System

Abstract

A system is provided.SOLUTION: A system including a means for collecting weather data, a means for collecting topographical data, a means for inputting the collected weather data and topographical data to generative artificial intelligence and analyzing a risk of inundation, a means for a resident to transmit a photograph or information of a dangerous place using a smartphone application, a means for analyzing the transmitted information and specifying position information or a degree of danger, a means for notifying other residents of the analyzed danger information in real time, and a means for providing information of a safe evacuation route or an evacuation place to residents.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Inland flooding can occur unexpectedly, causing serious damage to people's lives, such as flooding roads and flooding under the floors of homes. However, the problem is that there are insufficient concrete measures in place to predict the risk of inland flooding in advance and to take prompt measures. In particular, as the risk of inland flooding increases due to the effects of climate change, new measures are needed to improve the safety and quality of life of residents. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. It includes a means for collecting meteorological data, a means for collecting topographical data, and a means for inputting the collected meteorological and topographical data into a generating AI and analyzing the risk of inland flooding. It also includes a means for residents to send photos and information about dangerous areas using a smartphone app, a means for analyzing the sent information and identifying location information and risk level, and a means for notifying other residents of the analyzed risk information in real time. It also includes a means for providing residents with information about safe evacuation routes and evacuation locations. In this way, by combining the means for collecting and analyzing data with the means for real-time information sharing and evacuation support, early countermeasures and information sharing can be realized, minimizing damage caused by inland flooding.

[0006] "Weather data" refers to information relating to weather, such as temperature, rainfall, wind speed, and humidity.

[0007] "Topographic data" refers to geographical information such as ground elevation, topographical shape, and the location of drainage facilities.

[0008] "Generative AI (generative artificial intelligence)" refers to artificial intelligence that analyzes collected data and generates information.

[0009] "Inland flooding" refers to the phenomenon in which water overflows a city due to heavy rain or other causes, exceeding its drainage capacity and causing flooding of roads and homes.

[0010] "Dangerous areas" refer to areas prone to damage caused by inland flooding.

[0011] "Smartphone app" refers to a software application that runs on a smartphone.

[0012] "Transmission means" refers to the function for transmitting information about dangerous areas to a server using a smartphone app.

[0013] "Analysis means" refers to a function for evaluating and identifying location information and risk level based on received information.

[0014] "Notification means" refers to a function for distributing analyzed risk information to other residents in real time.

[0015] "Evacuation support means" refers to functions for providing residents with information on safe evacuation routes and evacuation shelters. [Brief explanation of the drawings]

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

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

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

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

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

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

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

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

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

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

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0037] The present invention relates to a system that collects meteorological and topographical data, uses that data to generate AI that analyzes the risk of inland flooding, and allows residents to share information about dangerous areas via a smartphone app.

[0038] Data collection and analysis

[0039] The server periodically collects weather data (e.g., rainfall, wind speed, humidity) from the weather station.

[0040] The server collects topographical data (e.g., ground elevation, location of drainage facilities) from the municipal database.

[0041] The weather and topographical data collected by the server is input into the artificial intelligence (AI), which analyzes this data and outputs the risk level of inland flooding as a number or category.

[0042] Collection and transmission of risk information

[0043] If a user discovers flooding or abnormal water flow at home or in the neighborhood, they can launch the app on their smartphone.

[0044] The user takes a photo of the problem area using the app, enters a comment (e.g., depth of flooding, date and time of occurrence), and presses the send button.

[0045] The device acquires the user's current location information (GPS data) and sends it to the server along with the photo and comment.

[0046] Information analysis and real-time notifications

[0047] The server analyzes the received photos, comments, and location information, using image recognition technology to determine the depth and extent of flooding in the photos.

[0048] The server then uses the analysis results to determine the urgency of the danger information and organizes it. Criteria for urgency include the depth of flooding, pedestrian traffic, and residential density.

[0049] The server will prioritize and notify other residents of information of high urgency in real time.

[0050] Providing safety measures

[0051] The device displays the received notification to the user, providing detailed information such as warning messages and maps of dangerous areas.

[0052] Users can check the notification and consider evacuating to a safe location.

[0053] The device provides the user with information on safe evacuation routes and the nearest evacuation shelters.

[0054] Specific examples

[0055] For example, when a heavy rain warning is issued by the Meteorological Agency, the server quickly retrieves the data and analyzes it with the generation AI. The generation AI predicts that there is an increased risk of inland flooding in specific low-lying areas of the city. At the same time, a user sends a photo of a flooded road in that area to the server via the app. The server analyzes the received information, determines the depth and extent of the flooding, and sends a real-time notification to other residents in the area. Upon receiving the notification, the user quickly begins evacuation and reaches a safe destination by following the evacuation route instructions provided by the app.

[0056] This invention makes it possible to predict damage caused by inland flooding early and take prompt measures, thereby ensuring the safety of residents. This system functions as a powerful countermeasure against the risk of inland flooding in urban areas.

[0057] The processing flow will be explained below.

[0058] Step 1:

[0059] The server collects weather data (rainfall, wind speed, humidity, etc.) from the meteorological station at regular intervals.

[0060] Step 2:

[0061] The server collects topographical data (ground elevation, location of drainage facilities, etc.) from the local government database.

[0062] Step 3:

[0063] The weather and topographical data collected by the server is input into the generative artificial intelligence (generative AI).

[0064] Step 4:

[0065] The generative AI analyzes the input data and predicts the risk of inland flooding, outputting the risk level as a number or category.

[0066] Step 5:

[0067] If a user discovers flooding or abnormal water flow at home or in the neighborhood, they can launch the app on their smartphone.

[0068] Step 6:

[0069] The user takes a photo of the problem area using the app and enters comments (e.g., depth of flooding, date and time of occurrence).

[0070] Step 7:

[0071] The device acquires the user's current location information (GPS data) and sends it to the server along with the photo and comment.

[0072] Step 8:

[0073] The server analyzes the photos, comments, and location information received, and uses image recognition technology to determine the depth and extent of flooding in the photos.

[0074] Step 9:

[0075] The server determines the urgency of the danger information based on the analysis results, including the depth of flooding, the number of people moving about, and the density of residential areas.

[0076] Step 10:

[0077] The server will prioritize and notify other residents of information of high urgency in real time.

[0078] Step 11:

[0079] The device displays the received notification to the user, providing detailed information such as warning messages and maps of dangerous areas.

[0080] Step 12:

[0081] The user checks the notification and considers evacuating to a safe location.

[0082] Step 13:

[0083] The device provides the user with information on safe evacuation routes and the nearest evacuation shelters.

[0084] Step 14:

[0085] The server will continue to periodically collect new weather data and information from residents, and use generative AI to update risk predictions until the situation improves.

[0086] Example 1

[0087] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0088] Conventional inland flooding prevention systems have had difficulty quickly and accurately predicting flood risk and notifying residents of appropriate information in real time. This has prevented residents from evacuating safely and has prevented damage from being minimized. There has also been a lack of easy ways for residents to report risk information such as flooding. The purpose of this invention is to solve these problems and provide a more efficient and reliable inland flooding prediction and risk management system.

[0089] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0090] In this invention, the server includes means for collecting meteorological data, means for collecting topographical data, means for inputting the collected meteorological data and topographical data into a generating AI and analyzing the risk of inland flooding, means for residents to send photos and information of dangerous areas using mobile communication terminals, means for analyzing the sent information and identifying location information and risk level, means for notifying other residents of the analyzed risk information in real time, and means for providing residents with information on safe evacuation routes and evacuation sites. This enables fast and accurate prediction of inland flooding risks, sharing risk information among residents, and real-time evacuation instructions.

[0091] "Weather data" refers to numerical values ​​and information related to meteorological phenomena, such as rainfall, wind speed, and humidity.

[0092] "Topographic data" refers to numerical values ​​and information about the terrain, such as the elevation of the ground and the location of drainage facilities.

[0093] "Generative artificial intelligence" refers to artificial intelligence technology that analyzes collected data and outputs the risk level of inland flooding as a number or category.

[0094] "Inland flooding" refers to the phenomenon of undrained flooding that occurs in urban and residential areas due to precipitation exceeding drainage capacity.

[0095] "Residents" refers to ordinary people who use this system to share risk information and take evacuation action in the event of a disaster.

[0096] "Mobile communication terminal" refers to a portable communication device such as a smartphone or tablet.

[0097] "Analysis" refers to the act of evaluating and classifying collected data using artificial intelligence and image recognition technology.

[0098] "Danger information" refers to information with a level of urgency related to inland flooding, such as flooding or abnormal water flow.

[0099] "Real-time notification" refers to the act of immediately informing other residents of analyzed danger information.

[0100] An "evacuation route" refers to the optimal route for residents to move to safety in the event of inland flooding.

[0101] An "evacuation site" refers to a place where residents can temporarily ensure safety in the event of inland flooding.

[0102] This invention relates to a system that utilizes meteorological and topographical data, uses generative artificial intelligence (generative AI model) to analyze the risk of inland flooding, and provides appropriate information to residents in real time. This system functions in cooperation with three parties: a server, a terminal, and a user.

[0103] Data collection and analysis

[0104] The server retrieves weather data at a scheduled time. Specifically, it accesses the meteorological agency's API and collects data such as rainfall, wind speed, and humidity. Next, the server retrieves topographical data from the local government's topographical database. This data includes the ground elevation and the location of drainage facilities. The collected weather and topographical data is stored in the database.

[0105] Next, the server inputs the meteorological and topographical data stored in the database into the generative AI model. The generative AI model analyzes this data and outputs the risk level of inland flooding as a number or category (e.g., high risk, medium risk, low risk). The results are managed by the server.

[0106] Collection and transmission of risk information

[0107] When a user discovers flooding or abnormal water flow at home or in their neighborhood, they launch the smartphone app. Using the app's camera function, they take a photo of the problem area and enter a comment. This information includes the depth of the flooding and the date and time of the occurrence. The user's device obtains their current location information (GPS data) and sends an information packet containing the photo and comment to the server.

[0108] Information analysis and real-time notifications

[0109] The server analyzes the photos, comments, and location information it receives. Image recognition technology is used to determine the depth and extent of the flooding in the photos. Based on the analysis results, the server determines the urgency of the danger information and organizes the information. The urgency is determined by factors such as the depth of the flooding, the number of people passing by, and the density of housing. Information with a high level of urgency is prioritized and organized, and the server notifies other residents' devices in real time.

[0110] Providing safety measures

[0111] The device displays the received notification to the user. Detailed information such as warning messages and maps of dangerous areas are also displayed at the same time. The user can check the notification and consider evacuating to a safe location if necessary. The device provides the user with information on safe evacuation routes and the nearest evacuation shelters.

[0112] Specific examples

[0113] For example, when a heavy rainfall warning is issued, the server quickly retrieves the data from the meteorological bureau and analyzes it using a generative AI model. The generative AI model predicts an increased risk of inland flooding in specific low-lying areas of the city. At the same time, a user sends a photo of a flooded road in that area to the server via the app. The server analyzes the received information, determines the depth and extent of the flooding, and sends a real-time notification to other residents in the area. Upon receiving the notification, the user quickly begins evacuation and reaches a safe destination by following the evacuation route instructions provided by the app.

[0114] This system will enable early prediction of damage caused by inland flooding, allowing prompt countermeasures to be taken, and ensuring the safety of residents. It will therefore function as a powerful countermeasure against the risk of inland flooding in urban areas.

[0115] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0116] Program processing steps

[0117] Step 1: Collect weather data

[0118] The server accesses the weather station's API at specified times to obtain weather data such as rainfall, wind speed, and humidity.

[0119] Specific operation: Sends an API request, analyzes the obtained data, and saves it in a database.

[0120] Input: Weather Bureau API endpoint and credentials.

[0121] Output: Latest weather data stored in the database.

[0122] Step 2: Collect terrain data

[0123] The server accesses the local government's terrain database and obtains terrain data such as ground elevation and the location of drainage facilities.

[0124] Specific behavior: Query the required data from the local government database and store the resulting data in a local database.

[0125] Input: Access information and queries to municipal databases.

[0126] Output: Terrain data stored in a database.

[0127] Step 3: Generative AI risk analysis

[0128] The server inputs stored weather and terrain data into a generative AI model.

[0129] Specific operation: Data is input into the generative AI model and analysis begins. After analysis, the risk level of inland flooding is output as a number or category.

[0130] Input: Latest weather and terrain data.

[0131] Output: Risk level of inland flooding (numeric or categorical).

[0132] Step 4: User provides risk information

[0133] If a user discovers flooding or abnormal water flow at home or in the neighborhood, they can launch the app on their smartphone.

[0134] Specific actions: The user takes a photo using the app's camera function, enters a comment, and presses the send button.

[0135] Input: Flood depth, date and time of occurrence, and GPS data.

[0136] Output: Flood information packet sent to the server.

[0137] Step 5: Analyze and locate hazard information

[0138] The server analyzes the photos, comments, and location information received, and uses image recognition technology to determine the depth and extent of flooding in the photos.

[0139] Specific operation: The received data is input into an analysis algorithm to determine the level of danger and location information.

[0140] Input: photos, comments, location.

[0141] Output: Analyzed risk level and specific location information.

[0142] Step 6: Determine the level of urgency and organize the information

[0143] Based on the analysis results, the server determines the urgency of the dangerous information and organizes the information.

[0144] Specific operation: Calculates and prioritizes the level of urgency based on the depth of flooding, the number of people passing by, and the density of housing.

[0145] Input: Parsed risk level and location information.

[0146] Output: List of danger information with urgency level.

[0147] Step 7: Real-time notifications

[0148] The server notifies other residents' devices of highly urgent information in real time.

[0149] Specific operation: Selects information with high urgency and sends warnings to residents' smartphones via the notification system.

[0150] Input: A list of hazard information with urgency ratings.

[0151] Output: Notification message sent to the resident.

[0152] Step 8: Display warnings and provide evacuation information

[0153] The device displays the received notification to the user, providing warning messages and maps of dangerous areas.

[0154] Specific actions: Displaying pop-up notifications, drawing maps, and providing information on safe evacuation routes and nearest evacuation shelters.

[0155] Input: The notification message sent by the server.

[0156] Output: Warning messages and evacuation information displayed to the user.

[0157] keyword

[0158] Generative AI model, prompt sentence

[0159] (Application example 1)

[0160] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0161] Conventional inland flood risk management systems often lack the functionality to provide residents with the latest information in real time and encourage prompt evacuation. Furthermore, they lacked a mechanism for efficiently analyzing risk information sent by users and determining its urgency, making it difficult to provide residents with accurate information when needed. Furthermore, there were technical challenges in identifying the specific depth and extent of flooding using photos and comments sent by users.

[0162] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0163] In this invention, the server includes means for collecting meteorological data, means for collecting topographical data, means for inputting the collected meteorological data and topographical data into a generative AI model and analyzing the risk of inland flooding, means for users to send photos and information of dangerous areas using a mobile device, means for analyzing the sent information and identifying location information and risk level, means for notifying other residents of the analyzed risk information in real time, means for providing residents with information on safe evacuation routes and evacuation sites, means for analyzing photos sent by users using image recognition technology and determining the depth and extent of flooding, and means for determining the urgency of risk information based on the collected analysis information and notifying information with a higher urgency level first. This makes it possible to analyze and notify risk information of inland flooding in real time, and encourage residents to take quick and accurate evacuation action.

[0164] "Weather data" is a general term for information about weather, such as rainfall, wind speed, and humidity, obtained from meteorological stations.

[0165] "Topographical data" is a general term for information about topography obtained from a local government database, such as the elevation of the ground, the location of drainage facilities, etc.

[0166] "Generative artificial intelligence (generative AI)" is an artificial intelligence technology that analyzes the risk of inland flooding based on collected data and outputs the results.

[0167] "Mobile terminal" is a general term for portable electronic devices that users use on a daily basis, such as smartphones and smart glasses.

[0168] "Image recognition technology" refers to technology that analyzes photos sent by users and recognizes specific features and patterns.

[0169] "Flood depth" refers to the depth of flooded water.

[0170] "Urgency" is a standard for evaluating the seriousness and immediacy of dangerous information.

[0171] "Real-time notification" refers to the function of instantly sending analyzed information to other users.

[0172] An "evacuation route" is the optimal route for residents to evacuate safely.

[0173] An "evacuation site" is a place designated for residents to evacuate to in the event of a disaster.

[0174] "Location information" refers to a geographical location identified using GPS or other means.

[0175] The present invention relates to a system that collects meteorological and topographical data, uses that data to generate an AI model that analyzes the risk of inland flooding, and allows residents to share information about dangerous areas via mobile devices. This system is implemented as follows:

[0176] First, the server periodically collects weather data (e.g., rainfall, wind speed, humidity) from the meteorological station, and terrain data (e.g., ground elevation, location of drainage facilities) from the local government database. To retrieve the weather and terrain data, the Python requests library can be used.

[0177] The server then inputs the collected weather and topographical data into a generative AI model (e.g., a model created with TensorFlow). The generative AI model uses this data to analyze the risk level of inland flooding numerically or categorically, and outputs the results.

[0178] When a user discovers flooding or an abnormal water flow, they launch the app on their mobile device. They use the app to take a photo of the dangerous area and enter comments (e.g., the depth of the flooding, the date and time of the occurrence). The app also obtains the user's current location information (GPS data) and sends it to the server along with the photo and comment.

[0179] The server analyzes the received photos, comments, and location information. This analysis uses image recognition technology (e.g., image analysis using OpenCV and TensorFlow) to determine the depth and extent of flooding in the photos. Based on the analyzed information, the urgency of the danger information is determined. Criteria for the urgency include the depth of flooding, pedestrian traffic, and residential density.

[0180] The server uses the analysis results to notify other residents in real time, prioritizing information of high urgency. This notification is done using a web framework such as Flask, which organizes the information and distributes it to residents.

[0181] The device displays the received notification to the user and provides detailed information such as warning messages and maps of dangerous areas. The device also provides the user with information on safe evacuation routes and the nearest evacuation shelters, allowing the user to quickly begin evacuation and evacuate to a safe location.

[0182] For example, when heavy rain occurs, the following prompt is entered:

[0183] User: This is XX Street in Chuo Ward, and the road is flooded to over 1 meter.

[0184] Along with this prompt, the user sends a flooded photo they have taken, which is then analyzed by the server and immediately notified by other residents, encouraging them to take prompt evacuation action.

[0185] This system acts as a powerful countermeasure against the risk of inland flooding in urban areas and provides an efficient way to ensure the safety of residents.

[0186] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0187] Step 1:

[0188] The server periodically collects weather data (rainfall, wind speed, humidity) from the meteorological station. Specifically, it retrieves data from the API using the Python requests library. In this case, it sends an API request as input and retrieves weather data in JSON format as output.

[0189] Step 2:

[0190] The server collects terrain data (ground elevation, location of drainage facilities) from the local government database. It also retrieves data from the API using the requests library. In this case, it sends an API request as input and gets terrain data in JSON format as output.

[0191] Step 3:

[0192] The server inputs the collected weather and topographical data into a generative artificial intelligence (generative AI model). Specifically, it uses a TensorFlow model to analyze the risk of inland flooding. The weather and topographical data are preprocessed as input and then input into the TensorFlow model. The output is the risk level of inland flooding, expressed as a number or category.

[0193] Step 4:

[0194] When a user discovers flooding or an abnormal water flow, they launch the app on their mobile device. Using the app, the user takes a photo of the dangerous area and enters comments (depth of flooding, date and time of occurrence). The app obtains the user's current location information (GPS data) and sends the photo, comment, and location information to the server.

[0195] Step 5:

[0196] The server analyzes the received photos, comments, and location information. This is done using image recognition technology (e.g., image analysis using OpenCV and TensorFlow). The server analyzes the photos sent as input and determines the depth and extent of the flooding. The analysis results are then stored in a database as output.

[0197] Step 6:

[0198] The server determines the urgency of the danger information based on the analysis results. Specifically, it evaluates the urgency using indicators such as flood depth, pedestrian traffic, and residential density. In this case, it uses the analysis results as input to quantify the urgency. As output, it generates data that prioritizes notifications of information with a high urgency.

[0199] Step 7:

[0200] The server notifies other residents in real time, prioritizing information of high urgency. For this purpose, it uses web frameworks such as Flask to deliver notifications. At this time, it uses information of high urgency as input and generates notification messages as output.

[0201] Step 8:

[0202] The device displays the received notification to the user, providing the user with detailed information such as warning messages and maps of dangerous areas. At this time, the device receives the notification message as input and displays it on the user interface, allowing the user to immediately understand the situation.

[0203] Step 9:

[0204] The device provides the user with information on safe evacuation routes and the nearest evacuation shelters. Specifically, it uses an algorithm to calculate the evacuation route and presents the optimal route. In this case, the current location and evacuation shelter information are used as input, and the optimal evacuation route is presented as output.

