such as ArcGIS. The output is that information is uploaded to the server. Specifically, the officials input the geographic information, and the terminals call an API that uploads it to the server.

[0915] Step 3: Enter shelter information

[0916] Users input information about shelters, such as their capacity, earthquake resistance, and contact information for residents, into the system. The input includes detailed shelter information provided by users. The output is stored in a database on the server. Specifically, users enter data through a web interface, which is then sent as a POST request to the server and stored in the database.

[0917] Step 4: Data Preprocessing

[0918] The server preprocesses the collected weather data, geographic information, and evacuation shelter information, and fills in outliers and missing values. The input is the collected raw data. The output is a clean and complete dataset. Specifically, the server uses Python's Pandas library to clean the data, correct outliers, and fill in missing values ​​with the mean or median.

[0919] Step 5: Disaster prediction

[0920] The server inputs the preprocessed data into a machine learning algorithm (such as a random forest or neural network) to generate a model that calculates the probability of a disaster occurring. The input is a clean dataset. The output is the probability of a disaster occurring for each region. Specifically, the server trains the model using Scikit-learn or TensorFlow and calculates the prediction results.

[0921] Step 6: Optimize evacuation locations and routes

[0922] The server calculates the optimal evacuation locations and evacuation routes based on the predicted disaster occurrence probability and local geographic information. The inputs are the disaster occurrence probability and geographic information. The output is a list of optimal evacuation locations and evacuation routes. Specifically, the server uses the Google Maps API to calculate the optimal route taking into account real-time traffic information and stores the results in a database.

[0923] Step 7: Emotion Recognition

[0924] The server uses an emotion engine to analyze the user's emotional state. The inputs include the user's voice data and facial expression data. The output is the analyzed emotional state. Specifically, the server analyzes emotions using voice recognition software (e.g., voice recognition API) and facial expression recognition software (e.g., face API), and stores the results in a list.

[0925] Step 8: View and notify results

[0926] The server creates a digital disaster prevention map that displays optimized information on evacuation locations and evacuation routes on a map and notifies residents. The input is data on evacuation locations and evacuation routes. The output is a digital map and notification content. Specifically, the server generates the map using the Google Maps API and sends information to residents via SMS or email via the notification system.

[0927] The above is a description of the specific processing steps of this system.

[0928] (Application example 2)

[0929] 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."

[0930] The main function of conventional disaster prediction systems is to predict the probability of disaster occurrence based on collected data and optimize evacuation sites and evacuation routes, but these systems do not take into account the emotional state of each user, and have the problem of not being able to provide appropriate information if the user is in a high-stress state during an emergency.In particular, in situations where users may panic during a disaster, it is necessary to display information and notifications that correspond to the user's emotional state, but there was a lack of a mechanism to achieve this.

[0931] 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.

[0932] In this invention, the server includes means for predicting the probability of disaster occurrence in each area based on multiple disaster data collected, means for optimally locating multiple evacuation sites based on the disaster occurrence probability, means for displaying the evacuation sites and evacuation routes on a map, means for notifying the user of information on the map, and emotion analysis means for analyzing the emotional state of the user based on multiple factors such as voice, facial expression, and input speed, and adjusting the display content and notification method. This makes it possible to provide appropriate information that takes the emotional state of the user into consideration when a disaster occurs.

[0933] "Disaster data" refers to any information related to disasters, such as weather data, earthquake data, and flood data.

[0934] "Probability of disaster occurrence" is a prediction of the possibility of a disaster occurring in each region based on collected disaster data.

[0935] An "evacuation site" refers to a safe place where residents can temporarily take refuge in the event of a disaster.

[0936] An "evacuation route" refers to a route or path that allows a user to reach an evacuation site safely and efficiently.

[0937] "Means of displaying on a map" refers to a method for visually showing information such as the probability of disaster occurrence, evacuation locations, and evacuation routes in map format.

[0938] "Means of notification" refers to the method for providing disaster information and evacuation instructions to users, including email, SMS, and in-app notifications.

[0939] "Emotion analysis means" refers to a method for analyzing the user's emotional state based on multiple elements such as voice, facial expression, and input speed, and adjusting the display content and notification method.

[0940] "User" refers to an individual or local government official who uses this system.

[0941] "Server" refers to a computer system for collecting, storing, and processing disaster data.

[0942] This invention combines a system that predicts disasters, suggests evacuation sites, and supports the establishment of evacuation shelters with an emotion engine that recognizes the user's emotions. This system collects disaster data, predicts the probability of disaster occurrence, optimizes evacuation sites, and displays and notifies the results. It also analyzes the user's emotional state based on multiple factors such as voice, facial expression, and input speed, and adjusts the information displayed and the notification method accordingly.

[0943] Overall system configuration

[0944] Hardware and Software

[0945] 1. Server:

[0946] The server is a computer system for collecting, storing, and processing disaster data. Specific software includes Python and machine learning libraries (e.g., scikit-learn and TensorFlow) to train and run a disaster probability prediction model.

[0947] 2. Terminal:

[0948] The terminals are computers or tablets used by local government officials to input and update data such as geographical information for each region, building information, and infrastructure status. A browser-based dashboard is displayed on the terminals.

[0949] 3. User Device:

[0950] The user device is a smartphone used by residents. An application for receiving notifications is installed on the device. This application uses hardware such as a camera (facial expression recognition), microphone (voice recognition), and touch point detection (input speed) for emotion analysis.

[0951] Processing Details

[0952] The server operates as follows:

[0953] 1. Data Collection:

[0954] The server periodically obtains the latest weather, earthquake, and flood data from external information providers such as the Japan Meteorological Agency and stores it in a database. Local government officials also use terminals to input and update geographical information for each region, the earthquake resistance of buildings, the capacity of evacuation shelters, and the status of infrastructure.

[0955] 2. Disaster prediction model:

[0956] The server preprocesses the collected data and formats it into a format suitable for machine learning models. It then uses algorithms such as random forests and neural networks to train a model that can predict the probability of a disaster occurring. This makes it possible to predict the probability of a disaster occurring in each region.

[0957] 3. Optimizing evacuation locations:

[0958] Based on the predicted probability of disaster occurrence, the server optimally allocates multiple evacuation sites, taking into consideration the safety, capacity, and accessibility of each site. It also calculates the optimal evacuation route and displays it on a map.

[0959] 4. Emotion analysis:

[0960] The server analyzes the user's emotional state based on voice, facial expression, and input data collected from the user's device. The analysis engine uses OpenCV, Google Cloud Speech-to-Text, and touch data analysis algorithms. If the user's emotional state is tense, the notification information is simplified and an encouraging message is added.

[0961] 5. Display and notification of results:

[0962] The server displays optimized evacuation locations and evacuation routes on a map, which is then displayed on the device dashboard as a digital disaster prevention map. It also notifies residents of evacuation instructions and disaster information on their smartphones, adjusting the content and display method of the notifications based on the results of emotion analysis.

[0963] Examples:

[0964] For example, if a municipality experiences prolonged heavy rain and is at risk of flooding, the system can perform the following operations:

[0965] The server obtains the latest heavy rain data from the Japan Meteorological Agency and stores it in a database.

[0966] Local government officials operating the terminals input and update local geographical information, resident information, building earthquake resistance, and evacuation shelter information into the system.

