system

Abstract

We provide the system. [Solution] A data collection method that gathers information from multiple sources to determine the extent of damage during a natural disaster, A data analysis method that analyzes collected data and assesses the risk of disaster, An information provision method that provides evacuation routes and evacuation locations in real time based on analysis results, A feedback receiving mechanism that receives user feedback and updates system information, A disaster prediction method that uses artificial intelligence to predict and present information on urban-scale disasters based on accumulated data, A mobile information display means that displays information on the user's mobile device or visual device to provide support, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, the frequency and scale of natural disasters have been increasing, and it is required to make a prompt and accurate response when a disaster occurs. In particular, in the disaster area, it is important to collect and analyze information in real time, provide a safe evacuation route, and manage the situation of evacuation shelters in order to protect the lives and health of the disaster victims. However, in the conventional method, there is a problem that a large part of information collection and analysis depends on human work, and it is difficult to make a prompt response.

Means for Solving the Problems

[0005] This invention relates to a system for streamlining the collection, analysis, and provision of information during natural disasters. The invention includes a data collection means for collecting information from multiple sources during a natural disaster. This means acquires data from sources such as the internet, social networking services, sensors, and weather information. The collected data is analyzed by a data analysis means, and the risk of disaster is evaluated using AI. Based on the analysis results, an information provision means provides evacuation routes and shelter information to users in real time. Furthermore, user feedback is received via a feedback receiving means, and system information is updated to ensure that the latest information is always provided. In this way, efficient and rapid disaster response is achieved.

[0006] A "natural disaster" is a phenomenon that occurs in nature independently of human activity, such as earthquakes, floods, typhoons, tsunamis, and volcanic eruptions, and has a significant impact on people's lives and the environment.

[0007] "Data collection means" refers to technical methods or devices for acquiring relevant data from various sources in the event of a disaster.

[0008] "Data analysis means" refers to computer programs or devices used to process collected data, extract meaningful insights, and assess the extent of the damage.

[0009] "Information provision means" refers to communication methods for promptly transmitting appropriate evacuation routes and shelter information to users based on analysis results.

[0010] A "feedback receiving mechanism" is a mechanism for collecting information and opinions received from system users and adjusting the system's operation based on that information.

[0011] "AI" is an abbreviation for artificial intelligence, and it is a collection of machine learning algorithms and technologies that learn from data and make judgments and predictions based on that learning. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, a tagged processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, a tagged RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, a tagged storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0018] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the 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.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0026] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention provides a system for rapid and accurate information gathering, analysis, and provision during natural disasters. The system consists of a server, terminals, and users, each responsible for a specific function.

[0034] The server collects disaster information in real time from multiple data sources. Specifically, it acquires data from the internet, social networking services, environmental sensors, and weather information providers. This data is processed using AI-based data analysis methods to evaluate the specific damage situation in each region. For example, by comparing sensing data of rising river levels in a certain area with images posted on social media, the risk of flooding can be determined.

[0035] The terminal appropriately displays data provided by the server to the user. The terminal uses the user's current location information to calculate the optimal evacuation route and display it on a map. Furthermore, it can provide real-time updated information on the capacity of evacuation centers and the shortage of supplies. If the user requires voice notification, it can also transmit that information via voice through integration with the disaster prevention radio system.

[0036] Users can input information about their evacuation destination and necessary supplies through this system. This information is sent to the server as feedback and contributes to improving the accuracy of future data analysis and information provision. For example, if a user voluntarily posts their evacuation location on social media, the server will reflect that data as useful information for other evacuees.

[0037] As a concrete example, if urban flooding is predicted, the server analyzes the risk of flooding based on river water level sensors and social media posts, and sends the results to the terminal. The terminal issues an alert to the user and guides them to the shortest and safest evacuation route and available shelters. The user evacuates according to the instructions, and after completing the evacuation, they can provide feedback on the information to help other residents evacuate.

[0038] In this way, the entire system works in conjunction, and through a series of processes from information collection and analysis to provision and feedback, it aims to ensure the rapid evacuation of disaster victims and the safety of human lives.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server connects to information sources such as the internet, social networking services, environmental sensors, and weather information providers to collect data. This includes using SNS APIs to retrieve the latest posts relevant to a specific area and pulling environmental data such as water levels and wind speed from sensor databases in real time.

[0042] Step 2:

[0043] The server passes the collected data to a data analysis system, which uses AI to assess the extent of the damage. The server runs an AI model to perform image recognition and text mining, thereby identifying risks such as river flooding and road closures. The analysis results are organized by affected area and form the basis of the information provided to users.

[0044] Step 3:

[0045] Based on the analysis results, the server generates evacuation advisories and warning messages. Furthermore, it creates a comprehensive evacuation plan, including the location and capacity of evacuation centers, and traffic information, and sends it to the terminal. This information is updated in real time as the situation develops.

[0046] Step 4:

[0047] The terminal receives information sent from the server and notifies the user of its contents. The terminal uses the user's location information to calculate an individually optimized evacuation route and displays it on a map. It also informs the user of the current availability of evacuation shelters, helping them to secure an appropriate evacuation location.

[0048] Step 5:

[0049] Users will initiate swift and safe evacuation based on the information provided on their devices. Users will also contribute to updating the system's information by inputting information about their evacuation destination and necessary supplies via their devices, and feeding this information back to the server.

[0050] Step 6:

[0051] The server incorporates user feedback and updates the system's overall information. Based on this feedback, further data analysis is performed, ensuring the continued provision of highly accurate information. This allows for continuous improvement of the system's effectiveness and reliability.

[0052] (Example 1)

[0053] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0054] During natural disasters, rapid and accurate information gathering and analysis are crucial, as is the need for appropriate evacuation guidance and support for those affected. However, conventional systems have struggled to collect and analyze data from diverse sources in real time to provide users with useful information. Furthermore, mechanisms for updating and providing users with real-time information on the capacity of evacuation centers and the shortage of supplies have been insufficient.

[0055] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0056] In this invention, the server includes an information acquisition means that collects data from multiple sources in the event of a natural disaster to determine the extent of the damage; an information analysis means that analyzes the collected data using a large-scale data processing means to assess the risk of damage; and an information communication means that provides evacuation routes and evacuation locations in real time based on the analysis results. This enables users to receive complex disaster information in real time and obtain specific and rapid guidelines for optimal evacuation.

[0057] "Information acquisition methods" refer to technologies that collect data from various sources such as the internet, social networking services, environmental sensors, and weather information agencies when natural disasters occur.

[0058] "Information analysis methods" refer to technologies that process collected data and use AI technology to assess the risk level of the disaster.

[0059] "Information and communication means" refers to technology that provides users with information on evacuation routes and evacuation locations in real time, based on analysis results.

[0060] "Information receiving means" refers to technology that receives feedback from users and updates the information of the entire system.

[0061] "Route calculation means" refers to a technology that calculates and provides the optimal evacuation route based on the user's location information.

[0062] "Voice communication means" refers to technology that transmits warnings and instructions using voice.

[0063] "Predictive information generation means" refers to a technology that uses AI to predict future disaster situations based on collected data.

[0064] "Situation management means" refers to technology that continuously receives information on the occupancy status of evacuation centers and the shortage of supplies, and displays it to the user.

[0065] This invention is designed to realize a system that enables rapid and accurate information gathering, analysis, and provision during natural disasters. The system mainly consists of servers, terminals, and users, each playing its own unique role.

[0066] The server uses information acquisition methods to collect data from diverse sources such as the internet, social networking services, environmental sensors, and weather information agencies. This data is then processed by information analysis methods, and analysis is performed using AI technology, particularly deep learning frameworks such as TENSORFLOW® and PyTorch. As a result of the analysis, it is possible to evaluate the specific damage situation in each region and measure the risk. For example, the risk of flooding can be determined by comparing river water level rise data in a certain area with images posted on social media.

[0067] The terminal receives analysis results transmitted from the server and functions as a means of information communication. The terminal uses GPS to determine the user's current location and calculates a safe evacuation route using Google® Maps API, etc. This calculation result, as well as information on the capacity of evacuation centers and supplies, is displayed on the terminal in real time and communicated to the user. In addition, it is possible to convey evacuation orders and warnings by voice using voice communication means.

[0068] Users can provide feedback to the system regarding evacuation destinations and shortages of supplies obtained through information receiving means. This information is sent to the server and used as preparation for the next disaster using predictive information generation means. For example, if a user posts about the situation at an evacuation center on social media, the server collects that data and shares the analysis results with other evacuees.

[0069] An example of a prompt statement could be input to a generative AI model: "If flooding is predicted, develop an evacuation plan for a local city. In this process, how will you collect, analyze, and provide information to the user?"

[0070] This system enables rapid evacuation and information dissemination during natural disasters by coordinating servers, terminals, and users.

[0071] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0072] Step 1:

[0073] The server begins the process of collecting data from the internet, social media, environmental sensors, and weather information agencies using information acquisition methods. As input, it receives API keys and access information for each data source. Using this information, it accesses each platform, collects relevant disaster information, and outputs it as formatted raw data. Specifically, this includes using the Twitter API to collect posts containing the keyword "flood."

[0074] Step 2:

[0075] The server analyzes the raw data collected in Step 1 using information analysis tools. A deep learning model using TensorFlow is used for this analysis. Social media posts and environmental sensor data are provided as input, and the damage situation and risk level are assessed based on this data. The analysis results are generated in JSON format as output, and include a risk assessment score for a specific area. A specific example of its operation is comparing images posted on social media with river water level information to predict flood risk.

[0076] Step 3:

[0077] The server uses information and communication means to send the analysis results obtained in step 2 to the terminal. It receives the analysis results in JSON format as input and sends them to the terminal as data packets. The output is the analysis result data received by the terminal used by the user. Specifically, the analysis results are provided to the terminal in real time via the API.

[0078] Step 4:

[0079] The terminal displays information, including evacuation instructions, to the user based on the received analysis results. The terminal receives data packets from the server as input and uses location information to calculate safe evacuation routes using the Google Maps API. The output is a visually navigable evacuation map, displayed on the screen in an easy-to-understand format. Additionally, it issues voice warnings via voice communication as needed.

[0080] Step 5:

[0081] Users check evacuation information displayed on their devices and take safe evacuation actions. They receive evacuation route and shelter information displayed on their device screen as input and act accordingly. After completing the evacuation, they provide feedback on the evacuation location and the shortage of supplies. The output is feedback data sent to the server. Specifically, users add information to the system's overall database by inputting the congestion status of evacuation shelters through a smartphone app.

[0082] (Application Example 1)

[0083] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0084] In the event of a natural disaster, there is a need for a system that can quickly and accurately assess the extent of the damage and support safe evacuation. However, current systems lack real-time information provision and urban-scale disaster prediction, which can cause delays in the integration of information that users need. In particular, it is difficult to provide individual evacuation route guidance and to grasp the capacity of evacuation centers, and there is a need for means to improve user safety and convenience.

[0085] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0086] In this invention, the server includes data collection means for accumulating information when a natural disaster occurs, data analysis means for analyzing the information and evaluating the risk of damage, and disaster prediction means using artificial intelligence. This enables the provision of real-time evacuation information to users and rapid disaster response on a city scale.

[0087] A "system" refers to the entire device that has a series of functions for collecting and analyzing information in the event of a natural disaster and providing evacuation information to users.

[0088] A "data collection device" is a device that has the function of acquiring information necessary to understand the extent of the disaster from multiple information sources such as the internet and environmental sensors.

[0089] A "data analysis device" is a device that has the function of analyzing collected data and evaluating the risk and situation of a disaster.

[0090] An "information provision device" is a device that has the function of guiding users to evacuation routes and evacuation locations in real time based on the analyzed results.

[0091] A "feedback receiving means" is a device that has the function of receiving information and feedback from users and updating the information within the system.

[0092] Artificial intelligence is a technology that processes and analyzes large amounts of data to predict risks and evacuation routes during disasters.

[0093] A "mobile information display means" is a device that has the function of displaying necessary information in real time on a user's mobile device or visual device.

[0094] The system of the present invention is configured to quickly and accurately collect and analyze information in the event of a natural disaster and to provide users with necessary evacuation information.

[0095] The server collects data in real time from multiple sources, including the internet, environmental sensors, and social networking services. This data is used as foundational information to understand the extent of damage in each region. This data is then analyzed by artificial intelligence using machine learning libraries such as TensorFlow to optimize disaster risk assessments and evacuation routes.

[0096] Based on the analyzed data, the device uses the Google Maps API to display the optimal evacuation route based on the user's current location. Information on shelter occupancy and supply management is also updated in real time and displayed on the device's screen. The device is designed for devices such as smartphones and smart glasses, providing users with information visually and audibly.

[0097] Users evacuate safely based on the information provided. After evacuation, they provide feedback to the system to help other users evacuate and contribute to improving the overall accuracy of the information. For example, if a user is in an area where flooding is predicted, the system analyzes water level information and social media posts in that area and provides real-time information on the safest evacuation routes and shelters.

[0098] An example of a prompt might be: "When flood damage is predicted, what data and technology should be used to provide User A with the shortest evacuation route and evacuation shelter information in real time on their smart glasses?"

[0099] This system allows users to quickly and reliably obtain information to protect themselves from disasters, contributing to improved safety throughout the city.

[0100] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0101] Step 1:

[0102] The server collects data from disaster-stricken areas from the internet, environmental sensors, social media, and other sources. Specifically, it retrieves data in real time from each information source via APIs. Input data includes water level data, weather information, and images posted on social media, which are then collected on the server. The output is a raw dataset.