[0205] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0206] This invention combines an emotion engine with a system that predicts the risk of inland flooding through the collection and analysis of meteorological and topographical data, and allows residents to share information about dangerous areas via a smartphone app. This emotion engine recognizes the user's emotions and takes appropriate action.

[0207] Data collection and analysis

[0208] The server periodically collects weather data (rainfall, wind speed, humidity, etc.) from the weather station.

[0209] The server collects topographical data (ground elevation, location of drainage facilities, etc.) from the local government database.

[0210] The weather and topographical data collected by the server is input into the artificial intelligence (AI), which analyzes this data and outputs the risk level of inland flooding as a number or category.

[0211] Collection and transmission of user information

[0212] If a user discovers flooding or abnormal water flow at home or in the neighborhood, they can launch the app on their smartphone.

[0213] Users take photos of dangerous areas using the app and enter comments (e.g., flood depth, date and time of occurrence). The emotion engine then analyzes the user's voice and text comments to detect their emotional state.

[0214] The device acquires the user's current location information (GPS data) and sends emotional state information along with photos and comments to the server.

[0215] Information analysis and real-time notifications

[0216] The server analyzes the photos, comments, and location information received, and uses image recognition technology to determine the depth and extent of flooding in the photos.

[0217] The server adjusts the necessary measures and notification content based on the user's emotional state analyzed by the emotion engine. For example, if the user is showing strong anxiety, the notification content will be detailed and reassuring.

[0218] The server determines the urgency of the danger information based on the analysis results, including the depth of flooding, the number of people moving about, and the density of residential areas.

[0219] The server will prioritize and notify other residents of information of high urgency in real time.

[0220] Providing safety measures

[0221] The device displays the received notification to the user, providing detailed information such as warning messages and maps of dangerous areas. The emotion engine displays messages that take the user's emotions into consideration.

[0222] Users can check the notification and consider evacuating to a safe location.

[0223] The device provides users with information on safe evacuation routes and the nearest evacuation shelters, and the emotion engine displays appropriate messages containing encouragement and instructions to reduce the user's anxiety during evacuation.

[0224] Specific examples

[0225] For example, when a heavy rain warning is issued by the Meteorological Agency, the server quickly retrieves the data and analyzes it using the generation AI. The generation AI predicts that there is an increased risk of inland flooding in certain low-lying areas of the city. At the same time, a user sends a photo of a flooded road in that area to the server via the app. The device inputs the user's voice and comments into the emotion engine and determines that the user is feeling anxious. The server analyzes the received information, determines the depth and extent of the flooding, and sends a real-time notification to other residents in the area. Upon receiving the notification, the device displays a reassuring message from the emotion engine along with evacuation route instructions, thereby reducing the user's anxiety.

[0226] This invention not only makes it possible to predict damage caused by inland flooding early and implement prompt countermeasures, but also makes it possible to respond in a way that takes into consideration the emotions of users, thereby promoting safer and more secure evacuation behavior and contributing to ensuring the safety of residents.

[0227] The processing flow will be explained below.

[0228] Step 1:

[0229] The server collects weather data (rainfall, wind speed, humidity, etc.) from the meteorological station at regular intervals.

[0230] Step 2:

[0231] The server collects topographical data (ground elevation, location of drainage facilities, etc.) from the local government database.

[0232] Step 3:

[0233] The weather and topographical data collected by the server is input into the generative artificial intelligence (generative AI).

[0234] Step 4:

[0235] The generative AI analyzes the input data and predicts the risk of inland flooding, outputting the risk level as a number or category.

[0236] Step 5:

[0237] If a user discovers flooding or abnormal water flow at home or in the neighborhood, they can launch the app on their smartphone.

[0238] Step 6:

[0239] The user takes a photo of the problem area using the app and enters comments (e.g., the depth of the flooding, the date and time of the occurrence). The emotion engine also analyzes the user's voice and text comments to detect their emotional state.

[0240] Step 7:

[0241] The device acquires the user's current location information (GPS data) and sends photos, comments, and emotional state information to the server.

[0242] Step 8:

[0243] The server analyzes the photos, comments, and location information received, and uses image recognition technology to determine the depth and extent of the flooding in the photos.

[0244] Step 9:

[0245] The server adjusts the notification content based on the user's emotional state analyzed by the emotion engine. For example, if a user is highly anxious, it adds a detailed explanation or a reassuring message.

[0246] Step 10:

[0247] The server determines the urgency of the danger information based on the analysis results, using criteria such as the depth of flooding, pedestrian traffic, and residential density.

[0248] Step 11:

[0249] The server notifies other residents of information with high urgency on a priority basis in real time.

[0250] Step 12:

[0251] The device displays the received notification to the user, and the emotion engine displays messages that take into account the user's emotional state.

[0252] Step 13:

[0253] The user checks the notification and considers evacuating to a safe location.

[0254] Step 14:

[0255] The device provides users with information on safe evacuation routes and the nearest evacuation shelters, and the emotion engine displays appropriate messages containing encouragement and instructions to reduce anxiety during evacuation.

[0256] Step 15:

[0257] The server will continue to periodically collect new weather data and information from residents, and use generative AI to update risk predictions until the situation improves.

[0258] Example 2

[0259] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0260] Damage caused by inland flooding has a significant impact on the safety of residents and the infrastructure of daily life, especially in urban areas. Conventional systems are inadequate in early prediction of flood risk and prompt notification to residents, making it difficult for residents to take appropriate evacuation actions. In addition, responses do not take into consideration the emotions of residents, making it an issue to reduce psychological stress.

[0261] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0262] In this invention, the server includes means for collecting meteorological data, means for collecting topographical data, means for inputting the collected meteorological data and topographical data into a generating AI and analyzing the risk of inland flooding, means for residents to send photos and information of dangerous areas using a mobile communication terminal, means for analyzing the sent information and identifying location information and risk level, means for notifying other residents of the analyzed risk information in real time, means for providing residents with information on safe evacuation routes and evacuation sites, and means for performing emotion recognition and taking appropriate action based on the results. This enables early prediction of inland flooding risk, rapid emergency notification, and appropriate action that takes into account the emotions of residents.

[0263] "Weather data" refers to weather-related information such as rainfall, wind speed, and humidity collected from meteorological agencies and related organizations.

[0264] "Topographic data" refers to information about the terrain, such as the elevation of the ground and the location of drainage facilities, collected from local government databases, etc.

[0265] "Generative artificial intelligence" is an AI technology that analyzes and makes predictions based on large amounts of data, and specifically outputs the risk level of inland flooding as a number or category.

[0266] A "mobile communication terminal" is an electronic device with communication functions that can be used while on the move, such as a smartphone or tablet.

[0267] "Emotion recognition" is a technology that analyzes and detects a user's emotional state from their voice, text, etc.

[0268] "Analysis" is the process of identifying the risk and danger of inland flooding based on collected meteorological and topographical data, as well as information sent by users.

[0269] "Real-time notification" means sending collected and analyzed information to residents immediately and sharing the information promptly.

[0270] An "evacuation route" is a recommended route for evacuating from a dangerous area to a safe place.

[0271] An "evacuation site" is a place where residents can temporarily evacuate to ensure their safety in the event of a disaster.

[0272] I understand. Below is the "Mode for carrying out the invention."

[0273] This invention combines emotion recognition with a system that predicts the risk of inland flooding through the collection and analysis of meteorological and topographical data, and allows residents to share information about dangerous areas via mobile communication devices. The system consists of three main components: a server, a device, and a user.

[0274] The server performs the following functions. First, it periodically collects weather data such as rainfall, wind speed, and humidity using the meteorological bureau's API. It also obtains topographical data such as ground elevation and the location of drainage facilities from the local government's database and stores this data in the database. The collected weather and topographical data is input into a generative artificial intelligence (e.g., GPT-4) using a Python script, which outputs the risk level of inland flooding as a number or category. The results of this analysis are further analyzed within the system and notified to residents in real time. Furthermore, an emotion recognition engine is used to adjust the content of notifications based on the user's emotional state, and appropriate responses are taken.

[0275] The device mainly refers to a mobile communication device (such as a smartphone or tablet) and performs the following functions: When a user discovers a flooded area or an abnormal water flow, they can launch the app to take a photo and enter a comment and emotional state (text or voice). The user's location information is obtained using the device's GPS function, and all information is sent to the server. The received notification is displayed on the device as a pop-up message or alert, and a message of reassurance based on emotion recognition and evacuation route instructions are provided.

[0276] Users are responsible for reporting any abnormal water flow or flooding they notice in their daily lives through the app. This reporting involves taking photos and entering comments, and also inputting emotional state information, which is used for analysis by the system's emotion recognition engine. By receiving notifications, users can take prompt and appropriate evacuation action.

[0277] As a concrete example, when a heavy rain warning is issued, the server quickly retrieves the data and analyzes it using generative AI (e.g., GPT-4). The generative AI predicts that there is an increased risk of inland flooding in certain low-lying areas of the city. At the same time, a user sends a photo of flooded roads in that area and a comment to the server via an app. The device inputs the user's voice and comments into an emotion recognition engine and determines that the user is feeling anxious. The server analyzes the received information, determines the depth and extent of the flooding, and sends a real-time notification to other residents in the area. The device that receives the notification displays a reassuring message and evacuation route instructions using the emotion recognition engine, thereby alleviating the user's anxiety. This system not only makes it possible to predict damage caused by inland flooding early and implement prompt countermeasures, but also to respond in a way that takes the user's emotions into consideration.

[0278] Example prompt sentence:

[0279] Input prompt:

[0280] "In response to this heavy rain warning, please tell us the procedures for predicting the risk of inland flooding in low-lying areas of the city and encouraging residents to take appropriate measures."

[0281] Example expected output:

[0282] "When a heavy rain warning is issued, the server obtains meteorological and topographical data and inputs it into the generation AI. The generation AI identifies areas at high risk of inland flooding and analyzes this together with flooding information sent by users via the app. The server determines the level of urgency based on the analysis results and sends notifications to residents in real time. The device displays the notification content and provides a reassuring message using an emotion recognition engine, as well as evacuation route instructions."

[0283] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0284] Step 1: Meteorological data collection

[0285] A server collects weather data.

[0286] Input: Meteorological Agency API endpoint

[0287] Data processing: Obtaining data such as rainfall, wind speed, humidity, etc. from the meteorological bureau and converting it into the required format.

[0288] Output: Transformed weather data (rainfall, wind speed, humidity)

[0289] Specific operation: The server periodically sends requests to the weather bureau's API, receives the weather data returned in response in JSON format, and stores it in a database.

[0290] Step 2: Collect terrain data

[0291] The server collects the terrain data.

[0292] Input: API endpoint of the city's database

[0293] Data processing: Obtain topographical data such as ground elevation and drainage facility locations from the municipality's database and convert it into the required format.

[0294] Output: Converted terrain data (ground elevation, drainage facility locations)

[0295] Specific operation: The server sends a request to the local government database, receives the returned terrain data in JSON format, and stores it in the database.

[0296] Step 3: Data analysis

[0297] The server inputs meteorological and topographical data into the generation AI, which then analyzes the risk level of inland flooding.

[0298] Input: Weather data, terrain data

[0299] Data calculation: Meteorological and topographical data are input into a generating AI (e.g., GPT-4), and the risk level of inland flooding is output as a number or category.

[0300] Output: Risk level of inland flooding (numerical value, category)

[0301] Specific operation: The server runs a Python script, inputs meteorological and topographical data into the generation AI, and the generation AI predicts the risk level of inland flooding based on this data.

[0302] Step 4: Collect user information

[0303] The user reports information about dangerous locations using a mobile communication terminal.

[0304] Input: Photo, Comment, Emotional State (voice or text)

[0305] Data processing: Converts the information acquired by the terminal into a format that can be sent to the server.

[0306] Output: Data ready to send (photos, comments, emotional state)

[0307] Specific operation: The user launches the app, takes a photo of the dangerous area, enters a comment, and then performs voice input.

[0308] Step 5: Send data

[0309] The device acquires the user's current location information (GPS data) and sends photos, comments, and emotional state to the server.

[0310] Input: GPS data, photos, comments, emotional state

[0311] Data calculation: data integration and preparation for transmission

[0312] Output: Integrated data (GPS data, photos, comments, emotional state)

[0313] Specific operation: The device obtains location information using the GPS function and uploads all information to the server.

[0314] Step 6: Information Analysis

[0315] The server analyzes the received data.

[0316] Input: photos, comments, GPS data, emotional state

[0317] Data calculation: Image recognition technology (e.g., OpenCV and TensorFlow) is used to determine the depth and extent of flooding in the photo. An emotion engine is also used to analyze the user's emotional state.

[0318] Output: Analysis results (flood depth, spread, emotional state)

[0319] How it works: The server uses image recognition technology to analyze the received photos and determine the depth and extent of the flooding. At the same time, the emotion engine analyzes the user's emotional state.

[0320] Step 7: Real-time notifications

[0321] The server determines the urgency of the danger information and notifies residents in real time.

[0322] Input: Analysis results (flood depth, spread, emotional state)

[0323] Data calculation: Determining notification priority and generating notification content

[0324] Output: Emergency notification message

[0325] Specific operation: The server determines the urgency based on the analysis results, generates notification content, and sends notifications to other residents with priority.

[0326] Step 8: Provide safety measures

[0327] The terminal displays the received notification to the user.

[0328] Input: Emergency notification message

[0329] Data processing: Converting notification messages into display formats

[0330] Output: A notification message that is displayed to the user.

[0331] Specific operation: The device displays the notification as a pop-up message and provides a reassuring message or evacuation route instructions based on the results of emotion recognition.

[0332] (Application example 2)

[0333] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0334] Existing inland flood forecasting systems can predict risk by analyzing meteorological and topographical data, but they do not provide real-time information that takes into account residents' emotional state. As a result, residents are often unable to take appropriate action when they receive danger information and end up feeling anxious. Furthermore, because individual responses based on emotional state are not provided, it is difficult to encourage safe evacuation behavior.

[0335] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0336] In this invention, the server includes means for collecting weather data, means for collecting topographical data, means for inputting the collected weather data and topographical data into a generating AI and analyzing the risk of inland flooding, means for residents to send photos and information of dangerous areas using a smartphone app, means for analyzing the sent information and identifying location information and risk level, means for notifying other residents of the analyzed risk information in real time, means for providing residents with information on safe evacuation routes and evacuation sites, and means for analyzing the user's emotional state using an emotion engine and responding in a way that takes emotions into consideration. This enables the provision of information to residents quickly and in a way that takes emotions into consideration, thereby promoting safe evacuation behavior.

[0337] "Weather data" refers to numerical values ​​and information about weather, such as rainfall, wind speed, and humidity, collected from meteorological agencies and weather observation institutions.

[0338] "Topographic data" refers to numerical values ​​and information about the terrain, such as ground elevation and the location of drainage facilities, collected from local governments and surveying agencies.

[0339] "Generative AI" refers to an AI model designed to analyze the risk of inland flooding based on meteorological and topographical data.

[0340] "Inland flooding" is a phenomenon in which sewerage and drainage facilities are temporarily unable to handle the flow of water due to heavy rain or flooding, increasing the risk of flooding in urban areas and buildings.

[0341] "Means for analyzing risk" refers to the process of using collected data to evaluate the risk level of inland flooding numerically or in categories.

[0342] "Smartphone app" refers to application software that users can use on their smartphones, including tools for sending photos and information about dangerous areas.

[0343] "Means for analyzing submitted information" refers to the process of analyzing data such as photos, comments, and location information submitted by users to identify the situation and risk of inland flooding.

[0344] "Location information" refers to information that indicates a geographic location based on GPS data or a user's current location.

[0345] "Risk level" is an indicator that shows the possibility of inland flooding and the degree of damage it would cause, including the level of urgency.

[0346] "Means of real-time notification" refers to the process of promptly communicating analyzed danger information to other residents at the same time.

[0347] "Safe evacuation routes" refers to information that indicates routes to travel from areas experiencing inland flooding to evacuation shelters or safe locations.

[0348] An "evacuation site" is a facility or area designated as a temporary evacuation site for residents in the event of a disaster such as inland flooding.

[0349] An "emotion engine" is software or a system that analyzes a user's voice and text comments, detects their emotional state, and responds appropriately.

[0350] This invention combines an emotion engine with a system that predicts the risk of inland flooding through the collection and analysis of meteorological and topographical data, and allows residents to share information about dangerous areas via a smartphone app. This system is implemented in the following form.

[0351] The server periodically collects meteorological data (rainfall, wind speed, humidity, etc.) from meteorological stations and topographical data (ground elevation, location of drainage facilities, etc.) from local government databases. The collected meteorological and topographical data is input into a generative artificial intelligence (generative AI model), which outputs the risk level of inland flooding as a number or category.

[0352] When a user discovers flooding or abnormal water flow at home or in their neighborhood, they launch the app on their smartphone, take a photo of the dangerous area, and enter comments (e.g., depth of flooding, date and time of occurrence). In addition, the emotion engine analyzes the user's voice and text comments to detect their emotional state (e.g., anxiety, fear, panic). This information is sent to the server along with GPS data.

[0353] The server uses image recognition technology to analyze the received photos, comments, and location information to determine the depth and extent of flooding. During this process, an emotion engine analyzes the user's emotional state and adjusts the necessary measures and notification content based on that. For example, if the user expresses strong anxiety, the server will prepare a detailed, reassuring notification.

[0354] The server determines the urgency of the danger information based on the analysis results. Criteria for urgency include the depth of flooding, pedestrian traffic, and residential density. High-urgency information is given priority and notified to other residents in real time. This notification includes a message of reassurance generated by an emotion engine, and also provides information on safe evacuation routes and the nearest evacuation shelters.

[0355] As a specific example, when a heavy rain warning is issued, the server quickly retrieves the data and analyzes it using the generation AI. The generation AI predicts that there is an increased risk of inland flooding in certain low-lying areas of the city. At the same time, a user sends a photo of flooded roads in that area to the server via the app. The device inputs the user's voice and comments into the emotion engine and determines that the user is feeling anxious. The server analyzes the received information, determines the depth and extent of the flooding, and sends a real-time notification to other residents in the area. Upon receiving the notification, the device displays a reassuring message from the emotion engine along with evacuation route instructions, thereby reducing the user's anxiety.

[0356] Example prompt sentence:

[0357] "There is currently a very high risk of flooding. Please remain calm and evacuate to the nearest evacuation shelter."

[0358] "The risk of flooding is very high. Please remain calm and evacuate."

[0359] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0360] Step 1:

[0361] Meteorological and terrain data collection

[0362] The server periodically collects meteorological data such as rainfall, wind speed, and humidity from the meteorological bureau. It also obtains topographical data such as ground elevation and the location of drainage facilities from the local government database. The input is the API response from the meteorological bureau and the local government database, and the output is the formatted data required for analysis.

[0363] Step 2:

[0364] Data analysis and risk prediction

[0365] The server inputs the collected weather and topographical data into a generative artificial intelligence (generative AI model) and outputs the risk level of inland flooding as a number or category. The input is preformatted weather and topographical data, and the output is the risk level assessment result. Specifically, a machine learning algorithm is used to estimate the degree of danger and quantify the risk level.

[0366] Step 3:

[0367] User submission of risk information

[0368] When a user discovers flooding or abnormal water flow at home or in their neighborhood, they launch the smartphone app and take a photo of the dangerous area. They then enter comments such as the depth of the flooding and the date and time of the occurrence. The emotion engine then analyzes the user's voice and text comments to detect their emotional state. The inputs are the photos, comments, voice data, and GPS data, and the output is a consistent record of these data.

[0369] Step 4:

[0370] Analysis of risk information

[0371] The server receives photos, comments, and location information sent by users. It then uses image recognition technology to determine the depth and extent of flooding and analyzes comments to extract detailed information. The input is the data sent by users, and the output is the analysis results, such as information on the depth and extent of flooding.

[0372] Step 5:

[0373] Emotional state analysis and response adjustment

[0374] The server adjusts the necessary measures and notification content based on the user's emotional state analyzed by the emotion engine. For example, if the user shows strong anxiety, the notification content will be detailed and reassuring. The input is the emotional state evaluation result by the emotion engine, and the output is the adjusted notification content.

[0375] Step 6:

[0376] Urgency assessment and notification

[0377] The server determines the urgency of the danger information based on the analysis results. Criteria for urgency include the depth of flooding, foot traffic, and residential density. Information with a high urgency is given priority and notified to other residents in real time. The input is the analyzed danger information, and the output is notification information based on the urgency.

[0378] Step 7:

[0379] Providing evacuation information

[0380] The server provides residents with information on safe evacuation routes and evacuation locations. This includes messages based on the emotion engine that create a sense of security, encouraging users to evacuate safely. The input is danger information and the results of an evaluation of the user's emotional state, and the output is information on evacuation routes and evacuation locations, along with messages providing that information.

