system

Abstract

We provide the system. [Solution] A means for collecting earthquake-related data in real time, Means of obtaining earthquake-related information in real time, A method for analyzing acquired information and predicting earthquake occurrences using a deep learning algorithm, Based on the prediction results, a means of notifying potentially affected users of the warning, A means to achieve integration with the urban environment and automatically manage infrastructure facilities, A means of providing evacuation orders and information on evacuation facilities based on earthquake predictions, 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, the method including 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 as a 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] Earthquakes have a significant impact among natural disasters, and there is a need to reduce the damage caused by their occurrence and make prior preparations. Conventional earthquake predictions have insufficient accuracy, making it difficult to support prompt responses. In addition, prediction information about damage has not been appropriately communicated to the general public, and there has been a lack of means to automate protective measures, so the improvement of the resilience of local communities has been limited.

Means for Solving the Problems

[0005] This invention provides a system that accurately predicts earthquake occurrences by collecting earthquake-related data in real time and analyzing it using deep learning algorithms. The system includes means for notifying potentially affected users in real time based on the analyzed prediction results. Furthermore, it has the functionality to propose customized damage predictions and countermeasures for specific regions or users, and to control relevant infrastructure to implement automated protective measures, thereby minimizing damage caused by earthquakes.

[0006] "Earthquake-related data" refers to information such as crustal deformation, epicenter information, and past earthquake records that are collected to assess the likelihood of an earthquake occurring.

[0007] "Methods for collecting data in real time" refer to systems that use sensors and databases to instantly acquire data on phenomena that are currently in progress.

[0008] A "deep learning algorithm" is a computational method that uses multi-layered neural networks to learn complex data patterns and perform predictions and classifications.

[0009] "Methods for predicting earthquake occurrence" refer to technologies that predict the likelihood of an earthquake, its epicenter, and the time of occurrence based on collected data.

[0010] "Potentially affected users" refers to people and facilities in areas that may suffer direct or indirect damage from the predicted earthquake.

[0011] "Means of notifying warnings" refers to a system for quickly transmitting earthquake prediction information to users.

[0012] "Customized damage predictions" refer to predictive information that has been adjusted to suit specific regions or individual users.

[0013] "Means of proposing protective measures" refers to a function that provides specific guidelines and measures for taking immediate action in response to anticipated impacts.

[0014] "Means of interfacing with infrastructure systems" refers to a mechanism for implementing earthquake-related protective measures through information and communication technologies used to manage facilities and equipment. [Brief explanation of the drawing]

[0015] [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]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Modes for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, the numbered 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), etc.

[0019] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the numbered 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.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention provides a comprehensive system for predicting earthquakes in advance and minimizing their damage. This system improves earthquake prediction accuracy and enables efficient emergency response by collecting data in real time and performing advanced analysis. The following describes its embodiments.

[0037] First, the server collects data related to seismic activity in real time. This utilizes earthquake databases, IoT sensors placed in various locations, and geographic information systems (GIS). The server periodically retrieves this data and records it in central data storage.

[0038] The acquired data is input into a deep learning model on the server. This model is highly trained on past earthquake data and has the ability to predict the probability of an earthquake, its expected magnitude, and its epicenter from the newly input data. The prediction information obtained as a result of the analysis is stored in a database.

[0039] Next, the server identifies users in potentially affected areas based on the predicted earthquake information and sends notifications. These notifications include recommended evacuation actions and safety measures to help users respond quickly.

[0040] Users receive notifications through their own devices. Smartphones, tablets, and other devices receive notifications from the server, display alerts on the screen, and highlight the notifications with sound and vibration. This allows users to detect earthquake precursors early and take appropriate evacuation actions.

[0041] Furthermore, to enable integration with infrastructure, the server communicates with smart home systems and urban infrastructure to automatically execute protective measures. This includes functions such as automatically shutting off the gas supply to a building and activating safety devices. This coordination can prevent secondary disasters caused by earthquakes and mitigate damage.

[0042] Through the embodiments described above, the present invention provides a system that simultaneously improves the accuracy of earthquake prediction and enables rapid emergency response, thereby protecting human lives and minimizing property damage.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server collects data in real time. It retrieves data from earthquake-related databases, IoT sensors, and GIS via APIs and stores it in a central database. This collection includes the latest crustal deformation information and sensor data.

[0046] Step 2:

[0047] The server inputs the collected data into a deep learning model for analysis. The model uses frameworks such as TENSORFLOW® or PyTorch to calculate the probability and magnitude of earthquakes, as well as the predicted epicenter.

[0048] Step 3:

[0049] The server analyzes the prediction results and identifies specific regions and users that may be affected. Geographic information stored in the database is used to narrow down the target of notifications.

[0050] Step 4:

[0051] The server generates a warning notification and sends it to users in the affected area. The notification includes evacuation instructions and specific information for ensuring safety.

[0052] Step 5:

[0053] The device receives a notification from the server. Smartphones and tablets display an alert on the screen and alert the user with a notification sound or vibration.

[0054] Step 6:

[0055] The user will learn how to quickly evacuate to a safe place by following the instructions on the device. Based on information such as maps provided by the device, they will select the nearest evacuation center and a safe route.

[0056] Step 7:

[0057] The server works in conjunction with infrastructure equipment to execute automated protective measures. Specifically, it controls the shutoff of gas supplies in designated areas and the activation of building safety systems. This prevents secondary damage caused by earthquakes.

[0058] (Example 1)

[0059] 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."

[0060] To minimize damage caused by earthquakes, rapid and accurate prediction and efficient response are essential. However, conventional systems lack sufficient prediction accuracy and have limitations in providing customized responses for individual regions and users. Furthermore, automated protective measures to prevent secondary disasters caused by earthquakes are inadequate.

[0061] 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.

[0062] In this invention, the server includes a collection means for acquiring earthquake-related information in real time, an analysis means for analyzing the acquired information and predicting the occurrence of earthquakes using a machine learning algorithm, and a means for notifying potentially affected users based on the predicted information. This improves the accuracy of earthquake prediction and enables the automatic execution of protective measures for structures within the affected area.

[0063] "Collection means" refers to a device or process for acquiring earthquake-related information in real time.

[0064] "Analysis means" refers to a device or process for analyzing acquired earthquake-related information and predicting earthquake occurrences using machine learning algorithms.

[0065] "Means of notification" refers to a device or process for communicating warnings to potentially affected users based on predicted earthquake information.

[0066] "Means of coordination with infrastructure devices" refers to devices or processes for communicating with and controlling external infrastructure devices in order to implement protective measures against structures within a region.

[0067] A "machine learning algorithm" is a series of computational methods used to analyze large amounts of earthquake data, build predictive models, and predict future earthquake occurrences.

[0068] This invention provides a comprehensive system for predicting earthquakes and minimizing their damage. This system improves earthquake prediction accuracy and enables efficient emergency response by collecting information in real time and performing advanced analysis.

[0069] The server's first task is to collect information related to seismic activity. Specifically, IoT sensors installed in various locations are used as hardware. These sensors detect ground deformation and acceleration, and transmit this information to the server via the network. The server records the received data in a database and prepares it for analysis.

[0070] The server then inputs data into a deep learning model using TensorFlow, and the model, trained on past earthquake data, predicts the probability, magnitude, and epicenter of an earthquake. This identifies areas with a high probability of earthquakes, and the prediction results are stored in a database.

[0071] Based on the predicted information, the server identifies users in potentially affected areas and generates notifications. These notifications include evacuation recommendations and safety measures to help users respond quickly.

[0072] Users receive notifications from the server on their devices. When smartphones and tablets receive a notification, they display an alert on the screen and provide warnings via sound and vibration. This allows users to detect earthquake precursors early and take appropriate evacuation actions.

[0073] Furthermore, the server communicates with smart home systems and urban infrastructure to enable automated protective measures. For example, it can send signals to shut off the gas supply to a building or stop elevators at the nearest floor. This helps prevent secondary disasters caused by earthquakes and mitigate damage.

[0074] As a concrete example, if the probability of an earthquake increases in a certain area, the server can send a notification to users in that area stating, "There is a possibility of an earthquake. Please consider evacuating to a safe place as soon as possible." This system, by utilizing generated AI models and prompt messages, enables more reliable disaster prevention measures.

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] The server collects information related to seismic activity. It acquires ground deformation data in real time from IoT sensors installed in various locations and transmits it to the server via the network. The input is raw data from the sensors, and the output is seismic activity information stored in a database. Specifically, the server receives data packets from the sensors, organizes them as time-series data, and stores them.

[0078] Step 2:

[0079] The server analyzes the collected seismic activity information. It uses time-series data from the database saved in Step 1 as input. The server inputs the data into a deep learning model using TensorFlow to predict the probability of an earthquake, its epicenter, and its magnitude. The output is earthquake prediction data as a result of the analysis. Specifically, the server runs the model and compares and analyzes the new data with past earthquake data.

[0080] Step 3:

[0081] The server generates notifications based on the analysis results. The input is the earthquake prediction data obtained in step 2. The server identifies the areas expected to be affected and generates notification content for users. The output is the notification message sent to users. Specifically, the server generates messages including evacuation orders and safety measures according to the magnitude of the earthquake and creates a list of recipients.

[0082] Step 4:

[0083] The device receives notifications from the server and transmits them to the user. The input is the notification message sent from the server. The device displays the notification on the screen and alerts the user with sound and vibration. The output is an alert display that the user can recognize. Specifically, the device analyzes the received data and sends a push notification with synchronized sound and vibration, along with a pop-up alert.

[0084] Step 5:

[0085] The server works in conjunction with infrastructure devices to implement protective measures. The input is earthquake prediction data analyzed in step 2. The server communicates with local smart home systems and urban infrastructure and automatically sends control signals. The output is control commands to the relevant infrastructure devices. Specific examples include sending shutdown signals for gas supply systems and activating emergency equipment.

[0086] (Application Example 1)

[0087] 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."

[0088] Earthquakes are difficult to predict, and rapid information dissemination and response are necessary to mitigate their impact. However, current systems lack sufficient accuracy in earthquake prediction and rapid implementation of countermeasures, making it highly likely that the safety of citizens will be threatened. Furthermore, in urban environments, the integration with smart technologies is insufficient, making it difficult to implement a rapid and comprehensive response to minimize damage. Solving these challenges is essential.

[0089] 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.

[0090] In this invention, the server includes means for acquiring earthquake-related information in real time, means for analyzing the acquired information and predicting the occurrence of earthquakes using a deep learning algorithm, means for notifying potentially affected users of warnings based on the prediction results, means for realizing coordination with the urban environment and automatically managing infrastructure facilities, and means for providing evacuation orders and information on evacuation facilities based on earthquake predictions. This makes it possible to improve the safety of citizens through rapid information dissemination during earthquakes and automated infrastructure management.

[0091] "Information related to earthquakes" refers to data indicating seismic activity and external information necessary for prediction, which includes sensor data, geographical information, and historical earthquake data.

[0092] "Means of acquiring information in real time" refers to technologies and devices for immediately collecting and processing information about ongoing seismic activity.

[0093] "Deep learning algorithms" are a field of artificial intelligence that uses multi-layer neural networks to recognize and analyze complex patterns.

[0094] "Predictive means" refers to methods and devices used to predict future earthquake occurrences using acquired data.

[0095] "Means of notifying of warnings" refers to a system that transmits warnings and cautions to potentially affected users based on predicted earthquake information.

[0096] "Means of realizing collaboration with the urban environment" refers to technologies that enable automated control by sharing information through communication and collaboration with urban infrastructure and management systems.

[0097] "Means for automatically managing infrastructure facilities" refers to methods and devices for autonomously operating public facilities and building systems in cities based on earthquake predictions.

[0098] "Evacuation orders based on earthquake predictions" refer to the dissemination of information that provides users with appropriate evacuation advisories and action guidelines in response to predicted seismic activity.

[0099] "Information on evacuation facilities" refers to information about places and facilities where people can safely evacuate in the event of an earthquake, and this includes location information and capacity.

[0100] This invention is a comprehensive system for realizing earthquake prediction and safety measures based on that prediction. Servers, terminals, and users each play their respective roles and work together in a coordinated manner.

[0101] The server first acquires earthquake-related information in real time from various data sources. This information includes data from IoT sensors placed in various locations, geographic information systems (GIS), and historical earthquake data. The server continuously stores this data in central data storage. The server analyzes the stored data using deep learning algorithms to predict earthquake occurrences. Deep learning models built using machine learning libraries such as TensorFlow and Keras are used.

[0102] The device receives predictive information generated by the server. Smartphones, tablets, and other devices receive real-time alert notifications and display alerts to the user. Notification systems such as Firebase are used to deliver information quickly and reliably. Notifications include images and text, and are accompanied by sound and vibration to attract the user's attention.

[0103] Users take swift evacuation actions based on information provided by their devices. In this process, smart city infrastructure, capable of coordinating with the urban environment, automatically accepts instructions from the server and implements safety measures. This includes functions such as shutting off gas supplies to public facilities. Information about evacuation facilities within the city is also displayed on the devices, helping users to plan specific actions during evacuation.

[0104] For example, if an earthquake is predicted to occur near Tokyo, the user's device will instantly display information on the epicenter, seismic intensity, and evacuation shelters, urging them to evacuate. As a safety measure, traffic signals within the city will be controlled to prevent traffic accidents.

[0105] An example of a prompt message would be: "An earthquake has been predicted in Tokyo, with a magnitude of 7.0 and the epicenter in Shinjuku Ward. Please compile the information to display in the app in order to issue evacuation orders to users."

[0106] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0107] Step 1:

[0108] The server acquires earthquake-related information in real time. Inputs include data from IoT sensors, geographic information system (GIS) data, and historical earthquake data. The server stores this data in central data storage, performing the specific operation of organizing and saving the information in a database.

