System

Abstract

A system is provided.SOLUTION: A system comprising: means for acquiring topographical data; means for acquiring river flooding data; means for acquiring past disaster damage data; means for acquiring image data; means for integrating and normalizing the above-mentioned data; means for predicting damage at the time of disaster occurrence; means for acquiring a current position; means for calculating an evacuation route; means for evaluating a risk for the evacuation route; and means for displaying the evacuation route whose risk has been evaluated.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] When natural disasters and other disasters occur, it is extremely difficult for victims to make calm decisions and select the optimal evacuation route. In particular, panic can occur during large-scale disasters, hindering safe evacuation. For this reason, a system that can quickly and reliably provide safe evacuation routes is needed. Furthermore, conventional systems have difficulty predicting damage in real time or integrating various data for comprehensive evaluation. This has led to the problem of delays in providing appropriate evacuation routes. [Means for solving the problem]

[0005] The present invention provides a means for acquiring topographical data, river flood data, past disaster damage data, and image data, and integrating and normalizing the data. The present invention also solves the above-mentioned problems by providing a system including a means for predicting damage in the event of a disaster using the data, a means for acquiring the user's current location, a means for calculating an evacuation route, a means for assessing the risk of the calculated evacuation route, and a means for displaying the risk-assessed evacuation route. Furthermore, the system also includes a means for selecting an optimal evacuation shelter based on the shelter's location information and a means for analyzing the strength of building exterior walls based on image data, thereby enhancing the safety of evacuation routes.

[0006] "Topographic data" is information that indicates the terrain, altitude, and shape of the earth's surface.

[0007] "River flood data" refers to information such as past records of river flooding, predicted flood areas, and water levels at the time of flooding.

[0008] "Past disaster damage data" is information that indicates the damage situation, scope of impact, and extent of damage caused by disasters that have occurred in the past.

[0009] "Image data" refers to digital image data that contains visual information, such as street view and satellite images.

[0010] "Integration" refers to the process of combining different types of data so that they can be handled within a single system.

[0011] "Normalization" is the process of standardizing data into a consistent format and range, making different data sets easier to compare and analyze.

[0012] "Means for predicting damage" refers to methods and technologies for predicting the scale and scope of damage that may occur in the event of a disaster, based on acquired data.

[0013] "Means for obtaining current location" refers to methods or technologies for determining a user's current location using GPS or other location information technology.

[0014] "Means for calculating evacuation routes" refers to methods and technologies for calculating the optimal route from the current location to a safe evacuation shelter.

[0015] "Means for assessing risk" refers to methods and technologies that overlay predicted damage information on calculated evacuation routes to assess their safety.

[0016] A "risk-assessed evacuation route" is an evacuation route whose safety has been assessed based on damage prediction data.

[0017] "Evacuation shelter location information" is information that indicates the location of a place where evacuation is recommended in the event of a disaster.

[0018] "Means for analyzing the strength of building exterior walls" refers to methods and technologies that use image data to evaluate the resistance and vulnerability of building exterior walls. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

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

[0029] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] As an embodiment of the present invention, the system configuration of a disaster evacuation route navigation system and its specific operation will be described.

[0041] System Configuration

[0042] The system mainly consists of the following components:

[0043] Server: Acquires topographical data, river flood data, data on damage caused by past disasters, and image data, integrates and normalizes them, and predicts damage.

[0044] Terminal (user's smartphone, etc.): Obtains the user's current location, communicates with the server, and displays evacuation routes.

[0045] User: Operate the application and follow the evacuation instructions.

[0046] What the program does

[0047] 1. Data acquisition and preprocessing

[0048] server:

[0049] The server retrieves topographical data, river flood data, past disaster damage data, and image data from external databases and APIs. This data comes in different formats and needs to be integrated and normalized.

[0050] Examples:

[0051] The server retrieves topographical data from a geographic information system (GIS) and also retrieves recent flood data using the Japan Meteorological Agency's API.

[0052] 2. Damage prediction using AI models

[0053] server:

[0054] The acquired data is used to train an AI model. For example, deep learning can be used to predict the extent of flood damage or the risk of building collapse due to an earthquake. Furthermore, image data can be used to analyze the strength of building exterior walls and assess the risk of disasters within a specific area.

[0055] Examples:

[0056] The server uses past disaster data and Street View image data to predict how well a particular building will withstand an earthquake.

[0057] 3. Obtaining the user's current location and evacuation request

[0058] Device:

[0059] When a user launches the app, the device acquires its current location using GPS, which is then sent to the server, which requests the calculation of an evacuation route.

[0060] Examples:

[0061] When a user opens the smartphone app and requests an evacuation route, the device sends its current GPS location information to the server.

[0062] 4. Calculating the optimal evacuation route

[0063] server:

[0064] The server calculates the safest and quickest evacuation route based on the current location information and the location information of the evacuation shelter, and uses damage prediction data to evaluate the risk of each route and select the optimal route.

[0065] Examples:

[0066] The server calculates routes that avoid areas with a high risk of flooding and selects the optimal evacuation route based on the evaluation results.

[0067] 5. Display and guidance of evacuation routes

[0068] Device:

[0069] The evacuation route sent from the server is displayed on the device's application, which uses map display and voice guidance to guide the user safely to the evacuation shelter.

[0070] User:

[0071] The user begins evacuation by following this displayed route and follows instructions to secure a safe route.

[0072] Examples:

[0073] The device displays the evacuation route received from the server as a red line on a map and uses voice guidance to give instructions such as "Turn right at the next intersection."

[0074] Summary

[0075] In this way, the disaster evacuation route navigation system of the present invention is a system that utilizes various data to predict damage and provides users with the safest evacuation route, thereby enabling quick and reliable evacuation even in the event of a disaster, thereby improving safety.

[0076] The processing flow will be explained below.

[0077] Step 1:

[0078] Server: Acquisition of various data

[0079] The server obtains topographical data, river flood data, past disaster damage data, and image data from external databases and APIs, including the API of the Ministry of Land, Infrastructure, Transport and Tourism, open data from the Japan Meteorological Agency, and satellite images.

[0080] Step 2:

[0081] Server: Data integration and normalization

[0082] The acquired data has different formats, so it is integrated and normalized within the server, which enables consistent processing across different data sets.

[0083] Step 3:

[0084] Server: Training the AI ​​model

[0085] The combined data is used to train AI models such as deep learning models, for example to predict the extent of flood damage or the risk of building collapse due to earthquakes.

[0086] Step 4:

[0087] Server: Building Strength Analysis

[0088] The server analyzes the image data and evaluates the strength of the building's exterior walls, making it possible to assess the durability of buildings within a specific area.

[0089] Step 5:

[0090] Terminal: Obtain current location and request evacuation

[0091] When a user launches the app, the device obtains its current location using GPS and sends a request to the server to calculate an evacuation route.

[0092] Step 6:

[0093] Server: Evacuation route calculation

[0094] The server calculates the shortest and safest evacuation route based on the current location information and the location information of the evacuation shelter sent from the device. During this process, it performs a risk assessment using damage prediction data to confirm safety.

[0095] Step 7:

[0096] Server: Risk-assessed route selection

[0097] A risk assessment is performed on the calculated multiple evacuation routes, and the safest route is selected.

[0098] Step 8:

[0099] Server: Send risk-assessed route

[0100] The selected evacuation route is sent to the terminal.

[0101] Step 9:

[0102] Terminal: Display of evacuation route

[0103] The device displays the received evacuation route on the user interface, showing the route in red on a map and providing detailed directions.

[0104] Step 10:

[0105] User: Evacuation initiation

[0106] The user begins evacuation by following the displayed evacuation route and following the instructions on the device to safely and quickly reach a shelter.

[0107] Step 11:

[0108] Device: Real-time updates

[0109] If the disaster situation changes, the device will periodically communicate with the server to obtain the latest evacuation routes, providing the optimal route even during evacuation.

[0110] In this way, this system provides users with the optimal evacuation route through each step, supporting safe evacuation in the event of a disaster.

[0111] Example 1

[0112] 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."

[0113] In recent years, natural disasters have become more frequent, and many people are seeking safe evacuation methods. However, conventional evacuation systems do not adequately provide real-time damage predictions or appropriate evacuation routes, making it difficult to ensure rapid and reliable evacuation. In addition, there is a lack of systems that can accurately assess disaster risks and provide optimal evacuation routes based on those assessments. Therefore, there is a need for a system that enables safe and rapid evacuation even in the event of a disaster.

[0114] 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.

[0115] In this invention, the server includes means for acquiring topographical data, means for acquiring river flood data, means for acquiring past disaster damage data, means for acquiring image data, means for integrating and normalizing the above data, means for predicting damage in the event of a disaster, means for acquiring the user's current location, means for calculating an evacuation route, means for assessing the risk of the evacuation route, and means for displaying and providing audio guidance on the risk-assessed evacuation route. This makes it possible to accurately predict damage based on the various acquired data and provide the optimal evacuation route.

[0116] "Topographic data" refers to information about the shape of the Earth's surface, and is obtained from geographic information systems, maps, etc.

[0117] "River flood data" refers to past and current information on river flooding, including data on water levels and flooded areas.

[0118] "Past disaster damage data" refers to information on the damage and damage situation caused by past natural disasters.

[0119] "Image data" refers to visual information such as photographs and videos, and is used to analyze the strength of building exterior walls, etc.

[0120] "Integration" refers to the process of bringing together data of different formats and types into a single data set.

[0121] "Normalization" refers to the process of adjusting acquired data according to certain standards to make it consistent.

[0122] "Means for predicting damage" refers to systems or algorithms that use acquired data to predict damage in the event of a disaster.

[0123] "Means for obtaining current location" refers to technologies such as GPS for obtaining user location information.

[0124] "Means for calculating evacuation routes" refers to a system or software that calculates the optimal route from the user's current location to an evacuation shelter.

[0125] "Means for assessing risk" refers to systems or algorithms for assessing disaster risk against calculated evacuation routes.

[0126] "Means for displaying and providing audio guidance on risk-assessed evacuation routes" means a system or application for displaying risk-assessed evacuation routes on a user's device and providing audio guidance.

[0127] System Configuration

[0128] The present invention is a system that mainly comprises the following elements:

[0129] Server: Acquires topographical data, river flooding data, data on damage caused by past disasters, and image data, integrates and normalizes this data, and predicts damage in the event of a disaster.

[0130] Terminal (user's smartphone, etc.): Obtains the user's current location, communicates with the server to display evacuation routes, and provides voice guidance.

[0131] User: Operate the application and follow the evacuation instructions.

[0132] What the program does

[0133] Data Acquisition

[0134] The server obtains topographical data, river flooding data, past disaster damage data, and image data from external databases and APIs. Specifically, it can obtain topographical data from a geographic information system (GIS) and flood data using the Japan Meteorological Agency's API.

[0135] Data Preprocessing

[0136] The server integrates and normalizes the acquired data, and performs preprocessing such as filling in missing values ​​and scaling the data. For example, it integrates GIS topographical data and flood data into a single dataset and fills in missing items.

[0137] AI model training and damage prediction

[0138] The server trains an AI model based on the preprocessed data. Using techniques such as deep learning, it predicts the extent of flood impact and the risk of building collapse due to earthquakes. It also uses image data to analyze the strength of building exterior walls and assess the disaster risk in specific areas. For example, it uses past disaster data and Street View image data to predict how well buildings in a particular area can withstand an earthquake.

[0139] Get the user's current location

[0140] When a user launches an app, the device uses GPS to obtain the user's current location. This means that the moment a user launches a smartphone app, current location information is obtained from GPS.

[0141] Submitting an evacuation request

[0142] The device sends the acquired current location information to the server and requests it to calculate an evacuation route. When the user presses the "Search for evacuation route" button on the smartphone app, the GPS location information is sent to the server.

[0143] Evacuation route calculation and risk assessment

[0144] The server calculates the safest and most efficient evacuation route based on the current location information and the location of the evacuation shelter, taking into account damage prediction data. For example, it calculates a route that avoids areas at risk of flooding in addition to the current location and the location of the evacuation shelter, and selects the optimal route.

[0145] Evacuation route display and audio guidance

[0146] The device displays the evacuation route sent from the server on the app. The user is guided safely using a map display and voice guidance. The user begins evacuation by following the displayed route and the voice guidance. For example, the evacuation route is displayed as a red line on the user's smartphone, and a voice guide is played saying, "Turn right at the next intersection."

[0147] Prompt Sentence Examples

[0148] "I would like to design an application that displays effective evacuation routes in the event of the next natural disaster. Please explain in natural language the specific operation of a system that uses topographical data, river flooding data, data on damage caused by past disasters, and image data to predict the safest and fastest evacuation route and provide it to users."

[0149] In this way, the disaster evacuation route navigation system of the present invention is a system that utilizes various data to predict damage and provides the user with the safest evacuation route, thereby achieving safe and rapid evacuation.

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

[0151] Step 1: Get the data

[0152] The server obtains topographical data, river flooding data, past disaster damage data, and image data from external databases and APIs. This allows for efficient collection of necessary disaster information from a variety of data sources. As a specific example, topographical data is obtained from a geographic information system (GIS) and the latest flood data is collected through the API of meteorological agencies.

[0153] Input: Topographical data from geographic information systems (GIS), flood data from meteorological agencies, data on past disaster damage, and image data.

[0154] Output: Raw dataset

[0155] Step 2: Preprocessing the data

[0156] The server integrates and normalizes data acquired in different formats. During this process, it performs preprocessing such as filling in missing values ​​and scaling the data. This creates a unified dataset. For example, it integrates GIS topographical data and flood data, converts them into a single, well-organized dataset, fills in missing values, and standardizes them.

[0157] Input: Raw dataset

[0158] Output: A combined, normalized dataset

[0159] Step 3: Training the AI ​​model and predicting damage

[0160] The server uses the preprocessed data to train AI models such as deep learning. The trained model is then used to predict damage. In this process, the extent of flood impact and the risk of building collapse due to earthquakes are predicted. The strength of building exterior walls is analyzed from image data, and the disaster risk in specific areas is also assessed. As a specific example, past disaster data and Street View image data are used to predict how well a building can withstand an earthquake.

[0161] Input: Unified normalized dataset

[0162] Output: Damage prediction data

[0163] Step 4: Get the user's current location

[0164] When a user launches an app, the device uses GPS to obtain the user's current location. This allows the device to grasp the user's location information in real time. For example, the moment a user launches a smartphone app, current location information is obtained from GPS.

[0165] Input: App launch signal

[0166] Output: Current location data

[0167] Step 5: Submit an evacuation request

[0168] The device sends the acquired current location information to the server and requests it to calculate an evacuation route. This allows the user to respond quickly to the current emergency situation. For example, when a user presses the "Search for evacuation route" button on a smartphone app, the GPS location information is sent to the server.

[0169] Input: Current location data

[0170] Output: Evacuation route calculation request

[0171] Step 6: Evacuation route calculation and risk assessment

[0172] The server calculates the safest and most efficient evacuation route based on the current location information and the location information of the evacuation shelter, taking into account damage prediction data. This allows safe evacuation routes to be provided quickly. For example, in addition to the current location and the location of the evacuation shelter, it calculates a route that avoids areas at risk of flooding and selects the optimal route.

[0173] Input: current location data, evacuation shelter location data, damage prediction data

[0174] Output: Evaluated evacuation route data

[0175] Step 7: Evacuation route display and audio guidance

[0176] The device displays the evaluated evacuation route sent from the server on the app and provides voice guidance. The user begins evacuation by following the displayed route and the voice guidance. For example, the evacuation route is displayed as a red line on the user's smartphone, and a voice guidance is played saying, "Turn right at the next intersection."

[0177] Input: Evaluated evacuation route data

[0178] Output: Displayed evacuation route, audio guidance

[0179] (Application example 1)

[0180] 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."

[0181] Conventional evacuation route navigation systems require users to manually follow designated routes, potentially increasing confusion and anxiety during disasters. This poses a particular challenge for those with mobility issues, such as the elderly and people with disabilities, who find it even more difficult to evacuate safely. Furthermore, there is no fully established system that can quickly provide optimal evacuation routes by taking into account real-time disaster information. There is a need to solve these issues and realize safe and rapid evacuation using autonomous vehicles during disasters.

[0182] 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.

[0183] In this invention, the server includes a means for acquiring topographical data, a means for acquiring river flood data, a means for acquiring past disaster damage data, and a means for acquiring image data. This allows the data to be integrated and normalized. The server also includes a means for predicting damage in the event of a disaster, a means for acquiring a current location, a means for calculating an evacuation route, a means for assessing the risk of the evacuation route, a means for displaying the risk-assessed evacuation route, a means for transmitting the optimal evacuation route to an autonomous vehicle, and a means for causing the autonomous vehicle to autonomously drive based on the evacuation route. This allows the provision of an optimal evacuation route with risk assessed in real time, enabling quick and safe evacuation using an autonomous vehicle.

[0184] "Topography data" refers to data that indicates the detailed structure and characteristics of the topography.

[0185] "River flood data" refers to historical information and forecast data regarding river flooding.

[0186] "Past disaster damage data" is record data of damage caused by disasters that have occurred in the past.

[0187] "Image data" refers to digital image files that contain visual information.

[0188] "Integration" is the process of combining multiple pieces of data into one.

[0189] "Normalization" is the process of aligning data of different formats or scales into a uniform format.

[0190] "Damage prediction in the event of a disaster" means predicting the extent of damage that will occur when a disaster occurs.

[0191] "Current Location" means the current GPS location of a user or motor vehicle.

[0192] An "evacuation route" is a route that will allow you to reach a shelter safely and quickly.

[0193] "Risk assessment" refers to assessing the risk of encountering a disaster in relation to evacuation routes.

[0194] A "risk-assessed evacuation route" is the optimal evacuation route after the risk has been assessed.

[0195] "Send to automated vehicle" means transmitting information from the server to the automated vehicle.

[0196] "Autonomous driving" refers to a vehicle that drives autonomously without the need for human operation.

[0197] As an embodiment of the present invention, a specific example of applying a disaster evacuation route navigation system to an autonomous vehicle will be described. This system is constructed using the following various hardware and software.

[0198] Hardware Configuration

[0199] 1. Server: Collects topographical data, river flooding data, past disaster damage data, and image data, and uses AI models to predict damage. It uses geographic information systems (GIS), weather data APIs, Street View image data, etc.

[0200] 2. Self-driving vehicle: Obtains the user's current location and drives autonomously based on the evacuation route sent from the server. Equipped with a GPS module, on-board computer, and communication module.

[0201] 3. Smartphone: Receives the user's evacuation request, sends the current location to the server, and obtains the evacuation route. Uses an ANDROID (registered trademark) or iOS device.

[0202] System Operation Overview

[0203] 1. Data Collection and Normalization:

[0204] The server collects topographical data, river flood data, past disaster damage data, and image data from external APIs. It integrates and normalizes this data. Specifically, it obtains topographical data using GIS and flood data via meteorological data APIs.

[0205] 2. Damage Prediction:

[0206] The server trains an AI model based on the collected data to predict damage during disasters. For example, it uses deep learning to predict the extent of flooding and the risk of building collapse due to earthquakes. It also analyzes the strength of building exterior walls from image data and assesses the risk of disaster within the area.

[0207] 3. Obtaining the user's current location and requesting evacuation:

[0208] When a user launches the smartphone app and requests an evacuation route, the device uses GPS to obtain its current location and sends it to the server.

[0209] 4. Evacuation route calculation:

[0210] The server calculates the safest and quickest evacuation route based on the current location information and the location information of the evacuation shelter, and uses damage prediction data to evaluate the risk of each route and select the optimal route.

[0211] 5. Evacuation route display and automatic driving:

[0212] The calculated optimal evacuation route is displayed on the smartphone and on the autonomous vehicle's screen, and the vehicle automatically begins driving based on this information to guide the user to a safe evacuation site.

[0213] Examples of concrete examples and prompts

[0214] Examples:

[0215] If a user is in Tokyo with a GPS location of (35.6895, 139.6917), they request an evacuation route via their smartphone app. The server calculates a safe route based on the latest flood and earthquake risk data and sends that information to the autonomous vehicle. The vehicle then safely transports the user to an evacuation shelter via the specified route.

[0216] Example prompt sentence:

[0217] "The user's current location is 35.6895, 139.6917 in Tokyo. Please calculate the safest evacuation route from this location and provide instructions to the autonomous vehicle."

[0218] Thus, an embodiment of the present invention provides a system that assesses disaster risk in real time and enables quick and safe evacuation using autonomous vehicles.

[0219] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0220] Step 1:

[0221] The server obtains topographical data, river flooding data, past disaster damage data, and image data from external APIs (for example, GIS and meteorological data APIs). This data is integrated, normalized, and then stored. The input is external data, and the output is an integrated dataset. Specifically, the GIS data contains topographical elevation information, and the meteorological data API provides past flood history and forecast data. This allows data in different formats to be stored on the server in a unified format.

[0222] Step 2:

[0223] Based on the dataset acquired in step 1, the server uses an AI model (e.g., a deep learning model) to predict damage in the event of a disaster. The input is the integrated dataset, and the output is the predicted damage extent and risk assessment data. Specifically, the AI ​​model analyzes the height of the terrain and the structure of buildings to evaluate the risk of damage from floods and earthquakes. This process quantifies the risk within a specific area.

[0224] Step 3:

[0225] A user launches a smartphone app and requests an evacuation route. The device obtains its current location using a GPS module and sends that information to the server. The input is the GPS data of the current location, and the output is an evacuation request to the server. Specifically, when the user taps the evacuation button on the app, the app obtains the GPS data and sends it to the server in real time.

[0226] Step 4:

[0227] The server calculates the optimal evacuation route based on the user's current location, the location information of the evacuation shelter, and the damage information predicted in step 2. This calculation also includes a risk assessment of each route. The inputs are the current location, the location information of the evacuation shelter, and the damage prediction data, and the output is the evaluated optimal evacuation route. Specifically, the server uses the Dijkstra algorithm or the A algorithm to calculate the shortest route with the lowest risk.

[0228] Step 5:

[0229] The optimal evacuation route sent from the server is displayed on the smartphone app on the device and on the display of the autonomous vehicle. The user begins evacuation by following this route, and the autonomous vehicle also automatically begins driving based on this route. The input is data on the optimal evacuation route, and the output is evacuation instructions and driving instructions for the autonomous vehicle. Specifically, the smartphone app displays a map and provides voice guidance, while the autonomous vehicle drives this route autonomously.