[0967] The server predicts the probability of flood disasters occurring based on the collected data.

[0968] The server selects a safe evacuation location based on the prediction results and displays that information on the device.

[0969] The server calculates safe and efficient evacuation routes and displays them on a map.

[0970] The emotion engine analyzes the user's emotional state and displays brief evacuation information and adds encouraging messages to users with high stress levels.

[0971] The person in charge using the terminal will check the disaster prevention map, revise the contents if necessary, and then finalize the evacuation plan.

[0972] Based on the confirmed evacuation plan, the server will notify residents of evacuation information via SMS or email.

[0973] Example prompt sentence:

[0974] "It suggests optimal evacuation routes based on current weather conditions and adjusts notifications based on the user's emotional state."

[0975] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0976] Step 1:

[0977] The server obtains the latest weather data, earthquake data, flood data, etc. from external information providers such as the Japan Meteorological Agency. The input is disaster data obtained from external APIs, and the output is disaster data stored on the server. Specifically, it periodically sends API requests and stores the responses in a database.

[0978] Step 2:

[0979] Local government officials operating the terminals input and update local geographic information, building seismic performance, evacuation shelter capacity, and infrastructure status for each region. The input is manual entry of local information, and the output is updated local information that is uploaded to the server. Specific operations include entering information through a browser-based dashboard and pressing the submit button to upload the data.

[0980] Step 3:

[0981] The server preprocesses the collected disaster data and area information and formats it into a format suitable for the machine learning model. The input is the collected disaster data and area information, and the output is a formatted dataset. Specific operations include filling in missing values, removing outliers, and normalizing the data.

[0982] Step 4:

[0983] The server uses the shaped dataset to train a model that predicts the probability of disaster occurrence using algorithms such as random forests and neural networks. The input is the shaped dataset, and the output is a trained model that predicts the probability of disaster occurrence. Specifically, the server inputs the training data into the algorithm and optimizes the model parameters.

[0984] Step 5:

[0985] The server uses the trained model to predict the probability of disaster occurrence for each region in real time. The input is the latest disaster data, and the output is the probability of disaster occurrence for each region. Specifically, new data is input into the model, and the prediction results are obtained and stored in the database.

[0986] Step 6:

[0987] The server selects safe evacuation sites and calculates optimal evacuation routes based on the predicted probability of disaster occurrence. The inputs are the probability of disaster occurrence, local geographic information, and infrastructure information, and the output is information on evacuation sites and evacuation routes. Specifically, the server selects evacuation sites taking into account each site's capacity, safety, and accessibility, and calculates optimal evacuation routes based on traffic information.

[0988] Step 7:

[0989] The server displays information on evacuation locations and evacuation routes on a map and generates a digital disaster prevention map. The input is information on evacuation locations and evacuation routes, and the output is a digital disaster prevention map that is displayed on the device's dashboard. Specifically, the server visually displays evacuation locations and routes by overlaying them on the map data.

[0990] Step 8:

[0991] The user device acquires voice data, facial expression data, and input data and performs emotion analysis. The input is data acquired from the user device, and the output is the analyzed emotional state of the user. Specifically, data is collected using a camera and microphone and processed by an emotion analysis engine.

[0992] Step 9:

[0993] The server adjusts the display content and notification method based on the results of emotion analysis. The input is the analyzed emotional state and evacuation information, and the output is the adjusted notification information. Specifically, for users with high stress, the system simplifies the information and adds an encouraging message.

[0994] Step 10:

[0995] The server notifies residents of evacuation information via SMS or email based on the finalized evacuation plan. The input is the final evacuation plan, and the output is the notification sent to residents. Specifically, the server generates disaster information and evacuation instructions in text format and sends them using the communication system.

[0996] Example prompt sentence:

[0997] "It suggests optimal evacuation routes based on current weather conditions and adjusts notifications based on the user's emotional state."

[0998] 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.

[0999] 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.

[1000] 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.

[1001] [Fourth embodiment]

[1002] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1003] 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.

[1004] 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).

[1005] 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.

[1006] 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.

[1007] 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).

[1008] 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.

[1009] 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.

[1010] 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.

[1011] 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.

[1012] 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.

[1013] 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.

[1014] 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."

[1015] The present invention is a system for disaster prediction for local governments, which supports the proposal of evacuation sites and the establishment of evacuation shelters. This system includes multiple means for collecting disaster data, predicting the probability of disaster occurrence, optimizing evacuation sites, and displaying and notifying the results.

[1016] 1. Data Collection

[1017] The server periodically obtains disaster-related data such as weather data, earthquake data, and flood data from external information providers (e.g., the Japan Meteorological Agency) and stores it in a database. The terminals are used by local government officials to collect information on the geographical information of each region (topography, rivers, population density, etc.), the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (road conditions, bridge strength, etc.), and upload it to the server. Users enter this information into the system, and the collected data is updated daily.

[1018] 2. Creating a disaster prediction model

[1019] The server preprocesses the collected data and formats it into a format suitable for machine learning models. It then trains a model that calculates the probability of disaster occurrence using pre-defined algorithms (e.g., random forests, neural networks). This model predicts the probability of disaster occurrence for each region.

[1020] 3. Optimizing evacuation locations

[1021] The server executes a method to optimally locate multiple evacuation sites based on the predicted probability of disaster occurrence. Evacuation sites are determined based on their capacity, safety, and accessibility. It also calculates the optimal evacuation route. This evacuation route is designed to allow residents to evacuate most efficiently and safely, taking into account road congestion information and geographical constraints.

[1022] 4. Display and notification of results

[1023] The server generates a digital disaster prevention map that displays optimized evacuation locations and evacuation routes on a map. This disaster prevention map is displayed on the dashboard of the device used by local government officials. The system is also equipped with a notification function to quickly communicate evacuation instructions and disaster information to residents. This allows the device to deliver necessary information to residents via SMS and email.

[1024] Examples:

[1025] For example, if a typhoon is approaching a certain municipality, the following process can be carried out using this system.

[1026] 1. The server obtains the latest typhoon data from the Japan Meteorological Agency and stores it in a database.

[1027] 2. Local government officials operating the terminals input and update local geographical information, resident information, building earthquake resistance, and evacuation shelter information into the system.

[1028] 3. The server predicts the probability of a typhoon-related disaster occurring based on the collected data.

[1029] 4. The server selects a safe evacuation location based on the prediction results and displays that information on the device.

[1030] 5. The server calculates a safe and efficient evacuation route and displays it on a map.

[1031] 6. The person using the terminal checks the disaster prevention map, makes any necessary corrections, and then issues the final evacuation instructions.

[1032] 7. The server notifies residents of evacuation information via SMS or email.

[1033] This system will enable local governments to issue quick and accurate evacuation instructions to ensure the safety of residents.

[1034] The processing flow will be explained below.

[1035] Step 1:

[1036] The server automatically obtains the latest disaster data (e.g., typhoon data, flood data, earthquake data, etc.) from the Japan Meteorological Agency and seismic observation stations, and stores it in a database. This includes the process of periodically obtaining data using an API.

[1037] Step 2:

[1038] Local government officials operating the terminals input geographical information for each region (topography, river locations, population density, etc.) and upload it to the server. This involves manually entering data using a dedicated input form.