[0109] Step 2:

[0110] The server analyzes accumulated earthquake-related data using deep learning algorithms. A model built with TensorFlow is used, and the server supplies input data to the model to calculate the probability of earthquake occurrence, expected magnitude, and epicenter. The resulting output generates predicted values ​​based on each parameter.

[0111] Step 3:

[0112] The server identifies potentially affected users based on the analysis results. The input is generated predictive data, and the server performs data calculations to identify those who will be notified by matching it with the user's location information. A list of those who will be notified is output.

[0113] Step 4:

[0114] The server sends alert information to the recipient. The server utilizes notification services such as Firebase to send alerts to specific devices. Input includes the user's contact information and predictive data, and output is delivered as an alert message accompanied by voice or vibration.

[0115] Step 5:

[0116] The terminal displays the received alert information. The terminal receives data sent from the server and outputs visual warnings and audio information. It performs specific actions such as displaying alerts in detail on the screen so that the user can understand them immediately.

[0117] Step 6:

[0118] Users take swift evacuation action based on information from their devices. They check maps and route information for evacuation facilities provided by their devices, select an appropriate evacuation destination, and begin their actions. Safety is ensured through this process.

[0119] Step 7:

[0120] The server automatically controls infrastructure facilities in conjunction with the urban environment. The input is control commands based on earthquake predictions, and the server adjusts traffic signals, gas supply shutdowns, etc., based on the results analyzed by a generated AI model, and the output is the execution of safety measures.

[0121] 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.

[0122] This invention provides a system that accurately predicts earthquake occurrences and supports responses tailored to potential impacts, while also considering user emotions to achieve more flexible and personalized responses. This system combines conventional earthquake prediction systems with emotion recognition capabilities.

[0123] Specifically, the server acquires various earthquake-related data in real time and analyzes it using deep learning algorithms. Based on the prediction results obtained from the analysis, warnings about potential earthquakes and predictions of the resulting damage are issued.

[0124] The key element here is the emotion engine built into the device. This emotion engine analyzes the user's voice, facial expressions, or input actions to identify emotional states such as tension, anxiety, relief, and fear. The analysis is performed using machine learning algorithms, and the results are sent to the server in real time.

[0125] The server receives this emotional data and generates a warning message that is best suited to the user's current mental state. For example, if the server detects that the user is feeling anxious, a gentle and encouraging message will be selected; if the user is feeling at ease, more specific instructions will be provided.

[0126] When a user receives a warning message displayed on their device, it includes not only standard evacuation instructions but also advice tailored to their mental state. This allows users to receive information in a psychologically appropriate way and take appropriate action.

[0127] Furthermore, the server adjusts its coordination with the infrastructure system as needed based on this emotional data. For example, if a user's emotions indicate extreme anxiety, a faster response is required, and the implementation of protective measures will be prioritized.

[0128] Thus, the present invention enhances the quality of user response and supports more effective and reassuring disaster response by incorporating emotion recognition into a practical earthquake prediction system.

[0129] The following describes the processing flow.

[0130] Step 1:

[0131] The server acquires earthquake-related data in real time from various sensors and databases. This includes crustal deformation information, seismic activity history, and data from geographic information systems. This data is stored in a central database on the server.

[0132] Step 2:

[0133] The server analyzes the collected data using deep learning algorithms. It compares past earthquake patterns with current data to predict earthquake occurrences. This process yields predictions about the likelihood, magnitude, and location of future earthquakes.

[0134] Step 3:

[0135] An emotion engine built into the device recognizes the user's current emotional state in real time. It analyzes voice tone, changes in facial expressions, and input data to identify the psychological state the user is feeling. This result is transmitted from the device to the server.

[0136] Step 4:

[0137] The server integrates emotional data and earthquake prediction data to generate warning messages tailored to the user's emotions. Messages are adjusted to provide greater reassurance for highly anxious users, while calmer users receive more specific instructions.

[0138] Step 5:

[0139] The device notifies the user of a generated warning message. The device displays the message on the screen and uses vibration and sound as needed to attract attention. The user receives psychologically sensitive information and prepares to calmly take evacuation action.

[0140] Step 6:

[0141] Based on the displayed messages and map information, users can quickly and accurately begin evacuation to a safe location. Advice tailored to their emotional state is provided, allowing them to act with a sense of security.

[0142] Step 7:

[0143] The server considers the received emotional data and adjusts the operation of the collaborating infrastructure systems as needed. For example, if a user indicates high levels of anxiety, more intensive protective measures will be taken.

[0144] (Example 2)

[0145] 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 will be referred to as the "terminal."

[0146] Minimizing damage from earthquakes requires prompt and accurate warnings and appropriate responses. However, conventional earthquake prediction systems often fail to provide individualized responses that take into account the emotional state of users, resulting in uniform warning messages. As a result, information may not be adequately conveyed, and appropriate evacuation actions may not be taken. Furthermore, there is the challenge of providing a rapid response that also takes into account the impact on local infrastructure.

[0147] 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.

[0148] In this invention, the server includes means for collecting earthquake-related information in real time, means for analyzing the collected information and predicting the occurrence of earthquakes using machine learning algorithms, means for notifying users of individually optimized warnings by analyzing their emotional state based on the prediction results, and means for coordinating protective measures in cooperation with the infrastructure system. This enables flexible information provision and rapid infrastructure adjustment in accordance with the user's psychological state.

[0149] "Information related to earthquakes" refers to historical data, geological data, and current crustal activity information related to earthquakes.

[0150] "Means of real-time collection" refers to methods and technologies for continuously acquiring earthquake-related information with an emphasis on immediacy.

[0151] A "machine learning algorithm" is a set of computational methods that allow a computer to learn patterns based on given data and perform predictions and classifications.

[0152] "Methods for analyzing emotional states" refer to technologies that capture data such as the user's voice and facial expressions, and then use that data to identify and quantify the user's emotions.

[0153] "Means of providing individually optimized warnings" refers to methods and systems for delivering warnings to individual users in a format that is optimal for each user, based on analyzed user sentiment data.

[0154] "Infrastructure systems" refer to all systems, including social infrastructure facilities and interfaces, that are used to provide protection against earthquakes.

[0155] "Means of coordinating protective measures" refers to methods of controlling the operation of infrastructure systems to take timely and appropriate countermeasures based on earthquake predictions.

[0156] The invention is a system that predicts earthquake occurrences with high accuracy and provides individually optimized earthquake warnings based on the user's emotions. The following hardware and software are required to implement this system:

[0157] The servers are located in high-performance data centers and collect earthquake-related information in real time from various observation agencies. The software used includes TensorFlow and similar deep learning frameworks for data analysis. The servers utilize these tools to build earthquake prediction models and analyze the latest crustal activity.

[0158] The terminal is a device that has a direct interface with the user and is equipped with a camera and microphone to sense the user's voice and facial expressions. Using OpenCV and PyTorch, the terminal analyzes the user's emotions in real time. The analysis results are then quickly transmitted to the server.

[0159] When the server receives emotion data, it combines it with earthquake prediction data to generate the most appropriate warning message for each user. This message generation is customized according to the user's different emotional state, such as anxiety, tension, or reassurance. For example, if the user is analyzed as anxious, the message might say, "Please check your safety and remain calm while awaiting further instructions."

[0160] Furthermore, the servers work in conjunction with the infrastructure system to coordinate the protective measures required for each region and facility. This coordination includes, for example, emergency route guidance and the implementation of pre-emptive evacuation plans.

[0161] As a concrete example, here is an example of a prompt message for a generative AI model: "Explain how to generate warning messages that are appropriate to the user's individual psychological state, taking into account the user's emotions during an earthquake. Provide a specific example and show how the system works."

[0162] In this way, this invention enhances the quality of information provided to users and realizes a system that enables a sense of security in disaster response.

[0163] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0164] Step 1:

[0165] The server collects earthquake-related observation data in real time. Inputs include crustal activity information and historical earthquake data obtained from various earthquake detection agencies. Based on this data, it uses a deep learning framework to perform data analysis and execute an earthquake prediction model. Outputs include information on the predicted earthquake location and magnitude. This information is sent to other system modules.

[0166] Step 2:

[0167] The device acquires user voice and facial expression data in real time via its camera and microphone. Inputs include the user's voice signal and video images containing their facial expressions. An emotion analysis algorithm is used to identify the user's emotional state from this data, quantifying emotions such as "tension," "anxiety," and "relief." Specifically, it combines image analysis using OpenCV with voice analysis using PyTorch. The analyzed emotion information is sent to a server as output.

[0168] Step 3:

[0169] The server integrates received sentiment data and earthquake prediction data to generate a personalized warning message for each user. The inputs are sentiment data and earthquake prediction information. A generative AI model is used to create a message tailored to each individual user based on these inputs. In this process, the message content is customized depending on whether the user is anxious or reassured. The output is a personalized warning message sent to the device.

[0170] Step 4:

[0171] The user receives a warning message displayed on the device and acts accordingly. The input is the warning message displayed on the device. This provides the user with guidance for taking specific evacuation actions and countermeasures. Specifically, the user checks the instructed evacuation route and evacuates quickly while ensuring the safety of the surroundings. The output is the execution of the user's evacuation actions.

[0172] Step 5:

[0173] The server coordinates with the infrastructure system as needed to adjust protective measures. Inputs include collective user sentiment data and earthquake prediction information. Through the infrastructure system's control interface, it coordinates and distributes warning systems and evacuation route information for specific areas. The output is the provision of appropriate protective measures and information across the entire region.

[0174] (Application Example 2)

[0175] 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".

[0176] Earthquake prediction systems are required not only to notify users of earthquakes in advance, but also to provide information that takes into account the individual emotional state of each user. However, conventional earthquake prediction systems have struggled to provide customized information according to the user's emotions, and have failed to encourage the user to take the most appropriate action. Therefore, it is necessary to provide detailed responses that are tailored to the user's emotional state in order to alleviate fear and anxiety during disasters and support decisive action.

[0177] 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.

[0178] In this invention, the server includes a device for acquiring earthquake-related information in real time, a device for analyzing the acquired information and estimating the occurrence of earthquakes using a deep learning algorithm, a device for analyzing the user's emotional state and identifying emotions based on voice, facial expressions, or input operations, and a device for generating warning information that is most appropriate to the user's current mental state based on the acquired emotional information. This makes it possible to provide personalized information that takes the user's emotions into consideration.

[0179] "Information related to earthquakes" refers to data such as the time of the earthquake, the epicenter, the magnitude, and the distribution of seismic intensity.

[0180] "Real-time acquisition" means collecting data instantly and obtaining the latest information with minimal time lag.

[0181] A "deep learning algorithm" is a machine learning technique that uses multi-layered neural networks and is a method for learning complex patterns from large amounts of data.

[0182] "Estimating earthquake occurrence" means predicting potential future earthquakes based on past earthquake data and real-time observation data.

[0183] "User's emotional state" refers to the subjective feelings and psychological state experienced by individual users.

[0184] "Identifying emotions based on voice, facial expressions, or input actions" means analyzing the sounds a user makes, changes in their facial expressions, or input actions they make on the device to determine their current emotions.

[0185] "Acquired emotional information" refers to data recorded by analyzing the user's emotional state.

[0186] "Generating warning information" means creating user-specific notifications for evacuation and safety measures in response to predicted earthquakes.

[0187] This system is equipped with advanced devices for collecting and analyzing earthquake-related information in real time. The server first acquires earthquake data in real time and then uses deep learning algorithms to predict earthquake occurrences. The earthquake data includes information from sensors and observation stations, and by utilizing deep learning, it is possible to achieve more accurate predictions than ever before.

[0188] The device is equipped with voice recognition software and a facial expression analysis camera to analyze the user's emotional state. The device identifies emotions from the user's voice commands, facial expressions, or touch panel operations, and sends the results to a server. Based on this data, the server generates warning information appropriate to the user's current mental state. For example, if the server determines that the user is stressed, it can provide information to help them calm down.

[0189] Users receive these personalized warnings through devices such as smartphones and smart glasses. By considering each individual's emotional state, the system can take more appropriate measures against earthquakes, allowing users to confidently and quickly take self-protective action.

[0190] For example, if the user's facial expression or voice indicates anxiety while the whole family is gathered together, the system can provide encouraging messages along with information on actions to avoid and evacuation points for disaster preparedness. An example of a prompt for the generating AI model would be, "If an earthquake is predicted, please tell us how you are feeling now. We will then provide you with special advice."

[0191] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0192] Step 1:

[0193] The server acquires earthquake-related information in real time from seismic observatories and sensors. It receives earthquake data from sensors as input and stores it in a database. The output is established as an earthquake dataset. Specifically, it accesses the data using an API and updates the database.

[0194] Step 2:

[0195] The server applies a deep learning algorithm to the acquired earthquake dataset to estimate earthquake occurrences. The input is the earthquake dataset. A neural network model is used to analyze the data and calculate the probability of an earthquake occurring. The output is an earthquake prediction result. Specifically, the model is deployed using a GPU, and the estimation process is performed in real time.

[0196] Step 3:

[0197] The device analyzes the user's voice and facial expressions to identify their emotional state. Input consists of the user's voice data and camera images, and an emotion recognition algorithm is used to identify the user's mental state (anxiety, tension, etc.). Output is the user's emotional information. Specifically, it collects data using voice recognition software and a facial recognition camera, and feeds this data into a machine learning model.

[0198] Step 4:

[0199] The server generates customized warning messages based on earthquake prediction results and user sentiment information. The inputs are earthquake prediction results and user sentiment information. Using sentiment-based message templates, it creates the most appropriate warning information for the user. The output is a personalized warning message. Specifically, it uses a sentiment recognition AI model to select messages and format them as text data.

