system

Abstract

We provide the system. [Solution] A means for collecting precipitation data and river water level information in real time, A processing method equipped with a generative AI model that learns the correlation between precipitation and water level changes based on collected data, A means for evaluating the flood risk in a specific river using a generative AI model and generating evacuation information based on that risk, A means of notifying individuals of the generated evacuation information to their communication devices, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] With recent climate change, the risk of river flooding due to abnormal weather has been increasing globally. However, with conventional disaster prevention information dissemination means, it is difficult to quickly and surely disseminate information to the elderly and young people with low disaster prevention awareness. Therefore, there is a demand for the realization of a system that early evaluates the risk of flooding based on precipitation prediction and changes in river water levels and quickly provides evacuation information to individual terminals.

Means for Solving the Problems

[0005] This invention solves the problem by collecting precipitation data and river water level information in real time, and learning the correlation between precipitation and water level changes using a generated AI model based on this data. The model evaluates the flood risk in a specific river and notifies individuals of evacuation information generated based on that risk to their communication devices. Furthermore, it includes means to remove outliers using data preprocessing means to assist in accurate risk assessment, and means to display the notified evacuation information through a user interface and provide guidance information. This enables the rapid and accurate transmission of evacuation information.

[0006] "Precipitation data" refers to information that numerically represents the amount of precipitation in a specific area over a certain period of time.

[0007] "River water level information" refers to data showing the water level measured in a specific river.

[0008] "Means of real-time data collection" refers to technologies and methods that can acquire and process data instantly without any time delay.

[0009] A "generative AI model" is an artificial intelligence algorithm trained to generate useful patterns or predictions from specific input data.

[0010] "Means of assessing flood risk" refers to methods or techniques for calculating and predicting the likelihood of a river overflowing.

[0011] "Evacuation information" refers to information that includes guidelines for actions to take to ensure safety and specific instructions regarding evacuation locations.

[0012] "Means of notifying an individual's communication device" refers to methods of transmitting and displaying information on a personal communication device such as a smartphone or tablet.

[0013] "Data preprocessing means for detecting and removing outliers" refers to a method or technique for identifying data that deviates significantly from the norm and eliminating data unsuitable for analysis.

[0014] The "user interface" refers to the platform and screen configuration for users to receive and input information.

[0015] The "means for providing guidance information" is a technology or method that presents specific action guidance to users when evacuation is necessary.

Brief Description of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Embodiments for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] This invention is a system that rapidly assesses the risk of river flooding due to extreme weather and transmits accurate evacuation information to individuals. This system mainly consists of a server, terminals, and users.

[0038] The server first collects real-time precipitation and river water level data from weather data providers and observation stations. This allows it to constantly monitor the latest weather conditions. Next, the server uses this data to train a generative AI model. The training involves finding correlations between past precipitation and water level change patterns, improving the model's accuracy each time new data is input. This model is used to predict flood risk, taking into account the characteristics of specific topography and rivers.

[0039] If the risk is assessed as high, the server generates a notification, including specific evacuation instructions, based on the prediction results. This notification is sent to terminals belonging to a specific area.

[0040] When the device receives a notification from the server, it immediately provides the user with the information. The notification uses pop-ups and alarm functions to visually and audibly inform the user that evacuation is necessary. Furthermore, the device displays maps and evacuation routes, specifically indicating which direction to evacuate.

[0041] Users are expected to receive notifications and quickly begin evacuation. They will follow the instructions on their device and move safely to a safe evacuation center. The system is designed to be intuitive and easy to use, especially for the elderly and younger generations with low disaster preparedness awareness, thus supporting effective evacuation.

[0042] As a concrete example, suppose heavy rain is predicted to fall in a certain area in a short period of time. The server detects this and determines that the risk of flooding is high based on the water level forecast of nearby rivers. As a result, it sends a notification to users in the affected area via the notification system, instructing them to evacuate immediately to the nearest shelter. This notification is displayed on the user's device, and the information is immediately conveyed to the user, prompting them to take swift evacuation action.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server collects precipitation and forecast information in real time from weather data provision services. This is done using an API and a system that updates the latest data every hour.

[0046] Step 2:

[0047] The server collects water level data from local river level monitoring stations and stores it in a database. This data is recorded at short intervals and used to understand the river conditions.

[0048] Step 3:

[0049] The server preprocesses the collected precipitation and water level data, detecting and removing outliers and missing values. This increases the reliability of the data and enables accurate training of the AI ​​model.

[0050] Step 4:

[0051] The server uses a generative AI model to learn the correlation between precipitation and water level changes from historical data. The model also takes topographic data into consideration and is trained to predict flood risk in specific rivers.

[0052] Step 5:

[0053] The server inputs the latest precipitation forecast data into an AI model and calculates the flood risk for each river. Once the risk assessment is complete, the results are compiled into evacuation information.

[0054] Step 6:

[0055] The server prepares notifications for terminals in specific areas based on evacuation information. These notifications include specific evacuation orders and information about the nearest evacuation shelters.

[0056] Step 7:

[0057] The device receives notifications sent from the server and displays them to the user immediately. The device uses pop-ups and notification sounds to convey urgent information to the user.

[0058] Step 8:

[0059] Users check notifications on their devices and act based on the evacuation instructions provided. They then begin moving towards the designated evacuation shelter, using the evacuation route and map displayed on their devices as a guide.

[0060] (Example 1)

[0061] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0062] Conventional flood forecasting and evacuation information provision systems have been unable to respond quickly to rapid weather changes and have difficulty appropriately notifying individual users of accurate evacuation information. As a result, there was a risk that local residents would not be able to evacuate safely. This invention aims to solve these problems and realize highly accurate flood forecasting and personalized evacuation information based on real-time weather information.

[0063] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0064] In this invention, the server includes means for collecting precipitation information and water level information in real time from atmospheric phenomena data-related organizations and monitoring facilities; processing means equipped with a data analysis model that learns the correlation between precipitation and water level changes based on the collected information; means for evaluating the flood risk in a specific area using the data analysis model and generating evacuation information based on said risk; means for notifying individuals' electronic devices of the generated evacuation information; and means for identifying evacuation routes using geographic information of the target area. This enables real-time prediction of flood risk and the provision of rapid and accurate evacuation information.

[0065] "Precipitation information" refers to data about the amount of moisture in the atmosphere that falls to the ground as rain.

[0066] "Water level information" refers to data on the height of the water level in a specific river or body of water.

[0067] "Atmospheric phenomena data-related organizations" refer to government agencies and observation groups that provide meteorological data.

[0068] A "monitoring facility" is a collection of observation devices and equipment installed to collect environmental data for a specific area.

[0069] "Means of real-time data collection" refers to technologies and methods for instantly acquiring constantly updated information.

[0070] A "data analysis model" refers to an artificial intelligence algorithm or system that learns patterns based on different data and makes predictions and judgments.

[0071] "Flood risk" is an assessment that represents the possibility or danger of inundation by rivers or floods under specific conditions.

[0072] "Evacuation information" refers to information that includes instructions and guidelines for safely evacuating during a crisis situation.

[0073] "Electronic devices" is a general term for electrical equipment used for communication and data processing, and includes, for example, mobile phones and computers.

[0074] "Geographic information" refers to information about the topography and terrain of a specific region, and includes maps, place names, and longitude and latitude data.

[0075] An "evacuation route" is the optimal route for moving to a safe location in an emergency.

[0076] This invention is a system that rapidly and accurately assesses the risk of river flooding due to extreme weather conditions and provides appropriate evacuation information to individuals. This system mainly consists of a server, terminals, and users.

[0077] To collect data, the server first obtains real-time precipitation and water level information from atmospheric phenomena data-related organizations and monitoring facilities. This is done, for example, by obtaining data via APIs provided by government agencies. The data is then processed through formatting tools to detect and remove outliers and converted into an analyzable format. For analysis, machine learning libraries such as TENSORFLOW® are used.

[0078] The analyzed data is trained by a data analysis model. This model analyzes the correlation between past precipitation and water levels to predict flood risk in a specific area. An example of a prompt used in the model is the instruction, "Predict flood risk based on current precipitation and water level data for the area."

[0079] If a high risk of flooding is detected, the server automatically generates evacuation information suggesting appropriate evacuation routes and notifies individual electronic devices. The notification uses visual and auditory methods to present the information in a way that is intuitively understandable to the user.

[0080] The device receives notifications sent from the server and provides information to the user through pop-ups and alarms. Furthermore, it utilizes geographical information to visually display evacuation routes and support users in evacuating safely.

[0081] Users begin moving to a safe evacuation center by following instructions from their device. This system is designed to be particularly easy to use for the elderly and young people with low disaster preparedness awareness, and supports rapid evacuation.

[0082] As a concrete example, consider a scenario where heavy rain is predicted in a certain area in a short period of time. The server immediately receives this information and evaluates the flood risk based on a generated AI model. Depending on the result, the server notifies users in the affected area via their devices with information urging them to evacuate quickly. By quickly conveying this notification to users, they can take safe evacuation action.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The server uses APIs to acquire precipitation and water level information in real time from atmospheric phenomena data-related organizations and monitoring facilities. The acquired data is passed to a data processing system where outliers are detected and removed. This generates a clean dataset. This clean data is then stored in a database for analysis.

[0086] Step 2:

[0087] The server updates the generated AI model using the formatted data. Specifically, it uses machine learning libraries such as TensorFlow to learn the correlation between precipitation and water level changes based on historical data. As new data is input into the model, the model's prediction accuracy improves. As a result, a model is output that can predict the flood risk of a specific area with high accuracy.

[0088] Step 3:

[0089] The server sends a prompt message to the generating AI model. Specifically, the prompt instructs the model to "predict flood risk based on current regional precipitation and water level data." Upon receiving this instruction, the model analyzes the collected data and assesses the flood risk for the specific area. As a result of the assessment, evacuation information is generated according to the level of risk.

[0090] Step 4:

[0091] The server generates appropriate notifications for each user's electronic device based on the generated evacuation information. These notifications include evacuation routes and destinations that take the user's location into account. This information is transmitted to each device via the communication network. Users must pay immediate attention to the notification once it is sent to their device.

[0092] Step 5:

[0093] The terminal receives notifications from the server and provides them to the user through visual and auditory means. Specifically, it displays pop-ups on the screen and sounds an audible alarm to alert the user. It also displays evacuation routes on a map using geographical information and instructs the user on specific next steps. Because this information is immediate, users are expected to respond promptly.

[0094] Step 6:

[0095] Users follow the instructions provided by the device and move safely to the evacuation shelter using the designated evacuation route. The device continuously updates real-time information during evacuation, allowing users to always access the latest safety information. The device's interface is designed to be intuitive and easy to use, especially for users with low disaster preparedness awareness.

[0096] (Application Example 1)

[0097] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0098] In recent years, the risk of river flooding due to extreme weather has increased, necessitating rapid and accurate evacuation. However, there is a lack of systems that provide optimal evacuation route information and intuitive guidance to people within buildings with physical space (e.g., commercial and public facilities). In particular, insufficient guidance on evacuation routes and safe shelters hinders rapid evacuation.

[0099] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0100] In this invention, the server includes means for collecting precipitation data and river water level information in real time; processing means equipped with a generative AI model that learns the correlation between precipitation and water level changes based on the collected data; means for evaluating the flood risk in a specific river using the generative AI model and generating evacuation information based on the risk; and means for notifying a communication device of the generated evacuation information and providing evacuation route and shelter information according to location information. This enables rapid and intuitive evacuation guidance for personnel inside buildings.

[0101] "Precipitation data" refers to information that measures the amount of rain that fell in a specific area within a certain period of time.

[0102] "River water level information" refers to data that measures the water level at a specific point in a river in real time.

[0103] A "generative AI model" is an artificial intelligence model that learns patterns based on past data and makes predictions and classifications based on new data.

[0104] "Flood risk" is an indicator that shows the danger of water levels rising in a particular river and causing it to overflow.

[0105] "Communication devices" are electronic devices used to send and receive information, and include smartphones and tablets.

[0106] An "evacuation route" is a path used to evacuate to a safe place in the event of a disaster or emergency.

[0107] A "shelter" is a facility or place used to provide temporary safety and shelter during a disaster.

[0108] The system for realizing this invention consists of three elements: a server, a terminal, and a user. The server first collects precipitation data and river water level information in real time. This data is obtained from external weather data provision services and observation stations, and is configured to respond quickly to sudden changes in weather.

[0109] The server uses a generative AI model based on the collected data to learn the correlation between precipitation and water level changes. This model incorporates machine learning algorithms that can analyze historical data and predict flood risk in specific rivers with high accuracy. To improve the performance of the generative AI model, it updates itself each time new data is input.

[0110] If a high risk of flooding is assessed, the server generates evacuation information based on that information and notifies the user's communication device. These communication devices are common devices such as smartphones and tablets, and are capable of receiving information in real time.

[0111] The terminal displays the notified evacuation information through a user interface. This interface is intuitive to use and provides the user with specific evacuation directions through audio and visual output. This allows the user to select the optimal evacuation route based on their location.

[0112] As a concrete example, let's consider a scenario where extremely heavy rain is predicted to fall in a certain area in a short period of time. The server uses a generative AI model to predict the water levels of nearby rivers and recognizes that the risk is increasing. As a result, a notification is sent to users in that area urging them to evacuate quickly.

[0113] Example of a prompt:

[0114] "Input local weather data and use that data to predict flood risk. Also, generate notifications suggesting the best evacuation routes within the shopping mall."

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] The server collects precipitation data and river water level information in real time from weather data provision services and observation stations.

[0118] The input is an online weather data stream.

[0119] The output consists of the latest precipitation and water level data, which the server receives to prepare for analysis in the next step.

[0120] Step 2:

[0121] The server inputs the collected data into a generating AI model to assess the flood risk.

[0122] The input consists of precipitation and water level data obtained in Step 1.

[0123] Using the data, a generative AI model performs data calculations to recognize patterns of rapid water level rises by comparing them with past trends.

[0124] The output is a predicted value regarding the flood risk of a specific river. This quantifies the degree of flood risk.

[0125] Step 3:

[0126] The server generates evacuation information based on the assessed risk and creates a message to notify communication devices.