[1039] Step 3:

[1040] Local government officials operating the terminals collect data on the earthquake resistance of buildings in the area, the capacity of evacuation shelters, and the state of infrastructure (strength of roads and bridges, etc.), and enter this data into the system, again using a dedicated input form.

[1041] Step 4:

[1042] The server preprocesses the collected data, which includes imputing missing data, standardizing data, and treating outliers.

[1043] Step 5:

[1044] The server uses machine learning algorithms to predict the probability of disaster occurrence. At this stage, a model is trained based on the preprocessed data and the model is used to calculate the probability of disaster occurrence for each region.

[1045] Step 6:

[1046] The server selects safe evacuation sites based on the predicted probability of disaster occurrence, taking into account factors such as the shelter's capacity, safety, and ease of physical access.

[1047] Step 7:

[1048] The server calculates the optimal evacuation route from the evacuation site to the residents' residence, taking into account road congestion information and geographical constraints (e.g., obstacles such as rivers and mountains).

[1049] Step 8:

[1050] To visualize the results of the calculations, the server displays evacuation locations and routes on a map, which is digitally generated and displayed on a dashboard.

[1051] Step 9:

[1052] The local government official operating the device checks the displayed disaster prevention map and, if necessary, modifies and confirms the contents. Once the modifications are complete, the final evacuation plan is confirmed.

[1053] Step 10:

[1054] The server will then send evacuation information to residents via SMS or email based on the finalized evacuation plan, including evacuation locations, evacuation routes, and other important disaster information.

[1055] Step 11:

[1056] The user promptly begins evacuation based on the evacuation information received. The user heads to the evacuation site and stays there until safety is confirmed.

[1057] Step 12:

[1058] Local government officials using the devices will monitor the evacuation status of residents in real time and issue additional evacuation orders or rescue operations as necessary. This includes collecting and displaying real-time information.

[1059] The above are the detailed processing steps of the disaster prediction and evacuation support system of the present invention. This system enables local governments to respond quickly and appropriately when a disaster occurs, thereby ensuring the safety of residents.

[1060] Example 1

[1061] 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."

[1062] In modern society, disasters are difficult to predict, and selecting evacuation sites and ensuring efficient evacuation routes are major challenges, especially for local governments. Furthermore, if it is not possible to properly predict the probability of disaster occurrence or locate optimal evacuation sites, it becomes difficult to ensure the safety of residents. To address this situation, a system is needed that can accurately predict the probability of disaster occurrence, optimally locate evacuation sites, and quickly notify residents.

[1063] 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.

[1064] In this invention, the server includes means for predicting the probability of disaster occurrence in each region based on multiple disaster-related data collected, means for optimally locating multiple evacuation sites based on the disaster occurrence probability, means for displaying the evacuation sites and evacuation routes on a map, means for notifying users of the information on the map, means for formatting the collected data into a format suitable for a machine learning model, means for calculating the disaster occurrence probability using the machine learning model, and means for calculating evacuation routes taking into account the status of infrastructure. This enables accurate prediction of the disaster occurrence probability, optimal location of evacuation sites, efficient calculation of evacuation routes, and rapid information notification.

[1065] "Disaster-related data" refers to weather data, earthquake data, flood data and other disaster-related information.

[1066] "Means for predicting the probability of disaster occurrence" refers to algorithms and tools that calculate and predict the possibility of disasters occurring in each region based on collected disaster-related data.

[1067] "Methods for optimally locating evacuation shelters" refers to algorithms and methods for safely and efficiently locating evacuation shelters based on collected data and the predicted probability of disaster occurrence.

[1068] "Means for displaying on a map" refers to a graphical interface or digital map that visually displays calculated evacuation locations and evacuation routes.

[1069] "Means of notifying users of information" refers to the function of quickly conveying important evacuation and disaster information to users using communication methods such as SMS and email.

[1070] "Means of formatting data suitable for machine learning models" refers to procedures and methods for converting collected disaster-related data into a format that can be processed by machine learning algorithms.

[1071] "Means for calculating the probability of disaster occurrence" refers to models and algorithms that use data science techniques to calculate the probability of a disaster occurring.

[1072] "Means for calculating evacuation routes taking into account infrastructure conditions" refers to algorithms and tools for calculating safe and quick evacuation routes based on road congestion information and geographical constraints.

[1073] The present invention provides a disaster prediction system for local governments, and supports them in proposing evacuation sites and opening evacuation shelters. Detailed embodiments for carrying out the present invention will be described below.

[1074] This system involves a series of processing steps performed by a server, terminals, and users, including data collection, data processing, disaster prediction, evacuation site optimization, and result display and notification.

[1075] 1. Hardware and Software Used

[1076] The servers use cloud computing services (e.g., Amazon Web Services and Google Cloud Platform) to handle large amounts of data, and the database uses a database management system that supports SQL and NoSQL formats.

[1077] The terminals are devices such as computers and tablets used by local government officials, and they access the dashboard via a browser. The system is designed as a web application, and the front end uses JavaScript frameworks such as React and Vue.js.

[1078] Users are local government officials and residents who access the system through terminals and input or receive the necessary information. The user interface is designed to be intuitive and easy to operate.

[1079] 2. Data Collection and Processing

[1080] The server periodically obtains weather data, earthquake data, flood data, and other data from external information providers such as the Japan Meteorological Agency via API and stores it in a database, which is updated in real time.

[1081] Local government officials operating the terminals input detailed information such as the area's geographical location, the earthquake resistance of buildings, the capacity of evacuation shelters, the condition of roads and bridges, etc. The collected data is then instantly uploaded to a server.

[1082] The server preprocesses the collected data and formats it into a format suitable for machine learning models, such as converting text data into numerical data and imputing missing values.

[1083] 3. Disaster Prediction Using Machine Learning

[1084] The server uses the preprocessed data to train machine learning models, including algorithms such as random forests and neural networks (e.g., TensorFlow and PyTorch), which predict the probability of disasters occurring in each region.

[1085] 4. Optimization and display of evacuation locations

[1086] The server then executes a method to optimally locate evacuation sites based on the predicted probability of disaster occurrence. It also calculates optimal evacuation routes, taking into account infrastructure conditions (road congestion and geographical constraints). This allows the most efficient and safe evacuation route for residents to be designed.

[1087] The generated evacuation location and route information is compiled into a digital disaster prevention map and displayed on a dashboard on the device, allowing local government officials to intuitively check the information and make corrections if necessary.

[1088] 5. Notification of Results

[1089] The server notifies residents of the final evacuation location and evacuation route via SMS or email, enabling quick and accurate information transmission in the event of a disaster.

[1090] Specific examples

[1091] For example, if a typhoon is approaching, the following process will be executed:

[1092] 1. The server retrieves the latest typhoon data from the Japan Meteorological Agency's API and stores it in a database.

[1093] 2. Local government officials operate the terminals to input and update information such as local geographical information, resident information, building earthquake resistance, and evacuation shelter information.

[1094] 3. The server preprocesses the collected data and trains the disaster prediction model.

[1095] 4. The server uses the trained model to predict the probability of typhoon disasters.

[1096] 5. The server calculates the optimal evacuation location and evacuation route, and generates a digital disaster prevention map.

[1097] 6. Local government officials check the disaster prevention map on the terminal, make any necessary corrections, and issue final evacuation instructions.

[1098] 7. The server notifies residents of evacuation information via SMS or email.