[0381] Step 8:

[0382] Displaying notifications and encouraging evacuation

[0383] The device displays the received notification to the user and provides detailed information such as warning messages and maps of dangerous areas. The emotion engine displays messages that take the user's emotions into consideration, allowing the user to consider evacuating to a safe place. The input is notifications and messages from the server, and the output is prompting the user to take action.

[0384] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0385] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0386] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0387] [Second embodiment]

[0388] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0389] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0390] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0391] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0392] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0393] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0394] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0395] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0396] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0397] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0398] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0399] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0400] The present invention relates to a system that collects meteorological and topographical data, uses that data to generate AI that analyzes the risk of inland flooding, and allows residents to share information about dangerous areas via a smartphone app.

[0401] Data collection and analysis

[0402] The server periodically collects weather data (e.g., rainfall, wind speed, humidity) from the weather station.

[0403] The server collects topographical data (e.g., ground elevation, location of drainage facilities) from the municipal database.

[0404] The weather and topographical data collected by the server is input into the artificial intelligence (AI), which analyzes this data and outputs the risk level of inland flooding as a number or category.

[0405] Collection and transmission of risk information

[0406] If a user discovers flooding or abnormal water flow at home or in the neighborhood, they can launch the app on their smartphone.

[0407] The user takes a photo of the problem area using the app, enters a comment (e.g., depth of flooding, date and time of occurrence), and presses the send button.

[0408] The device acquires the user's current location information (GPS data) and sends it to the server along with the photo and comment.

[0409] Information analysis and real-time notifications

[0410] The server analyzes the received photos, comments, and location information, using image recognition technology to determine the depth and extent of flooding in the photos.

[0411] The server then uses the analysis results to determine the urgency of the danger information and organizes it. Criteria for urgency include the depth of flooding, pedestrian traffic, and residential density.

[0412] The server will prioritize and notify other residents of information of high urgency in real time.

[0413] Providing safety measures

[0414] The device displays the received notification to the user, providing detailed information such as warning messages and maps of dangerous areas.

[0415] Users can check the notification and consider evacuating to a safe location.

[0416] The device provides the user with information on safe evacuation routes and the nearest evacuation shelters.

[0417] Specific examples

[0418] For example, when a heavy rain warning is issued by the Meteorological Agency, the server quickly retrieves the data and analyzes it with the generation AI. The generation AI predicts that there is an increased risk of inland flooding in specific low-lying areas of the city. At the same time, a user sends a photo of a flooded road in that area to the server via the app. The server analyzes the received information, determines the depth and extent of the flooding, and sends a real-time notification to other residents in the area. Upon receiving the notification, the user quickly begins evacuation and reaches a safe destination by following the evacuation route instructions provided by the app.

[0419] This invention makes it possible to predict damage caused by inland flooding early and take prompt measures, thereby ensuring the safety of residents. This system functions as a powerful countermeasure against the risk of inland flooding in urban areas.

[0420] The processing flow will be explained below.

[0421] Step 1:

[0422] The server collects weather data (rainfall, wind speed, humidity, etc.) from the meteorological station at regular intervals.

[0423] Step 2:

[0424] The server collects topographical data (ground elevation, location of drainage facilities, etc.) from the local government database.

[0425] Step 3:

[0426] The weather and topographical data collected by the server is input into the generative artificial intelligence (generative AI).

[0427] Step 4:

[0428] The generative AI analyzes the input data and predicts the risk of inland flooding, outputting the risk level as a number or category.

[0429] Step 5:

[0430] If a user discovers flooding or abnormal water flow at home or in the neighborhood, they can launch the app on their smartphone.

[0431] Step 6:

[0432] The user takes a photo of the problem area using the app and enters comments (e.g., depth of flooding, date and time of occurrence).

[0433] Step 7:

[0434] The device acquires the user's current location information (GPS data) and sends it to the server along with the photo and comment.

[0435] Step 8:

[0436] The server analyzes the photos, comments, and location information received, and uses image recognition technology to determine the depth and extent of flooding in the photos.

[0437] Step 9:

[0438] The server determines the urgency of the danger information based on the analysis results, including the depth of flooding, the number of people moving about, and the density of residential areas.

[0439] Step 10:

[0440] The server will prioritize and notify other residents of information of high urgency in real time.

[0441] Step 11:

[0442] The device displays the received notification to the user, providing detailed information such as warning messages and maps of dangerous areas.

[0443] Step 12:

[0444] The user checks the notification and considers evacuating to a safe location.

[0445] Step 13:

[0446] The device provides the user with information on safe evacuation routes and the nearest evacuation shelters.

[0447] Step 14:

[0448] The server will continue to periodically collect new weather data and information from residents, and use generative AI to update risk predictions until the situation improves.

[0449] Example 1

[0450] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0451] Conventional inland flooding prevention systems have had difficulty quickly and accurately predicting flood risk and notifying residents of appropriate information in real time. This has prevented residents from evacuating safely and has prevented damage from being minimized. There has also been a lack of easy ways for residents to report risk information such as flooding. The purpose of this invention is to solve these problems and provide a more efficient and reliable inland flooding prediction and risk management system.

[0452] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0453] In this invention, the server includes means for collecting meteorological data, means for collecting topographical data, means for inputting the collected meteorological data and topographical data into a generating AI and analyzing the risk of inland flooding, means for residents to send photos and information of dangerous areas using mobile communication terminals, means for analyzing the sent information and identifying location information and risk level, means for notifying other residents of the analyzed risk information in real time, and means for providing residents with information on safe evacuation routes and evacuation sites. This enables fast and accurate prediction of inland flooding risks, sharing risk information among residents, and real-time evacuation instructions.

[0454] "Weather data" refers to numerical values ​​and information related to meteorological phenomena, such as rainfall, wind speed, and humidity.

[0455] "Topographic data" refers to numerical values ​​and information about the terrain, such as the elevation of the ground and the location of drainage facilities.

[0456] "Generative artificial intelligence" refers to artificial intelligence technology that analyzes collected data and outputs the risk level of inland flooding as a number or category.

[0457] "Inland flooding" refers to the phenomenon of undrained flooding that occurs in urban and residential areas due to precipitation exceeding drainage capacity.

[0458] "Residents" refers to ordinary people who use this system to share risk information and take evacuation action in the event of a disaster.

[0459] "Mobile communication terminal" refers to a portable communication device such as a smartphone or tablet.

[0460] "Analysis" refers to the act of evaluating and classifying collected data using artificial intelligence and image recognition technology.

[0461] "Danger information" refers to information with a level of urgency related to inland flooding, such as flooding or abnormal water flow.

[0462] "Real-time notification" refers to the act of immediately informing other residents of analyzed danger information.

[0463] An "evacuation route" refers to the optimal route for residents to move to safety in the event of inland flooding.

[0464] An "evacuation site" refers to a place where residents can temporarily ensure safety in the event of inland flooding.

[0465] This invention relates to a system that utilizes meteorological and topographical data, uses generative artificial intelligence (generative AI model) to analyze the risk of inland flooding, and provides appropriate information to residents in real time. This system functions in cooperation with three parties: a server, a terminal, and a user.

[0466] Data collection and analysis

[0467] The server retrieves weather data at a scheduled time. Specifically, it accesses the meteorological agency's API and collects data such as rainfall, wind speed, and humidity. Next, the server retrieves topographical data from the local government's topographical database. This data includes the ground elevation and the location of drainage facilities. The collected weather and topographical data is stored in the database.

[0468] Next, the server inputs the meteorological and topographical data stored in the database into the generative AI model. The generative AI model analyzes this data and outputs the risk level of inland flooding as a number or category (e.g., high risk, medium risk, low risk). The results are managed by the server.

[0469] Collection and transmission of risk information

[0470] When a user discovers flooding or abnormal water flow at home or in their neighborhood, they launch the smartphone app. Using the app's camera function, they take a photo of the problem area and enter a comment. This information includes the depth of the flooding and the date and time of the occurrence. The user's device obtains their current location information (GPS data) and sends an information packet containing the photo and comment to the server.

[0471] Information analysis and real-time notifications

[0472] The server analyzes the photos, comments, and location information it receives. Image recognition technology is used to determine the depth and extent of the flooding in the photos. Based on the analysis results, the server determines the urgency of the danger information and organizes the information. The urgency is determined by factors such as the depth of the flooding, the number of people passing by, and the density of housing. Information with a high level of urgency is prioritized and organized, and the server notifies other residents' devices in real time.

[0473] Providing safety measures

[0474] The device displays the received notification to the user. Detailed information such as warning messages and maps of dangerous areas are also displayed at the same time. The user can check the notification and consider evacuating to a safe location if necessary. The device provides the user with information on safe evacuation routes and the nearest evacuation shelters.

[0475] Specific examples

[0476] For example, when a heavy rainfall warning is issued, the server quickly retrieves the data from the meteorological bureau and analyzes it using a generative AI model. The generative AI model predicts an increased risk of inland flooding in specific low-lying areas of the city. At the same time, a user sends a photo of a flooded road in that area to the server via the app. The server analyzes the received information, determines the depth and extent of the flooding, and sends a real-time notification to other residents in the area. Upon receiving the notification, the user quickly begins evacuation and reaches a safe destination by following the evacuation route instructions provided by the app.

[0477] This system will enable early prediction of damage caused by inland flooding, allowing prompt countermeasures to be taken, and ensuring the safety of residents. It will therefore function as a powerful countermeasure against the risk of inland flooding in urban areas.

[0478] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0479] Program processing steps

[0480] Step 1: Collect weather data

[0481] The server accesses the weather station's API at specified times to obtain weather data such as rainfall, wind speed, and humidity.

[0482] Specific operation: Sends an API request, analyzes the obtained data, and saves it in a database.

[0483] Input: Weather Bureau API endpoint and credentials.

[0484] Output: Latest weather data stored in the database.

[0485] Step 2: Collect terrain data

[0486] The server accesses the local government's terrain database and obtains terrain data such as ground elevation and the location of drainage facilities.

[0487] Specific behavior: Query the required data from the local government database and store the resulting data in a local database.

[0488] Input: Access information and queries to municipal databases.

[0489] Output: Terrain data stored in a database.

[0490] Step 3: Generative AI risk analysis

[0491] The server inputs stored weather and terrain data into a generative AI model.

[0492] Specific operation: Data is input into the generative AI model and analysis begins. After analysis, the risk level of inland flooding is output as a number or category.

[0493] Input: Latest weather and terrain data.

[0494] Output: Risk level of inland flooding (numeric or categorical).

[0495] Step 4: User provides risk information

[0496] If a user discovers flooding or abnormal water flow at home or in the neighborhood, they can launch the app on their smartphone.

[0497] Specific actions: The user takes a photo using the app's camera function, enters a comment, and presses the send button.

[0498] Input: Flood depth, date and time of occurrence, and GPS data.

[0499] Output: Flood information packet sent to the server.

[0500] Step 5: Analyze and locate hazard information

[0501] The server analyzes the photos, comments, and location information received, and uses image recognition technology to determine the depth and extent of flooding in the photos.

[0502] Specific operation: The received data is input into an analysis algorithm to determine the level of danger and location information.

[0503] Input: photos, comments, location.

[0504] Output: Analyzed risk level and specific location information.

[0505] Step 6: Determine the level of urgency and organize the information

[0506] Based on the analysis results, the server determines the urgency of the dangerous information and organizes the information.

[0507] Specific operation: Calculates and prioritizes the level of urgency based on the depth of flooding, the number of people passing by, and the density of housing.

[0508] Input: Parsed risk level and location information.

[0509] Output: List of danger information with urgency level.

[0510] Step 7: Real-time notifications

[0511] The server notifies other residents' devices of highly urgent information in real time.

[0512] Specific operation: Selects information with high urgency and sends warnings to residents' smartphones via the notification system.

[0513] Input: A list of hazard information with urgency ratings.

[0514] Output: Notification message sent to the resident.

[0515] Step 8: Display warnings and provide evacuation information

[0516] The device displays the received notification to the user, providing warning messages and maps of dangerous areas.

[0517] Specific actions: Displaying pop-up notifications, drawing maps, and providing information on safe evacuation routes and nearest evacuation shelters.

[0518] Input: The notification message sent by the server.

[0519] Output: Warning messages and evacuation information displayed to the user.

[0520] keyword

[0521] Generative AI model, prompt sentence

[0522] (Application example 1)

[0523] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0524] Conventional inland flood risk management systems often lack the functionality to provide residents with the latest information in real time and encourage prompt evacuation. Furthermore, they lacked a mechanism for efficiently analyzing risk information sent by users and determining its urgency, making it difficult to provide residents with accurate information when needed. Furthermore, there were technical challenges in identifying the specific depth and extent of flooding using photos and comments sent by users.

[0525] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0526] In this invention, the server includes means for collecting meteorological data, means for collecting topographical data, means for inputting the collected meteorological data and topographical data into a generative AI model and analyzing the risk of inland flooding, means for users to send photos and information of dangerous areas using a mobile device, means for analyzing the sent information and identifying location information and risk level, means for notifying other residents of the analyzed risk information in real time, means for providing residents with information on safe evacuation routes and evacuation sites, means for analyzing photos sent by users using image recognition technology and determining the depth and extent of flooding, and means for determining the urgency of risk information based on the collected analysis information and notifying information with a higher urgency level first. This makes it possible to analyze and notify risk information of inland flooding in real time, and encourage residents to take quick and accurate evacuation action.

[0527] "Weather data" is a general term for information about weather, such as rainfall, wind speed, and humidity, obtained from meteorological stations.

[0528] "Topographical data" is a general term for information about topography obtained from a local government database, such as the elevation of the ground, the location of drainage facilities, etc.

[0529] "Generative artificial intelligence (generative AI)" is an artificial intelligence technology that analyzes the risk of inland flooding based on collected data and outputs the results.

[0530] "Mobile terminal" is a general term for portable electronic devices that users use on a daily basis, such as smartphones and smart glasses.

[0531] "Image recognition technology" refers to technology that analyzes photos sent by users and recognizes specific features and patterns.

[0532] "Flood depth" refers to the depth of flooded water.

[0533] "Urgency" is a standard for evaluating the seriousness and immediacy of dangerous information.

[0534] "Real-time notification" refers to the function of instantly sending analyzed information to other users.

[0535] An "evacuation route" is the optimal route for residents to evacuate safely.

[0536] An "evacuation site" is a place designated for residents to evacuate to in the event of a disaster.

[0537] "Location information" refers to a geographical location identified using GPS or other means.

[0538] The present invention relates to a system that collects meteorological and topographical data, uses that data to generate an AI model that analyzes the risk of inland flooding, and allows residents to share information about dangerous areas via mobile devices. This system is implemented as follows:

[0539] First, the server periodically collects weather data (e.g., rainfall, wind speed, humidity) from the meteorological station, and terrain data (e.g., ground elevation, location of drainage facilities) from the local government database. To retrieve the weather and terrain data, the Python requests library can be used.

[0540] The server then inputs the collected weather and topographical data into a generative AI model (e.g., a model created with TensorFlow). The generative AI model uses this data to analyze the risk level of inland flooding numerically or categorically, and outputs the results.

[0541] When a user discovers flooding or an abnormal water flow, they launch the app on their mobile device. They use the app to take a photo of the dangerous area and enter comments (e.g., the depth of the flooding, the date and time of the occurrence). The app also obtains the user's current location information (GPS data) and sends it to the server along with the photo and comment.

[0542] The server analyzes the received photos, comments, and location information. This analysis uses image recognition technology (e.g., image analysis using OpenCV and TensorFlow) to determine the depth and extent of flooding in the photos. Based on the analyzed information, the urgency of the danger information is determined. Criteria for the urgency include the depth of flooding, pedestrian traffic, and residential density.

[0543] The server uses the analysis results to notify other residents in real time, prioritizing information of high urgency. This notification is done using a web framework such as Flask, which organizes the information and distributes it to residents.

[0544] The device displays the received notification to the user and provides detailed information such as warning messages and maps of dangerous areas. The device also provides the user with information on safe evacuation routes and the nearest evacuation shelters, allowing the user to quickly begin evacuation and evacuate to a safe location.

[0545] For example, when heavy rain occurs, the following prompt is entered:

[0546] User: This is XX Street in Chuo Ward, and the road is flooded to over 1 meter.

[0547] Along with this prompt, the user sends a flooded photo they have taken, which is then analyzed by the server and immediately notified by other residents, encouraging them to take prompt evacuation action.

[0548] This system acts as a powerful countermeasure against the risk of inland flooding in urban areas and provides an efficient way to ensure the safety of residents.

[0549] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0550] Step 1:

[0551] The server periodically collects weather data (rainfall, wind speed, humidity) from the meteorological station. Specifically, it retrieves data from the API using the Python requests library. In this case, it sends an API request as input and retrieves weather data in JSON format as output.

[0552] Step 2:

[0553] The server collects terrain data (ground elevation, location of drainage facilities) from the local government database. It also retrieves data from the API using the requests library. In this case, it sends an API request as input and gets terrain data in JSON format as output.

[0554] Step 3:

[0555] The server inputs the collected weather and topographical data into a generative artificial intelligence (generative AI model). Specifically, it uses a TensorFlow model to analyze the risk of inland flooding. The weather and topographical data are preprocessed as input and then input into the TensorFlow model. The output is the risk level of inland flooding, expressed as a number or category.

[0556] Step 4:

[0557] When a user discovers flooding or an abnormal water flow, they launch the app on their mobile device. Using the app, the user takes a photo of the dangerous area and enters comments (depth of flooding, date and time of occurrence). The app obtains the user's current location information (GPS data) and sends the photo, comment, and location information to the server.

[0558] Step 5:

[0559] The server analyzes the received photos, comments, and location information. This is done using image recognition technology (e.g., image analysis using OpenCV and TensorFlow). The server analyzes the photos sent as input and determines the depth and extent of the flooding. The analysis results are then stored in a database as output.

[0560] Step 6:

[0561] The server determines the urgency of the danger information based on the analysis results. Specifically, it evaluates the urgency using indicators such as flood depth, pedestrian traffic, and residential density. In this case, it uses the analysis results as input to quantify the urgency. As output, it generates data that prioritizes notifications of information with a high urgency.

[0562] Step 7:

[0563] The server notifies other residents in real time, prioritizing information of high urgency. For this purpose, it uses web frameworks such as Flask to deliver notifications. At this time, it uses information of high urgency as input and generates notification messages as output.

[0564] Step 8:

[0565] The device displays the received notification to the user, providing the user with detailed information such as warning messages and maps of dangerous areas. At this time, the device receives the notification message as input and displays it on the user interface, allowing the user to immediately understand the situation.

[0566] Step 9:

[0567] The device provides the user with information on safe evacuation routes and the nearest evacuation shelters. Specifically, it uses an algorithm to calculate the evacuation route and presents the optimal route. In this case, the current location and evacuation shelter information are used as input, and the optimal evacuation route is presented as output.

[0568] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0569] This invention combines an emotion engine with a system that predicts the risk of inland flooding through the collection and analysis of meteorological and topographical data, and allows residents to share information about dangerous areas via a smartphone app. This emotion engine recognizes the user's emotions and takes appropriate action.

[0570] Data collection and analysis

[0571] The server periodically collects weather data (rainfall, wind speed, humidity, etc.) from the weather station.

[0572] The server collects topographical data (ground elevation, location of drainage facilities, etc.) from the local government database.

[0573] The weather and topographical data collected by the server is input into the artificial intelligence (AI), which analyzes this data and outputs the risk level of inland flooding as a number or category.

[0574] Collection and transmission of user information

[0575] If a user discovers flooding or abnormal water flow at home or in the neighborhood, they can launch the app on their smartphone.

[0576] Users take photos of dangerous areas using the app and enter comments (e.g., flood depth, date and time of occurrence). The emotion engine then analyzes the user's voice and text comments to detect their emotional state.

[0577] The device acquires the user's current location information (GPS data) and sends emotional state information along with photos and comments to the server.

[0578] Information analysis and real-time notifications

[0579] The server analyzes the photos, comments, and location information received, and uses image recognition technology to determine the depth and extent of flooding in the photos.

[0580] The server adjusts the necessary measures and notification content based on the user's emotional state analyzed by the emotion engine. For example, if the user is showing strong anxiety, the notification content will be detailed and reassuring.

[0581] The server determines the urgency of the danger information based on the analysis results, including the depth of flooding, the number of people moving about, and the density of residential areas.

[0582] The server will prioritize and notify other residents of information of high urgency in real time.

[0583] Providing safety measures

[0584] The device displays the received notification to the user, providing detailed information such as warning messages and maps of dangerous areas. The emotion engine displays messages that take the user's emotions into consideration.

[0585] Users can check the notification and consider evacuating to a safe location.

[0586] The device provides users with information on safe evacuation routes and the nearest evacuation shelters, and the emotion engine displays appropriate messages containing encouragement and instructions to reduce the user's anxiety during evacuation.

