system

Abstract

We provide the system. [Solution] A means of collecting environmental data from multiple observation devices installed in each region, A means having a computing device including artificial intelligence that receives and analyzes the aforementioned environmental data, Based on the aforementioned analysis results, a means for evaluating the risk of disaster and generating warnings and evacuation orders, A means for notifying the user of the generated alarm and evacuation order, A system that includes means of providing local governments with concrete disaster countermeasures proposals.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Natural disasters such as landslides and floods are difficult to predict their occurrence and often cause large-scale damage. Relying on existing warning systems and evacuation instructions has problems such as delayed information provision and putting many lives and properties at risk. The purpose of this invention is to minimize damage by enabling early prediction of disasters and prompt response.

Means for Solving the Problems

[0005] In this invention, multiple observation devices placed in each region collect environmental data such as rainfall, ground movement, water level, and wind speed in real time. This data is transmitted to a computing device and analyzed using artificial intelligence. Based on the analysis results, the risk of disaster is assessed, and appropriate warnings and evacuation orders are automatically generated and notified to the user. Furthermore, local governments are provided with concrete disaster countermeasures, enabling a rapid and efficient disaster response. In addition, the system improves the accuracy of predictions by continuously updating the model using past data.

[0006] An "observation device" is a device installed in each region to measure and collect environmental data, providing information such as rainfall, ground movement, water level, and wind speed.

[0007] "Environmental data" refers to data acquired to show the current state of the natural environment, and specifically includes rainfall, ground movement, water level, wind speed, etc.

[0008] A "computational unit" is a device used to analyze data collected from observation equipment, and in particular, it processes data using artificial intelligence.

[0009] "Artificial intelligence" is a technology that uses computer programs to analyze data and make predictions, such as assessing the risk of disasters.

[0010] An "alert" is a warning message issued to inform users of the danger of a disaster.

[0011] An "evacuation order" is an instruction given to users to quickly ensure their safety in the event of a potential disaster.

[0012] "Users" are individuals or groups whose purpose is to receive warnings and evacuation orders, and primarily refer to residents and local governments.

[0013] A "local government" is a local government organization responsible for providing public services in a region, and is the entity to which disaster response plans are provided. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention is implemented as a system that predicts the risk of natural disasters and enables rapid response by using environmental data acquired from observation devices installed in each region. Specifically, the system includes observation devices, a server, terminals, and users.

[0036] The server receives data such as rainfall, ground movement, water level, and wind speed from observation devices in real time. This allows for constant monitoring of the current situation in each region. The server then transfers the received data to an AI agent for analysis.

[0037] The AI ​​agent performs an analysis process, comparing it with past disaster data to assess the risk of disaster occurrence. In this process, the artificial intelligence uses statistical models to calculate the most probable risks from the data.

[0038] The server receives analysis results from the AI ​​agent and generates warning messages and evacuation orders if the risk is high. These messages are automatically created in clear and understandable natural language by the generating AI.

[0039] The generated alarms and evacuation orders are delivered to users via terminals. These terminals include smartphones and other communication devices that have the ability to alert users with voice and vibration. This allows users to receive important information in a timely manner.

[0040] The server will also present specific disaster response plans to each local government. These plans will include suggestions for optimal evacuation routes and detailed instructions regarding preventative measures. Local governments are expected to make swift decisions based on this information and take action to ensure the safety of their residents.

[0041] Furthermore, the system has the capability to continuously update the AI ​​agent's model by utilizing new data collected after a disaster occurs. This feedback loop improves prediction accuracy, thereby enhancing the system's ability to respond to future disasters.

[0042] As a concrete example, considering a scenario where there is a risk of landslides due to heavy rain, when the observation equipment detects abnormal rainfall and unstable ground movement, the server quickly processes the information, and the AI ​​agent determines it to be a high-risk situation. At this point, appropriate evacuation orders are immediately issued to the local government and residents, allowing for faster disaster preparedness than before.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server receives environmental data in real time from observation devices installed in each region. This includes information such as rainfall, ground movement, water level, and wind speed obtained via sensors. The server records and temporarily stores this data in a database.

[0046] Step 2:

[0047] The server transfers the collected data to the AI ​​agent. The AI ​​agent receives this data and performs analysis using historical disaster and weather data. Machine learning algorithms are used in the analysis to calculate the probability of a disaster occurring.

[0048] Step 3:

[0049] Once the AI ​​agent completes its analysis, the server assesses the disaster risk based on the results. If it determines that the risk exceeds a set threshold, it sets a flag for use in the next step.

[0050] Step 4:

[0051] The server uses AI to automatically generate warning messages and evacuation orders. The generated messages include specific details such as the likelihood of a disaster, recommended emergency measures, and evacuation routes.

[0052] Step 5:

[0053] The server sends the generated alarms and evacuation instructions to the terminal. The terminal receives them and provides the information to the user as visual and auditory alerts.

[0054] Step 6:

[0055] Based on the alarms and instructions received by the user, evacuation actions will be initiated. The server will continuously monitor the latest relevant data and will be ready to send additional instructions as needed.

[0056] Step 7:

[0057] When a disaster occurs, the server sends subsequent observation results back to the AI ​​agent to update the model. This enhances the system's ability to respond to future disasters and improves prediction accuracy.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] In modern society, accurate and rapid risk prediction and information provision are essential to minimize damage from natural disasters. However, current systems struggle to immediately analyze detailed environmental information for each region and provide warnings and evacuation orders in a timely manner. Therefore, a more accurate and real-time warning system is needed.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes means for collecting environmental information from a plurality of sensor devices installed in each region, means for having a processing device that includes a generative algorithm for receiving and analyzing the environmental information, and means for evaluating the risk of natural disasters and generating alerts and evacuation orders based on the analysis results. This enables highly accurate risk assessment based on environmental data for each region and the provision of rapid warnings and evacuation orders.

[0063] A "sensor device" is a device used to detect and measure environmental information in real time, and has the function of measuring precipitation, crustal movement, water level, and wind speed, among other things.

[0064] "Environmental information" refers to various data related to nature and weather measured by sensor devices, including information such as precipitation, crustal movement, water level, and wind speed.