[1099] Prompt Sentence Examples

[1100] "Use this system to select the best evacuation location for an approaching typhoon and calculate an efficient evacuation route."

[1101] The above describes a specific embodiment of the present invention. By implementing the invention in accordance with this embodiment, it is possible to accurately predict the probability of a disaster occurring, optimally locate evacuation sites, calculate efficient evacuation routes, and quickly notify users of the information.

[1102] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1103] Step 1: Data collection

[1104] The server periodically retrieves disaster-related data such as weather data, earthquake data, and flood data from external information providers (e.g., the Japan Meteorological Agency) through APIs and stores it in a database. This input data includes the latest weather information, earthquake occurrence status, river water level data, etc. In the process of retrieving this data, the server sends requests and parses and stores the data received as a response. As an output, a consistent storage of disaster-related data is formed in the database.

[1105] Step 2: Enter region data

[1106] Local government officials operating the terminals use a dedicated input form to input local geographic information (e.g., topography, rivers, population density, etc.), the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (e.g., road conditions, bridge strength, etc.). The input data covers detailed information about the area and the current state of infrastructure. The input information is uploaded to a server in real time and stored in a database. As a result, a rich dataset specific to the area is created.

[1107] Step 3: Preprocessing the data

[1108] The server preprocesses the collected disaster-related and local data. The input data undergoes processes such as missing value imputation, data normalization, and encoding of categorical variables. For example, it converts text data to numerical data and handles outliers. The output is a consistent dataset in a format suitable for machine learning models.

[1109] Step 4: Train the machine learning model

[1110] The server uses the preprocessed dataset to train a machine learning model. Algorithms used include random forests and neural networks (e.g., TensorFlow, PyTorch). The input data includes past disaster data and regional characteristics. The model can predict the probability of disaster occurrence for each region. The output is a trained disaster prediction model.

[1111] Step 5: Predict the probability of disaster occurrence

[1112] The server uses a trained machine learning model to predict the probability of disasters occurring in each region, taking the latest collected data as input. The input data includes current weather data and local information. The output is a predicted probability of disaster occurrence for each region, which is then stored in a database.

[1113] Step 6: Optimize evacuation locations

[1114] The server runs a mathematical optimization algorithm to optimally locate multiple evacuation sites based on the predicted probability of disaster occurrence. Input data includes the predicted probability of disaster occurrence, the capacity of the evacuation site, safety, accessibility, etc. The output is the calculation of the optimal evacuation site and evacuation route.

[1115] Step 7: Creating a digital disaster prevention map

[1116] The server generates a digital disaster prevention map based on the optimized evacuation location and evacuation route information. This digital disaster prevention map is designed to be easily referenced in the event of a disaster. The input data includes information on evacuation locations and routes. The output is a visually easy-to-understand map display.

[1117] Step 8: View the dashboard

[1118] Local government officials using the terminals can check the generated digital disaster prevention map on a dedicated dashboard. The input includes the generated disaster prevention map information. The output is the disaster prevention map displayed on the terminal screen.

[1119] Step 9: Notifications

[1120] The server notifies residents of optimized evacuation locations and routes via SMS and email. This process is done quickly, before a disaster occurs. Input data includes evacuation information and residents' contact information. The output is evacuation information sent to residents via SMS and email.

[1121] (Application example 1)

[1122] 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."

[1123] Conventional disaster prediction and evacuation systems often fail to predict the probability of disaster occurrence and suggest evacuation locations in sufficient real time, or provide insufficient optimal evacuation routes based on the user's location information. Furthermore, they lack a means to utilize generative AI models to instantly predict the probability of disaster occurrence and effectively notify users. This creates challenges in ensuring the safety of residents by preventing rapid and accurate evacuation in the event of a disaster.

[1124] 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.

[1125] In this invention, the server includes means for predicting the probability of disaster occurrence in each region based on multiple disaster data collected, means for optimally locating multiple evacuation sites based on the disaster occurrence probability, means for displaying the evacuation sites and evacuation routes on a map, means for notifying the user of the information on the map, means for calculating the disaster occurrence probability and evacuation site information in real time and proposing optimal evacuation sites and evacuation routes based on the user's location information, and means for receiving and notifying the disaster prediction results using a generative AI model in response to input of a prompt sentence. This makes it possible to provide the user with optimal evacuation information in real time and support rapid and accurate evacuation.

[1126] "Probability of disaster occurrence" is a probability value that represents the possibility of a disaster occurring in a specific area based on collected disaster data.

[1127] An "evacuation site" is a designated location for residents to evacuate safely in the event of a disaster.

[1128] An "evacuation route" is a route that allows residents to safely travel to an evacuation site.

[1129] "Means for displaying on a map" refers to the technology and methods for visually displaying evacuation locations and evacuation routes on a map.

[1130] The "means for notifying the user" is a method for promptly notifying the user of evacuation information.

[1131] "Real-time calculation" means that calculations are made instantly based on the current situation.

[1132] "User location information" is geographic information about the location where the user is currently located.

[1133] "Using a generative AI model" means using a model that uses artificial intelligence to make predictions and perform data analysis.

[1134] A "prompt" refers to an instruction or question that is input into a generative AI model.

[1135] "Disaster prediction results" are the predicted results of the probability and circumstances of disaster occurrence calculated by the generative AI model.

[1136] This invention is a system for predicting the probability of disaster occurrence in real time and proposing optimal evacuation sites and evacuation routes. This system includes multiple means for collecting disaster data, predicting the probability of disaster occurrence, optimizing evacuation sites, and displaying and notifying the results. This allows for rapid and accurate evacuation support in the event of a disaster.

[1137] The server periodically obtains disaster-related data, such as weather data, earthquake data, and flood data, from external information providers and stores it in a database. This data is used as training data for a model to predict the probability of disaster occurrence. The collected data is then preprocessed and formatted into a format suitable for the machine learning model. The machine learning model uses algorithms such as random forests and neural networks. This model calculates the probability of disaster occurrence and predicts the probability of disaster occurrence for each region.

[1138] The server also generates optimal evacuation locations and routes based on the predicted probability of disaster. Evacuation locations are determined based on their capacity, safety, and accessibility. Evacuation routes are designed to allow users to evacuate most efficiently and safely, taking into account road congestion information and geographical constraints.

[1139] The devices are used by local government officials to collect information on the area's geographical location, the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (road conditions and bridge strength), and upload it to a server. They also display real-time disaster information and evacuation instructions and notify residents. The device's dashboard displays optimized evacuation locations and evacuation routes on a map. Necessary information is also quickly delivered to residents via SMS and email.

[1140] Using a mobile device such as a smartphone, users can receive real-time information on optimal evacuation locations and routes based on their location. By entering a prompt, the user receives disaster prediction results from a generative AI model and obtains appropriate evacuation instructions in real time.

[1141] As a concrete example, if a typhoon is approaching a certain area, the system operates as follows: The server acquires weather data and predicts the probability of a typhoon-related disaster occurring. Based on the collected local information, it proposes optimal evacuation locations and calculates evacuation routes, displaying them on a map. The device displays the disaster prevention map to local government officials, who then issue evacuation instructions, and the server notifies residents via SMS or email. At this time, the user can obtain the disaster prediction results and evacuation information using the following prompt text:

[1142] Example prompt sentence:

[1143] "Use the latest weather data to predict the probability of a disaster occurring near my current location, suggest the safest evacuation location and evacuation route, and notify me of evacuation instructions in real time if necessary."

