system

Abstract

We provide the system. [Solution] Means for regularly collecting weather information, A means of receiving river water level information, Means for acquiring topographic information, A method for analyzing and evaluating the reliability of information posted on social media, A means of detecting and excluding fake images, A means to comprehensively analyze this information and assess flood risk, A system that includes means for issuing warnings based on risk assessment.

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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, due to climate change, local heavy rains have occurred frequently, and the accompanying flood damage has become a social problem. In such a situation, in order to ensure the safety of residents and minimize damage, accurate real-time risk prediction and prompt response are required. However, in conventional systems, there is a problem that the accuracy of data collection and analysis is limited, and it is difficult to issue timely warnings.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides a system that integrates the regular collection of weather information, reception of river water level information, acquisition of topographic information, analysis and reliability evaluation of information posted on social media, and detection and exclusion of fake images. This makes it possible to assess flood risk in real time with high accuracy and to quickly send warnings to user terminals via a dedicated application. Furthermore, the accuracy of risk assessment can be improved by using past case datasets and machine learning models.

[0006] "Weather information" refers to data about current and future weather conditions, and is a general term for information including precipitation, wind speed, temperature, and humidity.

[0007] "River water level information" refers to measured water levels in a specific river, and this serves as basic data for assessing the risk of river flooding.

[0008] "Topographic information" refers to data about geographical shape and land use, including information such as elevation differences, slopes, and land cover.

[0009] "Social media posts" refer to content such as text messages, images, and videos that users have published on social media platforms on the internet.

[0010] "Reliability assessment" is a process for determining the accuracy and consistency of acquired data and measuring the reliability of that data.

[0011] "Fake image detection" refers to a technology that analyzes the content of digital images to identify images that may have been altered or fabricated.

[0012] "Integrated analysis" is the process of combining data from multiple sources, evaluating the information as a whole, and drawing more accurate conclusions.

[0013] "Assessing flood risk" refers to the act of using collected data to predict the likelihood of floods and inundation occurring and the extent of their impact.

[0014] A "dedicated application" refers to a software framework that has functions specific to this invention and can be installed and used on a device.

[0015] A "user terminal" refers to an information processing device such as a mobile phone, smartphone, tablet, or computer that is commonly used by users to receive or input information.

[0016] A "past case dataset" refers to a collection of data based on similar events that have occurred in the past, and is used for training and evaluating machine learning models.

[0017] A "machine learning model" is a collection of algorithms that learn patterns from data and perform predictions and classifications, enabling computers to automatically interpret data patterns. [Brief explanation of the drawing]

[0018] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7]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 an 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 an emotion engine is combined.

Mode for Carrying Out the Invention

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

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

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

[0022] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0024] 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).

[0025] 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."

[0026] [First Embodiment]

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

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0033] 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.

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

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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".

[0039] This invention describes a specific embodiment of a system that assesses flood risk and issues rapid warnings by collecting and analyzing weather information, river water level information, topographic information, and social media posts in real time.

[0040] First, the server collects information from various data sources. For weather information, it obtains data such as precipitation, temperature, and wind speed from weather forecasting services via API. River water level information is received from river management systems equipped with water level sensors, and topographic information is extracted from Geographic Information System (GIS) databases. This allows for the acquisition of the latest and most detailed information for each region.

[0041] Next, the server uses social media APIs to collect data such as status reports, photos, and videos posted by users. This information is analyzed using natural language processing and image processing algorithms to extract reliable data. In addition, a fake image detection algorithm is used to eliminate images that may have been tampered with.

[0042] This data is integrated and analyzed within the server. An AI model is launched and compared with past flood data to predict the likelihood of flooding and inundation. The algorithm calculates the probability of flooding and the extent of its impact based on data patterns learned from past events.

[0043] After integrating and analyzing the information, if a high risk is determined, the server immediately activates the alarm generation module. Emergency alerts are then pushed to terminals via a dedicated application. The notification includes detailed evacuation instructions and risk levels for each area, allowing users to take swift and appropriate action. For example, if heavy rainfall is predicted to cause river flooding in a certain area, an alert is immediately sent to residents expected to be affected, providing them with safe evacuation routes.

[0044] Thus, this system automates the entire process, enabling highly accurate and efficient flood risk management.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The server connects to the weather data provider's API to obtain the latest weather information in real time. Specifically, it collects data such as rainfall, temperature, wind speed, and wind direction, and stores it in a database. Based on this information, it performs an initial assessment of the likelihood of heavy rainfall.

[0048] Step 2:

[0049] The server accesses the water level measurement system of the river management agency to obtain water level data for each river. The obtained water level information is stored in a database for comparison with past data and serves as basic data for assessing the risk of river flooding.

[0050] Step 3:

[0051] The server obtains topographic data for the area through a geographic information system. This includes elevation, terrain slope, and land use information. Based on this data, it simulates how water will flow and analyzes the possibility of flooding.

[0052] Step 4:

[0053] The server uses APIs from social media platforms to collect user-submitted information. Text data is analyzed using natural language processing to evaluate the reliability of the posts. Image data is also analyzed using a fake image detection algorithm to exclude inappropriate data.

[0054] Step 5:

[0055] The server uses AI and machine learning algorithms to comprehensively analyze all collected data. It compares it with past case datasets to assess flood and inundation risks with high accuracy. In doing so, it operates a predictive model that takes time-series data and topographic characteristics into account.

[0056] Step 6:

[0057] The server issues alerts as needed based on the assessed risk. It sends push notifications to devices via a dedicated application, issuing emergency alerts. These alerts include specific evacuation instructions and recommended actions to support safe evacuation.

[0058] Step 7:

[0059] The device notifies the user of any received alarms. The user checks the notification and begins evacuation according to the instructions. Ensure that information is reliably delivered, including alternative notifications via guaranteed communication methods (e.g., SMS or email).

[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] In recent years, floods caused by extreme weather events have become frequent, creating a need for technology that can quickly and accurately assess flood risk and issue timely warnings. Conventional systems have problems such as insufficient integrated information processing and low warning accuracy, which prevents appropriate evacuation orders from being issued.

[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 periodically acquiring weather information, means for receiving river water level data, and means for acquiring topographic data. This enables high-precision flood risk assessment and rapid warning issuance by quickly and accurately aggregating and analyzing data from a wide area.

[0065] "Weather information" refers to data related to weather conditions, including precipitation, temperature, and wind speed.

[0066] "Acquiring data periodically" means repeatedly collecting data at predetermined intervals.

[0067] "Water level data" refers to information about the water level of rivers and lakes.

[0068] "Topographic data" refers to information that shows the topography and structure of the land.

[0069] "Information from social media" refers to data such as text, images, and videos posted by users on online platforms.

[0070] "Assessing reliability" is the process of determining the accuracy and usefulness of data.

[0071] A "fake image" is false visual information created through manipulation or alteration.

[0072] "Integrated analysis" means combining multiple different data sources to perform an evaluation.

[0073] "Assessing the risk of flooding" means predicting the risk of floods and inundation.

[0074] "Issuing a warning based on a risk assessment" means issuing a warning based on the predicted risks.

[0075] "Automating" means executing a process without requiring human intervention.

[0076] "Sending an emergency alert to an electronic device" means delivering a warning message to a device when danger is imminent.

[0077] "Users checking evacuation information" means that users become aware of the safety instructions provided.

[0078] A "learning algorithm" is a computational method that uses machine learning to learn data patterns and assist in analysis.

[0079] A "specific application" is software designed for a particular purpose.

[0080] "User's device" refers to electronic devices that a user uses on a daily basis.

[0081] This invention is a system that assesses flood risks in real time and issues accurate warnings. Its specific form is described below.

[0082] The server is the central hub for collecting and integrating information from weather data, river water level data, topographic data, and social media. Weather data is obtained through APIs of weather forecasting services and includes information on precipitation, temperature, and wind speed. River water level data is acquired in real time from a river management system using sensors. Topographic data is extracted from a Geographic Information System (GIS). This allows for the immediate acquisition of detailed information for each region.

[0083] From social media, user posts are retrieved via APIs and analyzed using natural language processing (NLP) and image processing technologies. This extracts useful information while eliminating potentially manipulated visual information using fake image detection algorithms.

[0084] Based on this information, an AI model is launched on the server, and a learning algorithm is used to compare and analyze past flood disaster cases. Based on the results obtained in this way, the risk of flooding and inundation is assessed, and based on that assessment, a warning module is activated.

[0085] The device receives emergency alerts via push notifications through a dedicated application. These notifications include specific evacuation orders and regional risk levels, designed to encourage immediate action.

[0086] For example, the prompt "Assess flood risk and analyze whether a warning is necessary based on heavy rainfall forecast data for the following region: Region A, precipitation 80 mm, wind speed 20 m / s" can be used as input to the generating AI model. This allows the system to quickly and accurately assess the risk and prompt appropriate responses.

[0087] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0088] Step 1:

[0089] The server retrieves weather data from a weather API. The inputs in this step are precipitation, temperature, and wind speed data obtained from the API. The server stores this data in a database and uses it to monitor weather conditions in real time.

[0090] Step 2:

[0091] The server acquires water level data from sensors in the river management system. The input is water level information provided by the sensors, which is used to understand the river's condition. The server records this data to aid in trend analysis.

[0092] Step 3:

[0093] The server extracts topographic information from a GIS database. The input is topographic data for a specified region. The server uses this data to analyze topographic elevation differences, water flow characteristics, and other factors. This data is then used in disaster risk assessments.

[0094] Step 4:

[0095] The server collects user posts through social media APIs. The input consists of posted text, images, and video information. The server analyzes the data using natural language processing and image processing algorithms to extract useful information. During this process, a fake image detection algorithm is used to eliminate tampered data.

[0096] Step 5:

[0097] Based on this data, the server activates an AI model. The input consists of all data obtained from weather, river levels, topography, and social media. The server uses a learning algorithm to assess flood risk by comparing it to past events. The output is the predicted probability of flooding and the extent of its impact.

[0098] Step 6:

[0099] Based on the risk assessment, the server activates the alarm generation module. The input is risk assessment data generated by an AI model. The server generates an alarm message accordingly and creates an emergency alert.

[0100] Step 7:

[0101] The terminal receives push notifications of alarm messages via a dedicated application. The input is alarm data sent from the server. The terminal displays this data to help the user evacuate quickly. The output is an emergency evacuation order and a display of the risk level for the user.

[0102] (Application Example 1)

[0103] 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."

[0104] In modern society, damage caused by floods is a serious problem. To address this, it is necessary to quickly and accurately assess flood risk and encourage appropriate evacuation actions. However, conventional systems have struggled to perform comprehensive data analysis in real time and provide optimal information to individual users. Therefore, a new system is needed that can efficiently assess flood risk and support immediate evacuation.

[0105] 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.

[0106] In this invention, the server includes means for periodically collecting weather information, means for receiving river water level information, means for acquiring topographic information, means for analyzing and evaluating the reliability of posts from social media, means for detecting and excluding fake images, means for comprehensively analyzing this information and evaluating flood risk, means for issuing warnings based on the risk assessment, and means for notifying user devices of evacuation routes. This enables a rapid response to flood risk and accurate information provision to users.

[0107] "Weather information" refers to data about atmospheric conditions, including weather forecasts, temperature, precipitation, and wind speed.

[0108] "River water level information" refers to data on changes in water levels in rivers, obtained from water level sensors and river management systems.

[0109] "Topographic information" refers to data about the topography and terrain of a specific area, and is usually obtained from a Geographic Information System (GIS).

[0110] "Social media posts" refer to video and message data that users post on social networks and online platforms.

[0111] A "fake image" is visual data that is intentionally altered or created to differ from reality, and may misrepresent the truth.

[0112] "Risk assessment" is an evaluation calculated by analyzing the possibility of flooding, and includes the expected scope of impact and the probability of occurrence.

[0113] An "alert" is a notification that informs the user of the presence of a specific danger and includes instructions to prompt immediate action.

[0114] A "user device" is a device used by a user to receive information or perform operations, and includes smartphones and smart glasses.

[0115] An "evacuation route" is a recommended path for moving to a safe place during a disaster, and it is guided to the user using GPS data and other methods.

[0116] The system for realizing this invention functions by exchanging data between a server located in a cloud environment and a user's terminal (including smartphones and smart glasses).

[0117] The server periodically collects weather information, river water level information, and topographic information from their respective sources. Weather information is obtained through weather forecasting service APIs, river water level information is received as a real-time feed from water level sensors, and topographic information is extracted from geographic information systems (GIS). In addition, it uses social media APIs to collect and analyze user-posted information and evaluate its reliability. Fake images are detected and excluded by image processing algorithms.

[0118] The server comprehensively analyzes this data and uses AI-powered generative models to compare it with past flood data to assess flood risk. This assessment utilizes machine learning frameworks such as TENSORFLOW®, and Python libraries (such as pandas and NumPy) are used to analyze the collected data.

[0119] If a high risk is detected, the server will push an alert to the user's device. The notification will include information about the disaster, as well as the best route for the user to evacuate quickly and safely. This route guidance is updated in real time using Google® Maps API and other technologies.

[0120] As a concrete example, if heavy rain is forecast and river levels rise rapidly, the server will issue a warning to users in that area and notify them of evacuation orders and evacuation routes through the application. At this time, users can check detailed instructions on their terminal screen and take safe action. The generated AI model will use a prompt statement like the following: "Predict the flood risk based on current weather data, river level data, and past flood incidents in a given area."