[0065] "Generative algorithms" refer to computational methods for processing environmental information and conducting natural disaster risk assessments and generating alerts, utilizing artificial intelligence and machine learning models.

[0066] A "processing device" is a computer system that uses generative algorithms to analyze environmental information, assess disaster risks based on the results, and generate necessary alerts and evacuation orders.

[0067] "Natural disaster risk" is an evaluation index that predicts disaster events that may occur under specific environmental conditions and indicates the probability of their occurrence.

[0068] An "alert" is a warning or notification message issued to users or relevant organizations to draw their attention when a specific risk is identified.

[0069] An "evacuation order" is a message that instructs users on what actions they should take to ensure their safety, based on a specific natural disaster risk.

[0070] "Public institutions" refer to organizations responsible for disaster response, such as local governments and government agencies, which provide guidance and support to ensure the safety of local residents.

[0071] This invention describes an embodiment of a system that acquires environmental information in real time, predicts the risk of natural disasters, and provides rapid warnings and evacuation orders.

[0072] The server collects environmental information from sensor devices installed in each region. Specifically, it receives data from rain sensors, accelerometers that detect ground movement, water level sensors, and wind speed sensors. This data is stored in a database on the server via the internet.

[0073] Based on the received environmental information, the server analyzes the data using generative algorithms. Deep learning frameworks such as TENSORFLOW® and PyTorch are used for the analysis. This allows the server to compare past disaster information with current environmental information and assess the risk of natural disasters. The analysis results indicate when a disaster is predicted if a certain threshold is exceeded.

[0074] Upon receiving the analysis results, the server uses a generative AI model to generate alert messages and evacuation orders in natural language. These messages are provided in a format that is easy for users to understand. For example, a notification might read, "The risk of landslides due to heavy rain is increasing in area A. Please evacuate immediately to ensure your safety."

[0075] The generated alerts and evacuation orders are delivered to users via a terminal. This terminal can be a smartphone, tablet, or communication device including a local disaster prevention radio system. This allows users to receive warnings via voice or vibration.

[0076] The server also provides information to public authorities. This information includes specific disaster prevention measures, such as detailed instructions on optimal evacuation routes and preventative measures. Public authorities can use this information to implement appropriate measures to ensure the safety of local residents.

[0077] Furthermore, after a disaster occurs, the server updates the generative algorithm model using newly collected data. This feedback loop improves the accuracy of future predictions and strengthens the system's responsiveness.

[0078] For example, suppose in an area where heavy rainfall is predicted, a sensor device detects higher-than-usual rainfall, and related data indicating unstable ground conditions is recorded. Based on this information, the server recognizes that the risk of landslides has increased and generates appropriate instructions using pre-prepared prompts.

[0079] An example of a prompt message could be: "A prompt for a generative AI model that detects the risk of landslides due to heavy rain and sends evacuation instructions to a smartphone." By entering this prompt, the server can quickly and appropriately create and provide an alert.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The server collects environmental information in real time from sensor devices installed in each region. Inputs include digital data from precipitation sensors, crustal motion sensors, water level sensors, and wind speed sensors. This data is sent to the server's database via the network. Outputs include environmental data organized in chronological order. This data is stored for use in subsequent analysis steps.

[0083] Step 2:

[0084] The server inputs the collected environmental information into a generative algorithm and analyzes the data. This process references past disaster datasets and compares them with current data. Data processing includes noise reduction and normalization to prepare the dataset for the generative AI model to perform risk assessment. The output generates a risk score, quantifying specific disaster risks.

[0085] Step 3:

[0086] The server automatically generates alert messages and evacuation orders using a generation AI model based on the generated risk score. Instructions are given to the model using prompts to construct natural language messages. The input includes the risk score and prompts, and the output is a specific and clear warning message. A message in the format of, "The risk of landslides due to heavy rain is high in area A. Please evacuate immediately to ensure your safety," is generated.

[0087] Step 4:

[0088] The device receives alert messages and evacuation instructions sent from the server. Input is message data from the server, and output is alarm notifications via the device's display screen, audio, and vibration. Specifically, the smartphone emits an emergency notification sound, and the screen displays instructions for the necessary actions.

[0089] Step 5:

[0090] The server sends generated alerts and evacuation orders to public authorities and provides specific disaster prevention measures. Input includes detailed data on disaster risk, and output generates detailed guidelines on optimal evacuation routes and preventative measures. This information is distributed to public authorities via email and a dedicated communication system.

[0091] Step 6:

[0092] The server updates its generative algorithm model using new environmental data obtained after a disaster. In this process, the latest disaster data is used as input, and the generative AI model is retrained through a feedback loop. The output is a newly constructed model with improved prediction accuracy, thereby enhancing future predictive capabilities.

[0093] (Application Example 1)

[0094] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0095] Predicting and responding quickly to natural disasters is a critical challenge, especially in densely populated urban areas. Existing methods are insufficient for real-time, comprehensive situation assessment and for issuing appropriate and timely evacuation orders to residents, resulting in loss of life and property. This invention aims to improve the accuracy of disaster risk prediction based on observational data and to provide local governments and residents with quick and accurate information.

[0096] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0097] In this invention, the server includes means for collecting and analyzing observation data in real time, means for evaluating the risk of disaster using artificial intelligence and generating warnings and evacuation orders, and means for notifying users of information via terminal devices and allowing them to confirm evacuation routes. This enables highly accurate disaster prediction based on observation data and rapid information transmission.

[0098] An "observation device" is a device installed in each region to measure and collect environmental data in real time.

[0099] "Environmental data" refers to information about natural phenomena necessary for assessing disaster risk, such as rainfall, ground movement, water level, and wind speed.

[0100] A "processing device" is a computer device that receives environmental data and analyzes it using artificial intelligence.

[0101] "Artificial intelligence" is a technology that uses statistical models and historical disaster information to predict the risk of disaster from environmental data.

[0102] A "warning" is a message intended to inform users of the occurrence of a disaster or the danger it poses, and to urge them to take precautions.

[0103] An "evacuation order" is a set of specific action guidelines provided to users to ensure their safety during a disaster.

[0104] A "terminal device" refers to a smartphone or other communication device used by a user to receive notifications of alarms or evacuation orders.

