System

Abstract

A system is provided.SOLUTION: A system comprising: a data collection unit; a preprocessing unit; a data analysis unit; an earthquake forecast generation unit; and a user notification unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Earthquake forecasting is a scientifically challenging field that has a significant social impact. Therefore, it is necessary to accurately predict earthquake occurrences and raise disaster prevention awareness while avoiding social unrest. Current technology lacks a system for integrating and analyzing multiple pieces of information, such as seismic intensity data, abnormal animal behavior, and environmental changes, resulting in low accuracy and reliability of earthquake forecasts. This invention solves these problems and provides a system that provides accurate earthquake forecasts even with low probability of occurrence. [Means for solving the problem]

[0005] The present invention provides an earthquake forecasting system including a data collection means, a preprocessing means, a data analysis means, an earthquake forecast generation means, and a user notification means. Specifically, the system includes a data collection means including a means for acquiring seismic intensity meter data, a means for collecting animal behavior data, and a means for collecting environmental change data, and a preprocessing means for cleansing and normalizing the collected data. The system also includes a data analysis means having a means for analyzing data using an AI model and a means for evaluating the analysis results, and an earthquake forecast generation means having a means for generating an earthquake forecast based on the analysis results and transmitting the forecast to a user terminal. Furthermore, the system includes a user notification means for displaying notifications and encouraging user action, thereby enhancing daily disaster prevention awareness.

[0006] A "data collection tool" is a tool for obtaining data from multiple sources.

[0007] "Preprocessing means" refers to means for preparing collected data into an analyzable format.

[0008] The "data analysis means" is a means for performing analysis based on collected and preprocessed data and outputting the results.

[0009] The "earthquake forecast generating means" is a means for generating an earthquake forecast based on the analysis results of the data analyzing means.

[0010] The "user notification means" is a means for effectively communicating the generated earthquake forecast to the user.

[0011] "Seismic intensity data" refers to data related to earthquake shaking recorded by a seismic intensity meter.

[0012] "Animal behavior data" is data relating to abnormal behavior of a specific animal.

[0013] "Environmental change data" refers to data on environmental changes before and after an earthquake, such as earthquake clouds and ground changes.

[0014] "Cleansing" is a process that removes noise and redundancies from collected data to make it suitable for analysis.

[0015] "Normalization" is the process of standardizing data of different scales and formats to make them comparable.

[0016] An "AI model" is a mathematical model that uses artificial intelligence to analyze data and make predictions.

[0017] "Analysis results" are result information derived by the data analysis means. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0026] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0039] The present invention is an earthquake forecasting system that collects data, analyzes data, generates forecasts, and notifies users, mainly consisting of a server, terminals, and users. Specific embodiments of each element are described below.

[0040] Server Roles and Functions

[0041] Data collection

[0042] The server collects data necessary for earthquake forecasting from multiple sources, specifically seismic intensity data, animal behavior data, and environmental change data. This collection is done periodically, and the latest data is always kept.

[0043] Collection of seismic intensity data: The server collects real-time shaking data from seismic intensity meters installed across the country. The data includes the date and time of occurrence, epicenter, and seismic intensity.

[0044] Animal behavior data collection: The server collects information on abnormal animal behavior from social media and specialized databases. Specifically, it analyzes reports of mass sardine deaths, strandings of dolphins, and abnormal behavior in catfish and pets.

[0045] Environmental change data collection: The server collects data on environmental changes from monitoring satellites and ground sensors, including seismic cloud observations and ground deformation data.

[0046] Data Preprocessing

[0047] The server preprocesses the collected data, specifically cleansing it by removing noise and duplicate data, and normalizing data in different formats.

[0048] Data analysis

[0049] The server then uses an AI model to analyze the preprocessed data. The AI ​​model correlates past earthquake data with current data and detects abnormal patterns from multiple perspectives. The analysis results are output as a score indicating the likelihood of an earthquake occurring.

[0050] Earthquake forecast generation

[0051] The server generates earthquake forecasts based on the analysis results, which are formatted as detailed information including the probability of occurrence and phenomena to watch out for.

[0052] User Notifications

[0053] The server then sends the generated earthquake forecast to the user's device via push notification, email, or other means to grab the user's attention.

[0054] Device roles and functions

[0055] Receive notifications

[0056] The device receives the earthquake forecast notification sent from the server, and the notification is displayed immediately, alerting the user with an alarm sound or vibration if necessary.

[0057] Information display

[0058] The device visually displays the received forecast information, including the probability of an earthquake occurring, phenomena to watch out for, and recommended disaster prevention actions.

[0059] User Roles

[0060] Notification confirmation

[0061] The user checks the earthquake forecast notification displayed on the device and takes steps to ensure the safety of themselves and their families based on the contents of the notification.

[0062] action

[0063] Users can then make necessary disaster prevention preparations based on the forecast, such as checking their water and food stockpiles and evacuation routes.

[0064] Specific examples

[0065] For example, consider the following phenomenon observed in a certain area:

[0066] The seismometer detects an unusually small earthquake.

[0067] Local residents reported the "mass death of sardines" on social media.

[0068] Unusual earthquake clouds observed in satellite data.

[0069] The server immediately collects this data and performs data cleansing and normalization. The cleaned data is input into an AI model, where it is compared with past patterns and analyzed. The server calculates the likelihood of an earthquake occurring as a score and generates a forecast for that area. The generated forecast is immediately pushed to the device, informing the user that "There is a 10% chance of an earthquake occurring. Please make sure you are prepared." The user checks the notification and makes the necessary disaster prevention preparations. This allows users to maintain a high level of disaster prevention awareness on a daily basis.

[0070] In this way, the present invention provides a system for making comprehensive earthquake forecasts by utilizing a variety of data.

[0071] The processing flow will be explained below.

[0072] Step 1:

[0073] The server collects seismic intensity data. It accesses the nationwide seismic intensity network and obtains the latest shaking data. This data includes the epicenter, seismic intensity, and time of occurrence. The server performs this process periodically to maintain real-time accuracy.

[0074] Step 2:

[0075] The server collects animal behavior data. It monitors social media and animal observation databases, scanning for posts reporting mass sardine deaths or abnormal pet behavior. It uses text mining technology to extract useful information and store it in a database.

[0076] Step 3:

[0077] The server collects data on environmental changes. It uses satellite data and ground sensors to collect observations of earthquake clouds and ground changes. The server integrates this data and detects abnormal patterns.

[0078] Step 4:

[0079] The server preprocesses the collected data. First, it cleanses the data to remove noise and duplicate data. Next, it normalizes the data and standardizes data of different scales. This preprocessing makes it easier to input into the AI ​​model.

[0080] Step 5:

[0081] The server analyzes the data using an AI model. The preprocessed data is input into the AI ​​model, which then analyzes the current data against past earthquake data. The AI ​​model detects abnormal patterns and outputs a score indicating the likelihood of an earthquake occurring.

[0082] Step 6:

[0083] The server evaluates the analysis results. Based on the score output by the AI ​​model, it evaluates the reliability of the earthquake occurrence. Based on this evaluation result, it prepares to generate an earthquake forecast.

[0084] Step 7:

[0085] The server generates an earthquake forecast. Based on the evaluated analysis, it creates a detailed forecast of the likelihood of an earthquake occurring, including the probability of occurrence, what to watch out for, and recommended actions.

[0086] Step 8:

[0087] The server prepares the user notification and formats the generated forecast for transmission to the user's device, using push notifications or email.

[0088] Step 9:

[0089] The device receives and displays notifications. It displays notifications sent from the server immediately and uses alarm sounds or vibrations to attract the user's attention.

[0090] Step 10:

[0091] The user checks the notification and takes action. They check the earthquake forecast displayed on their device and make the necessary disaster prevention preparations, such as checking evacuation routes and emergency supplies.

[0092] Step 11:

[0093] Users provide feedback on the accuracy of the forecast and on improvements to the system. This feedback is used to improve the system in the future.

[0094] Example 1

[0095] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0096] Conventional earthquake forecasting systems have had issues in effectively aggregating data from multiple sources and making earthquake predictions in real time. In particular, there are limitations in preprocessing to improve data accuracy and analytical precision, and in detecting abnormal patterns. Furthermore, users are often not notified promptly and appropriately, making it difficult for them to take prompt disaster prevention action. To solve these problems, a system is needed that highly automates the entire process, from data collection and analysis to forecast generation and notification, achieving both accuracy and speed.

[0097] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0098] In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, an earthquake forecast generation means, a user notification means, an abnormal pattern detection means, an occurrence probability calculation means, and a detailed information generation means. This makes it possible to collect data from multiple information sources, perform advanced preprocessing, and generate an earthquake forecast through highly accurate analysis. Furthermore, by realizing prompt and accurate notification to the user, the user can take prompt disaster prevention action.

[0099] "Data collection means" refers to the means for obtaining necessary data from multiple sources.

[0100] The "preprocessing means" is a means for removing noise and redundancy from the collected data and converting it into a unified format.

[0101] The "data analysis means" is a means for performing analysis using preprocessed data to detect abnormal patterns.

[0102] The "earthquake forecast generating means" is a means for generating an earthquake forecast based on the results of data analysis.

[0103] The "user notification means" is a means for quickly notifying the user of the generated earthquake forecast.

[0104] The "abnormal pattern detection means" is a means for determining whether or not there is an abnormality in the current data through comparison with past data.

[0105] The "occurrence probability calculation means" is a means for quantifying the probability of an earthquake occurring based on the results of data analysis.

[0106] The "detailed information generating means" is a means for generating detailed information necessary for earthquake forecasting (probability of occurrence, phenomena to be aware of, disaster prevention actions, etc.).

[0107] "Means for obtaining seismic intensity meter data" refers to means for obtaining shaking data from seismic intensity meters installed throughout the country.

[0108] "Means for collecting animal behavior data" refers to means for collecting data on abnormal animal behavior.

[0109] "Means for collecting environmental change data" refers to means for collecting data on environmental changes such as earthquake clouds and ground deformation.

[0110] "Means for crawling data from social media" refers to means for automatically collecting posted data from social media.

[0111] "Means for acquiring satellite data" refers to means for acquiring data observed through a satellite.

[0112] "Means for removing noise and duplication from data" refers to means for removing outliers and duplicate data contained in collected data.

[0113] MODE FOR CARRYING OUT THE INVENTION

[0114] The present invention is a system for forecasting earthquakes, with a server, terminals, and users as the main actors. This system includes a data collection means, a preprocessing means, a data analysis means, an earthquake forecast generation means, a user notification means, an abnormal pattern detection means, an occurrence probability calculation means, and a detailed information generation means. This makes it possible to process information collected from various data sources and generate highly accurate earthquake forecasts.

[0115] Server Roles and Functions

[0116] Data collection

[0117] The server collects data from multiple sources, specifically seismic intensity data, animal behavior data, and environmental change data, and periodically stores the latest data.

[0118] Collection of seismic intensity data: The server obtains real-time shaking data from seismic intensity meters installed throughout the country via an API, for example, using the API of a public institution.

[0119] Collection of animal behavior data: The server uses crawling technology to collect information on abnormal animal behavior posted by local residents on social media. It also obtains data on dolphin strandings and abnormal catfish behavior from specialized databases.

[0120] Collection of environmental change data: The server uses the satellite data provider's API to obtain earthquake cloud observation data and environmental change data (such as ground deformation) from ground sensors.

[0121] Data Preprocessing

[0122] The server performs pre-processing on the collected data.

[0123] Noise removal: Detect outliers and missing values ​​and remove or impute them, e.g., by filling in missing values ​​with imputed means.

[0124] Data cleansing: Removing duplicate data and converting it into a consistent format, e.g. standardizing all time data to UTC.

[0125] Data normalization: Converting data from different sources into a uniform format, e.g., converting latitude and longitude data into a common coordinate system.

[0126] Data analysis

[0127] The server inputs the preprocessed data into the AI ​​model for analysis.

[0128] Generative AI model: Using historical and current earthquake data, we use a deep learning model trained on historical earthquake data to detect anomalous patterns.

[0129] Detecting abnormal patterns: Comparing new data with past patterns to determine whether there are any anomalies. For example, detecting a sudden change in seismic intensity data that matches animal behavior data.

[0130] Score calculation: As a result of the analysis, a score is calculated that indicates the possibility of an earthquake occurring. The score is expressed in a range from 0 to 100.

[0131] Earthquake forecast generation

[0132] The server generates an earthquake forecast based on the analysis results.

[0133] Forecast format: Generate a forecast based on the score, for example, "There is a 10% chance of an earthquake. Please make sure you are prepared."

[0134] Added detailed information: Not only the probability of occurrence, but also phenomena to watch out for (such as observation of earthquake clouds or abnormal animal behavior) and recommended disaster prevention actions.

[0135] User Notifications

[0136] The server notifies the generated earthquake forecast to the user's terminal.

[0137] Notification method: Users are notified by multiple methods, such as push notifications and email notifications. For example, push notifications are sent via smartphone apps.

[0138] Instant Notification: Earthquake forecasts are sent instantly, accompanied by an alarm sound and vibration to grab the user's attention.

[0139] Device roles and functions

[0140] Receive notifications

[0141] The device receives the earthquake forecast notification sent from the server, and the notification is displayed immediately, alerting the user with an alarm sound or vibration if necessary.

[0142] Information display

[0143] The device visually displays the received forecast information, including the probability of an earthquake occurring, phenomena to watch out for, and recommended disaster prevention actions.

[0144] User Roles

[0145] Notification confirmation

[0146] The user checks the earthquake forecast notification displayed on the device and takes steps to ensure the safety of themselves and their families based on the contents of the notification.

[0147] action

[0148] Users can then make necessary disaster prevention preparations based on the forecast, such as checking their water and food stockpiles and evacuation routes.

[0149] Specific examples

[0150] For example, consider the following phenomenon observed in a certain area:

[0151] The seismometer detects an unusually small earthquake.

[0152] Local residents reported the "mass death of sardines" on social media.

[0153] Unusual earthquake clouds observed in satellite data.

[0154] The server immediately collects this data and performs data cleansing and normalization. The cleaned data is input into an AI model, where it is compared with past patterns and analyzed. The server calculates the likelihood of an earthquake occurring as a score and generates a forecast for that area. The generated forecast is immediately pushed to the device, informing the user that "There is a 10% chance of an earthquake occurring. Please make sure you are prepared." The user checks the notification and makes the necessary disaster prevention preparations. This allows users to maintain a high level of disaster prevention awareness on a daily basis.

[0155] Prompt Sentence Examples

[0156] "We have developed a new earthquake forecasting system. This system collects data from seismometers, animal behavior data, and environmental change data, and analyzes it using an AI model. It calculates the probability of an earthquake occurring as a score and notifies the user. Please tell us the processing steps of this system."

[0157] By implementing this aspect, the present invention provides a system that utilizes a variety of data to perform comprehensive and highly accurate earthquake forecasting.

[0158] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0159] Step 1: Data collection

[0160] The server collects the necessary data from multiple sources. The inputs to this step are seismometer data, animal behavior data, and environmental change data. The output is a collection of these data. Specifically, the server performs the following:

[0161] Collection of seismometer data: The server obtains shaking data (occurrence date and time, epicenter, seismic intensity) from the seismometer. For example, it obtains real-time data by calling an API.

[0162] Collection of animal behavior data: The server uses scraping technology to obtain data on abnormal animal behavior from social media and specialized databases.

[0163] Collection of environmental change data: The server acquires environmental change data (earthquake cloud observation results, ground change data) from satellite data providers and ground sensors.

[0164] Step 2: Data Preprocessing

[0165] The server performs pre-processing on the collected data. The input to this step is the output data from step 1. The output is the cleansed and normalized data. Specifically, the server:

[0166] Noise removal: Detect outliers and missing values ​​in the data and remove or impute them, for example by filling in missing values ​​with imputed means.

[0167] Data cleansing: Removing duplicate data and converting it into a consistent format, for example, standardizing all date and time data to UTC.

[0168] Data normalization: Standardizing data from different sources into the same format, for example, converting latitude and longitude data into a common coordinate system.

[0169] Step 3: Data analysis

[0170] The server performs analysis using the AI ​​model based on the preprocessed data. The input for this step is the output data from step 2. The output is the anomaly pattern detection results and an earthquake occurrence probability score. Specifically, the server performs the following:

[0171] Use generative AI models: Use historical and current earthquake data to detect anomalous patterns. Use deep learning models trained on historical earthquake data.

[0172] Detecting abnormal patterns: Comparing new data with past patterns to determine whether there are any anomalies. For example, detecting a sudden change in seismic intensity data that matches animal behavior data.

[0173] Score calculation: As a result of the analysis, a score is calculated that indicates the possibility of an earthquake occurring. The score is expressed in a range from 0 to 100.

[0174] Step 4: Earthquake forecast generation

[0175] The server generates an earthquake forecast based on the analysis results. The input to this step is the output score from step 3. The output is earthquake forecast information. Specifically, the server performs the following operations:

[0176] Forecast format: Generate forecast content based on the score, for example, "There is a 10% chance of an earthquake. Please be prepared."

[0177] Add detailed information: Include not only the probability of occurrence, but also phenomena to watch out for (such as observation of earthquake clouds or abnormal animal behavior) and recommended disaster prevention actions.

[0178] Step 5: User Notification

[0179] The server notifies the generated earthquake forecast to the user's terminal. The input of this step is the forecast information output in step 4. The output is the notification information displayed on the terminal. Specifically, the server performs the following operations:

[0180] Selection of notification method: Notify users through multiple methods, such as push notifications and email notifications. For example, send push notifications through a smartphone app.

[0181] Instant Notification: Earthquake forecasts are sent instantly, accompanied by an alarm sound and vibration to grab the user's attention.

[0182] Step 6: Check notifications and take action

[0183] The user checks the earthquake forecast notification displayed on the terminal. The input of this step is the notification information output in step 5. The output is the specific disaster prevention action the user will take. Specifically, the user will:

[0184] Confirm notification: The user confirms the notification content and understands the possibility of an earthquake occurring and the recommended actions.

[0185] Disaster Preparedness: Make necessary disaster preparedness preparations based on the notification, such as checking your water and food stockpiles and checking whether your furniture is securely fastened.

[0186] (Application example 1)

[0187] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0188] Current earthquake forecasting systems lack the means to detect signs of an impending earthquake and quickly notify users. As a result, users are sometimes slow to respond to an earthquake, making it difficult to minimize damage. There is also a need for technology that can integrate information from different data sources to generate highly accurate forecasts. Furthermore, there is no mechanism for specifically recommending disaster prevention actions, making it difficult to raise users' disaster prevention awareness.

[0189] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0190] In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, and a push notification means. This allows the server to integrate information collected from multiple data sources, generate earthquake forecasts in real time, and promptly notify users via push notifications. Furthermore, by recommending specific disaster prevention actions, the server can raise users' disaster prevention awareness and promote early response to earthquakes.

[0191] "Data collection means" refers to the means of collecting data from multiple sources necessary for earthquake forecasting, such as seismic intensity data, animal behavior data, and environmental change data.

[0192] The "preprocessing means" is a means for removing noise and redundant data from collected data and unifying data in different formats.

[0193] The "data analysis means" is a means of analyzing preprocessed data using an AI model to calculate a score indicating the possibility of an earthquake occurring.

[0194] The "earthquake forecast generating means" is a means for generating an earthquake forecast based on the analysis results by the data analysis means.

[0195] The "user notification means" is a means for transmitting the generated earthquake forecast to the user's terminal and notifying the user.

[0196] The "push notification means" is a means for immediately notifying the user's terminal of an earthquake forecast generated based on the analyzed information in real time.

[0197] The "means for acquiring seismic intensity meter data" refers to a means for acquiring real-time shaking data from a seismic intensity meter.

[0198] "Means for collecting animal behavior data" refers to means for collecting data on abnormal animal behavior.

[0199] "Means for collecting environmental change data" refers to means for collecting data on environmental changes from monitoring satellites and ground sensors.

[0200] "Means for cleansing collected data" refers to means for removing noise and redundant data from collected data to generate more accurate data.

[0201] "Means for normalizing data" refers to means for standardizing data collected in different formats and making it suitable for analysis.

[0202] "Means for calculating the possibility of an earthquake occurring based on the analysis results" refers to means for quantitatively assessing the possibility of an earthquake occurring based on the analyzed data.

[0203] The "means for generating and sending a push notification" is a means for generating a forecast notification based on the analysis results and sending it to the user's device.

[0204] The "means for recommending disaster prevention actions based on the forecast content" is a means for recommending appropriate disaster prevention actions to a user based on the generated earthquake forecast.

[0205] The present invention is an earthquake forecasting system that collects data, analyzes data, generates forecasts, and notifies users, mainly consisting of a server, terminals, and users. Specific embodiments of each element are described below.

[0206] Server Roles and Functions

[0207] Data collection

[0208] The server collects data from sources necessary for earthquake forecasting, such as seismometer data, animal behavior data, and environmental change data. Data collection scripts are created using programming languages ​​such as Python to periodically retrieve information.

[0209] Data Preprocessing

[0210] We will remove noise and duplicate data from the collected data and unify data in different formats using pandas, a Python data processing library.

[0211] Data analysis

[0212] The preprocessed data is analyzed using an AI model. The AI ​​model uses TensorFlow and PyTorch to correlate past earthquake data with current data and detect abnormal patterns from multiple perspectives. The analysis results are calculated as a score indicating the possibility of an earthquake occurring.

[0213] Earthquake forecast generation

[0214] The server generates an earthquake forecast based on the analysis results. The forecast is formatted as detailed information including the probability of occurrence and phenomena to watch out for. The forecast also includes a message encouraging users to take disaster prevention action.

[0215] User Notifications

[0216] The server sends the generated earthquake forecast to the user's device. The user is notified in the form of a push notification using Firebase Cloud Messaging (FCM). The notification includes the probability of occurrence and recommended actions.

[0217] Device roles and functions

[0218] Receive notifications

[0219] The device receives the earthquake forecast notification sent from the server immediately and notifies the user. The notification is displayed visually and can use an alarm sound or vibration.

[0220] Information display

[0221] The user's device visually displays the received forecast, including the probability of an earthquake occurring and specific disaster prevention recommendations.

[0222] User Roles

[0223] Notification confirmation

[0224] The user checks the earthquake forecast notification displayed on the device and takes steps to ensure the safety of themselves and their families based on the contents of the notification.

[0225] action

[0226] Based on the forecast, users can make necessary disaster prevention preparations, such as checking their water and food stockpiles and evacuation routes.

[0227] Specific examples

[0228] For example, if the following phenomena are observed simultaneously in the Kanto region:

[0229] The seismometer detects an unusually small earthquake.

[0230] Local residents report the "mass inaction of frogs" on social media.

[0231] Observing abnormal cloud movements using satellite data.