[0121] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0122] Step 1:

[0123] The server periodically retrieves data such as precipitation, temperature, and wind speed from a weather information API. The input data is the weather data received as an API response. This data is parsed in JSON format, and the necessary information is extracted and stored. The output is a set of organized weather data.

[0124] Step 2:

[0125] The server receives water level sensor data from the river management system. The input data is real-time updated water level information. This data is processed into a list format and compared to a specific baseline value. The output is a flag indicating whether the current water level exceeds the danger level.

[0126] Step 3:

[0127] The server retrieves topographic information from a GIS database. The input is topographic map data extracted from a geographic information system. This data is plotted as an outline on a map and then formatted for analysis. The output is a plotted set of topographic data.

[0128] Step 4:

[0129] The server collects user-generated content using social media APIs. Input data includes posted status reports, photos, and videos. Natural language processing and image processing algorithms are used to extract reliable information and detect and remove fake images. The output is a set of reliable user-generated content.

[0130] Step 5:

[0131] The server performs flood risk assessment using TensorFlow. Input data includes weather information, water level information, topographic information, and user-submitted information. An AI model integrates and analyzes this data to predict the probability of flooding and the extent of its impact. Outputs include probability values ​​as a risk assessment and map information of the affected areas.

[0132] Step 6:

[0133] Based on the evaluation results, the server sends an alert via push notification to the user's terminal. Inputs include risk assessment results and user profile information. The alert includes detailed evacuation instructions and risk levels based on the user's location, and is displayed via a dedicated app. Output is the alert notification on the terminal.

[0134] Step 7:

[0135] The user terminal receives an alarm and displays a safe evacuation route. The input is evacuation route instruction data from the server. The route is plotted using the Google Maps API, providing the user with the optimal evacuation path in real time. The output is evacuation route guidance displayed on the terminal screen.

[0136] 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.

[0137] This invention combines a system that comprehensively analyzes weather information, river water level information, topographic information, and social media posts to assess flood risk with a user emotion recognition function. This allows for more effective communication by considering the user's emotions when issuing warnings.

[0138] First, the server periodically collects weather information, river water level data, and topographic information from multiple data sources. This compiles regional environmental data, building a foundation of information on flood risk. Simultaneously, the server collects text and image data from user posts on social media and analyzes them using a sentiment engine.

[0139] The emotion engine analyzes text data, particularly on social media, using natural language processing to identify the emotional state a user is expressing. For example, if a user strongly expresses emotions such as "anxiety" or "fear," this information is fed back to the alarm system. The server then uses this emotion data to adjust the alarm content to suit the user's emotional state. Specifically, it can prioritize sending alarms containing reassuring messages to users experiencing high levels of stress.

[0140] After a risk assessment is performed, the server sends an alert to the device using push notifications. The device immediately displays this notification to the user, helping them to take immediate evacuation action. The alert, adjusted by an emotion engine, is displayed in a specific and easy-to-understand format to help the user act more appropriately.

[0141] Therefore, this system not only assesses flood risk but also enhances safety by providing countermeasures that take into account the user's emotions. In this way, the present invention implements a form that utilizes an emotion engine to provide users with comprehensive and effective flood control measures.

[0142] The following describes the processing flow.

[0143] Step 1:

[0144] The server uses the weather data provider's API to collect real-time weather information. This data includes rainfall, temperature, wind speed, etc., and is stored in a database. Based on this, the server assesses the initial risk of precipitation.

[0145] Step 2:

[0146] The server receives river water level data from river management agencies. The water level information sent from each river sensor is an important indicator for predicting flood risk and is continuously monitored.

[0147] Step 3:

[0148] The server retrieves geographical information from a topographic database and analyzes the topographic characteristics of the area. This information is used to calculate how changes in rainfall and river levels will affect the terrain.

[0149] Step 4:

[0150] The server collects user posts via social media APIs and performs multilingual text analysis using an emotion engine. Here, it evaluates the emotions contained in the posts (e.g., fear, anxiety, relief) and feeds that data back into the system.

[0151] Step 5:

[0152] The server integrates all collected data and uses AI and machine learning models based on past cases to comprehensively assess flood risk. The risk assessment also takes into account the output of the emotion engine.

[0153] Step 6:

[0154] If the risk exceeds a certain threshold, the server generates an alert. The content of the alert is customized based on the analysis results of the emotion engine; for example, a user showing anxiety will receive a message with more reassuring language.

[0155] Step 7:

[0156] The server sends an alert to the device via a dedicated app using push notifications. The device receives this alert and immediately notifies the user to encourage evacuation. The user reviews the notification and prepares to evacuate to a safe place quickly according to the instructions.

[0157] (Example 2)

[0158] 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".

[0159] In recent years, damage from natural disasters has become increasingly severe around the world, necessitating effective risk assessment and swift, appropriate responses. However, conventional risk assessment systems have been insufficient in issuing warnings that take into account the emotional state of users, resulting in a lack of understanding of the warnings and difficulty in translating them into action. Therefore, there is a need to develop a new natural disaster risk assessment system that enables communication that takes user emotions into account.

[0160] 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.

[0161] In this invention, the server includes means for periodically collecting weather data, means for acquiring water level data, and means for acquiring geographical data. This enables rapid and effective assessment of natural disaster risks and the issuance of warnings tailored to the user's emotions.

[0162] "Meteorological data" refers to information about meteorological phenomena, including observational data such as temperature, precipitation, and wind speed.

[0163] "Water level data" refers to information about the water level in bodies of water such as rivers and lakes, and serves as data for assessing flood risk.

[0164] "Geographic data" refers to information about the shape and characteristics of land, and includes topographic maps and elevation data.

[0165] "Social media" refers to information published through internet platforms, and in particular includes posts and comments on social media.

[0166] "False data" refers to information that is inaccurate or untrue, and in particular includes false images and disguised information.

[0167] "Natural disaster risk" refers to an increased likelihood of disasters caused by weather or geological factors, and indicates the danger for which warnings and measures should be taken based on this possibility.

[0168] "Emotional state" refers to the type and intensity of emotions an individual experiences in a particular situation, and includes emotions such as anxiety, fear, and relief.

[0169] "Machine learning technology" refers to the field of technology in which computer systems learn patterns and rules from data and make predictions and decisions based on that learning.

[0170] "Information and communication technology" refers to technologies for generating, processing, transmitting, and receiving digital data, and in particular, technologies that enable real-time information sharing via the internet.

[0171] This embodiment of the invention provides a system that effectively assesses natural disaster risks and issues warnings that take into account the user's emotional state. Specifically, the server collects and analyzes information from various data sources. The server uses databases and APIs necessary for acquiring weather data and connects to sensors and monitoring systems for water level data. Geographic data is also acquired using a Geographic Information System (GIS). Based on this data, the server performs calculations to assess the risk.

[0172] The server further analyzes text data from social media using natural language processing tools. Specifically, it uses software such as Python's NLTK and spaCy to extract emotional states from user posts. This ensures that user emotions are reflected in the generation of warning messages. For example, the server identifies a user's post "I'm worried about heavy rain tonight" as an emotion of "anxiety" and uses this to adjust the warning message.

[0173] The generated alarm messages are then materialized through a generation AI model. As an example of a prompt, the server can execute a command to the generation AI model to "generate a user-facing alarm message based on risk and sentiment scores." This process generates emotionally sensitive, specific, and actionable alarms.

[0174] Finally, the server uses information and communication technology to send the generated alarm as a push notification to the user's terminal. In this way, the terminal instantly displays the alarm to the user, supporting quick action. As a result, the system functions as an effective tool to enhance user safety during disasters.

[0175] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0176] Step 1:

[0177] The server periodically collects weather data, river water level data, and geographical data from various sensors and database APIs. This process requires specific observation locations and measurement device identification information as input. After data collection, the server organizes and stores this data by date and location. The output is an integrated time-series dataset.

[0178] Step 2:

[0179] The server numerically assesses flood risk based on collected geographic information. The input is time-series weather and water level data obtained in the previous step. The server uses Python's NumPy and Pandas to perform statistical analysis and model-based predictions. The output of this process is a calculated risk score and the generation of a risk map for each region.

[0180] Step 3:

[0181] The server collects data from social media posts and analyzes the users' emotional states. It takes text data and, if possible, contextual information from each post as input. This text data is then subjected to emotional classification using natural language processing tools such as Python's NLTK or spaCy. The output is the user's emotional tone (e.g., positive, negative), which is quantified as an emotional score.

[0182] Step 4:

[0183] The server uses a generative AI model to generate alert messages based on risk and sentiment scores. The prompt is "Create a specific and emotionally sensitive alert message for the user." The input consists of previously evaluated risk and sentiment scores. The generated text is provided as an alert message with a tone and content appropriate for the user. The output is a customized message.

[0184] Step 5:

[0185] The server sends a push notification to the user's device to send the generated alarm message. The input consists of contact information and the generated alarm message. The message is sent to the device in real time using a communication protocol, and the device immediately displays this message to the user. As output, the individual message received by the user is displayed on the device screen.

[0186] Step 6:

[0187] The user reviews the received alarm and provides feedback as needed. The input is the content of the alarm message itself. The user provides feedback on whether the provided information is accurate and useful. The output is returned to the server as user feedback data and stored as a reference for future alarm generation.

[0188] (Application Example 2)

[0189] 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".

[0190] In recent years, with the increasing frequency of floods due to climate change, there is a growing need to effectively disseminate information and promote swift evacuation. However, conventional warning systems send uniform warning messages without considering the emotional state of users, which can cause anxiety and fail to encourage appropriate action. Therefore, there is a need for information provision that understands and appropriately considers the emotions of users.

[0191] 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.

[0192] In this invention, the server includes means for periodically collecting weather information, means for receiving river water level information, means for acquiring topographic information, means for analyzing data from social media and recognizing emotions, means for detecting and removing fake images, means for comprehensively analyzing this information and evaluating the threat of flooding, means for issuing emotion-based adjusted warnings, and means for sending warnings via push notifications to user devices through a specific application. This makes it possible to provide flood information in a way that takes into account the user's emotions and provides a sense of security, thereby encouraging appropriate and prompt evacuation actions.

[0193] "Weather information" refers to data on environmental conditions such as weather, temperature, precipitation, and wind speed. By accumulating this data, it provides basic information for understanding the weather conditions in a specific region.

[0194] "River water level information" refers to data measuring water levels at specific points along rivers, and is an important indicator for evaluating the likelihood of flooding.

[0195] "Topographic information" refers to data that shows the relief and topographical features of the land, and is used to assess the level of danger in a region and the risk of flooding.

[0196] "Methods for analyzing data from social media and recognizing emotions" refers to technologies that analyze the content of posts on online platforms and recognize the emotions and psychological states expressed by users.

[0197] "Methods for detecting and removing fake images" refer to technologies for identifying and excluding manipulated images and false information from analysis, and are crucial for reliable data analysis.

[0198] "Means for assessing flood threats" refers to methods for comprehensively evaluating flood risk by integrating meteorological information, river water level information, and topographic information.

[0199] "Means for issuing emotion-based, adjustable alarms" refers to technology that generates and delivers alarm messages whose content is adjusted according to the user's emotional state.

[0200] "A means of sending an alarm via push notification to a user's device through a specific application" refers to a technology that uses dedicated software to instantly send an alarm message to the user's electronic device.

[0201] The system of the present invention aims to assess the flood risk in a user's area based on their emotional state and issue appropriate warnings. This system integrates information from multiple data sources and includes the following components to achieve information delivery that takes the user's emotions into consideration.

[0202] The server first periodically collects and integrates weather information, river water level information, and topographic information. The specific hardware used for this is a data server with high processing power, and the software implements a dedicated application for data collection and analysis.

[0203] Next, the server analyzes posts from social media. This analysis uses natural language processing tools and sentiment analysis engines (e.g., NLP libraries) to identify the user's psychological state and quantify their emotions. This allows the server to discover emotions such as "anxiety" and "fear" that users are expressing, and uses this data to adjust the content of alerts.

[0204] Meanwhile, the terminal receives coordinated alerts transmitted from the server and immediately presents them to the user. This allows the user to understand the current flood risk and quickly take appropriate action, such as evacuation. The terminal is a portable electronic device such as a smartphone or tablet, and provides a user interface through an application.

[0205] As a concrete example, it is possible to perform sentiment analysis using a generative AI model, for instance, by "evaluating users' emotions based on content posted on the media and sending special warning messages to areas where there are posts indicating strong fear."

[0206] Examples of prompts include the following:

[0207] "Analyze the sentiment of social media posts coming from a particular geographic location. If the predominant sentiment is negative, especially fear or anxiety, suggest a comforting message that could be sent to users in that area."

[0208] Through this process, the system can effectively provide users with emotionally sensitive flood information, supporting safe and swift decision-making.

[0209] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0210] Step 1:

[0211] The server periodically collects weather information, river water level information, and topographic information from external databases and APIs. This information is received as configuration data, and the server updates the environmental information for each region. Input is data obtained from external information sources, and output is the latest environmental information stored in the server's database. The process includes automatically retrieving data using API requests.

[0212] Step 2:

[0213] The server collects posting data from a specific region via social media APIs and analyzes users' emotional states using a sentiment analysis engine. The input is posting data obtained from a specific geographical area, and the output is the emotional tendencies of users identified through the analysis (e.g., "anxiety" or "fear"). Data processing is performed by scoring the sentiment of the text using natural language processing techniques.