[0105] A "local government" is a local public entity that has jurisdiction over a specific area and is responsible for ensuring the safety of residents in the event of a disaster.

[0106] A "disaster response plan" refers to specific proposals for actions and measures that local governments should take depending on the risk of disaster.

[0107] The system that realizes this invention includes observation devices, a server, a terminal, and a user. The server receives environmental data in real time from multiple observation devices. These observation devices are installed in the area and measure environmental data such as rainfall, ground movement, water level, and wind speed. The server sends the received data to an AI agent, which performs data analysis using TensorFlow or similar software. This analysis compares the data with past disaster information and evaluates the risk of disaster based on a statistical model.

[0108] Based on the analysis results, the server uses a generative AI to create warnings and evacuation instructions in natural language. A natural language generation tool is used for the generative AI. The generated results are sent to the terminal via GOOGLE FI® rebase. The terminal, a communication device such as a smartphone owned by the user, notifies the user of the warnings and evacuation instructions via voice and vibration. Furthermore, the terminal also provides the user with information on evacuation routes.

[0109] As a concrete example, consider a scenario where heavy rainfall poses a risk of landslides. When the observation device detects abnormal rainfall and unstable ground movement, the server quickly processes the information, and the AI ​​agent determines that the risk is high. At this point, the AI ​​generates a prompt message such as, "There is a risk of landslides due to heavy rainfall. Begin evacuation immediately and check the designated evacuation route." This allows users to receive important information in real time and take swift action.

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The server collects environmental data in real time from observation devices installed in each region. The data transmitted from these devices includes information such as rainfall, ground movement, water level, and wind speed. The input environmental data is stored in a database.

[0113] Step 2:

[0114] The server transfers the collected environmental data to the AI ​​agent for analysis. The AI ​​agent uses TensorFlow to calculate the risk of damage by comparing it with past disaster data. In this process, the input is the environmental data, and the output is the result of the risk assessment. As part of the data processing, data cleansing is performed using an anomaly detection algorithm.

[0115] Step 3:

[0116] The server generates alarms and evacuation instructions using a generative AI model based on the analysis results from the AI ​​agent. The generative AI model converts the analysis results into natural language and outputs a message to be notified to the user. At this time, a natural language generation algorithm based on the prompt text is in operation.

[0117] Step 4:

[0118] The terminal notifies the user of alarms and evacuation orders received from the server. Notifications are made via smartphone, attracting the user's attention through sound and vibration. The input is the generated message, and the output is the user's recognition. Google® Firebase is used as the notification protocol.

[0119] Step 5:

[0120] Based on the information received through the device, the user confirms the designated evacuation route and initiates appropriate evacuation actions. The prompt messages clearly define the actions the user should take, enabling rapid safety assurance.

[0121] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0122] This invention provides a system that offers more effective warnings and evacuation instructions by taking user emotions into account in the prediction and risk assessment of natural disasters. The system includes observation devices, a server, terminals, a user, and an emotion engine.

[0123] First, the server receives environmental data in real time from observation devices installed in each region. This includes information such as rainfall, ground movement, water level, and wind speed. The server records this data in a database and sends it to an AI agent. The AI ​​agent uses historical disaster data and weather data to analyze the data and assess the risk of disaster.

[0124] Upon receiving the analysis results, the server first generates standard alarm messages and evacuation instructions. During this process, an emotion engine intervenes to recognize the user's stress level and emotional state. For example, it analyzes the user's facial expressions, voice tone, and touch behavior through the device's built-in camera and sensors to determine their emotional status.

[0125] The emotion engine analyzes the user's emotional state and customizes warning messages and evacuation instructions accordingly. Specifically, if the user is in a high-stress state, a more concise and reassuring message is sent. On the other hand, users in a calm state are provided with more detailed information and clearer instructions.

[0126] The device displays this personalized message to the user, notifying them through visual and auditory means for intuitive understanding. This allows users to receive evacuation instructions in a way that best suits their emotional state, enabling them to take swift action.

[0127] Furthermore, disaster response plans are also adjusted by the emotion engine. The server adjusts the response plans provided to local governments, taking into account the overall sentiment data of residents, to be useful for local communication strategies. In this way, utilizing sentiment information can enhance the overall responsiveness and effectiveness of the system.

[0128] For example, if the system determines there is a risk of flooding due to a typhoon, it will send a general warning via a standard communication protocol. However, if the emotion engine detects that the user is under high stress, it will send an additional message with specific instructions such as, "Avoid panicking and head to the nearest shelter." This approach is expected to reduce user stress and increase the rate of safety.

[0129] The following describes the processing flow.

[0130] Step 1:

[0131] The server receives environmental data in real time from observation devices installed in each region. The observation devices collect information such as rainfall, ground movement, water level, and wind speed, and this data is recorded in the server's database.

[0132] Step 2:

[0133] The server sends the collected data to the AI ​​agent. The AI ​​agent uses historical disaster data and weather data to analyze and assess disaster risk. The assessment results quantify the degree of risk and are used in the next step.

[0134] Step 3:

[0135] The server generates standard alarm messages and evacuation instructions based on the analysis results of the AI ​​agent. The generating AI uses natural language processing technology to convert the alarms into easily understandable text.

[0136] Step 4:

[0137] The device uses its built-in camera and microphone to input the user's facial expressions and voice tone into the emotion engine. Based on the data obtained, the system determines the user's stress level and emotional state.

[0138] Step 5:

[0139] The server uses the results of the emotion engine's analysis to modify or refine alarm messages and evacuation instructions according to the user's emotional state. For example, simple and reassuring language is used for users in a high-stress state.

[0140] Step 6:

[0141] The device notifies the user of coordinated alarm messages and evacuation instructions. Notifications are delivered via visual display, audio message, or vibration, and are designed to allow the user to quickly understand the content.

[0142] Step 7:

[0143] Users act based on the instructions they receive. Emotionally sensitive information provision enables users to take calm and appropriate evacuation actions.

[0144] Step 8:

[0145] The server uses new emotional data collected after the disaster to update the AI ​​agent's model. The updated model will be used to provide even more accurate risk assessment and emotional response during the next disaster.