[1144] This system allows users to quickly and accurately obtain evacuation information and ensure their safety.

[1145] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1146] Step 1:

[1147] The server periodically obtains disaster-related information such as weather data, earthquake data, and flood data from external information providers (e.g., the Japan Meteorological Agency) and stores it in a database. The input is data obtained from external information providers, and the output is data stored in the server's database. This ensures that the latest disaster information is always available.

[1148] Step 2:

[1149] The terminal collects information from local government officials about the geographical information for each region (topography, rivers, population density, etc.), the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (road conditions, bridge strength, etc.), and uploads it to a server. The input is the regional information entered by the local government officials, and the output is the regional information uploaded to the server. This allows detailed data for each region to be collected.

[1150] Step 3:

[1151] The server preprocesses the collected disaster data and local information and formats it into a format suitable for machine learning models. The input is the collected raw data, and the output is the preprocessed data. Preprocessing such as data cleaning and normalization is performed to create data suitable for model training.

[1152] Step 4:

[1153] The server uses a machine learning model to predict the probability of a disaster occurring. The input is preprocessed data, and the output is the predicted probability of a disaster occurring. Specifically, the prediction is made by applying algorithms such as random forests and neural networks.

[1154] Step 5:

[1155] The server calculates the optimal evacuation site and evacuation route based on the predicted probability of disaster occurrence. The input is the predicted probability of disaster occurrence and collected local information, and the output is the optimal evacuation site and evacuation route. The optimal route is calculated taking into account the capacity, safety, and accessibility of the evacuation site.

[1156] Step 6:

[1157] The terminal displays the optimal evacuation locations and evacuation routes received from the server on a map and generates a disaster prevention map. The input is evacuation information from the server, and the output is a disaster prevention map displayed on a map. This makes it easier for local government officials to understand the current situation.

[1158] Step 7:

[1159] The server notifies residents of evacuation instructions and disaster information via SMS and email. The input is the generated evacuation instructions, and the output is the notification sent to residents, allowing residents to take evacuation action quickly.

[1160] Step 8:

[1161] The user inputs a prompt using a smartphone, receives the disaster prediction results from the generative AI model, and obtains evacuation information in real time. The input is the prompt and the user's location information, and the output is the disaster prediction results from the generative AI model. The following example prompt can be used:

[1162] Example prompt sentence:

[1163] "Use the latest weather data to predict the probability of a disaster occurring near my current location, suggest the safest evacuation location and evacuation route, and notify me of evacuation instructions in real time if necessary."

[1164] Through the above processing steps, this system can provide users with optimal evacuation information in real time, supporting quick and accurate evacuation.

[1165] 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.

[1166] The present invention combines a system for disaster prediction, evacuation site proposals, and shelter establishment support for local governments with an emotion engine that recognizes user emotions. This system includes multiple means for collecting disaster data, predicting the probability of disaster occurrence, optimizing evacuation sites, and displaying and notifying the results, as well as an emotion engine that recognizes user emotions and adjusts the information display content and notification method.

[1167] 1. Data Collection

[1168] The server periodically obtains disaster-related data such as weather data, earthquake data, and flood data from external information providers (e.g., the Japan Meteorological Agency) and stores it in a database. The terminals are used by local government officials to collect information on the geographical information of each region (topography, rivers, population density, etc.), the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (road conditions, bridge strength, etc.), and upload it to the server. Users enter this information into the system, and the collected data is updated daily.

[1169] 2. Creating a disaster prediction model

[1170] The server preprocesses the collected data and formats it into a format suitable for machine learning models. It then trains a model that calculates the probability of disaster occurrence using pre-defined algorithms (e.g., random forests, neural networks). This model predicts the probability of disaster occurrence for each region.

[1171] 3. Optimizing evacuation locations

[1172] The server executes a method to optimally locate multiple evacuation sites based on the predicted probability of disaster occurrence. Evacuation sites are determined based on their capacity, safety, and accessibility. It also calculates the optimal evacuation route. This evacuation route is designed to allow residents to evacuate most efficiently and safely, taking into account road congestion information and geographical constraints.

[1173] 4. Information adjustment by emotion engine

[1174] The server analyzes the user's emotional state using an emotion engine. The emotion engine recognizes the user's emotions based on multiple factors, such as voice, facial expression, and input speed. If the user's stress level is high, the system simplifies notification information or adds encouraging messages to reduce the user's stress.

[1175] 5. Display and notification of results

[1176] The server generates a digital disaster prevention map that displays optimized information on evacuation locations and evacuation routes. This disaster prevention map is displayed on the dashboard of the device used by local government officials. It also has a notification function to quickly convey evacuation instructions and disaster information to residents. The display content and notification method of the information are adjusted according to the analysis results of the emotion engine, providing appropriate evacuation information to residents.

[1177] Examples:

[1178] For example, if a typhoon is approaching a certain municipality, the following process can be carried out using this system.

[1179] 1. The server obtains the latest typhoon data from the Japan Meteorological Agency and stores it in a database.

[1180] 2. Local government officials operating the terminals input and update local geographical information, resident information, building earthquake resistance, and evacuation shelter information into the system.

[1181] 3. The server predicts the probability of a typhoon-related disaster occurring based on the collected data.

[1182] 4. The server selects a safe evacuation location based on the prediction results and displays that information on the device.

[1183] 5. The server calculates a safe and efficient evacuation route and displays it on a map.

[1184] 6. The emotion engine analyzes the user's emotional state and displays brief evacuation information and adds encouraging messages to users with high stress levels.

[1185] 7. The person using the terminal checks the disaster prevention map, corrects the contents if necessary, and then finalizes the evacuation plan.

[1186] 8. The server will notify residents of evacuation information via SMS or email based on the confirmed evacuation plan.

[1187] This system enables local governments to issue quick and accurate evacuation instructions and ensure the safety of residents. In addition, the introduction of an emotion engine makes it possible to provide appropriate information according to the emotional state of each user, making evacuation support more effective.

[1188] The processing flow will be explained below.

[1189] Step 1:

[1190] The server automatically obtains the latest disaster data (e.g., typhoon data, flood data, earthquake data, etc.) from the Japan Meteorological Agency and seismic observation stations, and stores it in a database. This includes the process of periodically obtaining data using an API.

[1191] Step 2:

[1192] Local government officials operating the terminals input geographical information for each region (topography, river locations, population density, etc.) and upload it to the server. This involves manually entering data using a dedicated input form.

[1193] Step 3:

[1194] Local government officials operating the terminals collect data on the earthquake resistance of buildings in the area, the capacity of evacuation shelters, and the state of infrastructure (strength of roads and bridges, etc.), and enter this data into the system, again using a dedicated input form.

[1195] Step 4:

[1196] The server preprocesses the collected data, which includes imputing missing data, standardizing data, and treating outliers.

[1197] Step 5:

[1198] The server uses machine learning algorithms to predict the probability of disaster occurrence. At this stage, a model is trained based on the preprocessed data and the model is used to calculate the probability of disaster occurrence for each region.

[1199] Step 6:

[1200] The server selects safe evacuation sites based on the predicted probability of disaster occurrence, taking into account factors such as the evacuation site's capacity, safety, and physical accessibility.