[0103] Step 2:

[0104] The server analyzes the collected raw dataset using AI. Using machine learning models such as TensorFlow, it matches environmental sensor data with image data from social media to assess the risk of disaster. The input is the raw data collected in step 1, and the output is the analysis of risk levels and evacuation needs for each region. Specific data processing involves pattern recognition of matching data and risk scoring.

[0105] Step 3:

[0106] The server generates evacuation information based on the analysis results and sends it to the terminal. Specifically, it uses the Google Maps API to design evacuation routes and map the availability of evacuation shelters. The input is the risk level and current location information obtained in step 2, and the output is the optimized evacuation route and evacuation shelter information.

[0107] Step 4:

[0108] The terminal displays evacuation information received from the server to the user. Specifically, it displays evacuation routes and the locations of evacuation shelters on a map on the screen of a smartphone or smart glasses. If voice notifications are set, they are also provided. The input is the output information from step 3, and the output is the evacuation information presented to the user.

[0109] Step 5:

[0110] Users evacuate based on the information provided and send feedback to the server after completing the evacuation. Specifically, they input information such as obstacles and congestion along the evacuation route via a terminal. The input is user feedback, and the output is the registration of that feedback in the system's database. This improves the accuracy of future analysis and information provision.

[0111] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0112] This invention provides a system aimed at rapidly collecting, analyzing, and providing information during natural disasters, and further enhancing support by understanding the emotional state of users. This system mainly consists of a server, terminals, users, and an emotion engine.

[0113] The server collects data in real time from various sources, including network services, sensor networks, and weather information providers. This data is analyzed using AI-based data analysis tools to not only assess the extent of the damage but also predict future disaster risks.

[0114] The emotion engine analyzes data acquired from the user to determine their emotions. This engine takes in text data, voice data, or real-time interaction data provided by the user from their mobile device or PC as emotion data to understand the user's emotional state. Furthermore, based on the analysis of the emotional state, it determines the communication method optimized for the user and reflects it on the device through the information delivery means.

[0115] The device uses information on evacuation routes and locations transmitted from the server, along with analysis results from the emotion engine, to adjust how it guides and supports the user. For example, if it determines that the user is experiencing high levels of anxiety, it may suggest notifying emergency contacts or connecting the user to organizations that provide psychological support.

[0116] Users can act according to the information provided through their devices to ensure their own safety. They can also contribute to improving the system's functionality by inputting information about evacuation destinations and supply needs, and providing feedback. If necessary, they can also input their emotional state, which will allow the system to provide even more refined support plans.

[0117] As a concrete example, in a situation where evacuation is necessary due to heavy rain, the server predicts the risk of flooding based on river water level data, and the terminal notifies the user of this information. The emotion engine detects anxiety and stress from the content of the message sent by the user and simultaneously provides guidance on psychological support services through the terminal. In this way, the entire system protects the safety of disaster victims and realizes multifaceted support, including psychological support.

[0118] The following describes the processing flow.

[0119] Step 1:

[0120] The server collaborates with network services, environmental sensors, and weather information providers to collect real-time information from disaster-stricken areas. This allows the server to obtain the latest flood and weather data and identify the extent of the disaster's impact.

[0121] Step 2:

[0122] The server processes the collected data using data analysis tools and assesses the extent of the damage using AI algorithms. The analysis results indicate which areas have suffered the most severe damage, and based on this information, the server generates evacuation advisories and evacuation route plans.

[0123] Step 3:

[0124] The emotion engine analyzes text messages and voice data provided by the user to determine their emotional state. Based on this analysis, if the user is experiencing anxiety or stress, the server selects an appropriate support method.

[0125] Step 4:

[0126] The terminal receives evacuation information sent from the server and analysis results from the emotion engine, and notifies the user. Specifically, it displays a message tailored to the user's current emotional state and, if necessary, suggests access to psychological support services.

[0127] Step 5:

[0128] Users review the information provided through their devices and begin taking action to evacuate safely. Users also provide feedback on their emotional state and details of their evacuation destination, which is sent to the server and used to update the system's information.

[0129] Step 6:

[0130] The server updates system-wide information based on user feedback and adjusts subsequent information delivery, taking into account changes in the user's emotional state. This enables the continuous provision of safe and appropriate support to the user.

[0131] (Example 2)

[0132] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0133] During natural disasters, it is crucial to collect, analyze, and provide information quickly and accurately. However, existing systems lacked the functionality to provide appropriate support while considering the emotional state of users. Therefore, a support system is needed that can ensure the psychological safety of disaster victims.

[0134] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0135] In this invention, the server includes data acquisition means, data analysis means, and support information provision means. This makes it possible to acquire accurate information in real time when a natural disaster occurs and to provide optimal support information according to the user's emotional state.

[0136] "Data acquisition methods" refer to means of collecting information from multiple sources and gathering data necessary for assessing the extent of the disaster.

[0137] "Data analysis methods" refer to means of analyzing acquired data to assess the risk of disaster.

[0138] "Information provision means" refers to the means of providing users with evacuation routes and evacuation locations in real time based on analysis results.

[0139] "Emotion analysis means" refers to a method for analyzing input data from a terminal to determine the user's emotional state.

[0140] A "support information provision method" is a means of providing users with optimal support information based on the results of emotion analysis.

[0141] A "feedback receiving mechanism" is a means of receiving feedback from users and updating system information.

[0142] A "predictive tool" is a means of using artificial intelligence to predict the extent of a disaster and to assess the likelihood of future disasters.

[0143] "Information management means" refers to the means of continuously updating the occupancy status and shortage status of supplies at evacuation centers and displaying necessary information.

[0144] The invention will now be described in terms of embodiments. This system is designed to provide rapid and efficient information and user support in the event of a natural disaster, and its main components include a server, terminals, users, and an emotion engine.

[0145] The server is responsible for acquiring data from multiple sources. These sources include network services, sensor networks, and weather information providers. The HTTP protocol is used to acquire this data, collecting it in JSON format from APIs. The collected data is then analyzed using TensorFlow, an open-source machine learning platform. The analysis results are used to assess the extent of damage and predict future disaster risks.

[0146] The emotion engine is designed to understand the user's emotional state. It analyzes text and audio data provided by the user via mobile devices or PCs, and uses natural language processing technology to determine emotions. This process utilizes the emotion analysis library "emotion-lib," which makes it possible to quantify the user's anxiety and stress levels.

[0147] The device provides information and support to the user. In addition to evacuation route and location information transmitted from the server, it uses sentiment analysis results to determine the appropriate support method based on the user's situation. For example, if the user shows strong anxiety, the device will launch an emergency contact app and display psychological support services. It also uses the Google Maps API to provide safe evacuation routes in real time.

[0148] Users can take safe actions based on the information they receive through their devices. They can also send feedback to the system regarding the occupancy status of evacuation centers and the need for supplies. This feedback contributes to improving the accuracy of data analysis on the server.

[0149] As a concrete example, consider a situation where evacuation is necessary due to heavy rain. In this case, the server predicts the risk of flooding based on river water level data and sends this information to the terminal. The emotion engine detects anxiety from the user's message and introduces psychological support services through the terminal. At the same time, the terminal displays an evacuation route suitable for the user on Google Maps.

[0150] The following prompt statements are used as example inputs to the generative AI model.

[0151] "User message: 'I'm worried about today's heavy rain.' Analyze this message and determine the user's sentiment."

[0152] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0153] Step 1:

[0154] The server retrieves data from information sources, including network services, sensor networks, and weather information providers. The input data is weather data in JSON format obtained from each information source. This data is collected via the HTTP protocol and prepared for the next analysis step. Specifically, it queries real-time precipitation and wind speed data via APIs.

[0155] Step 2:

[0156] The server analyzes the acquired data. The input data is the weather data collected in Step 1. TensorFlow is used to analyze the data, assess the extent of the damage, and predict future disaster risks. This data processing involves applying machine learning algorithms using analytical models. The analysis results are output as a risk score indicating the likelihood of disaster.

[0157] Step 3:

[0158] The emotion engine collects and analyzes data from users. Input consists of text messages and audio data provided by users via mobile devices or PCs. It uses emotion-lib to extract emotions from the text and determines the emotional state through natural language processing. Data calculations quantify stress and anxiety, outputting them as emotional states. Specifically, it analyzes the user message "I'm worried about today's heavy rain" to determine the emotional state.

[0159] Step 4:

[0160] The device provides information based on analysis results from the server and the output of the emotion engine. Inputs are the risk score from Step 2 and the emotional state from Step 3. Using these, it presents the user with optimal evacuation route information and psychological support information. Specific actions include displaying evacuation routes using the Google Maps API and launching emergency contact apps.

[0161] Step 5:

[0162] The user acts based on the information provided by the terminal. The data entered is the evacuation information provided in step 4. The user takes safe evacuation actions and enters feedback into the terminal as needed. This feedback provides specific information about the shortage of goods in the disaster area and the capacity of evacuation centers. Particularly important feedback is sent to the server and used to improve the accuracy of the system.

[0163] (Application Example 2)

[0164] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0165] In the event of a natural disaster, it is difficult to quickly and accurately grasp the extent of the damage, provide appropriate evacuation information, and offer support that takes into account the emotional state of users. Furthermore, there is a need to reduce psychological anxiety during disasters, efficiently incorporate user feedback into the system, and realize safe and smooth support for disaster victims.

[0166] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0167] In this invention, the server includes data collection means for collecting information from multiple sources to determine the extent of damage in the event of a natural disaster, data analysis means for analyzing the collected data and evaluating the risk of damage, information provision means for providing evacuation routes and shelters in real time based on the analysis results, and emotion analysis means for analyzing the user's emotional state and providing psychological support as needed. This enables the rapid and appropriate provision of disaster information while also providing multifaceted support that takes into account the user's psychological state.

[0168] "Data collection methods" refer to means of collecting information from multiple sources to assess the extent of damage during a natural disaster.

[0169] "Data analysis methods" refer to means of analyzing collected data to assess the risk of disaster.

[0170] "Information provision means" refers to means of providing evacuation routes and evacuation locations in real time based on analysis results.

[0171] "Emotional analysis tools" are means of analyzing a user's emotional state and providing psychological support as needed.

[0172] A "feedback receiving mechanism" is a means of receiving feedback from users and updating system information.

[0173] A "predictive tool" is a method of predicting the extent of a disaster using artificial intelligence based on collected data.

[0174] "Information management means" refers to the means of continuously updating and displaying the occupancy status of evacuation centers and the shortage status of supplies.

[0175] The system to realize this application includes various hardware and software. When a natural disaster occurs, the server collects data in real time from specific sources and analyzes this data using AI to determine the extent of the damage.

[0176] The server acquires information from network services and sensors when collecting data, and manages it on Google Cloud or similar cloud services. It also utilizes deep learning algorithms to understand the situation in disaster-stricken areas and accurately provide information on evacuation routes and shelters. This is supported by ML frameworks such as TensorFlow.

[0177] The terminal functions as an interface for providing information to the user. These terminals, such as smartphones and smart glasses, manage user interaction. These devices use Firebase Cloud Messaging to provide real-time notifications and, as needed, select and present psychological support solutions to the user.

[0178] The emotion analysis system analyzes voice and text data sent by the user to determine the user's emotions. It utilizes speech recognition technology, employing tools such as IBM Watson® Tone Analyzer, to understand the user's emotional state.

[0179] Users receive information from the system, make decisions about their actions, and provide feedback if necessary. This feedback allows the system to make further improvements in preparation for future disasters.

[0180] As a concrete example, in the event of an evacuation advisory due to heavy rain, the server quickly analyzes river water level information and assesses the level of danger. It then notifies the terminal of information about nearby evacuation sites. If the sentiment analysis system detects that the user is feeling anxious, the terminal displays interactive guidance that provides psychological support. Below are examples of prompts generated using a generative AI model:

[0181] "You are your mother's care planner. If you recently noticed signs that your mother is feeling lonely, how would you respond? Please create a notification message."

[0182] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0183] Step 1:

[0184] The server collects information in real time from multiple data sources through sensors and network services. Inputs include weather data, geological information, and river water level data, which are aggregated in cloud storage. The collected data is stored in a database and used for subsequent data analysis.

[0185] Step 2:

[0186] The server processes the collected information using data analysis tools. It uses various disaster information obtained from a cloud-based database as input and analyzes it using AI algorithms. Specifically, it runs models that evaluate the risk of floods and earthquakes using tools like TensorFlow, and generates a risk assessment report as output.

[0187] Step 3:

[0188] The server generates information on evacuation routes and shelters based on the analysis results. It uses a risk assessment report as input to evaluate the capacity and accessibility of evacuation shelters. As output, it creates a list of recommended evacuation routes and shelters, which is then passed on to the next step.

[0189] Step 4:

[0190] The device notifies the user of evacuation information received from the server. It retrieves evacuation information from the server as input and sends push notifications to smartphones and smart glasses using Firebase Cloud Messaging. The information is displayed to the user visually or audibly to help them respond immediately.

[0191] Step 5:

[0192] The emotion analysis method analyzes user messages and voice data to determine their psychological state. It takes real-time chats and voice memos as input data and analyzes emotions using the IBM Watson API. As output, it creates an emotion state report and generates corresponding countermeasures in the next step.

[0193] Step 6:

[0194] The device provides psychological support information tailored to the user's emotional state. It uses an emotional state report as input, and if the user is feeling anxious, it provides information on relaxation methods and psychological support services. The user interface displays preventative measures and messages to promote reassurance.