[0230] The above are the specific processing steps in the system of the present invention, which enables users to evacuate quickly and safely in the event of a disaster.

[0231] 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.

[0232] As an embodiment of the present invention, a specific configuration and operation of a system that combines a disaster evacuation route navigation system and an emotion engine will be described.

[0233] System Configuration

[0234] The system mainly consists of the following components:

[0235] Server: Acquires topographical data, river flood data, data on damage caused by past disasters, and image data, integrates and normalizes them, and predicts damage.

[0236] Terminal (user's smartphone, etc.): Obtains the user's current location, communicates with the server, and displays evacuation routes.

[0237] Emotion Engine: Recognizes the user's emotional state and adaptively changes navigation methods.

[0238] User: Operate the application and follow the evacuation instructions.

[0239] What the program does

[0240] 1. Data acquisition and preprocessing

[0241] server:

[0242] The server retrieves topographical data, river flood data, past disaster damage data, and image data from external databases and APIs. This data comes in different formats, so it needs to be integrated and normalized.

[0243] Examples:

[0244] The server retrieves topographical data from a geographic information system (GIS) and also retrieves recent flood data using the Japan Meteorological Agency's API.

[0245] 2. Damage prediction using AI models

[0246] server:

[0247] The acquired data is used to train an AI model. For example, deep learning can be used to predict the extent of flood damage or the risk of building collapse due to an earthquake. Furthermore, image data can be used to analyze the strength of building exterior walls and assess the risk of disasters within a specific area.

[0248] Examples:

[0249] The server uses past disaster data and Street View image data to predict how well a particular building will withstand an earthquake.

[0250] 3. Obtaining the user's current location and evacuation request

[0251] Device:

[0252] When a user launches the app, the device obtains its current location using GPS and sends a request to the server to calculate an evacuation route.

[0253] Examples:

[0254] When a user opens the smartphone app and requests an evacuation route, the device sends its current GPS location information to the server.

[0255] 4. Calculating the optimal evacuation route

[0256] server:

[0257] The server calculates the safest and quickest evacuation route based on the current location information and the location information of the evacuation shelter, and uses damage prediction data to evaluate the risk of each route and select the optimal route.

[0258] Examples:

[0259] The server calculates routes that avoid areas with a high risk of flooding and selects the optimal evacuation route based on the evaluation results.

[0260] 5. Display and guidance of evacuation routes

[0261] Device:

[0262] The evacuation route sent from the server is displayed on the device's application, which uses map display and voice guidance to guide the user safely to the evacuation shelter.

[0263] User:

[0264] The user begins evacuation by following this displayed route and follows instructions to secure a safe route.

[0265] Examples:

[0266] The device displays the evacuation route received from the server as a red line on a map and uses voice guidance to give instructions such as "Turn right at the next intersection."

[0267] 6. User Emotion Recognition

[0268] Emotion Engine:

[0269] The device uses a camera and microphone to analyze the user's facial expressions and tone of voice to recognize their emotional state, and this data is collected and analyzed in real time.

[0270] Examples:

[0271] The device's camera recognizes the user's face, and when the emotion engine detects that the user is in a panic, it sends that information to the server.

[0272] 7. Emotionally Adapted Navigation

[0273] Servers and devices:

[0274] Based on the information obtained from the emotion engine, the navigation method is adaptively changed according to the user's emotional state. For example, a user who is not calm will receive more understandable instructions or reassuring messages.

[0275] Examples:

[0276] Based on the analysis results of the emotion engine, the server sends more detailed navigation and voice messages such as "Please stay calm."

[0277] Summary

[0278] In this way, the disaster evacuation route navigation system of the present invention is a system that utilizes various data to predict damage and provide users with the safest evacuation route, and by combining it with an emotion engine, it can provide appropriate navigation according to the user's emotional state. This system enables quick and reliable evacuation in the event of a disaster, improving safety and peace of mind.

[0279] The processing flow will be explained below.

[0280] Step 1:

[0281] Server: Acquisition of various data

[0282] The server retrieves topographical data, river flood data, past disaster damage data, and image data from external databases and APIs. This data includes open data from the Ministry of Land, Infrastructure, Transport and Tourism and the Japan Meteorological Agency, as well as various geographic information systems (GIS).

[0283] Step 2:

[0284] Server: Data integration and normalization

[0285] Since the acquired data is in different formats, it is integrated and normalized within the server, which enables consistent processing across each data set.

[0286] Step 3:

[0287] Server: Training the AI ​​model

[0288] The combined data is used to train AI models, for example using deep learning to create models that predict the extent of flood damage or the risk of building collapse in an earthquake.

[0289] Step 4:

[0290] Server: Building Strength Analysis

[0291] Image data obtained from Street View and other sources is analyzed to evaluate the strength of building exterior walls, making it possible to determine the durability of buildings in a specific area and assess the risk of disasters.

[0292] Step 5:

[0293] Terminal: Obtain current location and request evacuation

[0294] When a user launches the app, the device uses GPS to obtain its current location and sends a request to the server to calculate an evacuation route.

[0295] Step 6:

[0296] Server: Evacuation route calculation

[0297] The server calculates the safest and quickest evacuation route based on the current location information and the location information of the evacuation shelter sent from the device, and performs a risk assessment of each route using damage prediction data.

[0298] Step 7:

[0299] Server: Risk-assessed route selection

[0300] A risk assessment is performed on the calculated evacuation routes, and the safest route is selected from among them.

[0301] Step 8:

[0302] Server: Send risk-assessed route

[0303] The selected evacuation route is sent to the terminal.

[0304] Step 9:

[0305] Terminal: Display of evacuation route

[0306] The device displays the received evacuation route on the user interface, showing a safe evacuation route on a map and providing detailed directions.

[0307] Step 10:

[0308] Emotion Engine: Recognizing user emotions

[0309] The device uses a camera and microphone to analyze the user's facial expressions and tone of voice to recognize their emotional state, and this data is collected and analyzed in real time.

[0310] Step 11:

[0311] Server and Terminal: Emotion-Aware Navigation Adaptation

[0312] Based on information obtained from the emotion engine, the navigation method is adaptively changed depending on the user's emotional state. For example, if the user is panicking, more detailed instructions or reassuring messages are provided.

[0313] Step 12:

[0314] Terminal: Evacuation start and real-time updates

[0315] The user begins evacuation by following the displayed evacuation route. The device periodically communicates with the server to provide the user with the latest evacuation route and instructions according to the situation.

[0316] In this way, the system provides the user with the optimal evacuation route through each step, and the emotion engine provides appropriate navigation according to the user's psychological state.

[0317] Example 2

[0318] 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."

[0319] Conventional disaster evacuation systems are limited to presenting evacuation routes and predicting damage, and do not take into account the user's psychological state, making it difficult to provide appropriate support to users in a panic. Furthermore, there are challenges in predicting damage in real time and optimizing evacuation routes, making it difficult to evacuate quickly and safely.

[0320] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0321] In this invention, the server includes means for acquiring topographical data, means for acquiring river flood data, means for acquiring past disaster damage data, means for acquiring image data, means for integrating and normalizing the above data, means for predicting damage in the event of a disaster, means for acquiring a current location, means for calculating an evacuation route, means for assessing the risk of the evacuation route, means for displaying the risk-assessed evacuation route, means for recognizing the user's emotional state, and means for adaptively changing navigation based on the user's emotional state. This enables damage prediction and optimization of evacuation routes in real time, and further provides appropriate navigation according to the user's emotional state.

[0322] "Topography data" refers to data that includes information about the characteristics and shape of the topography.

[0323] "River flood data" refers to data that includes information on the state of rising water levels and flooding of rivers.

[0324] "Past disaster damage data" refers to data that includes records and statistical information on the damage caused by disasters that have occurred in the past.

[0325] "Image data" refers to visual information such as photographs and videos recorded in digital format.

[0326] "Integration and normalization means" refers to techniques and methods for converting data in different formats into a consistent format and unifying the data.

[0327] "Means for predicting damage in the event of a disaster" refers to technologies and methods for predicting the scope and extent of damage in the event of a disaster based on various data.

[0328] "Means for obtaining current location" refers to techniques or methods for determining a user's current physical location using GPS or other location information technology.

[0329] "Means for calculating an evacuation route" refers to a technique or method for calculating the optimal evacuation route based on the user's current location and the location of the evacuation destination.

[0330] "Means for assessing risk" refers to techniques and methods for analyzing disaster risks that exist for evacuation routes and assessing the level of those risks.

[0331] "Means for displaying risk-assessed evacuation routes" refers to techniques or methods for presenting risk-assessed evacuation routes to users by using maps, screen displays, or the like.

[0332] "Means for recognizing a user's emotional state" refers to technology or methods for analyzing and recognizing a user's emotions based on information obtained from a camera, microphone, etc.

[0333] "Means for adaptively changing navigation" refers to techniques and methods for changing and providing navigation instructions according to the emotional state of the user.

[0334] The present invention will now be described with reference to the specific configuration and operation of a system that combines a disaster evacuation route navigation system and an emotion engine.

[0335] System Configuration

[0336] The system mainly consists of the following components:

[0337] Server: Acquires topographical data, river flood data, past disaster damage data, and image data, integrates and normalizes them, and predicts damage.

[0338] Terminal (user's smartphone, etc.): Obtains the user's current location, communicates with the server, and displays evacuation routes.

[0339] Emotion Engine: Recognizes the user's emotional state and adaptively changes navigation methods.

[0340] User: Operate the application and follow the evacuation instructions.

[0341] Data acquisition and preprocessing

[0342] server:

[0343] The server retrieves topographical data, river flood data, past disaster damage data, and image data from external databases and APIs. This data comes in different formats and needs to be integrated and normalized.

[0344] Specifically, it obtains topographical data from a geographic information system (GIS) and also obtains the latest flood data using the Japan Meteorological Agency's API.

[0345] Damage prediction

[0346] server:

[0347] Using the acquired data, a deep learning framework (e.g., TENSORFLOW®) is used to train an AI model, which then predicts the extent of flood damage and the risk of building collapse due to an earthquake.

[0348] It also analyzes image data to assess the strength of building exterior walls and assess disaster risk within specific areas.

[0349] Obtaining the user's current location and evacuation request

[0350] Device:

[0351] When a user launches the app, the device's GPS acquires the current location and sends a request to the server to calculate an evacuation route.

[0352] Evacuation route calculation

[0353] server:

[0354] The server calculates the safest and quickest evacuation route based on the current location information and the location information of the evacuation shelter, and uses damage prediction data to evaluate the risk of each route and select the optimal route.

[0355] For example, the server calculates routes that avoid areas at high risk of flooding.

[0356] Evacuation route display and guidance

[0357] Device:

[0358] The evacuation route information sent from the server is displayed on the device's application, which uses map display and voice guidance to guide the user safely to an evacuation shelter.

[0359] User:

[0360] The user begins evacuation by following the displayed route and follows instructions to secure a safe route.

[0361] Specifically, the device displays the evacuation route received from the server as a red line on a map and issues voice guidance such as "Turn right at the next intersection."

[0362] User Emotion Recognition

[0363] Emotion Engine:

[0364] The device's camera and microphone are used to analyze the user's facial expressions and tone of voice to recognize their emotional state. This data is collected in real time and sent to a server.

[0365] For example, the device's camera recognizes the user's face and the emotion engine detects that the user is in a panic.

[0366] Emotionally adaptive navigation

[0367] Servers and devices:

[0368] Based on information obtained from the emotion engine, the navigation method is adaptively changed according to the user's emotional state. Users who are not calm are given clearer instructions and reassuring messages.

[0369] For example, the server sends a voice message such as "Please stay calm" to the terminal.

[0370] Prompt Sentence Examples

[0371] If the user's escape route is blocked by water, generate the following prompt:

[0372] "Currently, some roads are impassable due to flooding. If you are in a state of panic, please remain calm and follow the instructions below to continue evacuating."

[0373] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0374] Step 1: Data acquisition and preprocessing

[0375] server:

[0376] Input: topographical data, river flood data, past disaster damage data, image data

[0377] Output: Uniform format dataset

[0378] Specific behavior:

[0379] 1. The server retrieves terrain data from a geographic information system (GIS).

[0380] 2. Call the Japan Meteorological Agency's API to obtain the latest flood data.

[0381] 3. Obtain past disaster damage data and Street View image data from the database.

[0382] 4. The various data acquired are integrated and a normalization algorithm is applied to unify the format.

[0383] Step 2: Training and applying an AI model for damage prediction

[0384] server:

[0385] Input: Normalized dataset

[0386] Output: Damage prediction data

[0387] Specific behavior:

[0388] 1. Train an AI model using a deep learning framework (e.g., TensorFlow) based on the normalized dataset.

[0389] 2. Use trained AI models to predict the extent of flood damage and the risk of building collapse due to earthquakes.

[0390] 3. Analyze Street View image data and evaluate the strength of building exterior walls to assess disaster risk within a specific area.

[0391] Step 3: Get current location and send evacuation request

[0392] Device:

[0393] Input: User operation (app launch), GPS data

[0394] Output: Current location information

[0395] Specific behavior:

[0396] 1. The user launches the app.

[0397] 2. The device uses GPS to obtain its current location.

[0398] 3. Send the current location information to the server along with a request for evacuation route calculation.

[0399] Step 4: Calculate evacuation routes

[0400] server:

[0401] Input: current location information, evacuation shelter location information, damage prediction data

[0402] Output: Optimal evacuation route

[0403] Specific behavior:

[0404] 1. Generate multiple evacuation routes based on current location information and evacuation shelter location information.

[0405] 2. Use damage forecast data to assess the risk of each evacuation route.

[0406] 3. Based on the evaluation results, select the safest, fastest and most optimal evacuation route.

[0407] Step 5: Display and guide evacuation routes

[0408] Device:

[0409] Input: Optimal evacuation route data

[0410] Output: Map display and voice guidance

[0411] Specific behavior:

[0412] 1. Display the evacuation route information received from the server in the app's map module.

[0413] 2. The route will be displayed on the map with a red line, and a voice guidance will begin guiding you, saying, "Turn right at the next intersection."

[0414] User:

[0415] Input: Map display and voice guidance

[0416] Output: Evacuation execution and direction correction

[0417] Specific behavior:

[0418] 1. Check the route on the map and start moving.

[0419] 2. Correct your direction according to the voice guidance and map information.

[0420] Step 6: Recognizing User Emotions

[0421] Emotion Engine:

[0422] Input: Camera video, microphone audio

[0423] Output: Emotion recognition data

[0424] Specific behavior:

[0425] 1. The device camera captures the user's face and performs image analysis.

[0426] 2. The microphone collects the user's voice and the emotion engine analyzes the tone and content.

[0427] 3. Send the results to the server in real time.

[0428] Step 7: Adapt navigation based on emotions

[0429] Servers and devices:

[0430] Input: Emotion recognition data

[0431] Output: Adaptive navigation instructions

[0432] Specific behavior:

[0433] 1. The emotion engine recognizes the user's emotional state (e.g., panicked, calm).

[0434] 2. The server receives the analysis results and adjusts the voice guidance and message content.

[0435] 3. Send a reassuring voice message to the device, such as "Please stay calm."

[0436] (Application example 2)

[0437] 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."

[0438] Conventional disaster evacuation navigation systems simply calculate and present evacuation routes, but are unable to adapt to the user's emotional state during evacuation. This makes it difficult to provide appropriate support to users who are confused or panicked, which can result in delays in evacuation. In contrast, the present invention aims to promote quick and safe evacuation by recognizing the user's emotional state and adaptively changing the navigation method according to that state.

[0439] 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.

[0440] In this invention, the server includes a means for acquiring topographical data, a means for acquiring river flood data, and a means for acquiring past disaster damage data. This allows for the integration and normalization of various data, enabling damage prediction in the event of a disaster. The server also includes a means for acquiring a current location, a means for calculating an evacuation route, a means for assessing the risk of the evacuation route, a means for displaying the risk-assessed evacuation route, a means for recognizing a user's emotional state, and a means for adaptively changing the navigation method based on the recognized emotional state. This allows for the server to provide appropriate navigation according to the user's emotional state, supporting a quick and safe evacuation.

[0441] "Topographic data" refers to data that includes information on the shape and distribution of natural and artificial structures.

[0442] "River flood data" refers to data that includes information on water levels and the extent of damage when rivers flood.

[0443] "Past disaster damage data" refers to data that includes information on the type and extent of damage caused by disasters that have occurred in the past.

[0444] "Image data" is data that represents visual information in digital form.

[0445] "Emotional state" refers to an individual's internal feelings and moods, and is information acquired through sensors such as cameras and microphones.

[0446] "Navigation method" refers to the means of instructions or guidance for navigating a route to a destination.

[0447] "Current location" is the user's current geographical location information.

[0448] An "evacuation route" is a route for safe evacuation in the event of a disaster.

[0449] "Risk assessment" is the process of assessing the degree of danger that may arise under specific conditions.

[0450] "Normalization" is a data processing technique that standardizes data in different formats and units to make them easier to compare.

[0451] A "server" is a computer system that acquires and integrates various data and provides services to multiple clients.

[0452] As an embodiment of the present invention, a specific example of a security service application for smartphones is shown below. This application provides navigation for the user to safely evacuate in the event of a disaster, and furthermore, adaptively changes the navigation method according to the user's emotional state.

[0453] System Configuration

[0454] The system of the present invention mainly comprises the following components:

[0455] 1. Server

[0456] Data acquisition and preprocessing

[0457] The server uses a geographic information system (GIS) and the API of the Japan Meteorological Agency to obtain topographical data, river flood data, and past disaster damage data. Because this data is provided in different formats, it is unified and normalized.

[0458] 2. Device (smartphone)

[0459] Current location acquisition and evacuation request

[0460] When a user launches the app, it uses the smartphone's GPS function to obtain the user's current location and requests the server to calculate an evacuation route.

[0461] Evacuation route display and guidance

[0462] The evacuation route sent from the server is displayed on the smartphone application, and the user is guided using a map and voice guidance.

[0463] 3. Emotion Engine

[0464] User Emotion Recognition

[0465] The system uses the smartphone's camera and microphone to analyze the user's emotional state in real time and transmits the data to a server.

[0466] Emotionally adaptive navigation

[0467] The server optimizes the navigation method based on the emotional state and sends reassuring messages to the user.

[0468] Data processing and calculation

[0469] The system of the present invention performs the following data processing and data calculations:

[0470] 1. Data acquisition and preprocessing (server)

[0471] The server obtains topographical data, river flooding data, and past disaster damage data from GIS and the Japan Meteorological Agency's API. For example, topographical data is obtained from GIS, and river flooding data is obtained from the Japan Meteorological Agency's API. This data is converted into a unified format and normalized.

[0472] 2. Damage Prediction (Server)

[0473] The server uses the collected data to predict disaster risks using deep learning frameworks such as TensorFlow, for example, by calculating the risk of flooding or building collapse based on past disaster data and current conditions.

[0474] 3. Evacuation route calculation (server)

[0475] It obtains the user's current location information and calculates the optimal evacuation route, using an algorithm to avoid dangerous areas.

[0476] 4. Evacuation route display and guidance (terminal)

[0477] The evacuation route sent from the server is displayed on a map on the smartphone, and a voice guidance function is also provided, allowing users to receive instructions such as "Turn right at the next intersection."

[0478] 5. Emotion Recognition (Device, Emotion Engine)

[0479] Using the smartphone's camera and microphone, the system analyzes the user's facial expressions and tone of voice to recognize their emotional state. For example, if the user is in a panic state, the system detects this and sends it to the server.

[0480] 6. Adaptation of navigation methods (server, terminal)

[0481] The navigation method is optimized based on the results of emotion analysis. For example, if the user is in a panic, the server will send a reassuring message such as, "Please stay calm. We are calculating the quickest route to the evacuation shelter."

[0482] Specific examples

[0483] When a user opens a smartphone app and requests an evacuation route, the device sends its current GPS location information to the server. The server uses this information to calculate the optimal evacuation route and sends it to the device. The device displays the route on a map and navigates the user using voice guidance. If the user panics during evacuation, the camera detects this and sends it to the server in real time. The server adaptively changes the navigation message based on the user's emotional state, sending a message such as "Please stay calm."

[0484] Prompt Sentence Examples

[0485] 1. "Please remain calm. We are calculating the quickest route to the evacuation center."

[0486] 2. "Take a deep breath. Turn right at the next intersection."

[0487] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0488] Step 1:

[0489] Data acquisition and preprocessing (server)

[0490] The server obtains topographical data, river flooding data, and past disaster damage data from a geographic information system (GIS) and the Japan Meteorological Agency's API. Specifically, it downloads topographical data from the GIS and collects recent flood data using the Japan Meteorological Agency's API. Because these data are provided in different formats, they are converted into a unified format and normalized. The input is various types of data, and the output is integrated, normalized data.

[0491] Step 2:

[0492] Damage prediction (server)

[0493] The server uses a deep learning model (e.g., TensorFlow) based on the acquired data to predict disaster risk. Specifically, it trains the model using past disaster data and integrated data, and uses current data as input to predict the extent of damage and the risk of building collapse. The input is integrated, normalized data, and the output is a predicted disaster risk map.

[0494] Step 3:

[0495] Current location acquisition and evacuation request (terminal)

[0496] When a user launches the app, it uses the smartphone's GPS to obtain current location information. This location information is sent to the server, which then requests evacuation route calculation. The input is the user's current GPS coordinates, and the output is the request sent to the server.

[0497] Step 4:

[0498] Evacuation route calculation (server)

[0499] The server uses the received current location information and evacuation shelter location information to calculate the optimal evacuation route. Based on the obtained disaster risk map, it evaluates the risk of each route and selects the safest route. The input is the user's current location and the evacuation shelter location information, and the output is the evaluated evacuation route.

[0500] Step 5:

[0501] Evacuation route display and guidance (terminal)

[0502] The evacuation route sent from the server is displayed as a map on the smartphone application, and a voice guidance function is used to provide the user with specific instructions such as "Turn right at the next intersection." The input is the evaluated evacuation route, and the output is a map showing the route and voice guidance.