[0587] Specific examples

[0588] For example, when a heavy rain warning is issued by the Meteorological Agency, the server quickly retrieves the data and analyzes it using the generation AI. The generation AI predicts that there is an increased risk of inland flooding in certain low-lying areas of the city. At the same time, a user sends a photo of a flooded road in that area to the server via the app. The device inputs the user's voice and comments into the emotion engine and determines that the user is feeling anxious. The server analyzes the received information, determines the depth and extent of the flooding, and sends a real-time notification to other residents in the area. Upon receiving the notification, the device displays a reassuring message from the emotion engine along with evacuation route instructions, thereby reducing the user's anxiety.

[0589] This invention not only makes it possible to predict damage caused by inland flooding early and implement prompt countermeasures, but also makes it possible to respond in a way that takes into consideration the emotions of users, thereby promoting safer and more secure evacuation behavior and contributing to ensuring the safety of residents.

[0590] The processing flow will be explained below.

[0591] Step 1:

[0592] The server collects weather data (rainfall, wind speed, humidity, etc.) from the meteorological station at regular intervals.

[0593] Step 2:

[0594] The server collects topographical data (ground elevation, location of drainage facilities, etc.) from the local government database.

[0595] Step 3:

[0596] The weather and topographical data collected by the server is input into the generative artificial intelligence (generative AI).

[0597] Step 4:

[0598] The generative AI analyzes the input data and predicts the risk of inland flooding, outputting the risk level as a number or category.

[0599] Step 5:

[0600] If a user discovers flooding or abnormal water flow at home or in the neighborhood, they can launch the app on their smartphone.

[0601] Step 6:

[0602] The user takes a photo of the problem area using the app and enters comments (e.g., the depth of the flooding, the date and time of the occurrence). The emotion engine also analyzes the user's voice and text comments to detect their emotional state.

[0603] Step 7:

[0604] The device acquires the user's current location information (GPS data) and sends photos, comments, and emotional state information to the server.

[0605] Step 8:

[0606] The server analyzes the photos, comments, and location information received, and uses image recognition technology to determine the depth and extent of the flooding in the photos.

[0607] Step 9:

[0608] The server adjusts the notification content based on the user's emotional state analyzed by the emotion engine. For example, if a user is highly anxious, it adds a detailed explanation or a reassuring message.

[0609] Step 10:

[0610] The server determines the urgency of the danger information based on the analysis results, using criteria such as the depth of flooding, pedestrian traffic, and residential density.

[0611] Step 11:

[0612] The server notifies other residents of information with high urgency on a priority basis in real time.

[0613] Step 12:

[0614] The device displays the received notification to the user, and the emotion engine displays messages that take into account the user's emotional state.

[0615] Step 13:

[0616] The user checks the notification and considers evacuating to a safe location.

[0617] Step 14:

[0618] The device provides users with information on safe evacuation routes and the nearest evacuation shelters, and the emotion engine displays appropriate messages containing encouragement and instructions to reduce anxiety during evacuation.

[0619] Step 15:

[0620] The server will continue to periodically collect new weather data and information from residents, and use generative AI to update risk predictions until the situation improves.

[0621] Example 2

[0622] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0623] Damage caused by inland flooding has a significant impact on the safety of residents and the infrastructure of daily life, especially in urban areas. Conventional systems are inadequate in early prediction of flood risk and prompt notification to residents, making it difficult for residents to take appropriate evacuation actions. In addition, responses do not take into consideration the emotions of residents, making it an issue to reduce psychological stress.

[0624] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0625] In this invention, the server includes means for collecting meteorological data, means for collecting topographical data, means for inputting the collected meteorological data and topographical data into a generating AI and analyzing the risk of inland flooding, means for residents to send photos and information of dangerous areas using a mobile communication terminal, means for analyzing the sent information and identifying location information and risk level, means for notifying other residents of the analyzed risk information in real time, means for providing residents with information on safe evacuation routes and evacuation sites, and means for performing emotion recognition and taking appropriate action based on the results. This enables early prediction of inland flooding risk, rapid emergency notification, and appropriate action that takes into account the emotions of residents.

[0626] "Weather data" refers to weather-related information such as rainfall, wind speed, and humidity collected from meteorological agencies and related organizations.

[0627] "Topographic data" refers to information about the terrain, such as the elevation of the ground and the location of drainage facilities, collected from local government databases, etc.

[0628] "Generative artificial intelligence" is an AI technology that analyzes and makes predictions based on large amounts of data, and specifically outputs the risk level of inland flooding as a number or category.

[0629] A "mobile communication terminal" is an electronic device with communication functions that can be used while on the move, such as a smartphone or tablet.

[0630] "Emotion recognition" is a technology that analyzes and detects a user's emotional state from their voice, text, etc.

[0631] "Analysis" is the process of identifying the risk and danger of inland flooding based on collected meteorological and topographical data, as well as information sent by users.

[0632] "Real-time notification" means sending collected and analyzed information to residents immediately and sharing the information promptly.

[0633] An "evacuation route" is a recommended route for evacuating from a dangerous area to a safe place.

[0634] An "evacuation site" is a place where residents can temporarily evacuate to ensure their safety in the event of a disaster.

[0635] I understand. Below is the "Mode for carrying out the invention."

[0636] This invention combines emotion recognition with a system that predicts the risk of inland flooding through the collection and analysis of meteorological and topographical data, and allows residents to share information about dangerous areas via mobile communication devices. The system consists of three main components: a server, a device, and a user.

[0637] The server performs the following functions. First, it periodically collects weather data such as rainfall, wind speed, and humidity using the meteorological bureau's API. It also obtains topographical data such as ground elevation and the location of drainage facilities from the local government's database and stores this data in the database. The collected weather and topographical data is input into a generative artificial intelligence (e.g., GPT-4) using a Python script, which outputs the risk level of inland flooding as a number or category. The results of this analysis are further analyzed within the system and notified to residents in real time. Furthermore, an emotion recognition engine is used to adjust the content of notifications based on the user's emotional state, and appropriate responses are taken.

[0638] The device mainly refers to a mobile communication device (such as a smartphone or tablet) and performs the following functions: When a user discovers a flooded area or an abnormal water flow, they can launch the app to take a photo and enter a comment and emotional state (text or voice). The user's location information is obtained using the device's GPS function, and all information is sent to the server. The received notification is displayed on the device as a pop-up message or alert, and a message of reassurance based on emotion recognition and evacuation route instructions are provided.

[0639] Users are responsible for reporting any abnormal water flow or flooding they notice in their daily lives through the app. This reporting involves taking photos and entering comments, and also inputting emotional state information, which is used for analysis by the system's emotion recognition engine. By receiving notifications, users can take prompt and appropriate evacuation action.

[0640] As a concrete example, when a heavy rain warning is issued, the server quickly retrieves the data and analyzes it using generative AI (e.g., GPT-4). The generative AI predicts that there is an increased risk of inland flooding in certain low-lying areas of the city. At the same time, a user sends a photo of flooded roads in that area and a comment to the server via an app. The device inputs the user's voice and comments into an emotion recognition engine and determines that the user is feeling anxious. The server analyzes the received information, determines the depth and extent of the flooding, and sends a real-time notification to other residents in the area. The device that receives the notification displays a reassuring message and evacuation route instructions using the emotion recognition engine, thereby alleviating the user's anxiety. This system not only makes it possible to predict damage caused by inland flooding early and implement prompt countermeasures, but also to respond in a way that takes the user's emotions into consideration.

[0641] Example prompt sentence:

[0642] Input prompt:

[0643] "In response to this heavy rain warning, please tell us the procedures for predicting the risk of inland flooding in low-lying areas of the city and encouraging residents to take appropriate measures."

[0644] Example expected output:

[0645] "When a heavy rain warning is issued, the server obtains meteorological and topographical data and inputs it into the generation AI. The generation AI identifies areas at high risk of inland flooding and analyzes this together with flooding information sent by users via the app. The server determines the level of urgency based on the analysis results and sends notifications to residents in real time. The device displays the notification content and provides a reassuring message using an emotion recognition engine, as well as evacuation route instructions."

[0646] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0647] Step 1: Meteorological data collection

[0648] A server collects weather data.

[0649] Input: Meteorological Agency API endpoint

[0650] Data processing: Obtaining data such as rainfall, wind speed, humidity, etc. from the meteorological bureau and converting it into the required format.

[0651] Output: Transformed weather data (rainfall, wind speed, humidity)

[0652] Specific operation: The server periodically sends requests to the weather bureau's API, receives the weather data returned in response in JSON format, and stores it in a database.

[0653] Step 2: Collect terrain data

[0654] The server collects the terrain data.

[0655] Input: API endpoint of the city's database

[0656] Data processing: Obtain topographical data such as ground elevation and drainage facility locations from the municipality's database and convert it into the required format.

[0657] Output: Converted terrain data (ground elevation, drainage facility locations)

[0658] Specific operation: The server sends a request to the local government database, receives the returned terrain data in JSON format, and stores it in the database.

[0659] Step 3: Data analysis

[0660] The server inputs meteorological and topographical data into the generation AI, which then analyzes the risk level of inland flooding.

[0661] Input: Weather data, terrain data

[0662] Data calculation: Meteorological and topographical data are input into a generating AI (e.g., GPT-4), and the risk level of inland flooding is output as a number or category.

[0663] Output: Risk level of inland flooding (numerical value, category)

[0664] Specific operation: The server runs a Python script, inputs meteorological and topographical data into the generation AI, and the generation AI predicts the risk level of inland flooding based on this data.

[0665] Step 4: Collect user information

[0666] The user reports information about dangerous locations using a mobile communication terminal.

[0667] Input: Photo, Comment, Emotional State (voice or text)

[0668] Data processing: Converts the information acquired by the terminal into a format that can be sent to the server.

[0669] Output: Data ready to send (photos, comments, emotional state)

[0670] Specific operation: The user launches the app, takes a photo of the dangerous area, enters a comment, and then performs voice input.

[0671] Step 5: Send data

[0672] The device acquires the user's current location information (GPS data) and sends photos, comments, and emotional state to the server.

[0673] Input: GPS data, photos, comments, emotional state

[0674] Data calculation: data integration and preparation for transmission

[0675] Output: Integrated data (GPS data, photos, comments, emotional state)

[0676] Specific operation: The device obtains location information using the GPS function and uploads all information to the server.

[0677] Step 6: Information Analysis

[0678] The server analyzes the received data.

[0679] Input: photos, comments, GPS data, emotional state

[0680] Data calculation: Image recognition technology (e.g., OpenCV and TensorFlow) is used to determine the depth and extent of flooding in the photo. An emotion engine is also used to analyze the user's emotional state.

[0681] Output: Analysis results (flood depth, spread, emotional state)

[0682] How it works: The server uses image recognition technology to analyze the received photos and determine the depth and extent of the flooding. At the same time, the emotion engine analyzes the user's emotional state.

[0683] Step 7: Real-time notifications

[0684] The server determines the urgency of the danger information and notifies residents in real time.

[0685] Input: Analysis results (flood depth, spread, emotional state)

[0686] Data calculation: Determining notification priority and generating notification content

[0687] Output: Emergency notification message

[0688] Specific operation: The server determines the urgency based on the analysis results, generates notification content, and sends notifications to other residents with priority.

[0689] Step 8: Provide safety measures

[0690] The terminal displays the received notification to the user.

[0691] Input: Emergency notification message

[0692] Data processing: Converting notification messages into display formats

[0693] Output: A notification message that is displayed to the user.

[0694] Specific operation: The device displays the notification as a pop-up message and provides a reassuring message or evacuation route instructions based on the results of emotion recognition.

[0695] (Application example 2)

[0696] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0697] Existing inland flood forecasting systems can predict risk by analyzing meteorological and topographical data, but they do not provide real-time information that takes into account residents' emotional state. As a result, residents are often unable to take appropriate action when they receive danger information and end up feeling anxious. Furthermore, because individual responses based on emotional state are not provided, it is difficult to encourage safe evacuation behavior.

[0698] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0699] In this invention, the server includes means for collecting weather data, means for collecting topographical data, means for inputting the collected weather data and topographical data into a generating AI and analyzing the risk of inland flooding, means for residents to send photos and information of dangerous areas using a smartphone app, means for analyzing the sent information and identifying location information and risk level, means for notifying other residents of the analyzed risk information in real time, means for providing residents with information on safe evacuation routes and evacuation sites, and means for analyzing the user's emotional state using an emotion engine and responding in a way that takes emotions into consideration. This enables the provision of information to residents quickly and in a way that takes emotions into consideration, thereby promoting safe evacuation behavior.

[0700] "Weather data" refers to numerical values ​​and information about weather, such as rainfall, wind speed, and humidity, collected from meteorological agencies and weather observation institutions.

[0701] "Topographic data" refers to numerical values ​​and information about the terrain, such as ground elevation and the location of drainage facilities, collected from local governments and surveying agencies.

[0702] "Generative AI" refers to an AI model designed to analyze the risk of inland flooding based on meteorological and topographical data.

[0703] "Inland flooding" is a phenomenon in which sewerage and drainage facilities are temporarily unable to handle the flow of water due to heavy rain or flooding, increasing the risk of flooding in urban areas and buildings.

[0704] "Means for analyzing risk" refers to the process of using collected data to evaluate the risk level of inland flooding numerically or in categories.

[0705] "Smartphone app" refers to application software that users can use on their smartphones, including tools for sending photos and information about dangerous areas.

[0706] "Means for analyzing submitted information" refers to the process of analyzing data such as photos, comments, and location information submitted by users to identify the situation and risk of inland flooding.

[0707] "Location information" refers to information that indicates a geographic location based on GPS data or a user's current location.

[0708] "Risk level" is an indicator that shows the possibility of inland flooding and the degree of damage it would cause, including the level of urgency.

[0709] "Means of real-time notification" refers to the process of promptly communicating analyzed danger information to other residents at the same time.

[0710] "Safe evacuation routes" refers to information that indicates routes to travel from areas experiencing inland flooding to evacuation shelters or safe locations.

[0711] An "evacuation site" is a facility or area designated as a temporary evacuation site for residents in the event of a disaster such as inland flooding.

[0712] An "emotion engine" is software or a system that analyzes a user's voice and text comments, detects their emotional state, and responds appropriately.

[0713] This invention combines an emotion engine with a system that predicts the risk of inland flooding through the collection and analysis of meteorological and topographical data, and allows residents to share information about dangerous areas via a smartphone app. This system is implemented in the following form.

[0714] The server periodically collects meteorological data (rainfall, wind speed, humidity, etc.) from meteorological stations and topographical data (ground elevation, location of drainage facilities, etc.) from local government databases. The collected meteorological and topographical data is input into a generative artificial intelligence (generative AI model), which outputs the risk level of inland flooding as a number or category.

[0715] When a user discovers flooding or abnormal water flow at home or in their neighborhood, they launch the app on their smartphone, take a photo of the dangerous area, and enter comments (e.g., depth of flooding, date and time of occurrence). In addition, the emotion engine analyzes the user's voice and text comments to detect their emotional state (e.g., anxiety, fear, panic). This information is sent to the server along with GPS data.

[0716] The server uses image recognition technology to analyze the received photos, comments, and location information to determine the depth and extent of flooding. During this process, an emotion engine analyzes the user's emotional state and adjusts the necessary measures and notification content based on that. For example, if the user expresses strong anxiety, the server will prepare a detailed, reassuring notification.

[0717] The server determines the urgency of the danger information based on the analysis results. Criteria for urgency include the depth of flooding, pedestrian traffic, and residential density. High-urgency information is given priority and notified to other residents in real time. This notification includes a message of reassurance generated by an emotion engine, and also provides information on safe evacuation routes and the nearest evacuation shelters.

[0718] As a specific example, when a heavy rain warning is issued, the server quickly retrieves the data and analyzes it using the generation AI. The generation AI predicts that there is an increased risk of inland flooding in certain low-lying areas of the city. At the same time, a user sends a photo of flooded roads in that area to the server via the app. The device inputs the user's voice and comments into the emotion engine and determines that the user is feeling anxious. The server analyzes the received information, determines the depth and extent of the flooding, and sends a real-time notification to other residents in the area. Upon receiving the notification, the device displays a reassuring message from the emotion engine along with evacuation route instructions, thereby reducing the user's anxiety.

[0719] Example prompt sentence:

[0720] "There is currently a very high risk of flooding. Please remain calm and evacuate to the nearest evacuation shelter."

[0721] "The risk of flooding is very high. Please remain calm and evacuate."

[0722] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0723] Step 1:

[0724] Meteorological and terrain data collection

[0725] The server periodically collects meteorological data such as rainfall, wind speed, and humidity from the meteorological bureau. It also obtains topographical data such as ground elevation and the location of drainage facilities from the local government database. The input is the API response from the meteorological bureau and the local government database, and the output is the formatted data required for analysis.

[0726] Step 2:

[0727] Data analysis and risk prediction

[0728] The server inputs the collected weather and topographical data into a generative artificial intelligence (generative AI model) and outputs the risk level of inland flooding as a number or category. The input is preformatted weather and topographical data, and the output is the risk level assessment result. Specifically, a machine learning algorithm is used to estimate the degree of danger and quantify the risk level.

[0729] Step 3:

[0730] User submission of risk information

[0731] When a user discovers flooding or abnormal water flow at home or in their neighborhood, they launch the smartphone app and take a photo of the dangerous area. They then enter comments such as the depth of the flooding and the date and time of the occurrence. The emotion engine then analyzes the user's voice and text comments to detect their emotional state. The inputs are the photos, comments, voice data, and GPS data, and the output is a consistent record of these data.

[0732] Step 4:

[0733] Analysis of risk information

[0734] The server receives photos, comments, and location information sent by users. It then uses image recognition technology to determine the depth and extent of flooding and analyzes comments to extract detailed information. The input is the data sent by users, and the output is the analysis results, such as information on the depth and extent of flooding.

[0735] Step 5:

[0736] Emotional state analysis and response adjustment

[0737] The server adjusts the necessary measures and notification content based on the user's emotional state analyzed by the emotion engine. For example, if the user shows strong anxiety, the notification content will be detailed and reassuring. The input is the emotional state evaluation result by the emotion engine, and the output is the adjusted notification content.

[0738] Step 6:

[0739] Urgency assessment and notification

[0740] The server determines the urgency of the danger information based on the analysis results. Criteria for urgency include the depth of flooding, foot traffic, and residential density. Information with a high urgency is given priority and notified to other residents in real time. The input is the analyzed danger information, and the output is notification information based on the urgency.

[0741] Step 7:

[0742] Providing evacuation information

[0743] The server provides residents with information on safe evacuation routes and evacuation locations. This includes messages based on the emotion engine that create a sense of security, encouraging users to evacuate safely. The input is danger information and the results of an evaluation of the user's emotional state, and the output is information on evacuation routes and evacuation locations, along with messages providing that information.

[0744] Step 8:

[0745] Displaying notifications and encouraging evacuation

[0746] The device displays the received notification to the user and provides detailed information such as warning messages and maps of dangerous areas. The emotion engine displays messages that take the user's emotions into consideration, allowing the user to consider evacuating to a safe place. The input is notifications and messages from the server, and the output is prompting the user to take action.

[0747] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0748] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0749] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0750] [Third embodiment]

[0751] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0752] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0753] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0754] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0755] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0756] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0757] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0758] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0759] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0760] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0761] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0762] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0763] The present invention relates to a system that collects meteorological and topographical data, uses that data to generate AI that analyzes the risk of inland flooding, and allows residents to share information about dangerous areas via a smartphone app.

[0764] Data collection and analysis

[0765] The server periodically collects weather data (e.g., rainfall, wind speed, humidity) from the weather station.

[0766] The server collects topographical data (e.g., ground elevation, location of drainage facilities) from the municipal database.

[0767] The weather and topographical data collected by the server is input into the artificial intelligence (AI), which analyzes this data and outputs the risk level of inland flooding as a number or category.

[0768] Collection and transmission of risk information

[0769] If a user discovers flooding or abnormal water flow at home or in the neighborhood, they can launch the app on their smartphone.

[0770] The user takes a photo of the problem area using the app, enters a comment (e.g., depth of flooding, date and time of occurrence), and presses the send button.

[0771] The device acquires the user's current location information (GPS data) and sends it to the server along with the photo and comment.

[0772] Information analysis and real-time notifications

[0773] The server analyzes the received photos, comments, and location information, using image recognition technology to determine the depth and extent of flooding in the photos.

[0774] The server then uses the analysis results to determine the urgency of the danger information and organizes it. Criteria for urgency include the depth of flooding, pedestrian traffic, and residential density.

[0775] The server will prioritize and notify other residents of information of high urgency in real time.

[0776] Providing safety measures

[0777] The device displays the received notification to the user, providing detailed information such as warning messages and maps of dangerous areas.

[0778] Users can check the notification and consider evacuating to a safe location.