[0195] Step 7:

[0196] Users proceed with evacuation actions based on the information provided and return feedback to the system. For example, they report the situation at evacuation centers and the necessary supplies. The system receives user feedback as input and records it in a database on the server for future disaster response.

[0197] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0198] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0199] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0200] [Second Embodiment]

[0201] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0202] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0203] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0204] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0205] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0206] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0207] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0208] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0209] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0210] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0211] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0212] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0213] This invention provides a system for rapid and accurate information gathering, analysis, and provision during natural disasters. The system consists of a server, terminals, and users, each responsible for a specific function.

[0214] The server collects disaster information in real time from multiple data sources. Specifically, it acquires data from the internet, social networking services, environmental sensors, and weather information providers. This data is processed using AI-based data analysis methods to evaluate the specific damage situation in each region. For example, by comparing sensing data of rising river levels in a certain area with images posted on social media, the risk of flooding can be determined.

[0215] The terminal appropriately displays data provided by the server to the user. The terminal uses the user's current location information to calculate the optimal evacuation route and display it on a map. Furthermore, it can provide real-time updated information on the capacity of evacuation centers and the shortage of supplies. If the user requires voice notification, it can also transmit that information via voice through integration with the disaster prevention radio system.

[0216] Users can input information about their evacuation destination and necessary supplies through this system. This information is sent to the server as feedback and contributes to improving the accuracy of future data analysis and information provision. For example, if a user voluntarily posts their evacuation location on social media, the server will reflect that data as useful information for other evacuees.

[0217] As a concrete example, if urban flooding is predicted, the server analyzes the risk of flooding based on river water level sensors and social media posts, and sends the results to the terminal. The terminal issues an alert to the user and guides them to the shortest and safest evacuation route and available shelters. The user evacuates according to the instructions, and after completing the evacuation, they can provide feedback on the information to help other residents evacuate.

[0218] In this way, the entire system works in conjunction, and through a series of processes from information collection and analysis to provision and feedback, it aims to ensure the rapid evacuation of disaster victims and the safety of human lives.

[0219] The following describes the processing flow.

[0220] Step 1:

[0221] The server connects to information sources such as the internet, social networking services, environmental sensors, and weather information providers to collect data. This includes using SNS APIs to retrieve the latest posts relevant to a specific area and pulling environmental data such as water levels and wind speed from sensor databases in real time.

[0222] Step 2:

[0223] The server passes the collected data to a data analysis system, which uses AI to assess the extent of the damage. The server runs an AI model to perform image recognition and text mining, thereby identifying risks such as river flooding and road closures. The analysis results are organized by affected area and form the basis of the information provided to users.

[0224] Step 3:

[0225] Based on the analysis results, the server generates evacuation advisories and warning messages. Furthermore, it creates a comprehensive evacuation plan, including the location and capacity of evacuation centers, and traffic information, and sends it to the terminal. This information is updated in real time as the situation develops.

[0226] Step 4:

[0227] The terminal receives information sent from the server and notifies the user of its contents. The terminal uses the user's location information to calculate an individually optimized evacuation route and displays it on a map. It also informs the user of the current availability of evacuation shelters, helping them to secure an appropriate evacuation location.

[0228] Step 5:

[0229] Users will initiate swift and safe evacuation based on the information provided on their devices. Users will also contribute to updating the system's information by inputting information about their evacuation destination and necessary supplies via their devices, and feeding this information back to the server.

[0230] Step 6:

[0231] The server incorporates user feedback and updates the system's overall information. Based on this feedback, further data analysis is performed, ensuring the continued provision of highly accurate information. This allows for continuous improvement of the system's effectiveness and reliability.

[0232] (Example 1)

[0233] Next, we will describe Example 1. 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."

[0234] During natural disasters, rapid and accurate information gathering and analysis are crucial, as is the need for appropriate evacuation guidance and support for those affected. However, conventional systems have struggled to collect and analyze data from diverse sources in real time to provide users with useful information. Furthermore, mechanisms for updating and providing users with real-time information on the capacity of evacuation centers and the shortage of supplies have been insufficient.

[0235] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0236] In this invention, the server includes an information acquisition means that collects data from multiple sources in the event of a natural disaster to determine the extent of the damage; an information analysis means that analyzes the collected data using a large-scale data processing means to assess the risk of damage; and an information communication means that provides evacuation routes and evacuation locations in real time based on the analysis results. This enables users to receive complex disaster information in real time and obtain specific and rapid guidelines for optimal evacuation.

[0237] "Information acquisition methods" refer to technologies that collect data from various sources such as the internet, social networking services, environmental sensors, and weather information agencies when natural disasters occur.

[0238] "Information analysis methods" refer to technologies that process collected data and use AI technology to assess the risk level of the disaster.

[0239] "Information and communication means" refers to technology that provides users with information on evacuation routes and evacuation locations in real time, based on analysis results.

[0240] "Information receiving means" refers to technology that receives feedback from users and updates the information of the entire system.

[0241] "Route calculation means" refers to a technology that calculates and provides the optimal evacuation route based on the user's location information.

[0242] "Voice communication means" refers to technology that transmits warnings and instructions using voice.

[0243] "Predictive information generation means" refers to a technology that uses AI to predict future disaster situations based on collected data.

[0244] "Situation management means" refers to technology that continuously receives information on the occupancy status of evacuation centers and the shortage of supplies, and displays it to the user.

[0245] This invention is designed to realize a system that enables rapid and accurate information gathering, analysis, and provision during natural disasters. The system mainly consists of servers, terminals, and users, each playing its own unique role.

[0246] The server uses information acquisition methods to collect data from diverse sources such as the internet, social networking services, environmental sensors, and weather information agencies. This data is then processed by information analysis methods, and analysis is performed using AI technology, particularly deep learning frameworks such as TensorFlow and PyTorch. As a result of the analysis, it is possible to evaluate the specific damage situation in each region and measure the risk. For example, the risk of flooding can be determined by comparing river water level rise data in a certain area with images posted on social media.

[0247] The terminal receives analysis results transmitted from the server and functions as a means of information communication. The terminal uses GPS to determine the user's current location and calculates a safe evacuation route using the Google Maps API, etc. This calculation result, as well as information on the capacity of evacuation centers and supplies, is displayed on the terminal in real time and communicated to the user. In addition, it is possible to convey evacuation orders and warnings by voice using voice communication means.

[0248] Users can provide feedback to the system regarding evacuation destinations and shortages of supplies obtained through information receiving means. This information is sent to the server and used as preparation for the next disaster using predictive information generation means. For example, if a user posts about the situation at an evacuation center on social media, the server collects that data and shares the analysis results with other evacuees.

[0249] An example of a prompt statement could be input to a generative AI model: "If flooding is predicted, develop an evacuation plan for a local city. In this process, how will you collect, analyze, and provide information to the user?"

[0250] This system enables rapid evacuation and information dissemination during natural disasters by coordinating servers, terminals, and users.

[0251] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0252] Step 1:

[0253] The server begins the process of collecting data from the internet, social media, environmental sensors, and weather information agencies using information acquisition methods. As input, it receives API keys and access information for each data source. Using this information, it accesses each platform, collects relevant disaster information, and outputs it as formatted raw data. Specifically, this includes using the Twitter API to collect posts containing the keyword "flood."

[0254] Step 2:

[0255] The server analyzes the raw data collected in Step 1 using information analysis tools. A deep learning model using TensorFlow is used for this analysis. Social media posts and environmental sensor data are provided as input, and the damage situation and risk level are assessed based on this data. The analysis results are generated in JSON format as output, and include a risk assessment score for a specific area. A specific example of its operation is comparing images posted on social media with river water level information to predict flood risk.

[0256] Step 3:

[0257] The server uses information and communication means to send the analysis results obtained in step 2 to the terminal. It receives the analysis results in JSON format as input and sends them to the terminal as data packets. The output is the analysis result data received by the terminal used by the user. Specifically, the analysis results are provided to the terminal in real time via the API.

[0258] Step 4:

[0259] The terminal displays information, including evacuation instructions, to the user based on the received analysis results. The terminal receives data packets from the server as input and uses location information to calculate safe evacuation routes using the Google Maps API. The output is a visually navigable evacuation map, displayed on the screen in an easy-to-understand format. Additionally, it issues voice warnings via voice communication as needed.

[0260] Step 5:

[0261] Users check evacuation information displayed on their devices and take safe evacuation actions. They receive evacuation route and shelter information displayed on their device screen as input and act accordingly. After completing the evacuation, they provide feedback on the evacuation location and the shortage of supplies. The output is feedback data sent to the server. Specifically, users add information to the system's overall database by inputting the congestion status of evacuation shelters through a smartphone app.

[0262] (Application Example 1)

[0263] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0264] In the event of a natural disaster, there is a need for a system that can quickly and accurately assess the extent of the damage and support safe evacuation. However, current systems lack real-time information provision and urban-scale disaster prediction, which can cause delays in the integration of information that users need. In particular, it is difficult to provide individual evacuation route guidance and to grasp the capacity of evacuation centers, and there is a need for means to improve user safety and convenience.

[0265] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0266] In this invention, the server includes data collection means for accumulating information when a natural disaster occurs, data analysis means for analyzing the information and evaluating the risk of damage, and disaster prediction means using artificial intelligence. This enables the provision of real-time evacuation information to users and rapid disaster response on a city scale.

[0267] A "system" refers to the entire device that has a series of functions for collecting and analyzing information in the event of a natural disaster and providing evacuation information to users.

[0268] A "data collection device" is a device that has the function of acquiring information necessary to understand the extent of the disaster from multiple information sources such as the internet and environmental sensors.

[0269] A "data analysis device" is a device that has the function of analyzing collected data and evaluating the risk and situation of a disaster.

[0270] An "information provision device" is a device that has the function of guiding users to evacuation routes and evacuation locations in real time based on the analyzed results.

[0271] A "feedback receiving means" is a device that has the function of receiving information and feedback from users and updating the information within the system.

[0272] Artificial intelligence is a technology that processes and analyzes large amounts of data to predict risks and evacuation routes during disasters.

[0273] A "mobile information display means" is a device that has the function of displaying necessary information in real time on a user's mobile device or visual device.

[0274] The system of the present invention is configured to quickly and accurately collect and analyze information in the event of a natural disaster and to provide users with necessary evacuation information.

[0275] The server collects data in real time from multiple sources, including the internet, environmental sensors, and social networking services. This data is used as foundational information to understand the extent of damage in each region. This data is then analyzed by artificial intelligence using machine learning libraries such as TensorFlow to optimize disaster risk assessments and evacuation routes.

[0276] Based on the analyzed data, the device uses the Google Maps API to display the optimal evacuation route based on the user's current location. Information on shelter occupancy and supply management is also updated in real time and displayed on the device's screen. The device is designed for devices such as smartphones and smart glasses, providing users with information visually and audibly.

[0277] Users evacuate safely based on the information provided. After evacuation, they provide feedback to the system to help other users evacuate and contribute to improving the overall accuracy of the information. For example, if a user is in an area where flooding is predicted, the system analyzes water level information and social media posts in that area and provides real-time information on the safest evacuation routes and shelters.

[0278] An example of a prompt might be: "When flood damage is predicted, what data and technology should be used to provide User A with the shortest evacuation route and evacuation shelter information in real time on their smart glasses?"

[0279] This system allows users to quickly and reliably obtain information to protect themselves from disasters, contributing to improved safety throughout the city.

[0280] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0281] Step 1:

[0282] The server collects data on the disaster area from the Internet, environmental sensors, SNS, etc. As a specific operation, it obtains data in real time through APIs from each information source. The input of information includes water level data, weather information, SNS posted images, etc., and these are integrated into the server. The output is the raw data set.

[0283] Step 2:

[0284] The server analyzes the collected raw data set by AI. Using machine learning models such as TensorFlow, it collates the data from environmental sensors and image data on SNS to evaluate the risk of disaster. The input is the raw data integrated in Step 1, and the output is the analysis result of the risk level for each region and the necessity of evacuation. As specific data processing, pattern recognition of matching data and risk scoring are performed.

[0285] Step 3:

[0286] The server generates evacuation information based on the analysis results and sends it to the terminal. Specifically, using the Google Maps API, it designs evacuation routes and maps the vacancy information of shelters. The input is the risk level and current location information obtained in Step 2, and the output is the optimized evacuation route and shelter information.

[0287] Step 4:

[0288] The terminal displays the evacuation information received from the server to the user. In a specific operation, on the screens of smartphones or smart glasses, the evacuation route and the location of shelters are displayed on the map. If voice notification is set, it is also performed. The input is the output information of Step 3, and the output is the evacuation information presented to the user.

[0289] Step 5:

[0290] Users evacuate based on the information provided and send feedback to the server after completing the evacuation. Specifically, they input information such as obstacles and congestion along the evacuation route via a terminal. The input is user feedback, and the output is the registration of that feedback in the system's database. This improves the accuracy of future analysis and information provision.

[0291] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0292] This invention provides a system aimed at rapidly collecting, analyzing, and providing information during natural disasters, and further enhancing support by understanding the emotional state of users. This system mainly consists of a server, terminals, users, and an emotion engine.

[0293] The server collects data in real time from various sources, including network services, sensor networks, and weather information providers. This data is analyzed using AI-based data analysis tools to not only assess the extent of the damage but also predict future disaster risks.