[0200] Step 5:

[0201] The user receives personalized warning messages through their device. The input is the warning message, displayed on the device. The user can then take safe actions based on it. The output is a guide to the user's actions. Specifically, this involves activating a notification function on a smartphone or smart glasses and displaying information on the user interface.

[0202] 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.

[0203] Data generation model 58 is a 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 the following. 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 indicated 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.

[0204] 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.

[0205] [Second Embodiment]

[0206] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0207] 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.

[0208] 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).

[0209] 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.

[0210] 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.

[0211] 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).

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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".

[0218] This invention provides a comprehensive system for predicting earthquakes in advance and minimizing their damage. This system improves earthquake prediction accuracy and enables efficient emergency response by collecting data in real time and performing advanced analysis. The following describes its embodiments.

[0219] First, the server collects data related to seismic activity in real time. This utilizes earthquake databases, IoT sensors placed in various locations, and geographic information systems (GIS). The server periodically retrieves this data and records it in central data storage.

[0220] The acquired data is input into a deep learning model on the server. This model is highly trained on past earthquake data and has the ability to predict the probability of an earthquake, its expected magnitude, and its epicenter from the newly input data. The prediction information obtained as a result of the analysis is stored in a database.

[0221] Next, the server identifies users in potentially affected areas based on the predicted earthquake information and sends notifications. These notifications include recommended evacuation actions and safety measures to help users respond quickly.

[0222] Users receive notifications through their own devices. Smartphones, tablets, and other devices receive notifications from the server, display alerts on the screen, and highlight the notifications with sound and vibration. This allows users to detect earthquake precursors early and take appropriate evacuation actions.

[0223] Furthermore, to enable integration with infrastructure, the server communicates with smart home systems and urban infrastructure to automatically execute protective measures. This includes functions such as automatically shutting off the gas supply to a building and activating safety devices. This coordination can prevent secondary disasters caused by earthquakes and mitigate damage.

[0224] Through the embodiments described above, the present invention provides a system that simultaneously improves the accuracy of earthquake prediction and enables rapid emergency response, thereby protecting human lives and minimizing property damage.

[0225] The following describes the processing flow.

[0226] Step 1:

[0227] The server collects data in real time. It retrieves data from earthquake-related databases, IoT sensors, and GIS via APIs and stores it in a central database. This collection includes the latest crustal deformation information and sensor data.

[0228] Step 2:

[0229] The server inputs the collected data into a deep learning model for analysis. The model uses frameworks such as TensorFlow or PyTorch to calculate the probability and magnitude of earthquakes, as well as the predicted epicenter.

[0230] Step 3:

[0231] The server analyzes the prediction results and identifies specific regions and users that may be affected. Geographic information stored in the database is used to narrow down the target of notifications.

[0232] Step 4:

[0233] The server generates a warning notification and sends it to users in the affected area. The notification includes evacuation instructions and specific information for ensuring safety.

[0234] Step 5:

[0235] The device receives a notification from the server. Smartphones and tablets display an alert on the screen and alert the user with a notification sound or vibration.

[0236] Step 6:

[0237] The user will learn how to quickly evacuate to a safe place by following the instructions on the device. Based on information such as maps provided by the device, they will select the nearest evacuation center and a safe route.

[0238] Step 7:

[0239] The server works in conjunction with infrastructure equipment to execute automated protective measures. Specifically, it controls the shutoff of gas supplies in designated areas and the activation of building safety systems. This prevents secondary damage caused by earthquakes.

[0240] (Example 1)

[0241] 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."

[0242] To minimize damage caused by earthquakes, rapid and accurate prediction and efficient response are essential. However, conventional systems lack sufficient prediction accuracy and have limitations in providing customized responses for individual regions and users. Furthermore, automated protective measures to prevent secondary disasters caused by earthquakes are inadequate.

[0243] 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.

[0244] In this invention, the server includes a collection means for acquiring earthquake-related information in real time, an analysis means for analyzing the acquired information and predicting the occurrence of earthquakes using a machine learning algorithm, and a means for notifying potentially affected users based on the predicted information. This improves the accuracy of earthquake prediction and enables the automatic execution of protective measures for structures within the affected area.

[0245] "Collection means" refers to a device or process for acquiring earthquake-related information in real time.

[0246] "Analysis means" refers to a device or process for analyzing acquired earthquake-related information and predicting earthquake occurrences using machine learning algorithms.

[0247] "Means of notification" refers to a device or process for communicating warnings to potentially affected users based on predicted earthquake information.

[0248] "Means of coordination with infrastructure devices" refers to devices or processes for communicating with and controlling external infrastructure devices in order to implement protective measures against structures within a region.

[0249] A "machine learning algorithm" is a series of computational methods used to analyze large amounts of earthquake data, build predictive models, and predict future earthquake occurrences.

[0250] This invention provides a comprehensive system for predicting earthquakes and minimizing their damage. This system improves earthquake prediction accuracy and enables efficient emergency response by collecting information in real time and performing advanced analysis.

[0251] The server's first task is to collect information related to seismic activity. Specifically, IoT sensors installed in various locations are used as hardware. These sensors detect ground deformation and acceleration, and transmit this information to the server via the network. The server records the received data in a database and prepares it for analysis.

[0252] The server then inputs data into a deep learning model using TensorFlow, and the model, trained on past earthquake data, predicts the probability, magnitude, and epicenter of an earthquake. This identifies areas with a high probability of earthquakes, and the prediction results are stored in a database.

[0253] Based on the predicted information, the server identifies users in potentially affected areas and generates notifications. These notifications include evacuation recommendations and safety measures to help users respond quickly.

[0254] Users receive notifications from the server on their devices. When smartphones and tablets receive a notification, they display an alert on the screen and provide warnings via sound and vibration. This allows users to detect earthquake precursors early and take appropriate evacuation actions.

[0255] Furthermore, the server communicates with smart home systems and urban infrastructure to enable automated protective measures. For example, it can send signals to shut off the gas supply to a building or stop elevators at the nearest floor. This helps prevent secondary disasters caused by earthquakes and mitigate damage.

[0256] As a concrete example, if the probability of an earthquake increases in a certain area, the server can send a notification to users in that area stating, "There is a possibility of an earthquake. Please consider evacuating to a safe place as soon as possible." This system, by utilizing generated AI models and prompt messages, enables more reliable disaster prevention measures.

[0257] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0258] Step 1:

[0259] The server collects information related to seismic activity. It acquires ground deformation data in real time from IoT sensors installed in various locations and transmits it to the server via the network. The input is raw data from the sensors, and the output is seismic activity information stored in a database. Specifically, the server receives data packets from the sensors, organizes them as time-series data, and stores them.

[0260] Step 2:

[0261] The server analyzes the collected seismic activity information. It uses time-series data from the database saved in Step 1 as input. The server inputs the data into a deep learning model using TensorFlow to predict the probability of an earthquake, its epicenter, and its magnitude. The output is earthquake prediction data as a result of the analysis. Specifically, the server runs the model and compares and analyzes the new data with past earthquake data.

[0262] Step 3:

[0263] The server generates notifications based on the analysis results. The input is the earthquake prediction data obtained in step 2. The server identifies the areas expected to be affected and generates notification content for users. The output is the notification message sent to users. Specifically, the server generates messages including evacuation orders and safety measures according to the magnitude of the earthquake and creates a list of recipients.

[0264] Step 4:

[0265] The device receives notifications from the server and transmits them to the user. The input is the notification message sent from the server. The device displays the notification on the screen and alerts the user with sound and vibration. The output is an alert display that the user can recognize. Specifically, the device analyzes the received data and sends a push notification with synchronized sound and vibration, along with a pop-up alert.

[0266] Step 5:

[0267] The server works in conjunction with infrastructure devices to implement protective measures. The input is earthquake prediction data analyzed in step 2. The server communicates with local smart home systems and urban infrastructure and automatically sends control signals. The output is control commands to the relevant infrastructure devices. Specific examples include sending shutdown signals for gas supply systems and activating emergency equipment.

[0268] (Application Example 1)

[0269] 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."

[0270] Earthquakes are difficult to predict, and rapid information dissemination and response are necessary to mitigate their impact. However, current systems lack sufficient accuracy in earthquake prediction and rapid implementation of countermeasures, making it highly likely that the safety of citizens will be threatened. Furthermore, in urban environments, the integration with smart technologies is insufficient, making it difficult to implement a rapid and comprehensive response to minimize damage. Solving these challenges is essential.

[0271] 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.

[0272] In this invention, the server includes means for acquiring earthquake-related information in real time, means for analyzing the acquired information and predicting the occurrence of earthquakes using a deep learning algorithm, means for notifying potentially affected users of warnings based on the prediction results, means for realizing coordination with the urban environment and automatically managing infrastructure facilities, and means for providing evacuation orders and information on evacuation facilities based on earthquake predictions. This makes it possible to improve the safety of citizens through rapid information dissemination during earthquakes and automated infrastructure management.

[0273] "Information related to earthquakes" refers to data indicating seismic activity and external information necessary for prediction, which includes sensor data, geographical information, and historical earthquake data.

[0274] "Means of acquiring information in real time" refers to technologies and devices for immediately collecting and processing information about ongoing seismic activity.

[0275] "Deep learning algorithms" are a field of artificial intelligence that uses multi-layer neural networks to recognize and analyze complex patterns.

[0276] "Predictive means" refers to methods and devices used to predict future earthquake occurrences using acquired data.

[0277] "Means of notifying of warnings" refers to a system that transmits warnings and cautions to potentially affected users based on predicted earthquake information.

[0278] "Means of realizing collaboration with the urban environment" refers to technologies that enable automated control by sharing information through communication and collaboration with urban infrastructure and management systems.

[0279] "Means for automatically managing infrastructure facilities" refers to methods and devices for autonomously operating public facilities and building systems in cities based on earthquake predictions.

[0280] "Evacuation orders based on earthquake predictions" refer to the dissemination of information that provides users with appropriate evacuation advisories and action guidelines in response to predicted seismic activity.

[0281] "Information on evacuation facilities" refers to information about places and facilities where people can safely evacuate in the event of an earthquake, and this includes location information and capacity.

[0282] This invention is a comprehensive system for realizing earthquake prediction and safety measures based on that prediction. Servers, terminals, and users each play their respective roles and work together in a coordinated manner.

[0283] The server first acquires earthquake-related information in real time from various data sources. This information includes data from IoT sensors placed in various locations, geographic information systems (GIS), and historical earthquake data. The server continuously stores this data in central data storage. The server analyzes the stored data using deep learning algorithms to predict earthquake occurrences. Deep learning models built using machine learning libraries such as TensorFlow and Keras are used.

[0284] The terminal receives the prediction information generated by the server. Terminals such as smartphones and tablets receive the real-time sent warning notifications and display alerts to the users. A notification system such as Firebase is used to convey information quickly and reliably. The notifications include pictures and texts, and are accompanied by sounds and vibrations to draw the users' attention.

[0285] Based on the information provided by the terminal, the user takes immediate evacuation actions. At this time, the smart city infrastructure that can cooperate with the urban environment automatically accepts instructions from the server and implements safety measures. This includes functions such as stopping the gas supply in public facilities. In addition, information about evacuation facilities in the city is also displayed on the terminal, so that users can utilize it for specific actions when evacuating.

[0286] As a specific example, when an earthquake epicenter is predicted to be near Tokyo, the user's terminal immediately displays information about the epicenter, seismic intensity, and evacuation shelters, and prompts evacuation. As safety measures, measures such as controlling traffic signals in the city to prevent traffic accidents are taken.

[0287] An example of a prompt sentence is "An earthquake prediction has been made in Tokyo. The magnitude is 7.0 and the epicenter is in Shinjuku Ward. Please summarize the information to be displayed in the app to give evacuation instructions to the users."

[0288] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0289] Step 1:

[0290] The server obtains earthquake-related information in real time. The inputs include data from IoT sensors, geographic information system (GIS) data, past earthquake data, etc. The server accumulates these data in the central data storage, and performs specific operations such as sorting and storing the information in the database.

[0291] Step 2:

[0292] The server analyzes accumulated earthquake-related data using deep learning algorithms. A model built with TensorFlow is used, and the server supplies input data to the model to calculate the probability of earthquake occurrence, expected magnitude, and epicenter. The resulting output generates predicted values ​​based on each parameter.

[0293] Step 3:

[0294] The server identifies potentially affected users based on the analysis results. The input is generated predictive data, and the server performs data calculations to identify those who will be notified by matching it with the user's location information. A list of those who will be notified is output.

[0295] Step 4:

[0296] The server sends alert information to the recipient. The server utilizes notification services such as Firebase to send alerts to specific devices. Input includes the user's contact information and predictive data, and output is delivered as an alert message accompanied by voice or vibration.

[0297] Step 5:

[0298] The terminal displays the received alert information. The terminal receives data sent from the server and outputs visual warnings and audio information. It performs specific actions such as displaying alerts in detail on the screen so that the user can understand them immediately.

[0299] Step 6:

[0300] Users take swift evacuation action based on information from their devices. They check maps and route information for evacuation facilities provided by their devices, select an appropriate evacuation destination, and begin their actions. Safety is ensured through this process.

[0301] Step 7:

[0302] The server automatically controls the infrastructure in cooperation with the urban environment. The input is a control command based on earthquake prediction. The server adjusts the traffic signals and the shutdown of gas supply, etc. based on the results analyzed by the generated AI model, and safety measures are executed as the output.

[0303] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0304] The present invention is a system that highly accurately predicts the occurrence of an earthquake and supports countermeasures according to the possible impacts. By considering the user's emotion, it realizes a more flexible and personalized response. This system combines an emotion recognition function with a conventional earthquake prediction system.