[0503] Step 6:

[0504] User emotion recognition (device)

[0505] Using the smartphone's camera and microphone, the system analyzes the user's facial expressions and tone of voice to recognize their emotional state. This is done in real time, and the results are sent to a server. The input is the user's facial expressions and tone of voice, and the output is the analyzed emotional state data.

[0506] Step 7:

[0507] Adaptation of navigation methods (server, terminal)

[0508] The server optimizes the navigation method based on the results of emotion analysis. For example, if the user is in a panic state, the server generates a reassuring message such as "Please stay calm. We are calculating the fastest route to the evacuation shelter," and sends it to the device. The input is the analyzed emotional state data, and the output is an adaptively modified navigation message.

[0509] 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.

[0510] 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.

[0511] 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.

[0512] [Second embodiment]

[0513] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0514] 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.

[0515] 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).

[0516] 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.

[0517] 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.

[0518] 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).

[0519] 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.

[0520] 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.

[0521] 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.

[0522] 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.

[0523] 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.

[0524] 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."

[0525] As an embodiment of the present invention, the system configuration of a disaster evacuation route navigation system and its specific operation will be described.

[0526] System Configuration

[0527] The system mainly consists of the following components:

[0528] Server: Acquires topographical data, river flood data, data on damage caused by past disasters, and image data, integrates and normalizes them, and predicts damage.

[0529] Terminal (user's smartphone, etc.): Obtains the user's current location, communicates with the server, and displays evacuation routes.

[0530] User: Operate the application and follow the evacuation instructions.

[0531] What the program does

[0532] 1. Data acquisition and preprocessing

[0533] server:

[0534] The server retrieves topographical data, river flood data, past disaster damage data, and image data from external databases and APIs. This data comes in different formats and needs to be integrated and normalized.

[0535] Examples:

[0536] The server retrieves topographical data from a geographic information system (GIS) and also retrieves recent flood data using the Japan Meteorological Agency's API.

[0537] 2. Damage prediction using AI models

[0538] server:

[0539] The acquired data is used to train an AI model. For example, deep learning can be used to predict the extent of flood damage or the risk of building collapse due to an earthquake. Furthermore, image data can be used to analyze the strength of building exterior walls and assess the risk of disasters within a specific area.

[0540] Examples:

[0541] The server uses past disaster data and Street View image data to predict how well a particular building will withstand an earthquake.

[0542] 3. Obtaining the user's current location and evacuation request

[0543] Device:

[0544] When a user launches the app, the device acquires its current location using GPS, which is then sent to the server, which requests the calculation of an evacuation route.

[0545] Examples:

[0546] When a user opens the smartphone app and requests an evacuation route, the device sends its current GPS location information to the server.

[0547] 4. Calculating the optimal evacuation route

[0548] server:

[0549] The server calculates the safest and quickest evacuation route based on the current location information and the location information of the evacuation shelter, and uses damage prediction data to evaluate the risk of each route and select the optimal route.

[0550] Examples:

[0551] The server calculates routes that avoid areas with a high risk of flooding and selects the optimal evacuation route based on the evaluation results.

[0552] 5. Display and guidance of evacuation routes

[0553] Device:

[0554] The evacuation route sent from the server is displayed on the device's application, which uses map display and voice guidance to guide the user safely to the evacuation shelter.

[0555] User:

[0556] The user begins evacuation by following this displayed route and follows instructions to secure a safe route.

[0557] Examples:

[0558] The device displays the evacuation route received from the server as a red line on a map and uses voice guidance to give instructions such as "Turn right at the next intersection."

[0559] Summary

[0560] In this way, the disaster evacuation route navigation system of the present invention is a system that utilizes various data to predict damage and provides users with the safest evacuation route, thereby enabling quick and reliable evacuation even in the event of a disaster, thereby improving safety.

[0561] The processing flow will be explained below.

[0562] Step 1:

[0563] Server: Acquisition of various data

[0564] The server obtains topographical data, river flood data, past disaster damage data, and image data from external databases and APIs, including the API of the Ministry of Land, Infrastructure, Transport and Tourism, open data from the Japan Meteorological Agency, and satellite images.

[0565] Step 2:

[0566] Server: Data integration and normalization

[0567] The acquired data has different formats, so it is integrated and normalized within the server, which enables consistent processing across different data sets.

[0568] Step 3:

[0569] Server: Training the AI ​​model

[0570] The combined data is used to train AI models such as deep learning models, for example to predict the extent of flood damage or the risk of building collapse due to earthquakes.

[0571] Step 4:

[0572] Server: Building Strength Analysis

[0573] The server analyzes the image data and evaluates the strength of the building's exterior walls, making it possible to assess the durability of buildings within a specific area.

[0574] Step 5:

[0575] Terminal: Obtain current location and request evacuation

[0576] When a user launches the app, the device obtains its current location using GPS and sends a request to the server to calculate an evacuation route.

[0577] Step 6:

[0578] Server: Evacuation route calculation

[0579] The server calculates the shortest and safest evacuation route based on the current location information and the location information of the evacuation shelter sent from the device. During this process, it performs a risk assessment using damage prediction data to confirm safety.

[0580] Step 7:

[0581] Server: Risk-assessed route selection

[0582] A risk assessment is performed on the calculated multiple evacuation routes, and the safest route is selected.

[0583] Step 8:

[0584] Server: Send risk-assessed route

[0585] The selected evacuation route is sent to the terminal.

[0586] Step 9:

[0587] Terminal: Display of evacuation route

[0588] The device displays the received evacuation route on the user interface, showing the route in red on a map and providing detailed directions.

[0589] Step 10:

[0590] User: Evacuation initiation

[0591] The user begins evacuation by following the displayed evacuation route and following the instructions on the device to safely and quickly reach a shelter.

[0592] Step 11:

[0593] Device: Real-time updates

[0594] If the disaster situation changes, the device will periodically communicate with the server to obtain the latest evacuation routes, providing the optimal route even during evacuation.

[0595] In this way, this system provides users with the optimal evacuation route through each step, supporting safe evacuation in the event of a disaster.

[0596] Example 1

[0597] 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."

[0598] In recent years, natural disasters have become more frequent, and many people are seeking safe evacuation methods. However, conventional evacuation systems do not adequately provide real-time damage predictions or appropriate evacuation routes, making it difficult to ensure rapid and reliable evacuation. In addition, there is a lack of systems that can accurately assess disaster risks and provide optimal evacuation routes based on those assessments. Therefore, there is a need for a system that enables safe and rapid evacuation even in the event of a disaster.

[0599] 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.

[0600] In this invention, the server includes means for acquiring topographical data, means for acquiring river flood data, means for acquiring past disaster damage data, means for acquiring image data, means for integrating and normalizing the above data, means for predicting damage in the event of a disaster, means for acquiring the user's current location, means for calculating an evacuation route, means for assessing the risk of the evacuation route, and means for displaying and providing audio guidance on the risk-assessed evacuation route. This makes it possible to accurately predict damage based on the various acquired data and provide the optimal evacuation route.

[0601] "Topographic data" refers to information about the shape of the Earth's surface, and is obtained from geographic information systems, maps, etc.

[0602] "River flood data" refers to past and current information on river flooding, including data on water levels and flooded areas.

[0603] "Past disaster damage data" refers to information on the damage and damage situation caused by past natural disasters.

[0604] "Image data" refers to visual information such as photographs and videos, and is used to analyze the strength of building exterior walls, etc.

[0605] "Integration" refers to the process of bringing together data of different formats and types into a single data set.

[0606] "Normalization" refers to the process of adjusting acquired data according to certain standards to make it consistent.

[0607] "Means for predicting damage" refers to systems or algorithms that use acquired data to predict damage in the event of a disaster.

[0608] "Means for obtaining current location" refers to technologies such as GPS for obtaining user location information.

[0609] "Means for calculating evacuation routes" refers to a system or software that calculates the optimal route from the user's current location to an evacuation shelter.

[0610] "Means for assessing risk" refers to systems or algorithms for assessing disaster risk against calculated evacuation routes.

[0611] "Means for displaying and providing audio guidance on risk-assessed evacuation routes" means a system or application for displaying risk-assessed evacuation routes on a user's device and providing audio guidance.

[0612] System Configuration

[0613] The present invention is a system that mainly comprises the following elements:

[0614] Server: Acquires topographical data, river flooding data, data on damage caused by past disasters, and image data, integrates and normalizes this data, and predicts damage in the event of a disaster.

[0615] Terminal (user's smartphone, etc.): Obtains the user's current location, communicates with the server to display evacuation routes, and provides voice guidance.

[0616] User: Operate the application and follow the evacuation instructions.

[0617] What the program does

[0618] Data Acquisition

[0619] The server obtains topographical data, river flooding data, past disaster damage data, and image data from external databases and APIs. Specifically, it can obtain topographical data from a geographic information system (GIS) and flood data using the Japan Meteorological Agency's API.

[0620] Data Preprocessing

[0621] The server integrates and normalizes the acquired data, and performs preprocessing such as filling in missing values ​​and scaling the data. For example, it integrates GIS topographical data and flood data into a single dataset and fills in missing items.

[0622] AI model training and damage prediction

[0623] The server trains an AI model based on the preprocessed data. Using techniques such as deep learning, it predicts the extent of flood impact and the risk of building collapse due to earthquakes. It also uses image data to analyze the strength of building exterior walls and assess the disaster risk in specific areas. For example, it uses past disaster data and Street View image data to predict how well buildings in a particular area can withstand an earthquake.

[0624] Get the user's current location

[0625] When a user launches an app, the device uses GPS to obtain the user's current location. This means that the moment a user launches a smartphone app, current location information is obtained from GPS.

[0626] Submitting an evacuation request

[0627] The device sends the acquired current location information to the server and requests it to calculate an evacuation route. When the user presses the "Search for evacuation route" button on the smartphone app, the GPS location information is sent to the server.

[0628] Evacuation route calculation and risk assessment

[0629] The server calculates the safest and most efficient evacuation route based on the current location information and the location of the evacuation shelter, taking into account damage prediction data. For example, it calculates a route that avoids areas at risk of flooding in addition to the current location and the location of the evacuation shelter, and selects the optimal route.

[0630] Evacuation route display and audio guidance

[0631] The device displays the evacuation route sent from the server on the app. The user is guided safely using a map display and voice guidance. The user begins evacuation by following the displayed route and the voice guidance. For example, the evacuation route is displayed as a red line on the user's smartphone, and a voice guide is played saying, "Turn right at the next intersection."

[0632] Prompt Sentence Examples

[0633] "I would like to design an application that displays effective evacuation routes in the event of the next natural disaster. Please explain in natural language the specific operation of a system that uses topographical data, river flooding data, data on damage caused by past disasters, and image data to predict the safest and fastest evacuation route and provide it to users."

[0634] In this way, the disaster evacuation route navigation system of the present invention is a system that utilizes various data to predict damage and provides the user with the safest evacuation route, thereby achieving safe and rapid evacuation.

[0635] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0636] Step 1: Get the data

[0637] The server obtains topographical data, river flooding data, past disaster damage data, and image data from external databases and APIs. This allows for efficient collection of necessary disaster information from a variety of data sources. As a specific example, topographical data is obtained from a geographic information system (GIS) and the latest flood data is collected through the API of meteorological agencies.

[0638] Input: Topographical data from geographic information systems (GIS), flood data from meteorological agencies, data on past disaster damage, and image data.

[0639] Output: Raw dataset

[0640] Step 2: Preprocessing the data

[0641] The server integrates and normalizes data acquired in different formats. During this process, it performs preprocessing such as filling in missing values ​​and scaling the data. This creates a unified dataset. For example, it integrates GIS topographical data and flood data, converts them into a single, well-organized dataset, fills in missing values, and standardizes them.

[0642] Input: Raw dataset

[0643] Output: A combined, normalized dataset

[0644] Step 3: Training the AI ​​model and predicting damage

[0645] The server uses the preprocessed data to train AI models such as deep learning. The trained model is then used to predict damage. In this process, the extent of flood impact and the risk of building collapse due to earthquakes are predicted. The strength of building exterior walls is analyzed from image data, and the disaster risk in specific areas is also assessed. As a specific example, past disaster data and Street View image data are used to predict how well a building can withstand an earthquake.

[0646] Input: Unified normalized dataset

[0647] Output: Damage prediction data

[0648] Step 4: Get the user's current location

[0649] When a user launches an app, the device uses GPS to obtain the user's current location. This allows the device to grasp the user's location information in real time. For example, the moment a user launches a smartphone app, current location information is obtained from GPS.

[0650] Input: App launch signal

[0651] Output: Current location data

[0652] Step 5: Submit an evacuation request

[0653] The device sends the acquired current location information to the server and requests it to calculate an evacuation route. This allows the user to respond quickly to the current emergency situation. For example, when a user presses the "Search for evacuation route" button on a smartphone app, the GPS location information is sent to the server.

[0654] Input: Current location data

[0655] Output: Evacuation route calculation request

[0656] Step 6: Evacuation route calculation and risk assessment

[0657] The server calculates the safest and most efficient evacuation route based on the current location information and the location information of the evacuation shelter, taking into account damage prediction data. This allows safe evacuation routes to be provided quickly. For example, in addition to the current location and the location of the evacuation shelter, it calculates a route that avoids areas at risk of flooding and selects the optimal route.

[0658] Input: current location data, evacuation shelter location data, damage prediction data

[0659] Output: Evaluated evacuation route data

[0660] Step 7: Evacuation route display and audio guidance

[0661] The device displays the evaluated evacuation route sent from the server on the app and provides voice guidance. The user begins evacuation by following the displayed route and the voice guidance. For example, the evacuation route is displayed as a red line on the user's smartphone, and a voice guidance is played saying, "Turn right at the next intersection."

[0662] Input: Evaluated evacuation route data

[0663] Output: Displayed evacuation route, audio guidance

[0664] (Application example 1)

[0665] 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."

[0666] Conventional evacuation route navigation systems require users to manually follow designated routes, potentially increasing confusion and anxiety during disasters. This poses a particular challenge for those with mobility issues, such as the elderly and people with disabilities, who find it even more difficult to evacuate safely. Furthermore, there is no fully established system that can quickly provide optimal evacuation routes by taking into account real-time disaster information. There is a need to solve these issues and realize safe and rapid evacuation using autonomous vehicles during disasters.

[0667] 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.

[0668] In this invention, the server includes a means for acquiring topographical data, a means for acquiring river flood data, a means for acquiring past disaster damage data, and a means for acquiring image data. This allows the data to be integrated and normalized. The server also includes a means for predicting damage in the event of a disaster, a means for acquiring a current location, a means for calculating an evacuation route, a means for assessing the risk of the evacuation route, a means for displaying the risk-assessed evacuation route, a means for transmitting the optimal evacuation route to an autonomous vehicle, and a means for causing the autonomous vehicle to autonomously drive based on the evacuation route. This allows the provision of an optimal evacuation route with risk assessed in real time, enabling quick and safe evacuation using an autonomous vehicle.

[0669] "Topography data" refers to data that indicates the detailed structure and characteristics of the topography.

[0670] "River flood data" refers to historical information and forecast data regarding river flooding.

[0671] "Past disaster damage data" is record data of damage caused by disasters that have occurred in the past.

[0672] "Image data" refers to digital image files that contain visual information.

[0673] "Integration" is the process of combining multiple pieces of data into one.

[0674] "Normalization" is the process of aligning data of different formats or scales into a uniform format.

[0675] "Damage prediction in the event of a disaster" means predicting the extent of damage that will occur when a disaster occurs.

[0676] "Current Location" means the current GPS location of a user or motor vehicle.

[0677] An "evacuation route" is a route that will allow you to reach a shelter safely and quickly.

[0678] "Risk assessment" refers to assessing the risk of encountering a disaster in relation to evacuation routes.

[0679] A "risk-assessed evacuation route" is the optimal evacuation route after the risk has been assessed.

[0680] "Send to automated vehicle" means transmitting information from the server to the automated vehicle.

[0681] "Autonomous driving" refers to a vehicle that drives autonomously without the need for human operation.

[0682] As an embodiment of the present invention, a specific example of applying a disaster evacuation route navigation system to an autonomous vehicle will be described. This system is constructed using the following various hardware and software.

[0683] Hardware Configuration

[0684] 1. Server: Collects topographical data, river flooding data, past disaster damage data, and image data, and uses AI models to predict damage. It uses geographic information systems (GIS), weather data APIs, Street View image data, etc.

[0685] 2. Self-driving vehicle: Obtains the user's current location and drives autonomously based on the evacuation route sent from the server. Equipped with a GPS module, on-board computer, and communication module.

[0686] 3. Smartphone: Receives the user's evacuation request, sends the current location to the server, and obtains the evacuation route. Uses an Android or iOS device.

[0687] System Operation Overview

[0688] 1. Data Collection and Normalization:

[0689] The server collects topographical data, river flood data, past disaster damage data, and image data from external APIs. It integrates and normalizes this data. Specifically, it obtains topographical data using GIS and flood data via meteorological data APIs.

[0690] 2. Damage Prediction:

[0691] The server trains an AI model based on the collected data to predict damage during disasters. For example, it uses deep learning to predict the extent of flooding and the risk of building collapse due to earthquakes. It also analyzes the strength of building exterior walls from image data and assesses the risk of disaster within the area.

[0692] 3. Obtaining the user's current location and requesting evacuation:

[0693] When a user launches the smartphone app and requests an evacuation route, the device uses GPS to obtain its current location and sends it to the server.

[0694] 4. Evacuation route calculation:

[0695] The server calculates the safest and quickest evacuation route based on the current location information and the location information of the evacuation shelter, and uses damage prediction data to evaluate the risk of each route and select the optimal route.

[0696] 5. Evacuation route display and automatic driving:

[0697] The calculated optimal evacuation route is displayed on the smartphone and on the autonomous vehicle's screen, and the vehicle automatically begins driving based on this information to guide the user to a safe evacuation site.

[0698] Examples of concrete examples and prompts

[0699] Examples:

[0700] If a user is in Tokyo with a GPS location of (35.6895, 139.6917), they request an evacuation route via their smartphone app. The server calculates a safe route based on the latest flood and earthquake risk data and sends that information to the autonomous vehicle. The vehicle then safely transports the user to an evacuation shelter via the specified route.

[0701] Example prompt sentence:

[0702] "The user's current location is 35.6895, 139.6917 in Tokyo. Please calculate the safest evacuation route from this location and provide instructions to the autonomous vehicle."

[0703] Thus, an embodiment of the present invention provides a system that assesses disaster risk in real time and enables quick and safe evacuation using autonomous vehicles.

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

[0705] Step 1:

[0706] The server obtains topographical data, river flooding data, past disaster damage data, and image data from external APIs (for example, GIS and meteorological data APIs). This data is integrated, normalized, and then stored. The input is external data, and the output is an integrated dataset. Specifically, the GIS data contains topographical elevation information, and the meteorological data API provides past flood history and forecast data. This allows data in different formats to be stored on the server in a unified format.

[0707] Step 2:

[0708] Based on the dataset acquired in step 1, the server uses an AI model (e.g., a deep learning model) to predict damage in the event of a disaster. The input is the integrated dataset, and the output is the predicted damage extent and risk assessment data. Specifically, the AI ​​model analyzes the height of the terrain and the structure of buildings to evaluate the risk of damage from floods and earthquakes. This process quantifies the risk within a specific area.

[0709] Step 3:

[0710] A user launches a smartphone app and requests an evacuation route. The device obtains its current location using a GPS module and sends that information to the server. The input is the GPS data of the current location, and the output is an evacuation request to the server. Specifically, when the user taps the evacuation button on the app, the app obtains the GPS data and sends it to the server in real time.

[0711] Step 4:

[0712] The server calculates the optimal evacuation route based on the user's current location, the location information of the evacuation shelter, and the damage information predicted in step 2. This calculation also includes a risk assessment of each route. The inputs are the current location, the location information of the evacuation shelter, and the damage prediction data, and the output is the evaluated optimal evacuation route. Specifically, the server uses the Dijkstra algorithm or the A algorithm to calculate the shortest route with the lowest risk.

[0713] Step 5:

[0714] The optimal evacuation route sent from the server is displayed on the smartphone app on the device and on the display of the autonomous vehicle. The user begins evacuation by following this route, and the autonomous vehicle also automatically begins driving based on this route. The input is data on the optimal evacuation route, and the output is evacuation instructions and driving instructions for the autonomous vehicle. Specifically, the smartphone app displays a map and provides voice guidance, while the autonomous vehicle drives this route autonomously.

[0715] The above are the specific processing steps in the system of the present invention, which enables users to evacuate quickly and safely in the event of a disaster.

[0716] 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.

[0717] As an embodiment of the present invention, a specific configuration and operation of a system that combines a disaster evacuation route navigation system and an emotion engine will be described.

[0718] System Configuration

[0719] The system mainly consists of the following components:

[0720] Server: Acquires topographical data, river flood data, data on damage caused by past disasters, and image data, integrates and normalizes them, and predicts damage.

[0721] Terminal (user's smartphone, etc.): Obtains the user's current location, communicates with the server, and displays evacuation routes.

[0722] Emotion Engine: Recognizes the user's emotional state and adaptively changes navigation methods.

[0723] User: Operate the application and follow the evacuation instructions.

[0724] What the program does

[0725] 1. Data acquisition and preprocessing

[0726] server:

[0727] The server retrieves topographical data, river flood data, past disaster damage data, and image data from external databases and APIs. This data comes in different formats, so it needs to be integrated and normalized.

[0728] Examples:

[0729] The server retrieves topographical data from a geographic information system (GIS) and also retrieves recent flood data using the Japan Meteorological Agency's API.

[0730] 2. Damage prediction using AI models

[0731] server:

[0732] The acquired data is used to train an AI model. For example, deep learning can be used to predict the extent of flood damage or the risk of building collapse due to an earthquake. Furthermore, image data can be used to analyze the strength of building exterior walls and assess the risk of disasters within a specific area.

[0733] Examples:

[0734] The server uses past disaster data and Street View image data to predict how well a particular building will withstand an earthquake.

[0735] 3. Obtaining the user's current location and evacuation request

[0736] Device:

[0737] When a user launches the app, the device obtains its current location using GPS and sends a request to the server to calculate an evacuation route.

[0738] Examples:

[0739] When a user opens the smartphone app and requests an evacuation route, the device sends its current GPS location information to the server.