[0214] Step 3:

[0215] The server comprehensively assesses the flood threat based on all collected data. This assessment utilizes a method that integrates weather, river level, topography, and sentiment data to calculate a risk score. The input is a set of various data, and the output is a numerical representation of the flood risk as a risk score. Data calculations here include weighting and time series analysis.

[0216] Step 4:

[0217] The server generates alarm messages based on risk assessments and adjusts them to be emotionally appropriate. This process incorporates message templates that provide reassurance to users, especially those experiencing significant anxiety, using prompts from a generation AI model. Inputs are risk scores and sentiment analysis results, while output is the text of the alarm message. This process involves template selection and automatic text generation.

[0218] Step 5:

[0219] The terminal presents the user with a pre-configured alarm message sent from the server as a push notification. The input is alarm data from the server, and the output is the alarm message displayed on the terminal's user interface. The terminal uses the OS's notification function to ensure user attention. Based on this, the user can immediately decide on actions such as evacuation.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] [Second Embodiment]

[0224] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0225] 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.

[0226] 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).

[0227] 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.

[0228] 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.

[0229] 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).

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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".

[0236] This invention describes a specific embodiment of a system that assesses flood risk and issues rapid warnings by collecting and analyzing weather information, river water level information, topographic information, and social media posts in real time.

[0237] First, the server collects information from various data sources. For weather information, it obtains data such as precipitation, temperature, and wind speed from weather forecasting services via API. River water level information is received from river management systems equipped with water level sensors, and topographic information is extracted from Geographic Information System (GIS) databases. This allows for the acquisition of the latest and most detailed information for each region.

[0238] Next, the server uses social media APIs to collect data such as status reports, photos, and videos posted by users. This information is analyzed using natural language processing and image processing algorithms to extract reliable data. In addition, a fake image detection algorithm is used to eliminate images that may have been tampered with.

[0239] This data is integrated and analyzed within the server. An AI model is launched and compared with past flood data to predict the likelihood of flooding and inundation. The algorithm calculates the probability of flooding and the extent of its impact based on data patterns learned from past events.

[0240] After integrating and analyzing the information, if a high risk is determined, the server immediately activates the alarm generation module. Emergency alerts are then pushed to terminals via a dedicated application. The notification includes detailed evacuation instructions and risk levels for each area, allowing users to take swift and appropriate action. For example, if heavy rainfall is predicted to cause river flooding in a certain area, an alert is immediately sent to residents expected to be affected, providing them with safe evacuation routes.

[0241] Thus, this system automates the entire process, enabling highly accurate and efficient flood risk management.

[0242] The following describes the processing flow.

[0243] Step 1:

[0244] The server connects to the weather data provider's API to obtain the latest weather information in real time. Specifically, it collects data such as rainfall, temperature, wind speed, and wind direction, and stores it in a database. Based on this information, it performs an initial assessment of the likelihood of heavy rainfall.

[0245] Step 2:

[0246] The server accesses the water level measurement system of the river management agency to obtain water level data for each river. The obtained water level information is stored in a database for comparison with past data and serves as basic data for assessing the risk of river flooding.

[0247] Step 3:

[0248] The server obtains topographic data for the area through a geographic information system. This includes elevation, terrain slope, and land use information. Based on this data, it simulates how water will flow and analyzes the possibility of flooding.

[0249] Step 4:

[0250] The server uses APIs from social media platforms to collect user-submitted information. Text data is analyzed using natural language processing to evaluate the reliability of the posts. Image data is also analyzed using a fake image detection algorithm to exclude inappropriate data.

[0251] Step 5:

[0252] The server uses AI and machine learning algorithms to comprehensively analyze all collected data. It compares it with past case datasets to assess flood and inundation risks with high accuracy. In doing so, it operates a predictive model that takes time-series data and topographic characteristics into account.

[0253] Step 6:

[0254] The server issues alerts as needed based on the assessed risk. It sends push notifications to devices via a dedicated application, issuing emergency alerts. These alerts include specific evacuation instructions and recommended actions to support safe evacuation.

[0255] Step 7:

[0256] The device notifies the user of any received alarms. The user checks the notification and begins evacuation according to the instructions. Ensure that information is reliably delivered, including alternative notifications via guaranteed communication methods (e.g., SMS or email).

[0257] (Example 1)

[0258] 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."

[0259] In recent years, floods caused by extreme weather events have become frequent, creating a need for technology that can quickly and accurately assess flood risk and issue timely warnings. Conventional systems have problems such as insufficient integrated information processing and low warning accuracy, which prevents appropriate evacuation orders from being issued.

[0260] 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.

[0261] In this invention, the server includes means for periodically acquiring weather information, means for receiving river water level data, and means for acquiring topographic data. This enables high-precision flood risk assessment and rapid warning issuance by quickly and accurately aggregating and analyzing data from a wide area.

[0262] "Weather information" refers to data related to weather conditions, including precipitation, temperature, and wind speed.

[0263] "Acquiring data periodically" means repeatedly collecting data at predetermined intervals.

[0264] "Water level data" refers to information about the water level of rivers and lakes.

[0265] "Topographic data" refers to information that shows the topography and structure of the land.

[0266] "Information from social media" refers to data such as text, images, and videos posted by users on online platforms.

[0267] "Assessing reliability" is the process of determining the accuracy and usefulness of data.

[0268] A "fake image" is false visual information created through manipulation or alteration.

[0269] "Integrated analysis" means combining multiple different data sources to perform an evaluation.

[0270] "Assessing the risk of flooding" means predicting the risk of floods and inundation.

[0271] "Issuing a warning based on a risk assessment" means issuing a warning based on the predicted risks.

[0272] "Automating" means executing a process without requiring human intervention.

[0273] "Sending an emergency alert to an electronic device" means delivering a warning message to a device when danger is imminent.

[0274] "Users checking evacuation information" means that users become aware of the safety instructions provided.

[0275] A "learning algorithm" is a computational method that uses machine learning to learn data patterns and assist in analysis.

[0276] A "specific application" is software designed for a particular purpose.

[0277] "User's device" refers to electronic devices that a user uses on a daily basis.

[0278] This invention is a system that evaluates the risk related to floods in real time and issues accurate warnings. The following describes its specific forms.

[0279] The server is the center that collects meteorological data, river water level data, terrain data, and information from social media, and conducts integrated analysis. The meteorological data is obtained through the API of the weather forecast service and includes information such as precipitation, temperature, and wind speed. Also, the river water level data is obtained at any time from the river management system using sensors. The terrain data is extracted from the Geographic Information System (GIS). Thereby, detailed information for each region can be obtained immediately. <000​​​​​​​​​​​​​​​​​​​​ Step 1:

[0286] The server retrieves weather data from the weather API. The inputs at this step are the precipitation, temperature, and wind speed data obtained from the API. The server stores these data in the database and uses them to grasp the real-time weather conditions.

[0287] Step 2:

[0288] The server retrieves water level data from the sensors of the river management system. The input is the water level information provided by the sensors, and based on this, the server grasps the situation of the river. The server records this data for use in trend analysis.

[0289] Step 3:

[0290] The server extracts terrain information from the GIS database. The input is the terrain data of the specified area. The server uses this to analyze the elevation difference of the terrain, the ease of water flow, etc. The data is reflected in the disaster risk assessment.

[0291] Step 4:

[0292] The server collects user posts through the social media API. The inputs are the posted text, image, and video information. The server analyzes the data using natural language processing technology and image processing algorithms to extract useful information. At this time, the fake image detection algorithm is used to eliminate the tampered data.

[0293] Step 5:

[0294] Based on these data, the server activates the AI model. The input is all the data obtained from weather, river water level, terrain, and social media. The server uses learning algorithms to evaluate the flood risk by comparing with past cases. The output is the predicted probability of flood occurrence and the affected area.

[0295] Step 6:

[0296] Based on the risk assessment, the server activates the alarm generation module. The input is risk assessment data generated by an AI model. The server generates an alarm message accordingly and creates an emergency alert.

[0297] Step 7:

[0298] The terminal receives push notifications of alarm messages via a dedicated application. The input is alarm data sent from the server. The terminal displays this data to help the user evacuate quickly. The output is an emergency evacuation order and a display of the risk level for the user.

[0299] (Application Example 1)

[0300] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0301] In modern society, damage caused by floods is a serious problem. To address this, it is necessary to quickly and accurately assess flood risk and encourage appropriate evacuation actions. However, conventional systems have struggled to perform comprehensive data analysis in real time and provide optimal information to individual users. Therefore, a new system is needed that can efficiently assess flood risk and support immediate evacuation.

[0302] 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.

[0303] In this invention, the server includes means for periodically collecting meteorological information, means for receiving river water level information, means for acquiring terrain information, means for analyzing post information from social media and evaluating its reliability, means for detecting and excluding fake images, means for comprehensively analyzing these information and evaluating flood risks, means for transmitting an alarm based on the risk evaluation, and means for notifying the user device of an evacuation route. Thereby, it becomes possible to quickly respond to flood risks and accurately provide information to users.

[0304] "Meteorological information" refers to data related to the state of the atmosphere and includes information such as weather forecasts, temperature, precipitation, wind speed, etc.

[0305] "River water level information" refers to data related to changes in the water level of a river and is obtained from a water level sensor or a river management system.

[0306] "Terrain information" refers to data related to the terrain and topography of a specific area and is usually obtained from a Geographic Information System (GIS).

[0307] "Post information from social media" refers to data of videos and messages posted by users on social networks or online platforms.

[0308] "Fake image" refers to visual data that is intentionally modified or created differently from the actual situation and may mislead about the reality.

[0309] "Risk evaluation" refers to an evaluation calculated by analyzing the possibility of floods and includes the scope of expected impact and occurrence probability.

[0310] "Alarm" refers to a notification that informs users of the existence of a specific danger and includes instructions to prompt urgent actions.

[0311] A "user device" is a device used by a user to receive information or perform operations, and includes smartphones and smart glasses.

[0312] An "evacuation route" is a recommended path for moving to a safe place during a disaster, and it is guided to the user using GPS data and other methods.

[0313] The system for realizing this invention functions by exchanging data between a server located in a cloud environment and a user's terminal (including smartphones and smart glasses).

[0314] The server periodically collects weather information, river water level information, and topographic information from their respective sources. Weather information is obtained through weather forecasting service APIs, river water level information is received as a real-time feed from water level sensors, and topographic information is extracted from geographic information systems (GIS). In addition, it uses social media APIs to collect and analyze user-posted information and evaluate its reliability. Fake images are detected and excluded by image processing algorithms.

[0315] The server comprehensively analyzes this data and uses AI-powered generative models to compare it with past flood data to assess flood risk. This assessment utilizes machine learning frameworks such as TensorFlow, and Python libraries (such as pandas and NumPy) are used to analyze the collected data.

[0316] If a high risk is detected, the server will push an alert to the user's device. The notification will include information about the disaster, as well as the best route for the user to evacuate quickly and safely. This route guidance is updated in real time using the Google Maps API and other tools.

[0317] As a concrete example, if heavy rain is forecast and river levels rise rapidly, the server will issue a warning to users in that area and notify them of evacuation orders and evacuation routes through the application. At this time, users can check detailed instructions on their terminal screen and take safe action. The generated AI model will use a prompt statement like the following: "Predict the flood risk based on current weather data, river level data, and past flood incidents in a given area."

[0318] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0319] Step 1:

[0320] The server periodically retrieves data such as precipitation, temperature, and wind speed from a weather information API. The input data is the weather data received as an API response. This data is parsed in JSON format, and the necessary information is extracted and stored. The output is a set of organized weather data.

[0321] Step 2:

[0322] The server receives water level sensor data from the river management system. The input data is real-time updated water level information. This data is processed into a list format and compared to a specific baseline value. The output is a flag indicating whether the current water level exceeds the danger level.

[0323] Step 3:

[0324] The server retrieves topographic information from a GIS database. The input is topographic map data extracted from a geographic information system. This data is plotted as an outline on a map and then formatted for analysis. The output is a plotted set of topographic data.

[0325] Step 4:

[0326] The server collects user-generated content using social media APIs. Input data includes posted status reports, photos, and videos. Natural language processing and image processing algorithms are used to extract reliable information and detect and remove fake images. The output is a set of reliable user-generated content.

[0327] Step 5:

[0328] The server performs flood risk assessment using TensorFlow. Input data includes weather information, water level information, topographic information, and user-submitted information. An AI model integrates and analyzes this data to predict the probability of flooding and the extent of its impact. Outputs include probability values ​​as a risk assessment and map information of the affected areas.

[0329] Step 6:

[0330] Based on the evaluation results, the server sends an alert via push notification to the user's terminal. Inputs include risk assessment results and user profile information. The alert includes detailed evacuation instructions and risk levels based on the user's location, and is displayed via a dedicated app. Output is the alert notification on the terminal.

[0331] Step 7:

[0332] The user terminal receives an alarm and displays a safe evacuation route. The input is evacuation route instruction data from the server. The route is plotted using the Google Maps API, providing the user with the optimal evacuation path in real time. The output is evacuation route guidance displayed on the terminal screen.

[0333] 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.

[0334] This invention combines a system that comprehensively analyzes weather information, river water level information, topographic information, and social media posts to assess flood risk with a user emotion recognition function. This allows for more effective communication by considering the user's emotions when issuing warnings.

[0335] First, the server periodically collects weather information, river water level data, and topographic information from multiple data sources. This compiles regional environmental data, building a foundation of information on flood risk. Simultaneously, the server collects text and image data from user posts on social media and analyzes them using a sentiment engine.