[0305] Specifically, the server acquires various data related to earthquakes in real time and analyzes them using a deep learning algorithm. Based on the prediction results obtained by the analysis, warnings against possible earthquakes and accompanying damage predictions are made.

[0306] What is important here is the emotion engine provided in the terminal. This emotion engine has a function of analyzing emotions from the user's voice, expression, or input operation and identifying emotional states such as tension, anxiety, relief, fear, etc. The analysis is performed using a machine learning algorithm, and the results are transmitted to the server in real time.

[0307] The server receives this emotion data and generates a warning message most suitable for the user's current mental state. For example, when the user is recognized as feeling anxious, a message that gently encourages is selected, and when the user is feeling at ease, more specific instructions are provided.

[0308] When a user receives a warning message displayed on their device, it includes not only standard evacuation instructions but also advice tailored to their mental state. This allows users to receive information in a psychologically appropriate way and take appropriate action.

[0309] Furthermore, the server adjusts its coordination with the infrastructure system as needed based on this emotional data. For example, if a user's emotions indicate extreme anxiety, a faster response is required, and the implementation of protective measures will be prioritized.

[0310] Thus, the present invention enhances the quality of user response and supports more effective and reassuring disaster response by incorporating emotion recognition into a practical earthquake prediction system.

[0311] The following describes the processing flow.

[0312] Step 1:

[0313] The server acquires earthquake-related data in real time from various sensors and databases. This includes crustal deformation information, seismic activity history, and data from geographic information systems. This data is stored in a central database on the server.

[0314] Step 2:

[0315] The server analyzes the collected data using deep learning algorithms. It compares past earthquake patterns with current data to predict earthquake occurrences. This process yields predictions about the likelihood, magnitude, and location of future earthquakes.

[0316] Step 3:

[0317] An emotion engine built into the device recognizes the user's current emotional state in real time. It analyzes voice tone, changes in facial expressions, and input data to identify the psychological state the user is feeling. This result is transmitted from the device to the server.

[0318] Step 4:

[0319] The server integrates emotional data and earthquake prediction data to generate warning messages tailored to the user's emotions. Messages are adjusted to provide greater reassurance for highly anxious users, while calmer users receive more specific instructions.

[0320] Step 5:

[0321] The device notifies the user of a generated warning message. The device displays the message on the screen and uses vibration and sound as needed to attract attention. The user receives psychologically sensitive information and prepares to calmly take evacuation action.

[0322] Step 6:

[0323] Based on the displayed messages and map information, users can quickly and accurately begin evacuation to a safe location. Advice tailored to their emotional state is provided, allowing them to act with a sense of security.

[0324] Step 7:

[0325] The server considers the received emotional data and adjusts the operation of the collaborating infrastructure systems as needed. For example, if a user indicates high levels of anxiety, more intensive protective measures will be taken.

[0326] (Example 2)

[0327] 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 glasses 214 will be referred to as the "terminal".

[0328] Minimizing damage from earthquakes requires prompt and accurate warnings and appropriate responses. However, conventional earthquake prediction systems often fail to provide individualized responses that take into account the emotional state of users, resulting in uniform warning messages. As a result, information may not be adequately conveyed, and appropriate evacuation actions may not be taken. Furthermore, there is the challenge of providing a rapid response that also takes into account the impact on local infrastructure.

[0329] 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.

[0330] In this invention, the server includes means for collecting earthquake-related information in real time, means for analyzing the collected information and predicting the occurrence of earthquakes using machine learning algorithms, means for notifying users of individually optimized warnings by analyzing their emotional state based on the prediction results, and means for coordinating protective measures in cooperation with the infrastructure system. This enables flexible information provision and rapid infrastructure adjustment in accordance with the user's psychological state.

[0331] "Information related to earthquakes" refers to historical data, geological data, and current crustal activity information related to earthquakes.

[0332] "Means of real-time collection" refers to methods and technologies for continuously acquiring earthquake-related information with an emphasis on immediacy.

[0333] A "machine learning algorithm" is a set of computational methods that allow a computer to learn patterns based on given data and perform predictions and classifications.

[0334] "Methods for analyzing emotional states" refer to technologies that capture data such as the user's voice and facial expressions, and then use that data to identify and quantify the user's emotions.

[0335] "Means of providing individually optimized warnings" refers to methods and systems for delivering warnings to individual users in a format that is optimal for each user, based on analyzed user sentiment data.

[0336] "Infrastructure systems" refer to all systems, including social infrastructure facilities and interfaces, that are used to provide protection against earthquakes.

[0337] "Means of coordinating protective measures" refers to methods of controlling the operation of infrastructure systems to take timely and appropriate countermeasures based on earthquake predictions.

[0338] The invention is a system that predicts earthquake occurrences with high accuracy and provides individually optimized earthquake warnings based on the user's emotions. The following hardware and software are required to implement this system:

[0339] The servers are located in high-performance data centers and collect earthquake-related information in real time from various observation agencies. The software used includes TensorFlow and similar deep learning frameworks for data analysis. The servers utilize these tools to build earthquake prediction models and analyze the latest crustal activity.

[0340] The terminal is a device that has a direct interface with the user and is equipped with a camera and microphone to sense the user's voice and facial expressions. Using OpenCV and PyTorch, the terminal analyzes the user's emotions in real time. The analysis results are then quickly transmitted to the server.

[0341] When the server receives emotion data, it combines it with earthquake prediction data to generate the most appropriate warning message for each user. This message generation is customized according to the user's different emotional state, such as anxiety, tension, or reassurance. For example, if the user is analyzed as anxious, the message might say, "Please check your safety and remain calm while awaiting further instructions."

[0342] Furthermore, the servers work in conjunction with the infrastructure system to coordinate the protective measures required for each region and facility. This coordination includes, for example, emergency route guidance and the implementation of pre-emptive evacuation plans.

[0343] As a concrete example, here is an example of a prompt message for a generative AI model: "Explain how to generate warning messages that are appropriate to the user's individual psychological state, taking into account the user's emotions during an earthquake. Provide a specific example and show how the system works."

[0344] In this way, this invention enhances the quality of information provided to users and realizes a system that enables a sense of security in disaster response.

[0345] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0346] Step 1:

[0347] The server collects earthquake-related observation data in real time. Inputs include crustal activity information and historical earthquake data obtained from various earthquake detection agencies. Based on this data, it uses a deep learning framework to perform data analysis and execute an earthquake prediction model. Outputs include information on the predicted earthquake location and magnitude. This information is sent to other system modules.

[0348] Step 2:

[0349] The device acquires user voice and facial expression data in real time via its camera and microphone. Inputs include the user's voice signal and video images containing their facial expressions. An emotion analysis algorithm is used to identify the user's emotional state from this data, quantifying emotions such as "tension," "anxiety," and "relief." Specifically, it combines image analysis using OpenCV with voice analysis using PyTorch. The analyzed emotion information is sent to a server as output.

[0350] Step 3:

[0351] The server integrates received sentiment data and earthquake prediction data to generate a personalized warning message for each user. The inputs are sentiment data and earthquake prediction information. A generative AI model is used to create a message tailored to each individual user based on these inputs. In this process, the message content is customized depending on whether the user is anxious or reassured. The output is a personalized warning message sent to the device.

[0352] Step 4:

[0353] The user receives a warning message displayed on the device and acts accordingly. The input is the warning message displayed on the device. This provides the user with guidance for taking specific evacuation actions and countermeasures. Specifically, the user checks the instructed evacuation route and evacuates quickly while ensuring the safety of the surroundings. The output is the execution of the user's evacuation actions.

[0354] Step 5:

[0355] The server coordinates with the infrastructure system as needed to adjust protective measures. Inputs include collective user sentiment data and earthquake prediction information. Through the infrastructure system's control interface, it coordinates and distributes warning systems and evacuation route information for specific areas. The output is the provision of appropriate protective measures and information across the entire region.

[0356] (Application Example 2)

[0357] 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."

[0358] Earthquake prediction systems are required not only to notify users of earthquakes in advance, but also to provide information that takes into account the individual emotional state of each user. However, conventional earthquake prediction systems have struggled to provide customized information according to the user's emotions, and have failed to encourage the user to take the most appropriate action. Therefore, it is necessary to provide detailed responses that are tailored to the user's emotional state in order to alleviate fear and anxiety during disasters and support decisive action.

[0359] 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.

[0360] In this invention, the server includes a device for acquiring earthquake-related information in real time, a device for analyzing the acquired information and estimating the occurrence of earthquakes using a deep learning algorithm, a device for analyzing the user's emotional state and identifying emotions based on voice, facial expressions, or input operations, and a device for generating warning information that is most appropriate to the user's current mental state based on the acquired emotional information. This makes it possible to provide personalized information that takes the user's emotions into consideration.

[0361] "Information related to earthquakes" refers to data such as the time of the earthquake, the epicenter, the magnitude, and the distribution of seismic intensity.

[0362] "Real-time acquisition" means collecting data instantly and obtaining the latest information with minimal time lag.

[0363] A "deep learning algorithm" is a machine learning technique that uses multi-layered neural networks and is a method for learning complex patterns from large amounts of data.

[0364] "Estimating earthquake occurrence" means predicting potential future earthquakes based on past earthquake data and real-time observation data.

[0365] "User's emotional state" refers to the subjective feelings and psychological state experienced by individual users.

[0366] "Identifying emotions based on voice, facial expressions, or input actions" means analyzing the sounds a user makes, changes in their facial expressions, or input actions they make on the device to determine their current emotions.

[0367] "Acquired emotional information" refers to data recorded by analyzing the user's emotional state.

[0368] "Generating warning information" means creating user-specific notifications for evacuation and safety measures in response to predicted earthquakes.

[0369] This system is equipped with advanced devices for collecting and analyzing earthquake-related information in real time. The server first acquires earthquake data in real time and then uses deep learning algorithms to predict earthquake occurrences. The earthquake data includes information from sensors and observation stations, and by utilizing deep learning, it is possible to achieve more accurate predictions than ever before.

[0370] The device is equipped with voice recognition software and a facial expression analysis camera to analyze the user's emotional state. The device identifies emotions from the user's voice commands, facial expressions, or touch panel operations, and sends the results to a server. Based on this data, the server generates warning information appropriate to the user's current mental state. For example, if the server determines that the user is stressed, it can provide information to help them calm down.

[0371] Users receive these personalized warnings through devices such as smartphones and smart glasses. By considering each individual's emotional state, the system can take more appropriate measures against earthquakes, allowing users to confidently and quickly take self-protective action.

[0372] For example, if the user's facial expression or voice indicates anxiety while the whole family is gathered together, the system can provide encouraging messages along with information on actions to avoid and evacuation points for disaster preparedness. An example of a prompt for the generating AI model would be, "If an earthquake is predicted, please tell us how you are feeling now. We will then provide you with special advice."

[0373] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0374] Step 1:

[0375] The server acquires earthquake-related information in real time from seismic observatories and sensors. It receives earthquake data from sensors as input and stores it in a database. The output is established as an earthquake dataset. Specifically, it accesses the data using an API and updates the database.

[0376] Step 2:

[0377] The server applies a deep learning algorithm to the acquired earthquake dataset to estimate earthquake occurrences. The input is the earthquake dataset. A neural network model is used to analyze the data and calculate the probability of an earthquake occurring. The output is an earthquake prediction result. Specifically, the model is deployed using a GPU, and the estimation process is performed in real time.

[0378] Step 3:

[0379] The device analyzes the user's voice and facial expressions to identify their emotional state. Input consists of the user's voice data and camera images, and an emotion recognition algorithm is used to identify the user's mental state (anxiety, tension, etc.). Output is the user's emotional information. Specifically, it collects data using voice recognition software and a facial recognition camera, and feeds this data into a machine learning model.

[0380] Step 4:

[0381] The server generates customized warning messages based on earthquake prediction results and user sentiment information. The inputs are earthquake prediction results and user sentiment information. Using sentiment-based message templates, it creates the most appropriate warning information for the user. The output is a personalized warning message. Specifically, it uses a sentiment recognition AI model to select messages and format them as text data.

[0382] Step 5:

[0383] The user receives personalized warning messages through their device. The input is the warning message, displayed on the device. The user can then take safe actions based on it. The output is a guide to the user's actions. Specifically, this involves activating a notification function on a smartphone or smart glasses and displaying information on the user interface.

[0384] 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.

[0385] 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 the following. 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 indicated 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.

[0386] 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.

[0387] [Third Embodiment]

[0388] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0389] 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.

[0390] 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).

[0391] 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.

[0392] 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.

[0393] 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).

[0394] 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.

[0395] 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.

[0396] 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.

[0397] 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.

[0398] 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.

[0399] 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".

[0400] This invention provides a comprehensive system for predicting earthquakes in advance and minimizing their damage. This system improves earthquake prediction accuracy and enables efficient emergency response by collecting data in real time and performing advanced analysis. The following describes its embodiments.

[0401] First, the server collects data related to seismic activity in real time. This utilizes earthquake databases, IoT sensors placed in various locations, and geographic information systems (GIS). The server periodically retrieves this data and records it in central data storage.

[0402] The acquired data is input into a deep learning model on the server. This model is highly trained on past earthquake data and has the ability to predict the probability of an earthquake, its expected magnitude, and its epicenter from the newly input data. The prediction information obtained as a result of the analysis is stored in a database.

[0403] Next, the server identifies users in potentially affected areas based on the predicted earthquake information and sends notifications. These notifications include recommended evacuation actions and safety measures to help users respond quickly.

[0404] Users receive notifications through their own devices. Smartphones, tablets, and other devices receive notifications from the server, display alerts on the screen, and highlight the notifications with sound and vibration. This allows users to detect earthquake precursors early and take appropriate evacuation actions.