[0779] The device provides the user with information on safe evacuation routes and the nearest evacuation shelters.

[0780] Specific examples

[0781] For example, when a heavy rain warning is issued by the Meteorological Agency, the server quickly retrieves the data and analyzes it with the generation AI. The generation AI predicts that there is an increased risk of inland flooding in specific low-lying areas of the city. At the same time, a user sends a photo of a flooded road in that area to the server via the app. The server analyzes the received information, determines the depth and extent of the flooding, and sends a real-time notification to other residents in the area. Upon receiving the notification, the user quickly begins evacuation and reaches a safe destination by following the evacuation route instructions provided by the app.

[0782] This invention makes it possible to predict damage caused by inland flooding early and take prompt measures, thereby ensuring the safety of residents. This system functions as a powerful countermeasure against the risk of inland flooding in urban areas.

[0783] The processing flow will be explained below.

[0784] Step 1:

[0785] The server collects weather data (rainfall, wind speed, humidity, etc.) from the meteorological station at regular intervals.

[0786] Step 2:

[0787] The server collects topographical data (ground elevation, location of drainage facilities, etc.) from the local government database.

[0788] Step 3:

[0789] The weather and topographical data collected by the server is input into the generative artificial intelligence (generative AI).

[0790] Step 4:

[0791] The generative AI analyzes the input data and predicts the risk of inland flooding, outputting the risk level as a number or category.

[0792] Step 5:

[0793] If a user discovers flooding or abnormal water flow at home or in the neighborhood, they can launch the app on their smartphone.

[0794] Step 6:

[0795] The user takes a photo of the problem area using the app and enters comments (e.g., depth of flooding, date and time of occurrence).

[0796] Step 7:

[0797] The device acquires the user's current location information (GPS data) and sends it to the server along with the photo and comment.

[0798] Step 8:

[0799] The server analyzes the photos, comments, and location information received, and uses image recognition technology to determine the depth and extent of flooding in the photos.

[0800] Step 9:

[0801] The server determines the urgency of the danger information based on the analysis results, including the depth of flooding, the number of people moving about, and the density of residential areas.

[0802] Step 10:

[0803] The server will prioritize and notify other residents of information of high urgency in real time.

[0804] Step 11:

[0805] The device displays the received notification to the user, providing detailed information such as warning messages and maps of dangerous areas.

[0806] Step 12:

[0807] The user checks the notification and considers evacuating to a safe location.

[0808] Step 13:

[0809] The device provides the user with information on safe evacuation routes and the nearest evacuation shelters.

[0810] Step 14:

[0811] The server will continue to periodically collect new weather data and information from residents, and use generative AI to update risk predictions until the situation improves.

[0812] Example 1

[0813] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0814] Conventional inland flooding prevention systems have had difficulty quickly and accurately predicting flood risk and notifying residents of appropriate information in real time. This has prevented residents from evacuating safely and has prevented damage from being minimized. There has also been a lack of easy ways for residents to report risk information such as flooding. The purpose of this invention is to solve these problems and provide a more efficient and reliable inland flooding prediction and risk management system.

[0815] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0816] In this invention, the server includes means for collecting meteorological data, means for collecting topographical data, means for inputting the collected meteorological data and topographical data into a generating AI and analyzing the risk of inland flooding, means for residents to send photos and information of dangerous areas using mobile communication terminals, means for analyzing the sent information and identifying location information and risk level, means for notifying other residents of the analyzed risk information in real time, and means for providing residents with information on safe evacuation routes and evacuation sites. This enables fast and accurate prediction of inland flooding risks, sharing risk information among residents, and real-time evacuation instructions.

[0817] "Weather data" refers to numerical values ​​and information related to meteorological phenomena, such as rainfall, wind speed, and humidity.

[0818] "Topographic data" refers to numerical values ​​and information about the terrain, such as the elevation of the ground and the location of drainage facilities.

[0819] "Generative artificial intelligence" refers to artificial intelligence technology that analyzes collected data and outputs the risk level of inland flooding as a number or category.

[0820] "Inland flooding" refers to the phenomenon of undrained flooding that occurs in urban and residential areas due to precipitation exceeding drainage capacity.

[0821] "Residents" refers to ordinary people who use this system to share risk information and take evacuation action in the event of a disaster.

[0822] "Mobile communication terminal" refers to a portable communication device such as a smartphone or tablet.

[0823] "Analysis" refers to the act of evaluating and classifying collected data using artificial intelligence and image recognition technology.

[0824] "Danger information" refers to information with a level of urgency related to inland flooding, such as flooding or abnormal water flow.

[0825] "Real-time notification" refers to the act of immediately informing other residents of analyzed danger information.

[0826] An "evacuation route" refers to the optimal route for residents to move to safety in the event of inland flooding.

[0827] An "evacuation site" refers to a place where residents can temporarily ensure safety in the event of inland flooding.

[0828] This invention relates to a system that utilizes meteorological and topographical data, uses generative artificial intelligence (generative AI model) to analyze the risk of inland flooding, and provides appropriate information to residents in real time. This system functions in cooperation with three parties: a server, a terminal, and a user.

[0829] Data collection and analysis

[0830] The server retrieves weather data at a scheduled time. Specifically, it accesses the meteorological agency's API and collects data such as rainfall, wind speed, and humidity. Next, the server retrieves topographical data from the local government's topographical database. This data includes the ground elevation and the location of drainage facilities. The collected weather and topographical data is stored in the database.

[0831] Next, the server inputs the meteorological and topographical data stored in the database into the generative AI model. The generative AI model analyzes this data and outputs the risk level of inland flooding as a number or category (e.g., high risk, medium risk, low risk). The results are managed by the server.

[0832] Collection and transmission of risk information

[0833] When a user discovers flooding or abnormal water flow at home or in their neighborhood, they launch the smartphone app. Using the app's camera function, they take a photo of the problem area and enter a comment. This information includes the depth of the flooding and the date and time of the occurrence. The user's device obtains their current location information (GPS data) and sends an information packet containing the photo and comment to the server.

[0834] Information analysis and real-time notifications

[0835] The server analyzes the photos, comments, and location information it receives. Image recognition technology is used to determine the depth and extent of the flooding in the photos. Based on the analysis results, the server determines the urgency of the danger information and organizes the information. The urgency is determined by factors such as the depth of the flooding, the number of people passing by, and the density of housing. Information with a high level of urgency is prioritized and organized, and the server notifies other residents' devices in real time.

[0836] Providing safety measures

[0837] The device displays the received notification to the user. Detailed information such as warning messages and maps of dangerous areas are also displayed at the same time. The user can check the notification and consider evacuating to a safe location if necessary. The device provides the user with information on safe evacuation routes and the nearest evacuation shelters.

[0838] Specific examples

[0839] For example, when a heavy rainfall warning is issued, the server quickly retrieves the data from the meteorological bureau and analyzes it using a generative AI model. The generative AI model predicts an increased risk of inland flooding in specific low-lying areas of the city. At the same time, a user sends a photo of a flooded road in that area to the server via the app. The server analyzes the received information, determines the depth and extent of the flooding, and sends a real-time notification to other residents in the area. Upon receiving the notification, the user quickly begins evacuation and reaches a safe destination by following the evacuation route instructions provided by the app.

[0840] This system will enable early prediction of damage caused by inland flooding, allowing prompt countermeasures to be taken, and ensuring the safety of residents. It will therefore function as a powerful countermeasure against the risk of inland flooding in urban areas.

[0841] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0842] Program processing steps

[0843] Step 1: Collect weather data

[0844] The server accesses the weather station's API at specified times to obtain weather data such as rainfall, wind speed, and humidity.

[0845] Specific operation: Sends an API request, analyzes the obtained data, and saves it in a database.

[0846] Input: Weather Bureau API endpoint and credentials.

[0847] Output: Latest weather data stored in the database.

[0848] Step 2: Collect terrain data

[0849] The server accesses the local government's terrain database and obtains terrain data such as ground elevation and the location of drainage facilities.

[0850] Specific behavior: Query the required data from the local government database and store the resulting data in a local database.

[0851] Input: Access information and queries to municipal databases.

[0852] Output: Terrain data stored in a database.

[0853] Step 3: Generative AI risk analysis

[0854] The server inputs stored weather and terrain data into a generative AI model.

[0855] Specific operation: Data is input into the generative AI model and analysis begins. After analysis, the risk level of inland flooding is output as a number or category.

[0856] Input: Latest weather and terrain data.

[0857] Output: Risk level of inland flooding (numeric or categorical).

[0858] Step 4: User provides risk information

[0859] If a user discovers flooding or abnormal water flow at home or in the neighborhood, they can launch the app on their smartphone.

[0860] Specific actions: The user takes a photo using the app's camera function, enters a comment, and presses the send button.

[0861] Input: Flood depth, date and time of occurrence, and GPS data.

[0862] Output: Flood information packet sent to the server.

[0863] Step 5: Analyze and locate hazard information

[0864] The server analyzes the photos, comments, and location information received, and uses image recognition technology to determine the depth and extent of flooding in the photos.

[0865] Specific operation: The received data is input into an analysis algorithm to determine the level of danger and location information.

[0866] Input: photos, comments, location.

[0867] Output: Analyzed risk level and specific location information.

[0868] Step 6: Determine the level of urgency and organize the information

[0869] Based on the analysis results, the server determines the urgency of the dangerous information and organizes the information.

[0870] Specific operation: Calculates and prioritizes the level of urgency based on the depth of flooding, the number of people passing by, and the density of housing.

[0871] Input: Parsed risk level and location information.

[0872] Output: List of danger information with urgency level.

[0873] Step 7: Real-time notifications

[0874] The server notifies other residents' devices of highly urgent information in real time.

[0875] Specific operation: Selects information with high urgency and sends warnings to residents' smartphones via the notification system.

[0876] Input: A list of hazard information with urgency ratings.

[0877] Output: Notification message sent to the resident.

[0878] Step 8: Display warnings and provide evacuation information

[0879] The device displays the received notification to the user, providing warning messages and maps of dangerous areas.

[0880] Specific actions: Displaying pop-up notifications, drawing maps, and providing information on safe evacuation routes and nearest evacuation shelters.

[0881] Input: The notification message sent by the server.

[0882] Output: Warning messages and evacuation information displayed to the user.

[0883] keyword

[0884] Generative AI model, prompt sentence

[0885] (Application example 1)

[0886] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0887] Conventional inland flood risk management systems often lack the functionality to provide residents with the latest information in real time and encourage prompt evacuation. Furthermore, they lacked a mechanism for efficiently analyzing risk information sent by users and determining its urgency, making it difficult to provide residents with accurate information when needed. Furthermore, there were technical challenges in identifying the specific depth and extent of flooding using photos and comments sent by users.

[0888] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0889] In this invention, the server includes means for collecting meteorological data, means for collecting topographical data, means for inputting the collected meteorological data and topographical data into a generative AI model and analyzing the risk of inland flooding, means for users to send photos and information of dangerous areas using a mobile device, means for analyzing the sent information and identifying location information and risk level, means for notifying other residents of the analyzed risk information in real time, means for providing residents with information on safe evacuation routes and evacuation sites, means for analyzing photos sent by users using image recognition technology and determining the depth and extent of flooding, and means for determining the urgency of risk information based on the collected analysis information and notifying information with a higher urgency level first. This makes it possible to analyze and notify risk information of inland flooding in real time, and encourage residents to take quick and accurate evacuation action.

[0890] "Weather data" is a general term for information about weather, such as rainfall, wind speed, and humidity, obtained from meteorological stations.

[0891] "Topographical data" is a general term for information about topography obtained from a local government database, such as the elevation of the ground, the location of drainage facilities, etc.

[0892] "Generative artificial intelligence (generative AI)" is an artificial intelligence technology that analyzes the risk of inland flooding based on collected data and outputs the results.

[0893] "Mobile terminal" is a general term for portable electronic devices that users use on a daily basis, such as smartphones and smart glasses.

[0894] "Image recognition technology" refers to technology that analyzes photos sent by users and recognizes specific features and patterns.

[0895] "Flood depth" refers to the depth of flooded water.

[0896] "Urgency" is a standard for evaluating the seriousness and immediacy of dangerous information.

[0897] "Real-time notification" refers to the function of instantly sending analyzed information to other users.

[0898] An "evacuation route" is the optimal route for residents to evacuate safely.

[0899] An "evacuation site" is a place designated for residents to evacuate to in the event of a disaster.

[0900] "Location information" refers to a geographical location identified using GPS or other means.

[0901] The present invention relates to a system that collects meteorological and topographical data, uses that data to generate an AI model that analyzes the risk of inland flooding, and allows residents to share information about dangerous areas via mobile devices. This system is implemented as follows:

[0902] First, the server periodically collects weather data (e.g., rainfall, wind speed, humidity) from the meteorological station, and terrain data (e.g., ground elevation, location of drainage facilities) from the local government database. To retrieve the weather and terrain data, the Python requests library can be used.

[0903] The server then inputs the collected weather and topographical data into a generative AI model (e.g., a model created with TensorFlow). The generative AI model uses this data to analyze the risk level of inland flooding numerically or categorically, and outputs the results.

[0904] When a user discovers flooding or an abnormal water flow, they launch the app on their mobile device. They use the app to take a photo of the dangerous area and enter comments (e.g., the depth of the flooding, the date and time of the occurrence). The app also obtains the user's current location information (GPS data) and sends it to the server along with the photo and comment.

[0905] The server analyzes the received photos, comments, and location information. This analysis uses image recognition technology (e.g., image analysis using OpenCV and TensorFlow) to determine the depth and extent of flooding in the photos. Based on the analyzed information, the urgency of the danger information is determined. Criteria for the urgency include the depth of flooding, pedestrian traffic, and residential density.

[0906] The server uses the analysis results to notify other residents in real time, prioritizing information of high urgency. This notification is done using a web framework such as Flask, which organizes the information and distributes it to residents.

[0907] The device displays the received notification to the user and provides detailed information such as warning messages and maps of dangerous areas. The device also provides the user with information on safe evacuation routes and the nearest evacuation shelters, allowing the user to quickly begin evacuation and evacuate to a safe location.

[0908] For example, when heavy rain occurs, the following prompt is entered:

[0909] User: This is XX Street in Chuo Ward, and the road is flooded to over 1 meter.

[0910] Along with this prompt, the user sends a flooded photo they have taken, which is then analyzed by the server and immediately notified by other residents, encouraging them to take prompt evacuation action.

[0911] This system acts as a powerful countermeasure against the risk of inland flooding in urban areas and provides an efficient way to ensure the safety of residents.

[0912] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0913] Step 1:

[0914] The server periodically collects weather data (rainfall, wind speed, humidity) from the meteorological station. Specifically, it retrieves data from the API using the Python requests library. In this case, it sends an API request as input and retrieves weather data in JSON format as output.

[0915] Step 2:

[0916] The server collects terrain data (ground elevation, location of drainage facilities) from the local government database. It also retrieves data from the API using the requests library. In this case, it sends an API request as input and gets terrain data in JSON format as output.

[0917] Step 3:

[0918] The server inputs the collected weather and topographical data into a generative artificial intelligence (generative AI model). Specifically, it uses a TensorFlow model to analyze the risk of inland flooding. The weather and topographical data are preprocessed as input and then input into the TensorFlow model. The output is the risk level of inland flooding, expressed as a number or category.

[0919] Step 4:

[0920] When a user discovers flooding or an abnormal water flow, they launch the app on their mobile device. Using the app, the user takes a photo of the dangerous area and enters comments (depth of flooding, date and time of occurrence). The app obtains the user's current location information (GPS data) and sends the photo, comment, and location information to the server.

[0921] Step 5:

[0922] The server analyzes the received photos, comments, and location information. This is done using image recognition technology (e.g., image analysis using OpenCV and TensorFlow). The server analyzes the photos sent as input and determines the depth and extent of the flooding. The analysis results are then stored in a database as output.

[0923] Step 6:

[0924] The server determines the urgency of the danger information based on the analysis results. Specifically, it evaluates the urgency using indicators such as flood depth, pedestrian traffic, and residential density. In this case, it uses the analysis results as input to quantify the urgency. As output, it generates data that prioritizes notifications of information with a high urgency.

[0925] Step 7:

[0926] The server notifies other residents in real time, prioritizing information of high urgency. For this purpose, it uses web frameworks such as Flask to deliver notifications. At this time, it uses information of high urgency as input and generates notification messages as output.

[0927] Step 8:

[0928] The device displays the received notification to the user, providing the user with detailed information such as warning messages and maps of dangerous areas. At this time, the device receives the notification message as input and displays it on the user interface, allowing the user to immediately understand the situation.

[0929] Step 9:

[0930] The device provides the user with information on safe evacuation routes and the nearest evacuation shelters. Specifically, it uses an algorithm to calculate the evacuation route and presents the optimal route. In this case, the current location and evacuation shelter information are used as input, and the optimal evacuation route is presented as output.

[0931] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0932] This invention combines an emotion engine with a system that predicts the risk of inland flooding through the collection and analysis of meteorological and topographical data, and allows residents to share information about dangerous areas via a smartphone app. This emotion engine recognizes the user's emotions and takes appropriate action.

[0933] Data collection and analysis

[0934] The server periodically collects weather data (rainfall, wind speed, humidity, etc.) from the weather station.

[0935] The server collects topographical data (ground elevation, location of drainage facilities, etc.) from the local government database.

[0936] The weather and topographical data collected by the server is input into the artificial intelligence (AI), which analyzes this data and outputs the risk level of inland flooding as a number or category.

[0937] Collection and transmission of user information

[0938] If a user discovers flooding or abnormal water flow at home or in the neighborhood, they can launch the app on their smartphone.

[0939] Users take photos of dangerous areas using the app and enter comments (e.g., flood depth, date and time of occurrence). The emotion engine then analyzes the user's voice and text comments to detect their emotional state.

[0940] The device acquires the user's current location information (GPS data) and sends emotional state information along with photos and comments to the server.

[0941] Information analysis and real-time notifications

[0942] The server analyzes the photos, comments, and location information received, and uses image recognition technology to determine the depth and extent of flooding in the photos.

[0943] The server adjusts the necessary measures and notification content based on the user's emotional state analyzed by the emotion engine. For example, if the user is showing strong anxiety, the notification content will be detailed and reassuring.

[0944] The server determines the urgency of the danger information based on the analysis results, including the depth of flooding, the number of people moving about, and the density of residential areas.

[0945] The server will prioritize and notify other residents of information of high urgency in real time.

[0946] Providing safety measures

[0947] The device displays the received notification to the user, providing detailed information such as warning messages and maps of dangerous areas. The emotion engine displays messages that take the user's emotions into consideration.

[0948] Users can check the notification and consider evacuating to a safe location.

[0949] The device provides users with information on safe evacuation routes and the nearest evacuation shelters, and the emotion engine displays appropriate messages containing encouragement and instructions to reduce the user's anxiety during evacuation.

[0950] Specific examples

[0951] For example, when a heavy rain warning is issued by the Meteorological Agency, the server quickly retrieves the data and analyzes it using the generation AI. The generation AI predicts that there is an increased risk of inland flooding in certain low-lying areas of the city. At the same time, a user sends a photo of a flooded road in that area to the server via the app. The device inputs the user's voice and comments into the emotion engine and determines that the user is feeling anxious. The server analyzes the received information, determines the depth and extent of the flooding, and sends a real-time notification to other residents in the area. Upon receiving the notification, the device displays a reassuring message from the emotion engine along with evacuation route instructions, thereby reducing the user's anxiety.

[0952] This invention not only makes it possible to predict damage caused by inland flooding early and implement prompt countermeasures, but also makes it possible to respond in a way that takes into consideration the emotions of users, thereby promoting safer and more secure evacuation behavior and contributing to ensuring the safety of residents.

[0953] The processing flow will be explained below.

[0954] Step 1:

[0955] The server collects weather data (rainfall, wind speed, humidity, etc.) from the meteorological station at regular intervals.

[0956] Step 2:

[0957] The server collects topographical data (ground elevation, location of drainage facilities, etc.) from the local government database.

[0958] Step 3:

[0959] The weather and topographical data collected by the server is input into the generative artificial intelligence (generative AI).

[0960] Step 4:

[0961] The generative AI analyzes the input data and predicts the risk of inland flooding, outputting the risk level as a number or category.

[0962] Step 5:

[0963] If a user discovers flooding or abnormal water flow at home or in the neighborhood, they can launch the app on their smartphone.

[0964] Step 6:

[0965] The user takes a photo of the problem area using the app and enters comments (e.g., the depth of the flooding, the date and time of the occurrence). The emotion engine also analyzes the user's voice and text comments to detect their emotional state.

[0966] Step 7:

[0967] The device acquires the user's current location information (GPS data) and sends photos, comments, and emotional state information to the server.

[0968] Step 8:

[0969] The server analyzes the photos, comments, and location information received, and uses image recognition technology to determine the depth and extent of the flooding in the photos.