[0127] The input is the predicted flood risk value output in step 2.

[0128] If the risk level is high, a logic is executed to determine which areas to issue what kind of evacuation orders to.

[0129] The output is a message containing specific evacuation instructions and evacuation route information, which is sent to the user's communication device.

[0130] Step 4:

[0131] The terminal displays evacuation information received from the server through a user interface and prompts evacuation visually and audibly.

[0132] The input is the evacuation message generated by the server in step 3.

[0133] The device's display and speakers are used to provide users with interactive evacuation route guidance.

[0134] The output presents evacuation information in a way that appeals to the user's sight and hearing, enabling them to quickly understand the information and take action.

[0135] Step 5:

[0136] Users follow the instructions on their devices and take the optimal evacuation route to a safe shelter.

[0137] The input consists of the evacuation route and destination location information presented in Step 4.

[0138] By following the instructions on the device, a specific route to avoid risks is shown, and the actual movement is carried out.

[0139] The output is the safe evacuation actions that users experience. The effective functioning of this process ensures the safety of human lives.

[0140] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0141] This invention is a disaster prevention information transmission system that combines flood risk assessment based on precipitation data and river water level information with an emotion engine that recognizes user emotions. This system consists of three main components: a server, a terminal, and a user.

[0142] The server collects precipitation and forecast information in real time from weather data provision services. In parallel, it acquires water level data from river water level observation stations and uses data preprocessing to detect and remove anomalies. The server also uses a generative AI model to learn the correlation between precipitation and water level changes and calculate flood risk. Based on this risk assessment result, it generates evacuation information. The evacuation information includes specific instructions according to the risk level.

[0143] Furthermore, the server is equipped with an emotion engine that analyzes the user's emotional state. This emotion engine analyzes the user's past response data and current activity to infer emotions such as whether the user is stressed or confused. Based on the output of the emotion engine, the server adjusts the content and method of delivery of evacuation information and provides it in the format that is easiest for the user to understand. For example, if the server detects that the user is confused, it simplifies the information and enables the user to immediately begin evacuation.

[0144] The terminal receives evacuation information transmitted from the server and displays the information via the user interface according to the information presentation instructions provided by the emotion engine. This includes guidance information such as evacuation routes and details of the nearest evacuation shelters.

[0145] Users are expected to receive notifications from their devices and take appropriate evacuation actions based on the information provided. The emotion engine allows users to receive information in a way that suits their emotional state, prompting them to take appropriate action. For example, when the likelihood of flooding increases, the server detects the user's anxiety, and the device displays a message in a gentle tone such as, "Don't worry. You will be safe if you go to the designated evacuation center," thereby alleviating the user's anxiety and encouraging a swift evacuation.

[0146] Thus, the present invention provides a more effective disaster response by combining technical data with an understanding of human emotions.

[0147] The following describes the processing flow.

[0148] Step 1:

[0149] The server collects real-time precipitation and water level data from weather data provision services and river water level observation stations. This data is automatically retrieved via API and stored in a dedicated database.

[0150] Step 2:

[0151] The server preprocesses the collected data, detecting and removing outliers and missing values. This allows the generated AI model to learn accurately regardless of the quality of the data.

[0152] Step 3:

[0153] The server uses a generative AI model to learn the correlation between precipitation and changes in river levels by comparing them with historical data. This model assesses the likelihood of flooding and quantifies the risk.

[0154] Step 4:

[0155] The server analyzes the user's emotional state through an emotion engine, based on the user's past activity data and current situation information. It determines whether the user is stressed or confused.

[0156] Step 5:

[0157] The server integrates the risk assessment of the generation AI model with the output of the emotion engine to generate evacuation information. This information is optimized for the user's emotional state, for example, providing detailed explanations to calm users and concise, clear instructions to confused users.

[0158] Step 6:

[0159] The terminal receives evacuation information sent from the server and implements an information presentation method that responds to the user's emotions. This is done through visually easy-to-understand UI and friendly message sounds.

[0160] Step 7:

[0161] Users check evacuation information on their devices and begin evacuation actions based on that information. They use the guidance and map display on their devices to select the shortest and safest route and head to an evacuation center.

[0162] Through this series of processes, the present invention can realize disaster prevention information transmission that meets the individual needs of users and support swift and accurate evacuation actions.

[0163] (Example 2)

[0164] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0165] Conventional flood risk assessment systems that utilize precipitation and river water level information do not provide information tailored to the user's emotions or level of understanding, which can lead to confusion and anxiety. Furthermore, inaccurate risk assessments based on data containing outliers may occur, resulting in the failure to provide appropriate evacuation information.

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

[0167] In this invention, the server includes means for collecting precipitation data and river water level information in real time; information processing means equipped with a generative AI model that learns the correlation between precipitation and water level changes based on the collected data; means for evaluating the flood risk in a specific waterway using the generative AI model and generating evacuation information based on said risk; and means equipped with an emotion processing engine that analyzes emotional states and adjusts the content and method of transmission of evacuation information based on the analysis results. This makes it possible to provide accurate evacuation information that takes into account the emotional state of the user.

[0168] "Precipitation data" refers to information that quantifies the amount of rain that falls on the Earth's surface within a certain period of time.

[0169] "Water level information" refers to data indicating the height of water surfaces in rivers, lakes, and other bodies of water, and is used to understand the volume and flow of water.

[0170] "Means of real-time data collection" refers to technologies and methods for instantly acquiring and making available data that is constantly being generated in real time.

[0171] A "generative AI model" refers to an artificial intelligence model that automatically learns rules and patterns based on data to perform predictions and classifications.

[0172] "Information processing means" refers to methods and technologies for analyzing and processing acquired data to generate or extract valuable information according to a specific purpose.

[0173] "Flood risk" refers to an indicator that shows the degree of danger that water from rivers and other bodies of water will overflow their banks and cause damage to surrounding areas.

[0174] "Evacuation information" refers to information that includes instructions and guidelines for actions necessary to ensure safety during natural disasters.

[0175] "Personal communication devices" refer to electronic devices owned by individuals and used for sending and receiving information, such as mobile phones and smartphones.

[0176] An "emotional processing engine" refers to a technology or system that analyzes an individual's emotional state and understands that state in order to take appropriate action.

[0177] This invention is a disaster prevention information system that accurately assesses flood risk based on precipitation and river water level information and provides users with evacuation information that takes their emotions into consideration. An embodiment thereof is shown below.

[0178] The server collects precipitation and forecast information in real time from weather data provision services using APIs. This ensures that the latest precipitation data is always available. River water level information is obtained by connecting to the database of river water level observation stations. General communication infrastructure and cloud services are used for data collection.

[0179] The collected data is preprocessed on the server to detect and remove any anomalies. This preprocessing is a crucial step in maintaining data quality and improving the accuracy of the analysis results.

[0180] Next, the server utilizes a generative AI model based on the collected data to learn the correlation between precipitation and water level changes. This AI model is based on pattern recognition technology and can perform highly accurate flood risk assessments based on historical data. Specific analysis utilizes technologies such as trained models and neural networks.

[0181] Based on the generated risk assessment, the server creates optimal evacuation information. This evacuation information includes specific instructions tailored to the urgency and risk level. The generated information is automatically transmitted to the user's mobile device or other communication device.

[0182] Furthermore, the server is equipped with an emotion processing engine that analyzes the user's emotional state. This engine analyzes the user's past reaction logs and current operation logs to estimate the degree of stress and anxiety the user is experiencing. Based on this analysis, the presentation format and tone of the evacuation information are adjusted to make it easier for the user to understand and accept.

[0183] The terminal visually displays received evacuation information through a user interface. This includes infographics and evacuation route displays on maps, designed to allow users to intuitively understand the information and take quick action.

[0184] As a concrete example, if there are signs of an impending flood, the server prompts the AI ​​model with a message such as, "Use the precipitation data from the past 24 hours and the current river level data to assess the flood risk for the next 24 hours and generate evacuation information," thereby enabling accurate information generation. This allows for a comprehensive disaster response that includes understanding emotions.

[0185] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0186] Step 1:

[0187] The server collects precipitation and forecast information in real time through the API of a weather data provision service. In parallel, the server obtains water level information from a database of river water level observation stations. The latest precipitation and water level information is obtained as input from an external data provider. This data is stored in data storage for initial processing, in preparation for subsequent processing.

[0188] Step 2:

[0189] The server performs data cleaning on the collected data. Specifically, it uses data preprocessing to detect and remove outliers. For example, it filters out and deletes negative precipitation data and obviously abnormal water level data. Based on this input, it outputs a cleaned dataset and passes that dataset to a data analysis module.

[0190] Step 3:

[0191] The server inputs the processed data into a generating AI model, which learns the correlation between precipitation and water level changes. This AI model uses historical and current real-time data to assess flood risk. Through this process, the model generates a risk assessment output from the input data and calculates a detailed risk level.

[0192] Step 4:

[0193] The server generates evacuation information to be provided to the user based on the output of the generated AI model. This process includes specific instructions and suggested evacuation routes according to the risk level. The output is formatted evacuation information, which is then prepared for transmission to the user's communication device.

[0194] Step 5:

[0195] The server uses an emotion processing engine to analyze the user's emotional state. Inputs include the user's past reaction logs and current activity status. Through this analysis, the server estimates the user's stress and anxiety levels and adjusts the delivery method of evacuation information based on this information. The output is evacuation information optimized for the user.

[0196] Step 6:

[0197] The terminal receives evacuation information transmitted from the server and displays the information through a user interface. The terminal receives evacuation information as input and outputs it in an intuitively understandable format using infographics, maps, and other visual aids. This allows users to quickly grasp the information and take appropriate action.

[0198] (Application Example 2)

[0199] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0200] During natural disasters, information overload and misinformation make accurate and rapid evacuation difficult. Furthermore, there is a lack of evacuation information that can alleviate user stress and confusion in such situations and that can be tailored to individual emotional states. This invention aims to address these problems.

[0201] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0202] In this invention, the server includes means for collecting precipitation data and river water level information in real time, processing means equipped with a generative AI model that learns the correlation between precipitation and water level changes based on the collected data, and processing means equipped with an emotion engine that analyzes individual emotional states and adjusts the content and method of transmission of evacuation information based on the analysis results. This makes it possible to provide information that encourages appropriate and prompt evacuation actions without confusing the user.

[0203] "Precipitation data" refers to information that shows the amount of rain that fell in a specific area or at a specific time.

[0204] "River water level information" refers to data that shows the water level at a specific point in a river.

[0205] "Means of collecting data in real time" refers to a function or device that can collect data instantly.

[0206] A "generative AI model" refers to an artificial intelligence algorithm that analyzes collected data and learns specific rules and patterns.

[0207] "Processing means" refers to methods and devices for analyzing and processing data.

[0208] "Assessing flood risk" means predicting the possibility of a river overflowing and determining the degree of that risk.

[0209] "Means for generating evacuation information" refers to methods and devices for creating information that encourages safe actions when danger is imminent.

[0210] An "emotion engine" refers to a processing unit or function that analyzes the user's emotional state and adjusts the content and presentation of information based on the results.

[0211] "Personal communication device" refers to a communication-capable device belonging to a specific user, such as a smartphone.

[0212] "User interface" refers to the screens and operating environments that allow users to interact with a device or system.

[0213] "Individualized guidance information" refers to specific instructions and guidance provided in a way that is tailored to each user.

[0214] This invention is implemented using a system consisting of a server, a terminal, and a user. The server acquires precipitation data and river water level information in real time. Specifically, it collects data from weather APIs and river water level observation station databases that are publicly available via the internet. Data cleansing is performed using libraries such as NumPy to remove noise contained in the data.

[0215] Next, the server uses a generated AI model based on the collected data to analyze the correlation between precipitation and water level changes and calculate the flood risk. It builds a model using machine learning libraries such as scikit-learn and performs a risk assessment. Based on the results of this risk assessment, appropriate evacuation information is generated.

[0216] Furthermore, the server incorporates an emotion engine that analyzes the user's emotions. Specifically, it analyzes information obtained from the user's device and data on the user's past behavior to infer emotional states such as stress and anxiety. It utilizes the Natural Language Toolkit (NLTK) and other emotion analysis tools.

[0217] Once the user's emotional state is understood, the emotion engine optimizes the content and delivery method of evacuation information. For example, if the user is determined to be "anxious," the evacuation information will be presented in a gentle tone that takes that emotion into consideration. A specific example of a prompt message that could be used is, "The user's emotional state is 'anxious.' Please generate a reassuring message to calm them down."

[0218] The terminal displays the generated evacuation information through a user interface. Utilizing smartphones and tablet devices, the information is displayed in an intuitive and easy-to-understand manner. Visual information, such as real-time evacuation routes on a map, is also used to guide users toward taking swift action.

[0219] As a result, a system is realized that can encourage safe and rapid evacuation actions without causing confusion among users.

[0220] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0221] Step 1:

[0222] The server obtains precipitation data and river level information from a weather API via the internet. This data serves as input. Using the NumPy library, the server performs data cleansing to detect and remove anomalies from the acquired data. As a result, cleansed and accurate weather data is output.

[0223] Step 2:

[0224] The server uses a generated AI model based on the data cleansed in Step 1 to learn the correlation between precipitation and water level changes. Using scikit-learn, it computes this data to calculate flood risk. The results of the risk assessment are output as basic data for generating evacuation information.

[0225] Step 3:

[0226] The emotion engine installed on the server receives data from the user as input and analyzes the user's emotional state. This process uses the Natural Language Toolkit (NLTK) to calculate, for example, stress and anxiety levels. Based on the analysis results, the user's emotional state is output.

[0227] Step 4:

[0228] The server integrates the risk assessment results obtained in step 2 and the user sentiment analysis results in step 3 to generate optimized evacuation information. It generates prompt messages and constructs reassuring messages that correspond to specific emotional states. The generated evacuation information is output in a state ready to be notified to the user.

[0229] Step 5:

[0230] The terminal displays optimized evacuation information received from the server through a user interface. The input is the notified evacuation information. The terminal visualizes the information and outputs it in a format that is easy for the user to understand, such as displaying evacuation routes and the locations of evacuation shelters on a map. Because the information is presented in a user-friendly format, it encourages quick decision-making and action.