[0405] Furthermore, to enable integration with infrastructure, the server communicates with smart home systems and urban infrastructure to automatically execute protective measures. This includes functions such as automatically shutting off the gas supply to a building and activating safety devices. This coordination can prevent secondary disasters caused by earthquakes and mitigate damage.

[0406] Through the embodiments described above, the present invention provides a system that simultaneously improves the accuracy of earthquake prediction and enables rapid emergency response, thereby protecting human lives and minimizing property damage.

[0407] The following describes the processing flow.

[0408] Step 1:

[0409] The server collects data in real time. It retrieves data from earthquake-related databases, IoT sensors, and GIS via APIs and stores it in a central database. This collection includes the latest crustal deformation information and sensor data.

[0410] Step 2:

[0411] The server inputs the collected data into a deep learning model for analysis. The model uses frameworks such as TensorFlow or PyTorch to calculate the probability and magnitude of earthquakes, as well as the predicted epicenter.

[0412] Step 3:

[0413] The server analyzes the prediction results and identifies specific regions and users that may be affected. Geographic information stored in the database is used to narrow down the target of notifications.

[0414] Step 4:

[0415] The server generates a warning notification and sends it to users in the affected area. The notification includes evacuation instructions and specific information for ensuring safety.

[0416] Step 5:

[0417] The device receives a notification from the server. Smartphones and tablets display an alert on the screen and alert the user with a notification sound or vibration.

[0418] Step 6:

[0419] The user will learn how to quickly evacuate to a safe place by following the instructions on the device. Based on information such as maps provided by the device, they will select the nearest evacuation center and a safe route.

[0420] Step 7:

[0421] The server works in conjunction with infrastructure equipment to execute automated protective measures. Specifically, it controls the shutoff of gas supplies in designated areas and the activation of building safety systems. This prevents secondary damage caused by earthquakes.

[0422] (Example 1)

[0423] 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."

[0424] To minimize damage caused by earthquakes, rapid and accurate prediction and efficient response are essential. However, conventional systems lack sufficient prediction accuracy and have limitations in providing customized responses for individual regions and users. Furthermore, automated protective measures to prevent secondary disasters caused by earthquakes are inadequate.

[0425] 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.

[0426] In this invention, the server includes a collection means for acquiring earthquake-related information in real time, an analysis means for analyzing the acquired information and predicting the occurrence of earthquakes using a machine learning algorithm, and a means for notifying potentially affected users based on the predicted information. This improves the accuracy of earthquake prediction and enables the automatic execution of protective measures for structures within the affected area.

[0427] "Collection means" refers to a device or process for acquiring earthquake-related information in real time.

[0428] "Analysis means" refers to a device or process for analyzing acquired earthquake-related information and predicting earthquake occurrences using machine learning algorithms.

[0429] "Means of notification" refers to a device or process for communicating warnings to potentially affected users based on predicted earthquake information.

[0430] "Means of coordination with infrastructure devices" refers to devices or processes for communicating with and controlling external infrastructure devices in order to implement protective measures against structures within a region.

[0431] A "machine learning algorithm" is a series of computational methods used to analyze large amounts of earthquake data, build predictive models, and predict future earthquake occurrences.

[0432] This invention provides a comprehensive system for predicting earthquakes and minimizing their damage. This system improves earthquake prediction accuracy and enables efficient emergency response by collecting information in real time and performing advanced analysis.

[0433] The server's first task is to collect information related to seismic activity. Specifically, IoT sensors installed in various locations are used as hardware. These sensors detect ground deformation and acceleration, and transmit this information to the server via the network. The server records the received data in a database and prepares it for analysis.

[0434] The server then inputs data into a deep learning model using TensorFlow, and the model, trained on past earthquake data, predicts the probability, magnitude, and epicenter of an earthquake. This identifies areas with a high probability of earthquakes, and the prediction results are stored in a database.

[0435] Based on the predicted information, the server identifies users in potentially affected areas and generates notifications. These notifications include evacuation recommendations and safety measures to help users respond quickly.

[0436] Users receive notifications from the server on their devices. When smartphones and tablets receive a notification, they display an alert on the screen and provide warnings via sound and vibration. This allows users to detect earthquake precursors early and take appropriate evacuation actions.

[0437] Furthermore, the server communicates with smart home systems and urban infrastructure to enable automated protective measures. For example, it can send signals to shut off the gas supply to a building or stop elevators at the nearest floor. This helps prevent secondary disasters caused by earthquakes and mitigate damage.

[0438] As a concrete example, if the probability of an earthquake increases in a certain area, the server can send a notification to users in that area stating, "There is a possibility of an earthquake. Please consider evacuating to a safe place as soon as possible." This system, by utilizing generated AI models and prompt messages, enables more reliable disaster prevention measures.

[0439] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0440] Step 1:

[0441] The server collects information related to seismic activity. It acquires ground deformation data in real time from IoT sensors installed in various locations and transmits it to the server via the network. The input is raw data from the sensors, and the output is seismic activity information stored in a database. Specifically, the server receives data packets from the sensors, organizes them as time-series data, and stores them.

[0442] Step 2:

[0443] The server analyzes the collected seismic activity information. It uses time-series data from the database saved in Step 1 as input. The server inputs the data into a deep learning model using TensorFlow to predict the probability of an earthquake, its epicenter, and its magnitude. The output is earthquake prediction data as a result of the analysis. Specifically, the server runs the model and compares and analyzes the new data with past earthquake data.

[0444] Step 3:

[0445] The server generates notifications based on the analysis results. The input is the earthquake prediction data obtained in step 2. The server identifies the areas expected to be affected and generates notification content for users. The output is the notification message sent to users. Specifically, the server generates messages including evacuation orders and safety measures according to the magnitude of the earthquake and creates a list of recipients.

[0446] Step 4:

[0447] The device receives notifications from the server and transmits them to the user. The input is the notification message sent from the server. The device displays the notification on the screen and alerts the user with sound and vibration. The output is an alert display that the user can recognize. Specifically, the device analyzes the received data and sends a push notification with synchronized sound and vibration, along with a pop-up alert.

[0448] Step 5:

[0449] The server works in conjunction with infrastructure devices to implement protective measures. The input is earthquake prediction data analyzed in step 2. The server communicates with local smart home systems and urban infrastructure and automatically sends control signals. The output is control commands to the relevant infrastructure devices. Specific examples include sending shutdown signals for gas supply systems and activating emergency equipment.

[0450] (Application Example 1)

[0451] 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."

[0452] Earthquakes are difficult to predict, and rapid information dissemination and response are necessary to mitigate their impact. However, current systems lack sufficient accuracy in earthquake prediction and rapid implementation of countermeasures, making it highly likely that the safety of citizens will be threatened. Furthermore, in urban environments, the integration with smart technologies is insufficient, making it difficult to implement a rapid and comprehensive response to minimize damage. Solving these challenges is essential.

[0453] 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.

[0454] In this invention, the server includes means for acquiring earthquake-related information in real time, means for analyzing the acquired information and predicting the occurrence of earthquakes using a deep learning algorithm, means for notifying potentially affected users of warnings based on the prediction results, means for realizing coordination with the urban environment and automatically managing infrastructure facilities, and means for providing evacuation orders and information on evacuation facilities based on earthquake predictions. This makes it possible to improve the safety of citizens through rapid information dissemination during earthquakes and automated infrastructure management.

[0455] "Information related to earthquakes" refers to data indicating seismic activity and external information necessary for prediction, which includes sensor data, geographical information, and historical earthquake data.

[0456] "Means of acquiring information in real time" refers to technologies and devices for immediately collecting and processing information about ongoing seismic activity.

[0457] "Deep learning algorithms" are a field of artificial intelligence that uses multi-layer neural networks to recognize and analyze complex patterns.

[0458] "Predictive means" refers to methods and devices used to predict future earthquake occurrences using acquired data.

[0459] "Means of notifying of warnings" refers to a system that transmits warnings and cautions to potentially affected users based on predicted earthquake information.

[0460] "Means of realizing collaboration with the urban environment" refers to technologies that enable automated control by sharing information through communication and collaboration with urban infrastructure and management systems.

[0461] "Means for automatically managing infrastructure facilities" refers to methods and devices for autonomously operating public facilities and building systems in cities based on earthquake predictions.

[0462] "Evacuation orders based on earthquake predictions" refer to the dissemination of information that provides users with appropriate evacuation advisories and action guidelines in response to predicted seismic activity.

[0463] "Information on evacuation facilities" refers to information about places and facilities where people can safely evacuate in the event of an earthquake, and this includes location information and capacity.

[0464] This invention is a comprehensive system for realizing earthquake prediction and safety measures based on that prediction. Servers, terminals, and users each play their respective roles and work together in a coordinated manner.

[0465] The server first acquires earthquake-related information in real time from various data sources. This information includes data from IoT sensors placed in various locations, geographic information systems (GIS), and historical earthquake data. The server continuously stores this data in central data storage. The server analyzes the stored data using deep learning algorithms to predict earthquake occurrences. Deep learning models built using machine learning libraries such as TensorFlow and Keras are used.

[0466] The device receives predictive information generated by the server. Smartphones, tablets, and other devices receive real-time alert notifications and display alerts to the user. Notification systems such as Firebase are used to deliver information quickly and reliably. Notifications include images and text, and are accompanied by sound and vibration to attract the user's attention.

[0467] Users take swift evacuation actions based on information provided by their devices. In this process, smart city infrastructure, capable of coordinating with the urban environment, automatically accepts instructions from the server and implements safety measures. This includes functions such as shutting off gas supplies to public facilities. Information about evacuation facilities within the city is also displayed on the devices, helping users to plan specific actions during evacuation.

[0468] For example, if an earthquake is predicted to occur near Tokyo, the user's device will instantly display information on the epicenter, seismic intensity, and evacuation shelters, urging them to evacuate. As a safety measure, traffic signals within the city will be controlled to prevent traffic accidents.

[0469] An example of a prompt message would be: "An earthquake has been predicted in Tokyo, with a magnitude of 7.0 and the epicenter in Shinjuku Ward. Please compile the information to display in the app in order to issue evacuation orders to users."

[0470] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0471] Step 1:

[0472] The server acquires earthquake-related information in real time. Inputs include data from IoT sensors, geographic information system (GIS) data, and historical earthquake data. The server stores this data in central data storage, performing the specific operation of organizing and saving the information in a database.

[0473] Step 2:

[0474] The server analyzes accumulated earthquake-related data using deep learning algorithms. A model built with TensorFlow is used, and the server supplies input data to the model to calculate the probability of earthquake occurrence, expected magnitude, and epicenter. The resulting output generates predicted values ​​based on each parameter.

[0475] Step 3:

[0476] The server identifies potentially affected users based on the analysis results. The input is generated predictive data, and the server performs data calculations to identify those who will be notified by matching it with the user's location information. A list of those who will be notified is output.

[0477] Step 4:

[0478] The server sends alert information to the recipient. The server utilizes notification services such as Firebase to send alerts to specific devices. Input includes the user's contact information and predictive data, and output is delivered as an alert message accompanied by voice or vibration.

[0479] Step 5:

[0480] The terminal displays the received alert information. The terminal receives data sent from the server and outputs visual warnings and audio information. It performs specific actions such as displaying alerts in detail on the screen so that the user can understand them immediately.

[0481] Step 6:

[0482] Users take swift evacuation action based on information from their devices. They check maps and route information for evacuation facilities provided by their devices, select an appropriate evacuation destination, and begin their actions. Safety is ensured through this process.

[0483] Step 7:

[0484] The server automatically controls infrastructure facilities in conjunction with the urban environment. The input is control commands based on earthquake predictions, and the server adjusts traffic signals, gas supply shutdowns, etc., based on the results analyzed by a generated AI model, and the output is the execution of safety measures.

[0485] 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.

[0486] This invention provides a system that accurately predicts earthquake occurrences and supports responses tailored to potential impacts, while also considering user emotions to achieve more flexible and personalized responses. This system combines conventional earthquake prediction systems with emotion recognition capabilities.

[0487] Specifically, the server acquires various earthquake-related data in real time and analyzes it using deep learning algorithms. Based on the prediction results obtained from the analysis, warnings about potential earthquakes and predictions of the resulting damage are issued.

[0488] The key element here is the emotion engine built into the device. This emotion engine analyzes the user's voice, facial expressions, or input actions to identify emotional states such as tension, anxiety, relief, and fear. The analysis is performed using machine learning algorithms, and the results are sent to the server in real time.

[0489] The server receives this emotional data and generates a warning message that is best suited to the user's current mental state. For example, if the server detects that the user is feeling anxious, a gentle and encouraging message will be selected; if the user is feeling at ease, more specific instructions will be provided.

[0490] When a user receives a warning message displayed on their device, it includes not only standard evacuation instructions but also advice tailored to their mental state. This allows users to receive information in a psychologically appropriate way and take appropriate action.

[0491] Furthermore, the server adjusts its coordination with the infrastructure system as needed based on this emotional data. For example, if a user's emotions indicate extreme anxiety, a faster response is required, and the implementation of protective measures will be prioritized.

[0492] Thus, the present invention enhances the quality of user response and supports more effective and reassuring disaster response by incorporating emotion recognition into a practical earthquake prediction system.

[0493] The following describes the processing flow.

[0494] Step 1:

[0495] The server acquires earthquake-related data in real time from various sensors and databases. This includes crustal deformation information, seismic activity history, and data from geographic information systems. This data is stored in a central database on the server.

[0496] Step 2:

[0497] The server analyzes the collected data using deep learning algorithms. It compares past earthquake patterns with current data to predict earthquake occurrences. This process yields predictions about the likelihood, magnitude, and location of future earthquakes.