[0146] (Example 2)

[0147] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0148] In recent years, the increasing frequency of natural disasters has highlighted the need for safe and effective evacuation plans and warning systems. However, conventional systems send uniform warnings without considering the emotional state of users, which can lead to panic and make it difficult to convey accurate information. Furthermore, the lack of community-based disaster countermeasures that take into account the emotions of the entire population is also a challenge.

[0149] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0150] In this invention, the server includes means for collecting environmental information from multiple observation devices installed in each region, means for having an analysis device including artificial intelligence that receives and analyzes the environmental information, and means for recognizing the emotional state of the user and adjusting the warnings and evacuation orders according to the emotion. This provides personalized warnings and orders that take into account the user's emotions, minimizes confusion during disasters, and enables effective disaster countermeasures that take into account the emotions of the entire community.

[0151] "Observation equipment" refers to devices deployed in each region to collect environmental information in real time.

[0152] "Environmental information" refers to data such as precipitation, land deformation, water levels, and wind speed used to detect signs of natural disasters.

[0153] "Artificial intelligence" is an advanced information processing technology used to analyze received environmental information and assess disaster risks.

[0154] An "analysis device" is a computing device used to predict disasters based on environmental information and historical data.

[0155] A "user" is an individual or group that receives warnings and evacuation orders from this system.

[0156] "Emotional state" refers to the user's psychological state and includes information such as stress levels and emotional status.

[0157] A "personalized alert" is an alert message that is tailored to the user's emotional state and optimized for their individual needs.

[0158] "Disaster countermeasures" is a general term for plans and actions taken to prepare for natural disasters and minimize damage.

[0159] A "local government" is a public institution that carries out administrative and disaster response measures within a specific region.

[0160] This invention is a system that provides warnings and evacuation instructions that take into account the user's emotional state during a disaster. The system mainly consists of a server, terminals, an emotion engine, and various observation devices.

[0161] First, the server receives environmental information from multiple observation devices installed in each region to collect data such as precipitation, ground movement, water level, and wind speed. These observation devices utilize sensor technology to enable real-time data collection. The received data is stored on the server and analyzed by analytical devices, including artificial intelligence. This analysis uses historical disaster data and weather patterns to build predictive models for assessing future disaster risks.

[0162] The device then uses its built-in camera and microphone to analyze the user's facial expressions and voice tone, collecting emotional data. This allows for real-time assessment of the user's stress level and emotional state. The collected data is immediately transmitted to the server.

[0163] The emotion engine operates on the server and analyzes the user's emotional state. Utilizing natural language processing and emotion analysis techniques, the emotion engine generates the most appropriate warning messages and evacuation instructions for the user. For users experiencing high stress levels, it generates concise and reassuring messages, while for calm users, it creates messages with detailed instructions.

[0164] For example, when a typhoon approaches and the risk of flooding is deemed high, the server generates a standard warning message. However, if the emotion engine analyzes the user's emotional data and finds that their stress level is high, the message is adjusted to a more emotionally sensitive message such as, "Please remain calm. Move safely to the nearest shelter."

[0165] In this way, by providing warnings and instructions tailored to the individual emotional state of users, it is possible to promote appropriate actions during disasters.

[0166] Example of a prompt:

[0167] "Please customize typhoon flood warnings based on user sentiment data. Provide reassuring messages to highly stressed users and include detailed information for calmer users."

[0168] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0169] Step 1:

[0170] The server receives real-time environmental information regarding precipitation, ground movement, water level, and wind speed from observation devices installed in each region. The input consists of data streams from each sensor. The server aggregates this data and processes it by recording it in a database in a compatible format. The output is an environmental information dataset in an analyzable format.

[0171] Step 2:

[0172] The server transmits the collected environmental data to an analysis device that includes artificial intelligence. The input is the environmental information dataset obtained in Step 1. The AI ​​model performs data calculations to analyze the current data in comparison with past disaster data and assess disaster risk. During this process, machine learning algorithms are used, and the predictive model is updated. The output is the disaster risk assessment result for each region.

[0173] Step 3:

[0174] The device uses the user's built-in camera and microphone to collect emotional data such as facial expressions and voice tone. The input is the user's real-time visual and auditory emotional signals. The device analyzes this data and processes it to quantify the emotional state. The output is digital data of the user's stress level and emotional state.

[0175] Step 4:

[0176] The server sends the emotional data obtained in step 3 to the emotion engine for analysis. The input is digital data of the user's emotional state. The emotion engine uses natural language processing and emotion analysis algorithms to perform data calculations that generate alarm messages and evacuation instructions appropriate to the user's emotional state. The output is the adjusted alarm message and evacuation instruction.

[0177] Step 5:

[0178] The terminal notifies the user of a customized alarm message sent from the server. The input is the message generated in step 4. The terminal performs specific actions to convey the message to the user in visual and auditory ways. The output is information and instructions that the user can intuitively understand.

[0179] Through this step, evacuation instructions that take into account the user's emotional state are provided, promoting appropriate and swift action.

[0180] (Application Example 2)

[0181] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0182] Natural disasters are difficult to predict, requiring the provision of appropriate warnings and evacuation orders based on risk assessments. Furthermore, during disasters, responses that are sensitive to the emotional state of recipients are essential. However, current systems do not provide warnings or orders that take recipients' emotions into account, posing challenges to accelerating evacuation and ensuring safety.

[0183] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0184] In this invention, the server includes means for collecting environmental information from a plurality of sensing devices installed in each area; means for having an information processing device that receives and analyzes the environmental information, including machine learning; means for evaluating the degree of disaster risk and generating warnings and evacuation orders based on the analysis results; and means for evaluating the emotional state of the recipient and adjusting the warnings and evacuation orders according to the evaluation results. This makes it possible to provide optimized warnings and evacuation orders for the recipient.

[0185] A "sensing device" is a device that measures and collects information on the state of the global environment in real time, providing diverse environmental data such as precipitation, crustal movement, water level, and wind speed.

[0186] An "information processing device" is a computing device that receives collected environmental data and analyzes it using machine learning algorithms, and is responsible for assessing the risk of disasters and generating warnings.

[0187] "Machine learning" is a technology that learns patterns derived from past disaster and weather data and continuously improves disaster prediction models.