[0232] This information is immediately collected on a server, where it is cleansed and normalized. This clean data is then input into an AI model to generate analysis results. For example, if the analysis score is 0.15, a notification will be sent to the user's smartphone saying, "There is a 15% chance of an earthquake occurring. Please make sure you are prepared."

[0233] Example prompts for generative AI models

[0234] "Seismic intensity meters in the Kanto region have detected an unusually small earthquake, and reports of mass frog inactivity have been posted on social media. Furthermore, unusual cloud movement has been observed using satellite data. Please use this information to analyze the likelihood of an earthquake occurring and predict whether it will occur."

[0235] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0236] Step 1:

[0237] Data collection

[0238] The server collects seismic intensity data, animal behavior data, and environmental change data. The inputs used are real-time shaking data from the seismic intensity data, animal behavior reports from social media and specialized databases, and environmental change data from monitoring satellites and ground sensors. It periodically collects this data and runs a program that centrally aggregates it.

[0239] Step 2:

[0240] Data Preprocessing

[0241] The server preprocesses the collected data. The input data includes seismometer data, animal behavior data, and environmental change data. It cleanses noise and duplicate data from these data sets and unifies data in different formats using the pandas library. This results in a clean, unified dataset being output.

[0242] Step 3:

[0243] Data analysis

[0244] The server analyzes the preprocessed data. The input data includes cleansed and normalized seismic intensity data, animal behavior data, and environmental change data. This data is input into an AI model (using TensorFlow and PyTorch) to calculate a score indicating the likelihood of an earthquake occurring. The output is an analysis result indicating the likelihood of an earthquake occurring.

[0245] Step 4:

[0246] Earthquake forecast generation

[0247] The server generates an earthquake forecast based on the results of the data analysis. The input is the probability score of an earthquake occurring obtained through the analysis. Based on this score, the server formats the earthquake forecast text and disaster prevention action recommendations. This results in a detailed earthquake forecast and disaster prevention action recommendations being output.

[0248] Step 5:

[0249] User Notifications

[0250] The server sends the generated earthquake forecast to the user device. The input data includes the earthquake forecast and disaster prevention recommendations. This data is immediately sent to the user device as a push notification using Firebase Cloud Messaging (FCM). The output is the notification message received on the user device.

[0251] Step 6:

[0252] Notification reception (device side)

[0253] The user's device receives the notification sent from the server. The input is the received push notification message. The device notifies the user of the notification content visually and audibly. The output is an earthquake forecast notification displayed to the user.

[0254] Step 7:

[0255] Information display (terminal side)

[0256] Displays the earthquake forecast notification received by the device. The input data is the content of the received push notification. This is displayed visually so that the user can confirm the content. The output is a specific earthquake forecast and recommended disaster prevention actions displayed on the device screen.

[0257] Step 8:

[0258] Notification confirmation (user side)

[0259] The user checks the notification displayed on the device. The input is the earthquake forecast notification displayed on the device. Based on this notification, the user considers the actions necessary to ensure the safety of themselves and their families. The output is the user's disaster prevention actions.

[0260] Step 9:

[0261] Disaster prevention actions (user side)

[0262] The user makes specific disaster prevention preparations based on the notified forecast. The input data includes the notified earthquake forecast and recommended disaster prevention actions. This allows the user to check their water and food stockpiles, check evacuation routes, etc. The output is the specific disaster prevention actions the user should take.

[0263] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0264] This invention incorporates an emotion engine into an earthquake forecasting system to recognize the user's emotional state and customize notification content and disaster prevention action recommendations. This system operates with the server, terminals, and users as its main drivers, and not only improves the accuracy of earthquake forecasts but also provides responses that correspond to the user's psychological state.

[0265] Server Roles and Functions

[0266] Data collection

[0267] The server acquires information necessary for earthquake forecasting, including seismometer data, animal behavior data, and environmental change data. This data is collected periodically by the server and kept up to date.

[0268] Collection of seismic intensity data: The server collects detailed data such as epicenter, seismic intensity, and time of occurrence from seismic intensity meters across the country.

[0269] Collection of animal behavior data: The server collects information from social media and specialized databases about mass sardine deaths and abnormal pet behavior.

[0270] Collection of environmental change data: The server collects observations of earthquake clouds and ground changes using satellite data and ground sensors.

[0271] Data Preprocessing

[0272] The server cleanses and normalizes the collected data, which includes removing noise and duplicate data and unifying data in different formats.

[0273] Data analysis

[0274] The server inputs the preprocessed data into an AI model, which compares it with past earthquake data and analyzes it. The AI ​​model detects abnormal patterns and outputs a score indicating the likelihood of an earthquake occurring.

[0275] Earthquake forecast generation

[0276] The server evaluates the analysis results and generates a forecast of the likelihood of an earthquake, including the probability of occurrence, what to watch out for, and recommended actions.

[0277] Evaluation by Emotion Engine

[0278] The server uses an emotion engine to analyze the user's emotional data, for example, assessing the user's stress level or anxiety level based on their past actions and comments.

[0279] User notification preparation

[0280] The server adjusts the notification content based on the emotion engine's evaluation. For example, if the user is feeling high stress, the notification content will be changed to a more gentle expression and a supportive message will be added to reduce anxiety.

[0281] Device roles and functions

[0282] Receive notifications

[0283] The device receives notifications sent from the server, and the notifications are displayed immediately and, if necessary, notify the user with an alarm sound or vibration.

[0284] Information display

[0285] The device visually displays the received forecast, including the probability of an earthquake occurring, factors to be aware of, and recommended disaster prevention actions.

[0286] Collecting Emotional Data

[0287] The device collects information about the user's daily behavior and input emotions and sends it to the server, where it is used for analysis by the emotion engine.

[0288] User Roles

[0289] Notification confirmation

[0290] The user checks the notification on the device, understands the earthquake forecast, and makes disaster prevention preparations based on the notification content.

[0291] action

[0292] Users can take necessary disaster prevention actions based on the notification, such as checking their water and food stockpiles and checking evacuation routes.

[0293] feedback

[0294] Users can provide feedback on the accuracy of forecasts and notifications via their devices, which is then sent to the server and used to improve the system.

[0295] Specific examples

[0296] Suppose a seismometer detects an abnormal small earthquake in a certain area, and a mass death of sardines is reported on social media. Furthermore, if an abnormal earthquake cloud is observed in satellite data, this data is collected on a server. The server cleans and normalizes this data, and inputs it into an AI model for analysis. Based on the analysis results, it is determined that there is a high probability of an earthquake occurring.

[0297] As a result, the server generates an earthquake forecast and simultaneously evaluates the user's emotional state using an emotion engine. For example, if the user is feeling very stressed, the server softens the notification and adds a support message to promote disaster preparedness. This forecast notification is then sent to the user's device, which displays the notification to attract the user's attention.

[0298] The user checks the notification and makes the necessary disaster prevention preparations. At that time, the user provides feedback to the server via their device, contributing to improvements in the system. In this way, the present invention improves the accuracy and reliability of earthquake forecasts and provides disaster prevention support that takes user emotions into consideration.

[0299] The processing flow will be explained below.

[0300] Step 1:

[0301] The server collects seismic intensity data, accessing the nationwide seismic intensity network in real time to obtain the latest shaking data, including the epicenter, seismic intensity, and time of occurrence.

[0302] Step 2:

[0303] The server collects animal behavior data, scanning social media and specialized databases for posts about mass sardine deaths and abnormal pet behavior, and using text mining techniques to extract useful information and store it in a database.

[0304] Step 3:

[0305] The server collects data on environmental changes, such as earthquake cloud observations and ground deformation information using satellite images and ground sensors. This data is integrated to detect abnormal patterns.

[0306] Step 4:

[0307] The server preprocesses the collected data. First, it cleanses the data to remove noise and duplicate data. Next, it normalizes the data and standardizes data in different formats. This preprocessing makes it easier to input into the AI ​​model.

[0308] Step 5:

[0309] The server inputs the preprocessed data into an AI model for data analysis, which compares past earthquake data with current data to detect abnormal patterns and output a score indicating the likelihood of an earthquake occurring.

[0310] Step 6:

[0311] The server evaluates the analysis results. Based on the score output by the AI ​​model, it evaluates the reliability of the earthquake occurrence. Based on the analysis results, it prepares earthquake forecasts.

[0312] Step 7:

[0313] The server generates an earthquake forecast based on the analysis results, which includes the probability of an earthquake occurring, phenomena to watch out for, and recommended disaster prevention actions.

[0314] Step 8:

[0315] The server uses an emotion engine to analyze the user's emotional data, and evaluates their stress and anxiety levels based on their past behavioral history and input emotional data.

[0316] Step 9:

[0317] The server customizes the notification content based on the analysis results of the emotion engine. If the user is feeling high stress, the forecast notification will be softened and a reassuring message will be added.

[0318] Step 10:

[0319] The server then sends the coordinated forecast notification to the user's device, which includes the possibility of an earthquake occurring, what phenomena to watch out for, and recommended disaster prevention actions.

[0320] Step 11:

[0321] The device receives the notification and displays it immediately, using an alarm sound or vibration to get the user's attention.

[0322] Step 12:

[0323] The user checks the earthquake forecast notification displayed on the device, understands the forecast content, and makes the necessary disaster prevention preparations based on the notification.

[0324] Step 13:

[0325] The user takes disaster prevention actions, such as making specific preparations such as checking water and food stockpiles and evacuation routes.

[0326] Step 14:

[0327] Users can provide feedback on the content of notifications and the accuracy of forecasts. By sending feedback to the server via their device, they can contribute to improving the system. This feedback will be used to improve the accuracy of future forecasts.

[0328] Example 2

[0329] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0330] Conventional earthquake forecasting systems have a certain degree of accuracy in predicting earthquake occurrences, but they lack the ability to provide notification content that takes into account the user's psychological state. As a result, when users are in situations where they feel high levels of stress or anxiety, it can be difficult to take appropriate disaster prevention actions. A system that solves this problem and allows users to calmly take disaster prevention actions is needed.

[0331] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0332] In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, an earthquake forecast generation means, a user notification means, an emotional state analysis means, and a means for adjusting the notification content based on the emotional state of the user, thereby making it possible to provide notification content that takes the psychological state of the user into consideration.

[0333] "Data collection means" refers to a device or process that collects various data necessary for earthquake forecasting.

[0334] A "pre-processing means" is a device or process that cleanses and normalizes collected data and converts it into a suitable format for analysis.

[0335] "Data analysis means" refers to a device or process that analyzes the possibility of earthquake occurrence based on pre-processed data.

[0336] "Earthquake forecast generating means" refers to a device or process that generates an earthquake forecast based on the results of data analysis.

[0337] The "user notification means" is a device or process that notifies the user of the generated earthquake forecast.

[0338] "Emotional state analysis means" refers to a device or process that analyzes the user's emotional data and assesses the level of stress or anxiety.

[0339] The "means for adjusting notification content based on the emotional state of the user" refers to a device or process that appropriately adjusts notification content for the user based on the results of the emotional state analysis.

[0340] This invention is a system that incorporates an emotion engine into an earthquake forecasting system to recognize the user's emotional state and customize notification content and disaster prevention action recommendations. This system operates with the server, terminals, and users as its main actors, and not only improves the accuracy of earthquake forecasts but also provides responses that correspond to the user's psychological state.

[0341] Server Roles and Functions

[0342] 1. Data collection methods:

[0343] The server collects data on seismic intensity meters, animal behavior, and environmental changes. Specifically, it obtains detailed data such as the epicenter, intensity, and time of occurrence from seismic intensity meters across the country, and collects information on mass sardine deaths and abnormal pet behavior from social media and specialized databases. It also obtains observation results of earthquake clouds and ground changes using satellite data and ground sensors.

[0344] 2. Pretreatment methods:

[0345] The server cleanses and normalizes the collected data, removing noise and duplicate data and unifying data in different formats.

[0346] 3. Data analysis methods:

[0347] The server inputs the preprocessed data into an AI model to analyze the likelihood of an earthquake occurring, using TensorFlow as the AI ​​model and comparing it with past earthquake data to detect abnormal patterns.

[0348] 4. Earthquake forecast generation method:

[0349] The server generates an earthquake forecast based on the analysis results, which includes the probability of occurrence, phenomena to watch out for, and recommended actions.

[0350] 5. Emotional state analysis method:

[0351] The server uses an emotion engine to analyze the user's emotional data, specifically assessing their stress level and anxiety based on their past behavior and social media posts.

[0352] 6. How to tailor notifications based on the user's emotional state:

[0353] The server adjusts the notification content based on the results of the emotional state analysis. For example, if the user is feeling high stress, the server changes the notification content to a calmer one and adds a supportive message to reduce anxiety.

[0354] Device roles and functions

[0355] 1. Receive notifications:

[0356] The device receives notifications sent from the server, and the notifications are displayed immediately and, if necessary, notify the user with an alarm sound or vibration.

[0357] 2. Information display:

[0358] The device visually displays the received forecast, including the probability of an earthquake occurring, precautions to take, and recommended disaster prevention actions.

[0359] 3. Collecting Emotional Data:

[0360] The device collects data on the user's daily behavior and emotions and sends it to a server. Specifically, it measures the user's stress level and analyzes the contents of their diary entries and social media posts.

[0361] User Roles

[0362] 1. Notification confirmation:

[0363] The user checks the notification on the device, understands the earthquake forecast, and makes the necessary disaster prevention preparations based on the forecast.

[0364] 2. Action:

[0365] Users can take necessary disaster prevention actions based on the notification, such as checking their water and food stockpiles and evacuation routes.

[0366] 3. Feedback:

[0367] Users can provide feedback on the accuracy of forecasts and notifications via their devices, which is then sent to the server and used to improve the system.

[0368] Specific examples

[0369] If a seismometer detects an abnormally small earthquake in a certain area and a mass death of sardines is reported on social media, the server collects this data. The server cleans and normalizes the data, then inputs it into an AI model for analysis. Based on the analysis results, it determines the likelihood of an earthquake occurring.

[0370] As a result, the server generates an earthquake forecast and simultaneously evaluates the user's emotional state using an emotion engine. For example, if the user is feeling very stressed, the notification's wording will be softened and a support message will be added to promote disaster prevention preparations. This forecast notification is sent to the user's device, which displays the notification to attract the user's attention. The user then checks the notification and takes the necessary disaster prevention preparations. At that time, the user provides feedback to the server via their device, contributing to system improvements.

[0371] Specific examples of prompts to input to generative AI models

[0372] "Explain how an earthquake forecasting system can change the wording of notifications depending on the user's emotional state."

[0373] "Please explain how the earthquake forecasting system works, using seismic intensity data, animal behavior data, and environmental change data."

[0374] "Please provide a concrete example of how an earthquake forecasting system incorporating an emotion engine can provide notifications to users."

[0375] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0376] Step 1:

[0377] The server periodically collects seismic intensity data, animal behavior data, and environmental change data. Input data includes detailed data such as epicenter, intensity, and time of occurrence obtained from seismic intensity meters across the country, information on mass sardine deaths and abnormal pet behavior collected from social media and specialized databases, and earthquake cloud observation results and ground change data obtained from satellite data and ground sensors. This data is stored in the server's database.

[0378] Step 2:

[0379] The server cleanses and normalizes the collected data. The input is the raw data collected in step 1. Specifically, it removes noise, reduces duplicate data, and unifies data in different formats. As a result, it outputs clean data suitable for analysis.

[0380] Step 3:

[0381] The server inputs the preprocessed data into the AI ​​model for analysis. The input is the data preprocessed in step 2. The AI ​​model (using TensorFlow, for example) compares the input data with past earthquake data to detect abnormal patterns. As a result of the analysis, it outputs a score indicating the likelihood of an earthquake occurring.

[0382] Step 4:

[0383] The server generates an earthquake forecast based on the analysis results. The input is the earthquake occurrence probability score obtained in step 3. The earthquake forecast includes the occurrence probability, phenomena to watch out for, and recommended actions. This forecast is sent to the user notification means.

[0384] Step 5:

[0385] The server uses an emotion engine to analyze the user's emotional data. The input is the user's past behavioral data and social media posts. Based on this data, the server evaluates the user's stress level and anxiety level. The results of the emotion analysis are output.

[0386] Step 6:

[0387] The server adjusts the notification content based on the results of the emotional state analysis. The inputs are the earthquake forecast from step 4 and the emotion analysis results from step 5. For high-stress users, the notification content is changed to gentler language such as "Please stay calm" and a support message to reduce anxiety is added. The adjusted notification content is output and sent to the user notification means.

[0388] Step 7:

[0389] The device receives the notification sent from the server. The input is the notification content adjusted in step 6. The notification is displayed immediately and notifies the user with an alarm sound or vibration if necessary. The notification content is displayed on the device.

[0390] Step 8:

[0391] The terminal visually displays the received notification content. The input is the notification content received in step 7. The visual display includes the probability of an earthquake occurring, points to be aware of, and recommended disaster prevention actions. Information is provided visually to the user.

[0392] Step 9:

[0393] The user checks the notification on the device and understands the earthquake forecast. The input is the notification content displayed in step 8. Based on the notification content, the user makes the necessary disaster prevention preparations. The user checks their water and food stockpiles, checks evacuation routes, etc.

[0394] Step 10:

[0395] Users provide feedback on forecast accuracy and notification content through their devices. The input is the user's feedback. The feedback is sent from the device to the server. The feedback reaches the server and is used to improve the system.

[0396] (Application example 2)

[0397] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0398] Earthquake forecasting systems are required not only to improve the accuracy of earthquake predictions, but also to customize notification content and disaster prevention action recommendations according to the user's emotional state. However, conventional systems do not take the user's emotional state into consideration when providing notifications, and are therefore unable to reduce anxiety and stress. Therefore, efforts are needed to reduce users' psychological stress and anxiety in addition to improving the accuracy of earthquake forecasts.

[0399] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes data collection means, preprocessing means, data analysis means, earthquake forecast generation means, emotion engine means, notification content customization means, and user notification means. This improves the accuracy of earthquake forecasts and enables customized notifications to be provided according to the user's emotional state, thereby reducing the user's stress and anxiety.

[0400] The "data collection means" is a device or program that has the function of acquiring various data necessary for earthquake forecasting (seismic intensity data, animal behavior data, environmental change data, user emotion data, etc.).

[0401] The "preprocessing means" is a device or program that has the function of cleansing and normalizing the collected data and processing it into a format suitable for analysis.

[0402] "Data analysis means" refers to a device or program that has the function of analyzing the probability of earthquake occurrence, etc., using an AI model based on preprocessed data.

[0403] The "earthquake forecast generating means" is a device or program that has the function of generating a forecast that takes into account the possibility of an earthquake occurring based on the analyzed data.

[0404] The "emotion engine means" is a device or program that has the function of analyzing the user's emotion data and evaluating the user's current psychological state.

[0405] The "notification content customization means" is a device or program having a function of appropriately adjusting the notification content in accordance with the emotional state of the user based on the evaluation result of the emotion engine means.

[0406] The "user notification means" is a device or program having a function for transmitting the generated notification content to the user.

[0407] The present invention provides a system for providing disaster prevention notifications that take into account the emotional state of a user in an earthquake forecasting system. The system includes a data collection means, a preprocessing means, a data analysis means, an earthquake forecast generation means, an emotion engine means, a notification content customization means, and a user notification means.

[0408] Server Roles and Functions

[0409] Data collection

[0410] The server collects data necessary for earthquake forecasting. This data includes seismic intensity data, animal behavior data, environmental change data, and user emotion data. For example, seismic intensity data is obtained from seismic intensity data collected from seismic intensity data collected nationwide, and animal behavior data is collected from specialized databases and social media. Environmental change data is obtained from satellite data and ground sensors, and emotion data is collected from user comments and actions.

[0411] Data Preprocessing

[0412] The server cleanses and normalizes the collected data, which includes removing noise and duplicate data and standardizing data in different formats. For example, seismic intensity data and emotion data are properly scaled using standardization techniques.

[0413] Data analysis

[0414] The server then inputs the preprocessed data into an AI model, which compares it with past earthquake data and analyzes it. The AI ​​model detects abnormal patterns and outputs a score indicating the likelihood of an earthquake occurring. For example, an earthquake prediction model or sentiment analysis model trained with Keras is used for this analysis.

[0415] Earthquake forecast generation

[0416] The server evaluates the analysis results and generates a forecast of the possibility of an earthquake occurring, including the probability of occurrence, phenomena to watch out for, and recommended actions, to help users make appropriate disaster prevention preparations.

[0417] Evaluation by Emotion Engine

[0418] The server uses an emotion engine to analyze the user's emotional data. For example, it evaluates the user's stress level and anxiety level based on their past actions and comments. This allows the server to tailor the content of notifications to suit the user's psychological state.

[0419] Customizing notification content

[0420] The server adjusts the notification content based on the emotion engine's evaluation results: if the user is experiencing high stress, the notification's wording will be softer and a supportive message will be added to reduce anxiety.

[0421] User Notifications

[0422] The server sends a customized notification to the user's device, which displays the notification. The user can then check the notification content and take necessary disaster prevention preparations.

[0423] Specific examples

[0424] For example, if a seismometer detects an unusual small earthquake in a certain area, reports of abnormal animal behavior on social media and earthquake cloud observations from satellite data are collected on a server. At the same time, the user's emotional data is also collected and analyzed. The server inputs this data into an AI model and analyzes the high probability of an earthquake occurring. Based on the results, the emotion engine then evaluates the user's current psychological state and creates a notification. For example, it generates a notification that reassures the user, saying, "Don't worry. The predicted probability of an earthquake is 30%. You are safe for now." This notification is then sent to the user's smartphone, where the user can check it and provide feedback if necessary.

[0425] Prompt Sentence Examples

[0426] This program takes the emotion data of user "12345" and combines it with earthquake forecast data to generate a notification. If the emotion score is high, the notification content will be changed to be gentle.

[0427] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0428] Step 1:

[0429] The server acquires the data necessary for earthquake forecasting. Specifically, it collects seismometer data, animal behavior data, environmental change data, and user emotion data from each data source. This includes acquiring data from APIs and scraping social media data. The input is the initial data from each data source, and the output is the raw data stored in the server.

[0430] Step 2:

[0431] The server cleanses and normalizes the collected data, specifically removing noise and duplicate data, completing incomplete data, standardizing formats, etc. The input is the raw data obtained in step 1, and the output is the cleansed, normalized, and organized data.

[0432] Step 3:

[0433] The server inputs the preprocessed data into the AI ​​model for analysis. Specifically, it compares it with past earthquake data and calculates the probability of an earthquake occurring as a score. The input is the organized data obtained in Step 2, and the output is a probability score for the occurrence of an earthquake.

[0434] Step 4:

[0435] The server generates a forecast of the possibility of an earthquake occurring. Specifically, it evaluates the analysis results of the AI ​​model and creates a forecast that includes the probability of occurrence, phenomena to watch out for, and recommended actions. The input is the earthquake prediction score, and the output is the forecast data that is notified to the user.