[0498] Step 3:

[0499] An emotion engine built into the device recognizes the user's current emotional state in real time. It analyzes voice tone, changes in facial expressions, and input data to identify the psychological state the user is feeling. This result is transmitted from the device to the server.

[0500] Step 4:

[0501] The server integrates emotional data and earthquake prediction data to generate warning messages tailored to the user's emotions. Messages are adjusted to provide greater reassurance for highly anxious users, while calmer users receive more specific instructions.

[0502] Step 5:

[0503] The device notifies the user of a generated warning message. The device displays the message on the screen and uses vibration and sound as needed to attract attention. The user receives psychologically sensitive information and prepares to calmly take evacuation action.

[0504] Step 6:

[0505] Based on the displayed messages and map information, users can quickly and accurately begin evacuation to a safe location. Advice tailored to their emotional state is provided, allowing them to act with a sense of security.

[0506] Step 7:

[0507] The server considers the received emotional data and adjusts the operation of the collaborating infrastructure systems as needed. For example, if a user indicates high levels of anxiety, more intensive protective measures will be taken.

[0508] (Example 2)

[0509] 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."

[0510] Minimizing damage from earthquakes requires prompt and accurate warnings and appropriate responses. However, conventional earthquake prediction systems often fail to provide individualized responses that take into account the emotional state of users, resulting in uniform warning messages. As a result, information may not be adequately conveyed, and appropriate evacuation actions may not be taken. Furthermore, there is the challenge of providing a rapid response that also takes into account the impact on local infrastructure.

[0511] 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.

[0512] In this invention, the server includes means for collecting earthquake-related information in real time, means for analyzing the collected information and predicting the occurrence of earthquakes using machine learning algorithms, means for notifying users of individually optimized warnings by analyzing their emotional state based on the prediction results, and means for coordinating protective measures in cooperation with the infrastructure system. This enables flexible information provision and rapid infrastructure adjustment in accordance with the user's psychological state.

[0513] "Information related to earthquakes" refers to historical data, geological data, and current crustal activity information related to earthquakes.

[0514] "Means of real-time collection" refers to methods and technologies for continuously acquiring earthquake-related information with an emphasis on immediacy.

[0515] A "machine learning algorithm" is a set of computational methods that allow a computer to learn patterns based on given data and perform predictions and classifications.

[0516] "Methods for analyzing emotional states" refer to technologies that capture data such as the user's voice and facial expressions, and then use that data to identify and quantify the user's emotions.

[0517] "Means of providing individually optimized warnings" refers to methods and systems for delivering warnings to individual users in a format that is optimal for each user, based on analyzed user sentiment data.

[0518] "Infrastructure systems" refer to all systems, including social infrastructure facilities and interfaces, that are used to provide protection against earthquakes.

[0519] "Means of coordinating protective measures" refers to methods of controlling the operation of infrastructure systems to take timely and appropriate countermeasures based on earthquake predictions.

[0520] The invention is a system that predicts earthquake occurrences with high accuracy and provides individually optimized earthquake warnings based on the user's emotions. The following hardware and software are required to implement this system:

[0521] The servers are located in high-performance data centers and collect earthquake-related information in real time from various observation agencies. The software used includes TensorFlow and similar deep learning frameworks for data analysis. The servers utilize these tools to build earthquake prediction models and analyze the latest crustal activity.

[0522] The terminal is a device that has a direct interface with the user and is equipped with a camera and microphone to sense the user's voice and facial expressions. Using OpenCV and PyTorch, the terminal analyzes the user's emotions in real time. The analysis results are then quickly transmitted to the server.

[0523] When the server receives emotion data, it combines it with earthquake prediction data to generate the most appropriate warning message for each user. This message generation is customized according to the user's different emotional state, such as anxiety, tension, or reassurance. For example, if the user is analyzed as anxious, the message might say, "Please check your safety and remain calm while awaiting further instructions."

[0524] Furthermore, the servers work in conjunction with the infrastructure system to coordinate the protective measures required for each region and facility. This coordination includes, for example, emergency route guidance and the implementation of pre-emptive evacuation plans.

[0525] As a concrete example, here is an example of a prompt message for a generative AI model: "Explain how to generate warning messages that are appropriate to the user's individual psychological state, taking into account the user's emotions during an earthquake. Provide a specific example and show how the system works."

[0526] In this way, this invention enhances the quality of information provided to users and realizes a system that enables a sense of security in disaster response.

[0527] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0528] Step 1:

[0529] The server collects earthquake-related observation data in real time. Inputs include crustal activity information and historical earthquake data obtained from various earthquake detection agencies. Based on this data, it uses a deep learning framework to perform data analysis and execute an earthquake prediction model. Outputs include information on the predicted earthquake location and magnitude. This information is sent to other system modules.

[0530] Step 2:

[0531] The device acquires user voice and facial expression data in real time via its camera and microphone. Inputs include the user's voice signal and video images containing their facial expressions. An emotion analysis algorithm is used to identify the user's emotional state from this data, quantifying emotions such as "tension," "anxiety," and "relief." Specifically, it combines image analysis using OpenCV with voice analysis using PyTorch. The analyzed emotion information is sent to a server as output.

[0532] Step 3:

[0533] The server integrates received sentiment data and earthquake prediction data to generate a personalized warning message for each user. The inputs are sentiment data and earthquake prediction information. A generative AI model is used to create a message tailored to each individual user based on these inputs. In this process, the message content is customized depending on whether the user is anxious or reassured. The output is a personalized warning message sent to the device.

[0534] Step 4:

[0535] The user receives a warning message displayed on the device and acts accordingly. The input is the warning message displayed on the device. This provides the user with guidance for taking specific evacuation actions and countermeasures. Specifically, the user checks the instructed evacuation route and evacuates quickly while ensuring the safety of the surroundings. The output is the execution of the user's evacuation actions.

[0536] Step 5:

[0537] The server coordinates with the infrastructure system as needed to adjust protective measures. Inputs include collective user sentiment data and earthquake prediction information. Through the infrastructure system's control interface, it coordinates and distributes warning systems and evacuation route information for specific areas. The output is the provision of appropriate protective measures and information across the entire region.

[0538] (Application Example 2)

[0539] 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."

[0540] Earthquake prediction systems are required not only to notify users of earthquakes in advance, but also to provide information that takes into account the individual emotional state of each user. However, conventional earthquake prediction systems have struggled to provide customized information according to the user's emotions, and have failed to encourage the user to take the most appropriate action. Therefore, it is necessary to provide detailed responses that are tailored to the user's emotional state in order to alleviate fear and anxiety during disasters and support decisive action.

[0541] 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.

[0542] In this invention, the server includes a device for acquiring earthquake-related information in real time, a device for analyzing the acquired information and estimating the occurrence of earthquakes using a deep learning algorithm, a device for analyzing the user's emotional state and identifying emotions based on voice, facial expressions, or input operations, and a device for generating warning information that is most appropriate to the user's current mental state based on the acquired emotional information. This makes it possible to provide personalized information that takes the user's emotions into consideration.

[0543] "Information related to earthquakes" refers to data such as the time of the earthquake, the epicenter, the magnitude, and the distribution of seismic intensity.

[0544] "Real-time acquisition" means collecting data instantly and obtaining the latest information with minimal time lag.

[0545] A "deep learning algorithm" is a machine learning technique that uses multi-layered neural networks and is a method for learning complex patterns from large amounts of data.

[0546] "Estimating earthquake occurrence" means predicting potential future earthquakes based on past earthquake data and real-time observation data.

[0547] "User's emotional state" refers to the subjective feelings and psychological state experienced by individual users.

[0548] "Identifying emotions based on voice, facial expressions, or input actions" means analyzing the sounds a user makes, changes in their facial expressions, or input actions they make on the device to determine their current emotions.

[0549] "Acquired emotional information" refers to data recorded by analyzing the user's emotional state.

[0550] "Generating warning information" means creating user-specific notifications for evacuation and safety measures in response to predicted earthquakes.

[0551] This system is equipped with advanced devices for collecting and analyzing earthquake-related information in real time. The server first acquires earthquake data in real time and then uses deep learning algorithms to predict earthquake occurrences. The earthquake data includes information from sensors and observation stations, and by utilizing deep learning, it is possible to achieve more accurate predictions than ever before.

[0552] The device is equipped with voice recognition software and a facial expression analysis camera to analyze the user's emotional state. The device identifies emotions from the user's voice commands, facial expressions, or touch panel operations, and sends the results to a server. Based on this data, the server generates warning information appropriate to the user's current mental state. For example, if the server determines that the user is stressed, it can provide information to help them calm down.

[0553] Users receive these personalized warnings through devices such as smartphones and smart glasses. By considering each individual's emotional state, the system can take more appropriate measures against earthquakes, allowing users to confidently and quickly take self-protective action.

[0554] For example, if the user's facial expression or voice indicates anxiety while the whole family is gathered together, the system can provide encouraging messages along with information on actions to avoid and evacuation points for disaster preparedness. An example of a prompt for the generating AI model would be, "If an earthquake is predicted, please tell us how you are feeling now. We will then provide you with special advice."

[0555] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0556] Step 1:

[0557] The server acquires earthquake-related information in real time from seismic observatories and sensors. It receives earthquake data from sensors as input and stores it in a database. The output is established as an earthquake dataset. Specifically, it accesses the data using an API and updates the database.

[0558] Step 2:

[0559] The server applies a deep learning algorithm to the acquired earthquake dataset to estimate earthquake occurrences. The input is the earthquake dataset. A neural network model is used to analyze the data and calculate the probability of an earthquake occurring. The output is an earthquake prediction result. Specifically, the model is deployed using a GPU, and the estimation process is performed in real time.

[0560] Step 3:

[0561] The device analyzes the user's voice and facial expressions to identify their emotional state. Input consists of the user's voice data and camera images, and an emotion recognition algorithm is used to identify the user's mental state (anxiety, tension, etc.). Output is the user's emotional information. Specifically, it collects data using voice recognition software and a facial recognition camera, and feeds this data into a machine learning model.

[0562] Step 4:

[0563] The server generates customized warning messages based on earthquake prediction results and user sentiment information. The inputs are earthquake prediction results and user sentiment information. Using sentiment-based message templates, it creates the most appropriate warning information for the user. The output is a personalized warning message. Specifically, it uses a sentiment recognition AI model to select messages and format them as text data.

[0564] Step 5:

[0565] The user receives personalized warning messages through their device. The input is the warning message, displayed on the device. The user can then take safe actions based on it. The output is a guide to the user's actions. Specifically, this involves activating a notification function on a smartphone or smart glasses and displaying information on the user interface.

[0566] 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.

[0567] 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 the following. 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 indicated 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.

[0568] 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.

[0569] [Fourth Embodiment]

[0570] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0571] 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.

[0572] 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).

[0573] 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.

[0574] 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.

[0575] 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).

[0576] 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.

[0577] 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.

[0578] 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.

[0579] 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.

[0580] 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.

[0581] 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.

[0582] 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".

[0583] This invention provides a comprehensive system for predicting earthquakes in advance and minimizing their damage. This system improves earthquake prediction accuracy and enables efficient emergency response by collecting data in real time and performing advanced analysis. The following describes its embodiments.

[0584] First, the server collects data related to seismic activity in real time. This utilizes earthquake databases, IoT sensors placed in various locations, and geographic information systems (GIS). The server periodically retrieves this data and records it in central data storage.

[0585] The acquired data is input into a deep learning model on the server. This model is highly trained on past earthquake data and has the ability to predict the probability of an earthquake, its expected magnitude, and its epicenter from the newly input data. The prediction information obtained as a result of the analysis is stored in a database.

[0586] Next, the server identifies users in potentially affected areas based on the predicted earthquake information and sends notifications. These notifications include recommended evacuation actions and safety measures to help users respond quickly.

[0587] Users receive notifications through their own devices. Smartphones, tablets, and other devices receive notifications from the server, display alerts on the screen, and highlight the notifications with sound and vibration. This allows users to detect earthquake precursors early and take appropriate evacuation actions.

[0588] Furthermore, to enable integration with infrastructure, the server communicates with smart home systems and urban infrastructure to automatically execute protective measures. This includes functions such as automatically shutting off the gas supply to a building and activating safety devices. This coordination can prevent secondary disasters caused by earthquakes and mitigate damage.

[0589] Through the embodiments described above, the present invention provides a system that simultaneously improves the accuracy of earthquake prediction and enables rapid emergency response, thereby protecting human lives and minimizing property damage.

[0590] The following describes the processing flow.

[0591] Step 1:

[0592] The server collects data in real time. It retrieves data from earthquake-related databases, IoT sensors, and GIS via APIs and stores it in a central database. This collection includes the latest crustal deformation information and sensor data.

[0593] Step 2:

[0594] The server inputs the collected data into a deep learning model for analysis. The model uses frameworks such as TensorFlow or PyTorch to calculate the probability and magnitude of earthquakes, as well as the predicted epicenter.

[0595] Step 3:

[0596] The server analyzes the prediction results and identifies specific regions and users that may be affected. Geographic information stored in the database is used to narrow down the target of notifications.

[0597] Step 4:

[0598] The server generates a warning notification and sends it to users in the affected area. The notification includes evacuation instructions and specific information for ensuring safety.

[0599] Step 5:

[0600] The device receives a notification from the server. Smartphones and tablets display an alert on the screen and alert the user with a notification sound or vibration.

[0601] Step 6:

[0602] The user will learn how to quickly evacuate to a safe place by following the instructions on the device. Based on information such as maps provided by the device, they will select the nearest evacuation center and a safe route.