[0188] "Risk assessment" is the process of quantifying the likelihood of a natural disaster occurring based on analysis results and determining its severity.

[0189] A "warning and evacuation order" is an official message issued when there is a risk of disaster, intended to alert recipients and instruct them on safe actions.

[0190] A "recipient" is a person or community that receives a warning and evacuation order notification.

[0191] "Emotional state" refers to information that indicates the recipient's psychological and physiological responses, such as emotions like stress or relief, and is measured accordingly.

[0192] The system for carrying out this invention comprises multiple sensing devices, an information processing device, a user terminal, an emotion evaluation engine, and a communication infrastructure. The sensing devices are installed in each area and measure environmental information such as precipitation, crustal movement, wind speed, and water level in real time. The collected information is transmitted to the information processing device.

[0193] The information processing system incorporates machine learning technology, built using, for example, Python libraries and the Google Cloud AI platform. This allows for comparison and analysis of past disaster and weather data to assess the risk of disasters. Furthermore, warnings and evacuation orders are generated based on these analysis results.

[0194] The user terminal has a built-in camera and microphone, and analyzes the user's facial expressions and voice tone based on warning messages received from the server. Image analysis software such as OpenCV is used for this purpose. An emotion evaluation engine that assesses the user's emotional state integrates the results of facial recognition and voice analysis to determine whether the user is experiencing stress or tension.

[0195] In this way, the device displays warnings and instructions optimized for the user's emotions, prompting the user to take quick and effective action. For example, if a typhoon is approaching and the device determines that the user is feeling stressed, it will send a reassuring message such as, "Please stay calm. Please move to the nearest shelter."

[0196] As an implementation example, the following is an example of a prompt statement used when generating a response message during a disaster.

[0197] "Create messages that suggest safe and calming actions based on user sentiment data."

[0198] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0199] Step 1:

[0200] The server receives environmental information (precipitation, crustal movement, wind speed, water level, etc.) in real time from sensing devices installed in each region. The received data is preprocessed and filtered to remove unwanted noise. The input here is raw data from the sensing devices, and the output is clean environmental information.

[0201] Step 2:

[0202] The server inputs pre-processed environmental information into an information processing unit and applies a machine learning algorithm. This process uses a model that evaluates the risk of disasters using historical disaster data and generates prediction results. The server's input is clean environmental information, and its output is disaster risk and prediction information.

[0203] Step 3:

[0204] The server generates standard warnings and evacuation orders based on the risk assessment and prediction results. This phase utilizes an AI model to create optimal warning messages for disaster situations through the generated AI model. The input is the risk assessment results, and the output is the warnings and evacuation orders.

[0205] Step 4:

[0206] The terminal, along with receiving warnings and evacuation instructions from the server, uses the user's camera and microphone to assess the user's emotional state based on facial expressions and voice tone. An emotion assessment engine analyzes this data to determine the user's stress level. Input is video and audio data, and output is the user's emotional state.

[0207] Step 5:

[0208] The server receives output from the emotion assessment engine and adjusts warning messages and evacuation instructions according to the user's emotional state. Specifically, it generates simpler, more reassuring messages when the user is stressed, and includes more detailed instructions when the user is calm. The input here is the user's emotional state and a standard warning message, while the output is the adjusted warning message.

[0209] Step 6:

[0210] The device notifies the user of a tailored warning message. This notification is delivered both visually and audibly, ensuring intuitive understanding. The input here is the tailored warning message, and the output is the effective notification to the user.

[0211] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0212] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0213] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0214] [Second Embodiment]

[0215] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0216] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0217] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0218] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0219] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0220] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0221] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0222] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0223] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0224] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0225] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0226] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0227] This invention is implemented as a system that predicts the risk of natural disasters and enables rapid response by using environmental data acquired from observation devices installed in each region. Specifically, the system includes observation devices, a server, terminals, and users.

[0228] The server receives data such as rainfall, ground movement, water level, and wind speed from observation devices in real time. This allows for constant monitoring of the current situation in each region. The server then transfers the received data to an AI agent for analysis.

[0229] The AI ​​agent performs an analysis process, comparing it with past disaster data to assess the risk of disaster occurrence. In this process, the artificial intelligence uses statistical models to calculate the most probable risks from the data.

[0230] The server receives analysis results from the AI ​​agent and generates warning messages and evacuation orders if the risk is high. These messages are automatically created in clear and understandable natural language by the generating AI.

[0231] The generated alarms and evacuation orders are delivered to users via terminals. These terminals include smartphones and other communication devices that have the ability to alert users with voice and vibration. This allows users to receive important information in a timely manner.

[0232] The server will also present specific disaster response plans to each local government. These plans will include suggestions for optimal evacuation routes and detailed instructions regarding preventative measures. Local governments are expected to make swift decisions based on this information and take action to ensure the safety of their residents.

[0233] Furthermore, the system has the capability to continuously update the AI ​​agent's model by utilizing new data collected after a disaster occurs. This feedback loop improves prediction accuracy, thereby enhancing the system's ability to respond to future disasters.

[0234] As a concrete example, considering a scenario where there is a risk of landslides due to heavy rain, when the observation equipment detects abnormal rainfall and unstable ground movement, the server quickly processes the information, and the AI ​​agent determines it to be a high-risk situation. At this point, appropriate evacuation orders are immediately issued to the local government and residents, allowing for faster disaster preparedness than before.

[0235] The following describes the processing flow.

[0236] Step 1:

[0237] The server receives environmental data in real time from observation devices installed in each region. This includes information such as rainfall, ground movement, water level, and wind speed obtained via sensors. The server records and temporarily stores this data in a database.

[0238] Step 2:

[0239] The server transfers the collected data to the AI ​​agent. The AI ​​agent receives this data and performs analysis using historical disaster and weather data. Machine learning algorithms are used in the analysis to calculate the probability of a disaster occurring.

[0240] Step 3:

[0241] Once the AI ​​agent completes its analysis, the server assesses the disaster risk based on the results. If it determines that the risk exceeds a set threshold, it sets a flag for use in the next step.