[0294] The emotion engine analyzes data acquired from the user to determine their emotions. This engine takes in text data, voice data, or real-time interaction data provided by the user from their mobile device or PC as emotion data to understand the user's emotional state. Furthermore, based on the analysis of the emotional state, it determines the communication method optimized for the user and reflects it on the device through the information delivery means.

[0295] The device uses information on evacuation routes and locations transmitted from the server, along with analysis results from the emotion engine, to adjust how it guides and supports the user. For example, if it determines that the user is experiencing high levels of anxiety, it may suggest notifying emergency contacts or connecting the user to organizations that provide psychological support.

[0296] Users can act according to the information provided through their devices to ensure their own safety. They can also contribute to improving the system's functionality by inputting information about evacuation destinations and supply needs, and providing feedback. If necessary, they can also input their emotional state, which will allow the system to provide even more refined support plans.

[0297] As a concrete example, in a situation where evacuation is necessary due to heavy rain, the server predicts the risk of flooding based on river water level data, and the terminal notifies the user of this information. The emotion engine detects anxiety and stress from the content of the message sent by the user and simultaneously provides guidance on psychological support services through the terminal. In this way, the entire system protects the safety of disaster victims and realizes multifaceted support, including psychological support.

[0298] The following describes the processing flow.

[0299] Step 1:

[0300] The server collaborates with network services, environmental sensors, and weather information providers to collect real-time information from disaster-stricken areas. This allows the server to obtain the latest flood and weather data and identify the extent of the disaster's impact.

[0301] Step 2:

[0302] The server processes the collected data by means of data analysis and evaluates the disaster situation using an AI algorithm. The analysis results indicate which areas have suffered more serious damage, and based on this information, the server generates evacuation advisories and evacuation route plans.

[0303] Step 3:

[0304] The emotion engine analyzes the text messages and voice data provided by the user to determine the user's emotional state. Based on this analysis result, if the user is experiencing anxiety or stress, the server selects an appropriate support method.

[0305] Step 4:

[0306] The terminal receives the evacuation information sent from the server and the analysis result from the emotion engine and notifies the user. Specifically, it displays a message according to the user's current emotional state and proposes access to psychological support services if necessary.

[0307] Step 5: <000​​​​​​​​​​​​​​​​​​

[0313] During natural disasters, it is crucial to collect, analyze, and provide information quickly and accurately. However, existing systems lacked the functionality to provide appropriate support while considering the emotional state of users. Therefore, a support system is needed that can ensure the psychological safety of disaster victims.

[0314] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0315] In this invention, the server includes data acquisition means, data analysis means, and support information provision means. This makes it possible to acquire accurate information in real time when a natural disaster occurs and to provide optimal support information according to the user's emotional state.

[0316] "Data acquisition methods" refer to means of collecting information from multiple sources and gathering data necessary for assessing the extent of the disaster.

[0317] "Data analysis methods" refer to means of analyzing acquired data to assess the risk of disaster.

[0318] "Information provision means" refers to the means of providing users with evacuation routes and evacuation locations in real time based on analysis results.

[0319] "Emotion analysis means" refers to a method for analyzing input data from a terminal to determine the user's emotional state.

[0320] A "support information provision method" is a means of providing users with optimal support information based on the results of emotion analysis.

[0321] A "feedback receiving mechanism" is a means of receiving feedback from users and updating system information.

[0322] A "predictive tool" is a means of using artificial intelligence to predict the extent of a disaster and to assess the likelihood of future disasters.

[0323] "Information management means" refers to the means of continuously updating the occupancy status and shortage status of supplies at evacuation centers and displaying necessary information.

[0324] The invention will now be described in terms of embodiments. This system is designed to provide rapid and efficient information and user support in the event of a natural disaster, and its main components include a server, terminals, users, and an emotion engine.

[0325] The server is responsible for acquiring data from multiple sources. These sources include network services, sensor networks, and weather information providers. The HTTP protocol is used to acquire this data, collecting it in JSON format from APIs. The collected data is then analyzed using TensorFlow, an open-source machine learning platform. The analysis results are used to assess the extent of damage and predict future disaster risks.

[0326] The emotion engine is designed to understand the user's emotional state. It analyzes text and audio data provided by the user via mobile devices or PCs, and uses natural language processing technology to determine emotions. This process utilizes the emotion analysis library "emotion-lib," which makes it possible to quantify the user's anxiety and stress levels.

[0327] The device provides information and support to the user. In addition to evacuation route and location information transmitted from the server, it uses sentiment analysis results to determine the appropriate support method based on the user's situation. For example, if the user shows strong anxiety, the device will launch an emergency contact app and display psychological support services. It also uses the Google Maps API to provide safe evacuation routes in real time.

[0328] Users can take safe actions based on the information they receive through their devices. They can also send feedback to the system regarding the occupancy status of evacuation centers and the need for supplies. This feedback contributes to improving the accuracy of data analysis on the server.

[0329] As a concrete example, consider a situation where evacuation is necessary due to heavy rain. In this case, the server predicts the risk of flooding based on river water level data and sends this information to the terminal. The emotion engine detects anxiety from the user's message and introduces psychological support services through the terminal. At the same time, the terminal displays an evacuation route suitable for the user on Google Maps.

[0330] The following prompt statements are used as example inputs to the generative AI model.

[0331] "User message: 'I'm worried about today's heavy rain.' Analyze this message and determine the user's sentiment."

[0332] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0333] Step 1:

[0334] The server retrieves data from information sources, including network services, sensor networks, and weather information providers. The input data is weather data in JSON format obtained from each information source. This data is collected via the HTTP protocol and prepared for the next analysis step. Specifically, it queries real-time precipitation and wind speed data via APIs.

[0335] Step 2:

[0336] The server analyzes the acquired data. The input data is the weather data collected in Step 1. TensorFlow is used to analyze the data, assess the extent of the damage, and predict future disaster risks. This data processing involves applying machine learning algorithms using analytical models. The analysis results are output as a risk score indicating the likelihood of disaster.

[0337] Step 3:

[0338] The emotion engine collects and analyzes data from users. Input consists of text messages and audio data provided by users via mobile devices or PCs. It uses emotion-lib to extract emotions from the text and determines the emotional state through natural language processing. Data calculations quantify stress and anxiety, outputting them as emotional states. Specifically, it analyzes the user message "I'm worried about today's heavy rain" to determine the emotional state.

[0339] Step 4:

[0340] The device provides information based on analysis results from the server and the output of the emotion engine. Inputs are the risk score from Step 2 and the emotional state from Step 3. Using these, it presents the user with optimal evacuation route information and psychological support information. Specific actions include displaying evacuation routes using the Google Maps API and launching emergency contact apps.

[0341] Step 5:

[0342] The user acts based on the information provided by the terminal. The data entered is the evacuation information provided in step 4. The user takes safe evacuation actions and enters feedback into the terminal as needed. This feedback provides specific information about the shortage of goods in the disaster area and the capacity of evacuation centers. Particularly important feedback is sent to the server and used to improve the accuracy of the system.

[0343] (Application Example 2)

[0344] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0345] In the event of a natural disaster, it is difficult to quickly and accurately grasp the extent of the damage, provide appropriate evacuation information, and offer support that takes into account the emotional state of users. Furthermore, there is a need to reduce psychological anxiety during disasters, efficiently incorporate user feedback into the system, and realize safe and smooth support for disaster victims.

[0346] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0347] In this invention, the server includes data collection means for collecting information from multiple sources to determine the extent of damage in the event of a natural disaster, data analysis means for analyzing the collected data and evaluating the risk of damage, information provision means for providing evacuation routes and shelters in real time based on the analysis results, and emotion analysis means for analyzing the user's emotional state and providing psychological support as needed. This enables the rapid and appropriate provision of disaster information while also providing multifaceted support that takes into account the user's psychological state.

[0348] "Data collection methods" refer to means of collecting information from multiple sources to assess the extent of damage during a natural disaster.

[0349] "Data analysis methods" refer to means of analyzing collected data to assess the risk of disaster.

[0350] "Information provision means" refers to means of providing evacuation routes and evacuation locations in real time based on analysis results.

[0351] "Emotional analysis tools" are means of analyzing a user's emotional state and providing psychological support as needed.

[0352] A "feedback receiving mechanism" is a means of receiving feedback from users and updating system information.

[0353] A "predictive tool" is a method of predicting the extent of a disaster using artificial intelligence based on collected data.

[0354] "Information management means" refers to the means of continuously updating and displaying the occupancy status of evacuation centers and the shortage status of supplies.

[0355] The system to realize this application includes various hardware and software. When a natural disaster occurs, the server collects data in real time from specific sources and analyzes this data using AI to determine the extent of the damage.

[0356] The server acquires information from network services and sensors when collecting data, and manages it on Google Cloud or similar cloud services. It also utilizes deep learning algorithms to understand the situation in disaster-stricken areas and accurately provide information on evacuation routes and shelters. This is supported by ML frameworks such as TensorFlow.

[0357] The terminal functions as an interface for providing information to the user. These terminals, such as smartphones and smart glasses, manage user interaction. These devices use Firebase Cloud Messaging to provide real-time notifications and, as needed, select and present psychological support solutions to the user.

[0358] The emotion analysis system analyzes voice and text data sent by the user to determine the user's emotions. It utilizes speech recognition technology, employing tools such as IBM Watson's Tone Analyzer, to understand the user's emotional state.

[0359] Users receive information from the system, make decisions about their actions, and provide feedback if necessary. This feedback allows the system to make further improvements in preparation for future disasters.

[0360] As a concrete example, in the event of an evacuation advisory due to heavy rain, the server quickly analyzes river water level information and assesses the level of danger. It then notifies the terminal of information about nearby evacuation sites. If the sentiment analysis system detects that the user is feeling anxious, the terminal displays interactive guidance that provides psychological support. Below are examples of prompts generated using a generative AI model:

[0361] "You are your mother's care planner. If you recently noticed signs that your mother is feeling lonely, how would you respond? Please create a notification message."

[0362] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0363] Step 1:

[0364] The server collects information in real time from multiple data sources through sensors and network services. Inputs include weather data, geological information, and river water level data, which are aggregated in cloud storage. The collected data is stored in a database and used for subsequent data analysis.

[0365] Step 2:

[0366] The server processes the collected information using data analysis tools. It uses various disaster information obtained from a cloud-based database as input and analyzes it using AI algorithms. Specifically, it runs models that evaluate the risk of floods and earthquakes using tools like TensorFlow, and generates a risk assessment report as output.

[0367] Step 3:

[0368] The server generates information on evacuation routes and shelters based on the analysis results. It uses a risk assessment report as input to evaluate the capacity and accessibility of evacuation shelters. As output, it creates a list of recommended evacuation routes and shelters, which is then passed on to the next step.

[0369] Step 4:

[0370] The device notifies the user of evacuation information received from the server. It retrieves evacuation information from the server as input and sends push notifications to smartphones and smart glasses using Firebase Cloud Messaging. The information is displayed to the user visually or audibly to help them respond immediately.

[0371] Step 5:

[0372] The emotion analysis method analyzes user messages and voice data to determine their psychological state. It takes real-time chats and voice memos as input data and analyzes emotions using the IBM Watson API. As output, it creates an emotion state report and generates corresponding countermeasures in the next step.

[0373] Step 6:

[0374] The device provides psychological support information tailored to the user's emotional state. It uses an emotional state report as input, and if the user is feeling anxious, it provides information on relaxation methods and psychological support services. The user interface displays preventative measures and messages to promote reassurance.

[0375] Step 7:

[0376] Users proceed with evacuation actions based on the information provided and return feedback to the system. For example, they report the situation at evacuation centers and the necessary supplies. The system receives user feedback as input and records it in a database on the server for future disaster response.

[0377] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0378] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0379] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0380] [Third Embodiment]

[0381] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0382] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0383] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0384] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0385] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0386] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0387] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0388] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0389] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0390] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0391] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0392] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0393] This invention provides a system for rapid and accurate information gathering, analysis, and provision during natural disasters. The system consists of a server, terminals, and users, each responsible for a specific function.

[0394] The server collects disaster information in real time from multiple data sources. Specifically, it acquires data from the internet, social networking services, environmental sensors, and weather information providers. This data is processed using AI-based data analysis methods to evaluate the specific damage situation in each region. For example, by comparing sensing data of rising river levels in a certain area with images posted on social media, the risk of flooding can be determined.

[0395] The terminal appropriately displays data provided by the server to the user. The terminal uses the user's current location information to calculate the optimal evacuation route and display it on a map. Furthermore, it can provide real-time updated information on the capacity of evacuation centers and the shortage of supplies. If the user requires voice notification, it can also transmit that information via voice through integration with the disaster prevention radio system.

[0396] Users can input information about their evacuation destination and necessary supplies through this system. This information is sent to the server as feedback and contributes to improving the accuracy of future data analysis and information provision. For example, if a user voluntarily posts their evacuation location on social media, the server will reflect that data as useful information for other evacuees.

[0397] As a concrete example, if urban flooding is predicted, the server analyzes the risk of flooding based on river water level sensors and social media posts, and sends the results to the terminal. The terminal issues an alert to the user and guides them to the shortest and safest evacuation route and available shelters. The user evacuates according to the instructions, and after completing the evacuation, they can provide feedback on the information to help other residents evacuate.

[0398] In this way, the entire system works in conjunction, and through a series of processes from information collection and analysis to provision and feedback, it aims to ensure the rapid evacuation of disaster victims and the safety of human lives.

[0399] The following describes the processing flow.