[0336] The emotion engine analyzes text data, particularly on social media, using natural language processing to identify the emotional state a user is expressing. For example, if a user strongly expresses emotions such as "anxiety" or "fear," this information is fed back to the alarm system. The server then uses this emotion data to adjust the alarm content to suit the user's emotional state. Specifically, it can prioritize sending alarms containing reassuring messages to users experiencing high levels of stress.

[0337] After a risk assessment is performed, the server sends an alert to the device using push notifications. The device immediately displays this notification to the user, helping them to take immediate evacuation action. The alert, adjusted by an emotion engine, is displayed in a specific and easy-to-understand format to help the user act more appropriately.

[0338] Therefore, this system not only assesses flood risk but also enhances safety by providing countermeasures that take into account the user's emotions. In this way, the present invention implements a form that utilizes an emotion engine to provide users with comprehensive and effective flood control measures.

[0339] The following describes the processing flow.

[0340] Step 1:

[0341] The server uses the weather data provider's API to collect real-time weather information. This data includes rainfall, temperature, wind speed, etc., and is stored in a database. Based on this, the server assesses the initial risk of precipitation.

[0342] Step 2:

[0343] The server receives river water level data from river management agencies. The water level information sent from each river sensor is an important indicator for predicting flood risk and is continuously monitored.

[0344] Step 3:

[0345] The server retrieves geographical information from a topographic database and analyzes the topographic characteristics of the area. This information is used to calculate how changes in rainfall and river levels will affect the terrain.

[0346] Step 4:

[0347] The server collects user posts via social media APIs and performs multilingual text analysis using an emotion engine. Here, it evaluates the emotions contained in the posts (e.g., fear, anxiety, relief) and feeds that data back into the system.

[0348] Step 5:

[0349] The server integrates all collected data and uses AI and machine learning models based on past cases to comprehensively assess flood risk. The risk assessment also takes into account the output of the emotion engine.

[0350] Step 6:

[0351] If the risk exceeds a certain threshold, the server generates an alert. The content of the alert is customized based on the analysis results of the emotion engine; for example, a user showing anxiety will receive a message with more reassuring language.

[0352] Step 7:

[0353] The server sends an alert to the device via a dedicated app using push notifications. The device receives this alert and immediately notifies the user to encourage evacuation. The user reviews the notification and prepares to evacuate to a safe place quickly according to the instructions.

[0354] (Example 2)

[0355] 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".

[0356] In recent years, damage from natural disasters has become increasingly severe around the world, necessitating effective risk assessment and swift, appropriate responses. However, conventional risk assessment systems have been insufficient in issuing warnings that take into account the emotional state of users, resulting in a lack of understanding of the warnings and difficulty in translating them into action. Therefore, there is a need to develop a new natural disaster risk assessment system that enables communication that takes user emotions into account.

[0357] 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.

[0358] In this invention, the server includes means for periodically collecting weather data, means for acquiring water level data, and means for acquiring geographical data. This enables rapid and effective assessment of natural disaster risks and the issuance of warnings tailored to the user's emotions.

[0359] "Meteorological data" refers to information about meteorological phenomena, including observational data such as temperature, precipitation, and wind speed.

[0360] "Water level data" refers to information about the water level in bodies of water such as rivers and lakes, and serves as data for assessing flood risk.

[0361] "Geographic data" refers to information about the shape and characteristics of land, and includes topographic maps and elevation data.

[0362] "Social media" refers to information published through internet platforms, and in particular includes posts and comments on social media.

[0363] "False data" refers to information that is inaccurate or untrue, and in particular includes false images and disguised information.

[0364] "Natural disaster risk" refers to an increased likelihood of disasters caused by weather or geological factors, and indicates the danger for which warnings and measures should be taken based on this possibility.

[0365] "Emotional state" refers to the type and intensity of emotions an individual experiences in a particular situation, and includes emotions such as anxiety, fear, and relief.

[0366] "Machine learning technology" refers to the field of technology in which computer systems learn patterns and rules from data and make predictions and decisions based on that learning.

[0367] "Information and communication technology" refers to technologies for generating, processing, transmitting, and receiving digital data, and in particular, technologies that enable real-time information sharing via the internet.

[0368] This embodiment of the invention provides a system that effectively assesses natural disaster risks and issues warnings that take into account the user's emotional state. Specifically, the server collects and analyzes information from various data sources. The server uses databases and APIs necessary for acquiring weather data and connects to sensors and monitoring systems for water level data. Geographic data is also acquired using a Geographic Information System (GIS). Based on this data, the server performs calculations to assess the risk.

[0369] The server further analyzes text data from social media using natural language processing tools. Specifically, it uses software such as Python's NLTK and spaCy to extract emotional states from user posts. This ensures that user emotions are reflected in the generation of warning messages. For example, the server identifies a user's post "I'm worried about heavy rain tonight" as an emotion of "anxiety" and uses this to adjust the warning message.

[0370] The generated alarm messages are then materialized through a generation AI model. As an example of a prompt, the server can execute a command to the generation AI model to "generate a user-facing alarm message based on risk and sentiment scores." This process generates emotionally sensitive, specific, and actionable alarms.

[0371] Finally, the server uses information and communication technology to send the generated alarm as a push notification to the user's terminal. In this way, the terminal instantly displays the alarm to the user, supporting quick action. As a result, the system functions as an effective tool to enhance user safety during disasters.

[0372] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0373] Step 1:

[0374] The server periodically collects weather data, river water level data, and geographical data from various sensors and database APIs. This process requires specific observation locations and measurement device identification information as input. After data collection, the server organizes and stores this data by date and location. The output is an integrated time-series dataset.

[0375] Step 2:

[0376] The server numerically assesses flood risk based on collected geographic information. The input is time-series weather and water level data obtained in the previous step. The server uses Python's NumPy and Pandas to perform statistical analysis and model-based predictions. The output of this process is a calculated risk score and the generation of a risk map for each region.

[0377] Step 3:

[0378] The server collects data from social media posts and analyzes the users' emotional states. It takes text data and, if possible, contextual information from each post as input. This text data is then subjected to emotional classification using natural language processing tools such as Python's NLTK or spaCy. The output is the user's emotional tone (e.g., positive, negative), which is quantified as an emotional score.

[0379] Step 4:

[0380] The server uses a generative AI model to generate alert messages based on risk and sentiment scores. The prompt is "Create a specific and emotionally sensitive alert message for the user." The input consists of previously evaluated risk and sentiment scores. The generated text is provided as an alert message with a tone and content appropriate for the user. The output is a customized message.

[0381] Step 5:

[0382] The server sends a push notification to the user's device to send the generated alarm message. The input consists of contact information and the generated alarm message. The message is sent to the device in real time using a communication protocol, and the device immediately displays this message to the user. As output, the individual message received by the user is displayed on the device screen.

[0383] Step 6:

[0384] The user reviews the received alarm and provides feedback as needed. The input is the content of the alarm message itself. The user provides feedback on whether the provided information is accurate and useful. The output is returned to the server as user feedback data and stored as a reference for future alarm generation.

[0385] (Application Example 2)

[0386] 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."

[0387] In recent years, with the increasing frequency of floods due to climate change, there is a growing need to effectively disseminate information and promote swift evacuation. However, conventional warning systems send uniform warning messages without considering the emotional state of users, which can cause anxiety and fail to encourage appropriate action. Therefore, there is a need for information provision that understands and appropriately considers the emotions of users.

[0388] 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.

[0389] In this invention, the server includes means for periodically collecting weather information, means for receiving river water level information, means for acquiring topographic information, means for analyzing data from social media and recognizing emotions, means for detecting and removing fake images, means for comprehensively analyzing this information and evaluating the threat of flooding, means for issuing emotion-based adjusted warnings, and means for sending warnings via push notifications to user devices through a specific application. This makes it possible to provide flood information in a way that takes into account the user's emotions and provides a sense of security, thereby encouraging appropriate and prompt evacuation actions.

[0390] "Weather information" refers to data on environmental conditions such as weather, temperature, precipitation, and wind speed. By accumulating this data, it provides basic information for understanding the weather conditions in a specific region.

[0391] "River water level information" refers to data measuring water levels at specific points along rivers, and is an important indicator for evaluating the likelihood of flooding.

[0392] "Topographic information" refers to data that shows the relief and topographical features of the land, and is used to assess the level of danger in a region and the risk of flooding.

[0393] "Methods for analyzing data from social media and recognizing emotions" refers to technologies that analyze the content of posts on online platforms and recognize the emotions and psychological states expressed by users.

[0394] "Methods for detecting and removing fake images" refer to technologies for identifying and excluding manipulated images and false information from analysis, and are crucial for reliable data analysis.

[0395] "Means for assessing flood threats" refers to methods for comprehensively evaluating flood risk by integrating meteorological information, river water level information, and topographic information.

[0396] "Means for issuing emotion-based, adjustable alarms" refers to technology that generates and delivers alarm messages whose content is adjusted according to the user's emotional state.

[0397] "A means of sending an alarm via push notification to a user's device through a specific application" refers to a technology that uses dedicated software to instantly send an alarm message to the user's electronic device.

[0398] The system of the present invention aims to assess the flood risk in a user's area based on their emotional state and issue appropriate warnings. This system integrates information from multiple data sources and includes the following components to achieve information delivery that takes the user's emotions into consideration.

[0399] The server first periodically collects and integrates weather information, river water level information, and topographic information. The specific hardware used for this is a data server with high processing power, and the software implements a dedicated application for data collection and analysis.

[0400] Next, the server analyzes posts from social media. This analysis uses natural language processing tools and sentiment analysis engines (e.g., NLP libraries) to identify the user's psychological state and quantify their emotions. This allows the server to discover emotions such as "anxiety" and "fear" that users are expressing, and uses this data to adjust the content of alerts.

[0401] Meanwhile, the terminal receives coordinated alerts transmitted from the server and immediately presents them to the user. This allows the user to understand the current flood risk and quickly take appropriate action, such as evacuation. The terminal is a portable electronic device such as a smartphone or tablet, and provides a user interface through an application.

[0402] As a concrete example, it is possible to perform sentiment analysis using a generative AI model, for instance, by "evaluating users' emotions based on content posted on the media and sending special warning messages to areas where there are posts indicating strong fear."

[0403] Examples of prompts include the following:

[0404] "Analyze the sentiment of social media posts coming from a particular geographic location. If the predominant sentiment is negative, especially fear or anxiety, suggest a comforting message that could be sent to users in that area."

[0405] Through this process, the system can effectively provide users with emotionally sensitive flood information, supporting safe and swift decision-making.

[0406] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0407] Step 1:

[0408] The server periodically collects weather information, river water level information, and topographic information from external databases and APIs. This information is received as configuration data, and the server updates the environmental information for each region. Input is data obtained from external information sources, and output is the latest environmental information stored in the server's database. The process includes automatically retrieving data using API requests.

[0409] Step 2:

[0410] The server collects posting data from a specific region via social media APIs and analyzes users' emotional states using a sentiment analysis engine. The input is posting data obtained from a specific geographical area, and the output is the emotional tendencies of users identified through the analysis (e.g., "anxiety" or "fear"). Data processing is performed by scoring the sentiment of the text using natural language processing techniques.

[0411] Step 3:

[0412] The server comprehensively assesses the flood threat based on all collected data. This assessment utilizes a method that integrates weather, river level, topography, and sentiment data to calculate a risk score. The input is a set of various data, and the output is a numerical representation of the flood risk as a risk score. Data calculations here include weighting and time series analysis.

[0413] Step 4:

[0414] The server generates alarm messages based on risk assessments and adjusts them to be emotionally appropriate. This process incorporates message templates that provide reassurance to users, especially those experiencing significant anxiety, using prompts from a generation AI model. Inputs are risk scores and sentiment analysis results, while output is the text of the alarm message. This process involves template selection and automatic text generation.

[0415] Step 5:

[0416] The terminal presents the user with a pre-configured alarm message sent from the server as a push notification. The input is alarm data from the server, and the output is the alarm message displayed on the terminal's user interface. The terminal uses the OS's notification function to ensure user attention. Based on this, the user can immediately decide on actions such as evacuation.

[0417] 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.

[0418] 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.

[0419] 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.

[0420] [Third Embodiment]

[0421] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0422] 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.

[0423] 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).

[0424] 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.

[0425] 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.

[0426] 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).

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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.

[0432] 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".

[0433] This invention describes a specific embodiment of a system that assesses flood risk and issues rapid warnings by collecting and analyzing weather information, river water level information, topographic information, and social media posts in real time.

[0434] First, the server collects information from various data sources. For weather information, it obtains data such as precipitation, temperature, and wind speed from weather forecasting services via API. River water level information is received from river management systems equipped with water level sensors, and topographic information is extracted from Geographic Information System (GIS) databases. This allows for the acquisition of the latest and most detailed information for each region.

[0435] Next, the server uses social media APIs to collect data such as status reports, photos, and videos posted by users. This information is analyzed using natural language processing and image processing algorithms to extract reliable data. In addition, a fake image detection algorithm is used to eliminate images that may have been tampered with.

[0436] This data is integrated and analyzed within the server. An AI model is launched and compared with past flood data to predict the likelihood of flooding and inundation. The algorithm calculates the probability of flooding and the extent of its impact based on data patterns learned from past events.

[0437] After integrating and analyzing the information, if a high risk is determined, the server immediately activates the alarm generation module. Emergency alerts are then pushed to terminals via a dedicated application. The notification includes detailed evacuation instructions and risk levels for each area, allowing users to take swift and appropriate action. For example, if heavy rainfall is predicted to cause river flooding in a certain area, an alert is immediately sent to residents expected to be affected, providing them with safe evacuation routes.