[0603] Step 7:

[0604] The server works in conjunction with infrastructure equipment to execute automated protective measures. Specifically, it controls the shutoff of gas supplies in designated areas and the activation of building safety systems. This prevents secondary damage caused by earthquakes.

[0605] (Example 1)

[0606] 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".

[0607] To minimize damage caused by earthquakes, rapid and accurate prediction and efficient response are essential. However, conventional systems lack sufficient prediction accuracy and have limitations in providing customized responses for individual regions and users. Furthermore, automated protective measures to prevent secondary disasters caused by earthquakes are inadequate.

[0608] 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.

[0609] In this invention, the server includes a collection means for acquiring earthquake-related information in real time, an analysis means for analyzing the acquired information and predicting the occurrence of earthquakes using a machine learning algorithm, and a means for notifying potentially affected users based on the predicted information. This improves the accuracy of earthquake prediction and enables the automatic execution of protective measures for structures within the affected area.

[0610] "Collection means" refers to a device or process for acquiring earthquake-related information in real time.

[0611] "Analysis means" refers to a device or process for analyzing acquired earthquake-related information and predicting earthquake occurrences using machine learning algorithms.

[0612] "Means of notification" refers to a device or process for communicating warnings to potentially affected users based on predicted earthquake information.

[0613] "Means of coordination with infrastructure devices" refers to devices or processes for communicating with and controlling external infrastructure devices in order to implement protective measures against structures within a region.

[0614] A "machine learning algorithm" is a series of computational methods used to analyze large amounts of earthquake data, build predictive models, and predict future earthquake occurrences.

[0615] This invention provides a comprehensive system for predicting earthquakes and minimizing their damage. This system improves earthquake prediction accuracy and enables efficient emergency response by collecting information in real time and performing advanced analysis.

[0616] The server's first task is to collect information related to seismic activity. Specifically, IoT sensors installed in various locations are used as hardware. These sensors detect ground deformation and acceleration, and transmit this information to the server via the network. The server records the received data in a database and prepares it for analysis.

[0617] The server then inputs data into a deep learning model using TensorFlow, and the model, trained on past earthquake data, predicts the probability, magnitude, and epicenter of an earthquake. This identifies areas with a high probability of earthquakes, and the prediction results are stored in a database.

[0618] Based on the predicted information, the server identifies users in potentially affected areas and generates notifications. These notifications include evacuation recommendations and safety measures to help users respond quickly.

[0619] Users receive notifications from the server on their devices. When smartphones and tablets receive a notification, they display an alert on the screen and provide warnings via sound and vibration. This allows users to detect earthquake precursors early and take appropriate evacuation actions.

[0620] Furthermore, the server communicates with smart home systems and urban infrastructure to enable automated protective measures. For example, it can send signals to shut off the gas supply to a building or stop elevators at the nearest floor. This helps prevent secondary disasters caused by earthquakes and mitigate damage.

[0621] As a concrete example, if the probability of an earthquake increases in a certain area, the server can send a notification to users in that area stating, "There is a possibility of an earthquake. Please consider evacuating to a safe place as soon as possible." This system, by utilizing generated AI models and prompt messages, enables more reliable disaster prevention measures.

[0622] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0623] Step 1:

[0624] The server collects information related to seismic activity. It acquires ground deformation data in real time from IoT sensors installed in various locations and transmits it to the server via the network. The input is raw data from the sensors, and the output is seismic activity information stored in a database. Specifically, the server receives data packets from the sensors, organizes them as time-series data, and stores them.

[0625] Step 2:

[0626] The server analyzes the collected seismic activity information. It uses time-series data from the database saved in Step 1 as input. The server inputs the data into a deep learning model using TensorFlow to predict the probability of an earthquake, its epicenter, and its magnitude. The output is earthquake prediction data as a result of the analysis. Specifically, the server runs the model and compares and analyzes the new data with past earthquake data.

[0627] Step 3:

[0628] The server generates notifications based on the analysis results. The input is the earthquake prediction data obtained in step 2. The server identifies the areas expected to be affected and generates notification content for users. The output is the notification message sent to users. Specifically, the server generates messages including evacuation orders and safety measures according to the magnitude of the earthquake and creates a list of recipients.

[0629] Step 4:

[0630] The device receives notifications from the server and transmits them to the user. The input is the notification message sent from the server. The device displays the notification on the screen and alerts the user with sound and vibration. The output is an alert display that the user can recognize. Specifically, the device analyzes the received data and sends a push notification with synchronized sound and vibration, along with a pop-up alert.

[0631] Step 5:

[0632] The server works in conjunction with infrastructure devices to implement protective measures. The input is earthquake prediction data analyzed in step 2. The server communicates with local smart home systems and urban infrastructure and automatically sends control signals. The output is control commands to the relevant infrastructure devices. Specific examples include sending shutdown signals for gas supply systems and activating emergency equipment.

[0633] (Application Example 1)

[0634] 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".

[0635] Earthquakes are difficult to predict, and rapid information dissemination and response are necessary to mitigate their impact. However, current systems lack sufficient accuracy in earthquake prediction and rapid implementation of countermeasures, making it highly likely that the safety of citizens will be threatened. Furthermore, in urban environments, the integration with smart technologies is insufficient, making it difficult to implement a rapid and comprehensive response to minimize damage. Solving these challenges is essential.

[0636] 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.

[0637] In this invention, the server includes means for acquiring earthquake-related information in real time, means for analyzing the acquired information and predicting the occurrence of earthquakes using a deep learning algorithm, means for notifying potentially affected users of warnings based on the prediction results, means for realizing coordination with the urban environment and automatically managing infrastructure facilities, and means for providing evacuation orders and information on evacuation facilities based on earthquake predictions. This makes it possible to improve the safety of citizens through rapid information dissemination during earthquakes and automated infrastructure management.

[0638] "Information related to earthquakes" refers to data indicating seismic activity and external information necessary for prediction, which includes sensor data, geographical information, and historical earthquake data.

[0639] "Means of acquiring information in real time" refers to technologies and devices for immediately collecting and processing information about ongoing seismic activity.

[0640] "Deep learning algorithms" are a field of artificial intelligence that uses multi-layer neural networks to recognize and analyze complex patterns.

[0641] "Predictive means" refers to methods and devices used to predict future earthquake occurrences using acquired data.

[0642] "Means of notifying of warnings" refers to a system that transmits warnings and cautions to potentially affected users based on predicted earthquake information.

[0643] "Means of realizing collaboration with the urban environment" refers to technologies that enable automated control by sharing information through communication and collaboration with urban infrastructure and management systems.

[0644] "Means for automatically managing infrastructure facilities" refers to methods and devices for autonomously operating public facilities and building systems in cities based on earthquake predictions.

[0645] "Evacuation orders based on earthquake predictions" refer to the dissemination of information that provides users with appropriate evacuation advisories and action guidelines in response to predicted seismic activity.

[0646] "Information on evacuation facilities" refers to information about places and facilities where people can safely evacuate in the event of an earthquake, and this includes location information and capacity.

[0647] This invention is a comprehensive system for realizing earthquake prediction and safety measures based on that prediction. Servers, terminals, and users each play their respective roles and work together in a coordinated manner.

[0648] The server first acquires earthquake-related information in real time from various data sources. This information includes data from IoT sensors placed in various locations, geographic information systems (GIS), and historical earthquake data. The server continuously stores this data in central data storage. The server analyzes the stored data using deep learning algorithms to predict earthquake occurrences. Deep learning models built using machine learning libraries such as TensorFlow and Keras are used.

[0649] The device receives predictive information generated by the server. Smartphones, tablets, and other devices receive real-time alert notifications and display alerts to the user. Notification systems such as Firebase are used to deliver information quickly and reliably. Notifications include images and text, and are accompanied by sound and vibration to attract the user's attention.

[0650] Users take swift evacuation actions based on information provided by their devices. In this process, smart city infrastructure, capable of coordinating with the urban environment, automatically accepts instructions from the server and implements safety measures. This includes functions such as shutting off gas supplies to public facilities. Information about evacuation facilities within the city is also displayed on the devices, helping users to plan specific actions during evacuation.

[0651] For example, if an earthquake is predicted to occur near Tokyo, the user's device will instantly display information on the epicenter, seismic intensity, and evacuation shelters, urging them to evacuate. As a safety measure, traffic signals within the city will be controlled to prevent traffic accidents.

[0652] An example of a prompt message would be: "An earthquake has been predicted in Tokyo, with a magnitude of 7.0 and the epicenter in Shinjuku Ward. Please compile the information to display in the app in order to issue evacuation orders to users."

[0653] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0654] Step 1:

[0655] The server acquires earthquake-related information in real time. Inputs include data from IoT sensors, geographic information system (GIS) data, and historical earthquake data. The server stores this data in central data storage, performing the specific operation of organizing and saving the information in a database.

[0656] Step 2:

[0657] The server analyzes accumulated earthquake-related data using deep learning algorithms. A model built with TensorFlow is used, and the server supplies input data to the model to calculate the probability of earthquake occurrence, expected magnitude, and epicenter. The resulting output generates predicted values ​​based on each parameter.

[0658] Step 3:

[0659] The server identifies potentially affected users based on the analysis results. The input is generated predictive data, and the server performs data calculations to identify those who will be notified by matching it with the user's location information. A list of those who will be notified is output.

[0660] Step 4:

[0661] The server sends alert information to the recipient. The server utilizes notification services such as Firebase to send alerts to specific devices. Input includes the user's contact information and predictive data, and output is delivered as an alert message accompanied by voice or vibration.

[0662] Step 5:

[0663] The terminal displays the received alert information. The terminal receives data sent from the server and outputs visual warnings and audio information. It performs specific actions such as displaying alerts in detail on the screen so that the user can understand them immediately.

[0664] Step 6:

[0665] Users take swift evacuation action based on information from their devices. They check maps and route information for evacuation facilities provided by their devices, select an appropriate evacuation destination, and begin their actions. Safety is ensured through this process.

[0666] Step 7:

[0667] The server automatically controls infrastructure facilities in conjunction with the urban environment. The input is control commands based on earthquake predictions, and the server adjusts traffic signals, gas supply shutdowns, etc., based on the results analyzed by a generated AI model, and the output is the execution of safety measures.

[0668] 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.

[0669] This invention provides a system that accurately predicts earthquake occurrences and supports responses tailored to potential impacts, while also considering user emotions to achieve more flexible and personalized responses. This system combines conventional earthquake prediction systems with emotion recognition capabilities.

[0670] Specifically, the server acquires various earthquake-related data in real time and analyzes it using deep learning algorithms. Based on the prediction results obtained from the analysis, warnings about potential earthquakes and predictions of the resulting damage are issued.

[0671] The key element here is the emotion engine built into the device. This emotion engine analyzes the user's voice, facial expressions, or input actions to identify emotional states such as tension, anxiety, relief, and fear. The analysis is performed using machine learning algorithms, and the results are sent to the server in real time.

[0672] The server receives this emotional data and generates a warning message that is best suited to the user's current mental state. For example, if the server detects that the user is feeling anxious, a gentle and encouraging message will be selected; if the user is feeling at ease, more specific instructions will be provided.

[0673] When a user receives a warning message displayed on their device, it includes not only standard evacuation instructions but also advice tailored to their mental state. This allows users to receive information in a psychologically appropriate way and take appropriate action.

[0674] Furthermore, the server adjusts its coordination with the infrastructure system as needed based on this emotional data. For example, if a user's emotions indicate extreme anxiety, a faster response is required, and the implementation of protective measures will be prioritized.

[0675] Thus, the present invention enhances the quality of user response and supports more effective and reassuring disaster response by incorporating emotion recognition into a practical earthquake prediction system.

[0676] The following describes the processing flow.

[0677] Step 1:

[0678] The server acquires earthquake-related data in real time from various sensors and databases. This includes crustal deformation information, seismic activity history, and data from geographic information systems. This data is stored in a central database on the server.

[0679] Step 2:

[0680] The server analyzes the collected data using deep learning algorithms. It compares past earthquake patterns with current data to predict earthquake occurrences. This process yields predictions about the likelihood, magnitude, and location of future earthquakes.

[0681] Step 3:

[0682] An emotion engine built into the device recognizes the user's current emotional state in real time. It analyzes voice tone, changes in facial expressions, and input data to identify the psychological state the user is feeling. This result is transmitted from the device to the server.

[0683] Step 4:

[0684] The server integrates emotional data and earthquake prediction data to generate warning messages tailored to the user's emotions. Messages are adjusted to provide greater reassurance for highly anxious users, while calmer users receive more specific instructions.

[0685] Step 5:

[0686] The device notifies the user of a generated warning message. The device displays the message on the screen and uses vibration and sound as needed to attract attention. The user receives psychologically sensitive information and prepares to calmly take evacuation action.

[0687] Step 6:

[0688] Based on the displayed messages and map information, users can quickly and accurately begin evacuation to a safe location. Advice tailored to their emotional state is provided, allowing them to act with a sense of security.

[0689] Step 7:

[0690] The server considers the received emotional data and adjusts the operation of the collaborating infrastructure systems as needed. For example, if a user indicates high levels of anxiety, more intensive protective measures will be taken.

[0691] (Example 2)

[0692] 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".

[0693] Minimizing damage from earthquakes requires prompt and accurate warnings and appropriate responses. However, conventional earthquake prediction systems often fail to provide individualized responses that take into account the emotional state of users, resulting in uniform warning messages. As a result, information may not be adequately conveyed, and appropriate evacuation actions may not be taken. Furthermore, there is the challenge of providing a rapid response that also takes into account the impact on local infrastructure.

[0694] 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.