[0436] Step 5:

[0437] The server analyzes the user's emotion data using an emotion engine. Specifically, it uses an emotion analysis model to evaluate the stress level and anxiety level from the user's history and daily behavior. The input is the emotion data collected in step 1, and the output is the user's emotion score.

[0438] Step 6:

[0439] The server adjusts the notification content based on the emotion engine's evaluation results. Specifically, if the user's emotion score is high, the notification content is changed to a more gentle expression and a support message is added to promote disaster prevention preparation. The input is forecast data and emotion score, and the output is a customized notification message.

[0440] Step 7:

[0441] The server sends the customized notification to the user's device. Specifically, it pushes the generated notification message to the user's smartphone or other appropriate device. The input is the customized notification message, and the output is the notification message displayed on the user's device.

[0442] Step 8:

[0443] The user checks the notification displayed on the device and prepares for disaster. Specifically, the user takes necessary disaster prevention actions, such as checking water and food stockpiles and evacuation routes. The input is the notification content displayed on the device, and the output is the user's disaster prevention actions.

[0444] Step 9:

[0445] The user provides feedback to the server through the terminal. Specifically, the user sends their opinion on the notification content and forecast accuracy. The input is the user's feedback, and the output is the feedback data received by the server.

[0446] Step 10:

[0447] The server improves the system based on the received feedback. Specifically, it analyzes the feedback data, trains new predictive models, and improves notification content. The input is the feedback data, and the output is an improved system.

[0448] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0449] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0450] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0451] [Second embodiment]

[0452] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0453] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0454] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0455] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0456] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0457] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0458] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0459] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0460] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0461] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0462] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0463] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0464] The present invention is an earthquake forecasting system that collects data, analyzes data, generates forecasts, and notifies users, mainly consisting of a server, terminals, and users. Specific embodiments of each element are described below.

[0465] Server Roles and Functions

[0466] Data collection

[0467] The server collects data necessary for earthquake forecasting from multiple sources, specifically seismic intensity data, animal behavior data, and environmental change data. This collection is done periodically, and the latest data is always kept.

[0468] Collection of seismic intensity data: The server collects real-time shaking data from seismic intensity meters installed across the country. The data includes the date and time of occurrence, epicenter, and seismic intensity.

[0469] Animal behavior data collection: The server collects information on abnormal animal behavior from social media and specialized databases. Specifically, it analyzes reports of mass sardine deaths, strandings of dolphins, and abnormal behavior in catfish and pets.

[0470] Environmental change data collection: The server collects data on environmental changes from monitoring satellites and ground sensors, including seismic cloud observations and ground deformation data.

[0471] Data Preprocessing

[0472] The server preprocesses the collected data, specifically cleansing it by removing noise and duplicate data, and normalizing data in different formats.

[0473] Data analysis

[0474] The server then uses an AI model to analyze the preprocessed data. The AI ​​model correlates past earthquake data with current data and detects abnormal patterns from multiple perspectives. The analysis results are output as a score indicating the likelihood of an earthquake occurring.

[0475] Earthquake forecast generation

[0476] The server generates earthquake forecasts based on the analysis results, which are formatted as detailed information including the probability of occurrence and phenomena to watch out for.

[0477] User Notifications

[0478] The server then sends the generated earthquake forecast to the user's device via push notification, email, or other means to grab the user's attention.

[0479] Device roles and functions

[0480] Receive notifications

[0481] The device receives the earthquake forecast notification sent from the server, and the notification is displayed immediately, alerting the user with an alarm sound or vibration if necessary.

[0482] Information display

[0483] The device visually displays the received forecast information, including the probability of an earthquake occurring, phenomena to watch out for, and recommended disaster prevention actions.

[0484] User Roles

[0485] Notification confirmation

[0486] The user checks the earthquake forecast notification displayed on the device and takes steps to ensure the safety of themselves and their families based on the contents of the notification.

[0487] action

[0488] Users can then make necessary disaster prevention preparations based on the forecast, such as checking their water and food stockpiles and evacuation routes.

[0489] Specific examples

[0490] For example, consider the following phenomenon observed in a certain area:

[0491] The seismometer detects an unusually small earthquake.

[0492] Local residents reported the "mass death of sardines" on social media.

[0493] Unusual earthquake clouds observed in satellite data.

[0494] The server immediately collects this data and performs data cleansing and normalization. The cleaned data is input into an AI model, where it is compared with past patterns and analyzed. The server calculates the likelihood of an earthquake occurring as a score and generates a forecast for that area. The generated forecast is immediately pushed to the device, informing the user that "There is a 10% chance of an earthquake occurring. Please make sure you are prepared." The user checks the notification and makes the necessary disaster prevention preparations. This allows users to maintain a high level of disaster prevention awareness on a daily basis.

[0495] In this way, the present invention provides a system for making comprehensive earthquake forecasts by utilizing a variety of data.

[0496] The processing flow will be explained below.

[0497] Step 1:

[0498] The server collects seismic intensity data. It accesses the nationwide seismic intensity network and obtains the latest shaking data. This data includes the epicenter, seismic intensity, and time of occurrence. The server performs this process periodically to maintain real-time accuracy.

[0499] Step 2:

[0500] The server collects animal behavior data. It monitors social media and animal observation databases, scanning for posts reporting mass sardine deaths or abnormal pet behavior. It uses text mining technology to extract useful information and store it in a database.

[0501] Step 3:

[0502] The server collects data on environmental changes. It uses satellite data and ground sensors to collect observations of earthquake clouds and ground changes. The server integrates this data and detects abnormal patterns.

[0503] Step 4:

[0504] The server preprocesses the collected data. First, it cleanses the data to remove noise and duplicate data. Next, it normalizes the data and standardizes data of different scales. This preprocessing makes it easier to input into the AI ​​model.

[0505] Step 5:

[0506] The server analyzes the data using an AI model. The preprocessed data is input into the AI ​​model, which then analyzes the current data against past earthquake data. The AI ​​model detects abnormal patterns and outputs a score indicating the likelihood of an earthquake occurring.

[0507] Step 6:

[0508] The server evaluates the analysis results. Based on the score output by the AI ​​model, it evaluates the reliability of the earthquake occurrence. Based on this evaluation result, it prepares to generate an earthquake forecast.

[0509] Step 7:

[0510] The server generates an earthquake forecast. Based on the evaluated analysis, it creates a detailed forecast of the likelihood of an earthquake occurring, including the probability of occurrence, what to watch out for, and recommended actions.

[0511] Step 8:

[0512] The server prepares the user notification and formats the generated forecast for transmission to the user's device, using push notifications or email.

[0513] Step 9:

[0514] The device receives and displays notifications. It displays notifications sent from the server immediately and uses alarm sounds or vibrations to attract the user's attention.

[0515] Step 10:

[0516] The user checks the notification and takes action. They check the earthquake forecast displayed on their device and make the necessary disaster prevention preparations, such as checking evacuation routes and emergency supplies.

[0517] Step 11:

[0518] Users provide feedback on the accuracy of the forecast and on improvements to the system. This feedback is used to improve the system in the future.

[0519] Example 1

[0520] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0521] Conventional earthquake forecasting systems have had issues in effectively aggregating data from multiple sources and making earthquake predictions in real time. In particular, there are limitations in preprocessing to improve data accuracy and analytical precision, and in detecting abnormal patterns. Furthermore, users are often not notified promptly and appropriately, making it difficult for them to take prompt disaster prevention action. To solve these problems, a system is needed that highly automates the entire process, from data collection and analysis to forecast generation and notification, achieving both accuracy and speed.

[0522] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0523] In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, an earthquake forecast generation means, a user notification means, an abnormal pattern detection means, an occurrence probability calculation means, and a detailed information generation means. This makes it possible to collect data from multiple information sources, perform advanced preprocessing, and generate an earthquake forecast through highly accurate analysis. Furthermore, by realizing prompt and accurate notification to the user, the user can take prompt disaster prevention action.

[0524] "Data collection means" refers to the means for obtaining necessary data from multiple sources.

[0525] The "preprocessing means" is a means for removing noise and redundancy from the collected data and converting it into a unified format.

[0526] The "data analysis means" is a means for performing analysis using preprocessed data to detect abnormal patterns.

[0527] The "earthquake forecast generating means" is a means for generating an earthquake forecast based on the results of data analysis.

[0528] The "user notification means" is a means for quickly notifying the user of the generated earthquake forecast.

[0529] The "abnormal pattern detection means" is a means for determining whether or not there is an abnormality in the current data through comparison with past data.

[0530] The "occurrence probability calculation means" is a means for quantifying the probability of an earthquake occurring based on the results of data analysis.

[0531] The "detailed information generating means" is a means for generating detailed information necessary for earthquake forecasting (probability of occurrence, phenomena to be aware of, disaster prevention actions, etc.).

[0532] "Means for obtaining seismic intensity meter data" refers to means for obtaining shaking data from seismic intensity meters installed throughout the country.

[0533] "Means for collecting animal behavior data" refers to means for collecting data on abnormal animal behavior.

[0534] "Means for collecting environmental change data" refers to means for collecting data on environmental changes such as earthquake clouds and ground deformation.

[0535] "Means for crawling data from social media" refers to means for automatically collecting posted data from social media.

[0536] "Means for acquiring satellite data" refers to means for acquiring data observed through a satellite.

[0537] "Means for removing noise and duplication from data" refers to means for removing outliers and duplicate data contained in collected data.

[0538] MODE FOR CARRYING OUT THE INVENTION

[0539] The present invention is a system for forecasting earthquakes, with a server, terminals, and users as the main actors. This system includes a data collection means, a preprocessing means, a data analysis means, an earthquake forecast generation means, a user notification means, an abnormal pattern detection means, an occurrence probability calculation means, and a detailed information generation means. This makes it possible to process information collected from various data sources and generate highly accurate earthquake forecasts.

[0540] Server Roles and Functions

[0541] Data collection

[0542] The server collects data from multiple sources, specifically seismic intensity data, animal behavior data, and environmental change data, and periodically stores the latest data.

[0543] Collection of seismic intensity data: The server obtains real-time shaking data from seismic intensity meters installed throughout the country via an API, for example, using the API of a public institution.

[0544] Collection of animal behavior data: The server uses crawling technology to collect information on abnormal animal behavior posted by local residents on social media. It also obtains data on dolphin strandings and abnormal catfish behavior from specialized databases.

[0545] Collection of environmental change data: The server uses the satellite data provider's API to obtain earthquake cloud observation data and environmental change data (such as ground deformation) from ground sensors.

[0546] Data Preprocessing

[0547] The server performs pre-processing on the collected data.

[0548] Noise removal: Detect outliers and missing values ​​and remove or impute them, e.g., by filling in missing values ​​with imputed means.

[0549] Data cleansing: Removing duplicate data and converting it into a consistent format, e.g. standardizing all time data to UTC.

[0550] Data normalization: Converting data from different sources into a uniform format, e.g., converting latitude and longitude data into a common coordinate system.

[0551] Data analysis

[0552] The server inputs the preprocessed data into the AI ​​model for analysis.

[0553] Generative AI model: Using historical and current earthquake data, we use a deep learning model trained on historical earthquake data to detect anomalous patterns.

[0554] Detecting abnormal patterns: Comparing new data with past patterns to determine whether there are any anomalies. For example, detecting a sudden change in seismic intensity data that matches animal behavior data.

[0555] Score calculation: As a result of the analysis, a score is calculated that indicates the possibility of an earthquake occurring. The score is expressed in a range from 0 to 100.

[0556] Earthquake forecast generation

[0557] The server generates an earthquake forecast based on the analysis results.

[0558] Forecast format: Generate a forecast based on the score, for example, "There is a 10% chance of an earthquake. Please make sure you are prepared."

[0559] Added detailed information: Not only the probability of occurrence, but also phenomena to watch out for (such as observation of earthquake clouds or abnormal animal behavior) and recommended disaster prevention actions.

[0560] User Notifications

[0561] The server notifies the generated earthquake forecast to the user's terminal.

[0562] Notification method: Users are notified by multiple methods, such as push notifications and email notifications. For example, push notifications are sent via smartphone apps.

[0563] Instant Notification: Earthquake forecasts are sent instantly, accompanied by an alarm sound and vibration to grab the user's attention.

[0564] Device roles and functions

[0565] Receive notifications

[0566] The device receives the earthquake forecast notification sent from the server, and the notification is displayed immediately, alerting the user with an alarm sound or vibration if necessary.

[0567] Information display

[0568] The device visually displays the received forecast information, including the probability of an earthquake occurring, phenomena to watch out for, and recommended disaster prevention actions.

[0569] User Roles

[0570] Notification confirmation

[0571] The user checks the earthquake forecast notification displayed on the device and takes steps to ensure the safety of themselves and their families based on the contents of the notification.

[0572] action

[0573] Users can then make necessary disaster prevention preparations based on the forecast, such as checking their water and food stockpiles and evacuation routes.

[0574] Specific examples

[0575] For example, consider the following phenomenon observed in a certain area:

[0576] The seismometer detects an unusually small earthquake.

[0577] Local residents reported the "mass death of sardines" on social media.

[0578] Unusual earthquake clouds observed in satellite data.

[0579] The server immediately collects this data and performs data cleansing and normalization. The cleaned data is input into an AI model, where it is compared with past patterns and analyzed. The server calculates the likelihood of an earthquake occurring as a score and generates a forecast for that area. The generated forecast is immediately pushed to the device, informing the user that "There is a 10% chance of an earthquake occurring. Please make sure you are prepared." The user checks the notification and makes the necessary disaster prevention preparations. This allows users to maintain a high level of disaster prevention awareness on a daily basis.

[0580] Prompt Sentence Examples

[0581] "We have developed a new earthquake forecasting system. This system collects data from seismometers, animal behavior data, and environmental change data, and analyzes it using an AI model. It calculates the probability of an earthquake occurring as a score and notifies the user. Please tell us the processing steps of this system."

[0582] By implementing this aspect, the present invention provides a system that utilizes a variety of data to perform comprehensive and highly accurate earthquake forecasting.

[0583] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0584] Step 1: Data collection

[0585] The server collects the necessary data from multiple sources. The inputs to this step are seismometer data, animal behavior data, and environmental change data. The output is a collection of these data. Specifically, the server performs the following:

[0586] Collection of seismometer data: The server obtains shaking data (occurrence date and time, epicenter, seismic intensity) from the seismometer. For example, it obtains real-time data by calling an API.

[0587] Collection of animal behavior data: The server uses scraping technology to obtain data on abnormal animal behavior from social media and specialized databases.

[0588] Collection of environmental change data: The server acquires environmental change data (earthquake cloud observation results, ground change data) from satellite data providers and ground sensors.

[0589] Step 2: Data Preprocessing

[0590] The server performs pre-processing on the collected data. The input to this step is the output data from step 1. The output is the cleansed and normalized data. Specifically, the server:

[0591] Noise removal: Detect outliers and missing values ​​in the data and remove or impute them, for example by filling in missing values ​​with imputed means.

[0592] Data cleansing: Removing duplicate data and converting it into a consistent format, for example, standardizing all date and time data to UTC.

[0593] Data normalization: Standardizing data from different sources into the same format, for example, converting latitude and longitude data into a common coordinate system.

[0594] Step 3: Data analysis

[0595] The server performs analysis using the AI ​​model based on the preprocessed data. The input for this step is the output data from step 2. The output is the anomaly pattern detection results and an earthquake occurrence probability score. Specifically, the server performs the following:

[0596] Use generative AI models: Use historical and current earthquake data to detect anomalous patterns. Use deep learning models trained on historical earthquake data.

[0597] Detecting abnormal patterns: Comparing new data with past patterns to determine whether there are any anomalies. For example, detecting a sudden change in seismic intensity data that matches animal behavior data.

[0598] Score calculation: As a result of the analysis, a score is calculated that indicates the possibility of an earthquake occurring. The score is expressed in a range from 0 to 100.

[0599] Step 4: Earthquake forecast generation

[0600] The server generates an earthquake forecast based on the analysis results. The input to this step is the output score from step 3. The output is earthquake forecast information. Specifically, the server performs the following operations:

[0601] Forecast format: Generate forecast content based on the score, for example, "There is a 10% chance of an earthquake. Please be prepared."

[0602] Add detailed information: Include not only the probability of occurrence, but also phenomena to watch out for (such as observation of earthquake clouds or abnormal animal behavior) and recommended disaster prevention actions.

[0603] Step 5: User Notification

[0604] The server notifies the generated earthquake forecast to the user's terminal. The input of this step is the forecast information output in step 4. The output is the notification information displayed on the terminal. Specifically, the server performs the following operations:

[0605] Selection of notification method: Notify users through multiple methods, such as push notifications and email notifications. For example, send push notifications through a smartphone app.

[0606] Instant Notification: Earthquake forecasts are sent instantly, accompanied by an alarm sound and vibration to grab the user's attention.

[0607] Step 6: Check notifications and take action

[0608] The user checks the earthquake forecast notification displayed on the terminal. The input of this step is the notification information output in step 5. The output is the specific disaster prevention action the user will take. Specifically, the user will:

[0609] Confirm notification: The user confirms the notification content and understands the possibility of an earthquake occurring and the recommended actions.

[0610] Disaster Preparedness: Make necessary disaster preparedness preparations based on the notification, such as checking your water and food stockpiles and checking whether your furniture is securely fastened.

[0611] (Application example 1)

[0612] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0613] Current earthquake forecasting systems lack the means to detect signs of an impending earthquake and quickly notify users. As a result, users are sometimes slow to respond to an earthquake, making it difficult to minimize damage. There is also a need for technology that can integrate information from different data sources to generate highly accurate forecasts. Furthermore, there is no mechanism for specifically recommending disaster prevention actions, making it difficult to raise users' disaster prevention awareness.

[0614] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0615] In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, and a push notification means. This allows the server to integrate information collected from multiple data sources, generate earthquake forecasts in real time, and promptly notify users via push notifications. Furthermore, by recommending specific disaster prevention actions, the server can raise users' disaster prevention awareness and promote early response to earthquakes.

[0616] "Data collection means" refers to the means of collecting data from multiple sources necessary for earthquake forecasting, such as seismic intensity data, animal behavior data, and environmental change data.

[0617] The "preprocessing means" is a means for removing noise and redundant data from collected data and unifying data in different formats.

[0618] The "data analysis means" is a means of analyzing preprocessed data using an AI model to calculate a score indicating the possibility of an earthquake occurring.

[0619] The "earthquake forecast generating means" is a means for generating an earthquake forecast based on the analysis results by the data analysis means.

[0620] The "user notification means" is a means for transmitting the generated earthquake forecast to the user's terminal and notifying the user.

[0621] The "push notification means" is a means for immediately notifying the user's terminal of an earthquake forecast generated based on the analyzed information in real time.

[0622] The "means for acquiring seismic intensity meter data" refers to a means for acquiring real-time shaking data from a seismic intensity meter.

[0623] "Means for collecting animal behavior data" refers to means for collecting data on abnormal animal behavior.

[0624] "Means for collecting environmental change data" refers to means for collecting data on environmental changes from monitoring satellites and ground sensors.

[0625] "Means for cleansing collected data" refers to means for removing noise and redundant data from collected data to generate more accurate data.

[0626] "Means for normalizing data" refers to means for standardizing data collected in different formats and making it suitable for analysis.

[0627] "Means for calculating the possibility of an earthquake occurring based on the analysis results" refers to means for quantitatively assessing the possibility of an earthquake occurring based on the analyzed data.

[0628] The "means for generating and sending a push notification" is a means for generating a forecast notification based on the analysis results and sending it to the user's device.

[0629] The "means for recommending disaster prevention actions based on the forecast content" is a means for recommending appropriate disaster prevention actions to a user based on the generated earthquake forecast.

[0630] The present invention is an earthquake forecasting system that collects data, analyzes data, generates forecasts, and notifies users, mainly consisting of a server, terminals, and users. Specific embodiments of each element are described below.

[0631] Server Roles and Functions

[0632] Data collection

[0633] The server collects data from sources necessary for earthquake forecasting, such as seismometer data, animal behavior data, and environmental change data. Data collection scripts are created using programming languages ​​such as Python to periodically retrieve information.

[0634] Data Preprocessing

[0635] We will remove noise and duplicate data from the collected data and unify data in different formats using pandas, a Python data processing library.

[0636] Data analysis

[0637] The preprocessed data is analyzed using an AI model. The AI ​​model uses TensorFlow and PyTorch to correlate past earthquake data with current data and detect abnormal patterns from multiple perspectives. The analysis results are calculated as a score indicating the possibility of an earthquake occurring.

[0638] Earthquake forecast generation

[0639] The server generates an earthquake forecast based on the analysis results. The forecast is formatted as detailed information including the probability of occurrence and phenomena to watch out for. The forecast also includes a message encouraging users to take disaster prevention action.

[0640] User Notifications

[0641] The server sends the generated earthquake forecast to the user's device. The user is notified in the form of a push notification using Firebase Cloud Messaging (FCM). The notification includes the probability of occurrence and recommended actions.

[0642] Device roles and functions

[0643] Receive notifications

[0644] The device receives the earthquake forecast notification sent from the server immediately and notifies the user. The notification is displayed visually and can use an alarm sound or vibration.

[0645] Information display

[0646] The user's device visually displays the received forecast, including the probability of an earthquake occurring and specific disaster prevention recommendations.

[0647] User Roles

[0648] Notification confirmation

[0649] The user checks the earthquake forecast notification displayed on the device and takes steps to ensure the safety of themselves and their families based on the contents of the notification.

[0650] action

[0651] Based on the forecast, users can make necessary disaster prevention preparations, such as checking their water and food stockpiles and evacuation routes.

[0652] Specific examples

[0653] For example, if the following phenomena are observed simultaneously in the Kanto region:

[0654] The seismometer detects an unusually small earthquake.

[0655] Local residents report the "mass inaction of frogs" on social media.

[0656] Observing abnormal cloud movements using satellite data.

[0657] This information is immediately collected on a server, where it is cleansed and normalized. This clean data is then input into an AI model to generate analysis results. For example, if the analysis score is 0.15, a notification will be sent to the user's smartphone saying, "There is a 15% chance of an earthquake occurring. Please make sure you are prepared."

[0658] Example prompts for generative AI models

[0659] "Seismic intensity meters in the Kanto region have detected an unusually small earthquake, and reports of mass frog inactivity have been posted on social media. Furthermore, unusual cloud movement has been observed using satellite data. Please use this information to analyze the likelihood of an earthquake occurring and predict whether it will occur."

[0660] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0661] Step 1:

[0662] Data collection

[0663] The server collects seismic intensity data, animal behavior data, and environmental change data. The inputs used are real-time shaking data from the seismic intensity data, animal behavior reports from social media and specialized databases, and environmental change data from monitoring satellites and ground sensors. It periodically collects this data and runs a program that centrally aggregates it.