[0400] Step 1:

[0401] The server connects to information sources such as the internet, social networking services, environmental sensors, and weather information providers to collect data. This includes using SNS APIs to retrieve the latest posts relevant to a specific area and pulling environmental data such as water levels and wind speed from sensor databases in real time.

[0402] Step 2:

[0403] The server passes the collected data to a data analysis system, which uses AI to assess the extent of the damage. The server runs an AI model to perform image recognition and text mining, thereby identifying risks such as river flooding and road closures. The analysis results are organized by affected area and form the basis of the information provided to users.

[0404] Step 3:

[0405] Based on the analysis results, the server generates evacuation advisories and warning messages. Furthermore, it creates a comprehensive evacuation plan, including the location and capacity of evacuation centers, and traffic information, and sends it to the terminal. This information is updated in real time as the situation develops.

[0406] Step 4:

[0407] The terminal receives information sent from the server and notifies the user of its contents. The terminal uses the user's location information to calculate an individually optimized evacuation route and displays it on a map. It also informs the user of the current availability of evacuation shelters, helping them to secure an appropriate evacuation location.

[0408] Step 5:

[0409] Users will initiate swift and safe evacuation based on the information provided on their devices. Users will also contribute to updating the system's information by inputting information about their evacuation destination and necessary supplies via their devices, and feeding this information back to the server.

[0410] Step 6:

[0411] The server incorporates user feedback and updates the system's overall information. Based on this feedback, further data analysis is performed, ensuring the continued provision of highly accurate information. This allows for continuous improvement of the system's effectiveness and reliability.

[0412] (Example 1)

[0413] Next, we will describe Example 1. 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."

[0414] During natural disasters, rapid and accurate information gathering and analysis are crucial, as is the need for appropriate evacuation guidance and support for those affected. However, conventional systems have struggled to collect and analyze data from diverse sources in real time to provide users with useful information. Furthermore, mechanisms for updating and providing users with real-time information on the capacity of evacuation centers and the shortage of supplies have been insufficient.

[0415] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0416] In this invention, the server includes an information acquisition means that collects data from multiple sources in the event of a natural disaster to determine the extent of the damage; an information analysis means that analyzes the collected data using a large-scale data processing means to assess the risk of damage; and an information communication means that provides evacuation routes and evacuation locations in real time based on the analysis results. This enables users to receive complex disaster information in real time and obtain specific and rapid guidelines for optimal evacuation.

[0417] "Information acquisition methods" refer to technologies that collect data from various sources such as the internet, social networking services, environmental sensors, and weather information agencies when natural disasters occur.

[0418] "Information analysis methods" refer to technologies that process collected data and use AI technology to assess the risk level of the disaster.

[0419] "Information and communication means" refers to technology that provides users with information on evacuation routes and evacuation locations in real time, based on analysis results.

[0420] "Information receiving means" refers to technology that receives feedback from users and updates the information of the entire system.

[0421] "Route calculation means" refers to a technology that calculates and provides the optimal evacuation route based on the user's location information.

[0422] "Voice communication means" refers to technology that transmits warnings and instructions using voice.

[0423] "Predictive information generation means" refers to a technology that uses AI to predict future disaster situations based on collected data.

[0424] "Situation management means" refers to technology that continuously receives information on the occupancy status of evacuation centers and the shortage of supplies, and displays it to the user.

[0425] This invention is designed to realize a system that enables rapid and accurate information gathering, analysis, and provision during natural disasters. The system mainly consists of servers, terminals, and users, each playing its own unique role.

[0426] The server uses information acquisition methods to collect data from diverse sources such as the internet, social networking services, environmental sensors, and weather information agencies. This data is then processed by information analysis methods, and analysis is performed using AI technology, particularly deep learning frameworks such as TensorFlow and PyTorch. As a result of the analysis, it is possible to evaluate the specific damage situation in each region and measure the risk. For example, the risk of flooding can be determined by comparing river water level rise data in a certain area with images posted on social media.

[0427] The terminal receives analysis results transmitted from the server and functions as a means of information communication. The terminal uses GPS to determine the user's current location and calculates a safe evacuation route using the Google Maps API, etc. This calculation result, as well as information on the capacity of evacuation centers and supplies, is displayed on the terminal in real time and communicated to the user. In addition, it is possible to convey evacuation orders and warnings by voice using voice communication means.

[0428] Users can provide feedback to the system regarding evacuation destinations and shortages of supplies obtained through information receiving means. This information is sent to the server and used as preparation for the next disaster using predictive information generation means. For example, if a user posts about the situation at an evacuation center on social media, the server collects that data and shares the analysis results with other evacuees.

[0429] An example of a prompt statement could be input to a generative AI model: "If flooding is predicted, develop an evacuation plan for a local city. In this process, how will you collect, analyze, and provide information to the user?"

[0430] This system enables rapid evacuation and information dissemination during natural disasters by coordinating servers, terminals, and users.

[0431] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0432] Step 1:

[0433] The server begins the process of collecting data from the internet, social media, environmental sensors, and weather information agencies using information acquisition methods. As input, it receives API keys and access information for each data source. Using this information, it accesses each platform, collects relevant disaster information, and outputs it as formatted raw data. Specifically, this includes using the Twitter API to collect posts containing the keyword "flood."

[0434] Step 2:

[0435] The server analyzes the raw data collected in Step 1 using information analysis tools. A deep learning model using TensorFlow is used for this analysis. Social media posts and environmental sensor data are provided as input, and the damage situation and risk level are assessed based on this data. The analysis results are generated in JSON format as output, and include a risk assessment score for a specific area. A specific example of its operation is comparing images posted on social media with river water level information to predict flood risk.

[0436] Step 3:

[0437] The server uses information and communication means to send the analysis results obtained in step 2 to the terminal. It receives the analysis results in JSON format as input and sends them to the terminal as data packets. The output is the analysis result data received by the terminal used by the user. Specifically, the analysis results are provided to the terminal in real time via the API.

[0438] Step 4:

[0439] The terminal displays information, including evacuation instructions, to the user based on the received analysis results. The terminal receives data packets from the server as input and uses location information to calculate safe evacuation routes using the Google Maps API. The output is a visually navigable evacuation map, displayed on the screen in an easy-to-understand format. Additionally, it issues voice warnings via voice communication as needed.

[0440] Step 5:

[0441] Users check evacuation information displayed on their devices and take safe evacuation actions. They receive evacuation route and shelter information displayed on their device screen as input and act accordingly. After completing the evacuation, they provide feedback on the evacuation location and the shortage of supplies. The output is feedback data sent to the server. Specifically, users add information to the system's overall database by inputting the congestion status of evacuation shelters through a smartphone app.

[0442] (Application Example 1)

[0443] Next, we will explain Application Example 1. In the following explanation, 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."

[0444] In the event of a natural disaster, there is a need for a system that can quickly and accurately assess the extent of the damage and support safe evacuation. However, current systems lack real-time information provision and urban-scale disaster prediction, which can cause delays in the integration of information that users need. In particular, it is difficult to provide individual evacuation route guidance and to grasp the capacity of evacuation centers, and there is a need for means to improve user safety and convenience.

[0445] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0446] In this invention, the server includes data collection means for accumulating information when a natural disaster occurs, data analysis means for analyzing the information and evaluating the risk of damage, and disaster prediction means using artificial intelligence. This enables the provision of real-time evacuation information to users and rapid disaster response on a city scale.

[0447] A "system" refers to the entire device that has a series of functions for collecting and analyzing information in the event of a natural disaster and providing evacuation information to users.

[0448] A "data collection device" is a device that has the function of acquiring information necessary to understand the extent of the disaster from multiple information sources such as the internet and environmental sensors.

[0449] A "data analysis device" is a device that has the function of analyzing collected data and evaluating the risk and situation of a disaster.

[0450] An "information provision device" is a device that has the function of guiding users to evacuation routes and evacuation locations in real time based on the analyzed results.

[0451] A "feedback receiving means" is a device that has the function of receiving information and feedback from users and updating the information within the system.

[0452] Artificial intelligence is a technology that processes and analyzes large amounts of data to predict risks and evacuation routes during disasters.

[0453] A "mobile information display means" is a device that has the function of displaying necessary information in real time on a user's mobile device or visual device.

[0454] The system of the present invention is configured to quickly and accurately collect and analyze information in the event of a natural disaster and to provide users with necessary evacuation information.

[0455] The server collects data in real time from multiple sources, including the internet, environmental sensors, and social networking services. This data is used as foundational information to understand the extent of damage in each region. This data is then analyzed by artificial intelligence using machine learning libraries such as TensorFlow to optimize disaster risk assessments and evacuation routes.

[0456] Based on the analyzed data, the device uses the Google Maps API to display the optimal evacuation route based on the user's current location. Information on shelter occupancy and supply management is also updated in real time and displayed on the device's screen. The device is designed for devices such as smartphones and smart glasses, providing users with information visually and audibly.

[0457] Users evacuate safely based on the information provided. After evacuation, they provide feedback to the system to help other users evacuate and contribute to improving the overall accuracy of the information. For example, if a user is in an area where flooding is predicted, the system analyzes water level information and social media posts in that area and provides real-time information on the safest evacuation routes and shelters.

[0458] An example of a prompt might be: "When flood damage is predicted, what data and technology should be used to provide User A with the shortest evacuation route and evacuation shelter information in real time on their smart glasses?"

[0459] This system allows users to quickly and reliably obtain information to protect themselves from disasters, contributing to improved safety throughout the city.

[0460] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0461] Step 1:

[0462] The server collects data from disaster-stricken areas from the internet, environmental sensors, social media, and other sources. Specifically, it retrieves data in real time from each information source via APIs. Input data includes water level data, weather information, and images posted on social media, which are then collected on the server. The output is a raw dataset.

[0463] Step 2:

[0464] The server analyzes the collected raw dataset using AI. Using machine learning models such as TensorFlow, it matches environmental sensor data with image data from social media to assess the risk of disaster. The input is the raw data collected in step 1, and the output is the analysis of risk levels and evacuation needs for each region. Specific data processing involves pattern recognition of matching data and risk scoring.

[0465] Step 3:

[0466] The server generates evacuation information based on the analysis results and sends it to the terminal. Specifically, it uses the Google Maps API to design evacuation routes and map the availability of evacuation shelters. The input is the risk level and current location information obtained in step 2, and the output is the optimized evacuation route and evacuation shelter information.

[0467] Step 4:

[0468] The terminal displays evacuation information received from the server to the user. Specifically, it displays evacuation routes and the locations of evacuation shelters on a map on the screen of a smartphone or smart glasses. If voice notifications are set, they are also provided. The input is the output information from step 3, and the output is the evacuation information presented to the user.

[0469] Step 5:

[0470] Users evacuate based on the information provided and send feedback to the server after completing the evacuation. Specifically, they input information such as obstacles and congestion along the evacuation route via a terminal. The input is user feedback, and the output is the registration of that feedback in the system's database. This improves the accuracy of future analysis and information provision.

[0471] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0472] This invention provides a system aimed at rapidly collecting, analyzing, and providing information during natural disasters, and further enhancing support by understanding the emotional state of users. This system mainly consists of a server, terminals, users, and an emotion engine.

[0473] The server collects data in real time from various sources, including network services, sensor networks, and weather information providers. This data is analyzed using AI-based data analysis tools to not only assess the extent of the damage but also predict future disaster risks.

[0474] The emotion engine analyzes data acquired from the user to determine their emotions. This engine takes in text data, voice data, or real-time interaction data provided by the user from their mobile device or PC as emotion data to understand the user's emotional state. Furthermore, based on the analysis of the emotional state, it determines the communication method optimized for the user and reflects it on the device through the information delivery means.

[0475] The device uses information on evacuation routes and locations transmitted from the server, along with analysis results from the emotion engine, to adjust how it guides and supports the user. For example, if it determines that the user is experiencing high levels of anxiety, it may suggest notifying emergency contacts or connecting the user to organizations that provide psychological support.

[0476] Users can act according to the information provided through their devices to ensure their own safety. They can also contribute to improving the system's functionality by inputting information about evacuation destinations and supply needs, and providing feedback. If necessary, they can also input their emotional state, which will allow the system to provide even more refined support plans.

[0477] As a concrete example, in a situation where evacuation is necessary due to heavy rain, the server predicts the risk of flooding based on river water level data, and the terminal notifies the user of this information. The emotion engine detects anxiety and stress from the content of the message sent by the user and simultaneously provides guidance on psychological support services through the terminal. In this way, the entire system protects the safety of disaster victims and realizes multifaceted support, including psychological support.

[0478] The following describes the processing flow.

[0479] Step 1:

[0480] The server collaborates with network services, environmental sensors, and weather information providers to collect real-time information from disaster-stricken areas. This allows the server to obtain the latest flood and weather data and identify the extent of the disaster's impact.

[0481] Step 2:

[0482] The server processes the collected data using data analysis tools and assesses the extent of the damage using AI algorithms. The analysis results indicate which areas have suffered the most severe damage, and based on this information, the server generates evacuation advisories and evacuation route plans.

[0483] Step 3:

[0484] The emotion engine analyzes text messages and voice data provided by the user to determine their emotional state. Based on this analysis, if the user is experiencing anxiety or stress, the server selects an appropriate support method.

[0485] Step 4:

[0486] The terminal receives evacuation information sent from the server and analysis results from the emotion engine, and notifies the user. Specifically, it displays a message tailored to the user's current emotional state and, if necessary, suggests access to psychological support services.