[0438] Thus, this system automates the entire process, enabling highly accurate and efficient flood risk management.

[0439] The following describes the processing flow.

[0440] Step 1:

[0441] The server connects to the weather data provider's API to obtain the latest weather information in real time. Specifically, it collects data such as rainfall, temperature, wind speed, and wind direction, and stores it in a database. Based on this information, it performs an initial assessment of the likelihood of heavy rainfall.

[0442] Step 2:

[0443] The server accesses the water level measurement system of the river management agency to obtain water level data for each river. The obtained water level information is stored in a database for comparison with past data and serves as basic data for assessing the risk of river flooding.

[0444] Step 3:

[0445] The server obtains topographic data for the area through a geographic information system. This includes elevation, terrain slope, and land use information. Based on this data, it simulates how water will flow and analyzes the possibility of flooding.

[0446] Step 4:

[0447] The server uses APIs from social media platforms to collect user-submitted information. Text data is analyzed using natural language processing to evaluate the reliability of the posts. Image data is also analyzed using a fake image detection algorithm to exclude inappropriate data.

[0448] Step 5:

[0449] The server uses AI and machine learning algorithms to comprehensively analyze all collected data. It compares it with past case datasets to assess flood and inundation risks with high accuracy. In doing so, it operates a predictive model that takes time-series data and topographic characteristics into account.

[0450] Step 6:

[0451] The server issues alerts as needed based on the assessed risk. It sends push notifications to devices via a dedicated application, issuing emergency alerts. These alerts include specific evacuation instructions and recommended actions to support safe evacuation.

[0452] Step 7:

[0453] The device notifies the user of any received alarms. The user checks the notification and begins evacuation according to the instructions. Ensure that information is reliably delivered, including alternative notifications via guaranteed communication methods (e.g., SMS or email).

[0454] (Example 1)

[0455] 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."

[0456] In recent years, floods caused by extreme weather events have become frequent, creating a need for technology that can quickly and accurately assess flood risk and issue timely warnings. Conventional systems have problems such as insufficient integrated information processing and low warning accuracy, which prevents appropriate evacuation orders from being issued.

[0457] 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.

[0458] In this invention, the server includes means for periodically acquiring weather information, means for receiving river water level data, and means for acquiring topographic data. This enables high-precision flood risk assessment and rapid warning issuance by quickly and accurately aggregating and analyzing data from a wide area.

[0459] "Weather information" refers to data related to weather conditions, including precipitation, temperature, and wind speed.

[0460] "Acquiring data periodically" means repeatedly collecting data at predetermined intervals.

[0461] "Water level data" refers to information about the water level of rivers and lakes.

[0462] "Topographic data" refers to information that shows the topography and structure of the land.

[0463] "Information from social media" refers to data such as text, images, and videos posted by users on online platforms.

[0464] "Assessing reliability" is the process of determining the accuracy and usefulness of data.

[0465] A "fake image" is false visual information created through manipulation or alteration.

[0466] "Integrated analysis" means combining multiple different data sources to perform an evaluation.

[0467] "Assessing the risk of flooding" means predicting the risk of floods and inundation.

[0468] "Issuing a warning based on a risk assessment" means issuing a warning based on the predicted risks.

[0469] "Automating" means executing a process without requiring human intervention.

[0470] "Sending an emergency alert to an electronic device" means delivering a warning message to a device when danger is imminent.

[0471] "Users checking evacuation information" means that users become aware of the safety instructions provided.

[0472] A "learning algorithm" is a computational method that uses machine learning to learn data patterns and assist in analysis.

[0473] A "specific application" is software designed for a particular purpose.

[0474] "User's device" refers to electronic devices that a user uses on a daily basis.

[0475] This invention is a system that assesses flood risks in real time and issues accurate warnings. Its specific form is described below.

[0476] The server is the central hub for collecting and integrating information from weather data, river water level data, topographic data, and social media. Weather data is obtained through APIs of weather forecasting services and includes information on precipitation, temperature, and wind speed. River water level data is acquired in real time from a river management system using sensors. Topographic data is extracted from a Geographic Information System (GIS). This allows for the immediate acquisition of detailed information for each region.

[0477] From social media, user posts are retrieved via APIs and analyzed using natural language processing (NLP) and image processing technologies. This extracts useful information while eliminating potentially manipulated visual information using fake image detection algorithms.

[0478] Based on this information, an AI model is launched on the server, and a learning algorithm is used to compare and analyze past flood disaster cases. Based on the results obtained in this way, the risk of flooding and inundation is assessed, and based on that assessment, a warning module is activated.

[0479] The device receives emergency alerts via push notifications through a dedicated application. These notifications include specific evacuation orders and regional risk levels, designed to encourage immediate action.

[0480] For example, the prompt "Assess flood risk and analyze whether a warning is necessary based on heavy rainfall forecast data for the following region: Region A, precipitation 80 mm, wind speed 20 m / s" can be used as input to the generating AI model. This allows the system to quickly and accurately assess the risk and prompt appropriate responses.

[0481] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0482] Step 1:

[0483] The server retrieves weather data from a weather API. The inputs in this step are precipitation, temperature, and wind speed data obtained from the API. The server stores this data in a database and uses it to monitor weather conditions in real time.

[0484] Step 2:

[0485] The server acquires water level data from sensors in the river management system. The input is water level information provided by the sensors, which is used to understand the river's condition. The server records this data to aid in trend analysis.

[0486] Step 3:

[0487] The server extracts topographic information from a GIS database. The input is topographic data for a specified region. The server uses this data to analyze topographic elevation differences, water flow characteristics, and other factors. This data is then used in disaster risk assessments.

[0488] Step 4:

[0489] The server collects user posts through social media APIs. The input consists of posted text, images, and video information. The server analyzes the data using natural language processing and image processing algorithms to extract useful information. During this process, a fake image detection algorithm is used to eliminate tampered data.

[0490] Step 5:

[0491] Based on this data, the server activates an AI model. The input consists of all data obtained from weather, river levels, topography, and social media. The server uses a learning algorithm to assess flood risk by comparing it to past events. The output is the predicted probability of flooding and the extent of its impact.

[0492] Step 6:

[0493] Based on the risk assessment, the server activates the alarm generation module. The input is risk assessment data generated by an AI model. The server generates an alarm message accordingly and creates an emergency alert.

[0494] Step 7:

[0495] The terminal receives push notifications of alarm messages via a dedicated application. The input is alarm data sent from the server. The terminal displays this data to help the user evacuate quickly. The output is an emergency evacuation order and a display of the risk level for the user.

[0496] (Application Example 1)

[0497] 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."

[0498] In modern society, damage caused by floods is a serious problem. To address this, it is necessary to quickly and accurately assess flood risk and encourage appropriate evacuation actions. However, conventional systems have struggled to perform comprehensive data analysis in real time and provide optimal information to individual users. Therefore, a new system is needed that can efficiently assess flood risk and support immediate evacuation.

[0499] 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.

[0500] In this invention, the server includes means for periodically collecting weather information, means for receiving river water level information, means for acquiring topographic information, means for analyzing and evaluating the reliability of posts from social media, means for detecting and excluding fake images, means for comprehensively analyzing this information and evaluating flood risk, means for issuing warnings based on the risk assessment, and means for notifying user devices of evacuation routes. This enables a rapid response to flood risk and accurate information provision to users.

[0501] "Weather information" refers to data about atmospheric conditions, including weather forecasts, temperature, precipitation, and wind speed.

[0502] "River water level information" refers to data on changes in water levels in rivers, obtained from water level sensors and river management systems.

[0503] "Topographic information" refers to data about the topography and terrain of a specific area, and is usually obtained from a Geographic Information System (GIS).

[0504] "Social media posts" refer to video and message data that users post on social networks and online platforms.

[0505] A "fake image" is visual data that is intentionally altered or created to differ from reality, and may misrepresent the truth.

[0506] "Risk assessment" is an evaluation calculated by analyzing the possibility of flooding, and includes the expected scope of impact and the probability of occurrence.

[0507] An "alert" is a notification that informs the user of the presence of a specific danger and includes instructions to prompt immediate action.

[0508] A "user device" is a device used by a user to receive information or perform operations, and includes smartphones and smart glasses.

[0509] An "evacuation route" is a recommended path for moving to a safe place during a disaster, and it is guided to the user using GPS data and other methods.

[0510] The system for realizing this invention functions by exchanging data between a server located in a cloud environment and a user's terminal (including smartphones and smart glasses).

[0511] The server periodically collects weather information, river water level information, and topographic information from their respective sources. Weather information is obtained through weather forecasting service APIs, river water level information is received as a real-time feed from water level sensors, and topographic information is extracted from geographic information systems (GIS). In addition, it uses social media APIs to collect and analyze user-posted information and evaluate its reliability. Fake images are detected and excluded by image processing algorithms.

[0512] The server comprehensively analyzes this data and uses AI-powered generative models to compare it with past flood data to assess flood risk. This assessment utilizes machine learning frameworks such as TensorFlow, and Python libraries (such as pandas and NumPy) are used to analyze the collected data.

[0513] If a high risk is detected, the server will push an alert to the user's device. The notification will include information about the disaster, as well as the best route for the user to evacuate quickly and safely. This route guidance is updated in real time using the Google Maps API and other tools.

[0514] As a concrete example, if heavy rain is forecast and river levels rise rapidly, the server will issue a warning to users in that area and notify them of evacuation orders and evacuation routes through the application. At this time, users can check detailed instructions on their terminal screen and take safe action. The generated AI model will use a prompt statement like the following: "Predict the flood risk based on current weather data, river level data, and past flood incidents in a given area."

[0515] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0516] Step 1:

[0517] The server periodically retrieves data such as precipitation, temperature, and wind speed from a weather information API. The input data is the weather data received as an API response. This data is parsed in JSON format, and the necessary information is extracted and stored. The output is a set of organized weather data.

[0518] Step 2:

[0519] The server receives water level sensor data from the river management system. The input data is real-time updated water level information. This data is processed into a list format and compared to a specific baseline value. The output is a flag indicating whether the current water level exceeds the danger level.

[0520] Step 3:

[0521] The server retrieves topographic information from a GIS database. The input is topographic map data extracted from a geographic information system. This data is plotted as an outline on a map and then formatted for analysis. The output is a plotted set of topographic data.

[0522] Step 4:

[0523] The server collects user-generated content using social media APIs. Input data includes posted status reports, photos, and videos. Natural language processing and image processing algorithms are used to extract reliable information and detect and remove fake images. The output is a set of reliable user-generated content.

[0524] Step 5:

[0525] The server performs flood risk assessment using TensorFlow. Input data includes weather information, water level information, topographic information, and user-submitted information. An AI model integrates and analyzes this data to predict the probability of flooding and the extent of its impact. Outputs include probability values ​​as a risk assessment and map information of the affected areas.

[0526] Step 6:

[0527] Based on the evaluation results, the server sends an alert via push notification to the user's terminal. Inputs include risk assessment results and user profile information. The alert includes detailed evacuation instructions and risk levels based on the user's location, and is displayed via a dedicated app. Output is the alert notification on the terminal.

[0528] Step 7:

[0529] The user terminal receives an alarm and displays a safe evacuation route. The input is evacuation route instruction data from the server. The route is plotted using the Google Maps API, providing the user with the optimal evacuation path in real time. The output is evacuation route guidance displayed on the terminal screen.

[0530] 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.

[0531] This invention combines a system that comprehensively analyzes weather information, river water level information, topographic information, and social media posts to assess flood risk with a user emotion recognition function. This allows for more effective communication by considering the user's emotions when issuing warnings.

[0532] First, the server periodically collects weather information, river water level data, and topographic information from multiple data sources. This compiles regional environmental data, building a foundation of information on flood risk. Simultaneously, the server collects text and image data from user posts on social media and analyzes them using a sentiment engine.

[0533] The emotion engine analyzes text data, particularly on social media, using natural language processing to identify the emotional state a user is expressing. For example, if a user strongly expresses emotions such as "anxiety" or "fear," this information is fed back to the alarm system. The server then uses this emotion data to adjust the alarm content to suit the user's emotional state. Specifically, it can prioritize sending alarms containing reassuring messages to users experiencing high levels of stress.

[0534] After a risk assessment is performed, the server sends an alert to the device using push notifications. The device immediately displays this notification to the user, helping them to take immediate evacuation action. The alert, adjusted by an emotion engine, is displayed in a specific and easy-to-understand format to help the user act more appropriately.

[0535] Therefore, this system not only assesses flood risk but also enhances safety by providing countermeasures that take into account the user's emotions. In this way, the present invention implements a form that utilizes an emotion engine to provide users with comprehensive and effective flood control measures.

[0536] The following describes the processing flow.

[0537] Step 1:

[0538] The server uses the weather data provider's API to collect real-time weather information. This data includes rainfall, temperature, wind speed, etc., and is stored in a database. Based on this, the server assesses the initial risk of precipitation.

[0539] Step 2:

[0540] The server receives river water level data from river management agencies. The water level information sent from each river sensor is an important indicator for predicting flood risk and is continuously monitored.

[0541] Step 3:

[0542] The server retrieves geographical information from a topographic database and analyzes the topographic characteristics of the area. This information is used to calculate how changes in rainfall and river levels will affect the terrain.

[0543] Step 4:

[0544] The server collects user posts via social media APIs and performs multilingual text analysis using an emotion engine. Here, it evaluates the emotions contained in the posts (e.g., fear, anxiety, relief) and feeds that data back into the system.