[0231] Step 6:

[0232] Users take action to ensure their own safety based on the evacuation information displayed on their device. Because the outputted information is specific and intuitive, users are able to start evacuation actions appropriately.

[0233] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0234] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0235] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0236] [Second Embodiment]

[0237] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0238] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0239] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0240] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0241] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0242] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0243] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0244] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0245] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0246] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0247] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0248] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0249] This invention is a system that rapidly assesses the risk of river flooding due to extreme weather and transmits accurate evacuation information to individuals. This system mainly consists of a server, terminals, and users.

[0250] The server first collects real-time precipitation and river water level data from weather data providers and observation stations. This allows it to constantly monitor the latest weather conditions. Next, the server uses this data to train a generative AI model. The training involves finding correlations between past precipitation and water level change patterns, improving the model's accuracy each time new data is input. This model is used to predict flood risk, taking into account the characteristics of specific topography and rivers.

[0251] If the risk is assessed as high, the server generates a notification, including specific evacuation instructions, based on the prediction results. This notification is sent to terminals belonging to a specific area.

[0252] When the device receives a notification from the server, it immediately provides the user with the information. The notification uses pop-ups and alarm functions to visually and audibly inform the user that evacuation is necessary. Furthermore, the device displays maps and evacuation routes, specifically indicating which direction to evacuate.

[0253] Users are expected to receive notifications and quickly begin evacuation. They will follow the instructions on their device and move safely to a safe evacuation center. The system is designed to be intuitive and easy to use, especially for the elderly and younger generations with low disaster preparedness awareness, thus supporting effective evacuation.

[0254] As a concrete example, suppose heavy rain is predicted to fall in a certain area in a short period of time. The server detects this and determines that the risk of flooding is high based on the water level forecast of nearby rivers. As a result, it sends a notification to users in the affected area via the notification system, instructing them to evacuate immediately to the nearest shelter. This notification is displayed on the user's device, and the information is immediately conveyed to the user, prompting them to take swift evacuation action.

[0255] The following describes the processing flow.

[0256] Step 1:

[0257] The server collects precipitation and forecast information in real time from weather data provision services. This is done using an API and a system that updates the latest data every hour.

[0258] Step 2:

[0259] The server collects water level data from local river level monitoring stations and stores it in a database. This data is recorded at short intervals and used to understand the river conditions.

[0260] Step 3:

[0261] The server preprocesses the collected precipitation and water level data, detecting and removing outliers and missing values. This increases the reliability of the data and enables accurate training of the AI ​​model.

[0262] Step 4:

[0263] The server uses a generative AI model to learn the correlation between precipitation and water level changes from historical data. The model also takes topographic data into consideration and is trained to predict flood risk in specific rivers.

[0264] Step 5:

[0265] The server inputs the latest precipitation forecast data into an AI model and calculates the flood risk for each river. Once the risk assessment is complete, the results are compiled into evacuation information.

[0266] Step 6:

[0267] The server prepares notifications for terminals in specific areas based on evacuation information. These notifications include specific evacuation orders and information about the nearest evacuation shelters.

[0268] Step 7:

[0269] The device receives notifications sent from the server and displays them to the user immediately. The device uses pop-ups and notification sounds to convey urgent information to the user.

[0270] Step 8:

[0271] Users check notifications on their devices and act based on the evacuation instructions provided. They begin moving towards the designated evacuation shelter, using the evacuation route and map displayed on their devices as a guide.

[0272] (Example 1)

[0273] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0274] Conventional flood forecasting and evacuation information provision systems have been unable to respond quickly to rapid weather changes and have difficulty appropriately notifying individual users of accurate evacuation information. As a result, there was a risk that local residents would not be able to evacuate safely. This invention aims to solve these problems and realize highly accurate flood forecasting and personalized evacuation information based on real-time weather information.

[0275] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0276] In this invention, the server includes means for collecting precipitation information and water level information in real time from atmospheric phenomena data-related organizations and monitoring facilities; processing means equipped with a data analysis model that learns the correlation between precipitation and water level changes based on the collected information; means for evaluating the flood risk in a specific area using the data analysis model and generating evacuation information based on said risk; means for notifying individuals' electronic devices of the generated evacuation information; and means for identifying evacuation routes using geographic information of the target area. This enables real-time prediction of flood risk and the provision of rapid and accurate evacuation information.

[0277] "Precipitation information" refers to data regarding the amount of moisture in the atmosphere that falls to the ground as rain.

[0278] "Water level information" refers to data regarding the height of the water surface in a specific river or water area.

[0279] "Atmospheric phenomenon data-related institutions" refer to government agencies and observation groups that provide data related to meteorology.

[0280] "Monitoring facilities" refer to an aggregation of observation devices and equipment installed to collect environmental data in a specific area.

[0281] "Means for real-time collection" refer to technologies and methods for immediately acquiring information that is constantly updated.

[0282] "Data analysis models" refer to artificial intelligence algorithms and systems that learn patterns based on different data and perform predictions and judgments.

[0283] "Flood risk" refers to an assessment representing the possibility and danger of inundation by rivers or floods under specific conditions.

[0284] "Evacuation information" refers to information including instructions and guidelines for safe evacuation in a crisis situation.

[0285] "Electronic devices" refer to a general term for electrical devices used for communication and data processing, including, for example, mobile phones and computers.

[0286] "Geographical information" refers to information regarding the terrain and topography of a specific area, including maps, place names, and longitude and latitude data.

[0287] "Evacuation route" refers to the optimal route for moving to a safe location in an emergency.

[0288] This invention provides a system for rapidly and accurately assessing the risk of river flooding due to extreme weather conditions and for providing appropriate evacuation information to individuals. This system mainly consists of a server, terminals, and users.

[0289] To collect data, the server first obtains real-time precipitation and water level information from atmospheric phenomena data-related organizations and monitoring facilities. This is done, for example, by obtaining data via APIs provided by government agencies. The data is then processed through formatting tools to detect and remove outliers and converted into an analyzable format. Machine learning libraries such as TensorFlow are used for analysis.

[0290] The analyzed data is trained by a data analysis model. This model analyzes the correlation between past precipitation and water levels to predict flood risk in a specific area. An example of a prompt used in the model is the instruction, "Predict flood risk based on current precipitation and water level data for the area."

[0291] If a high risk of flooding is detected, the server automatically generates evacuation information suggesting appropriate evacuation routes and notifies individual electronic devices. The notification uses visual and auditory methods to present the information in a way that is intuitively understandable to the user.

[0292] The device receives notifications sent from the server and provides information to the user through pop-ups and alarms. Furthermore, it utilizes geographical information to visually display evacuation routes and support users in evacuating safely.

[0293] Users begin moving to a safe evacuation center by following instructions from their device. This system is designed to be particularly easy to use for the elderly and young people with low disaster preparedness awareness, and supports rapid evacuation.

[0294] As a concrete example, consider a scenario where heavy rain is predicted in a certain area in a short period of time. The server immediately receives this information and evaluates the flood risk based on a generated AI model. Depending on the result, the server notifies users in the affected area via their devices with information urging them to evacuate quickly. By quickly conveying this notification to users, they can take safe evacuation action.

[0295] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0296] Step 1:

[0297] The server uses APIs to acquire precipitation and water level information in real time from atmospheric phenomena data-related organizations and monitoring facilities. The acquired data is passed to a data processing system where outliers are detected and removed. This generates a clean dataset. This clean data is then stored in a database for analysis.

[0298] Step 2:

[0299] The server updates the generated AI model using the formatted data. Specifically, it uses machine learning libraries such as TensorFlow to learn the correlation between precipitation and water level changes based on historical data. As new data is input into the model, the model's prediction accuracy improves. As a result, a model is output that can predict the flood risk of a specific area with high accuracy.

[0300] Step 3:

[0301] The server sends a prompt message to the generating AI model. Specifically, the prompt instructs the model to "predict flood risk based on current regional precipitation and water level data." Upon receiving this instruction, the model analyzes the collected data and assesses the flood risk for the specific area. As a result of the assessment, evacuation information is generated according to the level of risk.

[0302] Step 4:

[0303] Based on the generated evacuation information, the server generates appropriate notifications for each user's electronic device. The notifications include evacuation routes and evacuation destinations considering the user's location information. This information is transmitted to each terminal via the communication network. When the notification is sent to the terminal, the user needs to pay immediate attention.

[0304] Step 5:

[0305] The terminal receives the notification from the server and provides it to the user using visual and auditory means. Specifically, a pop-up is displayed on the screen and an audio alarm is sounded to prompt the user's attention. Also, the evacuation route is displayed on the map using geographical information to instruct the user on specific next actions. Since this information is immediate, it is desirable for the user to respond immediately.

[0306] Step 6:

[0307] The user moves safely to the evacuation shelter using the designated evacuation route according to the instructions provided by the terminal. Even during evacuation, the terminal continues to update real-time information, so the user can always check the latest safety information. Especially for users with low disaster prevention awareness, the terminal interface is designed to be intuitive and easy to operate.

[0308] (Application Example 1)

[0309] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0310] In recent years, the risk of river flooding due to abnormal weather has been increasing, and rapid and accurate evacuation is required. However, there is a lack of a system that provides information on the optimal evacuation route and intuitively guides the personnel in buildings with real-world occupancy space (e.g., commercial facilities and public facilities). In particular, the guidance on evacuation routes and safe evacuation shelters is insufficient, which hinders rapid evacuation.

[0311] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0312] In this invention, the server includes means for collecting precipitation data and river water level information in real time; processing means equipped with a generative AI model that learns the correlation between precipitation and water level changes based on the collected data; means for evaluating the flood risk in a specific river using the generative AI model and generating evacuation information based on the risk; and means for notifying a communication device of the generated evacuation information and providing evacuation route and shelter information according to location information. This enables rapid and intuitive evacuation guidance for personnel inside buildings.

[0313] "Precipitation data" refers to information that measures the amount of rain that fell in a specific area within a certain period of time.

[0314] "River water level information" refers to data that measures the water level at a specific point in a river in real time.

[0315] A "generative AI model" is an artificial intelligence model that learns patterns based on past data and makes predictions and classifications based on new data.

[0316] "Flood risk" is an indicator that shows the danger of water levels rising in a particular river and causing it to overflow.

[0317] "Communication devices" are electronic devices used to send and receive information, and include smartphones and tablets.

[0318] An "evacuation route" is a path used to evacuate to a safe place in the event of a disaster or emergency.

[0319] A "shelter" is a facility or place used to provide temporary safety and shelter during a disaster.

[0320] The system for realizing this invention consists of three elements: a server, a terminal, and a user. The server first collects precipitation data and river water level information in real time. This data is obtained from external weather data provision services and observation stations, and is configured to respond quickly to sudden changes in weather.

[0321] The server uses a generative AI model based on the collected data to learn the correlation between precipitation and water level changes. This model incorporates machine learning algorithms that can analyze historical data and predict flood risk in specific rivers with high accuracy. To improve the performance of the generative AI model, it updates itself each time new data is input.

[0322] If a high risk of flooding is assessed, the server generates evacuation information based on that information and notifies the user's communication device. These communication devices are common devices such as smartphones and tablets, and are capable of receiving information in real time.

[0323] The terminal displays the notified evacuation information through a user interface. This interface is intuitive to use and provides the user with specific evacuation directions through audio and visual output. This allows the user to select the optimal evacuation route based on their location.

[0324] As a concrete example, let's consider a scenario where extremely heavy rain is predicted to fall in a certain area in a short period of time. The server uses a generative AI model to predict the water levels of nearby rivers and recognizes that the risk is increasing. As a result, a notification is sent to users in that area urging them to evacuate quickly.

[0325] Example of a prompt:

[0326] "Input local weather data and use that data to predict flood risk. Also, generate notifications suggesting the best evacuation routes within the shopping mall."

[0327] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0328] Step 1:

[0329] The server collects precipitation data and river water level information in real time from weather data provision services and observation stations.

[0330] The input is an online weather data stream.

[0331] The output consists of the latest precipitation and water level data, which the server receives to prepare for analysis in the next step.

[0332] Step 2:

[0333] The server inputs the collected data into a generating AI model to assess the flood risk.

[0334] The input consists of precipitation and water level data obtained in Step 1.

[0335] Using the data, a generative AI model performs data calculations to recognize patterns of rapid water level rises by comparing them with past trends.

[0336] The output is a predicted value regarding the flood risk of a specific river. This quantifies the degree of flood risk.

[0337] Step 3:

[0338] The server generates evacuation information based on the assessed risk and creates a message to notify communication devices.

[0339] The input is the predicted flood risk value output in step 2.

[0340] If the risk level is high, a logic is executed to determine which areas to issue what kind of evacuation orders to.

[0341] The output is a message containing specific evacuation instructions and evacuation route information, which is sent to the user's communication device.

[0342] Step 4:

[0343] The terminal displays evacuation information received from the server through a user interface and prompts evacuation visually and audibly.

[0344] The input is the evacuation message generated by the server in step 3.

[0345] The device's display and speakers are used to provide users with interactive evacuation route guidance.

[0346] The output presents evacuation information in a way that appeals to the user's sight and hearing, enabling them to quickly understand the information and take action.

[0347] Step 5:

[0348] Users follow the instructions on their devices and take the optimal evacuation route to a safe shelter.

[0349] The input consists of the evacuation route and destination location information presented in Step 4.

[0350] By following the instructions on the device, a specific route to avoid risks is shown, and the actual movement is carried out.

[0351] The output is the safe evacuation actions that users experience. The effective functioning of this process ensures the safety of human lives.

[0352] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0353] This invention is a disaster prevention information transmission system that combines flood risk assessment based on precipitation data and river water level information with an emotion engine that recognizes user emotions. This system consists of three main components: a server, a terminal, and a user.

[0354] The server collects precipitation and forecast information in real time from weather data provision services. In parallel, it acquires water level data from river water level observation stations and uses data preprocessing to detect and remove anomalies. The server also uses a generative AI model to learn the correlation between precipitation and water level changes and calculate flood risk. Based on this risk assessment result, it generates evacuation information. The evacuation information includes specific instructions according to the risk level.