[0664] Step 2:

[0665] Data Preprocessing

[0666] The server preprocesses the collected data. The input data includes seismometer data, animal behavior data, and environmental change data. It cleanses noise and duplicate data from these data sets and unifies data in different formats using the pandas library. This results in a clean, unified dataset being output.

[0667] Step 3:

[0668] Data analysis

[0669] The server analyzes the preprocessed data. The input data includes cleansed and normalized seismic intensity data, animal behavior data, and environmental change data. This data is input into an AI model (using TensorFlow and PyTorch) to calculate a score indicating the likelihood of an earthquake occurring. The output is an analysis result indicating the likelihood of an earthquake occurring.

[0670] Step 4:

[0671] Earthquake forecast generation

[0672] The server generates an earthquake forecast based on the results of the data analysis. The input is the probability score of an earthquake occurring obtained through the analysis. Based on this score, the server formats the earthquake forecast text and disaster prevention action recommendations. This results in a detailed earthquake forecast and disaster prevention action recommendations being output.

[0673] Step 5:

[0674] User Notifications

[0675] The server sends the generated earthquake forecast to the user device. The input data includes the earthquake forecast and disaster prevention recommendations. This data is immediately sent to the user device as a push notification using Firebase Cloud Messaging (FCM). The output is the notification message received on the user device.

[0676] Step 6:

[0677] Notification reception (device side)

[0678] The user's device receives the notification sent from the server. The input is the received push notification message. The device notifies the user of the notification content visually and audibly. The output is an earthquake forecast notification displayed to the user.

[0679] Step 7:

[0680] Information display (terminal side)

[0681] Displays the earthquake forecast notification received by the device. The input data is the content of the received push notification. This is displayed visually so that the user can confirm the content. The output is a specific earthquake forecast and recommended disaster prevention actions displayed on the device screen.

[0682] Step 8:

[0683] Notification confirmation (user side)

[0684] The user checks the notification displayed on the device. The input is the earthquake forecast notification displayed on the device. Based on this notification, the user considers the actions necessary to ensure the safety of themselves and their families. The output is the user's disaster prevention actions.

[0685] Step 9:

[0686] Disaster prevention actions (user side)

[0687] The user makes specific disaster prevention preparations based on the notified forecast. The input data includes the notified earthquake forecast and recommended disaster prevention actions. This allows the user to check their water and food stockpiles, check evacuation routes, etc. The output is the specific disaster prevention actions the user should take.

[0688] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0689] This invention incorporates an emotion engine into an earthquake forecasting system to recognize the user's emotional state and customize notification content and disaster prevention action recommendations. This system operates with the server, terminals, and users as its main drivers, and not only improves the accuracy of earthquake forecasts but also provides responses that correspond to the user's psychological state.

[0690] Server Roles and Functions

[0691] Data collection

[0692] The server acquires information necessary for earthquake forecasting, including seismometer data, animal behavior data, and environmental change data. This data is collected periodically by the server and kept up to date.

[0693] Collection of seismic intensity data: The server collects detailed data such as epicenter, seismic intensity, and time of occurrence from seismic intensity meters across the country.

[0694] Collection of animal behavior data: The server collects information from social media and specialized databases about mass sardine deaths and abnormal pet behavior.

[0695] Collection of environmental change data: The server collects observations of earthquake clouds and ground changes using satellite data and ground sensors.

[0696] Data Preprocessing

[0697] The server cleanses and normalizes the collected data, which includes removing noise and duplicate data and unifying data in different formats.

[0698] Data analysis

[0699] The server inputs the preprocessed data into an AI model, which compares it with past earthquake data and analyzes it. The AI ​​model detects abnormal patterns and outputs a score indicating the likelihood of an earthquake occurring.

[0700] Earthquake forecast generation

[0701] The server evaluates the analysis results and generates a forecast of the likelihood of an earthquake, including the probability of occurrence, what to watch out for, and recommended actions.

[0702] Evaluation by Emotion Engine

[0703] The server uses an emotion engine to analyze the user's emotional data, for example, assessing the user's stress level or anxiety level based on their past actions and comments.

[0704] User notification preparation

[0705] The server adjusts the notification content based on the emotion engine's evaluation. For example, if the user is feeling high stress, the notification content will be changed to a more gentle expression and a supportive message will be added to reduce anxiety.

[0706] Device roles and functions

[0707] Receive notifications

[0708] The device receives notifications sent from the server, and the notifications are displayed immediately and, if necessary, notify the user with an alarm sound or vibration.

[0709] Information display

[0710] The device visually displays the received forecast, including the probability of an earthquake occurring, factors to be aware of, and recommended disaster prevention actions.

[0711] Collecting Emotional Data

[0712] The device collects information about the user's daily behavior and input emotions and sends it to the server, where it is used for analysis by the emotion engine.

[0713] User Roles

[0714] Notification confirmation

[0715] The user checks the notification on the device, understands the earthquake forecast, and makes disaster prevention preparations based on the notification content.

[0716] action

[0717] Users can take necessary disaster prevention actions based on the notification, such as checking their water and food stockpiles and checking evacuation routes.

[0718] feedback

[0719] Users can provide feedback on the accuracy of forecasts and notifications via their devices, which is then sent to the server and used to improve the system.

[0720] Specific examples

[0721] Suppose a seismometer detects an abnormal small earthquake in a certain area, and a mass death of sardines is reported on social media. Furthermore, if an abnormal earthquake cloud is observed in satellite data, this data is collected on a server. The server cleans and normalizes this data, and inputs it into an AI model for analysis. Based on the analysis results, it is determined that there is a high probability of an earthquake occurring.

[0722] As a result, the server generates an earthquake forecast and simultaneously evaluates the user's emotional state using an emotion engine. For example, if the user is feeling very stressed, the server softens the notification and adds a support message to promote disaster preparedness. This forecast notification is then sent to the user's device, which displays the notification to attract the user's attention.

[0723] The user checks the notification and makes the necessary disaster prevention preparations. At that time, the user provides feedback to the server via their device, contributing to improvements in the system. In this way, the present invention improves the accuracy and reliability of earthquake forecasts and provides disaster prevention support that takes user emotions into consideration.

[0724] The processing flow will be explained below.

[0725] Step 1:

[0726] The server collects seismic intensity data, accessing the nationwide seismic intensity network in real time to obtain the latest shaking data, including the epicenter, seismic intensity, and time of occurrence.

[0727] Step 2:

[0728] The server collects animal behavior data, scanning social media and specialized databases for posts about mass sardine deaths and abnormal pet behavior, and using text mining techniques to extract useful information and store it in a database.

[0729] Step 3:

[0730] The server collects data on environmental changes, such as earthquake cloud observations and ground deformation information using satellite images and ground sensors. This data is integrated to detect abnormal patterns.

[0731] Step 4:

[0732] The server preprocesses the collected data. First, it cleanses the data to remove noise and duplicate data. Next, it normalizes the data and standardizes data in different formats. This preprocessing makes it easier to input into the AI ​​model.

[0733] Step 5:

[0734] The server inputs the preprocessed data into an AI model for data analysis, which compares past earthquake data with current data to detect abnormal patterns and output a score indicating the likelihood of an earthquake occurring.

[0735] Step 6:

[0736] The server evaluates the analysis results. Based on the score output by the AI ​​model, it evaluates the reliability of the earthquake occurrence. Based on the analysis results, it prepares earthquake forecasts.

[0737] Step 7:

[0738] The server generates an earthquake forecast based on the analysis results, which includes the probability of an earthquake occurring, phenomena to watch out for, and recommended disaster prevention actions.

[0739] Step 8:

[0740] The server uses an emotion engine to analyze the user's emotional data, and evaluates their stress and anxiety levels based on their past behavioral history and input emotional data.

[0741] Step 9:

[0742] The server customizes the notification content based on the analysis results of the emotion engine. If the user is feeling high stress, the forecast notification will be softened and a reassuring message will be added.

[0743] Step 10:

[0744] The server then sends the coordinated forecast notification to the user's device, which includes the possibility of an earthquake occurring, what phenomena to watch out for, and recommended disaster prevention actions.

[0745] Step 11:

[0746] The device receives the notification and displays it immediately, using an alarm sound or vibration to get the user's attention.

[0747] Step 12:

[0748] The user checks the earthquake forecast notification displayed on the device, understands the forecast content, and makes the necessary disaster prevention preparations based on the notification.

[0749] Step 13:

[0750] The user takes disaster prevention actions, such as making specific preparations such as checking water and food stockpiles and evacuation routes.

[0751] Step 14:

[0752] Users can provide feedback on the content of notifications and the accuracy of forecasts. By sending feedback to the server via their device, they can contribute to improving the system. This feedback will be used to improve the accuracy of future forecasts.

[0753] Example 2

[0754] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0755] Conventional earthquake forecasting systems have a certain degree of accuracy in predicting earthquake occurrences, but they lack the ability to provide notification content that takes into account the user's psychological state. As a result, when users are in situations where they feel high levels of stress or anxiety, it can be difficult to take appropriate disaster prevention actions. A system that solves this problem and allows users to calmly take disaster prevention actions is needed.

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

[0757] In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, an earthquake forecast generation means, a user notification means, an emotional state analysis means, and a means for adjusting the notification content based on the emotional state of the user, thereby making it possible to provide notification content that takes the psychological state of the user into consideration.

[0758] "Data collection means" refers to a device or process that collects various data necessary for earthquake forecasting.

[0759] A "pre-processing means" is a device or process that cleanses and normalizes collected data and converts it into a suitable format for analysis.

[0760] "Data analysis means" refers to a device or process that analyzes the possibility of earthquake occurrence based on pre-processed data.

[0761] "Earthquake forecast generating means" refers to a device or process that generates an earthquake forecast based on the results of data analysis.

[0762] The "user notification means" is a device or process that notifies the user of the generated earthquake forecast.

[0763] "Emotional state analysis means" refers to a device or process that analyzes the user's emotional data and assesses the level of stress or anxiety.

[0764] The "means for adjusting notification content based on the emotional state of the user" refers to a device or process that appropriately adjusts notification content for the user based on the results of the emotional state analysis.

[0765] This invention is a system that incorporates an emotion engine into an earthquake forecasting system to recognize the user's emotional state and customize notification content and disaster prevention action recommendations. This system operates with the server, terminals, and users as its main actors, and not only improves the accuracy of earthquake forecasts but also provides responses that correspond to the user's psychological state.

[0766] Server Roles and Functions

[0767] 1. Data collection methods:

[0768] The server collects data on seismic intensity meters, animal behavior, and environmental changes. Specifically, it obtains detailed data such as the epicenter, intensity, and time of occurrence from seismic intensity meters across the country, and collects information on mass sardine deaths and abnormal pet behavior from social media and specialized databases. It also obtains observation results of earthquake clouds and ground changes using satellite data and ground sensors.

[0769] 2. Pretreatment methods:

[0770] The server cleanses and normalizes the collected data, removing noise and duplicate data and unifying data in different formats.

[0771] 3. Data analysis methods:

[0772] The server inputs the preprocessed data into an AI model to analyze the likelihood of an earthquake occurring, using TensorFlow as the AI ​​model and comparing it with past earthquake data to detect abnormal patterns.

[0773] 4. Earthquake forecast generation method:

[0774] The server generates an earthquake forecast based on the analysis results, which includes the probability of occurrence, phenomena to watch out for, and recommended actions.

[0775] 5. Emotional state analysis method:

[0776] The server uses an emotion engine to analyze the user's emotional data, specifically assessing their stress level and anxiety based on their past behavior and social media posts.

[0777] 6. How to tailor notifications based on the user's emotional state:

[0778] The server adjusts the notification content based on the results of the emotional state analysis. For example, if the user is feeling high stress, the server changes the notification content to a calmer one and adds a supportive message to reduce anxiety.

[0779] Device roles and functions

[0780] 1. Receive notifications:

[0781] The device receives notifications sent from the server, and the notifications are displayed immediately and, if necessary, notify the user with an alarm sound or vibration.

[0782] 2. Information display:

[0783] The device visually displays the received forecast, including the probability of an earthquake occurring, precautions to take, and recommended disaster prevention actions.

[0784] 3. Collecting Emotional Data:

[0785] The device collects data on the user's daily behavior and emotions and sends it to a server. Specifically, it measures the user's stress level and analyzes the contents of their diary entries and social media posts.

[0786] User Roles

[0787] 1. Notification confirmation:

[0788] The user checks the notification on the device, understands the earthquake forecast, and makes the necessary disaster prevention preparations based on the forecast.

[0789] 2. Action:

[0790] Users can take necessary disaster prevention actions based on the notification, such as checking their water and food stockpiles and evacuation routes.

[0791] 3. Feedback:

[0792] Users can provide feedback on the accuracy of forecasts and notifications via their devices, which is then sent to the server and used to improve the system.

[0793] Specific examples

[0794] If a seismometer detects an abnormally small earthquake in a certain area and a mass death of sardines is reported on social media, the server collects this data. The server cleans and normalizes the data, then inputs it into an AI model for analysis. Based on the analysis results, it determines the likelihood of an earthquake occurring.

[0795] As a result, the server generates an earthquake forecast and simultaneously evaluates the user's emotional state using an emotion engine. For example, if the user is feeling very stressed, the notification's wording will be softened and a support message will be added to promote disaster prevention preparations. This forecast notification is sent to the user's device, which displays the notification to attract the user's attention. The user then checks the notification and takes the necessary disaster prevention preparations. At that time, the user provides feedback to the server via their device, contributing to system improvements.

[0796] Specific examples of prompts to input to generative AI models

[0797] "Explain how an earthquake forecasting system can change the wording of notifications depending on the user's emotional state."

[0798] "Please explain how the earthquake forecasting system works, using seismic intensity data, animal behavior data, and environmental change data."

[0799] "Please provide a concrete example of how an earthquake forecasting system incorporating an emotion engine can provide notifications to users."

[0800] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0801] Step 1:

[0802] The server periodically collects seismic intensity data, animal behavior data, and environmental change data. Input data includes detailed data such as epicenter, intensity, and time of occurrence obtained from seismic intensity meters across the country, information on mass sardine deaths and abnormal pet behavior collected from social media and specialized databases, and earthquake cloud observation results and ground change data obtained from satellite data and ground sensors. This data is stored in the server's database.

[0803] Step 2:

[0804] The server cleanses and normalizes the collected data. The input is the raw data collected in step 1. Specifically, it removes noise, reduces duplicate data, and unifies data in different formats. As a result, it outputs clean data suitable for analysis.

[0805] Step 3:

[0806] The server inputs the preprocessed data into the AI ​​model for analysis. The input is the data preprocessed in step 2. The AI ​​model (using TensorFlow, for example) compares the input data with past earthquake data to detect abnormal patterns. As a result of the analysis, it outputs a score indicating the likelihood of an earthquake occurring.

[0807] Step 4:

[0808] The server generates an earthquake forecast based on the analysis results. The input is the earthquake occurrence probability score obtained in step 3. The earthquake forecast includes the occurrence probability, phenomena to watch out for, and recommended actions. This forecast is sent to the user notification means.

[0809] Step 5:

[0810] The server uses an emotion engine to analyze the user's emotional data. The input is the user's past behavioral data and social media posts. Based on this data, the server evaluates the user's stress level and anxiety level. The results of the emotion analysis are output.

[0811] Step 6:

[0812] The server adjusts the notification content based on the results of the emotional state analysis. The inputs are the earthquake forecast from step 4 and the emotion analysis results from step 5. For high-stress users, the notification content is changed to gentler language such as "Please stay calm" and a support message to reduce anxiety is added. The adjusted notification content is output and sent to the user notification means.

[0813] Step 7:

[0814] The device receives the notification sent from the server. The input is the notification content adjusted in step 6. The notification is displayed immediately and notifies the user with an alarm sound or vibration if necessary. The notification content is displayed on the device.

[0815] Step 8:

[0816] The terminal visually displays the received notification content. The input is the notification content received in step 7. The visual display includes the probability of an earthquake occurring, points to be aware of, and recommended disaster prevention actions. Information is provided visually to the user.

[0817] Step 9:

[0818] The user checks the notification on the device and understands the earthquake forecast. The input is the notification content displayed in step 8. Based on the notification content, the user makes the necessary disaster prevention preparations. The user checks their water and food stockpiles, checks evacuation routes, etc.

[0819] Step 10:

[0820] Users provide feedback on forecast accuracy and notification content through their devices. The input is the user's feedback. The feedback is sent from the device to the server. The feedback reaches the server and is used to improve the system.

[0821] (Application example 2)

[0822] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0823] Earthquake forecasting systems are required not only to improve the accuracy of earthquake predictions, but also to customize notification content and disaster prevention action recommendations according to the user's emotional state. However, conventional systems do not take the user's emotional state into consideration when providing notifications, and are therefore unable to reduce anxiety and stress. Therefore, efforts are needed to reduce users' psychological stress and anxiety in addition to improving the accuracy of earthquake forecasts.

[0824] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes data collection means, preprocessing means, data analysis means, earthquake forecast generation means, emotion engine means, notification content customization means, and user notification means. This improves the accuracy of earthquake forecasts and enables customized notifications to be provided according to the user's emotional state, thereby reducing the user's stress and anxiety.

[0825] The "data collection means" is a device or program that has the function of acquiring various data necessary for earthquake forecasting (seismic intensity data, animal behavior data, environmental change data, user emotion data, etc.).

[0826] The "preprocessing means" is a device or program that has the function of cleansing and normalizing the collected data and processing it into a format suitable for analysis.

[0827] "Data analysis means" refers to a device or program that has the function of analyzing the probability of earthquake occurrence, etc., using an AI model based on preprocessed data.

[0828] The "earthquake forecast generating means" is a device or program that has the function of generating a forecast that takes into account the possibility of an earthquake occurring based on the analyzed data.

[0829] The "emotion engine means" is a device or program that has the function of analyzing the user's emotion data and evaluating the user's current psychological state.

[0830] The "notification content customization means" is a device or program having a function of appropriately adjusting the notification content in accordance with the emotional state of the user based on the evaluation result of the emotion engine means.

[0831] The "user notification means" is a device or program having a function for transmitting the generated notification content to the user.

[0832] The present invention provides a system for providing disaster prevention notifications that take into account the emotional state of a user in an earthquake forecasting system. The system includes a data collection means, a preprocessing means, a data analysis means, an earthquake forecast generation means, an emotion engine means, a notification content customization means, and a user notification means.

[0833] Server Roles and Functions

[0834] Data collection

[0835] The server collects data necessary for earthquake forecasting. This data includes seismic intensity data, animal behavior data, environmental change data, and user emotion data. For example, seismic intensity data is obtained from seismic intensity data collected from seismic intensity data collected nationwide, and animal behavior data is collected from specialized databases and social media. Environmental change data is obtained from satellite data and ground sensors, and emotion data is collected from user comments and actions.

[0836] Data Preprocessing

[0837] The server cleanses and normalizes the collected data, which includes removing noise and duplicate data and standardizing data in different formats. For example, seismic intensity data and emotion data are properly scaled using standardization techniques.

[0838] Data analysis

[0839] The server then inputs the preprocessed data into an AI model, which compares it with past earthquake data and analyzes it. The AI ​​model detects abnormal patterns and outputs a score indicating the likelihood of an earthquake occurring. For example, an earthquake prediction model or sentiment analysis model trained with Keras is used for this analysis.

[0840] Earthquake forecast generation

[0841] The server evaluates the analysis results and generates a forecast of the possibility of an earthquake occurring, including the probability of occurrence, phenomena to watch out for, and recommended actions, to help users make appropriate disaster prevention preparations.

[0842] Evaluation by Emotion Engine

[0843] The server uses an emotion engine to analyze the user's emotional data. For example, it evaluates the user's stress level and anxiety level based on their past actions and comments. This allows the server to tailor the content of notifications to suit the user's psychological state.

[0844] Customizing notification content

[0845] The server adjusts the notification content based on the emotion engine's evaluation results: if the user is experiencing high stress, the notification's wording will be softer and a supportive message will be added to reduce anxiety.

[0846] User Notifications

[0847] The server sends a customized notification to the user's device, which displays the notification. The user can then check the notification content and take necessary disaster prevention preparations.

[0848] Specific examples

[0849] For example, if a seismometer detects an unusual small earthquake in a certain area, reports of abnormal animal behavior on social media and earthquake cloud observations from satellite data are collected on a server. At the same time, the user's emotional data is also collected and analyzed. The server inputs this data into an AI model and analyzes the high probability of an earthquake occurring. Based on the results, the emotion engine then evaluates the user's current psychological state and creates a notification. For example, it generates a notification that reassures the user, saying, "Don't worry. The predicted probability of an earthquake is 30%. You are safe for now." This notification is then sent to the user's smartphone, where the user can check it and provide feedback if necessary.

[0850] Prompt Sentence Examples

[0851] This program takes the emotion data of user "12345" and combines it with earthquake forecast data to generate a notification. If the emotion score is high, the notification content will be changed to be gentle.

[0852] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0853] Step 1:

[0854] The server acquires the data necessary for earthquake forecasting. Specifically, it collects seismometer data, animal behavior data, environmental change data, and user emotion data from each data source. This includes acquiring data from APIs and scraping social media data. The input is the initial data from each data source, and the output is the raw data stored in the server.

[0855] Step 2:

[0856] The server cleanses and normalizes the collected data, specifically removing noise and duplicate data, completing incomplete data, standardizing formats, etc. The input is the raw data obtained in step 1, and the output is the cleansed, normalized, and organized data.

[0857] Step 3:

[0858] The server inputs the preprocessed data into the AI ​​model for analysis. Specifically, it compares it with past earthquake data and calculates the probability of an earthquake occurring as a score. The input is the organized data obtained in Step 2, and the output is a probability score for the occurrence of an earthquake.

[0859] Step 4:

[0860] The server generates a forecast of the possibility of an earthquake occurring. Specifically, it evaluates the analysis results of the AI ​​model and creates a forecast that includes the probability of occurrence, phenomena to watch out for, and recommended actions. The input is the earthquake prediction score, and the output is the forecast data that is notified to the user.

[0861] Step 5:

[0862] The server analyzes the user's emotion data using an emotion engine. Specifically, it uses an emotion analysis model to evaluate the stress level and anxiety level from the user's history and daily behavior. The input is the emotion data collected in step 1, and the output is the user's emotion score.

[0863] Step 6:

[0864] The server adjusts the notification content based on the emotion engine's evaluation results. Specifically, if the user's emotion score is high, the notification content is changed to a more gentle expression and a support message is added to promote disaster prevention preparation. The input is forecast data and emotion score, and the output is a customized notification message.

[0865] Step 7:

[0866] The server sends the customized notification to the user's device. Specifically, it pushes the generated notification message to the user's smartphone or other appropriate device. The input is the customized notification message, and the output is the notification message displayed on the user's device.