[0545] Step 5:

[0546] The server integrates all collected data and uses AI and machine learning models based on past cases to comprehensively assess flood risk. The risk assessment also takes into account the output of the emotion engine.

[0547] Step 6:

[0548] If the risk exceeds a certain threshold, the server generates an alert. The content of the alert is customized based on the analysis results of the emotion engine; for example, a user showing anxiety will receive a message with more reassuring language.

[0549] Step 7:

[0550] The server sends an alert to the device via a dedicated app using push notifications. The device receives this alert and immediately notifies the user to encourage evacuation. The user reviews the notification and prepares to evacuate to a safe place quickly according to the instructions.

[0551] (Example 2)

[0552] 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."

[0553] In recent years, damage from natural disasters has become increasingly severe around the world, necessitating effective risk assessment and swift, appropriate responses. However, conventional risk assessment systems have been insufficient in issuing warnings that take into account the emotional state of users, resulting in a lack of understanding of the warnings and difficulty in translating them into action. Therefore, there is a need to develop a new natural disaster risk assessment system that enables communication that takes user emotions into account.

[0554] 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.

[0555] In this invention, the server includes means for periodically collecting weather data, means for acquiring water level data, and means for acquiring geographical data. This enables rapid and effective assessment of natural disaster risks and the issuance of warnings tailored to the user's emotions.

[0556] "Meteorological data" refers to information about meteorological phenomena, including observational data such as temperature, precipitation, and wind speed.

[0557] "Water level data" refers to information about the water level in bodies of water such as rivers and lakes, and serves as data for assessing flood risk.

[0558] "Geographic data" refers to information about the shape and characteristics of land, and includes topographic maps and elevation data.

[0559] "Social media" refers to information published through internet platforms, and in particular includes posts and comments on social media.

[0560] "False data" refers to information that is inaccurate or untrue, and in particular includes false images and disguised information.

[0561] "Natural disaster risk" refers to an increased likelihood of disasters caused by weather or geological factors, and indicates the danger for which warnings and measures should be taken based on this possibility.

[0562] "Emotional state" refers to the type and intensity of emotions an individual experiences in a particular situation, and includes emotions such as anxiety, fear, and relief.

[0563] "Machine learning technology" refers to the field of technology in which computer systems learn patterns and rules from data and make predictions and decisions based on that learning.

[0564] "Information and communication technology" refers to technologies for generating, processing, transmitting, and receiving digital data, and in particular, technologies that enable real-time information sharing via the internet.

[0565] This embodiment of the invention provides a system that effectively assesses natural disaster risks and issues warnings that take into account the user's emotional state. Specifically, the server collects and analyzes information from various data sources. The server uses databases and APIs necessary for acquiring weather data and connects to sensors and monitoring systems for water level data. Geographic data is also acquired using a Geographic Information System (GIS). Based on this data, the server performs calculations to assess the risk.

[0566] The server further analyzes text data from social media using natural language processing tools. Specifically, it uses software such as Python's NLTK and spaCy to extract emotional states from user posts. This ensures that user emotions are reflected in the generation of warning messages. For example, the server identifies a user's post "I'm worried about heavy rain tonight" as an emotion of "anxiety" and uses this to adjust the warning message.

[0567] The generated alarm messages are then materialized through a generation AI model. As an example of a prompt, the server can execute a command to the generation AI model to "generate a user-facing alarm message based on risk and sentiment scores." This process generates emotionally sensitive, specific, and actionable alarms.

[0568] Finally, the server uses information and communication technology to send the generated alarm as a push notification to the user's terminal. In this way, the terminal instantly displays the alarm to the user, supporting quick action. As a result, the system functions as an effective tool to enhance user safety during disasters.

[0569] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0570] Step 1:

[0571] The server periodically collects weather data, river water level data, and geographical data from various sensors and database APIs. This process requires specific observation locations and measurement device identification information as input. After data collection, the server organizes and stores this data by date and location. The output is an integrated time-series dataset.

[0572] Step 2:

[0573] The server numerically assesses flood risk based on collected geographic information. The input is time-series weather and water level data obtained in the previous step. The server uses Python's NumPy and Pandas to perform statistical analysis and model-based predictions. The output of this process is a calculated risk score and the generation of a risk map for each region.

[0574] Step 3:

[0575] The server collects data from social media posts and analyzes the users' emotional states. It takes text data and, if possible, contextual information from each post as input. This text data is then subjected to emotional classification using natural language processing tools such as Python's NLTK or spaCy. The output is the user's emotional tone (e.g., positive, negative), which is quantified as an emotional score.

[0576] Step 4:

[0577] The server uses a generative AI model to generate alert messages based on risk and sentiment scores. The prompt is "Create a specific and emotionally sensitive alert message for the user." The input consists of previously evaluated risk and sentiment scores. The generated text is provided as an alert message with a tone and content appropriate for the user. The output is a customized message.

[0578] Step 5:

[0579] The server sends a push notification to the user's device to send the generated alarm message. The input consists of contact information and the generated alarm message. The message is sent to the device in real time using a communication protocol, and the device immediately displays this message to the user. As output, the individual message received by the user is displayed on the device screen.

[0580] Step 6:

[0581] The user reviews the received alarm and provides feedback as needed. The input is the content of the alarm message itself. The user provides feedback on whether the provided information is accurate and useful. The output is returned to the server as user feedback data and stored as a reference for future alarm generation.

[0582] (Application Example 2)

[0583] 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."

[0584] In recent years, with the increasing frequency of floods due to climate change, there is a growing need to effectively disseminate information and promote swift evacuation. However, conventional warning systems send uniform warning messages without considering the emotional state of users, which can cause anxiety and fail to encourage appropriate action. Therefore, there is a need for information provision that understands and appropriately considers the emotions of users.

[0585] 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.

[0586] In this invention, the server includes means for periodically collecting weather information, means for receiving river water level information, means for acquiring topographic information, means for analyzing data from social media and recognizing emotions, means for detecting and removing fake images, means for comprehensively analyzing this information and evaluating the threat of flooding, means for issuing emotion-based adjusted warnings, and means for sending warnings via push notifications to user devices through a specific application. This makes it possible to provide flood information in a way that takes into account the user's emotions and provides a sense of security, thereby encouraging appropriate and prompt evacuation actions.

[0587] "Weather information" refers to data on environmental conditions such as weather, temperature, precipitation, and wind speed. By accumulating this data, it provides basic information for understanding the weather conditions in a specific region.

[0588] "River water level information" refers to data measuring water levels at specific points along rivers, and is an important indicator for evaluating the likelihood of flooding.

[0589] "Topographic information" refers to data that shows the relief and topographical features of the land, and is used to assess the level of danger in a region and the risk of flooding.

[0590] "Methods for analyzing data from social media and recognizing emotions" refers to technologies that analyze the content of posts on online platforms and recognize the emotions and psychological states expressed by users.

[0591] "Methods for detecting and removing fake images" refer to technologies for identifying and excluding manipulated images and false information from analysis, and are crucial for reliable data analysis.

[0592] "Means for assessing flood threats" refers to methods for comprehensively evaluating flood risk by integrating meteorological information, river water level information, and topographic information.

[0593] "Means for issuing emotion-based, adjustable alarms" refers to technology that generates and delivers alarm messages whose content is adjusted according to the user's emotional state.

[0594] "A means of sending an alarm via push notification to a user's device through a specific application" refers to a technology that uses dedicated software to instantly send an alarm message to the user's electronic device.

[0595] The system of the present invention aims to assess the flood risk in a user's area based on their emotional state and issue appropriate warnings. This system integrates information from multiple data sources and includes the following components to achieve information delivery that takes the user's emotions into consideration.

[0596] The server first periodically collects and integrates weather information, river water level information, and topographic information. The specific hardware used for this is a data server with high processing power, and the software implements a dedicated application for data collection and analysis.

[0597] Next, the server analyzes posts from social media. This analysis uses natural language processing tools and sentiment analysis engines (e.g., NLP libraries) to identify the user's psychological state and quantify their emotions. This allows the server to discover emotions such as "anxiety" and "fear" that users are expressing, and uses this data to adjust the content of alerts.

[0598] Meanwhile, the terminal receives coordinated alerts transmitted from the server and immediately presents them to the user. This allows the user to understand the current flood risk and quickly take appropriate action, such as evacuation. The terminal is a portable electronic device such as a smartphone or tablet, and provides a user interface through an application.

[0599] As a concrete example, it is possible to perform sentiment analysis using a generative AI model, for instance, by "evaluating users' emotions based on content posted on the media and sending special warning messages to areas where there are posts indicating strong fear."

[0600] Examples of prompts include the following:

[0601] "Analyze the sentiment of social media posts coming from a particular geographic location. If the predominant sentiment is negative, especially fear or anxiety, suggest a comforting message that could be sent to users in that area."

[0602] Through this process, the system can effectively provide users with emotionally sensitive flood information, supporting safe and swift decision-making.

[0603] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0604] Step 1:

[0605] The server periodically collects weather information, river water level information, and topographic information from external databases and APIs. This information is received as configuration data, and the server updates the environmental information for each region. Input is data obtained from external information sources, and output is the latest environmental information stored in the server's database. The process includes automatically retrieving data using API requests.

[0606] Step 2:

[0607] The server collects posting data from a specific region via social media APIs and analyzes users' emotional states using a sentiment analysis engine. The input is posting data obtained from a specific geographical area, and the output is the emotional tendencies of users identified through the analysis (e.g., "anxiety" or "fear"). Data processing is performed by scoring the sentiment of the text using natural language processing techniques.

[0608] Step 3:

[0609] The server comprehensively assesses the flood threat based on all collected data. This assessment utilizes a method that integrates weather, river level, topography, and sentiment data to calculate a risk score. The input is a set of various data, and the output is a numerical representation of the flood risk as a risk score. Data calculations here include weighting and time series analysis.

[0610] Step 4:

[0611] The server generates alarm messages based on risk assessments and adjusts them to be emotionally appropriate. This process incorporates message templates that provide reassurance to users, especially those experiencing significant anxiety, using prompts from a generation AI model. Inputs are risk scores and sentiment analysis results, while output is the text of the alarm message. This process involves template selection and automatic text generation.

[0612] Step 5:

[0613] The terminal presents the user with a pre-configured alarm message sent from the server as a push notification. The input is alarm data from the server, and the output is the alarm message displayed on the terminal's user interface. The terminal uses the OS's notification function to ensure user attention. Based on this, the user can immediately decide on actions such as evacuation.

[0614] 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.

[0615] 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.

[0616] 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.

[0617] [Fourth Embodiment]

[0618] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0619] 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.

[0620] 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).

[0621] 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.

[0622] 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.

[0623] 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).

[0624] 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.

[0625] 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 in 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.

[0626] 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.

[0627] 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.

[0628] 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.

[0629] 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.

[0630] 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".

[0631] This invention describes a specific embodiment of a system that assesses flood risk and issues rapid warnings by collecting and analyzing weather information, river water level information, topographic information, and social media posts in real time.

[0632] First, the server collects information from various data sources. For weather information, it obtains data such as precipitation, temperature, and wind speed from weather forecasting services via API. River water level information is received from river management systems equipped with water level sensors, and topographic information is extracted from Geographic Information System (GIS) databases. This allows for the acquisition of the latest and most detailed information for each region.

[0633] Next, the server uses social media APIs to collect data such as status reports, photos, and videos posted by users. This information is analyzed using natural language processing and image processing algorithms to extract reliable data. In addition, a fake image detection algorithm is used to eliminate images that may have been tampered with.

[0634] This data is integrated and analyzed within the server. An AI model is launched and compared with past flood data to predict the likelihood of flooding and inundation. The algorithm calculates the probability of flooding and the extent of its impact based on data patterns learned from past events.

[0635] After integrating and analyzing the information, if a high risk is determined, the server immediately activates the alarm generation module. Emergency alerts are then pushed to terminals via a dedicated application. The notification includes detailed evacuation instructions and risk levels for each area, allowing users to take swift and appropriate action. For example, if heavy rainfall is predicted to cause river flooding in a certain area, an alert is immediately sent to residents expected to be affected, providing them with safe evacuation routes.

[0636] Thus, this system automates the entire process, enabling highly accurate and efficient flood risk management.

[0637] The following describes the processing flow.

[0638] Step 1:

[0639] The server connects to the weather data provider's API to obtain the latest weather information in real time. Specifically, it collects data such as rainfall, temperature, wind speed, and wind direction, and stores it in a database. Based on this information, it performs an initial assessment of the likelihood of heavy rainfall.

[0640] Step 2:

[0641] The server accesses the water level measurement system of the river management agency to obtain water level data for each river. The obtained water level information is stored in a database for comparison with past data and serves as basic data for assessing the risk of river flooding.

[0642] Step 3:

[0643] The server obtains topographic data for the area through a geographic information system. This includes elevation, terrain slope, and land use information. Based on this data, it simulates how water will flow and analyzes the possibility of flooding.

[0644] Step 4:

[0645] The server uses APIs from social media platforms to collect user-submitted information. Text data is analyzed using natural language processing to evaluate the reliability of the posts. Image data is also analyzed using a fake image detection algorithm to exclude inappropriate data.

[0646] Step 5:

[0647] The server uses AI and machine learning algorithms to comprehensively analyze all collected data. It compares it with past case datasets to assess flood and inundation risks with high accuracy. In doing so, it operates a predictive model that takes time-series data and topographic characteristics into account.