[0970] Step 9:

[0971] The server adjusts the notification content based on the user's emotional state analyzed by the emotion engine. For example, if a user is highly anxious, it adds a detailed explanation or a reassuring message.

[0972] Step 10:

[0973] The server determines the urgency of the danger information based on the analysis results, using criteria such as the depth of flooding, pedestrian traffic, and residential density.

[0974] Step 11:

[0975] The server notifies other residents of information with high urgency on a priority basis in real time.

[0976] Step 12:

[0977] The device displays the received notification to the user, and the emotion engine displays messages that take into account the user's emotional state.

[0978] Step 13:

[0979] The user checks the notification and considers evacuating to a safe location.

[0980] Step 14:

[0981] The device provides users with information on safe evacuation routes and the nearest evacuation shelters, and the emotion engine displays appropriate messages containing encouragement and instructions to reduce anxiety during evacuation.

[0982] Step 15:

[0983] The server will continue to periodically collect new weather data and information from residents, and use generative AI to update risk predictions until the situation improves.

[0984] Example 2

[0985] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0986] Damage caused by inland flooding has a significant impact on the safety of residents and the infrastructure of daily life, especially in urban areas. Conventional systems are inadequate in early prediction of flood risk and prompt notification to residents, making it difficult for residents to take appropriate evacuation actions. In addition, responses do not take into consideration the emotions of residents, making it an issue to reduce psychological stress.

[0987] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0988] In this invention, the server includes means for collecting meteorological data, means for collecting topographical data, means for inputting the collected meteorological data and topographical data into a generating AI and analyzing the risk of inland flooding, means for residents to send photos and information of dangerous areas using a mobile communication terminal, means for analyzing the sent information and identifying location information and risk level, means for notifying other residents of the analyzed risk information in real time, means for providing residents with information on safe evacuation routes and evacuation sites, and means for performing emotion recognition and taking appropriate action based on the results. This enables early prediction of inland flooding risk, rapid emergency notification, and appropriate action that takes into account the emotions of residents.

[0989] "Weather data" refers to weather-related information such as rainfall, wind speed, and humidity collected from meteorological agencies and related organizations.

[0990] "Topographic data" refers to information about the terrain, such as the elevation of the ground and the location of drainage facilities, collected from local government databases, etc.

[0991] "Generative artificial intelligence" is an AI technology that analyzes and makes predictions based on large amounts of data, and specifically outputs the risk level of inland flooding as a number or category.

[0992] A "mobile communication terminal" is an electronic device with communication functions that can be used while on the move, such as a smartphone or tablet.

[0993] "Emotion recognition" is a technology that analyzes and detects a user's emotional state from their voice, text, etc.

[0994] "Analysis" is the process of identifying the risk and danger of inland flooding based on collected meteorological and topographical data, as well as information sent by users.

[0995] "Real-time notification" means sending collected and analyzed information to residents immediately and sharing the information promptly.

[0996] An "evacuation route" is a recommended route for evacuating from a dangerous area to a safe place.

[0997] An "evacuation site" is a place where residents can temporarily evacuate to ensure their safety in the event of a disaster.

[0998] I understand. Below is the "Mode for carrying out the invention."

[0999] This invention combines emotion recognition with a system that predicts the risk of inland flooding through the collection and analysis of meteorological and topographical data, and allows residents to share information about dangerous areas via mobile communication devices. The system consists of three main components: a server, a device, and a user.

[1000] The server performs the following functions. First, it periodically collects weather data such as rainfall, wind speed, and humidity using the meteorological bureau's API. It also obtains topographical data such as ground elevation and the location of drainage facilities from the local government's database and stores this data in the database. The collected weather and topographical data is input into a generative artificial intelligence (e.g., GPT-4) using a Python script, which outputs the risk level of inland flooding as a number or category. The results of this analysis are further analyzed within the system and notified to residents in real time. Furthermore, an emotion recognition engine is used to adjust the content of notifications based on the user's emotional state, and appropriate responses are taken.

[1001] The device mainly refers to a mobile communication device (such as a smartphone or tablet) and performs the following functions: When a user discovers a flooded area or an abnormal water flow, they can launch the app to take a photo and enter a comment and emotional state (text or voice). The user's location information is obtained using the device's GPS function, and all information is sent to the server. The received notification is displayed on the device as a pop-up message or alert, and a message of reassurance based on emotion recognition and evacuation route instructions are provided.

[1002] Users are responsible for reporting any abnormal water flow or flooding they notice in their daily lives through the app. This reporting involves taking photos and entering comments, and also inputting emotional state information, which is used for analysis by the system's emotion recognition engine. By receiving notifications, users can take prompt and appropriate evacuation action.

[1003] As a concrete example, when a heavy rain warning is issued, the server quickly retrieves the data and analyzes it using generative AI (e.g., GPT-4). The generative AI predicts that there is an increased risk of inland flooding in certain low-lying areas of the city. At the same time, a user sends a photo of flooded roads in that area and a comment to the server via an app. The device inputs the user's voice and comments into an emotion recognition engine and determines that the user is feeling anxious. The server analyzes the received information, determines the depth and extent of the flooding, and sends a real-time notification to other residents in the area. The device that receives the notification displays a reassuring message and evacuation route instructions using the emotion recognition engine, thereby alleviating the user's anxiety. This system not only makes it possible to predict damage caused by inland flooding early and implement prompt countermeasures, but also to respond in a way that takes the user's emotions into consideration.

[1004] Example prompt sentence:

[1005] Input prompt:

[1006] "In response to this heavy rain warning, please tell us the procedures for predicting the risk of inland flooding in low-lying areas of the city and encouraging residents to take appropriate measures."

[1007] Example expected output:

[1008] "When a heavy rain warning is issued, the server obtains meteorological and topographical data and inputs it into the generation AI. The generation AI identifies areas at high risk of inland flooding and analyzes this together with flooding information sent by users via the app. The server determines the level of urgency based on the analysis results and sends notifications to residents in real time. The device displays the notification content and provides a reassuring message using an emotion recognition engine, as well as evacuation route instructions."

[1009] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1010] Step 1: Meteorological data collection

[1011] A server collects weather data.

[1012] Input: Meteorological Agency API endpoint

[1013] Data processing: Obtaining data such as rainfall, wind speed, humidity, etc. from the meteorological bureau and converting it into the required format.

[1014] Output: Transformed weather data (rainfall, wind speed, humidity)

[1015] Specific operation: The server periodically sends requests to the weather bureau's API, receives the weather data returned in response in JSON format, and stores it in a database.

[1016] Step 2: Collect terrain data

[1017] The server collects the terrain data.

[1018] Input: API endpoint of the city's database

[1019] Data processing: Obtain topographical data such as ground elevation and drainage facility locations from the municipality's database and convert it into the required format.

[1020] Output: Converted terrain data (ground elevation, drainage facility locations)

[1021] Specific operation: The server sends a request to the local government database, receives the returned terrain data in JSON format, and stores it in the database.

[1022] Step 3: Data analysis

[1023] The server inputs meteorological and topographical data into the generation AI, which then analyzes the risk level of inland flooding.

[1024] Input: Weather data, terrain data

[1025] Data calculation: Meteorological and topographical data are input into a generating AI (e.g., GPT-4), and the risk level of inland flooding is output as a number or category.

[1026] Output: Risk level of inland flooding (numerical value, category)

[1027] Specific operation: The server runs a Python script, inputs meteorological and topographical data into the generation AI, and the generation AI predicts the risk level of inland flooding based on this data.

[1028] Step 4: Collect user information

[1029] The user reports information about dangerous locations using a mobile communication terminal.

[1030] Input: Photo, Comment, Emotional State (voice or text)

[1031] Data processing: Converts the information acquired by the terminal into a format that can be sent to the server.

[1032] Output: Data ready to send (photos, comments, emotional state)

[1033] Specific operation: The user launches the app, takes a photo of the dangerous area, enters a comment, and then performs voice input.

[1034] Step 5: Send data

[1035] The device acquires the user's current location information (GPS data) and sends photos, comments, and emotional state to the server.

[1036] Input: GPS data, photos, comments, emotional state

[1037] Data calculation: data integration and preparation for transmission

[1038] Output: Integrated data (GPS data, photos, comments, emotional state)

[1039] Specific operation: The device obtains location information using the GPS function and uploads all information to the server.

[1040] Step 6: Information Analysis

[1041] The server analyzes the received data.

[1042] Input: photos, comments, GPS data, emotional state

[1043] Data calculation: Image recognition technology (e.g., OpenCV and TensorFlow) is used to determine the depth and extent of flooding in the photo. An emotion engine is also used to analyze the user's emotional state.

[1044] Output: Analysis results (flood depth, spread, emotional state)

[1045] How it works: The server uses image recognition technology to analyze the received photos and determine the depth and extent of the flooding. At the same time, the emotion engine analyzes the user's emotional state.

[1046] Step 7: Real-time notifications

[1047] The server determines the urgency of the danger information and notifies residents in real time.

[1048] Input: Analysis results (flood depth, spread, emotional state)

[1049] Data calculation: Determining notification priority and generating notification content

[1050] Output: Emergency notification message

[1051] Specific operation: The server determines the urgency based on the analysis results, generates notification content, and sends notifications to other residents with priority.

[1052] Step 8: Provide safety measures

[1053] The terminal displays the received notification to the user.

[1054] Input: Emergency notification message

[1055] Data processing: Converting notification messages into display formats

[1056] Output: A notification message that is displayed to the user.

[1057] Specific operation: The device displays the notification as a pop-up message and provides a reassuring message or evacuation route instructions based on the results of emotion recognition.

[1058] (Application example 2)

[1059] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1060] Existing inland flood forecasting systems can predict risk by analyzing meteorological and topographical data, but they do not provide real-time information that takes into account residents' emotional state. As a result, residents are often unable to take appropriate action when they receive danger information and end up feeling anxious. Furthermore, because individual responses based on emotional state are not provided, it is difficult to encourage safe evacuation behavior.

[1061] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1062] In this invention, the server includes means for collecting weather data, means for collecting topographical data, means for inputting the collected weather data and topographical data into a generating AI and analyzing the risk of inland flooding, means for residents to send photos and information of dangerous areas using a smartphone app, means for analyzing the sent information and identifying location information and risk level, means for notifying other residents of the analyzed risk information in real time, means for providing residents with information on safe evacuation routes and evacuation sites, and means for analyzing the user's emotional state using an emotion engine and responding in a way that takes emotions into consideration. This enables the provision of information to residents quickly and in a way that takes emotions into consideration, thereby promoting safe evacuation behavior.

[1063] "Weather data" refers to numerical values ​​and information about weather, such as rainfall, wind speed, and humidity, collected from meteorological agencies and weather observation institutions.

[1064] "Topographic data" refers to numerical values ​​and information about the terrain, such as ground elevation and the location of drainage facilities, collected from local governments and surveying agencies.

[1065] "Generative AI" refers to an AI model designed to analyze the risk of inland flooding based on meteorological and topographical data.

[1066] "Inland flooding" is a phenomenon in which sewerage and drainage facilities are temporarily unable to handle the flow of water due to heavy rain or flooding, increasing the risk of flooding in urban areas and buildings.

[1067] "Means for analyzing risk" refers to the process of using collected data to evaluate the risk level of inland flooding numerically or in categories.

[1068] "Smartphone app" refers to application software that users can use on their smartphones, including tools for sending photos and information about dangerous areas.

[1069] "Means for analyzing submitted information" refers to the process of analyzing data such as photos, comments, and location information submitted by users to identify the situation and risk of inland flooding.

[1070] "Location information" refers to information that indicates a geographic location based on GPS data or a user's current location.

[1071] "Risk level" is an indicator that shows the possibility of inland flooding and the degree of damage it would cause, including the level of urgency.

[1072] "Means of real-time notification" refers to the process of promptly communicating analyzed danger information to other residents at the same time.

[1073] "Safe evacuation routes" refers to information that indicates routes to travel from areas experiencing inland flooding to evacuation shelters or safe locations.

[1074] An "evacuation site" is a facility or area designated as a temporary evacuation site for residents in the event of a disaster such as inland flooding.

[1075] An "emotion engine" is software or a system that analyzes a user's voice and text comments, detects their emotional state, and responds appropriately.

[1076] This invention combines an emotion engine with a system that predicts the risk of inland flooding through the collection and analysis of meteorological and topographical data, and allows residents to share information about dangerous areas via a smartphone app. This system is implemented in the following form.

[1077] The server periodically collects meteorological data (rainfall, wind speed, humidity, etc.) from meteorological stations and topographical data (ground elevation, location of drainage facilities, etc.) from local government databases. The collected meteorological and topographical data is input into a generative artificial intelligence (generative AI model), which outputs the risk level of inland flooding as a number or category.

[1078] When a user discovers flooding or abnormal water flow at home or in their neighborhood, they launch the app on their smartphone, take a photo of the dangerous area, and enter comments (e.g., depth of flooding, date and time of occurrence). In addition, the emotion engine analyzes the user's voice and text comments to detect their emotional state (e.g., anxiety, fear, panic). This information is sent to the server along with GPS data.

[1079] The server uses image recognition technology to analyze the received photos, comments, and location information to determine the depth and extent of flooding. During this process, an emotion engine analyzes the user's emotional state and adjusts the necessary measures and notification content based on that. For example, if the user expresses strong anxiety, the server will prepare a detailed, reassuring notification.

[1080] The server determines the urgency of the danger information based on the analysis results. Criteria for urgency include the depth of flooding, pedestrian traffic, and residential density. High-urgency information is given priority and notified to other residents in real time. This notification includes a message of reassurance generated by an emotion engine, and also provides information on safe evacuation routes and the nearest evacuation shelters.

[1081] As a specific example, when a heavy rain warning is issued, the server quickly retrieves the data and analyzes it using the generation AI. The generation AI predicts that there is an increased risk of inland flooding in certain low-lying areas of the city. At the same time, a user sends a photo of flooded roads in that area to the server via the app. The device inputs the user's voice and comments into the emotion engine and determines that the user is feeling anxious. The server analyzes the received information, determines the depth and extent of the flooding, and sends a real-time notification to other residents in the area. Upon receiving the notification, the device displays a reassuring message from the emotion engine along with evacuation route instructions, thereby reducing the user's anxiety.

[1082] Example prompt sentence:

[1083] "There is currently a very high risk of flooding. Please remain calm and evacuate to the nearest evacuation shelter."

[1084] "The risk of flooding is very high. Please remain calm and evacuate."

[1085] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1086] Step 1:

[1087] Meteorological and terrain data collection

[1088] The server periodically collects meteorological data such as rainfall, wind speed, and humidity from the meteorological bureau. It also obtains topographical data such as ground elevation and the location of drainage facilities from the local government database. The input is the API response from the meteorological bureau and the local government database, and the output is the formatted data required for analysis.

[1089] Step 2:

[1090] Data analysis and risk prediction

[1091] The server inputs the collected weather and topographical data into a generative artificial intelligence (generative AI model) and outputs the risk level of inland flooding as a number or category. The input is preformatted weather and topographical data, and the output is the risk level assessment result. Specifically, a machine learning algorithm is used to estimate the degree of danger and quantify the risk level.

[1092] Step 3:

[1093] User submission of risk information

[1094] When a user discovers flooding or abnormal water flow at home or in their neighborhood, they launch the smartphone app and take a photo of the dangerous area. They then enter comments such as the depth of the flooding and the date and time of the occurrence. The emotion engine then analyzes the user's voice and text comments to detect their emotional state. The inputs are the photos, comments, voice data, and GPS data, and the output is a consistent record of these data.

[1095] Step 4:

[1096] Analysis of risk information

[1097] The server receives photos, comments, and location information sent by users. It then uses image recognition technology to determine the depth and extent of flooding and analyzes comments to extract detailed information. The input is the data sent by users, and the output is the analysis results, such as information on the depth and extent of flooding.

[1098] Step 5:

[1099] Emotional state analysis and response adjustment

[1100] The server adjusts the necessary measures and notification content based on the user's emotional state analyzed by the emotion engine. For example, if the user shows strong anxiety, the notification content will be detailed and reassuring. The input is the emotional state evaluation result by the emotion engine, and the output is the adjusted notification content.

[1101] Step 6:

[1102] Urgency assessment and notification

[1103] The server determines the urgency of the danger information based on the analysis results. Criteria for urgency include the depth of flooding, foot traffic, and residential density. Information with a high urgency is given priority and notified to other residents in real time. The input is the analyzed danger information, and the output is notification information based on the urgency.

[1104] Step 7:

[1105] Providing evacuation information

[1106] The server provides residents with information on safe evacuation routes and evacuation locations. This includes messages based on the emotion engine that create a sense of security, encouraging users to evacuate safely. The input is danger information and the results of an evaluation of the user's emotional state, and the output is information on evacuation routes and evacuation locations, along with messages providing that information.

[1107] Step 8:

[1108] Displaying notifications and encouraging evacuation

[1109] The device displays the received notification to the user and provides detailed information such as warning messages and maps of dangerous areas. The emotion engine displays messages that take the user's emotions into consideration, allowing the user to consider evacuating to a safe place. The input is notifications and messages from the server, and the output is prompting the user to take action.

[1110] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1111] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1112] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1113] [Fourth embodiment]

[1114] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1115] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1116] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1117] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1118] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1119] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1120] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1121] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1122] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1123] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1124] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1125] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1126] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1127] The present invention relates to a system that collects meteorological and topographical data, uses that data to generate AI that analyzes the risk of inland flooding, and allows residents to share information about dangerous areas via a smartphone app.

[1128] Data collection and analysis

[1129] The server periodically collects weather data (e.g., rainfall, wind speed, humidity) from the weather station.

[1130] The server collects topographical data (e.g., ground elevation, location of drainage facilities) from the municipal database.

[1131] The weather and topographical data collected by the server is input into the artificial intelligence (AI), which analyzes this data and outputs the risk level of inland flooding as a number or category.

[1132] Collection and transmission of risk information

[1133] If a user discovers flooding or abnormal water flow at home or in the neighborhood, they can launch the app on their smartphone.

[1134] The user takes a photo of the problem area using the app, enters a comment (e.g., depth of flooding, date and time of occurrence), and presses the send button.

[1135] The device acquires the user's current location information (GPS data) and sends it to the server along with the photo and comment.

[1136] Information analysis and real-time notifications

[1137] The server analyzes the received photos, comments, and location information, using image recognition technology to determine the depth and extent of flooding in the photos.

[1138] The server then uses the analysis results to determine the urgency of the danger information and organizes it. Criteria for urgency include the depth of flooding, pedestrian traffic, and residential density.

[1139] The server will prioritize and notify other residents of information of high urgency in real time.

[1140] Providing safety measures

[1141] The device displays the received notification to the user, providing detailed information such as warning messages and maps of dangerous areas.

[1142] Users can check the notification and consider evacuating to a safe location.

[1143] The device provides the user with information on safe evacuation routes and the nearest evacuation shelters.

[1144] Specific examples

[1145] For example, when a heavy rain warning is issued by the Meteorological Agency, the server quickly retrieves the data and analyzes it with the generation AI. The generation AI predicts that there is an increased risk of inland flooding in specific low-lying areas of the city. At the same time, a user sends a photo of a flooded road in that area to the server via the app. The server analyzes the received information, determines the depth and extent of the flooding, and sends a real-time notification to other residents in the area. Upon receiving the notification, the user quickly begins evacuation and reaches a safe destination by following the evacuation route instructions provided by the app.

[1146] This invention makes it possible to predict damage caused by inland flooding early and take prompt measures, thereby ensuring the safety of residents. This system functions as a powerful countermeasure against the risk of inland flooding in urban areas.

[1147] The processing flow will be explained below.

[1148] Step 1:

[1149] The server collects weather data (rainfall, wind speed, humidity, etc.) from the meteorological station at regular intervals.

[1150] Step 2:

[1151] The server collects topographical data (ground elevation, location of drainage facilities, etc.) from the local government database.

[1152] Step 3:

[1153] The weather and topographical data collected by the server is input into the generative artificial intelligence (generative AI).

[1154] Step 4:

[1155] The generative AI analyzes the input data and predicts the risk of inland flooding, outputting the risk level as a number or category.

[1156] Step 5:

[1157] If a user discovers flooding or abnormal water flow at home or in the neighborhood, they can launch the app on their smartphone.

[1158] Step 6:

[1159] The user takes a photo of the problem area using the app and enters comments (e.g., depth of flooding, date and time of occurrence).

[1160] Step 7:

[1161] The device acquires the user's current location information (GPS data) and sends it to the server along with the photo and comment.

[1162] Step 8:

[1163] The server analyzes the photos, comments, and location information received, and uses image recognition technology to determine the depth and extent of flooding in the photos.

[1164] Step 9:

[1165] The server determines the urgency of the danger information based on the analysis results, including the depth of flooding, the number of people moving about, and the density of residential areas.