[1201] Step 7:

[1202] The server calculates the optimal evacuation route from the evacuation site to the residents' residence, taking into account road congestion information and geographical constraints (e.g., obstacles such as rivers and mountains).

[1203] Step 8:

[1204] To visualize the results of the calculations, the server displays evacuation locations and routes on a map, which is digitally generated and displayed on a dashboard.

[1205] Step 9:

[1206] The emotion engine analyzes the user's emotional state and recognizes the user's emotions based on multiple factors such as the user's voice, facial expression, and input speed.

[1207] Step 10:

[1208] The server adjusts the information display and notification method according to the user's emotional state as recognized by the emotion engine. For example, a user with a high stress level will be shown simple information and an encouraging message will be added.

[1209] Step 11:

[1210] The local government official operating the device will check the displayed disaster prevention map, revise the content if necessary, and then finalize the evacuation plan.

[1211] Step 12:

[1212] The server will then send evacuation information to residents via SMS or email based on the finalized evacuation plan, including evacuation locations, evacuation routes, and other important disaster information.

[1213] Step 13:

[1214] The user promptly begins evacuation based on the evacuation information received. The user heads to the evacuation site and stays there until safety is confirmed.

[1215] Step 14:

[1216] Local government officials using the devices will monitor the evacuation status of residents in real time and issue additional evacuation orders or rescue operations as necessary. This includes collecting and displaying real-time information.

[1217] The above are the detailed processing steps of the disaster prediction and evacuation support system of the present invention. This system enables local governments to respond quickly and appropriately when a disaster occurs, ensuring the safety of residents. The introduction of an emotion engine enables the provision of appropriate information according to each user's emotional state, making evacuation support even more effective.

[1218] Example 2

[1219] 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."

[1220] In recent years, the risk of disasters due to weather changes and seismic activity has increased, making it necessary for local governments to evacuate residents quickly and accurately. However, current disaster prediction and evacuation systems provide uniform information without taking into account the emotional state of individual residents, which can lead to stress and confusion and reduce the effectiveness of evacuation. Furthermore, optimization of evacuation locations and provision of evacuation routes may not fully take into account real-time traffic information or geographical constraints. This poses a challenge in ensuring the safety of residents.

[1221] 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 predicting the probability of disaster occurrence in each area based on collected disaster data, a means for optimally arranging multiple evacuation sites based on the disaster occurrence probability, and an emotion recognition means for analyzing the emotional state of the user and adjusting the notification content. This makes it possible to quickly identify areas with a high probability of disaster occurrence, provide appropriate evacuation sites and evacuation routes, and provide information to reduce stress according to the user's emotional state.

[1222] "Disaster data" refers to information about natural disasters such as weather, earthquakes, and floods.

[1223] "Probability of disaster occurrence" is an indicator that shows the possibility of a disaster occurring in a specific area based on collected disaster data and past cases.

[1224] An "evacuation site" is a safe place designated for temporary evacuation of residents in the event of a disaster.

[1225] "Optimal location" means effectively locating evacuation shelters and evacuation routes, taking into account given conditions and constraints, such as capacity, ease of access, and safety.

[1226] "Emotion recognition" is a technology that analyzes a user's emotional state based on their voice, facial expressions, input speed, etc., and adjusts information and notifications based on the results.

[1227] "Displaying on a map" means using visual information such as digital maps to display evacuation locations and evacuation routes geographically in an easy-to-understand manner.

[1228] "Notifying" means transmitting important information or warnings from the system to the user. This notification can be done by various means such as SMS, email, or application notification.

[1229] The present invention combines a system for disaster prediction, evacuation site proposals, and shelter establishment support for local governments with an emotion engine that recognizes user emotions. This system includes multiple means for collecting disaster data, predicting the probability of disaster occurrence, optimizing evacuation sites, and displaying and notifying the results, as well as an emotion engine that recognizes user emotions and adjusts the information display content and notification method.

[1230] The server periodically obtains data on disasters, such as weather data, earthquake data, and flood data, from external information providers and stores it in a database. The server preprocesses the collected data, performs data cleaning to fill in outliers and missing values, and then generates a model that calculates the probability of disaster occurrence using machine learning algorithms (e.g., random forests and neural networks).

[1231] The terminals will be used by local government officials to collect information on each region's geographical information (topography, rivers, population density, etc.), the earthquake resistance of buildings, the capacity of evacuation shelters, and the state of infrastructure (road conditions, bridge strength, etc.), and upload it to a server. The terminals will also be used to check information on evacuation locations and evacuation routes needed in the event of a disaster.

[1232] Users are responsible for inputting the location, capacity, and seismic performance data of evacuation shelters into the system and receiving notifications from the system in the event of an emergency. The system utilizes emotion recognition to analyze the user's emotional state and, if stress levels are high, provides simplified information and encouraging messages to support evacuation behavior.

[1233] For example, if a typhoon is approaching a certain municipality, this system will execute the following specific processes: The server retrieves typhoon data from the Japan Meteorological Agency API and stores it in a database. The person operating the device enters local topographical and demographic data, and the user updates evacuation shelter location and capacity data. The server inputs the collected data into a machine learning model to predict the probability of a typhoon-related disaster. The server then optimizes evacuation sites and routes, and displays them on a map using the Google Maps API. The emotion engine analyzes the user's emotions, and simplified information and encouraging messages are sent to users in a highly stressed state.

[1234] An example of a prompt sentence to be input to the generative AI model is, "Please provide a detailed explanation of the disaster prediction system for local governments, including countermeasures that combine an emotion engine."

[1235] The above is an embodiment of the present invention, showing specific methods for processing collected disaster data, predicting the probability of disaster occurrence, optimizing evacuation sites, displaying the results, and recognizing user emotions. This system enables local governments to issue evacuation instructions quickly and accurately, ensuring the safety of residents.

[1236] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1237] Step 1: Data collection

[1238] The server periodically obtains weather data (temperature, precipitation, wind speed, etc.) from the Japan Meteorological Agency via API and stores it in its own database. The input is weather data obtained from an external API. The output is that data is stored in the server's database. Specifically, the server runs a scheduled job, fetches data from the API, and performs an INSERT operation on the database.

[1239] Step 2: Enter geographic information

[1240] Local government officials using the terminals manually input geographic information for each region (topography, river locations, flood risk areas, etc.) and upload it to the server. The input is geographic information collected by the officials using GIS software such as ArcGIS. The output is that information is uploaded to the server. Specifically, the officials input the geographic information, and the terminals call an API that uploads it to the server.

[1241] Step 3: Enter shelter information

[1242] Users input information about shelters, such as their capacity, earthquake resistance, and contact information for residents, into the system. The input includes detailed shelter information provided by users. The output is stored in a database on the server. Specifically, users enter data through a web interface, which is then sent as a POST request to the server and stored in the database.

[1243] Step 4: Data Preprocessing

[1244] The server preprocesses the collected weather data, geographic information, and evacuation shelter information, and fills in outliers and missing values. The input is the collected raw data. The output is a clean and complete dataset. Specifically, the server uses Python's Pandas library to clean the data, correct outliers, and fill in missing values ​​with the mean or median.