[0695] In this invention, the server includes means for collecting earthquake-related information in real time, means for analyzing the collected information and predicting the occurrence of earthquakes using machine learning algorithms, means for notifying users of individually optimized warnings by analyzing their emotional state based on the prediction results, and means for coordinating protective measures in cooperation with the infrastructure system. This enables flexible information provision and rapid infrastructure adjustment in accordance with the user's psychological state.

[0696] "Information related to earthquakes" refers to historical data, geological data, and current crustal activity information related to earthquakes.

[0697] "Means of real-time collection" refers to methods and technologies for continuously acquiring earthquake-related information with an emphasis on immediacy.

[0698] A "machine learning algorithm" is a set of computational methods that allow a computer to learn patterns based on given data and perform predictions and classifications.

[0699] "Methods for analyzing emotional states" refer to technologies that capture data such as the user's voice and facial expressions, and then use that data to identify and quantify the user's emotions.

[0700] "Means of providing individually optimized warnings" refers to methods and systems for delivering warnings to individual users in a format that is optimal for each user, based on analyzed user sentiment data.

[0701] "Infrastructure systems" refer to all systems, including social infrastructure facilities and interfaces, that are used to provide protection against earthquakes.

[0702] "Means of coordinating protective measures" refers to methods of controlling the operation of infrastructure systems to take timely and appropriate countermeasures based on earthquake predictions.

[0703] The invention is a system that predicts earthquake occurrences with high accuracy and provides individually optimized earthquake warnings based on the user's emotions. The following hardware and software are required to implement this system:

[0704] The servers are located in high-performance data centers and collect earthquake-related information in real time from various observation agencies. The software used includes TensorFlow and similar deep learning frameworks for data analysis. The servers utilize these tools to build earthquake prediction models and analyze the latest crustal activity.

[0705] The terminal is a device that has a direct interface with the user and is equipped with a camera and microphone to sense the user's voice and facial expressions. Using OpenCV and PyTorch, the terminal analyzes the user's emotions in real time. The analysis results are then quickly transmitted to the server.

[0706] When the server receives emotion data, it combines it with earthquake prediction data to generate the most appropriate warning message for each user. This message generation is customized according to the user's different emotional state, such as anxiety, tension, or reassurance. For example, if the user is analyzed as anxious, the message might say, "Please check your safety and remain calm while awaiting further instructions."

[0707] Furthermore, the servers work in conjunction with the infrastructure system to coordinate the protective measures required for each region and facility. This coordination includes, for example, emergency route guidance and the implementation of pre-emptive evacuation plans.

[0708] As a concrete example, here is an example of a prompt message for a generative AI model: "Explain how to generate warning messages that are appropriate to the user's individual psychological state, taking into account the user's emotions during an earthquake. Provide a specific example and show how the system works."

[0709] In this way, this invention enhances the quality of information provided to users and realizes a system that enables a sense of security in disaster response.

[0710] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0711] Step 1:

[0712] The server collects earthquake-related observation data in real time. Inputs include crustal activity information and historical earthquake data obtained from various earthquake detection agencies. Based on this data, it uses a deep learning framework to perform data analysis and execute an earthquake prediction model. Outputs include information on the predicted earthquake location and magnitude. This information is sent to other system modules.

[0713] Step 2:

[0714] The device acquires user voice and facial expression data in real time via its camera and microphone. Inputs include the user's voice signal and video images containing their facial expressions. An emotion analysis algorithm is used to identify the user's emotional state from this data, quantifying emotions such as "tension," "anxiety," and "relief." Specifically, it combines image analysis using OpenCV with voice analysis using PyTorch. The analyzed emotion information is sent to a server as output.

[0715] Step 3:

[0716] The server integrates received sentiment data and earthquake prediction data to generate a personalized warning message for each user. The inputs are sentiment data and earthquake prediction information. A generative AI model is used to create a message tailored to each individual user based on these inputs. In this process, the message content is customized depending on whether the user is anxious or reassured. The output is a personalized warning message sent to the device.

[0717] Step 4:

[0718] The user receives a warning message displayed on the device and acts accordingly. The input is the warning message displayed on the device. This provides the user with guidance for taking specific evacuation actions and countermeasures. Specifically, the user checks the instructed evacuation route and evacuates quickly while ensuring the safety of the surroundings. The output is the execution of the user's evacuation actions.

[0719] Step 5:

[0720] The server coordinates with the infrastructure system as needed to adjust protective measures. Inputs include collective user sentiment data and earthquake prediction information. Through the infrastructure system's control interface, it coordinates and distributes warning systems and evacuation route information for specific areas. The output is the provision of appropriate protective measures and information across the entire region.

[0721] (Application Example 2)

[0722] 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".

[0723] Earthquake prediction systems are required not only to notify users of earthquakes in advance, but also to provide information that takes into account the individual emotional state of each user. However, conventional earthquake prediction systems have struggled to provide customized information according to the user's emotions, and have failed to encourage the user to take the most appropriate action. Therefore, it is necessary to provide detailed responses that are tailored to the user's emotional state in order to alleviate fear and anxiety during disasters and support decisive action.

[0724] 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.

[0725] In this invention, the server includes a device for acquiring earthquake-related information in real time, a device for analyzing the acquired information and estimating the occurrence of earthquakes using a deep learning algorithm, a device for analyzing the user's emotional state and identifying emotions based on voice, facial expressions, or input operations, and a device for generating warning information that is most appropriate to the user's current mental state based on the acquired emotional information. This makes it possible to provide personalized information that takes the user's emotions into consideration.

[0726] "Information related to earthquakes" refers to data such as the time of the earthquake, the epicenter, the magnitude, and the distribution of seismic intensity.

[0727] "Real-time acquisition" means collecting data instantly and obtaining the latest information with minimal time lag.

[0728] A "deep learning algorithm" is a machine learning technique that uses multi-layered neural networks and is a method for learning complex patterns from large amounts of data.

[0729] "Estimating earthquake occurrence" means predicting potential future earthquakes based on past earthquake data and real-time observation data.

[0730] "User's emotional state" refers to the subjective feelings and psychological state experienced by individual users.

[0731] "Identifying emotions based on voice, facial expressions, or input actions" means analyzing the sounds a user makes, changes in their facial expressions, or input actions they make on the device to determine their current emotions.

[0732] "Acquired emotional information" refers to data recorded by analyzing the user's emotional state.

[0733] "Generating warning information" means creating user-specific notifications for evacuation and safety measures in response to predicted earthquakes.

[0734] This system is equipped with advanced devices for collecting and analyzing earthquake-related information in real time. The server first acquires earthquake data in real time and then uses deep learning algorithms to predict earthquake occurrences. The earthquake data includes information from sensors and observation stations, and by utilizing deep learning, it is possible to achieve more accurate predictions than ever before.

[0735] The device is equipped with voice recognition software and a facial expression analysis camera to analyze the user's emotional state. The device identifies emotions from the user's voice commands, facial expressions, or touch panel operations, and sends the results to a server. Based on this data, the server generates warning information appropriate to the user's current mental state. For example, if the server determines that the user is stressed, it can provide information to help them calm down.

[0736] Users receive these personalized warnings through devices such as smartphones and smart glasses. By considering each individual's emotional state, the system can take more appropriate measures against earthquakes, allowing users to confidently and quickly take self-protective action.

[0737] For example, if the user's facial expression or voice indicates anxiety while the whole family is gathered together, the system can provide encouraging messages along with information on actions to avoid and evacuation points for disaster preparedness. An example of a prompt for the generating AI model would be, "If an earthquake is predicted, please tell us how you are feeling now. We will then provide you with special advice."

[0738] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0739] Step 1:

[0740] The server acquires earthquake-related information in real time from seismic observatories and sensors. It receives earthquake data from sensors as input and stores it in a database. The output is established as an earthquake dataset. Specifically, it accesses the data using an API and updates the database.

[0741] Step 2:

[0742] The server applies a deep learning algorithm to the acquired earthquake dataset to estimate earthquake occurrences. The input is the earthquake dataset. A neural network model is used to analyze the data and calculate the probability of an earthquake occurring. The output is an earthquake prediction result. Specifically, the model is deployed using a GPU, and the estimation process is performed in real time.

[0743] Step 3:

[0744] The device analyzes the user's voice and facial expressions to identify their emotional state. Input consists of the user's voice data and camera images, and an emotion recognition algorithm is used to identify the user's mental state (anxiety, tension, etc.). Output is the user's emotional information. Specifically, it collects data using voice recognition software and a facial recognition camera, and feeds this data into a machine learning model.

[0745] Step 4:

[0746] The server generates customized warning messages based on earthquake prediction results and user sentiment information. The inputs are earthquake prediction results and user sentiment information. Using sentiment-based message templates, it creates the most appropriate warning information for the user. The output is a personalized warning message. Specifically, it uses a sentiment recognition AI model to select messages and format them as text data.

[0747] Step 5:

[0748] The user receives personalized warning messages through their device. The input is the warning message, displayed on the device. The user can then take safe actions based on it. The output is a guide to the user's actions. Specifically, this involves activating a notification function on a smartphone or smart glasses and displaying information on the user interface.

[0749] 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.

[0750] 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 the following. 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 indicated 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.

[0751] 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.

[0752] 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.

[0753] 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.

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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."

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] The following is further disclosed regarding the embodiments described above.

[0771] (Claim 1)

[0772] Means for collecting earthquake-related data in real time,

[0773] A method for analyzing collected data and predicting earthquake occurrences using deep learning algorithms,

[0774] A means of notifying potentially affected users of warnings based on the prediction results,

[0775] A system that includes this.

[0776] (Claim 2)

[0777] The system according to claim 1, characterized in that it includes means for proposing customized damage predictions and protective measures for a specific region or user based on the results of earthquake occurrence predictions.

[0778] (Claim 3)

[0779] The system according to claim 1, characterized in that it has an interface means with an infrastructure system that controls equipment in an area affected by a predicted earthquake and automatically performs protective measures.

[0780] "Example 1"

[0781] (Claim 1)

[0782] A means of collecting information related to earthquakes in real time,

[0783] An analytical method that analyzes acquired information and uses a machine learning algorithm to predict the occurrence of earthquakes,

[0784] Means of notifying potentially affected users based on predicted information,

[0785] A means of coordinating with infrastructure devices that control structures within the region based on acquired information and automatically execute protective measures,

[0786] A system that includes this.

[0787] (Claim 2)

[0788] The system according to claim 1, which provides customized countermeasures to a specific range or user based on the results of earthquake prediction.

[0789] (Claim 3)

[0790] The system according to claim 1, characterized in that it has means of communication with infrastructure equipment for controlling structures within a range that may be affected by a predicted earthquake and for automatically performing protective measures.

[0791] "Application Example 1"

[0792] (Claim 1)

[0793] Means of obtaining earthquake-related information in real time,

[0794] A method for analyzing acquired information and predicting earthquake occurrences using a deep learning algorithm,

[0795] Based on the prediction results, a means of notifying potentially affected users of the warning,

[0796] A means to achieve integration with the urban environment and automatically manage infrastructure facilities,

[0797] A means of providing evacuation orders and information on evacuation facilities based on earthquake predictions,

[0798] A system that includes this.

[0799] (Claim 2)

[0800] The system according to claim 1, characterized in that it includes means for proposing customized damage predictions and preventive measures for a specific area or user based on the results of earthquake occurrence predictions.

[0801] (Claim 3)

[0802] The system according to claim 1, characterized by having means for connecting to an infrastructure system that operates structures within an area affected by a predicted earthquake and automatically performs preventive measures.

[0803] "Example 2 of combining an emotion engine"

[0804] (Claim 1)

[0805] Means of collecting earthquake-related information in real time,

[0806] A method for analyzing collected information and predicting earthquake occurrences using machine learning algorithms,

[0807] Based on the prediction results, a means of notifying users of individually optimized warnings by analyzing their emotional state,

[0808] Means of coordinating protective measures in conjunction with infrastructure systems,

[0809] A system that includes this.

[0810] (Claim 2)

[0811] The system according to claim 1, characterized by having means to provide specific evacuation instructions tailored to the individual psychological state based on user emotion analysis data.

[0812] (Claim 3)

[0813] The system according to claim 1, characterized by having interface means for adjusting infrastructure facilities in an area potentially affected by a predicted earthquake and for automatically enabling a rapid response.

[0814] "Application example 2 when combining with an emotional engine"

[0815] (Claim 1)

[0816] A device that acquires earthquake-related information in real time,

[0817] A device that analyzes acquired information and uses a deep learning algorithm to estimate the occurrence of earthquakes,

[0818] A device that analyzes the emotional state of a user and identifies emotions based on voice, facial expressions, or input operations,

[0819] A device that generates warning information best suited to the user's current mental state based on acquired emotional information,

[0820] A system that includes this.

[0821] (Claim 2)

[0822] The system according to claim 1, characterized by comprising a device that proposes customized damage prediction and protection measures for a specific area or user based on the results of earthquake occurrence estimation and the emotional state of the user.

[0823] (Claim 3)

[0824] The system according to claim 1, characterized in that it has means for connecting to a base system that operates devices in an area potentially affected by an estimated earthquake and automatically executes protective measures. [Explanation of Symbols]

[0825] 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. Means of obtaining earthquake-related information in real time, A method for analyzing acquired information and predicting earthquake occurrences using a deep learning algorithm, Based on the prediction results, a means of notifying potentially affected users of the warning, A means to achieve integration with the urban environment and automatically manage infrastructure facilities, A means of providing evacuation orders and information on evacuation facilities based on earthquake predictions, A system that includes this.

2. The system according to claim 1, characterized in that it includes means for proposing customized damage predictions and preventive measures for a specific area or user based on the results of earthquake occurrence predictions.

3. The system according to claim 1, characterized in that it has means for connecting to an infrastructure system that operates structures within an area affected by a predicted earthquake and automatically performs preventive measures.

Images