[0867] Step 8:

[0868] The user checks the notification displayed on the device and prepares for disaster. Specifically, the user takes necessary disaster prevention actions, such as checking water and food stockpiles and evacuation routes. The input is the notification content displayed on the device, and the output is the user's disaster prevention actions.

[0869] Step 9:

[0870] The user provides feedback to the server through the terminal. Specifically, the user sends their opinion on the notification content and forecast accuracy. The input is the user's feedback, and the output is the feedback data received by the server.

[0871] Step 10:

[0872] The server improves the system based on the received feedback. Specifically, it analyzes the feedback data, trains new predictive models, and improves notification content. The input is the feedback data, and the output is an improved system.

[0873] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0874] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0875] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0876] [Third embodiment]

[0877] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0878] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0879] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0880] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0881] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0882] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0883] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0884] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0885] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0886] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0887] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0888] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0889] The present invention is an earthquake forecasting system that collects data, analyzes data, generates forecasts, and notifies users, mainly consisting of a server, terminals, and users. Specific embodiments of each element are described below.

[0890] Server Roles and Functions

[0891] Data collection

[0892] The server collects data necessary for earthquake forecasting from multiple sources, specifically seismic intensity data, animal behavior data, and environmental change data. This collection is done periodically, and the latest data is always kept.

[0893] Collection of seismic intensity data: The server collects real-time shaking data from seismic intensity meters installed across the country. The data includes the date and time of occurrence, epicenter, and seismic intensity.

[0894] Animal behavior data collection: The server collects information on abnormal animal behavior from social media and specialized databases. Specifically, it analyzes reports of mass sardine deaths, strandings of dolphins, and abnormal behavior in catfish and pets.

[0895] Environmental change data collection: The server collects data on environmental changes from monitoring satellites and ground sensors, including seismic cloud observations and ground deformation data.

[0896] Data Preprocessing

[0897] The server preprocesses the collected data, specifically cleansing it by removing noise and duplicate data, and normalizing data in different formats.

[0898] Data analysis

[0899] The server then uses an AI model to analyze the preprocessed data. The AI ​​model correlates past earthquake data with current data and detects abnormal patterns from multiple perspectives. The analysis results are output as a score indicating the likelihood of an earthquake occurring.

[0900] Earthquake forecast generation

[0901] The server generates earthquake forecasts based on the analysis results, which are formatted as detailed information including the probability of occurrence and phenomena to watch out for.

[0902] User Notifications

[0903] The server then sends the generated earthquake forecast to the user's device via push notification, email, or other means to grab the user's attention.

[0904] Device roles and functions

[0905] Receive notifications

[0906] The device receives the earthquake forecast notification sent from the server, and the notification is displayed immediately, alerting the user with an alarm sound or vibration if necessary.

[0907] Information display

[0908] The device visually displays the received forecast information, including the probability of an earthquake occurring, phenomena to watch out for, and recommended disaster prevention actions.

[0909] User Roles

[0910] Notification confirmation

[0911] The user checks the earthquake forecast notification displayed on the device and takes steps to ensure the safety of themselves and their families based on the contents of the notification.

[0912] action

[0913] Based on the forecast, users can make necessary disaster prevention preparations, such as checking their water and food stockpiles and evacuation routes.

[0914] Specific examples

[0915] For example, consider the following observations in a certain area:

[0916] The seismometer detects an unusually small earthquake.

[0917] Local residents reported the "mass death of sardines" on social media.

[0918] Unusual earthquake clouds observed in satellite data.

[0919] The server immediately collects this data and performs data cleansing and normalization. The cleaned data is input into an AI model, where it is compared with past patterns and analyzed. The server calculates the likelihood of an earthquake occurring as a score and generates a forecast for that area. The generated forecast is immediately pushed to the device, informing the user that "There is a 10% chance of an earthquake occurring. Please make sure you are prepared." The user checks the notification and makes the necessary disaster prevention preparations. This allows users to maintain a high level of disaster prevention awareness on a daily basis.

[0920] In this way, the present invention provides a system for making comprehensive earthquake forecasts by utilizing a variety of data.

[0921] The processing flow will be explained below.

[0922] Step 1:

[0923] The server collects seismic intensity data. It accesses the nationwide seismic intensity network and obtains the latest shaking data. This data includes the epicenter, seismic intensity, and time of occurrence. The server performs this process periodically to maintain real-time accuracy.

[0924] Step 2:

[0925] The server collects animal behavior data. It monitors social media and animal observation databases, scanning for posts reporting mass sardine deaths or abnormal pet behavior. It uses text mining technology to extract useful information and store it in a database.

[0926] Step 3:

[0927] The server collects data on environmental changes. It uses satellite data and ground sensors to collect observations of earthquake clouds and ground changes. The server integrates this data and detects abnormal patterns.

[0928] Step 4:

[0929] The server preprocesses the collected data. First, it cleanses the data to remove noise and duplicate data. Next, it normalizes the data to unify data of different scales. This preprocessing makes it easier to input into the AI ​​model.

[0930] Step 5:

[0931] The server analyzes the data using an AI model. The preprocessed data is input into the AI ​​model, which then analyzes the current data against past earthquake data. The AI ​​model detects abnormal patterns and outputs a score indicating the likelihood of an earthquake occurring.

[0932] Step 6:

[0933] The server evaluates the analysis results. Based on the score output by the AI ​​model, it evaluates the reliability of the earthquake occurrence. Based on this evaluation result, it prepares to generate an earthquake forecast.

[0934] Step 7:

[0935] The server generates an earthquake forecast. Based on the evaluated analysis, it creates a detailed forecast of the likelihood of an earthquake occurring, including the probability of occurrence, what to watch out for, and recommended actions.

[0936] Step 8:

[0937] The server prepares the user notification and formats the generated forecast for transmission to the user's device, using push notifications or email.

[0938] Step 9:

[0939] The device receives and displays notifications. It displays notifications sent from the server immediately and uses alarm sounds or vibrations to attract the user's attention.

[0940] Step 10:

[0941] The user checks the notification and takes action. They check the earthquake forecast displayed on their device and make the necessary disaster prevention preparations, such as checking evacuation routes and emergency supplies.

[0942] Step 11:

[0943] Users provide feedback on the accuracy of the forecast and on improvements to the system. This feedback is used to improve the system in the future.

[0944] Example 1

[0945] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0946] Conventional earthquake forecasting systems have had issues in effectively aggregating data from multiple sources and making earthquake predictions in real time. In particular, there are limitations in preprocessing to improve data accuracy and analytical precision, and in detecting abnormal patterns. Furthermore, users are often not notified promptly and appropriately, making it difficult for them to take prompt disaster prevention action. To solve these problems, a system is needed that highly automates the entire process, from data collection and analysis to forecast generation and notification, achieving both accuracy and speed.

[0947] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0948] In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, an earthquake forecast generation means, a user notification means, an abnormal pattern detection means, an occurrence probability calculation means, and a detailed information generation means. This makes it possible to collect data from multiple information sources, perform advanced preprocessing, and generate an earthquake forecast through highly accurate analysis. Furthermore, by realizing prompt and accurate notification to the user, the user can take prompt disaster prevention action.

[0949] "Data collection means" refers to the means for obtaining necessary data from multiple sources.

[0950] The "preprocessing means" is a means for removing noise and redundancy from the collected data and converting it into a unified format.

[0951] The "data analysis means" is a means for performing analysis using preprocessed data to detect abnormal patterns.

[0952] The "earthquake forecast generating means" is a means for generating an earthquake forecast based on the results of data analysis.

[0953] The "user notification means" is a means for quickly notifying the user of the generated earthquake forecast.

[0954] The "abnormal pattern detection means" is a means for determining whether or not there is an abnormality in the current data through comparison with past data.

[0955] The "occurrence probability calculation means" is a means for quantifying the probability of an earthquake occurring based on the results of data analysis.

[0956] The "detailed information generating means" is a means for generating detailed information necessary for earthquake forecasting (probability of occurrence, phenomena to be aware of, disaster prevention actions, etc.).

[0957] "Means for obtaining seismic intensity meter data" refers to means for obtaining shaking data from seismic intensity meters installed throughout the country.

[0958] "Means for collecting animal behavior data" refers to means for collecting data on abnormal animal behavior.

[0959] "Means for collecting environmental change data" refers to means for collecting data on environmental changes such as earthquake clouds and ground deformation.

[0960] "Means for crawling data from social media" refers to means for automatically collecting posted data from social media.

[0961] "Means for acquiring satellite data" refers to means for acquiring data observed through a satellite.

[0962] "Means for removing noise and duplication from data" refers to means for removing outliers and duplicate data contained in collected data.

[0963] MODE FOR CARRYING OUT THE INVENTION

[0964] The present invention is a system for forecasting earthquakes, with a server, terminals, and users as the main actors. This system includes a data collection means, a preprocessing means, a data analysis means, an earthquake forecast generation means, a user notification means, an abnormal pattern detection means, an occurrence probability calculation means, and a detailed information generation means. This makes it possible to process information collected from various data sources and generate highly accurate earthquake forecasts.

[0965] Server Roles and Functions

[0966] Data collection

[0967] The server collects data from multiple sources, specifically seismic intensity data, animal behavior data, and environmental change data, and periodically stores the latest data.

[0968] Collection of seismic intensity data: The server obtains real-time shaking data from seismic intensity meters installed throughout the country via an API, for example, using the API of a public institution.

[0969] Collection of animal behavior data: The server uses crawling technology to collect information on abnormal animal behavior posted by local residents on social media. It also obtains data on dolphin strandings and abnormal catfish behavior from specialized databases.

[0970] Collection of environmental change data: The server uses the satellite data provider's API to obtain earthquake cloud observation data and environmental change data (such as ground deformation) from ground sensors.

[0971] Data Preprocessing

[0972] The server performs pre-processing on the collected data.

[0973] Noise removal: Detect outliers and missing values ​​and remove or impute them, e.g., by filling in missing values ​​with imputed means.

[0974] Data cleansing: Removing duplicate data and converting it into a consistent format, e.g. standardizing all time data to UTC.

[0975] Data normalization: Converting data from different sources into a uniform format, e.g., converting latitude and longitude data into a common coordinate system.

[0976] Data analysis

[0977] The server inputs the preprocessed data into the AI ​​model for analysis.

[0978] Generative AI model: Using historical and current earthquake data, we use a deep learning model trained on historical earthquake data to detect anomalous patterns.

[0979] Detecting abnormal patterns: Comparing new data with past patterns to determine whether there are any anomalies. For example, detecting a sudden change in seismic intensity data that matches animal behavior data.

[0980] Score calculation: As a result of the analysis, a score is calculated that indicates the possibility of an earthquake occurring. The score is expressed in a range from 0 to 100.

[0981] Earthquake forecast generation

[0982] The server generates an earthquake forecast based on the analysis results.

[0983] Forecast format: Generate a forecast based on the score, for example, "There is a 10% chance of an earthquake. Please make sure you are prepared."

[0984] Added detailed information: Not only the probability of occurrence, but also phenomena to watch out for (such as observation of earthquake clouds or abnormal animal behavior) and recommended disaster prevention actions.

[0985] User Notifications

[0986] The server notifies the generated earthquake forecast to the user's terminal.

[0987] Notification method: Users are notified by multiple methods, such as push notifications and email notifications. For example, push notifications are sent via smartphone apps.

[0988] Instant Notification: Earthquake forecasts are sent instantly, accompanied by an alarm sound and vibration to grab the user's attention.

[0989] Device roles and functions

[0990] Receive notifications

[0991] The device receives the earthquake forecast notification sent from the server, and the notification is displayed immediately, alerting the user with an alarm sound or vibration if necessary.

[0992] Information display

[0993] The device visually displays the received forecast information, including the probability of an earthquake occurring, phenomena to watch out for, and recommended disaster prevention actions.

[0994] User Roles

[0995] Notification confirmation

[0996] The user checks the earthquake forecast notification displayed on the device and takes steps to ensure the safety of themselves and their families based on the contents of the notification.

[0997] action

[0998] Based on the forecast, users can make necessary disaster prevention preparations, such as checking their water and food stockpiles and evacuation routes.

[0999] Specific examples

[1000] For example, consider the following observations in a certain area:

[1001] The seismometer detects an unusually small earthquake.

[1002] Local residents reported the "mass death of sardines" on social media.

[1003] Unusual earthquake clouds observed in satellite data.

[1004] The server immediately collects this data and performs data cleansing and normalization. The cleaned data is input into an AI model, where it is compared with past patterns and analyzed. The server calculates the likelihood of an earthquake occurring as a score and generates a forecast for that area. The generated forecast is immediately pushed to the device, informing the user that "There is a 10% chance of an earthquake occurring. Please make sure you are prepared." The user checks the notification and makes the necessary disaster prevention preparations. This allows users to maintain a high level of disaster prevention awareness on a daily basis.

[1005] Prompt Sentence Examples

[1006] "We have developed a new earthquake forecasting system. This system collects data from seismometers, animal behavior data, and environmental change data, and analyzes it using an AI model. It calculates the probability of an earthquake occurring as a score and notifies the user. Please tell us the processing steps of this system."

[1007] By implementing this aspect, the present invention provides a system that utilizes a variety of data to perform comprehensive and highly accurate earthquake forecasting.

[1008] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1009] Step 1: Data collection

[1010] The server collects the necessary data from multiple sources. The inputs to this step are seismometer data, animal behavior data, and environmental change data. The output is a collection of these data. Specifically, the server performs the following:

[1011] Collection of seismometer data: The server obtains shaking data (occurrence date and time, epicenter, seismic intensity) from the seismometer. For example, it obtains real-time data by calling an API.

[1012] Collection of animal behavior data: The server uses scraping technology to obtain data on abnormal animal behavior from social media and specialized databases.

[1013] Collection of environmental change data: The server acquires environmental change data (earthquake cloud observation results, ground change data) from satellite data providers and ground sensors.

[1014] Step 2: Data Preprocessing

[1015] The server performs pre-processing on the collected data. The input to this step is the output data from step 1. The output is the cleansed and normalized data. Specifically, the server:

[1016] Noise removal: Detect outliers and missing values ​​in the data and remove or impute them, for example by filling in missing values ​​with imputed means.

[1017] Data cleansing: Removing duplicate data and converting it into a consistent format, for example, standardizing all date and time data to UTC.

[1018] Data normalization: Standardizing data from different sources into the same format, for example, converting latitude and longitude data into a common coordinate system.

[1019] Step 3: Data analysis

[1020] The server performs analysis using the AI ​​model based on the preprocessed data. The input for this step is the output data from step 2. The output is the anomaly pattern detection results and an earthquake occurrence probability score. Specifically, the server performs the following:

[1021] Use generative AI models: Use historical and current earthquake data to detect anomalous patterns. Use deep learning models trained on historical earthquake data.

[1022] Detecting abnormal patterns: Comparing new data with past patterns to determine whether there are any anomalies. For example, detecting a sudden change in seismic intensity data that matches animal behavior data.

[1023] Score calculation: As a result of the analysis, a score is calculated that indicates the possibility of an earthquake occurring. The score is expressed in a range from 0 to 100.

[1024] Step 4: Earthquake forecast generation

[1025] The server generates an earthquake forecast based on the analysis results. The input to this step is the output score from step 3. The output is earthquake forecast information. Specifically, the server performs the following operations:

[1026] Forecast format: Generate forecast content based on the score, for example, "There is a 10% chance of an earthquake. Please be prepared."

[1027] Add detailed information: Include not only the probability of occurrence, but also phenomena to watch out for (such as observation of earthquake clouds or abnormal animal behavior) and recommended disaster prevention actions.

[1028] Step 5: User Notification

[1029] The server notifies the generated earthquake forecast to the user's terminal. The input of this step is the forecast information output in step 4. The output is the notification information displayed on the terminal. Specifically, the server performs the following operations:

[1030] Selection of notification method: Notify users through multiple methods, such as push notifications and email notifications. For example, send push notifications through a smartphone app.

[1031] Instant Notification: Earthquake forecasts are sent instantly, accompanied by an alarm sound and vibration to grab the user's attention.

[1032] Step 6: Check notifications and take action

[1033] The user checks the earthquake forecast notification displayed on the terminal. The input of this step is the notification information output in step 5. The output is the specific disaster prevention action the user will take. Specifically, the user will:

[1034] Confirm notification: The user confirms the notification content and understands the possibility of an earthquake occurring and the recommended actions.

[1035] Disaster Preparedness: Make necessary disaster preparedness preparations based on the notification, such as checking your water and food stockpiles and checking whether your furniture is securely fastened.

[1036] (Application example 1)

[1037] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1038] Current earthquake forecasting systems lack the means to detect signs of an impending earthquake and quickly notify users. As a result, users are sometimes slow to respond to an earthquake, making it difficult to minimize damage. There is also a need for technology that can integrate information from different data sources to generate highly accurate forecasts. Furthermore, there is no mechanism for specifically recommending disaster prevention actions, making it difficult to raise users' disaster prevention awareness.

[1039] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1040] In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, and a push notification means. This allows the server to integrate information collected from multiple data sources, generate earthquake forecasts in real time, and promptly notify users via push notifications. Furthermore, by recommending specific disaster prevention actions, the server can raise users' disaster prevention awareness and promote early response to earthquakes.

[1041] "Data collection means" refers to the means of collecting data from multiple sources necessary for earthquake forecasting, such as seismic intensity data, animal behavior data, and environmental change data.

[1042] The "preprocessing means" is a means for removing noise and redundant data from collected data and unifying data in different formats.

[1043] The "data analysis means" is a means of analyzing preprocessed data using an AI model to calculate a score indicating the possibility of an earthquake occurring.

[1044] The "earthquake forecast generating means" is a means for generating an earthquake forecast based on the analysis results by the data analysis means.

[1045] The "user notification means" is a means for transmitting the generated earthquake forecast to the user's terminal and notifying the user.

[1046] The "push notification means" is a means for immediately notifying the user's terminal of an earthquake forecast generated based on the analyzed information in real time.

[1047] The "means for acquiring seismic intensity meter data" refers to a means for acquiring real-time shaking data from a seismic intensity meter.

[1048] "Means for collecting animal behavior data" refers to means for collecting data on abnormal animal behavior.

[1049] "Means for collecting environmental change data" refers to means for collecting data on environmental changes from monitoring satellites and ground sensors.

[1050] "Means for cleansing collected data" refers to means for removing noise and redundant data from collected data to generate more accurate data.

[1051] "Means for normalizing data" refers to means for standardizing data collected in different formats and making it suitable for analysis.

[1052] "Means for calculating the possibility of an earthquake occurring based on the analysis results" refers to means for quantitatively assessing the possibility of an earthquake occurring based on the analyzed data.

[1053] The "means for generating and sending a push notification" is a means for generating a forecast notification based on the analysis results and sending it to the user's device.

[1054] The "means for recommending disaster prevention actions based on the forecast content" is a means for recommending appropriate disaster prevention actions to a user based on the generated earthquake forecast.

[1055] The present invention is an earthquake forecasting system that collects data, analyzes data, generates forecasts, and notifies users, mainly consisting of a server, terminals, and users. Specific embodiments of each element are described below.

[1056] Server Roles and Functions

[1057] Data collection

[1058] The server collects data from sources necessary for earthquake forecasting, such as seismometer data, animal behavior data, and environmental change data. Data collection scripts are created using programming languages ​​such as Python to periodically retrieve information.

[1059] Data Preprocessing

[1060] We will remove noise and duplicate data from the collected data and unify data in different formats using pandas, a Python data processing library.

[1061] Data analysis

[1062] The preprocessed data is analyzed using an AI model. The AI ​​model uses TensorFlow and PyTorch to correlate past earthquake data with current data and detect abnormal patterns from multiple perspectives. The analysis results are calculated as a score indicating the possibility of an earthquake occurring.

[1063] Earthquake forecast generation

[1064] The server generates an earthquake forecast based on the analysis results. The forecast is formatted as detailed information including the probability of occurrence and phenomena to watch out for. The forecast also includes a message encouraging users to take disaster prevention action.

[1065] User Notifications

[1066] The server sends the generated earthquake forecast to the user's device. The user is notified in the form of a push notification using Firebase Cloud Messaging (FCM). The notification includes the probability of occurrence and recommended actions.

[1067] Device roles and functions

[1068] Receive notifications

[1069] The device receives the earthquake forecast notification sent from the server immediately and notifies the user. The notification is displayed visually and can use an alarm sound or vibration.

[1070] Information display

[1071] The user's device visually displays the received forecast, including the probability of an earthquake occurring and specific disaster prevention recommendations.

[1072] User Roles

[1073] Notification confirmation

[1074] The user checks the earthquake forecast notification displayed on the device and takes steps to ensure the safety of themselves and their families based on the contents of the notification.

[1075] action

[1076] Based on the forecast, users can make necessary disaster prevention preparations, such as checking their water and food stockpiles and evacuation routes.

[1077] Specific examples

[1078] For example, if the following phenomena are observed simultaneously in the Kanto region:

[1079] The seismometer detects an unusually small earthquake.

[1080] Local residents report the "mass inaction of frogs" on social media.

[1081] Observing abnormal cloud movements using satellite data.

[1082] This information is immediately collected on a server, where it is cleansed and normalized. This clean data is then input into an AI model to generate analysis results. For example, if the analysis score is 0.15, a notification will be sent to the user's smartphone saying, "There is a 15% chance of an earthquake occurring. Please make sure you are prepared."

[1083] Example prompts for generative AI models

[1084] "Seismic intensity meters in the Kanto region have detected an unusually small earthquake, and reports of mass frog inactivity have been posted on social media. Furthermore, unusual cloud movement has been observed using satellite data. Please use this information to analyze the likelihood of an earthquake occurring and predict whether it will occur."

[1085] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1086] Step 1:

[1087] Data collection

[1088] The server collects seismic intensity data, animal behavior data, and environmental change data. The inputs used are real-time shaking data from the seismic intensity data, animal behavior reports from social media and specialized databases, and environmental change data from monitoring satellites and ground sensors. It periodically collects this data and runs a program that centrally aggregates it.

[1089] Step 2:

[1090] Data Preprocessing

[1091] The server preprocesses the collected data. The input data includes seismometer data, animal behavior data, and environmental change data. It cleanses noise and duplicate data from these data sets and unifies data in different formats using the pandas library. This results in a clean, unified dataset being output.

[1092] Step 3:

[1093] Data analysis

[1094] The server analyzes the preprocessed data. The input data includes cleansed and normalized seismic intensity data, animal behavior data, and environmental change data. This data is input into an AI model (using TensorFlow and PyTorch) to calculate a score indicating the likelihood of an earthquake occurring. The output is an analysis result indicating the likelihood of an earthquake occurring.