[0740] 4. Calculating the optimal evacuation route

[0741] server:

[0742] The server calculates the safest and quickest evacuation route based on the current location information and the location information of the evacuation shelter, and uses damage prediction data to evaluate the risk of each route and select the optimal route.

[0743] Examples:

[0744] The server calculates routes that avoid areas with a high risk of flooding and selects the optimal evacuation route based on the evaluation results.

[0745] 5. Display and guidance of evacuation routes

[0746] Device:

[0747] The evacuation route sent from the server is displayed on the device's application, which uses map display and voice guidance to guide the user safely to the evacuation shelter.

[0748] User:

[0749] The user begins evacuation by following this displayed route and follows instructions to secure a safe route.

[0750] Examples:

[0751] The device displays the evacuation route received from the server as a red line on a map and uses voice guidance to give instructions such as "Turn right at the next intersection."

[0752] 6. User Emotion Recognition

[0753] Emotion Engine:

[0754] The device uses a camera and microphone to analyze the user's facial expressions and tone of voice to recognize their emotional state, and this data is collected and analyzed in real time.

[0755] Examples:

[0756] The device's camera recognizes the user's face, and when the emotion engine detects that the user is in a panic, it sends that information to the server.

[0757] 7. Emotionally Adapted Navigation

[0758] Servers and devices:

[0759] Based on the information obtained from the emotion engine, the navigation method is adaptively changed according to the user's emotional state. For example, a user who is not calm will receive more understandable instructions or reassuring messages.

[0760] Examples:

[0761] Based on the analysis results of the emotion engine, the server sends more detailed navigation and voice messages such as "Please stay calm."

[0762] Summary

[0763] In this way, the disaster evacuation route navigation system of the present invention is a system that utilizes various data to predict damage and provide users with the safest evacuation route, and by combining it with an emotion engine, it can provide appropriate navigation according to the user's emotional state. This system enables quick and reliable evacuation in the event of a disaster, improving safety and peace of mind.

[0764] The processing flow will be explained below.

[0765] Step 1:

[0766] Server: Acquisition of various data

[0767] The server retrieves topographical data, river flood data, past disaster damage data, and image data from external databases and APIs. This data includes open data from the Ministry of Land, Infrastructure, Transport and Tourism and the Japan Meteorological Agency, as well as various geographic information systems (GIS).

[0768] Step 2:

[0769] Server: Data integration and normalization

[0770] Since the acquired data is in different formats, it is integrated and normalized within the server, which enables consistent processing across each data set.

[0771] Step 3:

[0772] Server: Training the AI ​​model

[0773] The combined data is used to train AI models, for example using deep learning to create models that predict the extent of flood damage or the risk of building collapse in an earthquake.

[0774] Step 4:

[0775] Server: Building Strength Analysis

[0776] Image data obtained from Street View and other sources is analyzed to evaluate the strength of building exterior walls, making it possible to determine the durability of buildings in a specific area and assess the risk of disasters.

[0777] Step 5:

[0778] Terminal: Obtain current location and request evacuation

[0779] When a user launches the app, the device uses GPS to obtain its current location and sends a request to the server to calculate an evacuation route.

[0780] Step 6:

[0781] Server: Evacuation route calculation

[0782] The server calculates the safest and quickest evacuation route based on the current location information and the location information of the evacuation shelter sent from the device, and performs a risk assessment of each route using damage prediction data.

[0783] Step 7:

[0784] Server: Risk-assessed route selection

[0785] A risk assessment is performed on the calculated evacuation routes, and the safest route is selected from among them.

[0786] Step 8:

[0787] Server: Send risk-assessed route

[0788] The selected evacuation route is sent to the terminal.

[0789] Step 9:

[0790] Terminal: Display of evacuation route

[0791] The device displays the received evacuation route on the user interface, showing a safe evacuation route on a map and providing detailed directions.

[0792] Step 10:

[0793] Emotion Engine: Recognizing user emotions

[0794] The device uses a camera and microphone to analyze the user's facial expressions and tone of voice to recognize their emotional state, and this data is collected and analyzed in real time.

[0795] Step 11:

[0796] Server and Terminal: Emotion-Aware Navigation Adaptation

[0797] Based on information obtained from the emotion engine, the navigation method is adaptively changed depending on the user's emotional state. For example, if the user is panicking, more detailed instructions or reassuring messages are provided.

[0798] Step 12:

[0799] Terminal: Evacuation start and real-time updates

[0800] The user begins evacuation by following the displayed evacuation route. The device periodically communicates with the server to provide the user with the latest evacuation route and instructions according to the situation.

[0801] In this way, the system provides the user with the optimal evacuation route through each step, and the emotion engine provides appropriate navigation according to the user's psychological state.

[0802] Example 2

[0803] 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."

[0804] Conventional disaster evacuation systems are limited to presenting evacuation routes and predicting damage, and do not take into account the user's psychological state, making it difficult to provide appropriate support to users in a panic. Furthermore, there are challenges in predicting damage in real time and optimizing evacuation routes, making it difficult to evacuate quickly and safely.

[0805] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0806] In this invention, the server includes means for acquiring topographical data, means for acquiring river flood data, means for acquiring past disaster damage data, means for acquiring image data, means for integrating and normalizing the above data, means for predicting damage in the event of a disaster, means for acquiring a current location, means for calculating an evacuation route, means for assessing the risk of the evacuation route, means for displaying the risk-assessed evacuation route, means for recognizing the user's emotional state, and means for adaptively changing navigation based on the user's emotional state. This enables damage prediction and optimization of evacuation routes in real time, and further provides appropriate navigation according to the user's emotional state.

[0807] "Topography data" refers to data that includes information about the characteristics and shape of the topography.

[0808] "River flood data" refers to data that includes information on the state of rising water levels and flooding of rivers.

[0809] "Past disaster damage data" refers to data that includes records and statistical information on the damage caused by disasters that have occurred in the past.

[0810] "Image data" refers to visual information such as photographs and videos recorded in digital format.

[0811] "Integration and normalization means" refers to techniques and methods for converting data in different formats into a consistent format and unifying the data.

[0812] "Means for predicting damage in the event of a disaster" refers to technologies and methods for predicting the scope and extent of damage in the event of a disaster based on various data.

[0813] "Means for obtaining current location" refers to techniques or methods for determining a user's current physical location using GPS or other location information technology.

[0814] "Means for calculating an evacuation route" refers to a technique or method for calculating the optimal evacuation route based on the user's current location and the location of the evacuation destination.

[0815] "Means for assessing risk" refers to techniques and methods for analyzing disaster risks that exist for evacuation routes and assessing the level of those risks.

[0816] "Means for displaying risk-assessed evacuation routes" refers to techniques or methods for presenting risk-assessed evacuation routes to users by using maps, screen displays, or the like.

[0817] "Means for recognizing a user's emotional state" refers to technology or methods for analyzing and recognizing a user's emotions based on information obtained from a camera, microphone, etc.

[0818] "Means for adaptively changing navigation" refers to techniques and methods for changing and providing navigation instructions according to the emotional state of the user.

[0819] The present invention will now be described with reference to the specific configuration and operation of a system that combines a disaster evacuation route navigation system and an emotion engine.

[0820] System Configuration

[0821] The system mainly consists of the following components:

[0822] Server: Acquires topographical data, river flood data, past disaster damage data, and image data, integrates and normalizes them, and predicts damage.

[0823] Terminal (user's smartphone, etc.): Obtains the user's current location, communicates with the server, and displays evacuation routes.

[0824] Emotion Engine: Recognizes the user's emotional state and adaptively changes navigation methods.

[0825] User: Operate the application and follow the evacuation instructions.

[0826] Data acquisition and preprocessing

[0827] server:

[0828] The server retrieves topographical data, river flood data, past disaster damage data, and image data from external databases and APIs. This data comes in different formats and needs to be integrated and normalized.

[0829] Specifically, it obtains topographical data from a geographic information system (GIS) and also obtains the latest flood data using the Japan Meteorological Agency's API.

[0830] Damage prediction

[0831] server:

[0832] Using the acquired data, a deep learning framework (e.g., TensorFlow) is used to train an AI model that predicts the extent of flood damage and the risk of building collapse due to an earthquake.

[0833] It also analyzes image data to assess the strength of building exterior walls and assess disaster risk within specific areas.

[0834] Obtaining the user's current location and evacuation request

[0835] Device:

[0836] When a user launches the app, the device's GPS acquires the current location and sends a request to the server to calculate an evacuation route.

[0837] Evacuation route calculation

[0838] server:

[0839] The server calculates the safest and quickest evacuation route based on the current location information and the location information of the evacuation shelter, and uses damage prediction data to evaluate the risk of each route and select the optimal route.

[0840] For example, the server calculates routes that avoid areas at high risk of flooding.

[0841] Evacuation route display and guidance

[0842] Device:

[0843] The evacuation route information sent from the server is displayed on the device's application, which uses map display and voice guidance to guide the user safely to an evacuation shelter.

[0844] User:

[0845] The user begins evacuation by following the displayed route and follows instructions to secure a safe route.

[0846] Specifically, the device displays the evacuation route received from the server as a red line on a map and issues voice guidance such as "Turn right at the next intersection."

[0847] User Emotion Recognition

[0848] Emotion Engine:

[0849] The device's camera and microphone are used to analyze the user's facial expressions and tone of voice to recognize their emotional state. This data is collected in real time and sent to a server.

[0850] For example, the device's camera recognizes the user's face and the emotion engine detects that the user is in a panic.

[0851] Emotionally adaptive navigation

[0852] Servers and devices:

[0853] Based on information obtained from the emotion engine, the navigation method is adaptively changed according to the user's emotional state. Users who are not calm are given clearer instructions and reassuring messages.

[0854] For example, the server sends a voice message such as "Please stay calm" to the terminal.

[0855] Prompt Sentence Examples

[0856] If the user's escape route is blocked by water, generate the following prompt:

[0857] "Currently, some roads are impassable due to flooding. If you are in a state of panic, please remain calm and follow the instructions below to continue evacuating."

[0858] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0859] Step 1: Data acquisition and preprocessing

[0860] server:

[0861] Input: topographical data, river flood data, past disaster damage data, image data

[0862] Output: Uniform format dataset

[0863] Specific behavior:

[0864] 1. The server retrieves terrain data from a geographic information system (GIS).

[0865] 2. Call the Japan Meteorological Agency's API to obtain the latest flood data.

[0866] 3. Obtain past disaster damage data and Street View image data from the database.

[0867] 4. The various data acquired are integrated and a normalization algorithm is applied to unify the format.

[0868] Step 2: Training and applying an AI model for damage prediction

[0869] server:

[0870] Input: Normalized dataset

[0871] Output: Damage prediction data

[0872] Specific behavior:

[0873] 1. Train an AI model using a deep learning framework (e.g., TensorFlow) based on the normalized dataset.

[0874] 2. Use trained AI models to predict the extent of flood damage and the risk of building collapse due to earthquakes.

[0875] 3. Analyze Street View image data and evaluate the strength of building exterior walls to assess disaster risk within a specific area.

[0876] Step 3: Get current location and send evacuation request

[0877] Device:

[0878] Input: User operation (app launch), GPS data

[0879] Output: Current location information

[0880] Specific behavior:

[0881] 1. The user launches the app.

[0882] 2. The device uses GPS to obtain its current location.

[0883] 3. Send the current location information to the server along with a request for evacuation route calculation.

[0884] Step 4: Calculate evacuation routes

[0885] server:

[0886] Input: current location information, evacuation shelter location information, damage prediction data

[0887] Output: Optimal evacuation route

[0888] Specific behavior:

[0889] 1. Generate multiple evacuation routes based on current location information and evacuation shelter location information.

[0890] 2. Use damage forecast data to assess the risk of each evacuation route.

[0891] 3. Based on the evaluation results, select the safest, fastest and most optimal evacuation route.

[0892] Step 5: Display and guide evacuation routes

[0893] Device:

[0894] Input: Optimal evacuation route data

[0895] Output: Map display and voice guidance

[0896] Specific behavior:

[0897] 1. Display the evacuation route information received from the server in the app's map module.

[0898] 2. The route will be displayed on the map with a red line, and a voice guidance will begin guiding you, saying, "Turn right at the next intersection."

[0899] User:

[0900] Input: Map display and voice guidance

[0901] Output: Evacuation execution and direction correction

[0902] Specific behavior:

[0903] 1. Check the route on the map and start moving.

[0904] 2. Correct your direction according to the voice guidance and map information.

[0905] Step 6: Recognizing User Emotions

[0906] Emotion Engine:

[0907] Input: Camera video, microphone audio

[0908] Output: Emotion recognition data

[0909] Specific behavior:

[0910] 1. The device camera captures the user's face and performs image analysis.

[0911] 2. The microphone collects the user's voice and the emotion engine analyzes the tone and content.

[0912] 3. Send the results to the server in real time.

[0913] Step 7: Adapt navigation based on emotions

[0914] Servers and devices:

[0915] Input: Emotion recognition data

[0916] Output: Adaptive navigation instructions

[0917] Specific behavior:

[0918] 1. The emotion engine recognizes the user's emotional state (e.g., panicked, calm).

[0919] 2. The server receives the analysis results and adjusts the voice guidance and message content.

[0920] 3. Send a reassuring voice message to the device, such as "Please stay calm."

[0921] (Application example 2)

[0922] 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."

[0923] Conventional disaster evacuation navigation systems simply calculate and present evacuation routes, but are unable to adapt to the user's emotional state during evacuation. This makes it difficult to provide appropriate support to users who are confused or panicked, which can result in delays in evacuation. In contrast, the present invention aims to promote quick and safe evacuation by recognizing the user's emotional state and adaptively changing the navigation method according to that state.

[0924] 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.

[0925] In this invention, the server includes a means for acquiring topographical data, a means for acquiring river flood data, and a means for acquiring past disaster damage data. This allows for the integration and normalization of various data, enabling damage prediction in the event of a disaster. The server also includes a means for acquiring a current location, a means for calculating an evacuation route, a means for assessing the risk of the evacuation route, a means for displaying the risk-assessed evacuation route, a means for recognizing a user's emotional state, and a means for adaptively changing the navigation method based on the recognized emotional state. This allows for the server to provide appropriate navigation according to the user's emotional state, supporting a quick and safe evacuation.

[0926] "Topographic data" refers to data that includes information on the shape and distribution of natural and artificial structures.

[0927] "River flood data" refers to data that includes information on water levels and the extent of damage when rivers flood.

[0928] "Past disaster damage data" refers to data that includes information on the type and extent of damage caused by disasters that have occurred in the past.

[0929] "Image data" is data that represents visual information in digital form.

[0930] "Emotional state" refers to an individual's internal feelings and moods, and is information acquired through sensors such as cameras and microphones.

[0931] "Navigation method" refers to the means of instructions or guidance for navigating a route to a destination.

[0932] "Current location" is the user's current geographical location information.

[0933] An "evacuation route" is a route for safe evacuation in the event of a disaster.

[0934] "Risk assessment" is the process of assessing the degree of danger that may arise under specific conditions.

[0935] "Normalization" is a data processing technique that standardizes data in different formats and units to make them easier to compare.

[0936] A "server" is a computer system that acquires and integrates various data and provides services to multiple clients.

[0937] As an embodiment of the present invention, a specific example of a security service application for smartphones is shown below. This application provides navigation for the user to safely evacuate in the event of a disaster, and furthermore, adaptively changes the navigation method according to the user's emotional state.

[0938] System Configuration

[0939] The system of the present invention mainly comprises the following components:

[0940] 1. Server

[0941] Data acquisition and preprocessing

[0942] The server uses a geographic information system (GIS) and the API of the Japan Meteorological Agency to obtain topographical data, river flood data, and past disaster damage data. Because this data is provided in different formats, it is unified and normalized.

[0943] 2. Device (smartphone)

[0944] Current location acquisition and evacuation request

[0945] When a user launches the app, it uses the smartphone's GPS function to obtain the user's current location and requests the server to calculate an evacuation route.

[0946] Evacuation route display and guidance

[0947] The evacuation route sent from the server is displayed on the smartphone application, and the user is guided using a map and voice guidance.

[0948] 3. Emotion Engine

[0949] User Emotion Recognition

[0950] The system uses the smartphone's camera and microphone to analyze the user's emotional state in real time and transmits the data to a server.

[0951] Emotionally adaptive navigation

[0952] The server optimizes the navigation method based on the emotional state and sends reassuring messages to the user.

[0953] Data processing and calculation

[0954] The system of the present invention performs the following data processing and data calculations:

[0955] 1. Data acquisition and preprocessing (server)

[0956] The server obtains topographical data, river flooding data, and past disaster damage data from GIS and the Japan Meteorological Agency's API. For example, topographical data is obtained from GIS, and river flooding data is obtained from the Japan Meteorological Agency's API. This data is converted into a unified format and normalized.

[0957] 2. Damage Prediction (Server)

[0958] The server uses the collected data to predict disaster risks using deep learning frameworks such as TensorFlow, for example, by calculating the risk of flooding or building collapse based on past disaster data and current conditions.

[0959] 3. Evacuation route calculation (server)

[0960] It obtains the user's current location information and calculates the optimal evacuation route, using an algorithm to avoid dangerous areas.

[0961] 4. Evacuation route display and guidance (terminal)

[0962] The evacuation route sent from the server is displayed on a map on the smartphone, and a voice guidance function is also provided, allowing users to receive instructions such as "Turn right at the next intersection."

[0963] 5. Emotion Recognition (Device, Emotion Engine)

[0964] Using the smartphone's camera and microphone, the system analyzes the user's facial expressions and tone of voice to recognize their emotional state. For example, if the user is in a panic state, the system detects this and sends it to the server.

[0965] 6. Adaptation of navigation methods (server, terminal)

[0966] The navigation method is optimized based on the results of emotion analysis. For example, if the user is in a panic, the server will send a reassuring message such as, "Please stay calm. We are calculating the quickest route to the evacuation shelter."

[0967] Specific examples

[0968] When a user opens a smartphone app and requests an evacuation route, the device sends its current GPS location information to the server. The server uses this information to calculate the optimal evacuation route and sends it to the device. The device displays the route on a map and navigates the user using voice guidance. If the user panics during evacuation, the camera detects this and sends it to the server in real time. The server adaptively changes the navigation message based on the user's emotional state, sending a message such as "Please stay calm."

[0969] Prompt Sentence Examples

[0970] 1. "Please remain calm. We are calculating the quickest route to the evacuation center."

[0971] 2. "Take a deep breath. Turn right at the next intersection."

[0972] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0973] Step 1:

[0974] Data acquisition and preprocessing (server)

[0975] The server obtains topographical data, river flooding data, and past disaster damage data from a geographic information system (GIS) and the Japan Meteorological Agency's API. Specifically, it downloads topographical data from the GIS and collects recent flood data using the Japan Meteorological Agency's API. Because these data are provided in different formats, they are converted into a unified format and normalized. The input is various types of data, and the output is integrated, normalized data.

[0976] Step 2:

[0977] Damage prediction (server)

[0978] The server uses a deep learning model (e.g., TensorFlow) based on the acquired data to predict disaster risk. Specifically, it trains the model using past disaster data and integrated data, and uses current data as input to predict the extent of damage and the risk of building collapse. The input is integrated, normalized data, and the output is a predicted disaster risk map.

[0979] Step 3:

[0980] Current location acquisition and evacuation request (terminal)

[0981] When a user launches the app, it uses the smartphone's GPS to obtain current location information. This location information is sent to the server, which then requests evacuation route calculation. The input is the user's current GPS coordinates, and the output is the request sent to the server.

[0982] Step 4:

[0983] Evacuation route calculation (server)

[0984] The server uses the received current location information and evacuation shelter location information to calculate the optimal evacuation route. Based on the obtained disaster risk map, it evaluates the risk of each route and selects the safest route. The input is the user's current location and the evacuation shelter location information, and the output is the evaluated evacuation route.

[0985] Step 5:

[0986] Evacuation route display and guidance (terminal)

[0987] The evacuation route sent from the server is displayed as a map on the smartphone application, and a voice guidance function is used to provide the user with specific instructions such as "Turn right at the next intersection." The input is the evaluated evacuation route, and the output is a map showing the route and voice guidance.

[0988] Step 6:

[0989] User emotion recognition (device)

[0990] Using the smartphone's camera and microphone, the system analyzes the user's facial expressions and tone of voice to recognize their emotional state. This is done in real time, and the results are sent to a server. The input is the user's facial expressions and tone of voice, and the output is the analyzed emotional state data.

[0991] Step 7:

[0992] Adaptation of navigation methods (server, terminal)

[0993] The server optimizes the navigation method based on the results of emotion analysis. For example, if the user is in a panic state, the server generates a reassuring message such as "Please stay calm. We are calculating the fastest route to the evacuation shelter," and sends it to the device. The input is the analyzed emotional state data, and the output is an adaptively modified navigation message.

[0994] 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.

[0995] 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.

[0996] 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.

[0997] [Third embodiment]

[0998] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0999] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1000] 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).

[1001] 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.

[1002] 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.

[1003] 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).

[1004] 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.

[1005] 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.

[1006] 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.

[1007] 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.

[1008] 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.

[1009] 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."

[1010] As an embodiment of the present invention, the system configuration of a disaster evacuation route navigation system and its specific operation will be described.

[1011] System Configuration

[1012] The system mainly consists of the following components:

[1013] Server: Acquires topographical data, river flood data, data on damage caused by past disasters, and image data, integrates and normalizes them, and predicts damage.

[1014] Terminal (user's smartphone, etc.): Obtains the user's current location, communicates with the server, and displays evacuation routes.

[1015] User: Operate the application and follow the evacuation instructions.

[1016] What the program does

[1017] 1. Data acquisition and preprocessing

[1018] server:

[1019] The server retrieves topographical data, river flood data, past disaster damage data, and image data from external databases and APIs. This data comes in different formats and needs to be integrated and normalized.

[1020] Examples:

[1021] The server retrieves topographical data from a geographic information system (GIS) and also retrieves recent flood data using the Japan Meteorological Agency's API.

[1022] 2. Damage prediction using AI models

[1023] server:

[1024] The acquired data is used to train an AI model. For example, deep learning can be used to predict the extent of flood damage or the risk of building collapse due to an earthquake. Furthermore, image data can be used to analyze the strength of building exterior walls and assess the risk of disasters within a specific area.