[0487] Step 5:

[0488] Users review the information provided through their devices and begin taking action to evacuate safely. Users also provide feedback on their emotional state and details of their evacuation destination, which is sent to the server and used to update the system's information.

[0489] Step 6:

[0490] The server updates system-wide information based on user feedback and adjusts subsequent information delivery, taking into account changes in the user's emotional state. This enables the continuous provision of safe and appropriate support to the user.

[0491] (Example 2)

[0492] Next, we will describe Example 2. 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."

[0493] During natural disasters, it is crucial to collect, analyze, and provide information quickly and accurately. However, existing systems lacked the functionality to provide appropriate support while considering the emotional state of users. Therefore, a support system is needed that can ensure the psychological safety of disaster victims.

[0494] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0495] In this invention, the server includes data acquisition means, data analysis means, and support information provision means. This makes it possible to acquire accurate information in real time when a natural disaster occurs and to provide optimal support information according to the user's emotional state.

[0496] "Data acquisition methods" refer to means of collecting information from multiple sources and gathering data necessary for assessing the extent of the disaster.

[0497] "Data analysis methods" refer to means of analyzing acquired data to assess the risk of disaster.

[0498] "Information provision means" refers to the means of providing users with evacuation routes and evacuation locations in real time based on analysis results.

[0499] "Emotion analysis means" refers to a method for analyzing input data from a terminal to determine the user's emotional state.

[0500] A "support information provision method" is a means of providing users with optimal support information based on the results of emotion analysis.

[0501] A "feedback receiving mechanism" is a means of receiving feedback from users and updating system information.

[0502] A "predictive tool" is a means of using artificial intelligence to predict the extent of a disaster and to assess the likelihood of future disasters.

[0503] "Information management means" refers to the means of continuously updating the occupancy status and shortage status of supplies at evacuation centers and displaying necessary information.

[0504] The invention will now be described in terms of embodiments. This system is designed to provide rapid and efficient information and user support in the event of a natural disaster, and its main components include a server, terminals, users, and an emotion engine.

[0505] The server is responsible for acquiring data from multiple sources. These sources include network services, sensor networks, and weather information providers. The HTTP protocol is used to acquire this data, collecting it in JSON format from APIs. The collected data is then analyzed using TensorFlow, an open-source machine learning platform. The analysis results are used to assess the extent of damage and predict future disaster risks.

[0506] The emotion engine is designed to understand the user's emotional state. It analyzes text and audio data provided by the user via mobile devices or PCs, and uses natural language processing technology to determine emotions. This process utilizes the emotion analysis library "emotion-lib," which makes it possible to quantify the user's anxiety and stress levels.

[0507] The device provides information and support to the user. In addition to evacuation route and location information transmitted from the server, it uses sentiment analysis results to determine the appropriate support method based on the user's situation. For example, if the user shows strong anxiety, the device will launch an emergency contact app and display psychological support services. It also uses the Google Maps API to provide safe evacuation routes in real time.

[0508] Users can take safe actions based on the information they receive through their devices. They can also send feedback to the system regarding the occupancy status of evacuation centers and the need for supplies. This feedback contributes to improving the accuracy of data analysis on the server.

[0509] As a concrete example, consider a situation where evacuation is necessary due to heavy rain. In this case, the server predicts the risk of flooding based on river water level data and sends this information to the terminal. The emotion engine detects anxiety from the user's message and introduces psychological support services through the terminal. At the same time, the terminal displays an evacuation route suitable for the user on Google Maps.

[0510] The following prompt statements are used as example inputs to the generative AI model.

[0511] "User message: 'I'm worried about today's heavy rain.' Analyze this message and determine the user's sentiment."

[0512] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0513] Step 1:

[0514] The server retrieves data from information sources, including network services, sensor networks, and weather information providers. The input data is weather data in JSON format obtained from each information source. This data is collected via the HTTP protocol and prepared for the next analysis step. Specifically, it queries real-time precipitation and wind speed data via APIs.

[0515] Step 2:

[0516] The server analyzes the acquired data. The input data is the weather data collected in Step 1. TensorFlow is used to analyze the data, assess the extent of the damage, and predict future disaster risks. This data processing involves applying machine learning algorithms using analytical models. The analysis results are output as a risk score indicating the likelihood of disaster.

[0517] Step 3:

[0518] The emotion engine collects and analyzes data from users. Input consists of text messages and audio data provided by users via mobile devices or PCs. It uses emotion-lib to extract emotions from the text and determines the emotional state through natural language processing. Data calculations quantify stress and anxiety, outputting them as emotional states. Specifically, it analyzes the user message "I'm worried about today's heavy rain" to determine the emotional state.

[0519] Step 4:

[0520] The device provides information based on analysis results from the server and the output of the emotion engine. Inputs are the risk score from Step 2 and the emotional state from Step 3. Using these, it presents the user with optimal evacuation route information and psychological support information. Specific actions include displaying evacuation routes using the Google Maps API and launching emergency contact apps.

[0521] Step 5:

[0522] The user acts based on the information provided by the terminal. The data entered is the evacuation information provided in step 4. The user takes safe evacuation actions and enters feedback into the terminal as needed. This feedback provides specific information about the shortage of goods in the disaster area and the capacity of evacuation centers. Particularly important feedback is sent to the server and used to improve the accuracy of the system.

[0523] (Application Example 2)

[0524] Next, we will explain application example 2. In the following explanation, 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."

[0525] In the event of a natural disaster, it is difficult to quickly and accurately grasp the extent of the damage, provide appropriate evacuation information, and offer support that takes into account the emotional state of users. Furthermore, there is a need to reduce psychological anxiety during disasters, efficiently incorporate user feedback into the system, and realize safe and smooth support for disaster victims.

[0526] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0527] In this invention, the server includes data collection means for collecting information from multiple sources to determine the extent of damage in the event of a natural disaster, data analysis means for analyzing the collected data and evaluating the risk of damage, information provision means for providing evacuation routes and shelters in real time based on the analysis results, and emotion analysis means for analyzing the user's emotional state and providing psychological support as needed. This enables the rapid and appropriate provision of disaster information while also providing multifaceted support that takes into account the user's psychological state.

[0528] "Data collection methods" refer to means of collecting information from multiple sources to assess the extent of damage during a natural disaster.

[0529] "Data analysis methods" refer to means of analyzing collected data to assess the risk of disaster.

[0530] "Information provision means" refers to means of providing evacuation routes and evacuation locations in real time based on analysis results.

[0531] "Emotional analysis tools" are means of analyzing a user's emotional state and providing psychological support as needed.

[0532] A "feedback receiving mechanism" is a means of receiving feedback from users and updating system information.

[0533] A "predictive tool" is a method of predicting the extent of a disaster using artificial intelligence based on collected data.

[0534] "Information management means" refers to the means of continuously updating and displaying the occupancy status of evacuation centers and the shortage status of supplies.

[0535] The system to realize this application includes various hardware and software. When a natural disaster occurs, the server collects data in real time from specific sources and analyzes this data using AI to determine the extent of the damage.

[0536] The server acquires information from network services and sensors when collecting data, and manages it on Google Cloud or similar cloud services. It also utilizes deep learning algorithms to understand the situation in disaster-stricken areas and accurately provide information on evacuation routes and shelters. This is supported by ML frameworks such as TensorFlow.

[0537] The terminal functions as an interface for providing information to the user. These terminals, such as smartphones and smart glasses, manage user interaction. These devices use Firebase Cloud Messaging to provide real-time notifications and, as needed, select and present psychological support solutions to the user.

[0538] The emotion analysis system analyzes voice and text data sent by the user to determine the user's emotions. It utilizes speech recognition technology, employing tools such as IBM Watson's Tone Analyzer, to understand the user's emotional state.

[0539] Users receive information from the system, make decisions about their actions, and provide feedback if necessary. This feedback allows the system to make further improvements in preparation for future disasters.

[0540] As a concrete example, in the event of an evacuation advisory due to heavy rain, the server quickly analyzes river water level information and assesses the level of danger. It then notifies the terminal of information about nearby evacuation sites. If the sentiment analysis system detects that the user is feeling anxious, the terminal displays interactive guidance that provides psychological support. Below are examples of prompts generated using a generative AI model:

[0541] "You are your mother's care planner. If you recently noticed signs that your mother is feeling lonely, how would you respond? Please create a notification message."

[0542] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0543] Step 1:

[0544] The server collects information in real time from multiple data sources through sensors and network services. Inputs include weather data, geological information, and river water level data, which are aggregated in cloud storage. The collected data is stored in a database and used for subsequent data analysis.

[0545] Step 2:

[0546] The server processes the collected information using data analysis tools. It uses various disaster information obtained from a cloud-based database as input and analyzes it using AI algorithms. Specifically, it runs models that evaluate the risk of floods and earthquakes using tools like TensorFlow, and generates a risk assessment report as output.

[0547] Step 3:

[0548] The server generates information on evacuation routes and shelters based on the analysis results. It uses a risk assessment report as input to evaluate the capacity and accessibility of evacuation shelters. As output, it creates a list of recommended evacuation routes and shelters, which is then passed on to the next step.

[0549] Step 4:

[0550] The device notifies the user of evacuation information received from the server. It retrieves evacuation information from the server as input and sends push notifications to smartphones and smart glasses using Firebase Cloud Messaging. The information is displayed to the user visually or audibly to help them respond immediately.

[0551] Step 5:

[0552] The emotion analysis method analyzes user messages and voice data to determine their psychological state. It takes real-time chats and voice memos as input data and analyzes emotions using the IBM Watson API. As output, it creates an emotion state report and generates corresponding countermeasures in the next step.

[0553] Step 6:

[0554] The device provides psychological support information tailored to the user's emotional state. It uses an emotional state report as input, and if the user is feeling anxious, it provides information on relaxation methods and psychological support services. The user interface displays preventative measures and messages to promote reassurance.

[0555] Step 7:

[0556] Users proceed with evacuation actions based on the information provided and return feedback to the system. For example, they report the situation at evacuation centers and the necessary supplies. The system receives user feedback as input and records it in a database on the server for future disaster response.

[0557] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0558] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0559] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0560] [Fourth Embodiment]

[0561] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0562] As shown in Figure 7, the 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.

[0563] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0564] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0565] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0566] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0567] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0568] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0569] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0570] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0571] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0572] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0573] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0574] This invention provides a system for rapid and accurate information gathering, analysis, and provision during natural disasters. The system consists of a server, terminals, and users, each responsible for a specific function.

[0575] The server collects disaster information in real time from multiple data sources. Specifically, it acquires data from the internet, social networking services, environmental sensors, and weather information providers. This data is processed using AI-based data analysis methods to evaluate the specific damage situation in each region. For example, by comparing sensing data of rising river levels in a certain area with images posted on social media, the risk of flooding can be determined.

[0576] The terminal appropriately displays data provided by the server to the user. The terminal uses the user's current location information to calculate the optimal evacuation route and display it on a map. Furthermore, it can provide real-time updated information on the capacity of evacuation centers and the shortage of supplies. If the user requires voice notification, it can also transmit that information via voice through integration with the disaster prevention radio system.

[0577] Users can input information about their evacuation destination and necessary supplies through this system. This information is sent to the server as feedback and contributes to improving the accuracy of future data analysis and information provision. For example, if a user voluntarily posts their evacuation location on social media, the server will reflect that data as useful information for other evacuees.

[0578] As a concrete example, if urban flooding is predicted, the server analyzes the risk of flooding based on river water level sensors and social media posts, and sends the results to the terminal. The terminal issues an alert to the user and guides them to the shortest and safest evacuation route and available shelters. The user evacuates according to the instructions, and after completing the evacuation, they can provide feedback on the information to help other residents evacuate.

[0579] In this way, the entire system works in conjunction, and through a series of processes from information collection and analysis to provision and feedback, it aims to ensure the rapid evacuation of disaster victims and the safety of human lives.

[0580] The following describes the processing flow.

[0581] Step 1:

[0582] The server connects to information sources such as the internet, social networking services, environmental sensors, and weather information providers to collect data. This includes using SNS APIs to retrieve the latest posts relevant to a specific area and pulling environmental data such as water levels and wind speed from sensor databases in real time.

[0583] Step 2:

[0584] The server passes the collected data to a data analysis system, which uses AI to assess the extent of the damage. The server runs an AI model to perform image recognition and text mining, thereby identifying risks such as river flooding and road closures. The analysis results are organized by affected area and form the basis of the information provided to users.

[0585] Step 3:

[0586] Based on the analysis results, the server generates evacuation advisories and warning messages. Furthermore, it creates a comprehensive evacuation plan, including the location and capacity of evacuation centers, and traffic information, and sends it to the terminal. This information is updated in real time as the situation develops.

[0587] Step 4:

[0588] The terminal receives information sent from the server and notifies the user of its contents. The terminal uses the user's location information to calculate an individually optimized evacuation route and displays it on a map. It also informs the user of the current availability of evacuation shelters, helping them to secure an appropriate evacuation location.

[0589] Step 5:

[0590] Users will initiate swift and safe evacuation based on the information provided on their devices. Users will also contribute to updating the system's information by inputting information about their evacuation destination and necessary supplies via their devices, and feeding this information back to the server.

[0591] Step 6:

[0592] The server incorporates user feedback and updates the system's overall information. Based on this feedback, further data analysis is performed, ensuring the continued provision of highly accurate information. This allows for continuous improvement of the system's effectiveness and reliability.