[1095] Step 4:

[1096] Earthquake forecast generation

[1097] The server generates an earthquake forecast based on the results of the data analysis. The input is the probability score of an earthquake occurring obtained through the analysis. Based on this score, the server formats the earthquake forecast text and disaster prevention action recommendations. This results in a detailed earthquake forecast and disaster prevention action recommendations being output.

[1098] Step 5:

[1099] User Notifications

[1100] The server sends the generated earthquake forecast to the user device. The input data includes the earthquake forecast and disaster prevention recommendations. This data is immediately sent to the user device as a push notification using Firebase Cloud Messaging (FCM). The output is the notification message received on the user device.

[1101] Step 6:

[1102] Notification reception (device side)

[1103] The user's device receives the notification sent from the server. The input is the received push notification message. The device notifies the user of the notification content visually and audibly. The output is an earthquake forecast notification displayed to the user.

[1104] Step 7:

[1105] Information display (terminal side)

[1106] Displays the earthquake forecast notification received by the device. The input data is the content of the received push notification. This is displayed visually so that the user can confirm the content. The output is a specific earthquake forecast and recommended disaster prevention actions displayed on the device screen.

[1107] Step 8:

[1108] Notification confirmation (user side)

[1109] The user checks the notification displayed on the device. The input is the earthquake forecast notification displayed on the device. Based on this notification, the user considers the actions necessary to ensure the safety of themselves and their families. The output is the user's disaster prevention actions.

[1110] Step 9:

[1111] Disaster prevention actions (user side)

[1112] The user makes specific disaster prevention preparations based on the notified forecast. The input data includes the notified earthquake forecast and recommended disaster prevention actions. This allows the user to check their water and food stockpiles, check evacuation routes, etc. The output is the specific disaster prevention actions the user should take.

[1113] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1114] This invention incorporates an emotion engine into an earthquake forecasting system to recognize the user's emotional state and customize notification content and disaster prevention action recommendations. This system operates with the server, terminals, and users as its main drivers, and not only improves the accuracy of earthquake forecasts but also provides responses that correspond to the user's psychological state.

[1115] Server Roles and Functions

[1116] Data collection

[1117] The server acquires information necessary for earthquake forecasting, including seismometer data, animal behavior data, and environmental change data. This data is collected periodically by the server and kept up to date.

[1118] Collection of seismic intensity data: The server collects detailed data such as epicenter, seismic intensity, and time of occurrence from seismic intensity meters across the country.

[1119] Collection of animal behavior data: The server collects information from social media and specialized databases about mass sardine deaths and abnormal pet behavior.

[1120] Collection of environmental change data: The server collects observations of earthquake clouds and ground changes using satellite data and ground sensors.

[1121] Data Preprocessing

[1122] The server cleanses and normalizes the collected data, which includes removing noise and duplicate data, and unifying data in different formats.

[1123] Data analysis

[1124] The server inputs the preprocessed data into an AI model, which compares it with past earthquake data and analyzes it. The AI ​​model detects abnormal patterns and outputs a score indicating the likelihood of an earthquake occurring.

[1125] Earthquake forecast generation

[1126] The server evaluates the analysis results and generates a forecast of the likelihood of an earthquake, including the probability of occurrence, what to watch out for, and recommended actions.

[1127] Evaluation by Emotion Engine

[1128] The server uses an emotion engine to analyze the user's emotional data, for example, assessing the user's stress level or anxiety level based on their past actions and comments.

[1129] User notification preparation

[1130] The server adjusts the notification content based on the emotion engine's evaluation. For example, if the user is feeling high stress, the notification content will be changed to a more gentle expression and a supportive message will be added to reduce anxiety.

[1131] Device roles and functions

[1132] Receive notifications

[1133] The device receives notifications sent from the server, and the notifications are displayed immediately and, if necessary, notify the user with an alarm sound or vibration.

[1134] Information display

[1135] The device visually displays the received forecast, including the probability of an earthquake occurring, factors to be aware of, and recommended disaster prevention actions.

[1136] Collecting Emotional Data

[1137] The device collects information about the user's daily behavior and input emotions and sends it to the server, where it is used for analysis by the emotion engine.

[1138] User Roles

[1139] Notification confirmation

[1140] The user checks the notification on the device, understands the earthquake forecast, and makes disaster prevention preparations based on the notification content.

[1141] action

[1142] Users can take necessary disaster prevention actions based on the notification, such as checking their water and food stockpiles and checking evacuation routes.

[1143] feedback

[1144] Users can provide feedback on the accuracy of forecasts and notifications via their devices, which is then sent to the server and used to improve the system.

[1145] Specific examples

[1146] Suppose a seismometer detects an abnormal small earthquake in a certain area, and a mass death of sardines is reported on social media. Furthermore, if an abnormal earthquake cloud is observed in satellite data, this data is collected on a server. The server cleans and normalizes this data, and inputs it into an AI model for analysis. Based on the analysis results, it is determined that there is a high probability of an earthquake occurring.

[1147] As a result, the server generates an earthquake forecast and simultaneously evaluates the user's emotional state using an emotion engine. For example, if the user is feeling very stressed, the server softens the notification and adds a support message to promote disaster preparedness. This forecast notification is then sent to the user's device, which displays the notification to attract the user's attention.

[1148] The user checks the notification and makes the necessary disaster prevention preparations. At that time, the user provides feedback to the server via their device, contributing to improvements in the system. In this way, the present invention improves the accuracy and reliability of earthquake forecasts and provides disaster prevention support that takes user emotions into consideration.

[1149] The processing flow will be explained below.

[1150] Step 1:

[1151] The server collects seismic intensity data, accessing the nationwide seismic intensity network in real time to obtain the latest shaking data, including the epicenter, seismic intensity, and time of occurrence.

[1152] Step 2:

[1153] The server collects animal behavior data, scanning social media and specialized databases for posts about mass sardine deaths and abnormal pet behavior, and using text mining techniques to extract useful information and store it in a database.

[1154] Step 3:

[1155] The server collects data on environmental changes, such as earthquake cloud observations and ground deformation information using satellite images and ground sensors. This data is integrated to detect abnormal patterns.

[1156] Step 4:

[1157] The server preprocesses the collected data. First, it cleanses the data to remove noise and duplicate data. Next, it normalizes the data and standardizes data in different formats. This preprocessing makes it easier to input into the AI ​​model.

[1158] Step 5:

[1159] The server inputs the preprocessed data into an AI model for data analysis, which compares past earthquake data with current data to detect abnormal patterns and output a score indicating the likelihood of an earthquake occurring.

[1160] Step 6:

[1161] The server evaluates the analysis results. Based on the score output by the AI ​​model, it evaluates the reliability of the earthquake occurrence. Based on the analysis results, it prepares earthquake forecasts.

[1162] Step 7:

[1163] The server generates an earthquake forecast based on the analysis results, which includes the probability of an earthquake occurring, phenomena to watch out for, and recommended disaster prevention actions.

[1164] Step 8:

[1165] The server uses an emotion engine to analyze the user's emotional data, and evaluates their stress and anxiety levels based on their past behavioral history and input emotional data.

[1166] Step 9:

[1167] The server customizes the notification content based on the analysis results of the emotion engine. If the user is feeling high stress, the forecast notification will be softened and a reassuring message will be added.

[1168] Step 10:

[1169] The server then sends the coordinated forecast notification to the user's device, which includes the possibility of an earthquake occurring, what phenomena to watch out for, and recommended disaster prevention actions.

[1170] Step 11:

[1171] The device receives notifications and displays them immediately, using an alarm sound or vibration to get the user's attention.

[1172] Step 12:

[1173] The user checks the earthquake forecast notification displayed on the device, understands the forecast content, and makes the necessary disaster prevention preparations based on the notification.

[1174] Step 13:

[1175] The user takes disaster prevention actions, such as making specific preparations such as checking water and food stockpiles and evacuation routes.

[1176] Step 14:

[1177] Users can provide feedback on the content of notifications and the accuracy of forecasts. By sending feedback to the server via their device, they can contribute to improving the system. This feedback will be used to improve the accuracy of future forecasts.

[1178] Example 2

[1179] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1180] Conventional earthquake forecasting systems have a certain degree of accuracy in predicting earthquake occurrences, but they lack the ability to provide notification content that takes into account the user's psychological state. As a result, when users are in situations where they feel high levels of stress or anxiety, it can be difficult to take appropriate disaster prevention actions. A system that solves this problem and allows users to calmly take disaster prevention actions is needed.

[1181] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1182] In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, an earthquake forecast generation means, a user notification means, an emotional state analysis means, and a means for adjusting the notification content based on the emotional state of the user, thereby making it possible to provide notification content that takes the psychological state of the user into consideration.

[1183] "Data collection means" refers to a device or process that collects various data necessary for earthquake forecasting.

[1184] A "pre-processing means" is a device or process that cleanses and normalizes collected data and converts it into a suitable format for analysis.

[1185] "Data analysis means" refers to a device or process that analyzes the possibility of earthquake occurrence based on pre-processed data.

[1186] "Earthquake forecast generating means" refers to a device or process that generates an earthquake forecast based on the results of data analysis.

[1187] The "user notification means" is a device or process that notifies the user of the generated earthquake forecast.

[1188] "Emotional state analysis means" refers to a device or process that analyzes the user's emotional data and assesses the level of stress or anxiety.

[1189] The "means for adjusting notification content based on the emotional state of the user" refers to a device or process that appropriately adjusts notification content for the user based on the results of the emotional state analysis.

[1190] This invention is a system that incorporates an emotion engine into an earthquake forecasting system to recognize the user's emotional state and customize notification content and disaster prevention action recommendations. This system operates with the server, terminals, and users as its main actors, and not only improves the accuracy of earthquake forecasts but also provides responses that correspond to the user's psychological state.

[1191] Server Roles and Functions

[1192] 1. Data collection methods:

[1193] The server collects data on seismic intensity meters, animal behavior, and environmental changes. Specifically, it obtains detailed data such as the epicenter, intensity, and time of occurrence from seismic intensity meters across the country, and collects information on mass sardine deaths and abnormal pet behavior from social media and specialized databases. It also obtains observation results of earthquake clouds and ground changes using satellite data and ground sensors.

[1194] 2. Pretreatment methods:

[1195] The server cleanses and normalizes the collected data, removing noise and duplicate data and unifying data in different formats.

[1196] 3. Data analysis methods:

[1197] The server inputs the preprocessed data into an AI model to analyze the likelihood of an earthquake occurring, using TensorFlow as the AI ​​model and comparing it with past earthquake data to detect abnormal patterns.

[1198] 4. Earthquake forecast generation method:

[1199] The server generates an earthquake forecast based on the analysis results, which includes the probability of occurrence, phenomena to watch out for, and recommended actions.

[1200] 5. Emotional state analysis method:

[1201] The server uses an emotion engine to analyze the user's emotional data, specifically assessing their stress level and anxiety based on their past behavior and social media posts.

[1202] 6. How to tailor notifications based on the user's emotional state:

[1203] The server adjusts the notification content based on the results of the emotional state analysis. For example, if the user is feeling high stress, the server changes the notification content to a calmer one and adds a supportive message to reduce anxiety.

[1204] Device roles and functions

[1205] 1. Receive notifications:

[1206] The device receives notifications sent from the server, and the notifications are displayed immediately and, if necessary, notify the user with an alarm sound or vibration.

[1207] 2. Information display:

[1208] The device visually displays the received forecast, including the probability of an earthquake occurring, precautions to take, and recommended disaster prevention actions.

[1209] 3. Collecting Emotional Data:

[1210] The device collects data on the user's daily behavior and emotions and sends it to a server. Specifically, it measures the user's stress level and analyzes the contents of their diary entries and social media posts.

[1211] User Roles

[1212] 1. Notification confirmation:

[1213] The user checks the notification on the device, understands the earthquake forecast, and makes the necessary disaster prevention preparations based on the forecast.

[1214] 2. Action:

[1215] Users can take necessary disaster prevention actions based on the notification, such as checking their water and food stockpiles and evacuation routes.

[1216] 3. Feedback:

[1217] Users can provide feedback on the accuracy of forecasts and notifications via their devices, which is then sent to the server and used to improve the system.

[1218] Specific examples

[1219] If a seismometer detects an abnormally small earthquake in a certain area and a mass death of sardines is reported on social media, the server collects this data. The server cleans and normalizes the data, then inputs it into an AI model for analysis. Based on the analysis results, it determines the likelihood of an earthquake occurring.

[1220] As a result, the server generates an earthquake forecast and simultaneously evaluates the user's emotional state using an emotion engine. For example, if the user is feeling very stressed, the notification's wording will be softened and a support message will be added to promote disaster prevention preparations. This forecast notification is sent to the user's device, which displays the notification to attract the user's attention. The user then checks the notification and takes the necessary disaster prevention preparations. At that time, the user provides feedback to the server via their device, contributing to system improvements.

[1221] Specific examples of prompts to input to generative AI models

[1222] "Explain how an earthquake forecasting system can change the wording of notifications depending on the user's emotional state."

[1223] "Please explain how the earthquake forecasting system works, using seismic intensity data, animal behavior data, and environmental change data."

[1224] "Please provide a concrete example of how an earthquake forecasting system incorporating an emotion engine can provide notifications to users."

[1225] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1226] Step 1:

[1227] The server periodically collects seismic intensity data, animal behavior data, and environmental change data. Input data includes detailed data such as epicenter, intensity, and time of occurrence obtained from seismic intensity meters across the country, information on mass sardine deaths and abnormal pet behavior collected from social media and specialized databases, and earthquake cloud observation results and ground change data obtained from satellite data and ground sensors. This data is stored in the server's database.

[1228] Step 2:

[1229] The server cleanses and normalizes the collected data. The input is the raw data collected in step 1. Specifically, it removes noise, reduces duplicate data, and unifies data in different formats. As a result, it outputs clean data suitable for analysis.

[1230] Step 3:

[1231] The server inputs the preprocessed data into the AI ​​model for analysis. The input is the data preprocessed in step 2. The AI ​​model (using TensorFlow, for example) compares the input data with past earthquake data to detect abnormal patterns. As a result of the analysis, it outputs a score indicating the likelihood of an earthquake occurring.

[1232] Step 4:

[1233] The server generates an earthquake forecast based on the analysis results. The input is the earthquake occurrence probability score obtained in step 3. The earthquake forecast includes the occurrence probability, phenomena to watch out for, and recommended actions. This forecast is sent to the user notification means.

[1234] Step 5:

[1235] The server uses an emotion engine to analyze the user's emotional data. The input is the user's past behavioral data and social media posts. Based on this data, the server evaluates the user's stress level and anxiety level. The results of the emotion analysis are output.

[1236] Step 6:

[1237] The server adjusts the notification content based on the results of the emotional state analysis. The inputs are the earthquake forecast from step 4 and the emotion analysis results from step 5. For high-stress users, the notification content is changed to gentler language such as "Please stay calm" and a support message to reduce anxiety is added. The adjusted notification content is output and sent to the user notification means.

[1238] Step 7:

[1239] The device receives the notification sent from the server. The input is the notification content adjusted in step 6. The notification is displayed immediately and notifies the user with an alarm sound or vibration if necessary. The notification content is displayed on the device.

[1240] Step 8:

[1241] The terminal visually displays the received notification content. The input is the notification content received in step 7. The visual display includes the probability of an earthquake occurring, points to be aware of, and recommended disaster prevention actions. Information is provided visually to the user.

[1242] Step 9:

[1243] The user checks the notification on the device and understands the earthquake forecast. The input is the notification content displayed in step 8. Based on the notification content, the user makes the necessary disaster prevention preparations. The user checks their water and food stockpiles, checks evacuation routes, etc.

[1244] Step 10:

[1245] Users provide feedback on forecast accuracy and notification content through their devices. The input is the user's feedback. The feedback is sent from the device to the server. The feedback reaches the server and is used to improve the system.

[1246] (Application example 2)

[1247] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1248] Earthquake forecasting systems are required not only to improve the accuracy of earthquake predictions, but also to customize notification content and disaster prevention action recommendations according to the user's emotional state. However, conventional systems do not take the user's emotional state into consideration when providing notifications, and are therefore unable to reduce anxiety and stress. Therefore, efforts are needed to reduce users' psychological stress and anxiety in addition to improving the accuracy of earthquake forecasts.

[1249] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes data collection means, preprocessing means, data analysis means, earthquake forecast generation means, emotion engine means, notification content customization means, and user notification means. This improves the accuracy of earthquake forecasts and enables customized notifications to be provided according to the user's emotional state, thereby reducing the user's stress and anxiety.

[1250] The "data collection means" is a device or program that has the function of acquiring various data necessary for earthquake forecasting (seismic intensity data, animal behavior data, environmental change data, user emotion data, etc.).

[1251] The "preprocessing means" is a device or program that has the function of cleansing and normalizing the collected data and processing it into a format suitable for analysis.

[1252] "Data analysis means" refers to a device or program that has the function of analyzing the probability of earthquake occurrence, etc., using an AI model based on preprocessed data.

[1253] The "earthquake forecast generating means" is a device or program that has the function of generating a forecast that takes into account the possibility of an earthquake occurring based on the analyzed data.

[1254] The "emotion engine means" is a device or program that has the function of analyzing the user's emotion data and evaluating the user's current psychological state.

[1255] The "notification content customization means" is a device or program having a function of appropriately adjusting the notification content in accordance with the emotional state of the user based on the evaluation result of the emotion engine means.

[1256] The "user notification means" is a device or program having a function for transmitting the generated notification content to the user.

[1257] The present invention provides a system for providing disaster prevention notifications that take into account the emotional state of a user in an earthquake forecasting system. The system includes a data collection means, a preprocessing means, a data analysis means, an earthquake forecast generation means, an emotion engine means, a notification content customization means, and a user notification means.

[1258] Server Roles and Functions

[1259] Data collection

[1260] The server collects data necessary for earthquake forecasting. This data includes seismic intensity data, animal behavior data, environmental change data, and user emotion data. For example, seismic intensity data is obtained from seismic intensity data collected from seismic intensity data collected nationwide, and animal behavior data is collected from specialized databases and social media. Environmental change data is obtained from satellite data and ground sensors, and emotion data is collected from user comments and actions.

[1261] Data Preprocessing

[1262] The server cleanses and normalizes the collected data, which includes removing noise and duplicate data and standardizing data in different formats. For example, seismic intensity data and emotion data are properly scaled using standardization techniques.

[1263] Data analysis

[1264] The server then inputs the preprocessed data into an AI model, which compares it with past earthquake data and analyzes it. The AI ​​model detects abnormal patterns and outputs a score indicating the likelihood of an earthquake occurring. For example, an earthquake prediction model or sentiment analysis model trained with Keras is used for this analysis.

[1265] Earthquake forecast generation

[1266] The server evaluates the analysis results and generates a forecast of the possibility of an earthquake occurring, including the probability of occurrence, phenomena to watch out for, and recommended actions, to help users make appropriate disaster prevention preparations.

[1267] Evaluation by Emotion Engine

[1268] The server uses an emotion engine to analyze the user's emotional data. For example, it evaluates the user's stress level and anxiety level based on their past actions and comments. This allows the server to tailor the content of notifications to suit the user's psychological state.

[1269] Customizing notification content

[1270] The server adjusts the notification content based on the emotion engine's evaluation results: if the user is experiencing high stress, the notification's wording will be softer and a supportive message will be added to reduce anxiety.

[1271] User Notifications

[1272] The server sends a customized notification to the user's device, which displays the notification. The user can then check the notification content and take necessary disaster prevention preparations.

[1273] Specific examples

[1274] For example, if a seismometer detects an unusual small earthquake in a certain area, reports of abnormal animal behavior on social media and earthquake cloud observations from satellite data are collected on a server. At the same time, the user's emotional data is also collected and analyzed. The server inputs this data into an AI model and analyzes the high probability of an earthquake occurring. Based on the results, the emotion engine then evaluates the user's current psychological state and creates a notification. For example, it generates a notification that reassures the user, saying, "Don't worry. The predicted probability of an earthquake is 30%. You are safe for now." This notification is then sent to the user's smartphone, where the user can check it and provide feedback if necessary.

[1275] Prompt Sentence Examples

[1276] This program takes the emotion data of user "12345" and combines it with earthquake forecast data to generate a notification. If the emotion score is high, the notification content will be changed to be gentle.

[1277] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1278] Step 1:

[1279] The server acquires the data necessary for earthquake forecasting. Specifically, it collects seismometer data, animal behavior data, environmental change data, and user emotion data from each data source. This includes acquiring data from APIs and scraping social media data. The input is the initial data from each data source, and the output is the raw data stored in the server.

[1280] Step 2:

[1281] The server cleanses and normalizes the collected data, specifically removing noise and duplicate data, completing incomplete data, standardizing formats, etc. The input is the raw data obtained in step 1, and the output is the cleansed, normalized, and organized data.

[1282] Step 3:

[1283] The server inputs the preprocessed data into the AI ​​model for analysis. Specifically, it compares it with past earthquake data and calculates the probability of an earthquake occurring as a score. The input is the organized data obtained in Step 2, and the output is a probability score for the occurrence of an earthquake.

[1284] Step 4:

[1285] The server generates a forecast of the possibility of an earthquake occurring. Specifically, it evaluates the analysis results of the AI ​​model and creates a forecast that includes the probability of occurrence, phenomena to watch out for, and recommended actions. The input is the earthquake prediction score, and the output is the forecast data that is notified to the user.

[1286] Step 5:

[1287] The server analyzes the user's emotion data using an emotion engine. Specifically, it uses an emotion analysis model to evaluate the stress level and anxiety level from the user's history and daily behavior. The input is the emotion data collected in step 1, and the output is the user's emotion score.

[1288] Step 6:

[1289] The server adjusts the notification content based on the emotion engine's evaluation results. Specifically, if the user's emotion score is high, the notification content is changed to a more gentle expression and a support message is added to promote disaster prevention preparation. The input is forecast data and emotion score, and the output is a customized notification message.

[1290] Step 7:

[1291] The server sends the customized notification to the user's device. Specifically, it pushes the generated notification message to the user's smartphone or other appropriate device. The input is the customized notification message, and the output is the notification message displayed on the user's device.

[1292] Step 8:

[1293] The user checks the notification displayed on the device and prepares for disaster. Specifically, the user takes necessary disaster prevention actions, such as checking water and food stockpiles and evacuation routes. The input is the notification content displayed on the device, and the output is the user's disaster prevention actions.

[1294] Step 9:

[1295] The user provides feedback to the server through the terminal. Specifically, the user sends their opinion on the notification content and forecast accuracy. The input is the user's feedback, and the output is the feedback data received by the server.

[1296] Step 10:

[1297] The server improves the system based on the received feedback. Specifically, it analyzes the feedback data, trains new predictive models, and improves notification content. The input is the feedback data, and the output is an improved system.