[1025] Examples:

[1026] The server uses past disaster data and Street View image data to predict how well a particular building will withstand an earthquake.

[1027] 3. Obtaining the user's current location and evacuation request

[1028] Device:

[1029] When a user launches the app, the device acquires its current location using GPS, which is then sent to the server, which requests the calculation of an evacuation route.

[1030] Examples:

[1031] When a user opens the smartphone app and requests an evacuation route, the device sends its current GPS location information to the server.

[1032] 4. Calculating the optimal evacuation route

[1033] server:

[1034] The server calculates the safest and quickest evacuation route based on the current location information and the location information of the evacuation shelter, and uses damage prediction data to evaluate the risk of each route and select the optimal route.

[1035] Examples:

[1036] The server calculates routes that avoid areas with a high risk of flooding and selects the optimal evacuation route based on the evaluation results.

[1037] 5. Display and guidance of evacuation routes

[1038] Device:

[1039] The evacuation route sent from the server is displayed on the device's application, which uses map display and voice guidance to guide the user safely to the evacuation shelter.

[1040] User:

[1041] The user begins evacuation by following this displayed route and follows instructions to secure a safe route.

[1042] Examples:

[1043] The device displays the evacuation route received from the server as a red line on a map and uses voice guidance to give instructions such as "Turn right at the next intersection."

[1044] Summary

[1045] In this way, the disaster evacuation route navigation system of the present invention is a system that utilizes various data to predict damage and provides users with the safest evacuation route, thereby enabling quick and reliable evacuation even in the event of a disaster, thereby improving safety.

[1046] The processing flow will be explained below.

[1047] Step 1:

[1048] Server: Acquisition of various data

[1049] The server obtains topographical data, river flood data, past disaster damage data, and image data from external databases and APIs, including the API of the Ministry of Land, Infrastructure, Transport and Tourism, open data from the Japan Meteorological Agency, and satellite images.

[1050] Step 2:

[1051] Server: Data integration and normalization

[1052] The acquired data has different formats, so it is integrated and normalized within the server, which enables consistent processing across different data sets.

[1053] Step 3:

[1054] Server: Training the AI ​​model

[1055] The combined data is used to train AI models such as deep learning models, for example to predict the extent of flood damage or the risk of building collapse due to earthquakes.

[1056] Step 4:

[1057] Server: Building Strength Analysis

[1058] The server analyzes the image data and evaluates the strength of the building's exterior walls, making it possible to assess the durability of buildings within a specific area.

[1059] Step 5:

[1060] Terminal: Obtain current location and request evacuation

[1061] When a user launches the app, the device obtains its current location using GPS and sends a request to the server to calculate an evacuation route.

[1062] Step 6:

[1063] Server: Evacuation route calculation

[1064] The server calculates the shortest and safest evacuation route based on the current location information and the location information of the evacuation shelter sent from the device. During this process, it performs a risk assessment using damage prediction data to confirm safety.

[1065] Step 7:

[1066] Server: Risk-assessed route selection

[1067] A risk assessment is performed on the calculated multiple evacuation routes, and the safest route is selected.

[1068] Step 8:

[1069] Server: Send risk-assessed route

[1070] The selected evacuation route is sent to the terminal.

[1071] Step 9:

[1072] Terminal: Display of evacuation route

[1073] The device displays the received evacuation route on the user interface, showing the route in red on a map and providing detailed directions.

[1074] Step 10:

[1075] User: Evacuation initiation

[1076] The user begins evacuation by following the displayed evacuation route and following the instructions on the device to safely and quickly reach a shelter.

[1077] Step 11:

[1078] Device: Real-time updates

[1079] If the disaster situation changes, the device will periodically communicate with the server to obtain the latest evacuation routes, providing the optimal route even during evacuation.

[1080] In this way, this system provides users with the optimal evacuation route through each step, supporting safe evacuation in the event of a disaster.

[1081] Example 1

[1082] 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."

[1083] In recent years, natural disasters have become more frequent, and many people are seeking safe evacuation methods. However, conventional evacuation systems do not adequately provide real-time damage predictions or appropriate evacuation routes, making it difficult to ensure rapid and reliable evacuation. In addition, there is a lack of systems that can accurately assess disaster risks and provide optimal evacuation routes based on those assessments. Therefore, there is a need for a system that enables safe and rapid evacuation even in the event of a disaster.

[1084] 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.

[1085] In this invention, the server includes means for acquiring topographical data, means for acquiring river flood data, means for acquiring past disaster damage data, means for acquiring image data, means for integrating and normalizing the above data, means for predicting damage in the event of a disaster, means for acquiring the user's current location, means for calculating an evacuation route, means for assessing the risk of the evacuation route, and means for displaying and providing audio guidance on the risk-assessed evacuation route. This makes it possible to accurately predict damage based on the various acquired data and provide the optimal evacuation route.

[1086] "Topographic data" refers to information about the shape of the Earth's surface, and is obtained from geographic information systems, maps, etc.

[1087] "River flood data" refers to past and current information on river flooding, including data on water levels and flooded areas.

[1088] "Past disaster damage data" refers to information on the damage and damage situation caused by past natural disasters.

[1089] "Image data" refers to visual information such as photographs and videos, and is used to analyze the strength of building exterior walls, etc.

[1090] "Integration" refers to the process of bringing together data of different formats and types into a single data set.

[1091] "Normalization" refers to the process of adjusting acquired data according to certain standards to make it consistent.

[1092] "Means for predicting damage" refers to systems or algorithms that use acquired data to predict damage in the event of a disaster.

[1093] "Means for obtaining current location" refers to technologies such as GPS for obtaining user location information.

[1094] "Means for calculating evacuation routes" refers to a system or software that calculates the optimal route from the user's current location to an evacuation shelter.

[1095] "Means for assessing risk" refers to systems or algorithms for assessing disaster risk against calculated evacuation routes.

[1096] "Means for displaying and providing audio guidance on risk-assessed evacuation routes" means a system or application for displaying risk-assessed evacuation routes on a user's device and providing audio guidance.

[1097] System Configuration

[1098] The present invention is a system that mainly comprises the following elements:

[1099] Server: Acquires topographical data, river flooding data, data on damage caused by past disasters, and image data, integrates and normalizes this data, and predicts damage in the event of a disaster.

[1100] Terminal (user's smartphone, etc.): Obtains the user's current location, communicates with the server to display evacuation routes, and provides voice guidance.

[1101] User: Operate the application and follow the evacuation instructions.

[1102] What the program does

[1103] Data Acquisition

[1104] The server obtains topographical data, river flooding data, past disaster damage data, and image data from external databases and APIs. Specifically, it can obtain topographical data from a geographic information system (GIS) and flood data using the Japan Meteorological Agency's API.

[1105] Data Preprocessing

[1106] The server integrates and normalizes the acquired data, and performs preprocessing such as filling in missing values ​​and scaling the data. For example, it integrates GIS topographical data and flood data into a single dataset and fills in missing items.

[1107] AI model training and damage prediction

[1108] The server trains an AI model based on the preprocessed data. Using techniques such as deep learning, it predicts the extent of flood impact and the risk of building collapse due to earthquakes. It also uses image data to analyze the strength of building exterior walls and assess the disaster risk in specific areas. For example, it uses past disaster data and Street View image data to predict how well buildings in a particular area can withstand an earthquake.

[1109] Get the user's current location

[1110] When a user launches an app, the device uses GPS to obtain the user's current location. This means that the moment a user launches a smartphone app, current location information is obtained from GPS.

[1111] Submitting an evacuation request

[1112] The device sends the acquired current location information to the server and requests it to calculate an evacuation route. When the user presses the "Search for evacuation route" button on the smartphone app, the GPS location information is sent to the server.

[1113] Evacuation route calculation and risk assessment

[1114] The server calculates the safest and most efficient evacuation route based on the current location information and the location of the evacuation shelter, taking into account damage prediction data. For example, it calculates a route that avoids areas at risk of flooding in addition to the current location and the location of the evacuation shelter, and selects the optimal route.

[1115] Evacuation route display and audio guidance

[1116] The device displays the evacuation route sent from the server on the app. The user is guided safely using a map display and voice guidance. The user begins evacuation by following the displayed route and the voice guidance. For example, the evacuation route is displayed as a red line on the user's smartphone, and a voice guide is played saying, "Turn right at the next intersection."

[1117] Prompt Sentence Examples

[1118] "I would like to design an application that displays effective evacuation routes in the event of the next natural disaster. Please explain in natural language the specific operation of a system that uses topographical data, river flooding data, data on damage caused by past disasters, and image data to predict the safest and fastest evacuation route and provide it to users."

[1119] In this way, the disaster evacuation route navigation system of the present invention is a system that utilizes various data to predict damage and provides the user with the safest evacuation route, thereby achieving safe and rapid evacuation.

[1120] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1121] Step 1: Get the data

[1122] The server obtains topographical data, river flooding data, past disaster damage data, and image data from external databases and APIs. This allows for efficient collection of necessary disaster information from a variety of data sources. As a specific example, topographical data is obtained from a geographic information system (GIS) and the latest flood data is collected through the API of meteorological agencies.

[1123] Input: Topographical data from geographic information systems (GIS), flood data from meteorological agencies, data on past disaster damage, and image data.

[1124] Output: Raw dataset

[1125] Step 2: Preprocessing the data

[1126] The server integrates and normalizes data acquired in different formats. During this process, it performs preprocessing such as filling in missing values ​​and scaling the data. This creates a unified dataset. For example, it integrates GIS topographical data and flood data, converts them into a single, well-organized dataset, fills in missing values, and standardizes them.

[1127] Input: Raw dataset

[1128] Output: A combined, normalized dataset

[1129] Step 3: Training the AI ​​model and predicting damage

[1130] The server uses the preprocessed data to train AI models such as deep learning. The trained model is then used to predict damage. In this process, the extent of flood impact and the risk of building collapse due to earthquakes are predicted. The strength of building exterior walls is analyzed from image data, and the disaster risk in specific areas is also assessed. As a specific example, past disaster data and Street View image data are used to predict how well a building can withstand an earthquake.

[1131] Input: Unified normalized dataset

[1132] Output: Damage prediction data

[1133] Step 4: Get the user's current location

[1134] When a user launches an app, the device uses GPS to obtain the user's current location. This allows the device to grasp the user's location information in real time. For example, the moment a user launches a smartphone app, current location information is obtained from GPS.

[1135] Input: App launch signal

[1136] Output: Current location data

[1137] Step 5: Submit an evacuation request

[1138] The device sends the acquired current location information to the server and requests it to calculate an evacuation route. This allows the user to respond quickly to the current emergency situation. For example, when a user presses the "Search for evacuation route" button on a smartphone app, the GPS location information is sent to the server.

[1139] Input: Current location data

[1140] Output: Evacuation route calculation request

[1141] Step 6: Evacuation route calculation and risk assessment

[1142] The server calculates the safest and most efficient evacuation route based on the current location information and the location information of the evacuation shelter, taking into account damage prediction data. This allows safe evacuation routes to be provided quickly. For example, in addition to the current location and the location of the evacuation shelter, it calculates a route that avoids areas at risk of flooding and selects the optimal route.

[1143] Input: current location data, evacuation shelter location data, damage prediction data

[1144] Output: Evaluated evacuation route data

[1145] Step 7: Evacuation route display and audio guidance

[1146] The device displays the evaluated evacuation route sent from the server on the app and provides voice guidance. The user begins evacuation by following the displayed route and the voice guidance. For example, the evacuation route is displayed as a red line on the user's smartphone, and a voice guidance is played saying, "Turn right at the next intersection."

[1147] Input: Evaluated evacuation route data

[1148] Output: Displayed evacuation route, audio guidance

[1149] (Application example 1)

[1150] 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."

[1151] Conventional evacuation route navigation systems require users to manually follow designated routes, potentially increasing confusion and anxiety during disasters. This poses a particular challenge for those with mobility issues, such as the elderly and people with disabilities, who find it even more difficult to evacuate safely. Furthermore, there is no fully established system that can quickly provide optimal evacuation routes by taking into account real-time disaster information. There is a need to solve these issues and realize safe and rapid evacuation using autonomous vehicles during disasters.

[1152] 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.

[1153] In this invention, the server includes a means for acquiring topographical data, a means for acquiring river flood data, a means for acquiring past disaster damage data, and a means for acquiring image data. This allows the data to be integrated and normalized. The server also includes a means for predicting damage in the event of a disaster, a means for acquiring a current location, a means for calculating an evacuation route, a means for assessing the risk of the evacuation route, a means for displaying the risk-assessed evacuation route, a means for transmitting the optimal evacuation route to an autonomous vehicle, and a means for causing the autonomous vehicle to autonomously drive based on the evacuation route. This allows the provision of an optimal evacuation route with risk assessed in real time, enabling quick and safe evacuation using an autonomous vehicle.

[1154] "Topography data" refers to data that indicates the detailed structure and characteristics of the topography.

[1155] "River flood data" refers to historical information and forecast data regarding river flooding.

[1156] "Past disaster damage data" is record data of damage caused by disasters that have occurred in the past.

[1157] "Image data" refers to digital image files that contain visual information.

[1158] "Integration" is the process of combining multiple pieces of data into one.

[1159] "Normalization" is the process of aligning data of different formats or scales into a uniform format.

[1160] "Damage prediction in the event of a disaster" means predicting the extent of damage that will occur when a disaster occurs.

[1161] "Current Location" means the current GPS location of a user or motor vehicle.

[1162] An "evacuation route" is a route that will allow you to reach a shelter safely and quickly.

[1163] "Risk assessment" refers to assessing the risk of encountering a disaster in relation to evacuation routes.

[1164] A "risk-assessed evacuation route" is the optimal evacuation route after the risk has been assessed.

[1165] "Send to automated vehicle" means transmitting information from the server to the automated vehicle.

[1166] "Autonomous driving" refers to a vehicle that drives autonomously without the need for human operation.

[1167] As an embodiment of the present invention, a specific example of applying a disaster evacuation route navigation system to an autonomous vehicle will be described. This system is constructed using the following various hardware and software.

[1168] Hardware Configuration

[1169] 1. Server: Collects topographical data, river flooding data, past disaster damage data, and image data, and uses AI models to predict damage. It uses geographic information systems (GIS), weather data APIs, Street View image data, etc.

[1170] 2. Self-driving vehicle: Obtains the user's current location and drives autonomously based on the evacuation route sent from the server. Equipped with a GPS module, on-board computer, and communication module.

[1171] 3. Smartphone: Receives the user's evacuation request, sends the current location to the server, and obtains the evacuation route. Uses an Android or iOS device.

[1172] System Operation Overview

[1173] 1. Data Collection and Normalization:

[1174] The server collects topographical data, river flood data, past disaster damage data, and image data from external APIs. It integrates and normalizes this data. Specifically, it obtains topographical data using GIS and flood data via meteorological data APIs.

[1175] 2. Damage Prediction:

[1176] The server trains an AI model based on the collected data to predict damage during disasters. For example, it uses deep learning to predict the extent of flooding and the risk of building collapse due to earthquakes. It also analyzes the strength of building exterior walls from image data and assesses the risk of disaster within the area.

[1177] 3. Obtaining the user's current location and requesting evacuation:

[1178] When a user launches the smartphone app and requests an evacuation route, the device uses GPS to obtain its current location and sends it to the server.

[1179] 4. Evacuation route calculation:

[1180] The server calculates the safest and quickest evacuation route based on the current location information and the location information of the evacuation shelter, and uses damage prediction data to evaluate the risk of each route and select the optimal route.

[1181] 5. Evacuation route display and automatic driving:

[1182] The calculated optimal evacuation route is displayed on the smartphone and on the autonomous vehicle's screen, and the vehicle automatically begins driving based on this information to guide the user to a safe evacuation site.

[1183] Examples of concrete examples and prompts

[1184] Examples:

[1185] If a user is in Tokyo with a GPS location of (35.6895, 139.6917), they request an evacuation route via their smartphone app. The server calculates a safe route based on the latest flood and earthquake risk data and sends that information to the autonomous vehicle. The vehicle then safely transports the user to an evacuation shelter via the specified route.

[1186] Example prompt sentence:

[1187] "The user's current location is 35.6895, 139.6917 in Tokyo. Please calculate the safest evacuation route from this location and provide instructions to the autonomous vehicle."

[1188] Thus, an embodiment of the present invention provides a system that assesses disaster risk in real time and enables quick and safe evacuation using autonomous vehicles.

[1189] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1190] Step 1:

[1191] The server obtains topographical data, river flooding data, past disaster damage data, and image data from external APIs (for example, GIS and meteorological data APIs). This data is integrated, normalized, and then stored. The input is external data, and the output is an integrated dataset. Specifically, the GIS data contains topographical elevation information, and the meteorological data API provides past flood history and forecast data. This allows data in different formats to be stored on the server in a unified format.

[1192] Step 2:

[1193] Based on the dataset acquired in step 1, the server uses an AI model (e.g., a deep learning model) to predict damage in the event of a disaster. The input is the integrated dataset, and the output is the predicted damage extent and risk assessment data. Specifically, the AI ​​model analyzes the height of the terrain and the structure of buildings to evaluate the risk of damage from floods and earthquakes. This process quantifies the risk within a specific area.

[1194] Step 3:

[1195] A user launches a smartphone app and requests an evacuation route. The device obtains its current location using a GPS module and sends that information to the server. The input is the GPS data of the current location, and the output is an evacuation request to the server. Specifically, when the user taps the evacuation button on the app, the app obtains the GPS data and sends it to the server in real time.

[1196] Step 4:

[1197] The server calculates the optimal evacuation route based on the user's current location, the location information of the evacuation shelter, and the damage information predicted in step 2. This calculation also includes a risk assessment of each route. The inputs are the current location, the location information of the evacuation shelter, and the damage prediction data, and the output is the evaluated optimal evacuation route. Specifically, the server uses the Dijkstra algorithm or the A algorithm to calculate the shortest route with the lowest risk.

[1198] Step 5:

[1199] The optimal evacuation route sent from the server is displayed on the smartphone app on the device and on the display of the autonomous vehicle. The user begins evacuation by following this route, and the autonomous vehicle also automatically begins driving based on this route. The input is data on the optimal evacuation route, and the output is evacuation instructions and driving instructions for the autonomous vehicle. Specifically, the smartphone app displays a map and provides voice guidance, while the autonomous vehicle drives this route autonomously.

[1200] The above are the specific processing steps in the system of the present invention, which enables users to evacuate quickly and safely in the event of a disaster.

[1201] 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.

[1202] As an embodiment of the present invention, a specific configuration and operation of a system that combines a disaster evacuation route navigation system and an emotion engine will be described.

[1203] System Configuration

[1204] The system mainly consists of the following components:

[1205] Server: Acquires topographical data, river flood data, data on damage caused by past disasters, and image data, integrates and normalizes them, and predicts damage.

[1206] Terminal (user's smartphone, etc.): Obtains the user's current location, communicates with the server, and displays evacuation routes.

[1207] Emotion Engine: Recognizes the user's emotional state and adaptively changes navigation methods.

[1208] User: Operate the application and follow the evacuation instructions.

[1209] What the program does

[1210] 1. Data acquisition and preprocessing

[1211] server:

[1212] The server retrieves topographical data, river flood data, past disaster damage data, and image data from external databases and APIs. This data comes in different formats, so it needs to be integrated and normalized.

[1213] Examples:

[1214] The server retrieves topographical data from a geographic information system (GIS) and also retrieves recent flood data using the Japan Meteorological Agency's API.

[1215] 2. Damage prediction using AI models

[1216] server:

[1217] The acquired data is used to train an AI model. For example, deep learning can be used to predict the extent of flood damage or the risk of building collapse due to an earthquake. Furthermore, image data can be used to analyze the strength of building exterior walls and assess the risk of disasters within a specific area.

[1218] Examples:

[1219] The server uses past disaster data and Street View image data to predict how well a particular building will withstand an earthquake.

[1220] 3. Obtaining the user's current location and evacuation request

[1221] Device:

[1222] When a user launches the app, the device obtains its current location using GPS and sends a request to the server to calculate an evacuation route.

[1223] Examples:

[1224] When a user opens the smartphone app and requests an evacuation route, the device sends its current GPS location information to the server.

[1225] 4. Calculating the optimal evacuation route

[1226] server:

[1227] The server calculates the safest and quickest evacuation route based on the current location information and the location information of the evacuation shelter, and uses damage prediction data to evaluate the risk of each route and select the optimal route.

[1228] Examples:

[1229] The server calculates routes that avoid areas with a high risk of flooding and selects the optimal evacuation route based on the evaluation results.

[1230] 5. Display and guidance of evacuation routes

[1231] Device:

[1232] The evacuation route sent from the server is displayed on the device's application, which uses map display and voice guidance to guide the user safely to the evacuation shelter.

[1233] User:

[1234] The user begins evacuation by following this displayed route and follows instructions to secure a safe route.

[1235] Examples:

[1236] The device displays the evacuation route received from the server as a red line on a map and uses voice guidance to give instructions such as "Turn right at the next intersection."

[1237] 6. User Emotion Recognition

[1238] Emotion Engine:

[1239] The device uses a camera and microphone to analyze the user's facial expressions and tone of voice to recognize their emotional state, and this data is collected and analyzed in real time.

[1240] Examples:

[1241] The device's camera recognizes the user's face, and when the emotion engine detects that the user is in a panic, it sends that information to the server.

[1242] 7. Emotionally Adapted Navigation

[1243] Servers and devices:

[1244] Based on the information obtained from the emotion engine, the navigation method is adaptively changed according to the user's emotional state. For example, a user who is not calm will receive more understandable instructions or reassuring messages.

[1245] Examples:

[1246] Based on the analysis results of the emotion engine, the server sends more detailed navigation and voice messages such as "Please stay calm."

[1247] Summary

[1248] In this way, the disaster evacuation route navigation system of the present invention is a system that utilizes various data to predict damage and provide users with the safest evacuation route, and by combining it with an emotion engine, it can provide appropriate navigation according to the user's emotional state. This system enables quick and reliable evacuation in the event of a disaster, improving safety and peace of mind.

[1249] The processing flow will be explained below.