[0242] Step 4:

[0243] The server uses AI to automatically generate warning messages and evacuation orders. The generated messages include specific details such as the likelihood of a disaster, recommended emergency measures, and evacuation routes.

[0244] Step 5:

[0245] The server sends the generated alarms and evacuation instructions to the terminal. The terminal receives them and provides the information to the user as visual and auditory alerts.

[0246] Step 6:

[0247] Based on the alarms and instructions received by the user, evacuation actions will be initiated. The server will continuously monitor the latest relevant data and will be ready to send additional instructions as needed.

[0248] Step 7:

[0249] When a disaster occurs, the server sends subsequent observation results back to the AI ​​agent to update the model. This enhances the system's ability to respond to future disasters and improves prediction accuracy.

[0250] (Example 1)

[0251] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0252] In modern society, accurate and rapid risk prediction and information provision are essential to minimize damage from natural disasters. However, current systems struggle to immediately analyze detailed environmental information for each region and provide warnings and evacuation orders in a timely manner. Therefore, a more accurate and real-time warning system is needed.

[0253] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0254] In this invention, the server includes means for collecting environmental information from a plurality of sensor devices installed in each region, means for having a processing device that includes a generative algorithm for receiving and analyzing the environmental information, and means for evaluating the risk of natural disasters and generating alerts and evacuation orders based on the analysis results. This enables highly accurate risk assessment based on environmental data for each region and the provision of rapid warnings and evacuation orders.

[0255] A "sensor device" is a device used to detect and measure environmental information in real time, and has the function of measuring precipitation, crustal movement, water level, and wind speed, among other things.

[0256] "Environmental information" refers to various data related to nature and weather measured by sensor devices, including information such as precipitation, crustal movement, water level, and wind speed.

[0257] "Generative algorithms" refer to computational methods for processing environmental information and conducting natural disaster risk assessments and generating alerts, utilizing artificial intelligence and machine learning models.

[0258] A "processing device" is a computer system that uses generative algorithms to analyze environmental information, assess disaster risks based on the results, and generate necessary alerts and evacuation orders.

[0259] "Natural disaster risk" is an evaluation index that predicts disaster events that may occur under specific environmental conditions and indicates the probability of their occurrence.

[0260] An "alert" is a warning or notification message issued to users or relevant organizations to draw their attention when a specific risk is identified.

[0261] An "evacuation order" is a message that instructs users on what actions they should take to ensure their safety, based on a specific natural disaster risk.

[0262] "Public institutions" refer to organizations responsible for disaster response, such as local governments and government agencies, which provide guidance and support to ensure the safety of local residents.

[0263] This invention describes an embodiment of a system that acquires environmental information in real time, predicts the risk of natural disasters, and provides rapid warnings and evacuation orders.

[0264] The server collects environmental information from sensor devices installed in each region. Specifically, it receives data from rain sensors, accelerometers that detect ground movement, water level sensors, and wind speed sensors. This data is stored in a database on the server via the internet.

[0265] Based on the received environmental information, the server analyzes the data using generative algorithms. Deep learning frameworks such as TensorFlow and PyTorch are used for this analysis. This allows the server to compare past disaster information with current environmental information and assess the risk of natural disasters. The analysis results indicate when a disaster is predicted if a certain threshold is exceeded.

[0266] Upon receiving the analysis results, the server uses a generative AI model to generate alert messages and evacuation orders in natural language. These messages are provided in a format that is easy for users to understand. For example, a notification might read, "The risk of landslides due to heavy rain is increasing in area A. Please evacuate immediately to ensure your safety."

[0267] The generated alerts and evacuation orders are delivered to users via a terminal. This terminal can be a smartphone, tablet, or communication device including a local disaster prevention radio system. This allows users to receive warnings via voice or vibration.

[0268] The server also provides information to public authorities. This information includes specific disaster prevention measures, such as detailed instructions on optimal evacuation routes and preventative measures. Public authorities can use this information to implement appropriate measures to ensure the safety of local residents.

[0269] Furthermore, after a disaster occurs, the server updates the generative algorithm model using newly collected data. This feedback loop improves the accuracy of future predictions and strengthens the system's responsiveness.

[0270] For example, suppose in an area where heavy rainfall is predicted, a sensor device detects higher-than-usual rainfall, and related data indicating unstable ground conditions is recorded. Based on this information, the server recognizes that the risk of landslides has increased and generates appropriate instructions using pre-prepared prompts.

[0271] An example of a prompt message could be: "A prompt for a generative AI model that detects the risk of landslides due to heavy rain and sends evacuation instructions to a smartphone." By entering this prompt, the server can quickly and appropriately create and provide an alert.

[0272] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0273] Step 1:

[0274] The server collects environmental information in real time from sensor devices installed in each region. Inputs include digital data from precipitation sensors, crustal motion sensors, water level sensors, and wind speed sensors. This data is sent to the server's database via the network. Outputs include environmental data organized in chronological order. This data is stored for use in subsequent analysis steps.

[0275] Step 2:

[0276] The server inputs the collected environmental information into a generative algorithm and analyzes the data. This process references past disaster datasets and compares them with current data. Data processing includes noise reduction and normalization to prepare the dataset for the generative AI model to perform risk assessment. The output generates a risk score, quantifying specific disaster risks.

[0277] Step 3:

[0278] Based on the generated risk score, the server automatically generates alert messages and evacuation instructions using the generative AI model. Using prompt texts, it instructs the model to construct natural language messages. The input includes the risk score and prompt texts, and the output is a specific and clear warning message. A message in the form of "The risk of landslides due to heavy rain in Area A is increasing. To ensure safety, please evacuate immediately." is generated.

[0279] Step 4:

[0280] The terminal receives the alert messages and evacuation instructions sent from the server. As input, there is message data from the server, and as output, alert notifications are made through the device's display screen, sound, and vibration. As a specific operation, the smartphone makes an emergency notification sound, and the screen displays action instructions to be taken.

[0281] Step 5:

[0282] The server sends the generated alerts and evacuation instructions to public institutions and provides specific disaster prevention countermeasure plans. The input includes detailed data on disaster risks, and as output, detailed guidelines on optimal evacuation routes and preventive measures are generated. This information is distributed to public institutions using email or a dedicated communication system.