[0355] Furthermore, the server is equipped with an emotion engine that analyzes the user's emotional state. This emotion engine analyzes the user's past response data and current activity to infer emotions such as whether the user is stressed or confused. Based on the output of the emotion engine, the server adjusts the content and method of delivery of evacuation information and provides it in the format that is easiest for the user to understand. For example, if the server detects that the user is confused, it simplifies the information and enables the user to immediately begin evacuation.

[0356] The terminal receives evacuation information transmitted from the server and displays the information via the user interface according to the information presentation instructions provided by the emotion engine. This includes guidance information such as evacuation routes and details of the nearest evacuation shelters.

[0357] Users are expected to receive notifications from their devices and take appropriate evacuation actions based on the information provided. The emotion engine allows users to receive information in a way that suits their emotional state, prompting them to take appropriate action. For example, when the likelihood of flooding increases, the server detects the user's anxiety, and the device displays a message in a gentle tone such as, "Don't worry. You will be safe if you go to the designated evacuation center," thereby alleviating the user's anxiety and encouraging a swift evacuation.

[0358] Thus, the present invention provides a more effective disaster response by combining technical data with an understanding of human emotions.

[0359] The following describes the processing flow.

[0360] Step 1:

[0361] The server collects real-time precipitation and water level data from weather data provision services and river water level observation stations. This data is automatically retrieved via API and stored in a dedicated database.

[0362] Step 2:

[0363] The server preprocesses the collected data, detecting and removing outliers and missing values. This allows the generated AI model to learn accurately regardless of the quality of the data.

[0364] Step 3:

[0365] The server uses a generative AI model to learn the correlation between precipitation and changes in river levels by comparing them with historical data. This model assesses the likelihood of flooding and quantifies the risk.

[0366] Step 4:

[0367] The server analyzes the user's emotional state through an emotion engine, based on the user's past activity data and current situation information. It determines whether the user is stressed or confused.

[0368] Step 5:

[0369] The server integrates the risk assessment of the generation AI model with the output of the emotion engine to generate evacuation information. This information is optimized for the user's emotional state, for example, providing detailed explanations to calm users and concise, clear instructions to confused users.

[0370] Step 6:

[0371] The terminal receives evacuation information sent from the server and implements an information presentation method that responds to the user's emotions. This is done through visually easy-to-understand UI and friendly message sounds.

[0372] Step 7:

[0373] Users check evacuation information on their devices and begin evacuation actions based on that information. They use the guidance and map display on their devices to select the shortest and safest route and head to an evacuation center.

[0374] Through this series of processes, the present invention can realize disaster prevention information transmission that meets the individual needs of users and support swift and accurate evacuation actions.

[0375] (Example 2)

[0376] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0377] Conventional flood risk assessment systems that utilize precipitation and river water level information do not provide information tailored to the user's emotions or level of understanding, which can lead to confusion and anxiety. Furthermore, inaccurate risk assessments based on data containing outliers may occur, resulting in the failure to provide appropriate evacuation information.

[0378] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0379] In this invention, the server includes means for collecting precipitation data and river water level information in real time; information processing means equipped with a generative AI model that learns the correlation between precipitation and water level changes based on the collected data; means for evaluating the flood risk in a specific waterway using the generative AI model and generating evacuation information based on the risk; and means equipped with an emotion processing engine that analyzes emotional states and adjusts the content and method of transmission of evacuation information based on the analysis results. This makes it possible to provide accurate evacuation information that takes into account the emotional state of the user.

[0380] "Precipitation data" refers to information that quantifies the amount of rain that falls on the Earth's surface within a certain period of time.

[0381] "Water level information" refers to data indicating the height of water surfaces in rivers, lakes, and other bodies of water, and is used to understand the volume and flow of water.

[0382] "Means of real-time data collection" refers to technologies and methods for instantly acquiring and making available data that is constantly being generated in real time.

[0383] A "generative AI model" refers to an artificial intelligence model that automatically learns rules and patterns based on data to perform predictions and classifications.

[0384] "Information processing means" refers to methods and technologies for analyzing and processing acquired data to generate or extract valuable information according to a specific purpose.

[0385] "Flood risk" refers to an indicator that shows the degree of danger that water from rivers and other bodies of water will overflow their banks and cause damage to surrounding areas.

[0386] "Evacuation information" refers to information that includes instructions and guidelines for actions necessary to ensure safety during natural disasters.

[0387] "Personal communication devices" refer to electronic devices owned by individuals and used for sending and receiving information, such as mobile phones and smartphones.

[0388] An "emotional processing engine" refers to a technology or system that analyzes an individual's emotional state and understands that state in order to take appropriate action.

[0389] This invention is a disaster prevention information system that accurately assesses flood risk based on precipitation and river water level information and provides users with evacuation information that takes their emotions into consideration. An embodiment thereof is shown below.

[0390] The server collects precipitation and forecast information in real time from weather data provision services using APIs. This ensures that the latest precipitation data is always available. River water level information is obtained by connecting to the database of river water level observation stations. General communication infrastructure and cloud services are used for data collection.

[0391] The collected data is preprocessed on the server to detect and remove any anomalies. This preprocessing is a crucial step in maintaining data quality and improving the accuracy of the analysis results.

[0392] Next, the server utilizes a generative AI model based on the collected data to learn the correlation between precipitation and water level changes. This AI model is based on pattern recognition technology and can perform highly accurate flood risk assessments based on historical data. Specific analysis utilizes technologies such as trained models and neural networks.

[0393] Based on the generated risk assessment, the server creates optimal evacuation information. This evacuation information includes specific instructions tailored to the urgency and risk level. The generated information is automatically transmitted to the user's mobile device or other communication device.

[0394] Furthermore, the server is equipped with an emotion processing engine that analyzes the user's emotional state. This engine analyzes the user's past reaction logs and current operation logs to estimate the degree of stress and anxiety the user is experiencing. Based on this analysis, the presentation format and tone of the evacuation information are adjusted to make it easier for the user to understand and accept.

[0395] The terminal visually displays received evacuation information through a user interface. This includes infographics and evacuation route displays on maps, designed to allow users to intuitively understand the information and take quick action.

[0396] As a concrete example, if there are signs of an impending flood, the server prompts the AI ​​model with a message such as, "Use the precipitation data from the past 24 hours and the current river level data to assess the flood risk for the next 24 hours and generate evacuation information," thereby enabling accurate information generation. This allows for a comprehensive disaster response that includes understanding emotions.

[0397] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0398] Step 1:

[0399] The server collects precipitation and forecast information in real time through the API of a weather data provision service. In parallel, the server obtains water level information from a database of river water level observation stations. The latest precipitation and water level information is obtained as input from an external data provider. This data is stored in data storage for initial processing, in preparation for subsequent processing.

[0400] Step 2:

[0401] The server performs data cleaning on the collected data. Specifically, it uses data preprocessing to detect and remove outliers. For example, it filters out and deletes negative precipitation data and obviously abnormal water level data. Based on this input, it outputs a cleaned dataset and passes that dataset to a data analysis module.

[0402] Step 3:

[0403] The server inputs the processed data into a generating AI model, which learns the correlation between precipitation and water level changes. This AI model uses historical and current real-time data to assess flood risk. Through this process, the model generates a risk assessment output from the input data and calculates a detailed risk level.

[0404] Step 4:

[0405] The server generates evacuation information to be provided to the user based on the output of the generated AI model. This process includes specific instructions and suggested evacuation routes according to the risk level. The output is formatted evacuation information, which is then prepared for transmission to the user's communication device.

[0406] Step 5:

[0407] The server uses an emotion processing engine to analyze the user's emotional state. Inputs include the user's past reaction logs and current activity status. Through this analysis, the server estimates the user's stress and anxiety levels and adjusts the delivery method of evacuation information based on this information. The output is evacuation information optimized for the user.

[0408] Step 6:

[0409] The terminal receives evacuation information transmitted from the server and displays the information through a user interface. The terminal receives evacuation information as input and outputs it in an intuitively understandable format using infographics, maps, and other visual aids. This allows users to quickly grasp the information and take appropriate action.

[0410] (Application Example 2)

[0411] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0412] During natural disasters, information overload and misinformation make accurate and rapid evacuation difficult. Furthermore, there is a lack of evacuation information that can alleviate user stress and confusion in such situations and that can be tailored to individual emotional states. This invention aims to address these problems.

[0413] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0414] In this invention, the server includes means for collecting precipitation data and river water level information in real time, processing means equipped with a generative AI model that learns the correlation between precipitation and water level changes based on the collected data, and processing means equipped with an emotion engine that analyzes individual emotional states and adjusts the content and method of transmission of evacuation information based on the analysis results. This makes it possible to provide information that encourages appropriate and prompt evacuation actions without confusing the user.

[0415] "Precipitation data" refers to information that shows the amount of rain that fell in a specific area or at a specific time.

[0416] "River water level information" refers to data that shows the water level at a specific point in a river.

[0417] "Means of collecting data in real time" refers to a function or device that can collect data instantly.

[0418] A "generative AI model" refers to an artificial intelligence algorithm that analyzes collected data and learns specific rules and patterns.

[0419] "Processing means" refers to methods and devices for analyzing and processing data.

[0420] "Assessing flood risk" means predicting the possibility of a river overflowing and determining the degree of that risk.

[0421] "Means for generating evacuation information" refers to methods and devices for creating information that encourages safe actions when danger is imminent.

[0422] An "emotion engine" refers to a processing unit or function that analyzes the user's emotional state and adjusts the content and presentation of information based on the results.

[0423] "Personal communication device" refers to a communication-capable device belonging to a specific user, such as a smartphone.

[0424] "User interface" refers to the screens and operating environments that allow users to interact with a device or system.

[0425] "Individualized guidance information" refers to specific instructions and guidance provided in a way that is tailored to each user.

[0426] This invention is implemented using a system consisting of a server, a terminal, and a user. The server acquires precipitation data and river water level information in real time. Specifically, it collects data from weather APIs and river water level observation station databases that are publicly available via the internet. Data cleansing is performed using libraries such as NumPy to remove noise contained in the data.

[0427] Next, the server uses a generated AI model based on the collected data to analyze the correlation between precipitation and water level changes and calculate the flood risk. It builds a model using machine learning libraries such as scikit-learn and performs a risk assessment. Based on the results of this risk assessment, appropriate evacuation information is generated.

[0428] Furthermore, the server incorporates an emotion engine that analyzes the user's emotions. Specifically, it analyzes information obtained from the user's device and data on the user's past behavior to infer emotional states such as stress and anxiety. It utilizes the Natural Language Toolkit (NLTK) and other emotion analysis tools.

[0429] Once the user's emotional state is understood, the emotion engine optimizes the content and delivery method of evacuation information. For example, if the user is determined to be "anxious," the evacuation information will be presented in a gentle tone that takes that emotion into consideration. A specific example of a prompt message that could be used is, "The user's emotional state is 'anxious.' Please generate a reassuring message to calm them down."

[0430] The terminal displays the generated evacuation information through a user interface. Utilizing smartphones and tablet devices, the information is displayed in an intuitive and easy-to-understand manner. Visual information, such as real-time evacuation routes on a map, is also used to guide users toward taking swift action.

[0431] As a result, a system is realized that can encourage safe and rapid evacuation actions without causing confusion among users.

[0432] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0433] Step 1:

[0434] The server obtains precipitation data and river level information from a weather API via the internet. This data serves as input. Using the NumPy library, the server performs data cleansing to detect and remove anomalies from the acquired data. As a result, cleansed and accurate weather data is output.

[0435] Step 2:

[0436] The server uses a generated AI model based on the data cleansed in Step 1 to learn the correlation between precipitation and water level changes. Using scikit-learn, it computes this data to calculate flood risk. The results of the risk assessment are output as basic data for generating evacuation information.

[0437] Step 3:

[0438] The emotion engine installed on the server receives data from the user as input and analyzes the user's emotional state. This process uses the Natural Language Toolkit (NLTK) to calculate, for example, stress and anxiety levels. Based on the analysis results, the user's emotional state is output.

[0439] Step 4:

[0440] The server integrates the risk assessment results obtained in step 2 and the user sentiment analysis results in step 3 to generate optimized evacuation information. It generates prompt messages and constructs reassuring messages that correspond to specific emotional states. The generated evacuation information is output in a state ready to be notified to the user.

[0441] Step 5:

[0442] The terminal displays optimized evacuation information received from the server through a user interface. The input is the notified evacuation information. The terminal visualizes the information and outputs it in a format that is easy for the user to understand, such as displaying evacuation routes and the locations of evacuation shelters on a map. Because the information is presented in a user-friendly format, it encourages quick decision-making and action.

[0443] Step 6:

[0444] Users take action to ensure their own safety based on the evacuation information displayed on their device. Because the outputted information is specific and intuitive, users are able to start evacuation actions appropriately.

[0445] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0446] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0447] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0448] [Third Embodiment]

[0449] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0450] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0451] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0452] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0453] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0454] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0455] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0456] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0457] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0458] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0459] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0460] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0461] This invention is a system that rapidly assesses the risk of river flooding due to extreme weather and transmits accurate evacuation information to individuals. This system mainly consists of a server, terminals, and users.

[0462] The server first collects real-time precipitation and river water level data from weather data providers and observation stations. This allows it to constantly monitor the latest weather conditions. Next, the server uses this data to train a generative AI model. The training involves finding correlations between past precipitation and water level change patterns, improving the model's accuracy each time new data is input. This model is used to predict flood risk, taking into account the characteristics of specific topography and rivers.

[0463] If the risk is assessed as high, the server generates a notification, including specific evacuation instructions, based on the prediction results. This notification is sent to terminals belonging to a specific area.

[0464] When the device receives a notification from the server, it immediately provides the user with the information. The notification uses pop-ups and alarm functions to visually and audibly inform the user that evacuation is necessary. Furthermore, the device displays maps and evacuation routes, specifically indicating which direction to evacuate.

[0465] Users are expected to receive notifications and quickly begin evacuation. They will follow the instructions on their device and move safely to a safe evacuation center. The system is designed to be intuitive and easy to use, especially for the elderly and younger generations with low disaster preparedness awareness, thus supporting effective evacuation.