[0593] (Example 1)

[0594] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0595] During natural disasters, rapid and accurate information gathering and analysis are crucial, as is the need for appropriate evacuation guidance and support for those affected. However, conventional systems have struggled to collect and analyze data from diverse sources in real time to provide users with useful information. Furthermore, mechanisms for updating and providing users with real-time information on the capacity of evacuation centers and the shortage of supplies have been insufficient.

[0596] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0597] In this invention, the server includes an information acquisition means that collects data from multiple sources in the event of a natural disaster to determine the extent of the damage; an information analysis means that analyzes the collected data using a large-scale data processing means to assess the risk of damage; and an information communication means that provides evacuation routes and evacuation locations in real time based on the analysis results. This enables users to receive complex disaster information in real time and obtain specific and rapid guidelines for optimal evacuation.

[0598] "Information acquisition methods" refer to technologies that collect data from various sources such as the internet, social networking services, environmental sensors, and weather information agencies when natural disasters occur.

[0599] "Information analysis methods" refer to technologies that process collected data and use AI technology to assess the risk level of the disaster.

[0600] "Information and communication means" refers to technology that provides users with information on evacuation routes and evacuation locations in real time, based on analysis results.

[0601] "Information receiving means" refers to technology that receives feedback from users and updates the information of the entire system.

[0602] "Route calculation means" refers to a technology that calculates and provides the optimal evacuation route based on the user's location information.

[0603] "Voice communication means" refers to technology that transmits warnings and instructions using voice.

[0604] "Predictive information generation means" refers to a technology that uses AI to predict future disaster situations based on collected data.

[0605] "Situation management means" refers to technology that continuously receives information on the occupancy status of evacuation centers and the shortage of supplies, and displays it to the user.

[0606] This invention is designed to realize a system that enables rapid and accurate information gathering, analysis, and provision during natural disasters. The system mainly consists of servers, terminals, and users, each playing its own unique role.

[0607] The server uses information acquisition methods to collect data from diverse sources such as the internet, social networking services, environmental sensors, and weather information agencies. This data is then processed by information analysis methods, and analysis is performed using AI technology, particularly deep learning frameworks such as TensorFlow and PyTorch. As a result of the analysis, it is possible to evaluate the specific damage situation in each region and measure the risk. For example, the risk of flooding can be determined by comparing river water level rise data in a certain area with images posted on social media.

[0608] The terminal receives analysis results transmitted from the server and functions as a means of information communication. The terminal uses GPS to determine the user's current location and calculates a safe evacuation route using the Google Maps API, etc. This calculation result, as well as information on the capacity of evacuation centers and supplies, is displayed on the terminal in real time and communicated to the user. In addition, it is possible to convey evacuation orders and warnings by voice using voice communication means.

[0609] Users can provide feedback to the system regarding evacuation destinations and shortages of supplies obtained through information receiving means. This information is sent to the server and used as preparation for the next disaster using predictive information generation means. For example, if a user posts about the situation at an evacuation center on social media, the server collects that data and shares the analysis results with other evacuees.

[0610] An example of a prompt statement could be input to a generative AI model: "If flooding is predicted, develop an evacuation plan for a local city. In this process, how will you collect, analyze, and provide information to the user?"

[0611] This system enables rapid evacuation and information dissemination during natural disasters by coordinating servers, terminals, and users.

[0612] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0613] Step 1:

[0614] The server begins the process of collecting data from the internet, social media, environmental sensors, and weather information agencies using information acquisition methods. As input, it receives API keys and access information for each data source. Using this information, it accesses each platform, collects relevant disaster information, and outputs it as formatted raw data. Specifically, this includes using the Twitter API to collect posts containing the keyword "flood."

[0615] Step 2:

[0616] The server analyzes the raw data collected in Step 1 using information analysis tools. A deep learning model using TensorFlow is used for this analysis. Social media posts and environmental sensor data are provided as input, and the damage situation and risk level are assessed based on this data. The analysis results are generated in JSON format as output, and include a risk assessment score for a specific area. A specific example of its operation is comparing images posted on social media with river water level information to predict flood risk.

[0617] Step 3:

[0618] The server uses information and communication means to send the analysis results obtained in step 2 to the terminal. It receives the analysis results in JSON format as input and sends them to the terminal as data packets. The output is the analysis result data received by the terminal used by the user. Specifically, the analysis results are provided to the terminal in real time via the API.

[0619] Step 4:

[0620] The terminal displays information, including evacuation instructions, to the user based on the received analysis results. The terminal receives data packets from the server as input and uses location information to calculate safe evacuation routes using the Google Maps API. The output is a visually navigable evacuation map, displayed on the screen in an easy-to-understand format. Additionally, it issues voice warnings via voice communication as needed.

[0621] Step 5:

[0622] Users check evacuation information displayed on their devices and take safe evacuation actions. They receive evacuation route and shelter information displayed on their device screen as input and act accordingly. After completing the evacuation, they provide feedback on the evacuation location and the shortage of supplies. The output is feedback data sent to the server. Specifically, users add information to the system's overall database by inputting the congestion status of evacuation shelters through a smartphone app.

[0623] (Application Example 1)

[0624] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0625] In the event of a natural disaster, there is a need for a system that can quickly and accurately assess the extent of the damage and support safe evacuation. However, current systems lack real-time information provision and urban-scale disaster prediction, which can cause delays in the integration of information that users need. In particular, it is difficult to provide individual evacuation route guidance and to grasp the capacity of evacuation centers, and there is a need for means to improve user safety and convenience.

[0626] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0627] In this invention, the server includes data collection means for accumulating information when a natural disaster occurs, data analysis means for analyzing the information and evaluating the risk of damage, and disaster prediction means using artificial intelligence. This enables the provision of real-time evacuation information to users and rapid disaster response on a city scale.

[0628] A "system" refers to the entire device that has a series of functions for collecting and analyzing information in the event of a natural disaster and providing evacuation information to users.

[0629] A "data collection device" is a device that has the function of acquiring information necessary to understand the extent of the disaster from multiple information sources such as the internet and environmental sensors.

[0630] A "data analysis device" is a device that has the function of analyzing collected data and evaluating the risk and situation of a disaster.

[0631] An "information provision device" is a device that has the function of guiding users to evacuation routes and evacuation locations in real time based on the analyzed results.

[0632] A "feedback receiving means" is a device that has the function of receiving information and feedback from users and updating the information within the system.

[0633] Artificial intelligence is a technology that processes and analyzes large amounts of data to predict risks and evacuation routes during disasters.

[0634] A "mobile information display means" is a device that has the function of displaying necessary information in real time on a user's mobile device or visual device.

[0635] The system of the present invention is configured to quickly and accurately collect and analyze information in the event of a natural disaster and to provide users with necessary evacuation information.

[0636] The server collects data in real time from multiple sources, including the internet, environmental sensors, and social networking services. This data is used as foundational information to understand the extent of damage in each region. This data is then analyzed by artificial intelligence using machine learning libraries such as TensorFlow to optimize disaster risk assessments and evacuation routes.

[0637] Based on the analyzed data, the device uses the Google Maps API to display the optimal evacuation route based on the user's current location. Information on shelter occupancy and supply management is also updated in real time and displayed on the device's screen. The device is designed for devices such as smartphones and smart glasses, providing users with information visually and audibly.

[0638] Users evacuate safely based on the information provided. After evacuation, they provide feedback to the system to help other users evacuate and contribute to improving the overall accuracy of the information. For example, if a user is in an area where flooding is predicted, the system analyzes water level information and social media posts in that area and provides real-time information on the safest evacuation routes and shelters.

[0639] An example of a prompt might be: "When flood damage is predicted, what data and technology should be used to provide User A with the shortest evacuation route and evacuation shelter information in real time on their smart glasses?"

[0640] This system allows users to quickly and reliably obtain information to protect themselves from disasters, contributing to improved safety throughout the city.

[0641] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0642] Step 1:

[0643] The server collects data from disaster-stricken areas from the internet, environmental sensors, social media, and other sources. Specifically, it retrieves data in real time from each information source via APIs. Input data includes water level data, weather information, and images posted on social media, which are then collected on the server. The output is a raw dataset.

[0644] Step 2:

[0645] The server analyzes the collected raw dataset using AI. Using machine learning models such as TensorFlow, it matches environmental sensor data with image data from social media to assess the risk of disaster. The input is the raw data collected in step 1, and the output is the analysis of risk levels and evacuation needs for each region. Specific data processing involves pattern recognition of matching data and risk scoring.

[0646] Step 3:

[0647] The server generates evacuation information based on the analysis results and sends it to the terminal. Specifically, it uses the Google Maps API to design evacuation routes and map the availability of evacuation shelters. The input is the risk level and current location information obtained in step 2, and the output is the optimized evacuation route and evacuation shelter information.

[0648] Step 4:

[0649] The terminal displays evacuation information received from the server to the user. Specifically, it displays evacuation routes and the locations of evacuation shelters on a map on the screen of a smartphone or smart glasses. If voice notifications are set, they are also provided. The input is the output information from step 3, and the output is the evacuation information presented to the user.

[0650] Step 5:

[0651] Users evacuate based on the information provided and send feedback to the server after completing the evacuation. Specifically, they input information such as obstacles and congestion along the evacuation route via a terminal. The input is user feedback, and the output is the registration of that feedback in the system's database. This improves the accuracy of future analysis and information provision.

[0652] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0653] This invention provides a system aimed at rapidly collecting, analyzing, and providing information during natural disasters, and further enhancing support by understanding the emotional state of users. This system mainly consists of a server, terminals, users, and an emotion engine.

[0654] The server collects data in real time from various sources, including network services, sensor networks, and weather information providers. This data is analyzed using AI-based data analysis tools to not only assess the extent of the damage but also predict future disaster risks.

[0655] The emotion engine analyzes data acquired from the user to determine their emotions. This engine takes in text data, voice data, or real-time interaction data provided by the user from their mobile device or PC as emotion data to understand the user's emotional state. Furthermore, based on the analysis of the emotional state, it determines the communication method optimized for the user and reflects it on the device through the information delivery means.

[0656] The device uses information on evacuation routes and locations transmitted from the server, along with analysis results from the emotion engine, to adjust how it guides and supports the user. For example, if it determines that the user is experiencing high levels of anxiety, it may suggest notifying emergency contacts or connecting the user to organizations that provide psychological support.

[0657] Users can act according to the information provided through their devices to ensure their own safety. They can also contribute to improving the system's functionality by inputting information about evacuation destinations and supply needs, and providing feedback. If necessary, they can also input their emotional state, which will allow the system to provide even more refined support plans.

[0658] As a concrete example, in a situation where evacuation is necessary due to heavy rain, the server predicts the risk of flooding based on river water level data, and the terminal notifies the user of this information. The emotion engine detects anxiety and stress from the content of the message sent by the user and simultaneously provides guidance on psychological support services through the terminal. In this way, the entire system protects the safety of disaster victims and realizes multifaceted support, including psychological support.

[0659] The following describes the processing flow.

[0660] Step 1:

[0661] The server collaborates with network services, environmental sensors, and weather information providers to collect real-time information from disaster-stricken areas. This allows the server to obtain the latest flood and weather data and identify the extent of the disaster's impact.

[0662] Step 2:

[0663] The server processes the collected data using data analysis tools and assesses the extent of the damage using AI algorithms. The analysis results indicate which areas have suffered the most severe damage, and based on this information, the server generates evacuation advisories and evacuation route plans.

[0664] Step 3:

[0665] The emotion engine analyzes text messages and voice data provided by the user to determine their emotional state. Based on this analysis, if the user is experiencing anxiety or stress, the server selects an appropriate support method.

[0666] Step 4:

[0667] The terminal receives evacuation information sent from the server and analysis results from the emotion engine, and notifies the user. Specifically, it displays a message tailored to the user's current emotional state and, if necessary, suggests access to psychological support services.

[0668] Step 5:

[0669] Users review the information provided through their devices and begin taking action to evacuate safely. Users also provide feedback on their emotional state and details of their evacuation destination, which is sent to the server and used to update the system's information.

[0670] Step 6:

[0671] The server updates system-wide information based on user feedback and adjusts subsequent information delivery, taking into account changes in the user's emotional state. This enables the continuous provision of safe and appropriate support to the user.

[0672] (Example 2)

[0673] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0674] During natural disasters, it is crucial to collect, analyze, and provide information quickly and accurately. However, existing systems lacked the functionality to provide appropriate support while considering the emotional state of users. Therefore, a support system is needed that can ensure the psychological safety of disaster victims.

[0675] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0676] In this invention, the server includes data acquisition means, data analysis means, and support information provision means. This makes it possible to acquire accurate information in real time when a natural disaster occurs and to provide optimal support information according to the user's emotional state.

[0677] "Data acquisition methods" refer to means of collecting information from multiple sources and gathering data necessary for assessing the extent of the disaster.

[0678] "Data analysis methods" refer to means of analyzing acquired data to assess the risk of disaster.

[0679] "Information provision means" refers to the means of providing users with evacuation routes and evacuation locations in real time based on analysis results.

[0680] "Emotion analysis means" refers to a method for analyzing input data from a terminal to determine the user's emotional state.

[0681] A "support information provision method" is a means of providing users with optimal support information based on the results of emotion analysis.

[0682] A "feedback receiving mechanism" is a means of receiving feedback from users and updating system information.

[0683] A "predictive tool" is a means of using artificial intelligence to predict the extent of a disaster and to assess the likelihood of future disasters.

[0684] "Information management means" refers to the means of continuously updating the occupancy status and shortage status of supplies at evacuation centers and displaying necessary information.