[1245] Step 5: Disaster prediction

[1246] The server inputs the preprocessed data into a machine learning algorithm (such as a random forest or neural network) to generate a model that calculates the probability of a disaster occurring. The input is a clean dataset. The output is the probability of a disaster occurring for each region. Specifically, the server trains the model using Scikit-learn or TensorFlow and calculates the prediction results.

[1247] Step 6: Optimize evacuation locations and routes

[1248] The server calculates the optimal evacuation locations and evacuation routes based on the predicted disaster occurrence probability and local geographic information. The inputs are the disaster occurrence probability and geographic information. The output is a list of optimal evacuation locations and evacuation routes. Specifically, the server uses the Google Maps API to calculate the optimal route taking into account real-time traffic information and stores the results in a database.

[1249] Step 7: Emotion Recognition

[1250] The server uses an emotion engine to analyze the user's emotional state. The inputs include the user's voice data and facial expression data. The output is the analyzed emotional state. Specifically, the server analyzes emotions using voice recognition software (e.g., voice recognition API) and facial expression recognition software (e.g., face API), and stores the results in a list.

[1251] Step 8: View and notify results

[1252] The server creates a digital disaster prevention map that displays optimized information on evacuation locations and evacuation routes on a map and notifies residents. The input is data on evacuation locations and evacuation routes. The output is a digital map and notification content. Specifically, the server generates the map using the Google Maps API and sends information to residents via SMS or email via the notification system.

[1253] The above is a description of the specific processing steps of this system.

[1254] (Application example 2)

[1255] 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."

[1256] The main function of conventional disaster prediction systems is to predict the probability of disaster occurrence based on collected data and optimize evacuation sites and evacuation routes, but these systems do not take into account the emotional state of each user, and have the problem of not being able to provide appropriate information if the user is in a high-stress state during an emergency.In particular, in situations where users may panic during a disaster, it is necessary to display information and notifications that correspond to the user's emotional state, but there was a lack of a mechanism to achieve this.

[1257] 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.

[1258] In this invention, the server includes means for predicting the probability of disaster occurrence in each area based on multiple disaster data collected, means for optimally locating multiple evacuation sites based on the disaster occurrence probability, means for displaying the evacuation sites and evacuation routes on a map, means for notifying the user of information on the map, and emotion analysis means for analyzing the emotional state of the user based on multiple factors such as voice, facial expression, and input speed, and adjusting the display content and notification method. This makes it possible to provide appropriate information that takes the emotional state of the user into consideration when a disaster occurs.

[1259] "Disaster data" refers to any information related to disasters, such as weather data, earthquake data, and flood data.

[1260] "Probability of disaster occurrence" is a prediction of the possibility of a disaster occurring in each region based on collected disaster data.

[1261] An "evacuation site" refers to a safe place where residents can temporarily take refuge in the event of a disaster.

[1262] An "evacuation route" refers to a route or path that allows a user to reach an evacuation site safely and efficiently.

[1263] "Means of displaying on a map" refers to a method for visually showing information such as the probability of disaster occurrence, evacuation locations, and evacuation routes in map format.

[1264] "Means of notification" refers to the method for providing disaster information and evacuation instructions to users, including email, SMS, and in-app notifications.

[1265] "Emotion analysis means" refers to a method for analyzing the user's emotional state based on multiple elements such as voice, facial expression, and input speed, and adjusting the display content and notification method.

[1266] "User" refers to an individual or local government official who uses this system.

[1267] "Server" refers to a computer system for collecting, storing, and processing disaster data.

[1268] This invention combines a system that predicts disasters, suggests evacuation sites, and supports the establishment of evacuation shelters with an emotion engine that recognizes the user's emotions. This system collects disaster data, predicts the probability of disaster occurrence, optimizes evacuation sites, and displays and notifies the results. It also analyzes the user's emotional state based on multiple factors such as voice, facial expression, and input speed, and adjusts the information displayed and the notification method accordingly.

[1269] Overall system configuration

[1270] Hardware and Software

[1271] 1. Server:

[1272] The server is a computer system for collecting, storing, and processing disaster data. Specific software includes Python and machine learning libraries (e.g., scikit-learn and TensorFlow) to train and run a disaster probability prediction model.

[1273] 2. Terminal:

[1274] The terminals are computers or tablets used by local government officials to input and update data such as geographical information for each region, building information, and infrastructure status. A browser-based dashboard is displayed on the terminals.

[1275] 3. User Device:

[1276] The user device is a smartphone used by residents. An application for receiving notifications is installed on the device. This application uses hardware such as a camera (facial expression recognition), microphone (voice recognition), and touch point detection (input speed) for emotion analysis.

[1277] Processing Details

[1278] The server operates as follows:

[1279] 1. Data Collection:

[1280] The server periodically obtains the latest weather, earthquake, and flood data from external information providers such as the Japan Meteorological Agency and stores it in a database. Local government officials also use terminals to input and update geographical information for each region, the earthquake resistance of buildings, the capacity of evacuation shelters, and the status of infrastructure.

[1281] 2. Disaster prediction model:

[1282] The server preprocesses the collected data and formats it into a format suitable for machine learning models. It then uses algorithms such as random forests and neural networks to train a model that can predict the probability of a disaster occurring. This makes it possible to predict the probability of a disaster occurring in each region.

[1283] 3. Optimizing evacuation locations:

[1284] Based on the predicted probability of disaster occurrence, the server optimally allocates multiple evacuation sites, taking into consideration the safety, capacity, and accessibility of each site. It also calculates the optimal evacuation route and displays it on a map.

[1285] 4. Emotion analysis:

[1286] The server analyzes the user's emotional state based on voice, facial expression, and input data collected from the user's device. The analysis engine uses OpenCV, Google Cloud Speech-to-Text, and touch data analysis algorithms. If the user's emotional state is tense, the notification information is simplified and an encouraging message is added.

[1287] 5. Display and notification of results:

[1288] The server displays optimized evacuation locations and evacuation routes on a map, which is then displayed on the device dashboard as a digital disaster prevention map. It also notifies residents of evacuation instructions and disaster information on their smartphones, adjusting the content and display method of the notifications based on the results of emotion analysis.

[1289] Examples:

[1290] For example, if a municipality experiences prolonged heavy rain and is at risk of flooding, the system can perform the following operations:

[1291] The server obtains the latest heavy rain data from the Japan Meteorological Agency and stores it in a database.

[1292] Local government officials operating the terminals input and update local geographical information, resident information, building earthquake resistance, and evacuation shelter information into the system.

[1293] The server predicts the probability of flood disasters occurring based on the collected data.

[1294] The server selects a safe evacuation location based on the prediction results and displays that information on the device.

[1295] The server calculates safe and efficient evacuation routes and displays them on a map.

[1296] The emotion engine analyzes the user's emotional state and displays brief evacuation information and adds encouraging messages to users with high stress levels.

[1297] The person in charge using the terminal will check the disaster prevention map, revise the contents if necessary, and then finalize the evacuation plan.

[1298] Based on the confirmed evacuation plan, the server will notify residents of evacuation information via SMS or email.

[1299] Example prompt sentence:

[1300] "It suggests optimal evacuation routes based on current weather conditions and adjusts notifications based on the user's emotional state."

[1301] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1302] Step 1:

[1303] The server obtains the latest weather data, earthquake data, flood data, etc. from external information providers such as the Japan Meteorological Agency. The input is disaster data obtained from external APIs, and the output is disaster data stored on the server. Specifically, it periodically sends API requests and stores the responses in a database.