[0283] Step 6:

[0284] The server updates the model of the generative algorithm using the new environmental data obtained after the disaster occurred. In this process, the latest disaster data is the input, and the generative AI model is retrained through a feedback loop. As output, a new model with improved prediction accuracy is constructed. This enhances the future prediction ability.

[0285] (Application Example 1)

[0286] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0287] The prediction and prompt response to natural disasters are particularly important issues in densely populated urban areas. In existing methods, the overall situation cannot be grasped in real time, and appropriate and prompt evacuation instructions cannot be given to residents, resulting in losses of lives and property. The purpose of this invention is to improve the prediction accuracy of disaster risks based on observation data and provide timely and accurate information to local governments and residents.

[0288] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0289] In this invention, the server includes means for collecting and analyzing observation data in real time, means for evaluating the risk of disasters using artificial intelligence and generating warnings and evacuation instructions, and means for notifying users of information and allowing them to confirm evacuation routes via a terminal device. This enables high-precision disaster prediction based on observation data and rapid information transmission.

[0290] An "observation device" is a device installed in each region for measuring and collecting environmental data in real time.

[0291] "Environmental data" refers to information on natural phenomena necessary for evaluating the risk of disasters, such as rainfall, ground movement, water level, and wind speed.

[0292] A "processing device" is a computer device that receives environmental data and analyzes it using artificial intelligence.

[0293] "Artificial intelligence" is a technology for predicting the risk of disasters from environmental data using statistical models and past disaster information.

[0294] A "warning" is a message for notifying users of the occurrence or risk of disasters and prompting them to pay attention.

[0295] An "evacuation order" is a set of specific action guidelines provided to users to ensure their safety during a disaster.

[0296] A "terminal device" refers to a smartphone or other communication device used by a user to receive notifications of alarms or evacuation orders.

[0297] A "local government" is a local public entity that has jurisdiction over a specific area and is responsible for ensuring the safety of residents in the event of a disaster.

[0298] A "disaster response plan" refers to specific proposals for actions and measures that local governments should take depending on the risk of disaster.

[0299] The system that realizes this invention includes observation devices, a server, a terminal, and a user. The server receives environmental data in real time from multiple observation devices. These observation devices are installed in the area and measure environmental data such as rainfall, ground movement, water level, and wind speed. The server sends the received data to an AI agent, which performs data analysis using TensorFlow or similar software. This analysis compares the data with past disaster information and evaluates the risk of disaster based on a statistical model.

[0300] Based on the analysis results, the server uses a generative AI to create warnings and evacuation instructions in natural language. The generative AI uses a natural language generation tool. The generated results are sent to the device via Google Firebase. The device, such as the user's smartphone, notifies the user of the warnings and evacuation instructions via voice and vibration. Furthermore, the device also provides the user with information on evacuation routes.

[0301] As a specific example, considering a scenario where there is a risk of landslides due to heavy rain, when the observation device detects abnormal rainfall and unstable movement of the ground, the server quickly processes the information and the AI agent determines that the risk is high. At this time, the prompt text generated by the generative AI is a message such as "There is a risk of landslides due to heavy rain. Immediately start evacuation and check the designated evacuation route." As a result, users can receive important information in real-time and can start acting quickly.

[0302] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0303] Step 1:

[0304] The server collects environmental data in real-time from the observation devices installed in each region. At this time, the data transported from the observation devices includes information such as rainfall, ground movement, water level, wind speed, etc. The input environmental data is stored in the database.

[0305] Step 2:

[0306] The server transfers the collected environmental data to the AI agent for analysis. The AI agent uses TensorFlow to calculate the risk of damage by comparing with past disaster data. At this time, the input is the environmental data and the output is the result of the risk assessment. As data processing, data cleansing using an anomaly detection algorithm is performed.

[0307] Step 3:

[0308] Based on the analysis results from the AI agent, the server uses the generative AI model to generate warnings and evacuation instructions. The generative AI model converts the analysis results into natural language and outputs a message to be notified to the user. At this time, the natural language generation algorithm based on the prompt text operates.

[0309] Step 4:

[0310] The terminal notifies the user of alarms and evacuation orders received from the server. Notifications are sent via smartphone, using voice and vibration to alert the user. Input is the generated message, and output is the user's recognition. Google Firebase is used as the notification protocol.

[0311] Step 5:

[0312] Based on the information received through the device, the user confirms the designated evacuation route and initiates appropriate evacuation actions. The prompt messages clearly define the actions the user should take, enabling rapid safety assurance.

[0313] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0314] This invention provides a system that offers more effective warnings and evacuation instructions by taking user emotions into account in the prediction and risk assessment of natural disasters. The system includes observation devices, a server, terminals, a user, and an emotion engine.

[0315] First, the server receives environmental data in real time from observation devices installed in each region. This includes information such as rainfall, ground movement, water level, and wind speed. The server records this data in a database and sends it to an AI agent. The AI ​​agent uses historical disaster data and weather data to analyze the data and assess the risk of disaster.

[0316] Upon receiving the analysis results, the server first generates standard alarm messages and evacuation instructions. During this process, an emotion engine intervenes to recognize the user's stress level and emotional state. For example, it analyzes the user's facial expressions, voice tone, and touch behavior through the device's built-in camera and sensors to determine their emotional status.

[0317] The emotion engine analyzes the user's emotional state and customizes warning messages and evacuation instructions accordingly. Specifically, if the user is in a high-stress state, a more concise and reassuring message is sent. On the other hand, users in a calm state are provided with more detailed information and clearer instructions.

[0318] The device displays this personalized message to the user, notifying them through visual and auditory means for intuitive understanding. This allows users to receive evacuation instructions in a way that best suits their emotional state, enabling them to take swift action.

[0319] Furthermore, disaster response plans are also adjusted by the emotion engine. The server adjusts the response plans provided to local governments, taking into account the overall sentiment data of residents, to be useful for local communication strategies. In this way, utilizing sentiment information can enhance the overall responsiveness and effectiveness of the system.

[0320] For example, if the system determines there is a risk of flooding due to a typhoon, it will send a general warning via a standard communication protocol. However, if the emotion engine detects that the user is under high stress, it will send an additional message with specific instructions such as, "Avoid panicking and head to the nearest shelter." This approach is expected to reduce user stress and increase the rate of safety.