[1298] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1299] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1300] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1301] [Fourth embodiment]

[1302] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1303] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1304] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1305] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1306] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1307] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1308] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1309] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1310] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1311] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1312] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1313] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1314] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1315] The present invention is an earthquake forecasting system that collects data, analyzes data, generates forecasts, and notifies users, mainly consisting of a server, terminals, and users. Specific embodiments of each element are described below.

[1316] Server Roles and Functions

[1317] Data collection

[1318] The server collects data necessary for earthquake forecasting from multiple sources, specifically seismic intensity data, animal behavior data, and environmental change data. This collection is done periodically, and the latest data is always kept.

[1319] Collection of seismic intensity data: The server collects real-time shaking data from seismic intensity meters installed across the country. The data includes the date and time of occurrence, epicenter, and seismic intensity.

[1320] Animal behavior data collection: The server collects information on abnormal animal behavior from social media and specialized databases. Specifically, it analyzes reports of mass sardine deaths, strandings of dolphins, and abnormal behavior in catfish and pets.

[1321] Environmental change data collection: The server collects data on environmental changes from monitoring satellites and ground sensors, including seismic cloud observations and ground deformation data.

[1322] Data Preprocessing

[1323] The server preprocesses the collected data, specifically cleansing it by removing noise and duplicate data, and normalizing data in different formats.

[1324] Data analysis

[1325] The server then uses an AI model to analyze the preprocessed data. The AI ​​model correlates past earthquake data with current data and detects abnormal patterns from multiple perspectives. The analysis results are output as a score indicating the likelihood of an earthquake occurring.

[1326] Earthquake forecast generation

[1327] The server generates earthquake forecasts based on the analysis results, which are formatted as detailed information including the probability of occurrence and phenomena to watch out for.

[1328] User Notifications

[1329] The server then sends the generated earthquake forecast to the user's device via push notification, email, or other means to grab the user's attention.

[1330] Device roles and functions

[1331] Receive notifications

[1332] The device receives the earthquake forecast notification sent from the server, and the notification is displayed immediately, alerting the user with an alarm sound or vibration if necessary.

[1333] Information display

[1334] The device visually displays the received forecast information, including the probability of an earthquake occurring, phenomena to watch out for, and recommended disaster prevention actions.

[1335] User Roles

[1336] Notification confirmation

[1337] The user checks the earthquake forecast notification displayed on the device and takes steps to ensure the safety of themselves and their families based on the contents of the notification.

[1338] action

[1339] Based on the forecast, users can make necessary disaster prevention preparations, such as checking their water and food stockpiles and evacuation routes.

[1340] Specific examples

[1341] For example, consider the following observations in a certain area:

[1342] The seismometer detects an unusually small earthquake.

[1343] Local residents reported the "mass death of sardines" on social media.

[1344] Unusual earthquake clouds observed in satellite data.

[1345] The server immediately collects this data and performs data cleansing and normalization. The cleaned data is input into an AI model, where it is compared with past patterns and analyzed. The server calculates the likelihood of an earthquake occurring as a score and generates a forecast for that area. The generated forecast is immediately pushed to the device, informing the user that "There is a 10% chance of an earthquake occurring. Please make sure you are prepared." The user checks the notification and makes the necessary disaster prevention preparations. This allows users to maintain a high level of disaster prevention awareness on a daily basis.

[1346] In this way, the present invention provides a system for making comprehensive earthquake forecasts by utilizing a variety of data.

[1347] The processing flow will be explained below.

[1348] Step 1:

[1349] The server collects seismic intensity data. It accesses the nationwide seismic intensity network and obtains the latest shaking data. This data includes the epicenter, seismic intensity, and time of occurrence. The server performs this process periodically to maintain real-time accuracy.

[1350] Step 2:

[1351] The server collects animal behavior data. It monitors social media and animal observation databases, scanning for posts reporting mass sardine deaths or abnormal pet behavior. It uses text mining technology to extract useful information and store it in a database.

[1352] Step 3:

[1353] The server collects data on environmental changes. It uses satellite data and ground sensors to collect observations of earthquake clouds and ground changes. The server integrates this data and detects abnormal patterns.

[1354] Step 4:

[1355] The server preprocesses the collected data. First, it cleanses the data to remove noise and duplicate data. Next, it normalizes the data to unify data of different scales. This preprocessing makes it easier to input into the AI ​​model.

[1356] Step 5:

[1357] The server analyzes the data using an AI model. The preprocessed data is input into the AI ​​model, which then analyzes the current data against past earthquake data. The AI ​​model detects abnormal patterns and outputs a score indicating the likelihood of an earthquake occurring.

[1358] Step 6:

[1359] The server evaluates the analysis results. Based on the score output by the AI ​​model, it evaluates the reliability of the earthquake occurrence. Based on this evaluation result, it prepares to generate an earthquake forecast.

[1360] Step 7:

[1361] The server generates an earthquake forecast. Based on the evaluated analysis, it creates a detailed forecast of the likelihood of an earthquake occurring, including the probability of occurrence, what to watch out for, and recommended actions.

[1362] Step 8:

[1363] The server prepares the user notification and formats the generated forecast for transmission to the user's device, using push notifications or email.

[1364] Step 9:

[1365] The device receives and displays notifications. It displays notifications sent from the server immediately and uses alarm sounds or vibrations to attract the user's attention.

[1366] Step 10:

[1367] The user checks the notification and takes action. They check the earthquake forecast displayed on their device and make the necessary disaster prevention preparations, such as checking evacuation routes and emergency supplies.

[1368] Step 11:

[1369] Users provide feedback on the accuracy of the forecast and on improvements to the system. This feedback is used to improve the system in the future.

[1370] Example 1

[1371] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1372] Conventional earthquake forecasting systems have had issues in effectively aggregating data from multiple sources and making earthquake predictions in real time. In particular, there are limitations in preprocessing to improve data accuracy and analytical precision, and in detecting abnormal patterns. Furthermore, users are often not notified promptly and appropriately, making it difficult for them to take prompt disaster prevention action. To solve these problems, a system is needed that highly automates the entire process, from data collection and analysis to forecast generation and notification, achieving both accuracy and speed.

[1373] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1374] In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, an earthquake forecast generation means, a user notification means, an abnormal pattern detection means, an occurrence probability calculation means, and a detailed information generation means. This makes it possible to collect data from multiple information sources, perform advanced preprocessing, and generate an earthquake forecast through highly accurate analysis. Furthermore, by realizing prompt and accurate notification to the user, the user can take prompt disaster prevention action.

[1375] "Data collection means" refers to the means for obtaining necessary data from multiple sources.

[1376] The "preprocessing means" is a means for removing noise and redundancy from the collected data and converting it into a unified format.

[1377] The "data analysis means" is a means for performing analysis using preprocessed data to detect abnormal patterns.

[1378] The "earthquake forecast generating means" is a means for generating an earthquake forecast based on the results of data analysis.

[1379] The "user notification means" is a means for quickly notifying the user of the generated earthquake forecast.

[1380] The "abnormal pattern detection means" is a means for determining whether or not there is an abnormality in the current data through comparison with past data.

[1381] The "occurrence probability calculation means" is a means for quantifying the probability of an earthquake occurring based on the results of data analysis.

[1382] The "detailed information generating means" is a means for generating detailed information necessary for earthquake forecasting (probability of occurrence, phenomena to be aware of, disaster prevention actions, etc.).

[1383] "Means for obtaining seismic intensity meter data" refers to means for obtaining shaking data from seismic intensity meters installed throughout the country.

[1384] "Means for collecting animal behavior data" refers to means for collecting data on abnormal animal behavior.

[1385] "Means for collecting environmental change data" refers to means for collecting data on environmental changes such as earthquake clouds and ground deformation.

[1386] "Means for crawling data from social media" refers to means for automatically collecting posted data from social media.

[1387] "Means for acquiring satellite data" refers to means for acquiring data observed through a satellite.

[1388] "Means for removing noise and duplication from data" refers to means for removing outliers and duplicate data contained in collected data.

[1389] MODE FOR CARRYING OUT THE INVENTION

[1390] The present invention is a system for forecasting earthquakes, with a server, terminals, and users as the main actors. This system includes a data collection means, a preprocessing means, a data analysis means, an earthquake forecast generation means, a user notification means, an abnormal pattern detection means, an occurrence probability calculation means, and a detailed information generation means. This makes it possible to process information collected from various data sources and generate highly accurate earthquake forecasts.

[1391] Server Roles and Functions

[1392] Data collection

[1393] The server collects data from multiple sources, specifically seismic intensity data, animal behavior data, and environmental change data, and periodically stores the latest data.

[1394] Collection of seismic intensity data: The server obtains real-time shaking data from seismic intensity meters installed throughout the country via an API, for example, using the API of a public institution.

[1395] Collection of animal behavior data: The server uses crawling technology to collect information on abnormal animal behavior posted by local residents on social media. It also obtains data on dolphin strandings and abnormal catfish behavior from specialized databases.

[1396] Collection of environmental change data: The server uses the satellite data provider's API to obtain earthquake cloud observation data and environmental change data (such as ground deformation) from ground sensors.

[1397] Data Preprocessing

[1398] The server performs pre-processing on the collected data.

[1399] Noise removal: Detect outliers and missing values ​​and remove or impute them, e.g., by filling in missing values ​​with imputed means.

[1400] Data cleansing: Removing duplicate data and converting it into a consistent format, e.g. standardizing all time data to UTC.

[1401] Data normalization: Converting data from different sources into a uniform format, e.g., converting latitude and longitude data into a common coordinate system.

[1402] Data analysis

[1403] The server inputs the preprocessed data into the AI ​​model for analysis.

[1404] Generative AI model: Using historical and current earthquake data, we use a deep learning model trained on historical earthquake data to detect anomalous patterns.

[1405] Detecting abnormal patterns: Comparing new data with past patterns to determine whether there are any anomalies. For example, detecting a sudden change in seismic intensity data that matches animal behavior data.

[1406] Score calculation: As a result of the analysis, a score is calculated that indicates the possibility of an earthquake occurring. The score is expressed in a range from 0 to 100.

[1407] Earthquake forecast generation

[1408] The server generates an earthquake forecast based on the analysis results.

[1409] Forecast format: Generate a forecast based on the score, for example, "There is a 10% chance of an earthquake. Please make sure you are prepared."

[1410] Added detailed information: Not only the probability of occurrence, but also phenomena to watch out for (such as observation of earthquake clouds or abnormal animal behavior) and recommended disaster prevention actions.

[1411] User Notifications

[1412] The server notifies the generated earthquake forecast to the user's terminal.

[1413] Notification method: Users are notified by multiple methods, such as push notifications and email notifications. For example, push notifications are sent via smartphone apps.

[1414] Instant Notification: Earthquake forecasts are sent instantly, accompanied by an alarm sound and vibration to grab the user's attention.

[1415] Device roles and functions

[1416] Receive notifications

[1417] The device receives the earthquake forecast notification sent from the server, and the notification is displayed immediately, alerting the user with an alarm sound or vibration if necessary.

[1418] Information display

[1419] The device visually displays the received forecast information, including the probability of an earthquake occurring, phenomena to watch out for, and recommended disaster prevention actions.

[1420] User Roles

[1421] Notification confirmation

[1422] The user checks the earthquake forecast notification displayed on the device and takes steps to ensure the safety of themselves and their families based on the contents of the notification.

[1423] action

[1424] Based on the forecast, users can make necessary disaster prevention preparations, such as checking their water and food stockpiles and evacuation routes.

[1425] Specific examples

[1426] For example, consider the following observations in a certain area:

[1427] The seismometer detects an unusually small earthquake.

[1428] Local residents reported the "mass death of sardines" on social media.

[1429] Unusual earthquake clouds observed in satellite data.

[1430] The server immediately collects this data and performs data cleansing and normalization. The cleaned data is input into an AI model, where it is compared with past patterns and analyzed. The server calculates the likelihood of an earthquake occurring as a score and generates a forecast for that area. The generated forecast is immediately pushed to the device, informing the user that "There is a 10% chance of an earthquake occurring. Please make sure you are prepared." The user checks the notification and makes the necessary disaster prevention preparations. This allows users to maintain a high level of disaster prevention awareness on a daily basis.

[1431] Prompt Sentence Examples

[1432] "We have developed a new earthquake forecasting system. This system collects data from seismometers, animal behavior data, and environmental change data, and analyzes it using an AI model. It calculates the probability of an earthquake occurring as a score and notifies the user. Please tell us the processing steps of this system."

[1433] By implementing this aspect, the present invention provides a system that utilizes a variety of data to perform comprehensive and highly accurate earthquake forecasting.

[1434] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1435] Step 1: Data collection

[1436] The server collects the necessary data from multiple sources. The inputs to this step are seismometer data, animal behavior data, and environmental change data. The output is a collection of these data. Specifically, the server performs the following:

[1437] Collection of seismometer data: The server obtains shaking data (occurrence date and time, epicenter, seismic intensity) from the seismometer. For example, it obtains real-time data by calling an API.

[1438] Collection of animal behavior data: The server uses scraping technology to obtain data on abnormal animal behavior from social media and specialized databases.

[1439] Collection of environmental change data: The server acquires environmental change data (earthquake cloud observation results, ground change data) from satellite data providers and ground sensors.

[1440] Step 2: Data Preprocessing

[1441] The server performs pre-processing on the collected data. The input to this step is the output data from step 1. The output is the cleansed and normalized data. Specifically, the server:

[1442] Noise removal: Detect outliers and missing values ​​in the data and remove or impute them, for example by filling in missing values ​​with imputed means.

[1443] Data cleansing: Removing duplicate data and converting it into a consistent format, for example, standardizing all date and time data to UTC.

[1444] Data normalization: Standardizing data from different sources into the same format, for example, converting latitude and longitude data into a common coordinate system.

[1445] Step 3: Data analysis

[1446] The server performs analysis using the AI ​​model based on the preprocessed data. The input for this step is the output data from step 2. The output is the anomaly pattern detection results and an earthquake occurrence probability score. Specifically, the server performs the following:

[1447] Use generative AI models: Use historical and current earthquake data to detect anomalous patterns. Use deep learning models trained on historical earthquake data.

[1448] Detecting abnormal patterns: Comparing new data with past patterns to determine whether there are any anomalies. For example, detecting a sudden change in seismic intensity data that matches animal behavior data.

[1449] Score calculation: As a result of the analysis, a score is calculated that indicates the possibility of an earthquake occurring. The score is expressed in a range from 0 to 100.

[1450] Step 4: Earthquake forecast generation

[1451] The server generates an earthquake forecast based on the analysis results. The input to this step is the output score from step 3. The output is earthquake forecast information. Specifically, the server performs the following operations:

[1452] Forecast format: Generate forecast content based on the score, for example, "There is a 10% chance of an earthquake. Please be prepared."

[1453] Add detailed information: Include not only the probability of occurrence, but also phenomena to watch out for (such as observation of earthquake clouds or abnormal animal behavior) and recommended disaster prevention actions.

[1454] Step 5: User Notification

[1455] The server notifies the generated earthquake forecast to the user's terminal. The input of this step is the forecast information output in step 4. The output is the notification information displayed on the terminal. Specifically, the server performs the following operations:

[1456] Selection of notification method: Notify users through multiple methods, such as push notifications and email notifications. For example, send push notifications through a smartphone app.

[1457] Instant Notification: Earthquake forecasts are sent instantly, accompanied by an alarm sound and vibration to grab the user's attention.

[1458] Step 6: Check notifications and take action

[1459] The user checks the earthquake forecast notification displayed on the terminal. The input of this step is the notification information output in step 5. The output is the specific disaster prevention action the user will take. Specifically, the user will:

[1460] Confirm notification: The user confirms the notification content and understands the possibility of an earthquake occurring and the recommended actions.

[1461] Disaster Preparedness: Make necessary disaster preparedness preparations based on the notification, such as checking your water and food stockpiles and checking whether your furniture is securely fastened.

[1462] (Application example 1)

[1463] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1464] Current earthquake forecasting systems lack the means to detect signs of an impending earthquake and quickly notify users. As a result, users are sometimes slow to respond to an earthquake, making it difficult to minimize damage. There is also a need for technology that can integrate information from different data sources to generate highly accurate forecasts. Furthermore, there is no mechanism for specifically recommending disaster prevention actions, making it difficult to raise users' disaster prevention awareness.

[1465] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1466] In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, and a push notification means. This allows the server to integrate information collected from multiple data sources, generate earthquake forecasts in real time, and promptly notify users via push notifications. Furthermore, by recommending specific disaster prevention actions, the server can raise users' disaster prevention awareness and promote early response to earthquakes.

[1467] "Data collection means" refers to the means of collecting data from multiple sources necessary for earthquake forecasting, such as seismic intensity data, animal behavior data, and environmental change data.

[1468] The "preprocessing means" is a means for removing noise and redundant data from collected data and unifying data in different formats.

[1469] The "data analysis means" is a means of analyzing preprocessed data using an AI model to calculate a score indicating the possibility of an earthquake occurring.

[1470] The "earthquake forecast generating means" is a means for generating an earthquake forecast based on the analysis results by the data analysis means.

[1471] The "user notification means" is a means for transmitting the generated earthquake forecast to the user's terminal and notifying the user.

[1472] The "push notification means" is a means for immediately notifying the user's terminal of an earthquake forecast generated based on the analyzed information in real time.

[1473] The "means for acquiring seismic intensity meter data" refers to a means for acquiring real-time shaking data from a seismic intensity meter.

[1474] "Means for collecting animal behavior data" refers to means for collecting data on abnormal animal behavior.

[1475] "Means for collecting environmental change data" refers to means for collecting data on environmental changes from monitoring satellites and ground sensors.

[1476] "Means for cleansing collected data" refers to means for removing noise and redundant data from collected data to generate more accurate data.

[1477] "Means for normalizing data" refers to means for standardizing data collected in different formats and making it suitable for analysis.

[1478] "Means for calculating the possibility of an earthquake occurring based on the analysis results" refers to means for quantitatively assessing the possibility of an earthquake occurring based on the analyzed data.

[1479] The "means for generating and sending a push notification" is a means for generating a forecast notification based on the analysis results and sending it to the user's device.

[1480] The "means for recommending disaster prevention actions based on the forecast content" is a means for recommending appropriate disaster prevention actions to a user based on the generated earthquake forecast.

[1481] The present invention is an earthquake forecasting system that collects data, analyzes data, generates forecasts, and notifies users, mainly consisting of a server, terminals, and users. Specific embodiments of each element are described below.

[1482] Server Roles and Functions

[1483] Data collection

[1484] The server collects data from sources necessary for earthquake forecasting, such as seismometer data, animal behavior data, and environmental change data. Data collection scripts are created using programming languages ​​such as Python to periodically retrieve information.

[1485] Data Preprocessing

[1486] We will remove noise and duplicate data from the collected data and unify data in different formats using pandas, a Python data processing library.

[1487] Data analysis

[1488] The preprocessed data is analyzed using an AI model. The AI ​​model uses TensorFlow and PyTorch to correlate past earthquake data with current data and detect abnormal patterns from multiple perspectives. The analysis results are calculated as a score indicating the possibility of an earthquake occurring.

[1489] Earthquake forecast generation

[1490] The server generates an earthquake forecast based on the analysis results. The forecast is formatted as detailed information including the probability of occurrence and phenomena to watch out for. The forecast also includes a message encouraging users to take disaster prevention action.

[1491] User Notifications

[1492] The server sends the generated earthquake forecast to the user's device. The user is notified in the form of a push notification using Firebase Cloud Messaging (FCM). The notification includes the probability of occurrence and recommended actions.

[1493] Device roles and functions

[1494] Receive notifications

[1495] The device receives the earthquake forecast notification sent from the server immediately and notifies the user. The notification is displayed visually and can use an alarm sound or vibration.

[1496] Information display

[1497] The user's device visually displays the received forecast, including the probability of an earthquake occurring and specific disaster prevention recommendations.

[1498] User Roles

[1499] Notification confirmation

[1500] The user checks the earthquake forecast notification displayed on the device and takes steps to ensure the safety of themselves and their families based on the contents of the notification.

[1501] action

[1502] Based on the forecast, users can make necessary disaster prevention preparations, such as checking their water and food stockpiles and evacuation routes.

[1503] Specific examples

[1504] For example, if the following phenomena are observed simultaneously in the Kanto region:

[1505] The seismometer detects an unusually small earthquake.

[1506] Local residents report the "mass inaction of frogs" on social media.

[1507] Observing abnormal cloud movements using satellite data.

[1508] This information is immediately collected on a server, where it is cleansed and normalized. This clean data is then input into an AI model to generate analysis results. For example, if the analysis score is 0.15, a notification will be sent to the user's smartphone saying, "There is a 15% chance of an earthquake occurring. Please make sure you are prepared."

[1509] Example prompts for generative AI models

[1510] "Seismic intensity meters in the Kanto region have detected an unusually small earthquake, and reports of mass frog inactivity have been posted on social media. Furthermore, unusual cloud movement has been observed using satellite data. Please use this information to analyze the likelihood of an earthquake occurring and predict whether it will occur."

[1511] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1512] Step 1:

[1513] Data collection

[1514] The server collects seismic intensity data, animal behavior data, and environmental change data. The inputs used are real-time shaking data from the seismic intensity data, animal behavior reports from social media and specialized databases, and environmental change data from monitoring satellites and ground sensors. It periodically collects this data and runs a program that centrally aggregates it.

[1515] Step 2:

[1516] Data Preprocessing

[1517] The server preprocesses the collected data. The input data includes seismometer data, animal behavior data, and environmental change data. It cleanses noise and duplicate data from these data sets and unifies data in different formats using the pandas library. This results in a clean, unified dataset being output.

[1518] Step 3:

[1519] Data analysis

[1520] The server analyzes the preprocessed data. The input data includes cleansed and normalized seismic intensity data, animal behavior data, and environmental change data. This data is input into an AI model (using TensorFlow and PyTorch) to calculate a score indicating the likelihood of an earthquake occurring. The output is an analysis result indicating the likelihood of an earthquake occurring.

[1521] Step 4:

[1522] Earthquake forecast generation

[1523] The server generates an earthquake forecast based on the results of the data analysis. The input is the probability score of an earthquake occurring obtained through the analysis. Based on this score, the server formats the earthquake forecast text and disaster prevention action recommendations. This results in a detailed earthquake forecast and disaster prevention action recommendations being output.

[1524] Step 5:

[1525] User Notifications

[1526] The server sends the generated earthquake forecast to the user device. The input data includes the earthquake forecast and disaster prevention recommendations. This data is immediately sent to the user device as a push notification using Firebase Cloud Messaging (FCM). The output is the notification message received on the user device.

[1527] Step 6:

[1528] Notification reception (device side)

[1529] The user's device receives the notification sent from the server. The input is the received push notification message. The device notifies the user of the notification content visually and audibly. The output is an earthquake forecast notification displayed to the user.