[0466] As a concrete example, suppose heavy rain is predicted to fall in a certain area in a short period of time. The server detects this and determines that the risk of flooding is high based on the water level forecast of nearby rivers. As a result, it sends a notification to users in the affected area via the notification system, instructing them to evacuate immediately to the nearest shelter. This notification is displayed on the user's device, and the information is immediately conveyed to the user, prompting them to take swift evacuation action.

[0467] The following describes the processing flow.

[0468] Step 1:

[0469] The server collects precipitation and forecast information in real time from weather data provision services. This is done using an API and a system that updates the latest data every hour.

[0470] Step 2:

[0471] The server collects water level data from local river level monitoring stations and stores it in a database. This data is recorded at short intervals and used to understand the river conditions.

[0472] Step 3:

[0473] The server preprocesses the collected precipitation and water level data, detecting and removing outliers and missing values. This increases the reliability of the data and enables accurate training of the AI ​​model.

[0474] Step 4:

[0475] The server uses a generative AI model to learn the correlation between precipitation and water level changes from historical data. The model also takes topographic data into consideration and is trained to predict flood risk in specific rivers.

[0476] Step 5:

[0477] The server inputs the latest precipitation forecast data into an AI model and calculates the flood risk for each river. Once the risk assessment is complete, the results are compiled into evacuation information.

[0478] Step 6:

[0479] The server prepares notifications for terminals in specific areas based on evacuation information. These notifications include specific evacuation orders and information about the nearest evacuation shelters.

[0480] Step 7:

[0481] The device receives notifications sent from the server and displays them to the user immediately. The device uses pop-ups and notification sounds to convey urgent information to the user.

[0482] Step 8:

[0483] Users check notifications on their devices and act based on the evacuation instructions provided. They begin moving towards the designated evacuation shelter, using the evacuation route and map displayed on their devices as a guide.

[0484] (Example 1)

[0485] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0486] Conventional flood forecasting and evacuation information provision systems have been unable to respond quickly to rapid weather changes and have difficulty appropriately notifying individual users of accurate evacuation information. As a result, there was a risk that local residents would not be able to evacuate safely. This invention aims to solve these problems and realize highly accurate flood forecasting and personalized evacuation information based on real-time weather information.

[0487] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0488] In this invention, the server includes means for collecting precipitation information and water level information in real time from atmospheric phenomena data-related organizations and monitoring facilities; processing means equipped with a data analysis model that learns the correlation between precipitation and water level changes based on the collected information; means for evaluating the flood risk in a specific area using the data analysis model and generating evacuation information based on said risk; means for notifying individuals' electronic devices of the generated evacuation information; and means for identifying evacuation routes using geographic information of the target area. This enables real-time prediction of flood risk and the provision of rapid and accurate evacuation information.

[0489] "Precipitation information" refers to data about the amount of moisture in the atmosphere that falls to the ground as rain.

[0490] "Water level information" refers to data on the height of the water level in a specific river or body of water.

[0491] "Atmospheric phenomena data-related organizations" refer to government agencies and observation groups that provide meteorological data.

[0492] A "monitoring facility" is a collection of observation devices and equipment installed to collect environmental data for a specific area.

[0493] "Means of real-time data collection" refers to technologies and methods for instantly acquiring constantly updated information.

[0494] A "data analysis model" refers to an artificial intelligence algorithm or system that learns patterns based on different data and makes predictions and judgments.

[0495] "Flood risk" is an assessment that represents the possibility or danger of inundation by rivers or floods under specific conditions.

[0496] "Evacuation information" refers to information that includes instructions and guidelines for safely evacuating during a crisis situation.

[0497] "Electronic devices" is a general term for electrical equipment used for communication and data processing, and includes, for example, mobile phones and computers.

[0498] "Geographic information" refers to information about the topography and terrain of a specific region, and includes maps, place names, and longitude and latitude data.

[0499] An "evacuation route" is the optimal route for moving to a safe location in an emergency.

[0500] This invention provides a system for rapidly and accurately assessing the risk of river flooding due to extreme weather conditions and for providing appropriate evacuation information to individuals. This system mainly consists of a server, terminals, and users.

[0501] To collect data, the server first obtains real-time precipitation and water level information from atmospheric phenomena data-related organizations and monitoring facilities. This is done, for example, by obtaining data via APIs provided by government agencies. The data is then processed through formatting tools to detect and remove outliers and converted into an analyzable format. Machine learning libraries such as TensorFlow are used for analysis.

[0502] The analyzed data is trained by a data analysis model. This model analyzes the correlation between past precipitation and water levels to predict flood risk in a specific area. An example of a prompt used in the model is the instruction, "Predict flood risk based on current precipitation and water level data for the area."

[0503] If a high risk of flooding is detected, the server automatically generates evacuation information suggesting appropriate evacuation routes and notifies individual electronic devices. The notification uses visual and auditory methods to present the information in a way that is intuitively understandable to the user.

[0504] The device receives notifications sent from the server and provides information to the user through pop-ups and alarms. Furthermore, it utilizes geographical information to visually display evacuation routes and support users in evacuating safely.

[0505] Users begin moving to a safe evacuation center by following instructions from their device. This system is designed to be particularly easy to use for the elderly and young people with low disaster preparedness awareness, and supports rapid evacuation.

[0506] As a concrete example, consider a scenario where heavy rain is predicted in a certain area in a short period of time. The server immediately receives this information and evaluates the flood risk based on a generated AI model. Depending on the result, the server notifies users in the affected area via their devices with information urging them to evacuate quickly. By quickly conveying this notification to users, they can take safe evacuation action.

[0507] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0508] Step 1:

[0509] The server uses APIs to acquire precipitation and water level information in real time from atmospheric phenomena data-related organizations and monitoring facilities. The acquired data is passed to a data processing system where outliers are detected and removed. This generates a clean dataset. This clean data is then stored in a database for analysis.

[0510] Step 2:

[0511] The server updates the generated AI model using the formatted data. Specifically, it uses machine learning libraries such as TensorFlow to learn the correlation between precipitation and water level changes based on historical data. As new data is input into the model, the model's prediction accuracy improves. As a result, a model is output that can predict the flood risk of a specific area with high accuracy.

[0512] Step 3:

[0513] The server sends a prompt message to the generating AI model. Specifically, the prompt instructs the model to "predict flood risk based on current regional precipitation and water level data." Upon receiving this instruction, the model analyzes the collected data and assesses the flood risk for the specific area. As a result of the assessment, evacuation information is generated according to the level of risk.

[0514] Step 4:

[0515] The server generates appropriate notifications for each user's electronic device based on the generated evacuation information. These notifications include evacuation routes and destinations that take the user's location into account. This information is transmitted to each device via the communication network. Users must pay immediate attention when a notification is sent to their device.

[0516] Step 5:

[0517] The terminal receives notifications from the server and provides them to the user through visual and auditory means. Specifically, it displays pop-ups on the screen and sounds an audible alarm to alert the user. It also displays evacuation routes on a map using geographical information and instructs the user on specific next steps. Because this information is immediate, users are expected to respond promptly.

[0518] Step 6:

[0519] Users follow the instructions provided by the device and move safely to the evacuation shelter using the designated evacuation route. The device continuously updates real-time information during evacuation, allowing users to always access the latest safety information. The device's interface is designed to be intuitive and easy to use, especially for users with low disaster preparedness awareness.

[0520] (Application Example 1)

[0521] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0522] In recent years, the risk of river flooding due to extreme weather has increased, necessitating rapid and accurate evacuation. However, there is a lack of systems that provide optimal evacuation route information and intuitive guidance to people within buildings with physical space (e.g., commercial and public facilities). In particular, insufficient guidance on evacuation routes and safe shelters hinders rapid evacuation.

[0523] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0524] In this invention, the server includes means for collecting precipitation data and river water level information in real time; processing means equipped with a generative AI model that learns the correlation between precipitation and water level changes based on the collected data; means for evaluating the flood risk in a specific river using the generative AI model and generating evacuation information based on the risk; and means for notifying a communication device of the generated evacuation information and providing evacuation route and shelter information according to location information. This enables rapid and intuitive evacuation guidance for personnel inside buildings.

[0525] "Precipitation data" refers to information that measures the amount of rain that fell in a specific area within a certain period of time.

[0526] "River water level information" refers to data that measures the water level at a specific point in a river in real time.

[0527] A "generative AI model" is an artificial intelligence model that learns patterns based on past data and makes predictions and classifications based on new data.

[0528] "Flood risk" is an indicator that shows the danger of water levels rising in a particular river and causing it to overflow.

[0529] "Communication devices" are electronic devices used to send and receive information, and include smartphones and tablets.

[0530] An "evacuation route" is a path used to evacuate to a safe place in the event of a disaster or emergency.

[0531] A "shelter" is a facility or place used to provide temporary safety and shelter during a disaster.

[0532] The system for realizing this invention consists of three elements: a server, a terminal, and a user. The server first collects precipitation data and river water level information in real time. This data is obtained from external weather data provision services and observation stations, and is configured to respond quickly to sudden changes in weather.

[0533] The server uses a generative AI model based on the collected data to learn the correlation between precipitation and water level changes. This model incorporates machine learning algorithms that can analyze historical data and predict flood risk in specific rivers with high accuracy. To improve the performance of the generative AI model, it updates itself each time new data is input.

[0534] If a high risk of flooding is assessed, the server generates evacuation information based on that information and notifies the user's communication device. These communication devices are common devices such as smartphones and tablets, and are capable of receiving information in real time.

[0535] The terminal displays the notified evacuation information through a user interface. This interface is intuitive to use and provides the user with specific evacuation directions through audio and visual output. This allows the user to select the optimal evacuation route based on their location.

[0536] As a concrete example, let's consider a scenario where extremely heavy rain is predicted to fall in a certain area in a short period of time. The server uses a generative AI model to predict the water levels of nearby rivers and recognizes that the risk is increasing. As a result, a notification is sent to users in that area urging them to evacuate quickly.

[0537] Example of a prompt:

[0538] "Input local weather data and use that data to predict flood risk. Also, generate notifications suggesting the best evacuation routes within the shopping mall."

[0539] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0540] Step 1:

[0541] The server collects precipitation data and river water level information in real time from weather data provision services and observation stations.

[0542] The input is an online weather data stream.

[0543] The output consists of the latest precipitation and water level data, which the server receives to prepare for analysis in the next step.

[0544] Step 2:

[0545] The server inputs the collected data into a generating AI model to assess the flood risk.

[0546] The input consists of precipitation and water level data obtained in Step 1.

[0547] Using the data, a generative AI model performs data calculations to recognize patterns of rapid water level rises by comparing them with past trends.

[0548] The output is a predicted value regarding the flood risk of a specific river. This quantifies the degree of flood risk.

[0549] Step 3:

[0550] The server generates evacuation information based on the assessed risk and creates a message to notify communication devices.

[0551] The input is the predicted flood risk value output in step 2.

[0552] If the risk level is high, a logic is executed to determine which areas to issue what kind of evacuation orders to.

[0553] The output is a message containing specific evacuation instructions and evacuation route information, which is sent to the user's communication device.

[0554] Step 4:

[0555] The terminal displays evacuation information received from the server through a user interface and prompts evacuation visually and audibly.

[0556] The input is the evacuation message generated by the server in step 3.

[0557] The device's display and speakers are used to provide users with interactive evacuation route guidance.

[0558] The output presents evacuation information in a way that appeals to the user's sight and hearing, enabling them to quickly understand the information and take action.

[0559] Step 5:

[0560] Users follow the instructions on their devices and take the optimal evacuation route to a safe shelter.

[0561] The input consists of the evacuation route and destination location information presented in Step 4.

[0562] By following the instructions on the device, a specific route to avoid risks is shown, and the actual movement is carried out.

[0563] The output is the safe evacuation actions that users experience. The effective functioning of this process ensures the safety of human lives.

[0564] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0565] This invention is a disaster prevention information transmission system that combines flood risk assessment based on precipitation data and river water level information with an emotion engine that recognizes user emotions. This system consists of three main components: a server, a terminal, and a user.

[0566] The server collects precipitation and forecast information in real time from weather data provision services. In parallel, it acquires water level data from river water level observation stations and uses data preprocessing to detect and remove anomalies. The server also uses a generative AI model to learn the correlation between precipitation and water level changes and calculate flood risk. Based on this risk assessment result, it generates evacuation information. The evacuation information includes specific instructions according to the risk level.

[0567] Furthermore, the server is equipped with an emotion engine that analyzes the user's emotional state. This emotion engine analyzes the user's past response data and current activity to infer emotions such as whether the user is stressed or confused. Based on the output of the emotion engine, the server adjusts the content and method of delivery of evacuation information and provides it in the format that is easiest for the user to understand. For example, if the server detects that the user is confused, it simplifies the information and enables the user to immediately begin evacuation.

[0568] The terminal receives evacuation information transmitted from the server and displays the information via the user interface according to the information presentation instructions provided by the emotion engine. This includes guidance information such as evacuation routes and details of the nearest evacuation shelters.

[0569] Users are expected to receive notifications from their devices and take appropriate evacuation actions based on the information provided. The emotion engine allows users to receive information in a way that suits their emotional state, prompting them to take appropriate action. For example, when the likelihood of flooding increases, the server detects the user's anxiety, and the device displays a message in a gentle tone such as, "Don't worry. You will be safe if you go to the designated evacuation center," thereby alleviating the user's anxiety and encouraging a swift evacuation.

[0570] Thus, the present invention provides a more effective disaster response by combining technical data with an understanding of human emotions.

[0571] The following describes the processing flow.

[0572] Step 1:

[0573] The server collects real-time precipitation and water level data from weather data provision services and river water level observation stations. This data is automatically retrieved via API and stored in a dedicated database.

[0574] Step 2:

[0575] The server preprocesses the collected data, detecting and removing outliers and missing values. This allows the generated AI model to learn accurately regardless of the quality of the data.

[0576] Step 3:

[0577] The server uses a generative AI model to learn the correlation between precipitation and changes in river levels by comparing them with historical data. This model assesses the likelihood of flooding and quantifies the risk.

[0578] Step 4:

[0579] The server analyzes the user's emotional state through an emotion engine, based on the user's past activity data and current situation information. It determines whether the user is stressed or confused.