[1250] Step 1:

[1251] Server: Acquisition of various data

[1252] The server retrieves topographical data, river flood data, past disaster damage data, and image data from external databases and APIs. This data includes open data from the Ministry of Land, Infrastructure, Transport and Tourism and the Japan Meteorological Agency, as well as various geographic information systems (GIS).

[1253] Step 2:

[1254] Server: Data integration and normalization

[1255] Since the acquired data is in different formats, it is integrated and normalized within the server, which enables consistent processing across each data set.

[1256] Step 3:

[1257] Server: Training the AI ​​model

[1258] The combined data is used to train AI models, for example using deep learning to create models that predict the extent of flood damage or the risk of building collapse in an earthquake.

[1259] Step 4:

[1260] Server: Building Strength Analysis

[1261] Image data obtained from Street View and other sources is analyzed to evaluate the strength of building exterior walls, making it possible to determine the durability of buildings in a specific area and assess the risk of disasters.

[1262] Step 5:

[1263] Terminal: Obtain current location and request evacuation

[1264] When a user launches the app, the device uses GPS to obtain its current location and sends a request to the server to calculate an evacuation route.

[1265] Step 6:

[1266] Server: Evacuation route calculation

[1267] The server calculates the safest and quickest evacuation route based on the current location information and the location information of the evacuation shelter sent from the device, and performs a risk assessment of each route using damage prediction data.

[1268] Step 7:

[1269] Server: Risk-assessed route selection

[1270] A risk assessment is performed on the calculated evacuation routes, and the safest route is selected from among them.

[1271] Step 8:

[1272] Server: Send risk-assessed route

[1273] The selected evacuation route is sent to the terminal.

[1274] Step 9:

[1275] Terminal: Display of evacuation route

[1276] The device displays the received evacuation route on the user interface, showing a safe evacuation route on a map and providing detailed directions.

[1277] Step 10:

[1278] Emotion Engine: Recognizing user emotions

[1279] The device uses a camera and microphone to analyze the user's facial expressions and tone of voice to recognize their emotional state, and this data is collected and analyzed in real time.

[1280] Step 11:

[1281] Server and Terminal: Emotion-Aware Navigation Adaptation

[1282] Based on information obtained from the emotion engine, the navigation method is adaptively changed depending on the user's emotional state. For example, if the user is panicking, more detailed instructions or reassuring messages are provided.

[1283] Step 12:

[1284] Terminal: Evacuation start and real-time updates

[1285] The user begins evacuation by following the displayed evacuation route. The device periodically communicates with the server to provide the user with the latest evacuation route and instructions according to the situation.

[1286] In this way, the system provides the user with the optimal evacuation route through each step, and the emotion engine provides appropriate navigation according to the user's psychological state.

[1287] Example 2

[1288] 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."

[1289] Conventional disaster evacuation systems are limited to presenting evacuation routes and predicting damage, and do not take into account the user's psychological state, making it difficult to provide appropriate support to users in a panic. Furthermore, there are challenges in predicting damage in real time and optimizing evacuation routes, making it difficult to evacuate quickly and safely.

[1290] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1291] In this invention, the server includes means for acquiring topographical data, means for acquiring river flood data, means for acquiring past disaster damage data, means for acquiring image data, means for integrating and normalizing the above data, means for predicting damage in the event of a disaster, means for acquiring a current location, means for calculating an evacuation route, means for assessing the risk of the evacuation route, means for displaying the risk-assessed evacuation route, means for recognizing the user's emotional state, and means for adaptively changing navigation based on the user's emotional state. This enables damage prediction and optimization of evacuation routes in real time, and further provides appropriate navigation according to the user's emotional state.

[1292] "Topography data" refers to data that includes information about the characteristics and shape of the topography.

[1293] "River flood data" refers to data that includes information on the state of rising water levels and flooding of rivers.

[1294] "Past disaster damage data" refers to data that includes records and statistical information on the damage caused by disasters that have occurred in the past.

[1295] "Image data" refers to visual information such as photographs and videos recorded in digital format.

[1296] "Integration and normalization means" refers to techniques and methods for converting data in different formats into a consistent format and unifying the data.

[1297] "Means for predicting damage in the event of a disaster" refers to technologies and methods for predicting the scope and extent of damage in the event of a disaster based on various data.

[1298] "Means for obtaining current location" refers to techniques or methods for determining a user's current physical location using GPS or other location information technology.

[1299] "Means for calculating an evacuation route" refers to a technique or method for calculating the optimal evacuation route based on the user's current location and the location of the evacuation destination.

[1300] "Means for assessing risk" refers to techniques and methods for analyzing disaster risks that exist for evacuation routes and assessing the level of those risks.

[1301] "Means for displaying risk-assessed evacuation routes" refers to techniques or methods for presenting risk-assessed evacuation routes to users by using maps, screen displays, or the like.

[1302] "Means for recognizing a user's emotional state" refers to technology or methods for analyzing and recognizing a user's emotions based on information obtained from a camera, microphone, etc.

[1303] "Means for adaptively changing navigation" refers to techniques and methods for changing and providing navigation instructions according to the emotional state of the user.

[1304] The present invention will now be described with reference to the specific configuration and operation of a system that combines a disaster evacuation route navigation system and an emotion engine.

[1305] System Configuration

[1306] The system mainly consists of the following components:

[1307] Server: Acquires topographical data, river flood data, past disaster damage data, and image data, integrates and normalizes them, and predicts damage.

[1308] Terminal (user's smartphone, etc.): Obtains the user's current location, communicates with the server, and displays evacuation routes.

[1309] Emotion Engine: Recognizes the user's emotional state and adaptively changes navigation methods.

[1310] User: Operate the application and follow the evacuation instructions.

[1311] Data acquisition and preprocessing

[1312] server:

[1313] The server retrieves topographical data, river flood data, past disaster damage data, and image data from external databases and APIs. This data comes in different formats and needs to be integrated and normalized.

[1314] Specifically, it obtains topographical data from a geographic information system (GIS) and also obtains the latest flood data using the Japan Meteorological Agency's API.

[1315] Damage prediction

[1316] server:

[1317] Using the acquired data, a deep learning framework (e.g., TensorFlow) is used to train an AI model that predicts the extent of flood damage and the risk of building collapse due to an earthquake.

[1318] It also analyzes image data to assess the strength of building exterior walls and assess disaster risk within specific areas.

[1319] Obtaining the user's current location and evacuation request

[1320] Device:

[1321] When a user launches the app, the device's GPS acquires the current location and sends a request to the server to calculate an evacuation route.

[1322] Evacuation route calculation

[1323] server:

[1324] The server calculates the safest and quickest evacuation route based on the current location information and the location information of the evacuation shelter, and uses damage prediction data to evaluate the risk of each route and select the optimal route.

[1325] For example, the server calculates routes that avoid areas at high risk of flooding.

[1326] Evacuation route display and guidance

[1327] Device:

[1328] The evacuation route information sent from the server is displayed on the device's application, which uses map display and voice guidance to guide the user safely to an evacuation shelter.

[1329] User:

[1330] The user begins evacuation by following the displayed route and follows instructions to secure a safe route.

[1331] Specifically, the device displays the evacuation route received from the server as a red line on a map and issues voice guidance such as "Turn right at the next intersection."

[1332] User Emotion Recognition

[1333] Emotion Engine:

[1334] The device's camera and microphone are used to analyze the user's facial expressions and tone of voice to recognize their emotional state. This data is collected in real time and sent to a server.

[1335] For example, the device's camera recognizes the user's face and the emotion engine detects that the user is in a panic.

[1336] Emotionally adaptive navigation

[1337] Servers and devices:

[1338] Based on information obtained from the emotion engine, the navigation method is adaptively changed according to the user's emotional state. Users who are not calm are given clearer instructions and reassuring messages.

[1339] For example, the server sends a voice message such as "Please stay calm" to the terminal.

[1340] Prompt Sentence Examples

[1341] If the user's escape route is blocked by water, generate the following prompt:

[1342] "Currently, some roads are impassable due to flooding. If you are in a state of panic, please remain calm and follow the instructions below to continue evacuating."

[1343] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1344] Step 1: Data acquisition and preprocessing

[1345] server:

[1346] Input: topographical data, river flood data, past disaster damage data, image data

[1347] Output: Uniform format dataset

[1348] Specific behavior:

[1349] 1. The server retrieves terrain data from a geographic information system (GIS).

[1350] 2. Call the Japan Meteorological Agency's API to obtain the latest flood data.

[1351] 3. Obtain past disaster damage data and Street View image data from the database.

[1352] 4. The various data acquired are integrated and a normalization algorithm is applied to unify the format.

[1353] Step 2: Training and applying an AI model for damage prediction

[1354] server:

[1355] Input: Normalized dataset

[1356] Output: Damage prediction data

[1357] Specific behavior:

[1358] 1. Train an AI model using a deep learning framework (e.g., TensorFlow) based on the normalized dataset.

[1359] 2. Use trained AI models to predict the extent of flood damage and the risk of building collapse due to earthquakes.

[1360] 3. Analyze Street View image data and evaluate the strength of building exterior walls to assess disaster risk within a specific area.

[1361] Step 3: Get current location and send evacuation request

[1362] Device:

[1363] Input: User operation (app launch), GPS data

[1364] Output: Current location information

[1365] Specific behavior:

[1366] 1. The user launches the app.

[1367] 2. The device uses GPS to obtain its current location.

[1368] 3. Send the current location information to the server along with a request for evacuation route calculation.

[1369] Step 4: Calculate evacuation routes

[1370] server:

[1371] Input: current location information, evacuation shelter location information, damage prediction data

[1372] Output: Optimal evacuation route

[1373] Specific behavior:

[1374] 1. Generate multiple evacuation routes based on current location information and evacuation shelter location information.

[1375] 2. Use damage forecast data to assess the risk of each evacuation route.

[1376] 3. Based on the evaluation results, select the safest, fastest and most optimal evacuation route.

[1377] Step 5: Display and guide evacuation routes

[1378] Device:

[1379] Input: Optimal evacuation route data

[1380] Output: Map display and voice guidance

[1381] Specific behavior:

[1382] 1. Display the evacuation route information received from the server in the app's map module.

[1383] 2. The route will be displayed on the map with a red line, and a voice guidance will begin guiding you, saying, "Turn right at the next intersection."

[1384] User:

[1385] Input: Map display and voice guidance

[1386] Output: Evacuation execution and direction correction

[1387] Specific behavior:

[1388] 1. Check the route on the map and start moving.

[1389] 2. Correct your direction according to the voice guidance and map information.

[1390] Step 6: Recognizing User Emotions

[1391] Emotion Engine:

[1392] Input: Camera video, microphone audio

[1393] Output: Emotion recognition data

[1394] Specific behavior:

[1395] 1. The device camera captures the user's face and performs image analysis.

[1396] 2. The microphone collects the user's voice and the emotion engine analyzes the tone and content.

[1397] 3. Send the results to the server in real time.

[1398] Step 7: Adapt navigation based on emotions

[1399] Servers and devices:

[1400] Input: Emotion recognition data

[1401] Output: Adaptive navigation instructions

[1402] Specific behavior:

[1403] 1. The emotion engine recognizes the user's emotional state (e.g., panicked, calm).

[1404] 2. The server receives the analysis results and adjusts the voice guidance and message content.

[1405] 3. Send a reassuring voice message to the device, such as "Please stay calm."

[1406] (Application example 2)

[1407] 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."

[1408] Conventional disaster evacuation navigation systems simply calculate and present evacuation routes, but are unable to adapt to the user's emotional state during evacuation. This makes it difficult to provide appropriate support to users who are confused or panicked, which can result in delays in evacuation. In contrast, the present invention aims to promote quick and safe evacuation by recognizing the user's emotional state and adaptively changing the navigation method according to that state.

[1409] 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.

[1410] In this invention, the server includes a means for acquiring topographical data, a means for acquiring river flood data, and a means for acquiring past disaster damage data. This allows for the integration and normalization of various data, enabling damage prediction in the event of a disaster. The server also includes a means for acquiring a current location, a means for calculating an evacuation route, a means for assessing the risk of the evacuation route, a means for displaying the risk-assessed evacuation route, a means for recognizing a user's emotional state, and a means for adaptively changing the navigation method based on the recognized emotional state. This allows for the server to provide appropriate navigation according to the user's emotional state, supporting a quick and safe evacuation.

[1411] "Topographic data" refers to data that includes information on the shape and distribution of natural and artificial structures.

[1412] "River flood data" refers to data that includes information on water levels and the extent of damage when rivers flood.

[1413] "Past disaster damage data" refers to data that includes information on the type and extent of damage caused by disasters that have occurred in the past.

[1414] "Image data" is data that represents visual information in digital form.

[1415] "Emotional state" refers to an individual's internal feelings and moods, and is information acquired through sensors such as cameras and microphones.

[1416] "Navigation method" refers to the means of instructions or guidance for navigating a route to a destination.

[1417] "Current location" is the user's current geographical location information.

[1418] An "evacuation route" is a route for safe evacuation in the event of a disaster.

[1419] "Risk assessment" is the process of assessing the degree of danger that may arise under specific conditions.

[1420] "Normalization" is a data processing technique that standardizes data in different formats and units to make them easier to compare.

[1421] A "server" is a computer system that acquires and integrates various data and provides services to multiple clients.

[1422] As an embodiment of the present invention, a specific example of a security service application for smartphones is shown below. This application provides navigation for the user to safely evacuate in the event of a disaster, and furthermore, adaptively changes the navigation method according to the user's emotional state.

[1423] System Configuration

[1424] The system of the present invention mainly comprises the following components:

[1425] 1. Server

[1426] Data acquisition and preprocessing

[1427] The server uses a geographic information system (GIS) and the API of the Japan Meteorological Agency to obtain topographical data, river flood data, and past disaster damage data. Because this data is provided in different formats, it is unified and normalized.

[1428] 2. Device (smartphone)

[1429] Current location acquisition and evacuation request

[1430] When a user launches the app, it uses the smartphone's GPS function to obtain the user's current location and requests the server to calculate an evacuation route.

[1431] Evacuation route display and guidance

[1432] The evacuation route sent from the server is displayed on the smartphone application, and the user is guided using a map and voice guidance.

[1433] 3. Emotion Engine

[1434] User Emotion Recognition

[1435] The system uses the smartphone's camera and microphone to analyze the user's emotional state in real time and transmits the data to a server.

[1436] Emotionally adaptive navigation

[1437] The server optimizes the navigation method based on the emotional state and sends reassuring messages to the user.

[1438] Data processing and calculation

[1439] The system of the present invention performs the following data processing and data calculations:

[1440] 1. Data acquisition and preprocessing (server)

[1441] The server obtains topographical data, river flooding data, and past disaster damage data from GIS and the Japan Meteorological Agency's API. For example, topographical data is obtained from GIS, and river flooding data is obtained from the Japan Meteorological Agency's API. This data is converted into a unified format and normalized.

[1442] 2. Damage Prediction (Server)

[1443] The server uses the collected data to predict disaster risks using deep learning frameworks such as TensorFlow, for example, by calculating the risk of flooding or building collapse based on past disaster data and current conditions.

[1444] 3. Evacuation route calculation (server)

[1445] It obtains the user's current location information and calculates the optimal evacuation route, using an algorithm to avoid dangerous areas.

[1446] 4. Evacuation route display and guidance (terminal)

[1447] The evacuation route sent from the server is displayed on a map on the smartphone, and a voice guidance function is also provided, allowing users to receive instructions such as "Turn right at the next intersection."

[1448] 5. Emotion Recognition (Device, Emotion Engine)

[1449] Using the smartphone's camera and microphone, the system analyzes the user's facial expressions and tone of voice to recognize their emotional state. For example, if the user is in a panic state, the system detects this and sends it to the server.

[1450] 6. Adaptation of navigation methods (server, terminal)

[1451] The navigation method is optimized based on the results of emotion analysis. For example, if the user is in a panic, the server will send a reassuring message such as, "Please stay calm. We are calculating the quickest route to the evacuation shelter."

[1452] Specific examples

[1453] When a user opens a smartphone app and requests an evacuation route, the device sends its current GPS location information to the server. The server uses this information to calculate the optimal evacuation route and sends it to the device. The device displays the route on a map and navigates the user using voice guidance. If the user panics during evacuation, the camera detects this and sends it to the server in real time. The server adaptively changes the navigation message based on the user's emotional state, sending a message such as "Please stay calm."

[1454] Prompt Sentence Examples

[1455] 1. "Please remain calm. We are calculating the quickest route to the evacuation center."

[1456] 2. "Take a deep breath. Turn right at the next intersection."

[1457] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1458] Step 1:

[1459] Data acquisition and preprocessing (server)

[1460] The server obtains topographical data, river flooding data, and past disaster damage data from a geographic information system (GIS) and the Japan Meteorological Agency's API. Specifically, it downloads topographical data from the GIS and collects recent flood data using the Japan Meteorological Agency's API. Because these data are provided in different formats, they are converted into a unified format and normalized. The input is various types of data, and the output is integrated, normalized data.

[1461] Step 2:

[1462] Damage prediction (server)

[1463] The server uses a deep learning model (e.g., TensorFlow) based on the acquired data to predict disaster risk. Specifically, it trains the model using past disaster data and integrated data, and uses current data as input to predict the extent of damage and the risk of building collapse. The input is integrated, normalized data, and the output is a predicted disaster risk map.

[1464] Step 3:

[1465] Current location acquisition and evacuation request (terminal)

[1466] When a user launches the app, it uses the smartphone's GPS to obtain current location information. This location information is sent to the server, which then requests evacuation route calculation. The input is the user's current GPS coordinates, and the output is the request sent to the server.

[1467] Step 4:

[1468] Evacuation route calculation (server)

[1469] The server uses the received current location information and evacuation shelter location information to calculate the optimal evacuation route. Based on the obtained disaster risk map, it evaluates the risk of each route and selects the safest route. The input is the user's current location and the evacuation shelter location information, and the output is the evaluated evacuation route.

[1470] Step 5:

[1471] Evacuation route display and guidance (terminal)

[1472] The evacuation route sent from the server is displayed as a map on the smartphone application, and a voice guidance function is used to provide the user with specific instructions such as "Turn right at the next intersection." The input is the evaluated evacuation route, and the output is a map showing the route and voice guidance.

[1473] Step 6:

[1474] User emotion recognition (device)

[1475] Using the smartphone's camera and microphone, the system analyzes the user's facial expressions and tone of voice to recognize their emotional state. This is done in real time, and the results are sent to a server. The input is the user's facial expressions and tone of voice, and the output is the analyzed emotional state data.

[1476] Step 7:

[1477] Adaptation of navigation methods (server, terminal)

[1478] The server optimizes the navigation method based on the results of emotion analysis. For example, if the user is in a panic state, the server generates a reassuring message such as "Please stay calm. We are calculating the fastest route to the evacuation shelter," and sends it to the device. The input is the analyzed emotional state data, and the output is an adaptively modified navigation message.

[1479] 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.

[1480] 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.

[1481] 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.

[1482] [Fourth embodiment]

[1483] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1484] 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.

[1485] 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).

[1486] 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.

[1487] 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.

[1488] 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).

[1489] 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.

[1490] 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.

[1491] 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.

[1492] 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.

[1493] 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.

[1494] 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.

[1495] 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."

[1496] As an embodiment of the present invention, the system configuration of a disaster evacuation route navigation system and its specific operation will be described.

[1497] System Configuration

[1498] The system mainly consists of the following components:

[1499] Server: Acquires topographical data, river flood data, data on damage caused by past disasters, and image data, integrates and normalizes them, and predicts damage.

[1500] Terminal (user's smartphone, etc.): Obtains the user's current location, communicates with the server, and displays evacuation routes.

[1501] User: Operate the application and follow the evacuation instructions.

[1502] What the program does

[1503] 1. Data acquisition and preprocessing

[1504] server:

[1505] The server retrieves topographical data, river flood data, past disaster damage data, and image data from external databases and APIs. This data comes in different formats and needs to be integrated and normalized.

[1506] Examples:

[1507] The server retrieves topographical data from a geographic information system (GIS) and also retrieves recent flood data using the Japan Meteorological Agency's API.

[1508] 2. Damage prediction using AI models

[1509] server:

[1510] The acquired data is used to train an AI model. For example, deep learning can be used to predict the extent of flood damage or the risk of building collapse due to an earthquake. Furthermore, image data can be used to analyze the strength of building exterior walls and assess the risk of disasters within a specific area.

[1511] Examples:

[1512] The server uses past disaster data and Street View image data to predict how well a particular building will withstand an earthquake.

[1513] 3. Obtaining the user's current location and evacuation request

[1514] Device:

[1515] When a user launches the app, the device acquires its current location using GPS, which is then sent to the server, which requests the calculation of an evacuation route.

[1516] Examples:

[1517] When a user opens the smartphone app and requests an evacuation route, the device sends its current GPS location information to the server.

[1518] 4. Calculating the optimal evacuation route

[1519] server:

[1520] The server calculates the safest and quickest evacuation route based on the current location information and the location information of the evacuation shelter, and uses damage prediction data to evaluate the risk of each route and select the optimal route.

[1521] Examples:

[1522] The server calculates routes that avoid areas with a high risk of flooding and selects the optimal evacuation route based on the evaluation results.

[1523] 5. Display and guidance of evacuation routes

[1524] Device:

[1525] The evacuation route sent from the server is displayed on the device's application, which uses map display and voice guidance to guide the user safely to the evacuation shelter.

[1526] User:

[1527] The user begins evacuation by following this displayed route and follows instructions to secure a safe route.

[1528] Examples:

[1529] The device displays the evacuation route received from the server as a red line on a map and uses voice guidance to give instructions such as "Turn right at the next intersection."

[1530] Summary

[1531] In this way, the disaster evacuation route navigation system of the present invention is a system that utilizes various data to predict damage and provides users with the safest evacuation route, thereby enabling quick and reliable evacuation even in the event of a disaster, thereby improving safety.

[1532] The processing flow will be explained below.

[1533] Step 1:

[1534] Server: Acquisition of various data

[1535] The server obtains topographical data, river flood data, past disaster damage data, and image data from external databases and APIs, including the API of the Ministry of Land, Infrastructure, Transport and Tourism, open data from the Japan Meteorological Agency, and satellite images.

[1536] Step 2:

[1537] Server: Data integration and normalization

[1538] The acquired data has different formats, so it is integrated and normalized within the server, which enables consistent processing across different data sets.