[1530] Step 7:

[1531] Information display (terminal side)

[1532] Displays the earthquake forecast notification received by the device. The input data is the content of the received push notification. This is displayed visually so that the user can confirm the content. The output is a specific earthquake forecast and recommended disaster prevention actions displayed on the device screen.

[1533] Step 8:

[1534] Notification confirmation (user side)

[1535] The user checks the notification displayed on the device. The input is the earthquake forecast notification displayed on the device. Based on this notification, the user considers the actions necessary to ensure the safety of themselves and their families. The output is the user's disaster prevention actions.

[1536] Step 9:

[1537] Disaster prevention actions (user side)

[1538] The user makes specific disaster prevention preparations based on the notified forecast. The input data includes the notified earthquake forecast and recommended disaster prevention actions. This allows the user to check their water and food stockpiles, check evacuation routes, etc. The output is the specific disaster prevention actions the user should take.

[1539] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1540] This invention incorporates an emotion engine into an earthquake forecasting system to recognize the user's emotional state and customize notification content and disaster prevention action recommendations. This system operates with the server, terminals, and users as its main drivers, and not only improves the accuracy of earthquake forecasts but also provides responses that correspond to the user's psychological state.

[1541] Server Roles and Functions

[1542] Data collection

[1543] The server acquires information necessary for earthquake forecasting, including seismometer data, animal behavior data, and environmental change data. This data is collected periodically by the server and kept up to date.

[1544] Collection of seismic intensity data: The server collects detailed data such as epicenter, seismic intensity, and time of occurrence from seismic intensity meters across the country.

[1545] Collection of animal behavior data: The server collects information from social media and specialized databases about mass sardine deaths and abnormal pet behavior.

[1546] Collection of environmental change data: The server collects observations of earthquake clouds and ground changes using satellite data and ground sensors.

[1547] Data Preprocessing

[1548] The server cleanses and normalizes the collected data, which includes removing noise and duplicate data, and unifying data in different formats.

[1549] Data analysis

[1550] The server inputs the preprocessed data into an AI model, which compares it with past earthquake data and analyzes it. The AI ​​model detects abnormal patterns and outputs a score indicating the likelihood of an earthquake occurring.

[1551] Earthquake forecast generation

[1552] The server evaluates the analysis results and generates a forecast of the likelihood of an earthquake, including the probability of occurrence, what to watch out for, and recommended actions.

[1553] Evaluation by Emotion Engine

[1554] The server uses an emotion engine to analyze the user's emotional data, for example, assessing the user's stress level or anxiety level based on their past actions and comments.

[1555] User notification preparation

[1556] The server adjusts the notification content based on the emotion engine's evaluation. For example, if the user is feeling high stress, the notification content will be changed to a more gentle expression and a supportive message will be added to reduce anxiety.

[1557] Device roles and functions

[1558] Receive notifications

[1559] The device receives notifications sent from the server, and the notifications are displayed immediately and, if necessary, notify the user with an alarm sound or vibration.

[1560] Information display

[1561] The device visually displays the received forecast, including the probability of an earthquake occurring, factors to be aware of, and recommended disaster prevention actions.

[1562] Collecting Emotional Data

[1563] The device collects information about the user's daily behavior and input emotions and sends it to the server, where it is used for analysis by the emotion engine.

[1564] User Roles

[1565] Notification confirmation

[1566] The user checks the notification on the device, understands the earthquake forecast, and makes disaster prevention preparations based on the notification content.

[1567] action

[1568] Users can take necessary disaster prevention actions based on the notification, such as checking their water and food stockpiles and checking evacuation routes.

[1569] feedback

[1570] Users can provide feedback on the accuracy of forecasts and notifications via their devices, which is then sent to the server and used to improve the system.

[1571] Specific examples

[1572] Suppose a seismometer detects an abnormal small earthquake in a certain area, and a mass death of sardines is reported on social media. Furthermore, if an abnormal earthquake cloud is observed in satellite data, this data is collected on a server. The server cleans and normalizes this data, and inputs it into an AI model for analysis. Based on the analysis results, it is determined that there is a high probability of an earthquake occurring.

[1573] As a result, the server generates an earthquake forecast and simultaneously evaluates the user's emotional state using an emotion engine. For example, if the user is feeling very stressed, the server softens the notification and adds a support message to promote disaster preparedness. This forecast notification is then sent to the user's device, which displays the notification to attract the user's attention.

[1574] The user checks the notification and makes the necessary disaster prevention preparations. At that time, the user provides feedback to the server via their device, contributing to improvements in the system. In this way, the present invention improves the accuracy and reliability of earthquake forecasts and provides disaster prevention support that takes user emotions into consideration.

[1575] The processing flow will be explained below.

[1576] Step 1:

[1577] The server collects seismic intensity data, accessing the nationwide seismic intensity network in real time to obtain the latest shaking data, including the epicenter, seismic intensity, and time of occurrence.

[1578] Step 2:

[1579] The server collects animal behavior data, scanning social media and specialized databases for posts about mass sardine deaths and abnormal pet behavior, and using text mining techniques to extract useful information and store it in a database.

[1580] Step 3:

[1581] The server collects data on environmental changes, such as earthquake cloud observations and ground deformation information using satellite images and ground sensors. This data is integrated to detect abnormal patterns.

[1582] Step 4:

[1583] The server preprocesses the collected data. First, it cleanses the data to remove noise and duplicate data. Next, it normalizes the data and standardizes data in different formats. This preprocessing makes it easier to input into the AI ​​model.

[1584] Step 5:

[1585] The server inputs the preprocessed data into an AI model for data analysis, which compares past earthquake data with current data to detect abnormal patterns and output a score indicating the likelihood of an earthquake occurring.

[1586] Step 6:

[1587] The server evaluates the analysis results. Based on the score output by the AI ​​model, it evaluates the reliability of the earthquake occurrence. Based on the analysis results, it prepares earthquake forecasts.

[1588] Step 7:

[1589] The server generates an earthquake forecast based on the analysis results, which includes the probability of an earthquake occurring, phenomena to watch out for, and recommended disaster prevention actions.

[1590] Step 8:

[1591] The server uses an emotion engine to analyze the user's emotional data, and evaluates their stress and anxiety levels based on their past behavioral history and input emotional data.

[1592] Step 9:

[1593] The server customizes the notification content based on the analysis results of the emotion engine. If the user is feeling high stress, the forecast notification will be softened and a reassuring message will be added.

[1594] Step 10:

[1595] The server then sends the coordinated forecast notification to the user's device, which includes the possibility of an earthquake occurring, what phenomena to watch out for, and recommended disaster prevention actions.

[1596] Step 11:

[1597] The device receives notifications and displays them immediately, using an alarm sound or vibration to get the user's attention.

[1598] Step 12:

[1599] The user checks the earthquake forecast notification displayed on the device, understands the forecast content, and makes the necessary disaster prevention preparations based on the notification.

[1600] Step 13:

[1601] The user takes disaster prevention actions, such as making specific preparations such as checking water and food stockpiles and evacuation routes.

[1602] Step 14:

[1603] Users can provide feedback on the content of notifications and the accuracy of forecasts. By sending feedback to the server via their device, they can contribute to improving the system. This feedback will be used to improve the accuracy of future forecasts.

[1604] Example 2

[1605] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1606] Conventional earthquake forecasting systems have a certain degree of accuracy in predicting earthquake occurrences, but they lack the ability to provide notification content that takes into account the user's psychological state. As a result, when users are in situations where they feel high levels of stress or anxiety, it can be difficult to take appropriate disaster prevention actions. A system that solves this problem and allows users to calmly take disaster prevention actions is needed.

[1607] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1608] In this invention, the server includes a data collection means, a preprocessing means, a data analysis means, an earthquake forecast generation means, a user notification means, an emotional state analysis means, and a means for adjusting the notification content based on the emotional state of the user, thereby making it possible to provide notification content that takes the psychological state of the user into consideration.

[1609] "Data collection means" refers to a device or process that collects various data necessary for earthquake forecasting.

[1610] A "pre-processing means" is a device or process that cleanses and normalizes collected data and converts it into a suitable format for analysis.

[1611] "Data analysis means" refers to a device or process that analyzes the possibility of earthquake occurrence based on pre-processed data.

[1612] "Earthquake forecast generating means" refers to a device or process that generates an earthquake forecast based on the results of data analysis.

[1613] The "user notification means" is a device or process that notifies the user of the generated earthquake forecast.

[1614] "Emotional state analysis means" refers to a device or process that analyzes the user's emotional data and assesses the level of stress or anxiety.

[1615] The "means for adjusting notification content based on the emotional state of the user" refers to a device or process that appropriately adjusts notification content for the user based on the results of the emotional state analysis.

[1616] This invention is a system that incorporates an emotion engine into an earthquake forecasting system to recognize the user's emotional state and customize notification content and disaster prevention action recommendations. This system operates with the server, terminals, and users as its main actors, and not only improves the accuracy of earthquake forecasts but also provides responses that correspond to the user's psychological state.

[1617] Server Roles and Functions

[1618] 1. Data collection methods:

[1619] The server collects data on seismic intensity meters, animal behavior, and environmental changes. Specifically, it obtains detailed data such as the epicenter, intensity, and time of occurrence from seismic intensity meters across the country, and collects information on mass sardine deaths and abnormal pet behavior from social media and specialized databases. It also obtains observation results of earthquake clouds and ground changes using satellite data and ground sensors.

[1620] 2. Pretreatment methods:

[1621] The server cleanses and normalizes the collected data, removing noise and duplicate data and unifying data in different formats.

[1622] 3. Data analysis methods:

[1623] The server inputs the preprocessed data into an AI model to analyze the likelihood of an earthquake occurring, using TensorFlow as the AI ​​model and comparing it with past earthquake data to detect abnormal patterns.

[1624] 4. Earthquake forecast generation method:

[1625] The server generates an earthquake forecast based on the analysis results, which includes the probability of occurrence, phenomena to watch out for, and recommended actions.

[1626] 5. Emotional state analysis method:

[1627] The server uses an emotion engine to analyze the user's emotional data, specifically assessing their stress and anxiety levels based on their past behavior and social media posts.

[1628] 6. How to tailor notifications based on the user's emotional state:

[1629] The server adjusts the notification content based on the results of the emotional state analysis. For example, if the user is feeling high stress, the server changes the notification content to a calmer one and adds a supportive message to reduce anxiety.

[1630] Device roles and functions

[1631] 1. Receive notifications:

[1632] The device receives notifications sent from the server, and the notifications are displayed immediately and, if necessary, notify the user with an alarm sound or vibration.

[1633] 2. Information display:

[1634] The device visually displays the received forecast, including the probability of an earthquake occurring, precautions to take, and recommended disaster prevention actions.

[1635] 3. Collecting Emotional Data:

[1636] The device collects data on the user's daily behavior and emotions and sends it to a server. Specifically, it measures the user's stress level and analyzes the contents of their diary entries and social media posts.

[1637] User Roles

[1638] 1. Notification confirmation:

[1639] The user checks the notification on the device, understands the earthquake forecast, and makes the necessary disaster prevention preparations based on the forecast.

[1640] 2. Action:

[1641] Users can take necessary disaster prevention actions based on the notification, such as checking their water and food stockpiles and evacuation routes.

[1642] 3. Feedback:

[1643] Users can provide feedback on the accuracy of forecasts and notifications via their devices, which is then sent to the server and used to improve the system.

[1644] Specific examples

[1645] If a seismometer detects an abnormally small earthquake in a certain area and a mass death of sardines is reported on social media, the server collects this data. The server cleans and normalizes the data, then inputs it into an AI model for analysis. Based on the analysis results, it determines the likelihood of an earthquake occurring.

[1646] As a result, the server generates an earthquake forecast and simultaneously evaluates the user's emotional state using an emotion engine. For example, if the user is feeling very stressed, the notification's wording will be softened and a support message will be added to promote disaster prevention preparations. This forecast notification is sent to the user's device, which displays the notification to attract the user's attention. The user then checks the notification and takes the necessary disaster prevention preparations. At that time, the user provides feedback to the server via their device, contributing to improvements in the system.

[1647] Specific examples of prompts to input to generative AI models

[1648] "Explain how an earthquake forecasting system can change the wording of notifications depending on the user's emotional state."

[1649] "Please explain how the earthquake forecasting system works, using seismic intensity data, animal behavior data, and environmental change data."

[1650] "Please provide a concrete example of how an earthquake forecasting system incorporating an emotion engine can provide notifications to users."

[1651] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1652] Step 1:

[1653] The server periodically collects seismic intensity data, animal behavior data, and environmental change data. Input data includes detailed data such as epicenter, intensity, and time of occurrence obtained from seismic intensity meters across the country, information on mass sardine deaths and abnormal pet behavior collected from social media and specialized databases, and earthquake cloud observation results and ground change data obtained from satellite data and ground sensors. This data is stored in the server's database.

[1654] Step 2:

[1655] The server cleanses and normalizes the collected data. The input is the raw data collected in step 1. Specifically, it removes noise, reduces duplicate data, and unifies data in different formats. As a result, it outputs clean data suitable for analysis.

[1656] Step 3:

[1657] The server inputs the preprocessed data into the AI ​​model for analysis. The input is the data preprocessed in step 2. The AI ​​model (using TensorFlow, for example) compares the input data with past earthquake data to detect abnormal patterns. As a result of the analysis, it outputs a score indicating the likelihood of an earthquake occurring.

[1658] Step 4:

[1659] The server generates an earthquake forecast based on the analysis results. The input is the earthquake occurrence probability score obtained in step 3. The earthquake forecast includes the occurrence probability, phenomena to watch out for, and recommended actions. This forecast is sent to the user notification means.

[1660] Step 5:

[1661] The server uses an emotion engine to analyze the user's emotional data. The input is the user's past behavioral data and social media posts. Based on this data, the server evaluates the user's stress level and anxiety level. The results of the emotion analysis are output.

[1662] Step 6:

[1663] The server adjusts the notification content based on the results of the emotional state analysis. The inputs are the earthquake forecast from step 4 and the emotion analysis results from step 5. For high-stress users, the notification content is changed to gentler language such as "Please stay calm" and a support message to reduce anxiety is added. The adjusted notification content is output and sent to the user notification means.

[1664] Step 7:

[1665] The device receives the notification sent from the server. The input is the notification content adjusted in step 6. The notification is displayed immediately and notifies the user with an alarm sound or vibration if necessary. The notification content is displayed on the device.

[1666] Step 8:

[1667] The terminal visually displays the received notification content. The input is the notification content received in step 7. The visual display includes the probability of an earthquake occurring, points to be aware of, and recommended disaster prevention actions. Information is provided visually to the user.

[1668] Step 9:

[1669] The user checks the notification on the device and understands the earthquake forecast. The input is the notification content displayed in step 8. Based on the notification content, the user makes the necessary disaster prevention preparations. The user checks their water and food stockpiles, checks evacuation routes, etc.

[1670] Step 10:

[1671] Users provide feedback on forecast accuracy and notification content through their devices. The input is the user's feedback. The feedback is sent from the device to the server. The feedback reaches the server and is used to improve the system.

[1672] (Application example 2)

[1673] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1674] Earthquake forecasting systems are required not only to improve the accuracy of earthquake predictions, but also to customize notification content and disaster prevention action recommendations according to the user's emotional state. However, conventional systems do not take the user's emotional state into consideration when providing notifications, and are therefore unable to reduce anxiety and stress. Therefore, efforts are needed to reduce users' psychological stress and anxiety in addition to improving the accuracy of earthquake forecasts.

[1675] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes data collection means, preprocessing means, data analysis means, earthquake forecast generation means, emotion engine means, notification content customization means, and user notification means. This improves the accuracy of earthquake forecasts and enables customized notifications to be provided according to the user's emotional state, thereby reducing the user's stress and anxiety.

[1676] The "data collection means" is a device or program that has the function of acquiring various data necessary for earthquake forecasting (seismic intensity data, animal behavior data, environmental change data, user emotion data, etc.).

[1677] The "preprocessing means" is a device or program that has the function of cleansing and normalizing the collected data and processing it into a format suitable for analysis.

[1678] "Data analysis means" refers to a device or program that has the function of analyzing the probability of earthquake occurrence, etc., using an AI model based on preprocessed data.

[1679] The "earthquake forecast generating means" is a device or program that has the function of generating a forecast that takes into account the possibility of an earthquake occurring based on the analyzed data.

[1680] The "emotion engine means" is a device or program that has the function of analyzing the user's emotion data and evaluating the user's current psychological state.

[1681] The "notification content customization means" is a device or program having a function of appropriately adjusting the notification content in accordance with the emotional state of the user based on the evaluation result of the emotion engine means.

[1682] The "user notification means" is a device or program having a function for transmitting the generated notification content to the user.

[1683] The present invention provides a system for providing disaster prevention notifications that take into account the emotional state of a user in an earthquake forecasting system. The system includes a data collection means, a preprocessing means, a data analysis means, an earthquake forecast generation means, an emotion engine means, a notification content customization means, and a user notification means.

[1684] Server Roles and Functions

[1685] Data collection

[1686] The server collects data necessary for earthquake forecasting. This data includes seismic intensity data, animal behavior data, environmental change data, and user emotion data. For example, seismic intensity data is obtained from seismic intensity data collected from seismic intensity data collected nationwide, and animal behavior data is collected from specialized databases and social media. Environmental change data is obtained from satellite data and ground sensors, and emotion data is collected from user comments and actions.

[1687] Data Preprocessing

[1688] The server cleanses and normalizes the collected data, which includes removing noise and duplicate data and standardizing data in different formats. For example, seismometer data and emotion data are properly scaled using standardization techniques.

[1689] Data analysis

[1690] The server then inputs the preprocessed data into an AI model, which compares it with past earthquake data and analyzes it. The AI ​​model detects abnormal patterns and outputs a score indicating the likelihood of an earthquake occurring. For example, an earthquake prediction model or sentiment analysis model trained with Keras is used for this analysis.

[1691] Earthquake forecast generation

[1692] The server evaluates the analysis results and generates a forecast of the possibility of an earthquake occurring, including the probability of occurrence, phenomena to watch out for, and recommended actions, to help users make appropriate disaster prevention preparations.

[1693] Evaluation by Emotion Engine

[1694] The server uses an emotion engine to analyze the user's emotional data. For example, it evaluates the user's stress level and anxiety level based on their past actions and comments. This allows it to tailor the content of notifications to suit the user's psychological state.

[1695] Customizing notification content

[1696] The server adjusts the notification content based on the emotion engine's evaluation results: if the user is experiencing high stress, the notification's wording will be softer and a supportive message will be added to reduce anxiety.

[1697] User Notifications

[1698] The server sends a customized notification to the user's device, which displays the notification. The user can then check the notification content and take the necessary disaster prevention preparations.

[1699] Specific examples

[1700] For example, if a seismometer detects an unusual small earthquake in a certain area, reports of abnormal animal behavior on social media and earthquake cloud observations from satellite data are collected on a server. At the same time, the user's emotional data is also collected and analyzed. The server inputs this data into an AI model and analyzes the high probability of an earthquake occurring. Based on the results, the emotion engine then evaluates the user's current psychological state and creates a notification. For example, it generates a notification that reassures the user, saying, "Don't worry. The predicted probability of an earthquake is 30%. You are safe for now." This notification is then sent to the user's smartphone, where the user can check it and provide feedback if necessary.

[1701] Prompt Sentence Examples

[1702] This program takes the emotion data of user "12345" and combines it with earthquake forecast data to generate a notification. If the emotion score is high, the notification content will be changed to be gentle.

[1703] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1704] Step 1:

[1705] The server acquires the data necessary for earthquake forecasting. Specifically, it collects seismometer data, animal behavior data, environmental change data, and user emotion data from each data source. This includes acquiring data from APIs and scraping social media data. The input is the initial data from each data source, and the output is the raw data stored in the server.

[1706] Step 2:

[1707] The server cleanses and normalizes the collected data, specifically removing noise and duplicate data, completing incomplete data, standardizing formats, etc. The input is the raw data obtained in step 1, and the output is the cleansed, normalized, and organized data.

[1708] Step 3:

[1709] The server inputs the preprocessed data into the AI ​​model for analysis. Specifically, it compares it with past earthquake data and calculates a score for the likelihood of an earthquake occurring. The input is the organized data obtained in Step 2, and the output is a probability score for the occurrence of an earthquake.

[1710] Step 4:

[1711] The server generates a forecast of the possibility of an earthquake occurring. Specifically, it evaluates the analysis results of the AI ​​model and creates a forecast that includes the probability of occurrence, phenomena to watch out for, and recommended actions. The input is the earthquake prediction score, and the output is the forecast data that is notified to the user.

[1712] Step 5:

[1713] The server analyzes the user's emotion data using an emotion engine. Specifically, it uses an emotion analysis model to evaluate the stress level and anxiety level from the user's history and daily behavior. The input is the emotion data collected in step 1, and the output is the user's emotion score.

[1714] Step 6:

[1715] The server adjusts the notification content based on the emotion engine's evaluation results. Specifically, if the user's emotion score is high, the notification content is changed to a more gentle expression and a support message is added to promote disaster prevention preparation. The input is forecast data and emotion score, and the output is a customized notification message.

[1716] Step 7:

[1717] The server sends the customized notification to the user's device. Specifically, it pushes the generated notification message to the user's smartphone or other appropriate device. The input is the customized notification message, and the output is the notification message displayed on the user's device.

[1718] Step 8:

[1719] The user checks the notification displayed on the device and prepares for disaster. Specifically, the user takes necessary disaster prevention actions, such as checking water and food stockpiles and evacuation routes. The input is the notification content displayed on the device, and the output is the user's disaster prevention actions.

[1720] Step 9:

[1721] The user provides feedback to the server through the terminal. Specifically, the user sends their opinion on the notification content and forecast accuracy. The input is the user's feedback, and the output is the feedback data received by the server.

[1722] Step 10:

[1723] The server improves the system based on the received feedback. Specifically, it analyzes the feedback data, trains new predictive models, and improves notification content. The input is the feedback data, and the output is an improved system.

[1724] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1725] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1726] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1727] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1728] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1729] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1730] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1731] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1732] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1733] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1734] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for examp...

Claims

1. data collection means; A pre-processing means; data analysis means; An earthquake forecast generating means; a user notification means; A system including:

2. a means for acquiring seismic intensity data; a means for collecting animal behavior data; a means for collecting environmental change data; The system of claim 1 further comprising:

3. a means for cleansing the collected data; and a means of normalizing the data; The system of claim 1 further comprising:

4. A means of analyzing data with AI models, a means for evaluating the analysis results; The system of claim 1 further comprising:

5. means for generating an earthquake forecast based on the analysis results; means for transmitting the generated forecast to a user terminal; The system of claim 1 further comprising:

6. a means for displaying the notification; A means of encouraging users to take action; The system of claim 1 further comprising:

Images