[0580] Step 5:

[0581] The server integrates the risk assessment of the generation AI model with the output of the emotion engine to generate evacuation information. This information is optimized for the user's emotional state, for example, providing detailed explanations to calm users and concise, clear instructions to confused users.

[0582] Step 6:

[0583] The terminal receives evacuation information sent from the server and implements an information presentation method that responds to the user's emotions. This is done through visually easy-to-understand UI and friendly message sounds.

[0584] Step 7:

[0585] Users check evacuation information on their devices and begin evacuation actions based on that information. They use the guidance and map display on their devices to select the shortest and safest route and head to an evacuation center.

[0586] Through this series of processes, the present invention can realize disaster prevention information transmission that meets the individual needs of users and support swift and accurate evacuation actions.

[0587] (Example 2)

[0588] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0589] Conventional flood risk assessment systems that utilize precipitation and river water level information do not provide information tailored to the user's emotions or level of understanding, which can lead to confusion and anxiety. Furthermore, inaccurate risk assessments based on data containing outliers may occur, resulting in the failure to provide appropriate evacuation information.

[0590] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0591] In this invention, the server includes means for collecting precipitation data and river water level information in real time; information processing means equipped with a generative AI model that learns the correlation between precipitation and water level changes based on the collected data; means for evaluating the flood risk in a specific waterway using the generative AI model and generating evacuation information based on the risk; and means equipped with an emotion processing engine that analyzes emotional states and adjusts the content and method of transmission of evacuation information based on the analysis results. This makes it possible to provide accurate evacuation information that takes into account the emotional state of the user.

[0592] "Precipitation data" refers to information that quantifies the amount of rain that falls on the Earth's surface within a certain period of time.

[0593] "Water level information" refers to data indicating the height of water surfaces in rivers, lakes, and other bodies of water, and is used to understand the volume and flow of water.

[0594] "Means of real-time data collection" refers to technologies and methods for instantly acquiring and making available data that is constantly being generated in real time.

[0595] A "generative AI model" refers to an artificial intelligence model that automatically learns rules and patterns based on data to perform predictions and classifications.

[0596] "Information processing means" refers to methods and technologies for analyzing and processing acquired data to generate or extract valuable information according to a specific purpose.

[0597] "Flood risk" refers to an indicator that shows the degree of danger that water from rivers and other bodies of water will overflow their banks and cause damage to surrounding areas.

[0598] "Evacuation information" refers to information that includes instructions and guidelines for actions necessary to ensure safety during natural disasters.

[0599] "Personal communication devices" refer to electronic devices owned by individuals and used for sending and receiving information, such as mobile phones and smartphones.

[0600] An "emotional processing engine" refers to a technology or system that analyzes an individual's emotional state and understands that state in order to take appropriate action.

[0601] This invention is a disaster prevention information system that accurately assesses flood risk based on precipitation and river water level information and provides users with evacuation information that takes their emotions into consideration. An embodiment thereof is shown below.

[0602] The server collects precipitation and forecast information in real time from weather data provision services using APIs. This ensures that the latest precipitation data is always available. River water level information is obtained by connecting to the database of river water level observation stations. General communication infrastructure and cloud services are used for data collection.

[0603] The collected data is preprocessed on the server to detect and remove any anomalies. This preprocessing is a crucial step in maintaining data quality and improving the accuracy of the analysis results.

[0604] Next, the server utilizes a generative AI model based on the collected data to learn the correlation between precipitation and water level changes. This AI model is based on pattern recognition technology and can perform highly accurate flood risk assessments based on historical data. Specific analysis utilizes technologies such as trained models and neural networks.

[0605] Based on the generated risk assessment, the server creates optimal evacuation information. This evacuation information includes specific instructions tailored to the urgency and risk level. The generated information is automatically transmitted to the user's mobile device or other communication device.

[0606] Furthermore, the server is equipped with an emotion processing engine that analyzes the user's emotional state. This engine analyzes the user's past reaction logs and current operation logs to estimate the degree of stress and anxiety the user is experiencing. Based on this analysis, the presentation format and tone of the evacuation information are adjusted to make it easier for the user to understand and accept.

[0607] The terminal visually displays received evacuation information through a user interface. This includes infographics and evacuation route displays on maps, designed to allow users to intuitively understand the information and take quick action.

[0608] As a concrete example, if there are signs of an impending flood, the server prompts the AI ​​model with a message such as, "Use the precipitation data from the past 24 hours and the current river level data to assess the flood risk for the next 24 hours and generate evacuation information," thereby enabling accurate information generation. This allows for a comprehensive disaster response that includes understanding emotions.

[0609] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0610] Step 1:

[0611] The server collects precipitation and forecast information in real time through the API of a weather data provision service. In parallel, the server obtains water level information from a database of river water level observation stations. The latest precipitation and water level information is obtained as input from an external data provider. This data is stored in data storage for initial processing, in preparation for subsequent processing.

[0612] Step 2:

[0613] The server performs data cleaning on the collected data. Specifically, it uses data preprocessing to detect and remove outliers. For example, it filters out and deletes negative precipitation data and obviously abnormal water level data. Based on this input, it outputs a cleaned dataset and passes that dataset to a data analysis module.

[0614] Step 3:

[0615] The server inputs the processed data into a generating AI model, which learns the correlation between precipitation and water level changes. This AI model uses historical and current real-time data to assess flood risk. Through this process, the model generates a risk assessment output from the input data and calculates a detailed risk level.

[0616] Step 4:

[0617] The server generates evacuation information to be provided to the user based on the output of the generated AI model. This process includes specific instructions and suggested evacuation routes according to the risk level. The output is formatted evacuation information, which is then prepared for transmission to the user's communication device.

[0618] Step 5:

[0619] The server uses an emotion processing engine to analyze the user's emotional state. Inputs include the user's past reaction logs and current activity status. Through this analysis, the server estimates the user's stress and anxiety levels and adjusts the delivery method of evacuation information based on this information. The output is evacuation information optimized for the user.

[0620] Step 6:

[0621] The terminal receives evacuation information transmitted from the server and displays the information through a user interface. The terminal receives evacuation information as input and outputs it in an intuitively understandable format using infographics, maps, and other visual aids. This allows users to quickly grasp the information and take appropriate action.

[0622] (Application Example 2)

[0623] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0624] During natural disasters, information overload and misinformation make accurate and rapid evacuation difficult. Furthermore, there is a lack of evacuation information that can alleviate user stress and confusion in such situations and that can be tailored to individual emotional states. This invention aims to address these problems.

[0625] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0626] In this invention, the server includes means for collecting precipitation data and river water level information in real time, processing means equipped with a generative AI model that learns the correlation between precipitation and water level changes based on the collected data, and processing means equipped with an emotion engine that analyzes individual emotional states and adjusts the content and method of transmission of evacuation information based on the analysis results. This makes it possible to provide information that encourages appropriate and prompt evacuation actions without confusing the user.

[0627] "Precipitation data" refers to information that shows the amount of rain that fell in a specific area or at a specific time.

[0628] "River water level information" refers to data that shows the water level at a specific point in a river.

[0629] "Means of collecting data in real time" refers to a function or device that can collect data instantly.

[0630] A "generative AI model" refers to an artificial intelligence algorithm that analyzes collected data and learns specific rules and patterns.

[0631] "Processing means" refers to methods and devices for analyzing and processing data.

[0632] "Assessing flood risk" means predicting the possibility of a river overflowing and determining the degree of that risk.

[0633] "Means for generating evacuation information" refers to methods and devices for creating information that encourages safe actions when danger is imminent.

[0634] An "emotion engine" refers to a processing unit or function that analyzes the user's emotional state and adjusts the content and presentation of information based on the results.

[0635] "Personal communication device" refers to a communication-capable device belonging to a specific user, such as a smartphone.

[0636] "User interface" refers to the screens and operating environments that allow users to interact with a device or system.

[0637] "Individualized guidance information" refers to specific instructions and guidance provided in a way that is tailored to each user.

[0638] This invention is implemented using a system consisting of a server, a terminal, and a user. The server acquires precipitation data and river water level information in real time. Specifically, it collects data from weather APIs and river water level observation station databases that are publicly available via the internet. Data cleansing is performed using libraries such as NumPy to remove noise contained in the data.

[0639] Next, the server uses a generated AI model based on the collected data to analyze the correlation between precipitation and water level changes and calculate the flood risk. It builds a model using machine learning libraries such as scikit-learn and performs a risk assessment. Based on the results of this risk assessment, appropriate evacuation information is generated.

[0640] Furthermore, the server incorporates an emotion engine that analyzes the user's emotions. Specifically, it analyzes information obtained from the user's device and data on the user's past behavior to infer emotional states such as stress and anxiety. It utilizes the Natural Language Toolkit (NLTK) and other emotion analysis tools.

[0641] Once the user's emotional state is understood, the emotion engine optimizes the content and delivery method of evacuation information. For example, if the user is determined to be "anxious," the evacuation information will be presented in a gentle tone that takes that emotion into consideration. A specific example of a prompt message that could be used is, "The user's emotional state is 'anxious.' Please generate a reassuring message to calm them down."

[0642] The terminal displays the generated evacuation information through a user interface. Utilizing smartphones and tablet devices, the information is displayed in an intuitive and easy-to-understand manner. Visual information, such as real-time evacuation routes on a map, is also used to guide users toward taking swift action.

[0643] As a result, a system is realized that can encourage safe and rapid evacuation actions without causing confusion among users.

[0644] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0645] Step 1:

[0646] The server obtains precipitation data and river water level information from a weather API via the internet. This data serves as input. Using the NumPy library, the server performs data cleansing to detect and remove anomalies from the obtained data. As a result, cleansed and accurate weather data is output.

[0647] Step 2:

[0648] The server uses a generative AI model based on the data cleansed in Step 1 to learn the correlation between precipitation and water level changes. Using scikit-learn, it computes this data and calculates flood risk. The results of the risk assessment are output as basic data for generating evacuation information.

[0649] Step 3:

[0650] The emotion engine installed on the server receives data from the user as input and analyzes the user's emotional state. This process uses the Natural Language Toolkit (NLTK) to calculate, for example, stress and anxiety levels. Based on the analysis results, the user's emotional state is output.

[0651] Step 4:

[0652] The server integrates the risk assessment results obtained in step 2 and the user sentiment analysis results in step 3 to generate optimized evacuation information. It generates prompt messages and constructs reassuring messages that correspond to specific emotional states. The generated evacuation information is output in a state ready to be notified to the user.

[0653] Step 5:

[0654] The terminal displays optimized evacuation information received from the server through a user interface. The input is the notified evacuation information. The terminal visualizes the information and outputs it in a format that is easy for the user to understand, such as displaying evacuation routes and the locations of evacuation shelters on a map. Because the information is presented in a user-friendly format, it encourages quick decision-making and action.

[0655] Step 6:

[0656] Users take action to ensure their own safety based on the evacuation information displayed on their device. Because the outputted information is specific and intuitive, users are able to start evacuation actions appropriately.

[0657] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0658] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0659] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0660] [Fourth Embodiment]

[0661] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0662] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0663] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0664] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0665] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0666] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0667] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0668] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0669] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0670] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0671] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0672] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0673] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0674] This invention is a system that rapidly assesses the risk of river flooding due to extreme weather and transmits accurate evacuation information to individuals. This system mainly consists of a server, terminals, and users.

[0675] The server first collects real-time precipitation and river water level data from weather data providers and observation stations. This allows it to constantly monitor the latest weather conditions. Next, the server uses this data to train a generative AI model. The training involves finding correlations between past precipitation and water level change patterns, improving the model's accuracy each time new data is input. This model is used to predict flood risk, taking into account the characteristics of specific topography and rivers.

[0676] If the risk is assessed as high, the server generates a notification, including specific evacuation instructions, based on the prediction results. This notification is sent to terminals belonging to a specific area.

[0677] When the device receives a notification from the server, it immediately provides the user with the information. The notification uses pop-ups and alarm functions to visually and audibly inform the user that evacuation is necessary. Furthermore, the device displays maps and evacuation routes, specifically indicating which direction to evacuate.

[0678] Users are expected to receive notifications and quickly begin evacuation. They will follow the instructions on their device and move safely to a safe evacuation center. The system is designed to be intuitive and easy to use, especially for the elderly and younger generations with low disaster preparedness awareness, thus supporting effective evacuation.

[0679] As a concrete example, suppose heavy rain is predicted to fall in a certain area in a short period of time. The server detects this and determines that the risk of flooding is high based on the water level forecast of nearby rivers. As a result, it sends a notification to users in the affected area via the notification system, instructing them to evacuate immediately to the nearest shelter. This notification is displayed on the user's device, and the information is immediately conveyed to the user, prompting them to take swift evacuation action.

[0680] The following describes the processing flow.

[0681] Step 1:

[0682] The server collects precipitation and forecast information in real time from weather data provision services. This is done using an API and a system that updates the latest data every hour.

[0683] Step 2:

[0684] The server collects water level data from local river level monitoring stations and stores it in a database. This data is recorded at short intervals and used to understand the river conditions.

[0685] Step 3:

[0686] The server preprocesses the collected precipitation and water level data, detecting and removing outliers and missing values. This increases the reliability of the data and enables accurate training of the AI ​​model.

[0687] Step 4:

[0688] The server uses a generative AI model to learn the correlation between precipitation and water level changes from historical data. The model also takes topographic data into consideration and is trained to predict flood risk in specific rivers.

[0689] Step 5:

[0690] The server inputs the latest precipitation forecast data into an AI model and calculates the flood risk for each river. Once the risk assessment is complete, the results are compiled into evacuation information.

[0691] Step 6:

[0692] The server prepares notifications for terminals in specific areas based on evacuation information. These notifications include specific evacuation orders and information about the nearest evacuation shelters.

[0693] Step 7:

[0694] The device receives notifications sent from the server and displays them to the user immediately. The device uses pop-ups and notification sounds to convey urgent information to the user.

[0695] Step 8:

[0696] Users check notifications on their devices and act based on the evacuation instructions provided. They begin moving towards the designated evacuation shelter, using the evacuation route and map displayed on their devices as a guide.