[0648] Step 6:

[0649] The server issues alerts as needed based on the assessed risk. It sends push notifications to devices via a dedicated application, issuing emergency alerts. These alerts include specific evacuation instructions and recommended actions to support safe evacuation.

[0650] Step 7:

[0651] The device notifies the user of any received alarms. The user checks the notification and begins evacuation according to the instructions. Ensure that information is reliably delivered, including alternative notifications via guaranteed communication methods (e.g., SMS or email).

[0652] (Example 1)

[0653] 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".

[0654] In recent years, floods caused by extreme weather events have become frequent, creating a need for technology that can quickly and accurately assess flood risk and issue timely warnings. Conventional systems have problems such as insufficient integrated information processing and low warning accuracy, which prevents appropriate evacuation orders from being issued.

[0655] 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.

[0656] In this invention, the server includes means for periodically acquiring weather information, means for receiving river water level data, and means for acquiring topographic data. This enables high-precision flood risk assessment and rapid warning issuance by quickly and accurately aggregating and analyzing data from a wide area.

[0657] "Weather information" refers to data related to weather conditions, including precipitation, temperature, and wind speed.

[0658] "Acquiring data periodically" means repeatedly collecting data at predetermined intervals.

[0659] "Water level data" refers to information about the water level of rivers and lakes.

[0660] "Topographic data" refers to information that shows the topography and structure of the land.

[0661] "Information from social media" refers to data such as text, images, and videos posted by users on online platforms.

[0662] "Assessing reliability" is the process of determining the accuracy and usefulness of data.

[0663] A "fake image" is false visual information created through manipulation or alteration.

[0664] "Integrated analysis" means combining multiple different data sources to perform an evaluation.

[0665] "Assessing the risk of flooding" means predicting the risk of floods and inundation.

[0666] "Issuing a warning based on a risk assessment" means issuing a warning based on the predicted risks.

[0667] "Automating" means executing a process without requiring human intervention.

[0668] "Sending an emergency alert to an electronic device" means delivering a warning message to a device when danger is imminent.

[0669] "Users checking evacuation information" means that users become aware of the safety instructions provided.

[0670] A "learning algorithm" is a computational method that uses machine learning to learn data patterns and assist in analysis.

[0671] A "specific application" is software designed for a particular purpose.

[0672] "User's device" refers to electronic devices that a user uses on a daily basis.

[0673] This invention is a system that assesses flood risks in real time and issues accurate warnings. Its specific form is described below.

[0674] The server is the central hub for collecting and integrating information from weather data, river water level data, topographic data, and social media. Weather data is obtained through APIs of weather forecasting services and includes information on precipitation, temperature, and wind speed. River water level data is acquired in real time from a river management system using sensors. Topographic data is extracted from a Geographic Information System (GIS). This allows for the immediate acquisition of detailed information for each region.

[0675] From social media, user posts are retrieved via APIs and analyzed using natural language processing (NLP) and image processing technologies. This extracts useful information while eliminating potentially manipulated visual information using fake image detection algorithms.

[0676] Based on this information, an AI model is launched on the server, and a learning algorithm is used to compare and analyze past flood disaster cases. Based on the results obtained in this way, the risk of flooding and inundation is assessed, and based on that assessment, a warning module is activated.

[0677] The device receives emergency alerts via push notifications through a dedicated application. These notifications include specific evacuation orders and regional risk levels, designed to encourage immediate action.

[0678] For example, the prompt "Assess flood risk and analyze whether a warning is necessary based on heavy rainfall forecast data for the following region: Region A, precipitation 80 mm, wind speed 20 m / s" can be used as input to the generating AI model. This allows the system to quickly and accurately assess the risk and prompt appropriate responses.

[0679] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0680] Step 1:

[0681] The server retrieves weather data from a weather API. The inputs in this step are precipitation, temperature, and wind speed data obtained from the API. The server stores this data in a database and uses it to monitor weather conditions in real time.

[0682] Step 2:

[0683] The server acquires water level data from sensors in the river management system. The input is water level information provided by the sensors, which is used to understand the river's condition. The server records this data to aid in trend analysis.

[0684] Step 3:

[0685] The server extracts topographic information from a GIS database. The input is topographic data for a specified region. The server uses this data to analyze topographic elevation differences, water flow characteristics, and other factors. This data is then used in disaster risk assessments.

[0686] Step 4:

[0687] The server collects user posts through social media APIs. The input consists of posted text, images, and video information. The server analyzes the data using natural language processing and image processing algorithms to extract useful information. During this process, a fake image detection algorithm is used to eliminate tampered data.

[0688] Step 5:

[0689] Based on this data, the server activates an AI model. The input consists of all data obtained from weather, river levels, topography, and social media. The server uses a learning algorithm to assess flood risk by comparing it to past events. The output is the predicted probability of flooding and the extent of its impact.

[0690] Step 6:

[0691] Based on the risk assessment, the server activates the alarm generation module. The input is risk assessment data generated by an AI model. The server generates an alarm message accordingly and creates an emergency alert.

[0692] Step 7:

[0693] The terminal receives push notifications of alarm messages via a dedicated application. The input is alarm data sent from the server. The terminal displays this data to help the user evacuate quickly. The output is an emergency evacuation order and a display of the risk level for the user.

[0694] (Application Example 1)

[0695] 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".

[0696] In modern society, damage caused by floods is a serious problem. To address this, it is necessary to quickly and accurately assess flood risk and encourage appropriate evacuation actions. However, conventional systems have struggled to perform comprehensive data analysis in real time and provide optimal information to individual users. Therefore, a new system is needed that can efficiently assess flood risk and support immediate evacuation.

[0697] 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.

[0698] In this invention, the server includes means for periodically collecting weather information, means for receiving river water level information, means for acquiring topographic information, means for analyzing and evaluating the reliability of posts from social media, means for detecting and excluding fake images, means for comprehensively analyzing this information and evaluating flood risk, means for issuing warnings based on the risk assessment, and means for notifying user devices of evacuation routes. This enables a rapid response to flood risk and accurate information provision to users.

[0699] "Weather information" refers to data about atmospheric conditions, including weather forecasts, temperature, precipitation, and wind speed.

[0700] "River water level information" refers to data on changes in water levels in rivers, obtained from water level sensors and river management systems.

[0701] "Topographic information" refers to data about the topography and terrain of a specific area, and is usually obtained from a Geographic Information System (GIS).

[0702] "Social media posts" refer to video and message data that users post on social networks and online platforms.

[0703] A "fake image" is visual data that is intentionally altered or created to differ from reality, and may misrepresent the truth.

[0704] "Risk assessment" is an evaluation calculated by analyzing the possibility of flooding, and includes the expected scope of impact and the probability of occurrence.

[0705] An "alert" is a notification that informs the user of the presence of a specific danger and includes instructions to prompt immediate action.

[0706] A "user device" is a device used by a user to receive information or perform operations, and includes smartphones and smart glasses.

[0707] An "evacuation route" is a recommended path for moving to a safe place during a disaster, and it is guided to the user using GPS data and other methods.

[0708] The system for realizing this invention functions by exchanging data between a server located in a cloud environment and a user's terminal (including smartphones and smart glasses).

[0709] The server periodically collects weather information, river water level information, and topographic information from their respective sources. Weather information is obtained through weather forecasting service APIs, river water level information is received as a real-time feed from water level sensors, and topographic information is extracted from geographic information systems (GIS). In addition, it uses social media APIs to collect and analyze user-posted information and evaluate its reliability. Fake images are detected and excluded by image processing algorithms.

[0710] The server comprehensively analyzes this data and uses AI-powered generative models to compare it with past flood data to assess flood risk. This assessment utilizes machine learning frameworks such as TensorFlow, and Python libraries (such as pandas and NumPy) are used to analyze the collected data.

[0711] If a high risk is detected, the server will push an alert to the user's device. The notification will include information about the disaster, as well as the best route for the user to evacuate quickly and safely. This route guidance is updated in real time using the Google Maps API and other tools.

[0712] As a concrete example, if heavy rain is forecast and river levels rise rapidly, the server will issue a warning to users in that area and notify them of evacuation orders and evacuation routes through the application. At this time, users can check detailed instructions on their terminal screen and take safe action. The generated AI model will use a prompt statement like the following: "Predict the flood risk based on current weather data, river level data, and past flood incidents in a given area."

[0713] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0714] Step 1:

[0715] The server periodically retrieves data such as precipitation, temperature, and wind speed from a weather information API. The input data is the weather data received as an API response. This data is parsed in JSON format, and the necessary information is extracted and stored. The output is a set of organized weather data.

[0716] Step 2:

[0717] The server receives water level sensor data from the river management system. The input data is real-time updated water level information. This data is processed into a list format and compared to a specific baseline value. The output is a flag indicating whether the current water level exceeds the danger level.

[0718] Step 3:

[0719] The server retrieves topographic information from a GIS database. The input is topographic map data extracted from a geographic information system. This data is plotted as an outline on a map and then formatted for analysis. The output is a plotted set of topographic data.

[0720] Step 4:

[0721] The server collects user-generated content using social media APIs. Input data includes posted status reports, photos, and videos. Natural language processing and image processing algorithms are used to extract reliable information and detect and remove fake images. The output is a set of reliable user-generated content.

[0722] Step 5:

[0723] The server performs flood risk assessment using TensorFlow. Input data includes weather information, water level information, topographic information, and user-submitted information. An AI model integrates and analyzes this data to predict the probability of flooding and the extent of its impact. Outputs include probability values ​​as a risk assessment and map information of the affected areas.

[0724] Step 6:

[0725] Based on the evaluation results, the server sends an alert via push notification to the user's terminal. Inputs include risk assessment results and user profile information. The alert includes detailed evacuation instructions and risk levels based on the user's location, and is displayed via a dedicated app. Output is the alert notification on the terminal.

[0726] Step 7:

[0727] The user terminal receives an alarm and displays a safe evacuation route. The input is evacuation route instruction data from the server. The route is plotted using the Google Maps API, providing the user with the optimal evacuation path in real time. The output is evacuation route guidance displayed on the terminal screen.

[0728] 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.

[0729] This invention combines a system that comprehensively analyzes weather information, river water level information, topographic information, and social media posts to assess flood risk with a user emotion recognition function. This allows for more effective communication by considering the user's emotions when issuing warnings.

[0730] First, the server periodically collects weather information, river water level data, and topographic information from multiple data sources. This compiles regional environmental data, building a foundation of information on flood risk. Simultaneously, the server collects text and image data from user posts on social media and analyzes them using a sentiment engine.

[0731] The emotion engine analyzes text data, particularly on social media, using natural language processing to identify the emotional state a user is expressing. For example, if a user strongly expresses emotions such as "anxiety" or "fear," this information is fed back to the alarm system. The server then uses this emotion data to adjust the alarm content to suit the user's emotional state. Specifically, it can prioritize sending alarms containing reassuring messages to users experiencing high levels of stress.

[0732] After a risk assessment is performed, the server sends an alert to the device using push notifications. The device immediately displays this notification to the user, helping them to take immediate evacuation action. The alert, adjusted by an emotion engine, is displayed in a specific and easy-to-understand format to help the user act more appropriately.

[0733] Therefore, this system not only assesses flood risk but also enhances safety by providing countermeasures that take into account the user's emotions. In this way, the present invention implements a form that utilizes an emotion engine to provide users with comprehensive and effective flood control measures.

[0734] The following describes the processing flow.

[0735] Step 1:

[0736] The server uses the weather data provider's API to collect real-time weather information. This data includes rainfall, temperature, wind speed, etc., and is stored in a database. Based on this, the server assesses the initial risk of precipitation.

[0737] Step 2:

[0738] The server receives river water level data from river management agencies. The water level information sent from each river sensor is an important indicator for predicting flood risk and is continuously monitored.

[0739] Step 3:

[0740] The server retrieves geographical information from a topographic database and analyzes the topographic characteristics of the area. This information is used to calculate how changes in rainfall and river levels will affect the terrain.

[0741] Step 4:

[0742] The server collects user posts via social media APIs and performs multilingual text analysis using an emotion engine. Here, it evaluates the emotions contained in the posts (e.g., fear, anxiety, relief) and feeds that data back into the system.

[0743] Step 5:

[0744] The server integrates all collected data and uses AI and machine learning models based on past cases to comprehensively assess flood risk. The risk assessment also takes into account the output of the emotion engine.

[0745] Step 6:

[0746] If the risk exceeds a certain threshold, the server generates an alert. The content of the alert is customized based on the analysis results of the emotion engine; for example, a user showing anxiety will receive a message with more reassuring language.

[0747] Step 7:

[0748] The server sends an alert to the device via a dedicated app using push notifications. The device receives this alert and immediately notifies the user to encourage evacuation. The user reviews the notification and prepares to evacuate to a safe place quickly according to the instructions.

[0749] (Example 2)

[0750] 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".

[0751] In recent years, damage from natural disasters has become increasingly severe around the world, necessitating effective risk assessment and swift, appropriate responses. However, conventional risk assessment systems have been insufficient in issuing warnings that take into account the emotional state of users, resulting in a lack of understanding of the warnings and difficulty in translating them into action. Therefore, there is a need to develop a new natural disaster risk assessment system that enables communication that takes user emotions into account.

[0752] 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.

[0753] In this invention, the server includes means for periodically collecting weather data, means for acquiring water level data, and means for acquiring geographical data. This enables rapid and effective assessment of natural disaster risks and the issuance of warnings tailored to the user's emotions.

[0754] "Meteorological data" refers to information about meteorological phenomena, including observational data such as temperature, precipitation, and wind speed.