[1166] Step 10:

[1167] The server will prioritize and notify other residents of information of high urgency in real time.

[1168] Step 11:

[1169] The device displays the received notification to the user, providing detailed information such as warning messages and maps of dangerous areas.

[1170] Step 12:

[1171] The user checks the notification and considers evacuating to a safe location.

[1172] Step 13:

[1173] The device provides the user with information on safe evacuation routes and the nearest evacuation shelters.

[1174] Step 14:

[1175] The server will continue to periodically collect new weather data and information from residents, and use generative AI to update risk predictions until the situation improves.

[1176] Example 1

[1177] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1178] Conventional inland flooding prevention systems have had difficulty quickly and accurately predicting flood risk and notifying residents of appropriate information in real time. This has prevented residents from evacuating safely and has prevented damage from being minimized. There has also been a lack of easy ways for residents to report risk information such as flooding. The purpose of this invention is to solve these problems and provide a more efficient and reliable inland flooding prediction and risk management system.

[1179] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1180] In this invention, the server includes means for collecting meteorological data, means for collecting topographical data, means for inputting the collected meteorological data and topographical data into a generating AI and analyzing the risk of inland flooding, means for residents to send photos and information of dangerous areas using mobile communication terminals, means for analyzing the sent information and identifying location information and risk level, means for notifying other residents of the analyzed risk information in real time, and means for providing residents with information on safe evacuation routes and evacuation sites. This enables fast and accurate prediction of inland flooding risks, sharing risk information among residents, and real-time evacuation instructions.

[1181] "Weather data" refers to numerical values ​​and information related to meteorological phenomena, such as rainfall, wind speed, and humidity.

[1182] "Topographic data" refers to numerical values ​​and information about the terrain, such as the elevation of the ground and the location of drainage facilities.

[1183] "Generative artificial intelligence" refers to artificial intelligence technology that analyzes collected data and outputs the risk level of inland flooding as a number or category.

[1184] "Inland flooding" refers to the phenomenon of undrained flooding that occurs in urban and residential areas due to precipitation exceeding drainage capacity.

[1185] "Residents" refers to ordinary people who use this system to share risk information and take evacuation action in the event of a disaster.

[1186] "Mobile communication terminal" refers to a portable communication device such as a smartphone or tablet.

[1187] "Analysis" refers to the act of evaluating and classifying collected data using artificial intelligence and image recognition technology.

[1188] "Danger information" refers to information with a level of urgency related to inland flooding, such as flooding or abnormal water flow.

[1189] "Real-time notification" refers to the act of immediately informing other residents of analyzed danger information.

[1190] An "evacuation route" refers to the optimal route for residents to move to safety in the event of inland flooding.

[1191] An "evacuation site" refers to a place where residents can temporarily ensure safety in the event of inland flooding.

[1192] This invention relates to a system that utilizes meteorological and topographical data, uses generative artificial intelligence (generative AI model) to analyze the risk of inland flooding, and provides appropriate information to residents in real time. This system functions in cooperation with three parties: a server, a terminal, and a user.

[1193] Data collection and analysis

[1194] The server retrieves weather data at a scheduled time. Specifically, it accesses the meteorological agency's API and collects data such as rainfall, wind speed, and humidity. Next, the server retrieves topographical data from the local government's topographical database. This data includes the ground elevation and the location of drainage facilities. The collected weather and topographical data is stored in the database.

[1195] Next, the server inputs the meteorological and topographical data stored in the database into the generative AI model. The generative AI model analyzes this data and outputs the risk level of inland flooding as a number or category (e.g., high risk, medium risk, low risk). The results are managed by the server.

[1196] Collection and transmission of risk information

[1197] When a user discovers flooding or abnormal water flow at home or in their neighborhood, they launch the smartphone app. Using the app's camera function, they take a photo of the problem area and enter a comment. This information includes the depth of the flooding and the date and time of the occurrence. The user's device obtains their current location information (GPS data) and sends an information packet containing the photo and comment to the server.

[1198] Information analysis and real-time notifications

[1199] The server analyzes the photos, comments, and location information it receives. Image recognition technology is used to determine the depth and extent of the flooding in the photos. Based on the analysis results, the server determines the urgency of the danger information and organizes the information. The urgency is determined by factors such as the depth of the flooding, the number of people passing by, and the density of housing. Information with a high level of urgency is prioritized and organized, and the server notifies other residents' devices in real time.

[1200] Providing safety measures

[1201] The device displays the received notification to the user. Detailed information such as warning messages and maps of dangerous areas are also displayed at the same time. The user can check the notification and consider evacuating to a safe location if necessary. The device provides the user with information on safe evacuation routes and the nearest evacuation shelters.

[1202] Specific examples

[1203] For example, when a heavy rainfall warning is issued, the server quickly retrieves the data from the meteorological bureau and analyzes it using a generative AI model. The generative AI model predicts an increased risk of inland flooding in specific low-lying areas of the city. At the same time, a user sends a photo of a flooded road in that area to the server via the app. The server analyzes the received information, determines the depth and extent of the flooding, and sends a real-time notification to other residents in the area. Upon receiving the notification, the user quickly begins evacuation and reaches a safe destination by following the evacuation route instructions provided by the app.

[1204] This system will enable early prediction of damage caused by inland flooding, allowing prompt countermeasures to be taken, and ensuring the safety of residents. It will therefore function as a powerful countermeasure against the risk of inland flooding in urban areas.

[1205] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1206] Program processing steps

[1207] Step 1: Collect weather data

[1208] The server accesses the weather station's API at specified times to obtain weather data such as rainfall, wind speed, and humidity.

[1209] Specific operation: Sends an API request, analyzes the obtained data, and saves it in a database.

[1210] Input: Weather Bureau API endpoint and credentials.

[1211] Output: Latest weather data stored in the database.

[1212] Step 2: Collect terrain data

[1213] The server accesses the local government's terrain database and obtains terrain data such as ground elevation and the location of drainage facilities.

[1214] Specific behavior: Query the required data from the local government database and store the resulting data in a local database.

[1215] Input: Access information and queries to municipal databases.

[1216] Output: Terrain data stored in a database.

[1217] Step 3: Generative AI risk analysis

[1218] The server inputs stored weather and terrain data into a generative AI model.

[1219] Specific operation: Data is input into the generative AI model and analysis begins. After analysis, the risk level of inland flooding is output as a number or category.

[1220] Input: Latest weather and terrain data.

[1221] Output: Risk level of inland flooding (numeric or categorical).

[1222] Step 4: User provides risk information

[1223] If a user discovers flooding or abnormal water flow at home or in the neighborhood, they can launch the app on their smartphone.

[1224] Specific actions: The user takes a photo using the app's camera function, enters a comment, and presses the send button.

[1225] Input: Flood depth, date and time of occurrence, and GPS data.

[1226] Output: Flood information packet sent to the server.

[1227] Step 5: Analyze and locate hazard information

[1228] The server analyzes the photos, comments, and location information received, and uses image recognition technology to determine the depth and extent of flooding in the photos.

[1229] Specific operation: The received data is input into an analysis algorithm to determine the level of danger and location information.

[1230] Input: photos, comments, location.

[1231] Output: Analyzed risk level and specific location information.

[1232] Step 6: Determine the level of urgency and organize the information

[1233] Based on the analysis results, the server determines the urgency of the dangerous information and organizes the information.

[1234] Specific operation: Calculates and prioritizes the level of urgency based on the depth of flooding, the number of people passing by, and the density of housing.

[1235] Input: Parsed risk level and location information.

[1236] Output: List of danger information with urgency level.

[1237] Step 7: Real-time notifications

[1238] The server notifies other residents' devices of highly urgent information in real time.

[1239] Specific operation: Selects information with high urgency and sends warnings to residents' smartphones via the notification system.

[1240] Input: A list of hazard information with urgency ratings.

[1241] Output: Notification message sent to the resident.

[1242] Step 8: Display warnings and provide evacuation information

[1243] The device displays the received notification to the user, providing warning messages and maps of dangerous areas.

[1244] Specific actions: Displaying pop-up notifications, drawing maps, and providing information on safe evacuation routes and nearest evacuation shelters.

[1245] Input: The notification message sent by the server.

[1246] Output: Warning messages and evacuation information displayed to the user.

[1247] keyword

[1248] Generative AI model, prompt sentence

[1249] (Application example 1)

[1250] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1251] Conventional inland flood risk management systems often lack the functionality to provide residents with the latest information in real time and encourage prompt evacuation. Furthermore, they lacked a mechanism for efficiently analyzing risk information sent by users and determining its urgency, making it difficult to provide residents with accurate information when needed. Furthermore, there were technical challenges in identifying the specific depth and extent of flooding using photos and comments sent by users.

[1252] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1253] In this invention, the server includes means for collecting meteorological data, means for collecting topographical data, means for inputting the collected meteorological data and topographical data into a generative AI model and analyzing the risk of inland flooding, means for users to send photos and information of dangerous areas using a mobile device, means for analyzing the sent information and identifying location information and risk level, means for notifying other residents of the analyzed risk information in real time, means for providing residents with information on safe evacuation routes and evacuation sites, means for analyzing photos sent by users using image recognition technology and determining the depth and extent of flooding, and means for determining the urgency of risk information based on the collected analysis information and notifying information with a higher urgency level first. This makes it possible to analyze and notify risk information of inland flooding in real time, and encourage residents to take quick and accurate evacuation action.

[1254] "Weather data" is a general term for information about weather, such as rainfall, wind speed, and humidity, obtained from meteorological stations.

[1255] "Topographical data" is a general term for information about topography obtained from a local government database, such as the elevation of the ground, the location of drainage facilities, etc.

[1256] "Generative artificial intelligence (generative AI)" is an artificial intelligence technology that analyzes the risk of inland flooding based on collected data and outputs the results.

[1257] "Mobile terminal" is a general term for portable electronic devices that users use on a daily basis, such as smartphones and smart glasses.

[1258] "Image recognition technology" refers to technology that analyzes photos sent by users and recognizes specific features and patterns.

[1259] "Flood depth" refers to the depth of flooded water.

[1260] "Urgency" is a standard for evaluating the seriousness and immediacy of dangerous information.

[1261] "Real-time notification" refers to the function of instantly sending analyzed information to other users.

[1262] An "evacuation route" is the optimal route for residents to evacuate safely.

[1263] An "evacuation site" is a place designated for residents to evacuate to in the event of a disaster.

[1264] "Location information" refers to a geographical location identified using GPS or other means.

[1265] The present invention relates to a system that collects meteorological and topographical data, uses that data to generate an AI model that analyzes the risk of inland flooding, and allows residents to share information about dangerous areas via mobile devices. This system is implemented as follows:

[1266] First, the server periodically collects weather data (e.g., rainfall, wind speed, humidity) from the meteorological station, and terrain data (e.g., ground elevation, location of drainage facilities) from the local government database. To retrieve the weather and terrain data, the Python requests library can be used.

[1267] The server then inputs the collected weather and topographical data into a generative AI model (e.g., a model created with TensorFlow). The generative AI model uses this data to analyze the risk level of inland flooding numerically or categorically, and outputs the results.

[1268] When a user discovers flooding or an abnormal water flow, they launch the app on their mobile device. They use the app to take a photo of the dangerous area and enter comments (e.g., the depth of the flooding, the date and time of the occurrence). The app also obtains the user's current location information (GPS data) and sends it to the server along with the photo and comment.

[1269] The server analyzes the received photos, comments, and location information. This analysis uses image recognition technology (e.g., image analysis using OpenCV and TensorFlow) to determine the depth and extent of flooding in the photos. Based on the analyzed information, the urgency of the danger information is determined. Criteria for the urgency include the depth of flooding, pedestrian traffic, and residential density.

[1270] The server uses the analysis results to notify other residents in real time, prioritizing information of high urgency. This notification is done using a web framework such as Flask, which organizes the information and distributes it to residents.

[1271] The device displays the received notification to the user and provides detailed information such as warning messages and maps of dangerous areas. The device also provides the user with information on safe evacuation routes and the nearest evacuation shelters, allowing the user to quickly begin evacuation and evacuate to a safe location.

[1272] For example, when heavy rain occurs, the following prompt is entered:

[1273] User: This is XX Street in Chuo Ward, and the road is flooded to over 1 meter.

[1274] Along with this prompt, the user sends a flooded photo they have taken, which is then analyzed by the server and immediately notified by other residents, encouraging them to take prompt evacuation action.

[1275] This system acts as a powerful countermeasure against the risk of inland flooding in urban areas and provides an efficient way to ensure the safety of residents.

[1276] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1277] Step 1:

[1278] The server periodically collects weather data (rainfall, wind speed, humidity) from the meteorological station. Specifically, it retrieves data from the API using the Python requests library. In this case, it sends an API request as input and retrieves weather data in JSON format as output.

[1279] Step 2:

[1280] The server collects terrain data (ground elevation, location of drainage facilities) from the local government database. It also retrieves data from the API using the requests library. In this case, it sends an API request as input and gets terrain data in JSON format as output.

[1281] Step 3:

[1282] The server inputs the collected weather and topographical data into a generative artificial intelligence (generative AI model). Specifically, it uses a TensorFlow model to analyze the risk of inland flooding. The weather and topographical data are preprocessed as input and then input into the TensorFlow model. The output is the risk level of inland flooding, expressed as a number or category.

[1283] Step 4:

[1284] When a user discovers flooding or an abnormal water flow, they launch the app on their mobile device. Using the app, the user takes a photo of the dangerous area and enters comments (depth of flooding, date and time of occurrence). The app obtains the user's current location information (GPS data) and sends the photo, comment, and location information to the server.

[1285] Step 5:

[1286] The server analyzes the received photos, comments, and location information. This is done using image recognition technology (e.g., image analysis using OpenCV and TensorFlow). The server analyzes the photos sent as input and determines the depth and extent of the flooding. The analysis results are then stored in a database as output.

[1287] Step 6:

[1288] The server determines the urgency of the danger information based on the analysis results. Specifically, it evaluates the urgency using indicators such as flood depth, pedestrian traffic, and residential density. In this case, it uses the analysis results as input to quantify the urgency. As output, it generates data that prioritizes notifications of information with a high urgency.

[1289] Step 7:

[1290] The server notifies other residents in real time, prioritizing information of high urgency. For this purpose, it uses web frameworks such as Flask to deliver notifications. At this time, it uses information of high urgency as input and generates notification messages as output.

[1291] Step 8:

[1292] The device displays the received notification to the user, providing the user with detailed information such as warning messages and maps of dangerous areas. At this time, the device receives the notification message as input and displays it on the user interface, allowing the user to immediately understand the situation.

[1293] Step 9:

[1294] The device provides the user with information on safe evacuation routes and the nearest evacuation shelters. Specifically, it uses an algorithm to calculate the evacuation route and presents the optimal route. In this case, the current location and evacuation shelter information are used as input, and the optimal evacuation route is presented as output.

[1295] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1296] This invention combines an emotion engine with a system that predicts the risk of inland flooding through the collection and analysis of meteorological and topographical data, and allows residents to share information about dangerous areas via a smartphone app. This emotion engine recognizes the user's emotions and takes appropriate action.

[1297] Data collection and analysis

[1298] The server periodically collects weather data (rainfall, wind speed, humidity, etc.) from the weather station.

[1299] The server collects topographical data (ground elevation, location of drainage facilities, etc.) from the local government database.

[1300] The weather and topographical data collected by the server is input into the artificial intelligence (AI), which analyzes this data and outputs the risk level of inland flooding as a number or category.

[1301] Collection and transmission of user information

[1302] If a user discovers flooding or abnormal water flow at home or in the neighborhood, they can launch the app on their smartphone.

[1303] Users take photos of dangerous areas using the app and enter comments (e.g., flood depth, date and time of occurrence). The emotion engine then analyzes the user's voice and text comments to detect their emotional state.

[1304] The device acquires the user's current location information (GPS data) and sends emotional state information along with photos and comments to the server.

[1305] Information analysis and real-time notifications

[1306] The server analyzes the photos, comments, and location information received, and uses image recognition technology to determine the depth and extent of flooding in the photos.

[1307] The server adjusts the necessary measures and notification content based on the user's emotional state analyzed by the emotion engine. For example, if the user is showing strong anxiety, the notification content will be detailed and reassuring.

[1308] The server determines the urgency of the danger information based on the analysis results, including the depth of flooding, the number of people moving about, and the density of residential areas.

[1309] The server will prioritize and notify other residents of information of high urgency in real time.

[1310] Providing safety measures

[1311] The device displays the received notification to the user, providing detailed information such as warning messages and maps of dangerous areas. The emotion engine displays messages that take the user's emotions into consideration.

[1312] Users can check the notification and consider evacuating to a safe location.

[1313] The device provides users with information on safe evacuation routes and the nearest evacuation shelters, and the emotion engine displays appropriate messages containing encouragement and instructions to reduce the user's anxiety during evacuation.

[1314] Specific examples

[1315] For example, when a heavy rain warning is issued by the Meteorological Agency, the server quickly retrieves the data and analyzes it using the generation AI. The generation AI predicts that there is an increased risk of inland flooding in certain low-lying areas of the city. At the same time, a user sends a photo of a flooded road in that area to the server via the app. The device inputs the user's voice and comments into the emotion engine and determines that the user is feeling anxious. The server analyzes the received information, determines the depth and extent of the flooding, and sends a real-time notification to other residents in the area. Upon receiving the notification, the device displays a reassuring message from the emotion engine along with evacuation route instructions, thereby reducing the user's anxiety.

[1316] This invention not only makes it possible to predict damage caused by inland flooding early and implement prompt countermeasures, but also makes it possible to respond in a way that takes into consideration the emotions of users, thereby promoting safer and more secure evacuation behavior and contributing to ensuring the safety of residents.

[1317] The processing flow will be explained below.

[1318] Step 1:

[1319] The server collects weather data (rainfall, wind speed, humidity, etc.) from the meteorological station at regular intervals.

[1320] Step 2:

[1321] The server collects topographical data (ground elevation, location of drainage facilities, etc.) from the local government database.

[1322] Step 3:

[1323] The weather and topographical data collected by the server is input into the generative artificial intelligence (generative AI).

[1324] Step 4:

[1325] The generative AI analyzes the input data and predicts the risk of inland flooding, outputting the risk level as a number or category.

[1326] Step 5:

[1327] If a user discovers flooding or abnormal water flow at home or in the neighborhood, they can launch the app on their smartphone.

[1328] Step 6:

[1329] The user takes a photo of the problem area using the app and enters comments (e.g., the depth of the flooding, the date and time of the occurrence). The emotion engine also analyzes the user's voice and text comments to detect their emotional state.

[1330] Step 7:

[1331] The device acquires the user's current location information (GPS data) and sends photos, comments, and emotional state information to the server.

[1332] Step 8:

[1333] The server analyzes the photos, comments, and location information received, and uses image recognition technology to determine the depth and extent of the flooding in the photos.

[1334] Step 9:

[1335] The server adjusts the notification content based on the user's emotional state analyzed by the emotion engine. For example, if a user is highly anxious, it adds a detailed explanation or a reassuring message.

[1336] Step 10:

[1337] The server determines the urgency of the danger information based on the analysis results, using criteria such as the depth of flooding, pedestrian traffic, and residential density.

[1338] Step 11:

[1339] The server notifies other residents of information with high urgency on a priority basis in real time.

[1340] Step 12:

[1341] The device displays the received notification to the user, and the emotion engine displays messages that take into account the user's emotional state.

[1342] Step 13:

[1343] The user checks the notification and considers evacuating to a safe location.

[1344] Step 14:

[1345] The device provides users with information on safe evacuation routes and the nearest evacuation shelters, and the emotion engine displays appropriate messages containing encouragement and instructions to reduce anxiety during evacuation.

[1346] Step 15:

[1347] The server will continue to periodically collect new weather data and information from residents, and use generative AI to update risk predictions until the situation improves.

[1348] Example 2

[1349] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1350] Damage caused by inland flooding has a significant impact on the safety of residents and the infrastructure of daily life, especially in urban areas. Conventional systems are inadequate in early prediction of flood risk and prompt notification to residents, making it difficult for residents to take appropriate evacuation actions. In addition, responses do not take into consideration the emotions of residents, making it an issue to reduce psychological stress.

[1351] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1352] In this invention, the server includes means for collecting meteorological data, means for collecting topographical data, means for inputting the collected meteorological data and topographical data into a generating AI and analyzing the risk of inland flooding, means for residents to send photos and information of dangerous areas using a mobile communication terminal, means for analyzing the sent information and identifying location information and risk level, means for notifying other residents of the analyzed risk information in real time, means for providing residents with information on safe evacuation routes and evacuation sites, and means for performing emotion recognition and taking appropriate action based on the results. This enables early prediction of inland flooding risk, rapid emergency notification, and appropriate action that takes into account the emotions of residents.