[0697] (Example 1)

[0698] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0699] Conventional flood forecasting and evacuation information provision systems have been unable to respond quickly to rapid weather changes and have difficulty appropriately notifying individual users of accurate evacuation information. As a result, there was a risk that local residents would not be able to evacuate safely. This invention aims to solve these problems and realize highly accurate flood forecasting and personalized evacuation information based on real-time weather information.

[0700] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0701] In this invention, the server includes means for collecting precipitation information and water level information in real time from atmospheric phenomena data-related organizations and monitoring facilities; processing means equipped with a data analysis model that learns the correlation between precipitation and water level changes based on the collected information; means for evaluating the flood risk in a specific area using the data analysis model and generating evacuation information based on said risk; means for notifying individuals' electronic devices of the generated evacuation information; and means for identifying evacuation routes using geographic information of the target area. This enables real-time prediction of flood risk and the provision of rapid and accurate evacuation information.

[0702] "Precipitation information" refers to data about the amount of moisture in the atmosphere that falls to the ground as rain.

[0703] "Water level information" refers to data on the height of the water level in a specific river or body of water.

[0704] "Atmospheric phenomena data-related organizations" refer to government agencies and observation groups that provide meteorological data.

[0705] A "monitoring facility" is a collection of observation devices and equipment installed to collect environmental data for a specific area.

[0706] "Means of real-time data collection" refers to technologies and methods for instantly acquiring constantly updated information.

[0707] A "data analysis model" refers to an artificial intelligence algorithm or system that learns patterns based on different data and makes predictions and judgments.

[0708] "Flood risk" is an assessment that represents the possibility or danger of inundation by rivers or floods under specific conditions.

[0709] "Evacuation information" refers to information that includes instructions and guidelines for safely evacuating during a crisis situation.

[0710] "Electronic devices" is a general term for electrical equipment used for communication and data processing, and includes, for example, mobile phones and computers.

[0711] "Geographic information" refers to information about the topography and terrain of a specific region, and includes maps, place names, and longitude and latitude data.

[0712] An "evacuation route" is the optimal route for moving to a safe location in an emergency.

[0713] This invention provides a system for rapidly and accurately assessing the risk of river flooding due to extreme weather conditions and for providing appropriate evacuation information to individuals. This system mainly consists of a server, terminals, and users.

[0714] To collect data, the server first obtains real-time precipitation and water level information from atmospheric phenomena data-related organizations and monitoring facilities. This is done, for example, by obtaining data via APIs provided by government agencies. The data is then processed through formatting tools to detect and remove outliers and converted into an analyzable format. Machine learning libraries such as TensorFlow are used for analysis.

[0715] The analyzed data is trained by a data analysis model. This model analyzes the correlation between past precipitation and water levels to predict flood risk in a specific area. An example of a prompt used in the model is the instruction, "Predict flood risk based on current precipitation and water level data for the area."

[0716] If a high risk of flooding is detected, the server automatically generates evacuation information suggesting appropriate evacuation routes and notifies individual electronic devices. The notification uses visual and auditory methods to present the information in a way that is intuitively understandable to the user.

[0717] The device receives notifications sent from the server and provides information to the user through pop-ups and alarms. Furthermore, it utilizes geographical information to visually display evacuation routes and support users in evacuating safely.

[0718] Users begin moving to a safe evacuation center by following instructions from their device. This system is designed to be particularly easy to use for the elderly and young people with low disaster preparedness awareness, and supports rapid evacuation.

[0719] As a concrete example, consider a scenario where heavy rain is predicted in a certain area in a short period of time. The server immediately receives this information and evaluates the flood risk based on a generated AI model. Depending on the result, the server notifies users in the affected area via their devices with information urging them to evacuate quickly. By quickly conveying this notification to users, they can take safe evacuation action.

[0720] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0721] Step 1:

[0722] The server uses APIs to acquire precipitation and water level information in real time from atmospheric phenomena data-related organizations and monitoring facilities. The acquired data is passed to a data processing system where outliers are detected and removed. This generates a clean dataset. This clean data is then stored in a database for analysis.

[0723] Step 2:

[0724] The server updates the generated AI model using the formatted data. Specifically, it uses machine learning libraries such as TensorFlow to learn the correlation between precipitation and water level changes based on historical data. As new data is input into the model, the model's prediction accuracy improves. As a result, a model is output that can predict the flood risk of a specific area with high accuracy.

[0725] Step 3:

[0726] The server sends a prompt message to the generating AI model. Specifically, the prompt instructs the model to "predict flood risk based on current regional precipitation and water level data." Upon receiving this instruction, the model analyzes the collected data and assesses the flood risk for the specific area. As a result of the assessment, evacuation information is generated according to the level of risk.

[0727] Step 4:

[0728] The server generates appropriate notifications for each user's electronic device based on the generated evacuation information. These notifications include evacuation routes and destinations that take the user's location into account. This information is transmitted to each device via the communication network. Users must pay immediate attention when a notification is sent to their device.

[0729] Step 5:

[0730] The terminal receives notifications from the server and provides them to the user through visual and auditory means. Specifically, it displays pop-ups on the screen and sounds an audible alarm to alert the user. It also displays evacuation routes on a map using geographical information and instructs the user on specific next steps. Because this information is immediate, users are expected to respond promptly.

[0731] Step 6:

[0732] Users follow the instructions provided by the device and move safely to the evacuation shelter using the designated evacuation route. The device continuously updates real-time information during evacuation, allowing users to always access the latest safety information. The device's interface is designed to be intuitive and easy to use, especially for users with low disaster preparedness awareness.

[0733] (Application Example 1)

[0734] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0735] In recent years, the risk of river flooding due to extreme weather has increased, necessitating rapid and accurate evacuation. However, there is a lack of systems that provide optimal evacuation route information and intuitive guidance to people within buildings with physical space (e.g., commercial and public facilities). In particular, insufficient guidance on evacuation routes and safe shelters hinders rapid evacuation.

[0736] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0737] In this invention, the server includes means for collecting precipitation data and river water level information in real time; processing means equipped with a generative AI model that learns the correlation between precipitation and water level changes based on the collected data; means for evaluating the flood risk in a specific river using the generative AI model and generating evacuation information based on the risk; and means for notifying a communication device of the generated evacuation information and providing evacuation route and shelter information according to location information. This enables rapid and intuitive evacuation guidance for personnel inside buildings.

[0738] "Precipitation data" refers to information that measures the amount of rain that fell in a specific area within a certain period of time.

[0739] "River water level information" refers to data that measures the water level at a specific point in a river in real time.

[0740] A "generative AI model" is an artificial intelligence model that learns patterns based on past data and makes predictions and classifications based on new data.

[0741] "Flood risk" is an indicator that shows the danger of water levels rising in a particular river and causing it to overflow.

[0742] "Communication devices" are electronic devices used to send and receive information, and include smartphones and tablets.

[0743] An "evacuation route" is a path used to evacuate to a safe place in the event of a disaster or emergency.

[0744] A "shelter" is a facility or place used to provide temporary safety and shelter during a disaster.

[0745] The system for realizing this invention consists of three elements: a server, a terminal, and a user. The server first collects precipitation data and river water level information in real time. This data is obtained from external weather data provision services and observation stations, and is configured to respond quickly to sudden changes in weather.

[0746] The server uses a generative AI model based on the collected data to learn the correlation between precipitation and water level changes. This model incorporates machine learning algorithms that can analyze historical data and predict flood risk in specific rivers with high accuracy. To improve the performance of the generative AI model, it updates itself each time new data is input.

[0747] If a high risk of flooding is assessed, the server generates evacuation information based on that information and notifies the user's communication device. These communication devices are common devices such as smartphones and tablets, and are capable of receiving information in real time.

[0748] The terminal displays the notified evacuation information through a user interface. This interface is intuitive to use and provides the user with specific evacuation directions through audio and visual output. This allows the user to select the optimal evacuation route based on their location.

[0749] As a concrete example, let's consider a scenario where extremely heavy rain is predicted to fall in a certain area in a short period of time. The server uses a generative AI model to predict the water levels of nearby rivers and recognizes that the risk is increasing. As a result, a notification is sent to users in that area urging them to evacuate quickly.

[0750] Example of a prompt:

[0751] "Input local weather data and use that data to predict flood risk. Also, generate notifications suggesting the best evacuation routes within the shopping mall."

[0752] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0753] Step 1:

[0754] The server collects precipitation data and river water level information in real time from weather data provision services and observation stations.

[0755] The input is an online weather data stream.

[0756] The output consists of the latest precipitation and water level data, which the server receives to prepare for analysis in the next step.

[0757] Step 2:

[0758] The server inputs the collected data into a generating AI model to assess the flood risk.

[0759] The input consists of precipitation and water level data obtained in Step 1.

[0760] Using the data, a generative AI model performs data calculations to recognize patterns of rapid water level rises by comparing them with past trends.

[0761] The output is a predicted value regarding the flood risk of a specific river. This quantifies the degree of flood risk.

[0762] Step 3:

[0763] The server generates evacuation information based on the assessed risk and creates a message to notify communication devices.

[0764] The input is the predicted flood risk value output in step 2.

[0765] If the risk level is high, a logic is executed to determine which areas to issue what kind of evacuation orders to.

[0766] The output is a message containing specific evacuation instructions and evacuation route information, which is sent to the user's communication device.

[0767] Step 4:

[0768] The terminal displays evacuation information received from the server through a user interface and prompts evacuation visually and audibly.

[0769] The input is the evacuation message generated by the server in step 3.

[0770] The device's display and speakers are used to provide users with interactive evacuation route guidance.

[0771] The output presents evacuation information in a way that appeals to the user's sight and hearing, enabling them to quickly understand the information and take action.

[0772] Step 5:

[0773] Users follow the instructions on their devices and take the optimal evacuation route to a safe shelter.

[0774] The input consists of the evacuation route and destination location information presented in Step 4.

[0775] By following the instructions on the device, a specific route to avoid risks is shown, and the actual movement is carried out.

[0776] The output is the safe evacuation actions that users experience. The effective functioning of this process ensures the safety of human lives.

[0777] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0778] This invention is a disaster prevention information transmission system that combines flood risk assessment based on precipitation data and river water level information with an emotion engine that recognizes user emotions. This system consists of three main components: a server, a terminal, and a user.

[0779] The server collects precipitation and forecast information in real time from weather data provision services. In parallel, it acquires water level data from river water level observation stations and uses data preprocessing to detect and remove anomalies. The server also uses a generative AI model to learn the correlation between precipitation and water level changes and calculate flood risk. Based on this risk assessment result, it generates evacuation information. The evacuation information includes specific instructions according to the risk level.

[0780] Furthermore, the server is equipped with an emotion engine that analyzes the user's emotional state. This emotion engine analyzes the user's past response data and current activity to infer emotions such as whether the user is stressed or confused. Based on the output of the emotion engine, the server adjusts the content and method of delivery of evacuation information and provides it in the format that is easiest for the user to understand. For example, if the server detects that the user is confused, it simplifies the information and enables the user to immediately begin evacuation.

[0781] The terminal receives evacuation information transmitted from the server and displays the information via the user interface according to the information presentation instructions provided by the emotion engine. This includes guidance information such as evacuation routes and details of the nearest evacuation shelters.

[0782] Users are expected to receive notifications from their devices and take appropriate evacuation actions based on the information provided. The emotion engine allows users to receive information in a way that suits their emotional state, prompting them to take appropriate action. For example, when the likelihood of flooding increases, the server detects the user's anxiety, and the device displays a message in a gentle tone such as, "Don't worry. You will be safe if you go to the designated evacuation center," thereby alleviating the user's anxiety and encouraging a swift evacuation.

[0783] Thus, the present invention provides a more effective disaster response by combining technical data with an understanding of human emotions.

[0784] The following describes the processing flow.

[0785] Step 1:

[0786] The server collects real-time precipitation and water level data from weather data provision services and river water level observation stations. This data is automatically retrieved via API and stored in a dedicated database.

[0787] Step 2:

[0788] The server preprocesses the collected data, detecting and removing outliers and missing values. This allows the generated AI model to learn accurately regardless of the quality of the data.

[0789] Step 3:

[0790] The server uses a generative AI model to learn the correlation between precipitation and changes in river levels by comparing them with historical data. This model assesses the likelihood of flooding and quantifies the risk.

[0791] Step 4:

[0792] The server analyzes the user's emotional state through an emotion engine, based on the user's past activity data and current situation information. It determines whether the user is stressed or confused.

[0793] Step 5:

[0794] The server integrates the risk assessment of the generation AI model with the output of the emotion engine to generate evacuation information. This information is optimized for the user's emotional state, for example, providing detailed explanations to calm users and concise, clear instructions to confused users.

[0795] Step 6:

[0796] The terminal receives evacuation information sent from the server and implements an information presentation method that responds to the user's emotions. This is done through visually easy-to-understand UI and friendly message sounds.

[0797] Step 7:

[0798] Users check evacuation information on their devices and begin evacuation actions based on that information. They use the guidance and map display on their devices to select the shortest and safest route and head to an evacuation center.

[0799] Through this series of processes, the present invention can realize disaster prevention information transmission that meets the individual needs of users and support swift and accurate evacuation actions.

[0800] (Example 2)

[0801] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0802] Conventional flood risk assessment systems that utilize precipitation and river water level information do not provide information tailored to the user's emotions or level of understanding, which can lead to confusion and anxiety. Furthermore, inaccurate risk assessments based on data containing outliers may occur, resulting in the failure to provide appropriate evacuation information.

[0803] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0804] In this invention, the server includes means for collecting precipitation data and river water level information in real time; information processing means equipped with a generative AI model that learns the correlation between precipitation and water level changes based on the collected data; means for evaluating the flood risk in a specific waterway using the generative AI model and generating evacuation information based on the risk; and means equipped with an emotion processing engine that analyzes emotional states and adjusts the content and method of transmission of evacuation information based on the analysis results. This makes it possible to provide accurate evacuation information that takes into account the emotional state of the user.

[0805] "Precipitation data" refers to information that quantifies the amount of rain that falls on the Earth's surface within a certain period of time.

[0806] "Water level information" refers to data indicating the height of water surfaces in rivers, lakes, and other bodies of water, and is used to understand the volume and flow of water.