[0755] "Water level data" refers to information about the water level in bodies of water such as rivers and lakes, and serves as data for assessing flood risk.

[0756] "Geographic data" refers to information about the shape and characteristics of land, and includes topographic maps and elevation data.

[0757] "Social media" refers to information published through internet platforms, and in particular includes posts and comments on social media.

[0758] "False data" refers to information that is inaccurate or untrue, and in particular includes false images and disguised information.

[0759] "Natural disaster risk" refers to an increased likelihood of disasters caused by weather or geological factors, and indicates the danger for which warnings and measures should be taken based on this possibility.

[0760] "Emotional state" refers to the type and intensity of emotions an individual experiences in a particular situation, and includes emotions such as anxiety, fear, and relief.

[0761] "Machine learning technology" refers to the field of technology in which computer systems learn patterns and rules from data and make predictions and decisions based on that learning.

[0762] "Information and communication technology" refers to technologies for generating, processing, transmitting, and receiving digital data, and in particular, technologies that enable real-time information sharing via the internet.

[0763] This embodiment of the invention provides a system that effectively assesses natural disaster risks and issues warnings that take into account the user's emotional state. Specifically, the server collects and analyzes information from various data sources. The server uses databases and APIs necessary for acquiring weather data and connects to sensors and monitoring systems for water level data. Geographic data is also acquired using a Geographic Information System (GIS). Based on this data, the server performs calculations to assess the risk.

[0764] The server further analyzes text data from social media using natural language processing tools. Specifically, it uses software such as Python's NLTK and spaCy to extract emotional states from user posts. This ensures that user emotions are reflected in the generation of warning messages. For example, the server identifies a user's post "I'm worried about heavy rain tonight" as an emotion of "anxiety" and uses this to adjust the warning message.

[0765] The generated alarm messages are then materialized through a generation AI model. As an example of a prompt, the server can execute a command to the generation AI model to "generate a user-facing alarm message based on risk and sentiment scores." This process generates emotionally sensitive, specific, and actionable alarms.

[0766] Finally, the server uses information and communication technology to send the generated alarm as a push notification to the user's terminal. In this way, the terminal instantly displays the alarm to the user, supporting quick action. As a result, the system functions as an effective tool to enhance user safety during disasters.

[0767] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0768] Step 1:

[0769] The server periodically collects weather data, river water level data, and geographical data from various sensors and database APIs. This process requires specific observation locations and measurement device identification information as input. After data collection, the server organizes and stores this data by date and location. The output is an integrated time-series dataset.

[0770] Step 2:

[0771] The server numerically assesses flood risk based on collected geographic information. The input is time-series weather and water level data obtained in the previous step. The server uses Python's NumPy and Pandas to perform statistical analysis and model-based predictions. The output of this process is a calculated risk score and the generation of a risk map for each region.

[0772] Step 3:

[0773] The server collects data from social media posts and analyzes the users' emotional states. It takes text data and, if possible, contextual information from each post as input. This text data is then subjected to emotional classification using natural language processing tools such as Python's NLTK or spaCy. The output is the user's emotional tone (e.g., positive, negative), which is quantified as an emotional score.

[0774] Step 4:

[0775] The server uses a generative AI model to generate alert messages based on risk and sentiment scores. The prompt is "Create a specific and emotionally sensitive alert message for the user." The input consists of previously evaluated risk and sentiment scores. The generated text is provided as an alert message with a tone and content appropriate for the user. The output is a customized message.

[0776] Step 5:

[0777] The server sends a push notification to the user's device to send the generated alarm message. The input consists of contact information and the generated alarm message. The message is sent to the device in real time using a communication protocol, and the device immediately displays this message to the user. As output, the individual message received by the user is displayed on the device screen.

[0778] Step 6:

[0779] The user reviews the received alarm and provides feedback as needed. The input is the content of the alarm message itself. The user provides feedback on whether the provided information is accurate and useful. The output is returned to the server as user feedback data and stored as a reference for future alarm generation.

[0780] (Application Example 2)

[0781] 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".

[0782] In recent years, with the increasing frequency of floods due to climate change, there is a growing need to effectively disseminate information and promote swift evacuation. However, conventional warning systems send uniform warning messages without considering the emotional state of users, which can cause anxiety and fail to encourage appropriate action. Therefore, there is a need for information provision that understands and appropriately considers the emotions of users.

[0783] 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.

[0784] In this invention, the server includes means for periodically collecting weather information, means for receiving river water level information, means for acquiring topographic information, means for analyzing data from social media and recognizing emotions, means for detecting and removing fake images, means for comprehensively analyzing this information and evaluating the threat of flooding, means for issuing emotion-based adjusted warnings, and means for sending warnings via push notifications to user devices through a specific application. This makes it possible to provide flood information in a way that takes into account the user's emotions and provides a sense of security, thereby encouraging appropriate and prompt evacuation actions.

[0785] "Weather information" refers to data on environmental conditions such as weather, temperature, precipitation, and wind speed. By accumulating this data, it provides basic information for understanding the weather conditions in a specific region.

[0786] "River water level information" refers to data measuring water levels at specific points along rivers, and is an important indicator for evaluating the likelihood of flooding.

[0787] "Topographic information" refers to data that shows the relief and topographical features of the land, and is used to assess the level of danger in a region and the risk of flooding.

[0788] "Methods for analyzing data from social media and recognizing emotions" refers to technologies that analyze the content of posts on online platforms and recognize the emotions and psychological states expressed by users.

[0789] "Methods for detecting and removing fake images" refer to technologies for identifying and excluding manipulated images and false information from analysis, and are crucial for reliable data analysis.

[0790] "Means for assessing flood threats" refers to methods for comprehensively evaluating flood risk by integrating meteorological information, river water level information, and topographic information.

[0791] "Means for issuing emotion-based, adjustable alarms" refers to technology that generates and delivers alarm messages whose content is adjusted according to the user's emotional state.

[0792] "A means of sending an alarm via push notification to a user's device through a specific application" refers to a technology that uses dedicated software to instantly send an alarm message to the user's electronic device.

[0793] The system of the present invention aims to assess the flood risk in a user's area based on their emotional state and issue appropriate warnings. This system integrates information from multiple data sources and includes the following components to achieve information delivery that takes the user's emotions into consideration.

[0794] The server first periodically collects and integrates weather information, river water level information, and topographic information. The specific hardware used for this is a data server with high processing power, and the software implements a dedicated application for data collection and analysis.

[0795] Next, the server analyzes posts from social media. This analysis uses natural language processing tools and sentiment analysis engines (e.g., NLP libraries) to identify the user's psychological state and quantify their emotions. This allows the server to discover emotions such as "anxiety" and "fear" that users are expressing, and uses this data to adjust the content of alerts.

[0796] Meanwhile, the terminal receives coordinated alerts transmitted from the server and immediately presents them to the user. This allows the user to understand the current flood risk and quickly take appropriate action, such as evacuation. The terminal is a portable electronic device such as a smartphone or tablet, and provides a user interface through an application.

[0797] As a concrete example, it is possible to perform sentiment analysis using a generative AI model, for instance, by "evaluating users' emotions based on content posted on the media and sending special warning messages to areas where there are posts indicating strong fear."

[0798] Examples of prompts include the following:

[0799] "Analyze the sentiment of social media posts coming from a particular geographic location. If the predominant sentiment is negative, especially fear or anxiety, suggest a comforting message that could be sent to users in that area."

[0800] Through this process, the system can effectively provide users with emotionally sensitive flood information, supporting safe and swift decision-making.

[0801] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0802] Step 1:

[0803] The server periodically collects weather information, river water level information, and topographic information from external databases and APIs. This information is received as configuration data, and the server updates the environmental information for each region. Input is data obtained from external information sources, and output is the latest environmental information stored in the server's database. The process includes automatically retrieving data using API requests.

[0804] Step 2:

[0805] The server collects posting data from a specific region via social media APIs and analyzes users' emotional states using a sentiment analysis engine. The input is posting data obtained from a specific geographical area, and the output is the emotional tendencies of users identified through the analysis (e.g., "anxiety" or "fear"). Data processing is performed by scoring the sentiment of the text using natural language processing techniques.

[0806] Step 3:

[0807] The server comprehensively assesses the flood threat based on all collected data. This assessment utilizes a method that integrates weather, river level, topography, and sentiment data to calculate a risk score. The input is a set of various data, and the output is a numerical representation of the flood risk as a risk score. Data calculations here include weighting and time series analysis.

[0808] Step 4:

[0809] The server generates alarm messages based on risk assessments and adjusts them to be emotionally appropriate. This process incorporates message templates that provide reassurance to users, especially those experiencing significant anxiety, using prompts from a generation AI model. Inputs are risk scores and sentiment analysis results, while output is the text of the alarm message. This process involves template selection and automatic text generation.

[0810] Step 5:

[0811] The terminal presents the user with a pre-configured alarm message sent from the server as a push notification. The input is alarm data from the server, and the output is the alarm message displayed on the terminal's user interface. The terminal uses the OS's notification function to ensure user attention. Based on this, the user can immediately decide on actions such as evacuation.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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."

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] The following is further disclosed regarding the embodiments described above.

[0834] (Claim 1)

[0835] Means for regularly collecting weather information,

[0836] A means of receiving river water level information,

[0837] Means for acquiring topographic information,

[0838] A method for analyzing and evaluating the reliability of information posted on social media,

[0839] A means of detecting and excluding fake images,

[0840] A means to comprehensively analyze this information and assess flood risk,

[0841] A system that includes means for issuing warnings based on risk assessment.

[0842] (Claim 2)

[0843] The system according to claim 1, comprising means for using a historical case dataset and a machine learning model for flood risk assessment.

[0844] (Claim 3)

[0845] The system according to claim 1, further comprising means for sending an alarm to a user's terminal via a dedicated app as a push notification.

[0846] "Example 1"

[0847] (Claim 1)

[0848] A means of periodically acquiring weather information,

[0849] A means of receiving river water level data,

[0850] Means for acquiring terrain data,

[0851] A means of analyzing information from social media and evaluating its reliability,

[0852] A means for detecting and removing false images,

[0853] A means to comprehensively analyze this information and assess the risk of flooding,

[0854] A means of issuing warnings based on risk assessment,

[0855] A means to automate the issuance of alarms,

[0856] Means for transmitting emergency alerts to electronic devices,

[0857] A system that includes means for users to check evacuation information.

[0858] (Claim 2)

[0859] The system according to claim 1, comprising means for using past case data and a learning algorithm for assessing the risk of flooding.

[0860] (Claim 3)

[0861] The system according to claim 1, further comprising means for transmitting an alarm to a user's device through a specific application.

[0862] "Application Example 1"

[0863] (Claim 1)

[0864] Means for regularly collecting weather information,

[0865] A means of receiving river water level information,

[0866] Means for acquiring topographic information,

[0867] A method for analyzing and evaluating the reliability of information posted on social media,

[0868] A means of detecting and excluding fake images,

[0869] A means to comprehensively analyze this information and assess flood risk,

[0870] A means of issuing warnings based on risk assessment,

[0871] A means of notifying the user device of the evacuation route,

[0872] A system that includes this.

[0873] (Claim 2)

[0874] The system according to claim 1, comprising means for using a historical case dataset and a generated predictive model for flood risk assessment.

[0875] (Claim 3)

[0876] The system according to claim 1, further comprising means for sending an alarm via a dedicated app to the user's display device as a push notification and guiding the user on an evacuation route.

[0877] "Example 2 of combining an emotion engine"

[0878] (Claim 1)

[0879] Means for regularly collecting weather data,

[0880] A means of acquiring water level data,

[0881] Means of acquiring geographic data,

[0882] A method for analyzing and evaluating the reliability of data posted from social media,

[0883] Means for detecting and removing fraudulent data,

[0884] A means of analyzing integrated data to assess natural disaster risk,

[0885] A means of analyzing emotional states and adjusting alarm content,

[0886] A system including means for generating alarms based on evaluation results.

[0887] (Claim 2)

[0888] The system according to claim 1, comprising means for analyzing past event datasets using machine learning techniques.

[0889] (Claim 3)

[0890] The system according to claim 1, comprising means for transmitting a notification to a user terminal using information and communication technology.

[0891] "Application example 2 when combining with an emotional engine"

[0892] (Claim 1)

[0893] A means of regularly collecting weather information,

[0894] A means of receiving river water level information,

[0895] Means for acquiring topographic information,

[0896] A means of analyzing data from social media and recognizing emotions,

[0897] A means for detecting and removing fake images,

[0898] A means to comprehensively analyze this information and assess the threat of flooding,

[0899] A system that includes means for issuing emotion-based, adjustable alarms.

[0900] (Claim 2)

[0901] The system according to claim 1, comprising means for using a dataset of past cases and a machine learning algorithm for flood threat assessment.

[0902] (Claim 3)

[0903] The system according to claim 1, further comprising means for sending an alarm via push notification to a user's device through a specific application. [Explanation of Symbols]

[0904] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for regularly collecting weather information, A means of receiving river water level information, Means for acquiring topographic information, A method for analyzing and evaluating the reliability of information posted on social media, A means of detecting and excluding fake images, A means to comprehensively analyze this information and assess flood risk, A system that includes means for issuing warnings based on risk assessment.

2. The system according to claim 1, comprising means for using a dataset of past cases and a machine learning model for flood risk assessment.

3. The system according to claim 1, further comprising means for sending an alarm to a user's terminal via a dedicated app as a push notification.

Images