[1304] Step 2:

[1305] Local government officials operating the terminals input and update local geographic information, building seismic performance, evacuation shelter capacity, and infrastructure status for each region. The input is manual entry of local information, and the output is updated local information that is uploaded to the server. Specific operations include entering information through a browser-based dashboard and pressing the submit button to upload the data.

[1306] Step 3:

[1307] The server preprocesses the collected disaster data and area information and formats it into a format suitable for the machine learning model. The input is the collected disaster data and area information, and the output is a formatted dataset. Specific operations include filling in missing values, removing outliers, and normalizing the data.

[1308] Step 4:

[1309] The server uses the shaped dataset to train a model that predicts the probability of disaster occurrence using algorithms such as random forests and neural networks. The input is the shaped dataset, and the output is a trained model that predicts the probability of disaster occurrence. Specifically, the server inputs the training data into the algorithm and optimizes the model parameters.

[1310] Step 5:

[1311] The server uses the trained model to predict the probability of disaster occurrence for each region in real time. The input is the latest disaster data, and the output is the probability of disaster occurrence for each region. Specifically, new data is input into the model, and the prediction results are obtained and stored in the database.

[1312] Step 6:

[1313] The server selects safe evacuation sites and calculates optimal evacuation routes based on the predicted probability of disaster occurrence. The inputs are the probability of disaster occurrence, local geographic information, and infrastructure information, and the output is information on evacuation sites and evacuation routes. Specifically, the server selects evacuation sites taking into account each site's capacity, safety, and accessibility, and calculates optimal evacuation routes based on traffic information.

[1314] Step 7:

[1315] The server displays information on evacuation locations and evacuation routes on a map and generates a digital disaster prevention map. The input is information on evacuation locations and evacuation routes, and the output is a digital disaster prevention map that is displayed on the device's dashboard. Specifically, the server visually displays evacuation locations and routes by overlaying them on the map data.

[1316] Step 8:

[1317] The user device acquires voice data, facial expression data, and input data and performs emotion analysis. The input is data acquired from the user device, and the output is the analyzed emotional state of the user. Specifically, data is collected using a camera and microphone and processed by an emotion analysis engine.

[1318] Step 9:

[1319] The server adjusts the display content and notification method based on the results of emotion analysis. The input is the analyzed emotional state and evacuation information, and the output is the adjusted notification information. Specifically, for users with high stress, the system simplifies the information and adds an encouraging message.

[1320] Step 10:

[1321] The server notifies residents of evacuation information via SMS or email based on the finalized evacuation plan. The input is the final evacuation plan, and the output is the notification sent to residents. Specifically, the server generates disaster information and evacuation instructions in text format and sends them using the communication system.

[1322] Example prompt sentence:

[1323] "It suggests optimal evacuation routes based on current weather conditions and adjusts notifications based on the user's emotional state."

[1324] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1325] 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.

[1326] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1327] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1328] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1329] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1330] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1331] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1332] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1333] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1334] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1335] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1336] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1337] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1338] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1339] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1340] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1341] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1342] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1343] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1344] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1345] The following is further disclosed regarding the above embodiment.

[1346] (Claim 1)

[1347] A means for predicting the probability of disaster occurrence in each region based on multiple disaster data collected;

[1348] a means for optimally arranging a plurality of evacuation sites based on the disaster occurrence probability;

[1349] means for displaying the evacuation locations and evacuation routes on a map;

[1350] means for notifying a user of information on the map;

[1351] A system including:

[1352] (Claim 2)

[1353] 2. The system of claim 1, wherein the collected disaster data includes weather data, earthquake data, and flood data.

[1354] (Claim 3)

[1355] The system according to claim 1 , wherein the evacuation route is optimized taking into account road congestion information and geographical constraints.

[1356] "Example 1"

[1357] (Claim 1)

[1358] A means for predicting the probability of a disaster occurring in each region based on multiple disaster-related data collected;

[1359] a means for optimally arranging a plurality of evacuation sites based on the disaster occurrence probability;

[1360] means for displaying the evacuation locations and evacuation routes on a map;

[1361] means for notifying a user of information on the map;

[1362] A means of formatting the collected data into a format suitable for machine learning models;

[1363] A means for calculating the probability of a disaster occurring using a machine learning model;

[1364] A means of calculating evacuation routes taking into account the state of infrastructure;

[1365] A system including:

[1366] (Claim 2)

[1367] 2. The system of claim 1, wherein the collected disaster data includes weather data, earthquake data, and flood data.

[1368] (Claim 3)

[1369] The system according to claim 1 , wherein the evacuation route is optimized taking into account road congestion information and geographical constraints.

[1370] "Application Example 1"

[1371] (Claim 1)

[1372] A means for predicting the probability of disaster occurrence in each region based on multiple disaster data collected;

[1373] a means for optimally arranging a plurality of evacuation sites based on the disaster occurrence probability;

[1374] means for displaying the evacuation locations and evacuation routes on a map;

[1375] means for notifying a user of information on the map;

[1376] means for calculating the disaster occurrence probability and evacuation site information in real time and proposing the most suitable evacuation site and evacuation route based on the user's location information;

[1377] A means for receiving and notifying disaster prediction results using a generative AI model by inputting a prompt sentence;

[1378] A system including:

[1379] (Claim 2)

[1380] 2. The system of claim 1, wherein the collected disaster data includes weather data, earthquake data, and flood data.

[1381] (Claim 3)

[1382] The system according to claim 1 , wherein the evacuation route is optimized taking into account road congestion information and geographical constraints.

[1383] "Example 2: Combining Emotion Engines"

[1384] (Claim 1)

[1385] A means for predicting the probability of disaster occurrence in each region based on multiple disaster data collected;

[1386] a means for optimally arranging a plurality of evacuation sites based on the disaster occurrence probability;

[1387] emotion recognition means for analyzing the user's emotional state and adjusting the notification content;

[1388] means for displaying the evacuation locations and evacuation routes on a map;

[1389] means for notifying a user of information on the map;

[1390] A system including:

[1391] (Claim 2)

[1392] 2. The system of claim 1, wherein the collected disaster data includes weather data, earthquake data, and flood data.

[1393] (Claim 3)

[1394] The system of claim 1 , wherein the evacuation route is optimized taking into account road traffic information and geographical constraints.

[1395] "Application example 2 when combining emotion engines"

[1396] (Claim 1)

[1397] A means for predicting the probability of disaster occurrence in each region based on multiple disaster data collected;

[1398] a means for optimally arranging a plurality of evacuation sites based on the disaster occurrence probability;

[1399] means for displaying the evacuation locations and evacuation routes on a map;

[1400] means for notifying a user of information on the map;

[1401] An emotion analysis means for analyzing the emotional s...

Claims

1. A means for predicting the probability of disaster occurrence in each region based on multiple disaster data collected; a means for optimally arranging a plurality of evacuation sites based on the disaster occurrence probability; means for displaying the evacuation locations and evacuation routes on a map; means for notifying a user of information on the map; A system including:

2. The system of claim 1 , wherein the collected disaster data includes weather data, earthquake data, and flood data.

3. The system according to claim 1 , wherein the evacuation route is optimized taking into account road congestion information and geographical constraints.

Images