[0807] "Means of real-time data collection" refers to technologies and methods for instantly acquiring and making available data that is constantly being generated in real time.

[0808] A "generative AI model" refers to an artificial intelligence model that automatically learns rules and patterns based on data to perform predictions and classifications.

[0809] "Information processing means" refers to methods and technologies for analyzing and processing acquired data to generate or extract valuable information according to a specific purpose.

[0810] "Flood risk" refers to an indicator that shows the degree of danger that water from rivers and other bodies of water will overflow their banks and cause damage to surrounding areas.

[0811] "Evacuation information" refers to information that includes instructions and guidelines for actions necessary to ensure safety during natural disasters.

[0812] "Personal communication devices" refer to electronic devices owned by individuals and used for sending and receiving information, such as mobile phones and smartphones.

[0813] An "emotional processing engine" refers to a technology or system that analyzes an individual's emotional state and understands that state in order to take appropriate action.

[0814] This invention is a disaster prevention information system that accurately assesses flood risk based on precipitation and river water level information and provides users with evacuation information that takes their emotions into consideration. An embodiment thereof is shown below.

[0815] The server collects precipitation and forecast information in real time from weather data provision services using APIs. This ensures that the latest precipitation data is always available. River water level information is obtained by connecting to the database of river water level observation stations. General communication infrastructure and cloud services are used for data collection.

[0816] The collected data is preprocessed on the server to detect and remove any anomalies. This preprocessing is a crucial step in maintaining data quality and improving the accuracy of the analysis results.

[0817] Next, the server utilizes a generative AI model based on the collected data to learn the correlation between precipitation and water level changes. This AI model is based on pattern recognition technology and can perform highly accurate flood risk assessments based on historical data. Specific analysis utilizes technologies such as trained models and neural networks.

[0818] Based on the generated risk assessment, the server creates optimal evacuation information. This evacuation information includes specific instructions tailored to the urgency and risk level. The generated information is automatically transmitted to the user's mobile device or other communication device.

[0819] Furthermore, the server is equipped with an emotion processing engine that analyzes the user's emotional state. This engine analyzes the user's past reaction logs and current operation logs to estimate the degree of stress and anxiety the user is experiencing. Based on this analysis, the presentation format and tone of the evacuation information are adjusted to make it easier for the user to understand and accept.

[0820] The terminal visually displays received evacuation information through a user interface. This includes infographics and evacuation route displays on maps, designed to allow users to intuitively understand the information and take quick action.

[0821] As a concrete example, if there are signs of an impending flood, the server prompts the AI ​​model with a message such as, "Use the precipitation data from the past 24 hours and the current river level data to assess the flood risk for the next 24 hours and generate evacuation information," thereby enabling accurate information generation. This allows for a comprehensive disaster response that includes understanding emotions.

[0822] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0823] Step 1:

[0824] The server collects precipitation and forecast information in real time through the API of a weather data provision service. In parallel, the server obtains water level information from a database of river water level observation stations. The latest precipitation and water level information is obtained as input from an external data provider. This data is stored in data storage for initial processing, in preparation for subsequent processing.

[0825] Step 2:

[0826] The server performs data cleaning on the collected data. Specifically, it uses data preprocessing to detect and remove outliers. For example, it filters out and deletes negative precipitation data and obviously abnormal water level data. Based on this input, it outputs a cleaned dataset and passes that dataset to a data analysis module.

[0827] Step 3:

[0828] The server inputs the processed data into a generating AI model, which learns the correlation between precipitation and water level changes. This AI model uses historical and current real-time data to assess flood risk. Through this process, the model generates a risk assessment output from the input data and calculates a detailed risk level.

[0829] Step 4:

[0830] The server generates evacuation information to be provided to the user based on the output of the generated AI model. This process includes specific instructions and suggested evacuation routes according to the risk level. The output is formatted evacuation information, which is then prepared for transmission to the user's communication device.

[0831] Step 5:

[0832] The server uses an emotion processing engine to analyze the user's emotional state. Inputs include the user's past reaction logs and current activity status. Through this analysis, the server estimates the user's stress and anxiety levels and adjusts the delivery method of evacuation information based on this information. The output is evacuation information optimized for the user.

[0833] Step 6:

[0834] The terminal receives evacuation information transmitted from the server and displays the information through a user interface. The terminal receives evacuation information as input and outputs it in an intuitively understandable format using infographics, maps, and other visual aids. This allows users to quickly grasp the information and take appropriate action.

[0835] (Application Example 2)

[0836] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0837] During natural disasters, information overload and misinformation make accurate and rapid evacuation difficult. Furthermore, there is a lack of evacuation information that can alleviate user stress and confusion in such situations and that can be tailored to individual emotional states. This invention aims to address these problems.

[0838] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0839] In this invention, the server includes means for collecting precipitation data and river water level information in real time, processing means equipped with a generative AI model that learns the correlation between precipitation and water level changes based on the collected data, and processing means equipped with an emotion engine that analyzes individual emotional states and adjusts the content and method of transmission of evacuation information based on the analysis results. This makes it possible to provide information that encourages appropriate and prompt evacuation actions without confusing the user.

[0840] "Precipitation data" refers to information that shows the amount of rain that fell in a specific area or at a specific time.

[0841] "River water level information" refers to data that shows the water level at a specific point in a river.

[0842] "Means of collecting data in real time" refers to a function or device that can collect data instantly.

[0843] A "generative AI model" refers to an artificial intelligence algorithm that analyzes collected data and learns specific rules and patterns.

[0844] "Processing means" refers to methods and devices for analyzing and processing data.

[0845] "Assessing flood risk" means predicting the possibility of a river overflowing and determining the degree of that risk.

[0846] "Means for generating evacuation information" refers to methods and devices for creating information that encourages safe actions when danger is imminent.

[0847] An "emotion engine" refers to a processing unit or function that analyzes the user's emotional state and adjusts the content and presentation of information based on the results.

[0848] "Personal communication device" refers to a communication-capable device belonging to a specific user, such as a smartphone.

[0849] "User interface" refers to the screens and operating environments that allow users to interact with a device or system.

[0850] "Individualized guidance information" refers to specific instructions and guidance provided in a way that is tailored to each user.

[0851] This invention is implemented using a system consisting of a server, a terminal, and a user. The server acquires precipitation data and river water level information in real time. Specifically, it collects data from weather APIs and river water level observation station databases that are publicly available via the internet. Data cleansing is performed using libraries such as NumPy to remove noise contained in the data.

[0852] Next, the server uses a generated AI model based on the collected data to analyze the correlation between precipitation and water level changes and calculate the flood risk. It builds a model using machine learning libraries such as scikit-learn and performs a risk assessment. Based on the results of this risk assessment, appropriate evacuation information is generated.

[0853] Furthermore, the server incorporates an emotion engine that analyzes the user's emotions. Specifically, it analyzes information obtained from the user's device and data on the user's past behavior to infer emotional states such as stress and anxiety. It utilizes the Natural Language Toolkit (NLTK) and other emotion analysis tools.

[0854] Once the user's emotional state is understood, the emotion engine optimizes the content and delivery method of evacuation information. For example, if the user is determined to be "anxious," the evacuation information will be presented in a gentle tone that takes that emotion into consideration. A specific example of a prompt message that could be used is, "The user's emotional state is 'anxious.' Please generate a reassuring message to calm them down."

[0855] The terminal displays the generated evacuation information through a user interface. Utilizing smartphones and tablet devices, the information is displayed in an intuitive and easy-to-understand manner. Visual information, such as real-time evacuation routes on a map, is also used to guide users toward taking swift action.

[0856] As a result, a system is realized that can encourage safe and rapid evacuation actions without causing confusion among users.

[0857] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0858] Step 1:

[0859] The server obtains precipitation data and river water level information from a weather API via the internet. This data serves as input. Using the NumPy library, the server performs data cleansing to detect and remove anomalies from the obtained data. As a result, cleansed and accurate weather data is output.

[0860] Step 2:

[0861] The server uses a generative AI model based on the data cleansed in Step 1 to learn the correlation between precipitation and water level changes. Using scikit-learn, it computes this data and calculates flood risk. The results of the risk assessment are output as basic data for generating evacuation information.

[0862] Step 3:

[0863] The emotion engine installed on the server receives data from the user as input and analyzes the user's emotional state. This process uses the Natural Language Toolkit (NLTK) to calculate, for example, stress and anxiety levels. Based on the analysis results, the user's emotional state is output.

[0864] Step 4:

[0865] The server integrates the risk assessment results obtained in step 2 and the user sentiment analysis results in step 3 to generate optimized evacuation information. It generates prompt messages and constructs reassuring messages that correspond to specific emotional states. The generated evacuation information is output in a state ready to be notified to the user.

[0866] Step 5:

[0867] The terminal displays optimized evacuation information received from the server through a user interface. The input is the notified evacuation information. The terminal visualizes the information and outputs it in a format that is easy for the user to understand, such as displaying evacuation routes and the locations of evacuation shelters on a map. Because the information is presented in a user-friendly format, it encourages quick decision-making and action.

[0868] Step 6:

[0869] Users take action to ensure their own safety based on the evacuation information displayed on their device. Because the outputted information is specific and intuitive, users are able to start evacuation actions appropriately.

[0870] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0871] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0872] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0873] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0874] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0875] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0876] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0877] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0878] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0879] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0880] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0881] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0882] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0883] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0884] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0885] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0886] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0887] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0888] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0889] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0890] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0891] The following is further disclosed regarding the embodiments described above.

[0892] (Claim 1)

[0893] A means for collecting precipitation data and river water level information in real time,

[0894] A processing method equipped with a generative AI model that learns the correlation between precipitation and water level changes based on collected data,

[0895] A means for evaluating the flood risk in a specific river using a generative AI model and generating evacuation information based on that risk,

[0896] A means of notifying individuals of the generated evacuation information to their communication devices,

[0897] A system that includes this.

[0898] (Claim 2)

[0899] The system according to claim 1, characterized by comprising data preprocessing means for detecting and removing abnormal values ​​in precipitation data and water level information.

[0900] (Claim 3)

[0901] The system according to claim 1, characterized by comprising means for displaying notified evacuation information through a user interface and providing guidance information.

[0902] "Example 1"

[0903] (Claim 1)

[0904] A means of collecting precipitation information and water level information in real time from atmospheric phenomena data-related organizations and monitoring facilities,

[0905] A processing means equipped with a data analysis model that learns the correlation between precipitation and water level changes based on collected information,

[0906] A means for evaluating the flood risk in a specific area using a data analysis model and generating evacuation information based on that risk,

[0907] A means of notifying an individual's electronic device of the generated evacuation information,

[0908] A means of identifying evacuation routes using geographic information of the target area,

[0909] A system that includes this.

[0910] (Claim 2)

[0911] The system according to claim 1, characterized by comprising data shaping means for detecting and removing abnormal values ​​in atmospheric phenomenon data and water level information.

[0912] (Claim 3)

[0913] The system according to claim 1, characterized by comprising means for displaying notified evacuation information through a user interface and providing route guidance information.

[0914] "Application Example 1"

[0915] (Claim 1)

[0916] A means for collecting precipitation data and river water level information in real time,

[0917] A processing method equipped with a generative AI model that learns the correlation between precipitation and water level changes based on collected data,

[0918] A means for evaluating the flood risk in a specific river using a generative AI model and generating evacuation information based on that risk,

[0919] A means for notifying a communication device of the generated evacuation information and providing evacuation route and shelter information according to location information,

[0920] A system that includes this.

[0921] (Claim 2)

[0922] The system according to claim 1, characterized by having means for intuitively guiding people inside a building with occupied space in the real world to safe evacuation due to extreme weather.

[0923] (Claim 3)

[0924] The system according to claim 1, characterized in that it includes means for displaying notified evacuation information through a user interface and indicating the direction of evacuation by audio output and visual output.

[0925] "Example 2 of combining an emotion engine"

[0926] (Claim 1)

[0927] A means for collecting precipitation data and river water level information in real time,

[0928] An information processing means equipped with a generative AI model that learns the correlation between precipitation and water level changes based on collected data,

[0929] A means for evaluating the flood risk in a specific waterway using a generative AI model and generating evacuation information based on that risk,

[0930] A means of notifying personal communication devices of the generated evacuation information,

[0931] It includes an emotion processing engine that analyzes emotional states, and means for adjusting the content and method of transmission of evacuation information based on the analysis results,

[0932] A system that includes this.

[0933] (Claim 2)

[0934] The system according to claim 1, characterized by comprising data preprocessing means for detecting and removing abnormal values ​​in precipitation data and water level information.

[0935] (Claim 3)

[0936] The system according to claim 1, characterized by comprising means for displaying notified evacuation information through a user interface and providing guidance information.

[0937] "Application example 2 when combining with an emotional engine"

[0938] (Claim 1)

[0939] A means for collecting precipitation data and river water level information in real time,

[0940] A processing method equipped with a generative AI model that learns the correlation between precipitation and water level changes based on collected data,

[0941] A means for evaluating the flood risk in a specific river using a generative AI model and generating evacuation information based on that risk,

[0942] A processing means equipped with an emotion engine that analyzes individual emotional states and adjusts the content and method of transmission of evacuation information based on the analysis results,

[0943] A means of notifying individuals of the generated evacuation information to their communication devices,

[0944] A system that includes this.

[0945] (Claim 2)

[0946] The system according to claim 1, characterized by comprising data preprocessing means for detecting and removing abnormal values ​​in precipitation data and water level information.

[0947] (Claim 3)

[0948] The system according to claim 1, characterized by comprising means for displaying notified evacuation information through a user interface and providing individual guidance information. [Explanation of symbols]

[0949] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting precipitation data and river water level information in real time, A processing method equipped with a generative AI model that learns the correlation between precipitation and water level changes based on collected data, A means for evaluating the flood risk in a specific river using a generative AI model and generating evacuation information based on that risk, A means of notifying individuals of the generated evacuation information to their communication devices, A system that includes this.

2. The system according to claim 1, characterized by comprising data preprocessing means for detecting and removing abnormal values ​​in precipitation data and water level information.

3. The system according to claim 1, characterized by comprising means for displaying notified evacuation information through a user interface and providing guidance information.

Images