[1353] "Weather data" refers to weather-related information such as rainfall, wind speed, and humidity collected from meteorological agencies and related organizations.

[1354] "Topographic data" refers to information about the terrain, such as the elevation of the ground and the location of drainage facilities, collected from local government databases, etc.

[1355] "Generative artificial intelligence" is an AI technology that analyzes and makes predictions based on large amounts of data, and specifically outputs the risk level of inland flooding as a number or category.

[1356] A "mobile communication terminal" is an electronic device with communication functions that can be used while on the move, such as a smartphone or tablet.

[1357] "Emotion recognition" is a technology that analyzes and detects a user's emotional state from their voice, text, etc.

[1358] "Analysis" is the process of identifying the risk and danger of inland flooding based on collected meteorological and topographical data, as well as information sent by users.

[1359] "Real-time notification" means sending collected and analyzed information to residents immediately and sharing the information promptly.

[1360] An "evacuation route" is a recommended route for evacuating from a dangerous area to a safe place.

[1361] An "evacuation site" is a place where residents can temporarily evacuate to ensure their safety in the event of a disaster.

[1362] I understand. Below is the "Mode for carrying out the invention."

[1363] This invention combines emotion recognition with a system that predicts the risk of inland flooding through the collection and analysis of meteorological and topographical data, and allows residents to share information about dangerous areas via mobile communication devices. The system consists of three main components: a server, a device, and a user.

[1364] The server performs the following functions. First, it periodically collects weather data such as rainfall, wind speed, and humidity using the meteorological bureau's API. It also obtains topographical data such as ground elevation and the location of drainage facilities from the local government's database and stores this data in the database. The collected weather and topographical data is input into a generative artificial intelligence (e.g., GPT-4) using a Python script, which outputs the risk level of inland flooding as a number or category. The results of this analysis are further analyzed within the system and notified to residents in real time. Furthermore, an emotion recognition engine is used to adjust the content of notifications based on the user's emotional state, and appropriate responses are taken.

[1365] The device mainly refers to a mobile communication device (such as a smartphone or tablet) and performs the following functions: When a user discovers a flooded area or an abnormal water flow, they can launch the app to take a photo and enter a comment and emotional state (text or voice). The user's location information is obtained using the device's GPS function, and all information is sent to the server. The received notification is displayed on the device as a pop-up message or alert, and a message of reassurance based on emotion recognition and evacuation route instructions are provided.

[1366] Users are responsible for reporting any abnormal water flow or flooding they notice in their daily lives through the app. This reporting involves taking photos and entering comments, and also inputting emotional state information, which is used for analysis by the system's emotion recognition engine. By receiving notifications, users can take prompt and appropriate evacuation action.

[1367] As a concrete example, when a heavy rain warning is issued, the server quickly retrieves the data and analyzes it using generative AI (e.g., GPT-4). The generative AI predicts that there is an increased risk of inland flooding in certain low-lying areas of the city. At the same time, a user sends a photo of flooded roads in that area and a comment to the server via an app. The device inputs the user's voice and comments into an emotion recognition engine and determines that the user is feeling anxious. The server analyzes the received information, determines the depth and extent of the flooding, and sends a real-time notification to other residents in the area. The device that receives the notification displays a reassuring message and evacuation route instructions using the emotion recognition engine, thereby alleviating the user's anxiety. This system not only makes it possible to predict damage caused by inland flooding early and implement prompt countermeasures, but also to respond in a way that takes the user's emotions into consideration.

[1368] Example prompt sentence:

[1369] Input prompt:

[1370] "In response to this heavy rain warning, please tell us the procedures for predicting the risk of inland flooding in low-lying areas of the city and encouraging residents to take appropriate measures."

[1371] Example expected output:

[1372] "When a heavy rain warning is issued, the server obtains meteorological and topographical data and inputs it into the generation AI. The generation AI identifies areas at high risk of inland flooding and analyzes this together with flooding information sent by users via the app. The server determines the level of urgency based on the analysis results and sends notifications to residents in real time. The device displays the notification content and provides a reassuring message using an emotion recognition engine, as well as evacuation route instructions."

[1373] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1374] Step 1: Meteorological data collection

[1375] A server collects weather data.

[1376] Input: Meteorological Agency API endpoint

[1377] Data processing: Obtaining data such as rainfall, wind speed, humidity, etc. from the meteorological bureau and converting it into the required format.

[1378] Output: Transformed weather data (rainfall, wind speed, humidity)

[1379] Specific operation: The server periodically sends requests to the weather bureau's API, receives the weather data returned in response in JSON format, and stores it in a database.

[1380] Step 2: Collect terrain data

[1381] The server collects the terrain data.

[1382] Input: API endpoint of the city's database

[1383] Data processing: Obtain topographical data such as ground elevation and drainage facility locations from the municipality's database and convert it into the required format.

[1384] Output: Converted terrain data (ground elevation, drainage facility locations)

[1385] Specific operation: The server sends a request to the local government database, receives the returned terrain data in JSON format, and stores it in the database.

[1386] Step 3: Data analysis

[1387] The server inputs meteorological and topographical data into the generation AI, which then analyzes the risk level of inland flooding.

[1388] Input: Weather data, terrain data

[1389] Data calculation: Meteorological and topographical data are input into a generating AI (e.g., GPT-4), and the risk level of inland flooding is output as a number or category.

[1390] Output: Risk level of inland flooding (numerical value, category)

[1391] Specific operation: The server runs a Python script, inputs meteorological and topographical data into the generation AI, and the generation AI predicts the risk level of inland flooding based on this data.

[1392] Step 4: Collect user information

[1393] The user reports information about dangerous locations using a mobile communication terminal.

[1394] Input: Photo, Comment, Emotional State (voice or text)

[1395] Data processing: Converts the information acquired by the terminal into a format that can be sent to the server.

[1396] Output: Data ready to send (photos, comments, emotional state)

[1397] Specific operation: The user launches the app, takes a photo of the dangerous area, enters a comment, and then performs voice input.

[1398] Step 5: Send data

[1399] The device acquires the user's current location information (GPS data) and sends photos, comments, and emotional state to the server.

[1400] Input: GPS data, photos, comments, emotional state

[1401] Data calculation: data integration and preparation for transmission

[1402] Output: Integrated data (GPS data, photos, comments, emotional state)

[1403] Specific operation: The device obtains location information using the GPS function and uploads all information to the server.

[1404] Step 6: Information Analysis

[1405] The server analyzes the received data.

[1406] Input: photos, comments, GPS data, emotional state

[1407] Data calculation: Image recognition technology (e.g., OpenCV and TensorFlow) is used to determine the depth and extent of flooding in the photo. An emotion engine is also used to analyze the user's emotional state.

[1408] Output: Analysis results (flood depth, spread, emotional state)

[1409] How it works: The server uses image recognition technology to analyze the received photos and determine the depth and extent of the flooding. At the same time, the emotion engine analyzes the user's emotional state.

[1410] Step 7: Real-time notifications

[1411] The server determines the urgency of the danger information and notifies residents in real time.

[1412] Input: Analysis results (flood depth, spread, emotional state)

[1413] Data calculation: Determining notification priority and generating notification content

[1414] Output: Emergency notification message

[1415] Specific operation: The server determines the urgency based on the analysis results, generates notification content, and sends notifications to other residents with priority.

[1416] Step 8: Provide safety measures

[1417] The terminal displays the received notification to the user.

[1418] Input: Emergency notification message

[1419] Data processing: Converting notification messages into display formats

[1420] Output: A notification message that is displayed to the user.

[1421] Specific operation: The device displays the notification as a pop-up message and provides a reassuring message or evacuation route instructions based on the results of emotion recognition.

[1422] (Application example 2)

[1423] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1424] Existing inland flood forecasting systems can predict risk by analyzing meteorological and topographical data, but they do not provide real-time information that takes into account residents' emotional state. As a result, residents are often unable to take appropriate action when they receive danger information and end up feeling anxious. Furthermore, because individual responses based on emotional state are not provided, it is difficult to encourage safe evacuation behavior.

[1425] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1426] In this invention, the server includes means for collecting weather data, means for collecting topographical data, means for inputting the collected weather data and topographical data into a generating AI and analyzing the risk of inland flooding, means for residents to send photos and information of dangerous areas using a smartphone app, means for analyzing the sent information and identifying location information and risk level, means for notifying other residents of the analyzed risk information in real time, means for providing residents with information on safe evacuation routes and evacuation sites, and means for analyzing the user's emotional state using an emotion engine and responding in a way that takes emotions into consideration. This enables the provision of information to residents quickly and in a way that takes emotions into consideration, thereby promoting safe evacuation behavior.

[1427] "Weather data" refers to numerical values ​​and information about weather, such as rainfall, wind speed, and humidity, collected from meteorological agencies and weather observation institutions.

[1428] "Topographic data" refers to numerical values ​​and information about the terrain, such as ground elevation and the location of drainage facilities, collected from local governments and surveying agencies.

[1429] "Generative AI" refers to an AI model designed to analyze the risk of inland flooding based on meteorological and topographical data.

[1430] "Inland flooding" is a phenomenon in which sewerage and drainage facilities are temporarily unable to handle the flow of water due to heavy rain or flooding, increasing the risk of flooding in urban areas and buildings.

[1431] "Means for analyzing risk" refers to the process of using collected data to evaluate the risk level of inland flooding numerically or in categories.

[1432] "Smartphone app" refers to application software that users can use on their smartphones, including tools for sending photos and information about dangerous areas.

[1433] "Means for analyzing submitted information" refers to the process of analyzing data such as photos, comments, and location information submitted by users to identify the situation and risk of inland flooding.

[1434] "Location information" refers to information that indicates a geographic location based on GPS data or a user's current location.

[1435] "Risk level" is an indicator that shows the possibility of inland flooding and the degree of damage it would cause, including the level of urgency.

[1436] "Means of real-time notification" refers to the process of promptly communicating analyzed danger information to other residents at the same time.

[1437] "Safe evacuation routes" refers to information that indicates routes to travel from areas experiencing inland flooding to evacuation shelters or safe locations.

[1438] An "evacuation site" is a facility or area designated as a temporary evacuation site for residents in the event of a disaster such as inland flooding.

[1439] An "emotion engine" is software or a system that analyzes a user's voice and text comments, detects their emotional state, and responds appropriately.

[1440] This invention combines an emotion engine with a system that predicts the risk of inland flooding through the collection and analysis of meteorological and topographical data, and allows residents to share information about dangerous areas via a smartphone app. This system is implemented in the following form.

[1441] The server periodically collects meteorological data (rainfall, wind speed, humidity, etc.) from meteorological stations and topographical data (ground elevation, location of drainage facilities, etc.) from local government databases. The collected meteorological and topographical data is input into a generative artificial intelligence (generative AI model), which outputs the risk level of inland flooding as a number or category.

[1442] When a user discovers flooding or abnormal water flow at home or in their neighborhood, they launch the app on their smartphone, take a photo of the dangerous area, and enter comments (e.g., depth of flooding, date and time of occurrence). In addition, the emotion engine analyzes the user's voice and text comments to detect their emotional state (e.g., anxiety, fear, panic). This information is sent to the server along with GPS data.

[1443] The server uses image recognition technology to analyze the received photos, comments, and location information to determine the depth and extent of flooding. During this process, an emotion engine analyzes the user's emotional state and adjusts the necessary measures and notification content based on that. For example, if the user expresses strong anxiety, the server will prepare a detailed, reassuring notification.

[1444] The server determines the urgency of the danger information based on the analysis results. Criteria for urgency include the depth of flooding, pedestrian traffic, and residential density. High-urgency information is given priority and notified to other residents in real time. This notification includes a message of reassurance generated by an emotion engine, and also provides information on safe evacuation routes and the nearest evacuation shelters.

[1445] As a specific example, when a heavy rain warning is issued, the server quickly retrieves the data and analyzes it using the generation AI. The generation AI predicts that there is an increased risk of inland flooding in certain low-lying areas of the city. At the same time, a user sends a photo of flooded roads in that area to the server via the app. The device inputs the user's voice and comments into the emotion engine and determines that the user is feeling anxious. The server analyzes the received information, determines the depth and extent of the flooding, and sends a real-time notification to other residents in the area. Upon receiving the notification, the device displays a reassuring message from the emotion engine along with evacuation route instructions, thereby reducing the user's anxiety.

[1446] Example prompt sentence:

[1447] "There is currently a very high risk of flooding. Please remain calm and evacuate to the nearest evacuation shelter."

[1448] "The risk of flooding is very high. Please remain calm and evacuate."

[1449] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1450] Step 1:

[1451] Meteorological and terrain data collection

[1452] The server periodically collects meteorological data such as rainfall, wind speed, and humidity from the meteorological bureau. It also obtains topographical data such as ground elevation and the location of drainage facilities from the local government database. The input is the API response from the meteorological bureau and the local government database, and the output is the formatted data required for analysis.

[1453] Step 2:

[1454] Data analysis and risk prediction

[1455] The server inputs the collected weather and topographical data into a generative artificial intelligence (generative AI model) and outputs the risk level of inland flooding as a number or category. The input is preformatted weather and topographical data, and the output is the risk level assessment result. Specifically, a machine learning algorithm is used to estimate the degree of danger and quantify the risk level.

[1456] Step 3:

[1457] User submission of risk information

[1458] When a user discovers flooding or abnormal water flow at home or in their neighborhood, they launch the smartphone app and take a photo of the dangerous area. They then enter comments such as the depth of the flooding and the date and time of the occurrence. The emotion engine then analyzes the user's voice and text comments to detect their emotional state. The inputs are the photos, comments, voice data, and GPS data, and the output is a consistent record of these data.

[1459] Step 4:

[1460] Analysis of risk information

[1461] The server receives photos, comments, and location information sent by users. It then uses image recognition technology to determine the depth and extent of flooding and analyzes comments to extract detailed information. The input is the data sent by users, and the output is the analysis results, such as information on the depth and extent of flooding.

[1462] Step 5:

[1463] Emotional state analysis and response adjustment

[1464] The server adjusts the necessary measures and notification content based on the user's emotional state analyzed by the emotion engine. For example, if the user shows strong anxiety, the notification content will be detailed and reassuring. The input is the emotional state evaluation result by the emotion engine, and the output is the adjusted notification content.

[1465] Step 6:

[1466] Urgency assessment and notification

[1467] The server determines the urgency of the danger information based on the analysis results. Criteria for urgency include the depth of flooding, foot traffic, and residential density. Information with a high urgency is given priority and notified to other residents in real time. The input is the analyzed danger information, and the output is notification information based on the urgency.

[1468] Step 7:

[1469] Providing evacuation information

[1470] The server provides residents with information on safe evacuation routes and evacuation locations. This includes messages based on the emotion engine that create a sense of security, encouraging users to evacuate safely. The input is danger information and the results of an evaluation of the user's emotional state, and the output is information on evacuation routes and evacuation locations, along with messages providing that information.

[1471] Step 8:

[1472] Displaying notifications and encouraging evacuation

[1473] The device displays the received notification to the user and provides detailed information such as warning messages and maps of dangerous areas. The emotion engine displays messages that take the user's emotions into consideration, allowing the user to consider evacuating to a safe place. The input is notifications and messages from the server, and the output is prompting the user to take action.

[1474] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1475] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1476] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1477] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1478] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1479] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1480] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1481] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1482] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1483] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1484] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1485] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1486] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1487] 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.

[1488] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1489] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1490] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1491] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1492] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1493] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1494] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1495] The following is further disclosed regarding the above embodiment.

[1496] (Claim 1)

[1497] a means for collecting meteorological data;

[1498] means for collecting topographical data;

[1499] A means of inputting the collected meteorological and topographical data into a generation artificial intelligence to analyze the risk of inland flooding;

[1500] A method for residents to send photos and information about dangerous areas using a smartphone app,

[1501] A means for analyzing the transmitted information and identifying location information and risk level;

[1502] A means of notifying other residents of the analyzed risk information in real time;

[1503] A means of providing residents with information on safe evacuation routes and evacuation shelters;

[1504] A system including:

[1505] (Claim 2)

[1506] The system according to claim 1, comprising a generating artificial intelligence that outputs the risk level of inland flooding as a number or category based on the collected information.

[1507] (Claim 3)

[1508] 2. The system according to claim 1, further comprising an information sorting means for prioritizing information of high urgency when notifying.

[1509] "Example 1"

[1510] (Claim 1)

[1511] a means for collecting meteorological data;

[1512] means for collecting topographical data;

[1513] A means of inputting the collected meteorological and topographical data into a generation artificial intelligence to analyze the risk of inland flooding;

[1514] A means for residents to send photos and information of dangerous areas using mobile communication terminals;

[1515] A means for analyzing the transmitted information and identifying location information and risk level;

[1516] A means of notifying other residents of the analyzed risk information in real time;

[1517] A means of providing residents with information on safe evacuation routes and evacuation shelters;

[1518] A system including:

[1519] (Claim 2)

[1520] The system according to claim 1, comprising a generating artificial intelligence that outputs the risk level of inland flooding as a number or category based on the collected meteorological and topographical data.

[1521] (Claim 3)

[1522] 2. The system according to claim 1, further comprising an information sorting means for giving priority to information with a high degree of urgency in the notification of analyzed danger information.

[1523] "Application Example 1"

[1524] (Claim 1)

[1525] a means for collecting meteorological data;

[1526] means for collecting topographical data;

[1527] A means of inputting the collected meteorological and topographical data into a generation artificial intelligence to analyze the risk of inland flooding;

[1528] A means for residents to send photos and information about dangerous areas using mobile devices;

[1529] A means for analyzing the transmitted information and identifying location information and risk level;

[1530] A means of notifying other residents of the analyzed risk information in real time;

[1531] A means of providing residents with information on safe evacuation routes and evacuation shelters;

[1532] A method to analyze photos sent by users using image recognition technology to determine the depth and extent of flooding,

[1533] A means for determining the urgency of risk information based on the collected analysis information and notifying information with a high urgency as a priority;

[1534] A system including:

[1535] (Claim 2)

[1536] The system according to claim 1, comprising a generating artificial intelligence that outputs the risk level of inland flooding as a number or category based on the collected information.

[1537] (Claim 3)

[1538] 2. The system according to claim 1, further comprising an information sorting means for prioritizing information of high urgency when notifying.

[1539] "Example 2: Combining Emotion Engines"

[1540] (Claim 1)

[1541] a means for collecting meteorological data;

[1542] means for collecting topographical data;

[1543] A means of inputting the collected meteorological and topographical data into a generation artificial intelligence to analyze the risk of inland flooding;

[1544] A means for residents to send photos and information of dangerous areas using mobile communication terminals;

[1545] A means for analyzing the transmitted information and identifying location information and risk level;

[1546] A means of notifying other residents of the analyzed risk information in real time;

[1547] A means of providing residents with information on safe evacuation routes and evacuation shelters;

[1548] A means for performing emotion recognition and taking appropriate action based on the results;

[1549] A system including:

[1550] (Claim 2)

[1551] The system according to claim 1, comprising a generating artificial intelligence that outputs the risk level of inland flooding as a number or category based on the collected information.

[1552] (Claim 3)

[1553] 2. The system according to claim 1, further comprising an information sorting means for prioritizing information of high urgency when notifying.

[1554] "Application example 2 when combining emotion engines"

[1555] (Claim 1)

[1556] a means for collecting meteorological data;

[1557] means for collecting topographical data;

[1558] A means of inputting the collected meteorological and topographical data into a generation artificial intelligence to analyze the risk of inland flooding;

[1559] A method for residents to send photos and information about dangerous areas using a smartphone app,

[1560] A means for analyzing the transmitted information and identifying location information and risk level;

[1561] A means of notifying other residents of the analyzed risk information in real time;

[1562] A means of providing residents with information on safe evacuation routes and evacuation shelters;

[1563] A means for analyzing the emotional state of a user using an emotion engine and responding in a way that takes emotion into consideration;

[1564] A system including:

[1565] (Claim 2)

[1566] The system according to claim 1, comprising a generating artificial intelligence that outputs the risk level of inland flooding as a number or category based on the collected information.

[1567] (Claim 3)

[1568] 2. The system according to claim 1, further comprising an information sorting means for prioritizing information of high urgency when notifying. [Explanation of symbols]

[1569] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting meteorological data; means for collecting topographical data; A means of inputting the collected meteorological and topographical data into a generation artificial intelligence to analyze the risk of inland flooding; A method for residents to send photos and information about dangerous areas using a smartphone app, A means for analyzing the transmitted information and identifying location information and risk level; A means of notifying other residents of the analyzed risk information in real time; A means of providing residents with information on safe evacuation routes and evacuation shelters; A system including:

2. The system according to claim 1, further comprising a generating artificial intelligence that outputs the risk level of inland flooding as a number or category based on the collected information.

3. 2. The system according to claim 1, further comprising information sorting means for prioritizing information of high urgency when notifying.

Images