[1539] Step 3:

[1540] Server: Training the AI ​​model

[1541] The combined data is used to train AI models such as deep learning models, for example to predict the extent of flood damage or the risk of building collapse due to earthquakes.

[1542] Step 4:

[1543] Server: Building Strength Analysis

[1544] The server analyzes the image data and evaluates the strength of the building's exterior walls, making it possible to assess the durability of buildings within a specific area.

[1545] Step 5:

[1546] Terminal: Obtain current location and request evacuation

[1547] When a user launches the app, the device obtains its current location using GPS and sends a request to the server to calculate an evacuation route.

[1548] Step 6:

[1549] Server: Evacuation route calculation

[1550] The server calculates the shortest and safest evacuation route based on the current location information and the location information of the evacuation shelter sent from the device. During this process, it performs a risk assessment using damage prediction data to confirm safety.

[1551] Step 7:

[1552] Server: Risk-assessed route selection

[1553] A risk assessment is performed on the calculated multiple evacuation routes, and the safest route is selected.

[1554] Step 8:

[1555] Server: Send risk-assessed route

[1556] The selected evacuation route is sent to the terminal.

[1557] Step 9:

[1558] Terminal: Display of evacuation route

[1559] The device displays the received evacuation route on the user interface, showing the route in red on a map and providing detailed directions.

[1560] Step 10:

[1561] User: Evacuation initiation

[1562] The user begins evacuation by following the displayed evacuation route and following the instructions on the device to safely and quickly reach a shelter.

[1563] Step 11:

[1564] Device: Real-time updates

[1565] If the disaster situation changes, the device will periodically communicate with the server to obtain the latest evacuation routes, providing the optimal route even during evacuation.

[1566] In this way, this system provides users with the optimal evacuation route through each step, supporting safe evacuation in the event of a disaster.

[1567] Example 1

[1568] 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."

[1569] In recent years, natural disasters have become more frequent, and many people are seeking safe evacuation methods. However, conventional evacuation systems do not adequately provide real-time damage predictions or appropriate evacuation routes, making it difficult to ensure rapid and reliable evacuation. In addition, there is a lack of systems that can accurately assess disaster risks and provide optimal evacuation routes based on those assessments. Therefore, there is a need for a system that enables safe and rapid evacuation even in the event of a disaster.

[1570] 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.

[1571] In this invention, the server includes means for acquiring topographical data, means for acquiring river flood data, means for acquiring past disaster damage data, means for acquiring image data, means for integrating and normalizing the above data, means for predicting damage in the event of a disaster, means for acquiring the user's current location, means for calculating an evacuation route, means for assessing the risk of the evacuation route, and means for displaying and providing audio guidance on the risk-assessed evacuation route. This makes it possible to accurately predict damage based on the various acquired data and provide the optimal evacuation route.

[1572] "Topographic data" refers to information about the shape of the Earth's surface, and is obtained from geographic information systems, maps, etc.

[1573] "River flood data" refers to past and current information on river flooding, including data on water levels and flooded areas.

[1574] "Past disaster damage data" refers to information on the damage and damage situation caused by past natural disasters.

[1575] "Image data" refers to visual information such as photographs and videos, and is used to analyze the strength of building exterior walls, etc.

[1576] "Integration" refers to the process of bringing together data of different formats and types into a single data set.

[1577] "Normalization" refers to the process of adjusting acquired data according to certain standards to make it consistent.

[1578] "Means for predicting damage" refers to systems or algorithms that use acquired data to predict damage in the event of a disaster.

[1579] "Means for obtaining current location" refers to technologies such as GPS for obtaining user location information.

[1580] "Means for calculating evacuation routes" refers to a system or software that calculates the optimal route from the user's current location to an evacuation shelter.

[1581] "Means for assessing risk" refers to systems or algorithms for assessing disaster risk against calculated evacuation routes.

[1582] "Means for displaying and providing audio guidance on risk-assessed evacuation routes" means a system or application for displaying risk-assessed evacuation routes on a user's device and providing audio guidance.

[1583] System Configuration

[1584] The present invention is a system that mainly comprises the following elements:

[1585] Server: Acquires topographical data, river flooding data, data on damage caused by past disasters, and image data, integrates and normalizes this data, and predicts damage in the event of a disaster.

[1586] Terminal (user's smartphone, etc.): Obtains the user's current location, communicates with the server to display evacuation routes, and provides voice guidance.

[1587] User: Operate the application and follow the evacuation instructions.

[1588] What the program does

[1589] Data Acquisition

[1590] The server obtains topographical data, river flooding data, past disaster damage data, and image data from external databases and APIs. Specifically, it can obtain topographical data from a geographic information system (GIS) and flood data using the Japan Meteorological Agency's API.

[1591] Data Preprocessing

[1592] The server integrates and normalizes the acquired data, and performs preprocessing such as filling in missing values ​​and scaling the data. For example, it integrates GIS topographical data and flood data into a single dataset and fills in missing items.

[1593] AI model training and damage prediction

[1594] The server trains an AI model based on the preprocessed data. Using techniques such as deep learning, it predicts the extent of flood impact and the risk of building collapse due to earthquakes. It also uses image data to analyze the strength of building exterior walls and assess the disaster risk in specific areas. For example, it uses past disaster data and Street View image data to predict how well buildings in a particular area can withstand an earthquake.

[1595] Get the user's current location

[1596] When a user launches an app, the device uses GPS to obtain the user's current location. This means that the moment a user launches a smartphone app, current location information is obtained from GPS.

[1597] Submitting an evacuation request

[1598] The device sends the acquired current location information to the server and requests it to calculate an evacuation route. When the user presses the "Search for evacuation route" button on the smartphone app, the GPS location information is sent to the server.

[1599] Evacuation route calculation and risk assessment

[1600] The server calculates the safest and most efficient evacuation route based on the current location information and the location of the evacuation shelter, taking into account damage prediction data. For example, it calculates a route that avoids areas at risk of flooding in addition to the current location and the location of the evacuation shelter, and selects the optimal route.

[1601] Evacuation route display and audio guidance

[1602] The device displays the evacuation route sent from the server on the app. The user is guided safely using a map display and voice guidance. The user begins evacuation by following the displayed route and the voice guidance. For example, the evacuation route is displayed as a red line on the user's smartphone, and a voice guide is played saying, "Turn right at the next intersection."

[1603] Prompt Sentence Examples

[1604] "I would like to design an application that displays effective evacuation routes in the event of the next natural disaster. Please explain in natural language the specific operation of a system that uses topographical data, river flooding data, data on damage caused by past disasters, and image data to predict the safest and fastest evacuation route and provide it to users."

[1605] In this way, the disaster evacuation route navigation system of the present invention is a system that utilizes various data to predict damage and provides the user with the safest evacuation route, thereby achieving safe and rapid evacuation.

[1606] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1607] Step 1: Get the data

[1608] The server obtains topographical data, river flooding data, past disaster damage data, and image data from external databases and APIs. This allows for efficient collection of necessary disaster information from a variety of data sources. As a specific example, topographical data is obtained from a geographic information system (GIS) and the latest flood data is collected through the API of meteorological agencies.

[1609] Input: Topographical data from geographic information systems (GIS), flood data from meteorological agencies, data on past disaster damage, and image data.

[1610] Output: Raw dataset

[1611] Step 2: Preprocessing the data

[1612] The server integrates and normalizes data acquired in different formats. During this process, it performs preprocessing such as filling in missing values ​​and scaling the data. This creates a unified dataset. For example, it integrates GIS topographical data and flood data, converts them into a single, well-organized dataset, fills in missing values, and standardizes them.

[1613] Input: Raw dataset

[1614] Output: A combined, normalized dataset

[1615] Step 3: Training the AI ​​model and predicting damage

[1616] The server uses the preprocessed data to train AI models such as deep learning. The trained model is then used to predict damage. In this process, the extent of flood impact and the risk of building collapse due to earthquakes are predicted. The strength of building exterior walls is analyzed from image data, and the disaster risk in specific areas is also assessed. As a specific example, past disaster data and Street View image data are used to predict how well a building can withstand an earthquake.

[1617] Input: Unified normalized dataset

[1618] Output: Damage prediction data

[1619] Step 4: Get the user's current location

[1620] When a user launches an app, the device uses GPS to obtain the user's current location. This allows the device to grasp the user's location information in real time. For example, the moment a user launches a smartphone app, current location information is obtained from GPS.

[1621] Input: App launch signal

[1622] Output: Current location data

[1623] Step 5: Submit an evacuation request

[1624] The device sends the acquired current location information to the server and requests it to calculate an evacuation route. This allows the user to respond quickly to the current emergency situation. For example, when a user presses the "Search for evacuation route" button on a smartphone app, the GPS location information is sent to the server.

[1625] Input: Current location data

[1626] Output: Evacuation route calculation request

[1627] Step 6: Evacuation route calculation and risk assessment

[1628] The server calculates the safest and most efficient evacuation route based on the current location information and the location information of the evacuation shelter, taking into account damage prediction data. This allows safe evacuation routes to be provided quickly. For example, in addition to the current location and the location of the evacuation shelter, it calculates a route that avoids areas at risk of flooding and selects the optimal route.

[1629] Input: current location data, evacuation shelter location data, damage prediction data

[1630] Output: Evaluated evacuation route data

[1631] Step 7: Evacuation route display and audio guidance

[1632] The device displays the evaluated evacuation route sent from the server on the app and provides voice guidance. The user begins evacuation by following the displayed route and the voice guidance. For example, the evacuation route is displayed as a red line on the user's smartphone, and a voice guidance is played saying, "Turn right at the next intersection."

[1633] Input: Evaluated evacuation route data

[1634] Output: Displayed evacuation route, audio guidance

[1635] (Application example 1)

[1636] 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."

[1637] Conventional evacuation route navigation systems require users to manually follow designated routes, potentially increasing confusion and anxiety during disasters. This poses a particular challenge for those with mobility issues, such as the elderly and people with disabilities, who find it even more difficult to evacuate safely. Furthermore, there is no fully established system that can quickly provide optimal evacuation routes by taking into account real-time disaster information. There is a need to solve these issues and realize safe and rapid evacuation using autonomous vehicles during disasters.

[1638] 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.

[1639] In this invention, the server includes a means for acquiring topographical data, a means for acquiring river flood data, a means for acquiring past disaster damage data, and a means for acquiring image data. This allows the data to be integrated and normalized. The server also includes a means for predicting damage in the event of a disaster, a means for acquiring a current location, a means for calculating an evacuation route, a means for assessing the risk of the evacuation route, a means for displaying the risk-assessed evacuation route, a means for transmitting the optimal evacuation route to an autonomous vehicle, and a means for causing the autonomous vehicle to autonomously drive based on the evacuation route. This allows the provision of an optimal evacuation route with risk assessed in real time, enabling quick and safe evacuation using an autonomous vehicle.

[1640] "Topography data" refers to data that indicates the detailed structure and characteristics of the topography.

[1641] "River flood data" refers to historical information and forecast data regarding river flooding.

[1642] "Past disaster damage data" is record data of damage caused by disasters that have occurred in the past.

[1643] "Image data" refers to digital image files that contain visual information.

[1644] "Integration" is the process of combining multiple pieces of data into one.

[1645] "Normalization" is the process of aligning data of different formats or scales into a uniform format.

[1646] "Damage prediction in the event of a disaster" means predicting the extent of damage that will occur when a disaster occurs.

[1647] "Current Location" means the current GPS location of a user or motor vehicle.

[1648] An "evacuation route" is a route that will allow you to reach a shelter safely and quickly.

[1649] "Risk assessment" refers to assessing the risk of encountering a disaster in relation to evacuation routes.

[1650] A "risk-assessed evacuation route" is the optimal evacuation route after the risk has been assessed.

[1651] "Send to automated vehicle" means transmitting information from the server to the automated vehicle.

[1652] "Autonomous driving" refers to a vehicle that drives autonomously without the need for human operation.

[1653] As an embodiment of the present invention, a specific example of applying a disaster evacuation route navigation system to an autonomous vehicle will be described. This system is constructed using the following various hardware and software.

[1654] Hardware Configuration

[1655] 1. Server: Collects topographical data, river flooding data, past disaster damage data, and image data, and uses AI models to predict damage. It uses geographic information systems (GIS), weather data APIs, Street View image data, etc.

[1656] 2. Self-driving vehicle: Obtains the user's current location and drives autonomously based on the evacuation route sent from the server. Equipped with a GPS module, on-board computer, and communication module.

[1657] 3. Smartphone: Receives the user's evacuation request, sends the current location to the server, and obtains the evacuation route. Uses an Android or iOS device.

[1658] System Operation Overview

[1659] 1. Data Collection and Normalization:

[1660] The server collects topographical data, river flood data, past disaster damage data, and image data from external APIs. It integrates and normalizes this data. Specifically, it obtains topographical data using GIS and flood data via meteorological data APIs.

[1661] 2. Damage Prediction:

[1662] The server trains an AI model based on the collected data to predict damage during disasters. For example, it uses deep learning to predict the extent of flooding and the risk of building collapse due to earthquakes. It also analyzes the strength of building exterior walls from image data and assesses the risk of disaster within the area.

[1663] 3. Obtaining the user's current location and requesting evacuation:

[1664] When a user launches the smartphone app and requests an evacuation route, the device uses GPS to obtain its current location and sends it to the server.

[1665] 4. Evacuation route calculation:

[1666] The server calculates the safest and quickest evacuation route based on the current location information and the location information of the evacuation shelter, and uses damage prediction data to evaluate the risk of each route and select the optimal route.

[1667] 5. Evacuation route display and automatic driving:

[1668] The calculated optimal evacuation route is displayed on the smartphone and on the autonomous vehicle's screen, and the vehicle automatically begins driving based on this information to guide the user to a safe evacuation site.

[1669] Examples of concrete examples and prompts

[1670] Examples:

[1671] If a user is in Tokyo with a GPS location of (35.6895, 139.6917), they request an evacuation route via their smartphone app. The server calculates a safe route based on the latest flood and earthquake risk data and sends that information to the autonomous vehicle. The vehicle then safely transports the user to an evacuation shelter via the specified route.

[1672] Example prompt sentence:

[1673] "The user's current location is 35.6895, 139.6917 in Tokyo. Please calculate the safest evacuation route from this location and provide instructions to the autonomous vehicle."

[1674] Thus, an embodiment of the present invention provides a system that assesses disaster risk in real time and enables quick and safe evacuation using autonomous vehicles.

[1675] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1676] Step 1:

[1677] The server obtains topographical data, river flooding data, past disaster damage data, and image data from external APIs (for example, GIS and meteorological data APIs). This data is integrated, normalized, and then stored. The input is external data, and the output is an integrated dataset. Specifically, the GIS data contains topographical elevation information, and the meteorological data API provides past flood history and forecast data. This allows data in different formats to be stored on the server in a unified format.

[1678] Step 2:

[1679] Based on the dataset acquired in step 1, the server uses an AI model (e.g., a deep learning model) to predict damage in the event of a disaster. The input is the integrated dataset, and the output is the predicted damage extent and risk assessment data. Specifically, the AI ​​model analyzes the height of the terrain and the structure of buildings to evaluate the risk of damage from floods and earthquakes. This process quantifies the risk within a specific area.

[1680] Step 3:

[1681] A user launches a smartphone app and requests an evacuation route. The device obtains its current location using a GPS module and sends that information to the server. The input is the GPS data of the current location, and the output is an evacuation request to the server. Specifically, when the user taps the evacuation button on the app, the app obtains the GPS data and sends it to the server in real time.

[1682] Step 4:

[1683] The server calculates the optimal evacuation route based on the user's current location, the location information of the evacuation shelter, and the damage information predicted in step 2. This calculation also includes a risk assessment of each route. The inputs are the current location, the location information of the evacuation shelter, and the damage prediction data, and the output is the evaluated optimal evacuation route. Specifically, the server uses the Dijkstra algorithm or the A algorithm to calculate the shortest route with the lowest risk.

[1684] Step 5:

[1685] The optimal evacuation route sent from the server is displayed on the smartphone app on the device and on the display of the autonomous vehicle. The user begins evacuation by following this route, and the autonomous vehicle also automatically begins driving based on this route. The input is data on the optimal evacuation route, and the output is evacuation instructions and driving instructions for the autonomous vehicle. Specifically, the smartphone app displays a map and provides voice guidance, while the autonomous vehicle drives this route autonomously.

[1686] The above are the specific processing steps in the system of the present invention, which enables users to evacuate quickly and safely in the event of a disaster.

[1687] 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.

[1688] As an embodiment of the present invention, a specific configuration and operation of a system that combines a disaster evacuation route navigation system and an emotion engine will be described.

[1689] System Configuration

[1690] The system mainly consists of the following components:

[1691] Server: Acquires topographical data, river flood data, data on damage caused by past disasters, and image data, integrates and normalizes them, and predicts damage.

[1692] Terminal (user's smartphone, etc.): Obtains the user's current location, communicates with the server, and displays evacuation routes.

[1693] Emotion Engine: Recognizes the user's emotional state and adaptively changes navigation methods.

[1694] User: Operate the application and follow the evacuation instructions.

[1695] What the program does

[1696] 1. Data acquisition and preprocessing

[1697] server:

[1698] The server retrieves topographical data, river flood data, past disaster damage data, and image data from external databases and APIs. This data comes in different formats, so it needs to be integrated and normalized.

[1699] Examples:

[1700] The server retrieves topographical data from a geographic information system (GIS) and also retrieves recent flood data using the Japan Meteorological Agency's API.

[1701] 2. Damage prediction using AI models

[1702] server:

[1703] The acquired data is used to train an AI model. For example, deep learning can be used to predict the extent of flood damage or the risk of building collapse due to an earthquake. Furthermore, image data can be used to analyze the strength of building exterior walls and assess the risk of disasters within a specific area.

[1704] Examples:

[1705] The server uses past disaster data and Street View image data to predict how well a particular building will withstand an earthquake.

[1706] 3. Obtaining the user's current location and evacuation request

[1707] Device:

[1708] When a user launches the app, the device obtains its current location using GPS and sends a request to the server to calculate an evacuation route.

[1709] Examples:

[1710] When a user opens the smartphone app and requests an evacuation route, the device sends its current GPS location information to the server.

[1711] 4. Calculating the optimal evacuation route

[1712] server:

[1713] The server calculates the safest and quickest evacuation route based on the current location information and the location information of the evacuation shelter, and uses damage prediction data to evaluate the risk of each route and select the optimal route.

[1714] Examples:

[1715] The server calculates routes that avoid areas with a high risk of flooding and selects the optimal evacuation route based on the evaluation results.

[1716] 5. Display and guidance of evacuation routes

[1717] Device:

[1718] The evacuation route sent from the server is displayed on the device's application, which uses map display and voice guidance to guide the user safely to the evacuation shelter.

[1719] User:

[1720] The user begins evacuation by following this displayed route and follows instructions to secure a safe route.

[1721] Examples:

[1722] The device displays the evacuation route received from the server as a red line on a map and uses voice guidance to give instructions such as "Turn right at the next intersection."

[1723] 6. User Emotion Recognition

[1724] Emotion Engine:

[1725] The device uses a camera and microphone to analyze the user's facial expressions and tone of voice to recognize their emotional state, and this data is collected and analyzed in real time.

[1726] Examples:

[1727] The device's camera recognizes the user's face, and when the emotion engine detects that the user is in a panic, it sends that information to the server.

[1728] 7. Emotionally Adapted Navigation

[1729] Servers and devices:

[1730] Based on the information obtained from the emotion engine, the navigation method is adaptively changed according to the user's emotional state. For example, a user who is not calm will receive more understandable instructions or reassuring messages.

[1731] Examples:

[1732] Based on the analysis results of the emotion engine, the server sends more detailed navigation and voice messages such as "Please stay calm."

[1733] Summary

[1734] In this way, the disaster evacuation route navigation system of the present invention is a system that utilizes various data to predict damage and provide users with the safest evacuation route, and by combining it with an emotion engine, it can provide appropriate navigation according to the user's emotional state. This system enables quick and reliable evacuation in the event of a disaster, improving safety and peace of mind.

[1735] The processing flow will be explained below.

[1736] Step 1:

[1737] Server: Acquisition of various data

[1738] The server retrieves topographical data, river flood data, past disaster damage data, and image data from external databases and APIs. This data includes open data from the Ministry of Land, Infrastructure, Transport and Tourism and the Japan Meteorological Agency, as well as various geographic information systems (GIS).

[1739] Step 2:

[1740] Server: Data integration and normalization

[1741] Since the acquired data is in different formats, it is integrated and normalized within the server, which enables consistent processing across each data set.

[1742] Step 3:

[1743] Server: Training the AI ​​model

[1744] The combined data is used to train AI models, for example using deep learning to create models that predict the extent of flood damage or the risk of building collapse in an earthquake.

[1745] Step 4:

[1746] Server: Building Strength Analysis

[1747] Image data obtained from Street View and other sources is analyzed to evaluate the strength of building exterior walls, making it possible to determine the durability of buildings in a specific area and assess the risk of disasters.

[1748] Step 5:

[1749] Terminal: Obtain current location and request evacuation

[1750] When a user launches the app, the device uses GPS to obtain its current location and sends a request to the server to calculate an evacuation route.

[1751] Step 6:

[1752] Server: Evacuation route calculation

[1753] The server calculates the safest and quickest evacuation route based on the current location information and the location information of the evacuation shelter sent from the device, and performs a risk assessment of each route using damage prediction data.

[1754] Step 7:

[1755] Server: Risk-assessed route selection

[1756] A risk assessment is performed on the calculated evacuation routes, and the safest route is selected from among them.

[1757] Step 8:

[1758] Server: Send risk-assessed route

[1759] The selected evacuation route is sent to the terminal.

[1760] Step 9:

[1761] Terminal: Display of evacuation route

[1762] The device displays the received evacuation route on the user interface, showing a safe evacuation route on a map and providing detailed directions.

[1763] Step 10:

[1764] Emotion Engine: Recognizing user emotions

[1765] The device uses a camera and microphone to analyze the user's facial expressions and tone of voice to recognize their emotional state, and this data is collected and analyzed in real time.