[0685] The invention will now be described in terms of embodiments. This system is designed to provide rapid and efficient information and user support in the event of a natural disaster, and its main components include a server, terminals, users, and an emotion engine.

[0686] The server is responsible for acquiring data from multiple sources. These sources include network services, sensor networks, and weather information providers. The HTTP protocol is used to acquire this data, collecting it in JSON format from APIs. The collected data is then analyzed using TensorFlow, an open-source machine learning platform. The analysis results are used to assess the extent of damage and predict future disaster risks.

[0687] The emotion engine is designed to understand the user's emotional state. It analyzes text and audio data provided by the user via mobile devices or PCs, and uses natural language processing technology to determine emotions. This process utilizes the emotion analysis library "emotion-lib," which makes it possible to quantify the user's anxiety and stress levels.

[0688] The device provides information and support to the user. In addition to evacuation route and location information transmitted from the server, it uses sentiment analysis results to determine the appropriate support method based on the user's situation. For example, if the user shows strong anxiety, the device will launch an emergency contact app and display psychological support services. It also uses the Google Maps API to provide safe evacuation routes in real time.

[0689] Users can take safe actions based on the information they receive through their devices. They can also send feedback to the system regarding the occupancy status of evacuation centers and the need for supplies. This feedback contributes to improving the accuracy of data analysis on the server.

[0690] As a concrete example, consider a situation where evacuation is necessary due to heavy rain. In this case, the server predicts the risk of flooding based on river water level data and sends this information to the terminal. The emotion engine detects anxiety from the user's message and introduces psychological support services through the terminal. At the same time, the terminal displays an evacuation route suitable for the user on Google Maps.

[0691] The following prompt statements are used as example inputs to the generative AI model.

[0692] "User message: 'I'm worried about today's heavy rain.' Analyze this message and determine the user's sentiment."

[0693] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0694] Step 1:

[0695] The server retrieves data from information sources, including network services, sensor networks, and weather information providers. The input data is weather data in JSON format obtained from each information source. This data is collected via the HTTP protocol and prepared for the next analysis step. Specifically, it queries real-time precipitation and wind speed data via APIs.

[0696] Step 2:

[0697] The server analyzes the acquired data. The input data is the weather data collected in Step 1. TensorFlow is used to analyze the data, assess the extent of the damage, and predict future disaster risks. This data processing involves applying machine learning algorithms using analytical models. The analysis results are output as a risk score indicating the likelihood of disaster.

[0698] Step 3:

[0699] The emotion engine collects and analyzes data from users. Input consists of text messages and audio data provided by users via mobile devices or PCs. It uses emotion-lib to extract emotions from the text and determines the emotional state through natural language processing. Data calculations quantify stress and anxiety, outputting them as emotional states. Specifically, it analyzes the user message "I'm worried about today's heavy rain" to determine the emotional state.

[0700] Step 4:

[0701] The device provides information based on analysis results from the server and the output of the emotion engine. Inputs are the risk score from Step 2 and the emotional state from Step 3. Using these, it presents the user with optimal evacuation route information and psychological support information. Specific actions include displaying evacuation routes using the Google Maps API and launching emergency contact apps.

[0702] Step 5:

[0703] The user acts based on the information provided by the terminal. The data entered is the evacuation information provided in step 4. The user takes safe evacuation actions and enters feedback into the terminal as needed. This feedback provides specific information about the shortage of goods in the disaster area and the capacity of evacuation centers. Particularly important feedback is sent to the server and used to improve the accuracy of the system.

[0704] (Application Example 2)

[0705] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0706] In the event of a natural disaster, it is difficult to quickly and accurately grasp the extent of the damage, provide appropriate evacuation information, and offer support that takes into account the emotional state of users. Furthermore, there is a need to reduce psychological anxiety during disasters, efficiently incorporate user feedback into the system, and realize safe and smooth support for disaster victims.

[0707] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0708] In this invention, the server includes data collection means for collecting information from multiple sources to determine the extent of damage in the event of a natural disaster, data analysis means for analyzing the collected data and evaluating the risk of damage, information provision means for providing evacuation routes and shelters in real time based on the analysis results, and emotion analysis means for analyzing the user's emotional state and providing psychological support as needed. This enables the rapid and appropriate provision of disaster information while also providing multifaceted support that takes into account the user's psychological state.

[0709] "Data collection methods" refer to means of collecting information from multiple sources to assess the extent of damage during a natural disaster.

[0710] "Data analysis methods" refer to means of analyzing collected data to assess the risk of disaster.

[0711] "Information provision means" refers to means of providing evacuation routes and evacuation locations in real time based on analysis results.

[0712] "Emotional analysis tools" are means of analyzing a user's emotional state and providing psychological support as needed.

[0713] A "feedback receiving mechanism" is a means of receiving feedback from users and updating system information.

[0714] A "predictive tool" is a method of predicting the extent of a disaster using artificial intelligence based on collected data.

[0715] "Information management means" refers to the means of continuously updating and displaying the occupancy status of evacuation centers and the shortage status of supplies.

[0716] The system to realize this application includes various hardware and software. When a natural disaster occurs, the server collects data in real time from specific sources and analyzes this data using AI to determine the extent of the damage.

[0717] The server acquires information from network services and sensors when collecting data, and manages it on Google Cloud or similar cloud services. It also utilizes deep learning algorithms to understand the situation in disaster-stricken areas and accurately provide information on evacuation routes and shelters. This is supported by ML frameworks such as TensorFlow.

[0718] The terminal functions as an interface for providing information to the user. These terminals, such as smartphones and smart glasses, manage user interaction. These devices use Firebase Cloud Messaging to provide real-time notifications and, as needed, select and present psychological support solutions to the user.

[0719] The emotion analysis system analyzes voice and text data sent by the user to determine the user's emotions. It utilizes speech recognition technology, employing tools such as IBM Watson's Tone Analyzer, to understand the user's emotional state.

[0720] Users receive information from the system, make decisions about their actions, and provide feedback if necessary. This feedback allows the system to make further improvements in preparation for future disasters.

[0721] As a concrete example, in the event of an evacuation advisory due to heavy rain, the server quickly analyzes river water level information and assesses the level of danger. It then notifies the terminal of information about nearby evacuation sites. If the sentiment analysis system detects that the user is feeling anxious, the terminal displays interactive guidance that provides psychological support. Below are examples of prompts generated using a generative AI model:

[0722] "You are your mother's care planner. If you recently noticed signs that your mother is feeling lonely, how would you respond? Please create a notification message."

[0723] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0724] Step 1:

[0725] The server collects information in real time from multiple data sources through sensors and network services. Inputs include weather data, geological information, and river water level data, which are aggregated in cloud storage. The collected data is stored in a database and used for subsequent data analysis.

[0726] Step 2:

[0727] The server processes the collected information using data analysis tools. It uses various disaster information obtained from a cloud-based database as input and analyzes it using AI algorithms. Specifically, it runs models that evaluate the risk of floods and earthquakes using tools like TensorFlow, and generates a risk assessment report as output.

[0728] Step 3:

[0729] The server generates information on evacuation routes and shelters based on the analysis results. It uses a risk assessment report as input to evaluate the capacity and accessibility of evacuation shelters. As output, it creates a list of recommended evacuation routes and shelters, which is then passed on to the next step.

[0730] Step 4:

[0731] The device notifies the user of evacuation information received from the server. It retrieves evacuation information from the server as input and sends push notifications to smartphones and smart glasses using Firebase Cloud Messaging. The information is displayed to the user visually or audibly to help them respond immediately.

[0732] Step 5:

[0733] The emotion analysis method analyzes user messages and voice data to determine their psychological state. It takes real-time chats and voice memos as input data and analyzes emotions using the IBM Watson API. As output, it creates an emotion state report and generates corresponding countermeasures in the next step.

[0734] Step 6:

[0735] The device provides psychological support information tailored to the user's emotional state. It uses an emotional state report as input, and if the user is feeling anxious, it provides information on relaxation methods and psychological support services. The user interface displays preventative measures and messages to promote reassurance.

[0736] Step 7:

[0737] Users proceed with evacuation actions based on the information provided and return feedback to the system. For example, they report the situation at evacuation centers and the necessary supplies. The system receives user feedback as input and records it in a database on the server for future disaster response.

[0738] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0739] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0740] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0741] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0742] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0743] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0744] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0745] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0746] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0747] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0748] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0749] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0750] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0751] 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.

[0752] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0753] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0754] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0755] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0756] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0757] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0758] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0759] The following is further disclosed regarding the embodiments described above.

[0760] (Claim 1)

[0761] A data collection method that gathers information from multiple sources to determine the extent of damage during a natural disaster,

[0762] A data analysis method that analyzes collected data and assesses the risk of disaster,

[0763] An information provision method that provides evacuation routes and evacuation locations in real time based on analysis results,

[0764] A feedback receiving mechanism that receives user feedback and updates system information,

[0765] A system that includes this.

[0766] (Claim 2)

[0767] The system according to claim 1, further comprising a prediction means that uses AI to predict the extent of damage based on collected data.

[0768] (Claim 3)

[0769] The system according to claim 1, further comprising an information management means for continuously updating and displaying the occupancy status of evacuation shelters and the shortage status of supplies.

[0770] "Example 1"

[0771] (Claim 1)

[0772] A means of acquiring information to determine the extent of damage in the event of a natural disaster by collecting data from multiple sources,

[0773] An information analysis method that analyzes collected data using large-scale data processing equipment to assess the risk of disaster,

[0774] Information and communication means that provide evacuation routes and shelters in real time based on analysis results,

[0775] An information receiving means that obtains information from users and updates the system content,

[0776] A route calculation means that provides the optimal evacuation route based on location information,

[0777] A voice communication means that provides warnings and instructions through voice information,

[0778] A system that includes this.

[0779] (Claim 2)

[0780] The system according to claim 1, further comprising a means for generating predictive information that automatically predicts disaster situations based on collected data.

[0781] (Claim 3)

[0782] The system according to claim 1, further comprising a status management means for receiving and displaying on a screen the occupancy status of evacuation centers and the shortage status of supplies in real time.

[0783] "Application Example 1"

[0784] (Claim 1)

[0785] A data collection method that gathers information from multiple sources to determine the extent of damage during a natural disaster,

[0786] A data analysis method that analyzes collected data and assesses the risk of disaster,

[0787] An information provision method that provides evacuation routes and evacuation locations in real time based on analysis results,

[0788] A feedback receiving mechanism that receives user feedback and updates system information,

[0789] A disaster prediction method that uses artificial intelligence to predict and present information on urban-scale disasters based on accumulated data,

[0790] A mobile information display means that displays information on the user's mobile device or visual device to provide support,

[0791] A system that includes this.

[0792] (Claim 2)

[0793] The system according to claim 1, further comprising a prediction means that predicts the extent of the disaster using artificial intelligence based on collected data.

[0794] (Claim 3)

[0795] The system according to claim 1, further comprising an information management means for continuously updating and displaying the occupancy status of evacuation shelters and the shortage status of supplies.

[0796] "Example 2 of combining an emotion engine"

[0797] (Claim 1)

[0798] A data acquisition method for obtaining information from multiple sources to determine the extent of damage during a natural disaster,

[0799] A data analysis method that analyzes acquired data and assesses the risk of disaster,

[0800] An information provision method that provides evacuation routes and evacuation locations in real time based on analysis results,

[0801] An emotion analysis means that analyzes input from a terminal and determines the emotional state,

[0802] A support information provision means that provides optimal support information to the user according to the results of the emotion analysis means,

[0803] A feedback receiving mechanism that receives user feedback and updates system information,

[0804] A system that includes this.

[0805] (Claim 2)

[0806] The system according to claim 1, further comprising a predictive means for predicting the extent of damage using artificial intelligence.

[0807] (Claim 3)

[0808] The system according to claim 1, further comprising an information management means for continuously updating and displaying the occupancy status of evacuation sites and the shortage status of supplies.

[0809] "Application example 2 when combining with an emotional engine"

[0810] (Claim 1)

[0811] A data collection method that gathers information from multiple sources to determine the extent of damage during a natural disaster,

[0812] A data analysis method that analyzes collected data and assesses the risk of disaster,

[0813] An information provision method that provides evacuation routes and evacuation locations in real time based on analysis results,

[0814] An emotion analysis tool that analyzes the user's emotional state and provides psychological support as needed,

[0815] A feedback receiving mechanism that receives user feedback and updates system information,

[0816] A system that includes this.

[0817] (Claim 2)

[0818] The system according to claim 1, further comprising a prediction means that predicts the extent of the disaster using artificial intelligence based on collected data.

[0819] (Claim 3)

[0820] The system according to claim 1, further comprising an information management means for continuously updating and displaying the occupancy status of evacuation shelters and the shortage status of supplies. [Explanation of symbols]

[0821] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A data collection method that gathers information from multiple sources to determine the extent of damage during a natural disaster, A data analysis method that analyzes collected data and assesses the risk of disaster, An information provision method that provides evacuation routes and evacuation locations in real time based on analysis results, A feedback receiving mechanism that receives user feedback and updates system information, A disaster prediction method that uses artificial intelligence to predict and present information on urban-scale disasters based on accumulated data, A mobile information display means that displays information on the user's mobile device or visual device to provide support, A system that includes this.

2. The system according to claim 1, further comprising a prediction means that predicts the extent of the disaster using artificial intelligence based on collected data.

3. The system according to claim 1, further comprising an information management means for continuously updating and displaying the occupancy status of evacuation centers and the shortage status of supplies.

Images