[1766] Step 11:

[1767] Server and Terminal: Emotion-Aware Navigation Adaptation

[1768] Based on information obtained from the emotion engine, the navigation method is adaptively changed depending on the user's emotional state. For example, if the user is panicking, more detailed instructions or reassuring messages are provided.

[1769] Step 12:

[1770] Terminal: Evacuation start and real-time updates

[1771] The user begins evacuation by following the displayed evacuation route. The device periodically communicates with the server to provide the user with the latest evacuation route and instructions according to the situation.

[1772] In this way, the system provides the user with the optimal evacuation route through each step, and the emotion engine provides appropriate navigation according to the user's psychological state.

[1773] Example 2

[1774] 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."

[1775] Conventional disaster evacuation systems are limited to presenting evacuation routes and predicting damage, and do not take into account the user's psychological state, making it difficult to provide appropriate support to users in a panic. Furthermore, there are challenges in predicting damage in real time and optimizing evacuation routes, making it difficult to evacuate quickly and safely.

[1776] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1777] In this invention, the server includes means for acquiring topographical data, means for acquiring river flood data, means for acquiring past disaster damage data, means for acquiring image data, means for integrating and normalizing the above data, means for predicting damage in the event of a disaster, means for acquiring a current location, means for calculating an evacuation route, means for assessing the risk of the evacuation route, means for displaying the risk-assessed evacuation route, means for recognizing the user's emotional state, and means for adaptively changing navigation based on the user's emotional state. This enables damage prediction and optimization of evacuation routes in real time, and further provides appropriate navigation according to the user's emotional state.

[1778] "Topography data" refers to data that includes information about the characteristics and shape of the topography.

[1779] "River flood data" refers to data that includes information on the state of rising water levels and flooding of rivers.

[1780] "Past disaster damage data" refers to data that includes records and statistical information on the damage caused by disasters that have occurred in the past.

[1781] "Image data" refers to visual information such as photographs and videos recorded in digital format.

[1782] "Integration and normalization means" refers to techniques and methods for converting data in different formats into a consistent format and unifying the data.

[1783] "Means for predicting damage in the event of a disaster" refers to technologies and methods for predicting the scope and extent of damage in the event of a disaster based on various data.

[1784] "Means for obtaining current location" refers to techniques or methods for determining a user's current physical location using GPS or other location information technology.

[1785] "Means for calculating an evacuation route" refers to a technique or method for calculating the optimal evacuation route based on the user's current location and the location of the evacuation destination.

[1786] "Means for assessing risk" refers to techniques and methods for analyzing disaster risks that exist for evacuation routes and assessing the level of those risks.

[1787] "Means for displaying risk-assessed evacuation routes" refers to techniques or methods for presenting risk-assessed evacuation routes to users by using maps, screen displays, or the like.

[1788] "Means for recognizing a user's emotional state" refers to technology or methods for analyzing and recognizing a user's emotions based on information obtained from a camera, microphone, etc.

[1789] "Means for adaptively changing navigation" refers to techniques and methods for changing and providing navigation instructions according to the emotional state of the user.

[1790] The present invention will now be described with reference to the specific configuration and operation of a system that combines a disaster evacuation route navigation system and an emotion engine.

[1791] System Configuration

[1792] The system mainly consists of the following components:

[1793] Server: Acquires topographical data, river flood data, past disaster damage data, and image data, integrates and normalizes them, and predicts damage.

[1794] Terminal (user's smartphone, etc.): Obtains the user's current location, communicates with the server, and displays evacuation routes.

[1795] Emotion Engine: Recognizes the user's emotional state and adaptively changes navigation methods.

[1796] User: Operate the application and follow the evacuation instructions.

[1797] Data acquisition and preprocessing

[1798] server:

[1799] The server retrieves topographical data, river flood data, past disaster damage data, and image data from external databases and APIs. This data comes in different formats and needs to be integrated and normalized.

[1800] Specifically, it obtains topographical data from a geographic information system (GIS) and also obtains the latest flood data using the Japan Meteorological Agency's API.

[1801] Damage prediction

[1802] server:

[1803] Using the acquired data, a deep learning framework (e.g., TensorFlow) is used to train an AI model that predicts the extent of flood damage and the risk of building collapse due to an earthquake.

[1804] It also analyzes image data to assess the strength of building exterior walls and assess disaster risk within specific areas.

[1805] Obtaining the user's current location and evacuation request

[1806] Device:

[1807] When a user launches the app, the device's GPS acquires the current location and sends a request to the server to calculate an evacuation route.

[1808] Evacuation route calculation

[1809] server:

[1810] The server calculates the safest and quickest evacuation route based on the current location information and the location information of the evacuation shelter, and uses damage prediction data to evaluate the risk of each route and select the optimal route.

[1811] For example, the server calculates routes that avoid areas at high risk of flooding.

[1812] Evacuation route display and guidance

[1813] Device:

[1814] The evacuation route information sent from the server is displayed on the device's application, which uses map display and voice guidance to guide the user safely to an evacuation shelter.

[1815] User:

[1816] The user begins evacuation by following the displayed route and follows instructions to secure a safe route.

[1817] Specifically, the device displays the evacuation route received from the server as a red line on a map and issues voice guidance such as "Turn right at the next intersection."

[1818] User Emotion Recognition

[1819] Emotion Engine:

[1820] The device's camera and microphone are used to analyze the user's facial expressions and tone of voice to recognize their emotional state. This data is collected in real time and sent to a server.

[1821] For example, the device's camera recognizes the user's face and the emotion engine detects that the user is in a panic.

[1822] Emotionally adaptive navigation

[1823] Servers and devices:

[1824] Based on information obtained from the emotion engine, the navigation method is adaptively changed according to the user's emotional state. Users who are not calm are given clearer instructions and reassuring messages.

[1825] For example, the server sends a voice message such as "Please stay calm" to the terminal.

[1826] Prompt Sentence Examples

[1827] If the user's escape route is blocked by water, generate the following prompt:

[1828] "Currently, some roads are impassable due to flooding. If you are in a state of panic, please remain calm and follow the instructions below to continue evacuating."

[1829] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1830] Step 1: Data acquisition and preprocessing

[1831] server:

[1832] Input: topographical data, river flood data, past disaster damage data, image data

[1833] Output: Uniform format dataset

[1834] Specific behavior:

[1835] 1. The server retrieves terrain data from a geographic information system (GIS).

[1836] 2. Call the Japan Meteorological Agency's API to obtain the latest flood data.

[1837] 3. Obtain past disaster damage data and Street View image data from the database.

[1838] 4. The various data acquired are integrated and a normalization algorithm is applied to unify the format.

[1839] Step 2: Training and applying an AI model for damage prediction

[1840] server:

[1841] Input: Normalized dataset

[1842] Output: Damage prediction data

[1843] Specific behavior:

[1844] 1. Train an AI model using a deep learning framework (e.g., TensorFlow) based on the normalized dataset.

[1845] 2. Use trained AI models to predict the extent of flood damage and the risk of building collapse due to earthquakes.

[1846] 3. Analyze Street View image data and evaluate the strength of building exterior walls to assess disaster risk within a specific area.

[1847] Step 3: Get current location and send evacuation request

[1848] Device:

[1849] Input: User operation (app launch), GPS data

[1850] Output: Current location information

[1851] Specific behavior:

[1852] 1. The user launches the app.

[1853] 2. The device uses GPS to obtain its current location.

[1854] 3. Send the current location information to the server along with a request for evacuation route calculation.

[1855] Step 4: Calculate evacuation routes

[1856] server:

[1857] Input: current location information, evacuation shelter location information, damage prediction data

[1858] Output: Optimal evacuation route

[1859] Specific behavior:

[1860] 1. Generate multiple evacuation routes based on current location information and evacuation shelter location information.

[1861] 2. Use damage forecast data to assess the risk of each evacuation route.

[1862] 3. Based on the evaluation results, select the safest, fastest and most optimal evacuation route.

[1863] Step 5: Display and guide evacuation routes

[1864] Device:

[1865] Input: Optimal evacuation route data

[1866] Output: Map display and voice guidance

[1867] Specific behavior:

[1868] 1. Display the evacuation route information received from the server in the app's map module.

[1869] 2. The route will be displayed on the map with a red line, and a voice guidance will begin guiding you, saying, "Turn right at the next intersection."

[1870] User:

[1871] Input: Map display and voice guidance

[1872] Output: Evacuation execution and direction correction

[1873] Specific behavior:

[1874] 1. Check the route on the map and start moving.

[1875] 2. Correct your direction according to the voice guidance and map information.

[1876] Step 6: Recognizing User Emotions

[1877] Emotion Engine:

[1878] Input: Camera video, microphone audio

[1879] Output: Emotion recognition data

[1880] Specific behavior:

[1881] 1. The device camera captures the user's face and performs image analysis.

[1882] 2. The microphone collects the user's voice and the emotion engine analyzes the tone and content.

[1883] 3. Send the results to the server in real time.

[1884] Step 7: Adapt navigation based on emotions

[1885] Servers and devices:

[1886] Input: Emotion recognition data

[1887] Output: Adaptive navigation instructions

[1888] Specific behavior:

[1889] 1. The emotion engine recognizes the user's emotional state (e.g., panicked, calm).

[1890] 2. The server receives the analysis results and adjusts the voice guidance and message content.

[1891] 3. Send a reassuring voice message to the device, such as "Please stay calm."

[1892] (Application example 2)

[1893] 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."

[1894] Conventional disaster evacuation navigation systems simply calculate and present evacuation routes, but are unable to adapt to the user's emotional state during evacuation. This makes it difficult to provide appropriate support to users who are confused or panicked, which can result in delays in evacuation. In contrast, the present invention aims to promote quick and safe evacuation by recognizing the user's emotional state and adaptively changing the navigation method according to that state.

[1895] 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.

[1896] In this invention, the server includes a means for acquiring topographical data, a means for acquiring river flood data, and a means for acquiring past disaster damage data. This allows for the integration and normalization of various data, enabling damage prediction in the event of a disaster. The server also includes a means for acquiring a current location, a means for calculating an evacuation route, a means for assessing the risk of the evacuation route, a means for displaying the risk-assessed evacuation route, a means for recognizing a user's emotional state, and a means for adaptively changing the navigation method based on the recognized emotional state. This allows for the server to provide appropriate navigation according to the user's emotional state, supporting a quick and safe evacuation.

[1897] "Topographic data" refers to data that includes information on the shape and distribution of natural and artificial structures.

[1898] "River flood data" refers to data that includes information on water levels and the extent of damage when rivers flood.

[1899] "Past disaster damage data" refers to data that includes information on the type and extent of damage caused by disasters that have occurred in the past.

[1900] "Image data" is data that represents visual information in digital form.

[1901] "Emotional state" refers to an individual's internal feelings and moods, and is information acquired through sensors such as cameras and microphones.

[1902] "Navigation method" refers to the means of instructions or guidance for navigating a route to a destination.

[1903] "Current location" is the user's current geographical location information.

[1904] An "evacuation route" is a route for safe evacuation in the event of a disaster.

[1905] "Risk assessment" is the process of assessing the degree of danger that may arise under specific conditions.

[1906] "Normalization" is a data processing technique that standardizes data in different formats and units to make them easier to compare.

[1907] A "server" is a computer system that acquires and integrates various data and provides services to multiple clients.

[1908] As an embodiment of the present invention, a specific example of a security service application for smartphones is shown below. This application provides navigation for the user to safely evacuate in the event of a disaster, and furthermore, adaptively changes the navigation method according to the user's emotional state.

[1909] System Configuration

[1910] The system of the present invention mainly comprises the following components:

[1911] 1. Server

[1912] Data acquisition and preprocessing

[1913] The server uses a geographic information system (GIS) and the API of the Japan Meteorological Agency to obtain topographical data, river flood data, and past disaster damage data. Because this data is provided in different formats, it is unified and normalized.

[1914] 2. Device (smartphone)

[1915] Current location acquisition and evacuation request

[1916] When a user launches the app, it uses the smartphone's GPS function to obtain the user's current location and requests the server to calculate an evacuation route.

[1917] Evacuation route display and guidance

[1918] The evacuation route sent from the server is displayed on the smartphone application, and the user is guided using a map and voice guidance.

[1919] 3. Emotion Engine

[1920] User Emotion Recognition

[1921] The system uses the smartphone's camera and microphone to analyze the user's emotional state in real time and transmits the data to a server.

[1922] Emotionally adaptive navigation

[1923] The server optimizes the navigation method based on the emotional state and sends reassuring messages to the user.

[1924] Data processing and calculation

[1925] The system of the present invention performs the following data processing and data calculations:

[1926] 1. Data acquisition and preprocessing (server)

[1927] The server obtains topographical data, river flooding data, and past disaster damage data from GIS and the Japan Meteorological Agency's API. For example, topographical data is obtained from GIS, and river flooding data is obtained from the Japan Meteorological Agency's API. This data is converted into a unified format and normalized.

[1928] 2. Damage Prediction (Server)

[1929] The server uses the collected data to predict disaster risks using deep learning frameworks such as TensorFlow, for example, by calculating the risk of flooding or building collapse based on past disaster data and current conditions.

[1930] 3. Evacuation route calculation (server)

[1931] It obtains the user's current location information and calculates the optimal evacuation route, using an algorithm to avoid dangerous areas.

[1932] 4. Evacuation route display and guidance (terminal)

[1933] The evacuation route sent from the server is displayed on a map on the smartphone, and a voice guidance function is also provided, allowing users to receive instructions such as "Turn right at the next intersection."

[1934] 5. Emotion Recognition (Device, Emotion Engine)

[1935] Using the smartphone's camera and microphone, the system analyzes the user's facial expressions and tone of voice to recognize their emotional state. For example, if the user is in a panic state, the system detects this and sends it to the server.

[1936] 6. Adaptation of navigation methods (server, terminal)

[1937] The navigation method is optimized based on the results of emotion analysis. For example, if the user is in a panic, the server will send a reassuring message such as, "Please stay calm. We are calculating the quickest route to the evacuation shelter."

[1938] Specific examples

[1939] When a user opens a smartphone app and requests an evacuation route, the device sends its current GPS location information to the server. The server uses this information to calculate the optimal evacuation route and sends it to the device. The device displays the route on a map and navigates the user using voice guidance. If the user panics during evacuation, the camera detects this and sends it to the server in real time. The server adaptively changes the navigation message based on the user's emotional state, sending a message such as "Please stay calm."

[1940] Prompt Sentence Examples

[1941] 1. "Please remain calm. We are calculating the quickest route to the evacuation center."

[1942] 2. "Take a deep breath. Turn right at the next intersection."

[1943] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1944] Step 1:

[1945] Data acquisition and preprocessing (server)

[1946] The server obtains topographical data, river flooding data, and past disaster damage data from a geographic information system (GIS) and the Japan Meteorological Agency's API. Specifically, it downloads topographical data from the GIS and collects recent flood data using the Japan Meteorological Agency's API. Because these data are provided in different formats, they are converted into a unified format and normalized. The input is various types of data, and the output is integrated, normalized data.

[1947] Step 2:

[1948] Damage prediction (server)

[1949] The server uses a deep learning model (e.g., TensorFlow) based on the acquired data to predict disaster risk. Specifically, it trains the model using past disaster data and integrated data, and uses current data as input to predict the extent of damage and the risk of building collapse. The input is integrated, normalized data, and the output is a predicted disaster risk map.

[1950] Step 3:

[1951] Current location acquisition and evacuation request (terminal)

[1952] When a user launches the app, it uses the smartphone's GPS to obtain current location information. This location information is sent to the server, which then requests evacuation route calculation. The input is the user's current GPS coordinates, and the output is the request sent to the server.

[1953] Step 4:

[1954] Evacuation route calculation (server)

[1955] The server uses the received current location information and evacuation shelter location information to calculate the optimal evacuation route. Based on the obtained disaster risk map, it evaluates the risk of each route and selects the safest route. The input is the user's current location and the evacuation shelter location information, and the output is the evaluated evacuation route.

[1956] Step 5:

[1957] Evacuation route display and guidance (terminal)

[1958] The evacuation route sent from the server is displayed as a map on the smartphone application, and a voice guidance function is used to provide the user with specific instructions such as "Turn right at the next intersection." The input is the evaluated evacuation route, and the output is a map showing the route and voice guidance.

[1959] Step 6:

[1960] User emotion recognition (device)

[1961] Using the smartphone's camera and microphone, the system analyzes the user's facial expressions and tone of voice to recognize their emotional state. This is done in real time, and the results are sent to a server. The input is the user's facial expressions and tone of voice, and the output is the analyzed emotional state data.

[1962] Step 7:

[1963] Adaptation of navigation methods (server, terminal)

[1964] The server optimizes the navigation method based on the results of emotion analysis. For example, if the user is in a panic state, the server generates a reassuring message such as "Please stay calm. We are calculating the fastest route to the evacuation shelter," and sends it to the device. The input is the analyzed emotional state data, and the output is an adaptively modified navigation message.

[1965] 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.

[1966] 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.

[1967] 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.

[1968] 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.

[1969] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1970] 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.

[1971] 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).

[1972] 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.

[1973] 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."

[1974] 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.

[1975] 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).

[1976] 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.

[1977] 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.

[1978] 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.

[1979] 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.

[1980] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1981] 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.

[1982] 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.

[1983] 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.

[1984] 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.

[1985] 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.

[1986] The following is further disclosed regarding the above embodiment.

[1987] (Claim 1)

[1988] a means for acquiring topographical data;

[1989] a means for obtaining river flood data;

[1990] A means of obtaining past disaster damage data;

[1991] means for acquiring image data;

[1992] A means of integrating and normalizing each of the above data;

[1993] A means of predicting damage in the event of a disaster;

[1994] A means for obtaining a current location;

[1995] a means for calculating an evacuation route;

[1996] means for assessing risk to said evacuation route;

[1997] a means of displaying risk-assessed evacuation routes;

[1998] A system including:

[1999] (Claim 2)

[2000] 10. The system of claim 1, further comprising means for selecting an optimal shelter based on the shelter location information.

[2001] (Claim 3)

[2002] The system of claim 1 , wherein the image data is image data for analyzing the strength of an exterior wall of a building.

[2003] "Example 1"

[2004] (Claim 1)

[2005] a means for acquiring topographical data;

[2006] a means for obtaining river flood data;

[2007] A means of obtaining past disaster damage data;

[2008] means for acquiring image data;

[2009] A means of integrating and normalizing each of the above data;

[2010] A means of predicting damage in the event of a disaster;

[2011] means for obtaining a user's current location;

[2012] a means for calculating an evacuation route;

[2013] means for assessing risk to said evacuation route;

[2014] A means for displaying and providing audio guidance of risk-assessed evacuation routes;

[2015] A system including:

[2016] (Claim 2)

[2017] 10. The system of claim 1, further comprising means for selecting an optimal shelter based on the shelter location information.

[2018] (Claim 3)

[2019] The system of claim 1 , wherein the image data is image data for analyzing the strength of an exterior wall of a building.

[2020] "Application Example 1"

[2021] (Claim 1)

[2022] a means for acquiring topographical data;

[2023] a means for obtaining river flood data;

[2024] A means of obtaining past disaster damage data;

[2025] means for acquiring image data;

[2026] A means of integrating and normalizing each of the above data;

[2027] A means of predicting damage in the event of a disaster;

[2028] A means for obtaining a current location;

[2029] a means for calculating an evacuation route;

[2030] means for assessing risk to said evacuation route;

[2031] a means of displaying risk-assessed evacuation routes;

[2032] means for transmitting an optimal evacuation route to the automated vehicle;

[2033] A means for causing an automated vehicle to automatically drive based on an evacuation route;

[2034] A system including:

[2035] (Claim 2)

[2036] 10. The system of claim 1, further comprising means for selecting an optimal shelter based on the shelter location information.

[2037] (Claim 3)

[2038] The system of claim 1 , wherein the image data is image data for analyzing the strength of an exterior wall of a building.

[2039] "Example 2: Combining Emotion Engines"

[2040] (Claim 1)

[2041] a means for acquiring topographical data;

[2042] a means for obtaining river flood data;

[2043] A means of obtaining past disaster damage data;

[2044] means for acquiring image data;

[2045] A means of integrating and normalizing each of the above data;

[2046] A means of predicting damage in the event of a disaster;

[2047] A means for obtaining a current location;

[2048] a means for calculating an evacuation route;

[2049] means for assessing risk to said evacuation route;

[2050] a means of displaying risk-assessed evacuation routes;

[2051] means for recognizing the emotional state of a user;

[2052] means for adaptively changing navigation based on emotional state;

[2053] A system including:

[2054] (Claim 2)

[2055] 10. The system of claim 1, further comprising means for selecting an optimal shelter based on the shelter location information.

[2056] (Claim 3)

[2057] The system of claim 1 , wherein the image data is image data for analyzing the strength of an exterior wall of a building.

[2058] "Application example 2 when combining emotion engines"

[2059] (Claim 1)

[2060] a means for acquiring topographical data;

[2061] a means for obtaining river flood data;

[2062] A means of obtaining past disaster damage data;

[2063] means for acquiring image data;

[2064] A means of integrating and normalizing each of the above data;

[2065] A means of predicting damage in the event of a disaster;

[2066] A means for obtaining a current location;

[2067] a means for calculating an evacuation route;

[2068] means for assessing risk to said evacuation route;

[2069] a means of displaying risk-assessed evacuation routes;

[2070] means for recognizing the emotional state of a user;

[2071] means for adaptively changing a navigation method based on the recognized emotional state;

[2072] A system including:

[2073] (Claim 2)

[2074] 10. The system of claim 1, further comprising means for selecting an optimal shelter based on the shelter location information.

[2075] (Claim 3)

[2076] The system of claim 1 , wherein the image data is image data for analyzing the strength of an exterior wall of a building. [Explanation of symbols]

[2077] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for acquiring topographical data; a means for obtaining river flood data; A means of obtaining past disaster damage data; means for acquiring image data; A means of integrating and normalizing each of the above data; A means of predicting damage in the event of a disaster; A means for obtaining a current location; a means for calculating an evacuation route; means for assessing risk to said evacuation route; a means of displaying risk-assessed evacuation routes; A system including:

2. The system of claim 1 , further comprising means for selecting an optimal shelter based on the location information of the shelter.

3. The system according to claim 1 , wherein the image data is image data for analyzing the strength of an exterior wall of a building.

Images