[0321] The following describes the processing flow.

[0322] Step 1:

[0323] The server receives environmental data in real time from observation devices installed in each region. The observation devices collect information such as rainfall, ground movement, water level, and wind speed, and this data is recorded in the server's database.

[0324] Step 2:

[0325] The server sends the collected data to the AI ​​agent. The AI ​​agent uses historical disaster data and weather data to analyze and assess disaster risk. The assessment results quantify the degree of risk and are used in the next step.

[0326] Step 3:

[0327] The server generates standard alarm messages and evacuation instructions based on the analysis results of the AI ​​agent. The generating AI uses natural language processing technology to convert the alarms into easily understandable text.

[0328] Step 4:

[0329] The device uses its built-in camera and microphone to input the user's facial expressions and voice tone into the emotion engine. Based on the data obtained, the system determines the user's stress level and emotional state.

[0330] Step 5:

[0331] The server uses the results of the emotion engine's analysis to modify or refine alarm messages and evacuation instructions according to the user's emotional state. For example, simple and reassuring language is used for users in a high-stress state.

[0332] Step 6:

[0333] The device notifies the user of coordinated alarm messages and evacuation instructions. Notifications are delivered via visual display, audio message, or vibration, and are designed to allow the user to quickly understand the content.

[0334] Step 7:

[0335] Users act based on the instructions they receive. Emotionally sensitive information provision enables users to take calm and appropriate evacuation actions.

[0336] Step 8:

[0337] The server uses new emotional data collected after the disaster to update the AI ​​agent's model. The updated model will be used to provide even more accurate risk assessment and emotional response during the next disaster.

[0338] (Example 2)

[0339] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0340] In recent years, the increasing frequency of natural disasters has highlighted the need for safe and effective evacuation plans and warning systems. However, conventional systems send uniform warnings without considering the emotional state of users, which can lead to panic and make it difficult to convey accurate information. Furthermore, the lack of community-based disaster countermeasures that take into account the emotions of the entire population is also a challenge.

[0341] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0342] In this invention, the server includes means for collecting environmental information from multiple observation devices installed in each region, means for having an analysis device including artificial intelligence that receives and analyzes the environmental information, and means for recognizing the emotional state of the user and adjusting the warnings and evacuation orders according to the emotion. This provides personalized warnings and orders that take into account the user's emotions, minimizes confusion during disasters, and enables effective disaster countermeasures that take into account the emotions of the entire community.

[0343] "Observation equipment" refers to devices deployed in each region to collect environmental information in real time.

[0344] "Environmental information" refers to data such as precipitation, land deformation, water levels, and wind speed used to detect signs of natural disasters.

[0345] "Artificial intelligence" is an advanced information processing technology used to analyze received environmental information and assess disaster risks.

[0346] An "analysis device" is a computing device used to predict disasters based on environmental information and historical data.

[0347] A "user" is an individual or group that receives warnings and evacuation orders from this system.

[0348] "Emotional state" refers to the user's psychological state and includes information such as stress levels and emotional status.

[0349] A "personalized alert" is an alert message that is tailored to the user's emotional state and optimized for their individual needs.

[0350] "Disaster countermeasures" is a general term for plans and actions taken to prepare for natural disasters and minimize damage.

[0351] A "local government" is a public institution that carries out administrative and disaster response measures within a specific region.

[0352] This invention is a system that provides warnings and evacuation instructions that take into account the user's emotional state during a disaster. The system mainly consists of a server, terminals, an emotion engine, and various observation devices.

[0353] First, the server receives environmental information from multiple observation devices installed in each region to collect data such as precipitation, ground movement, water level, and wind speed. These observation devices utilize sensor technology to enable real-time data collection. The received data is stored on the server and analyzed by analytical devices, including artificial intelligence. This analysis uses historical disaster data and weather patterns to build predictive models for assessing future disaster risks.

[0354] The device then uses its built-in camera and microphone to analyze the user's facial expressions and voice tone, collecting emotional data. This allows for real-time assessment of the user's stress level and emotional state. The collected data is immediately transmitted to the server.

[0355] The emotion engine operates on the server and analyzes the user's emotional state. Utilizing natural language processing and emotion analysis techniques, the emotion engine generates the most appropriate warning messages and evacuation instructions for the user. For users experiencing high stress levels, it generates concise and reassuring messages, while for calm users, it creates messages with detailed instructions.

[0356] For example, when a typhoon approaches and the risk of flooding is deemed high, the server generates a standard warning message. However, if the emotion engine analyzes the user's emotional data and finds that their stress level is high, the message is adjusted to a more emotionally sensitive message such as, "Please remain calm. Move safely to the nearest shelter."

[0357] In this way, by providing warnings and instructions tailored to the individual emotional state of users, it is possible to promote appropriate actions during disasters.

[0358] Example of a prompt:

[0359] "Please customize typhoon flood warnings based on user sentiment data. Provide reassuring messages to highly stressed users and include detailed information for calmer users."

[0360] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0361] Step 1:

[0362] The server receives real-time environmental information regarding precipitation, ground movement, water level, and wind speed from observation devices installed in each region. The input consists of data streams from each sensor. The server aggregates this data and processes it by recording it in a database in a compatible format. The output is an environmental information dataset in an analyzable format.

[0363] Step 2:

[0364] The server transmits the collected environmental data to an analysis device that includes artificial intelligence. The input is the environmental information dataset obtained in Step 1. The AI ​​model performs data calculations to analyze the current data in comparison with past disaster data and assess disaster risk. During this process, machine learning algorithms are used, and the predictive model is updated. The output is the disaster risk assessment result for each region.

[0365] Step 3:

[0366] The device uses the user's built-in camera and microphone to collect emotional data such as facial expressions and voice tone. The input is the user's real-time visual and auditory emotional signals. The device analyzes this data and processes it to quantify the emotional state. The output is digital data of the user's stress level and emotional state.

[0367] Step 4:

[0368] The server sends the emotional data obtained in step 3 to the emotion engine for analysis. The input is digital data of the user's emotional state. The emotion engine uses natural language processing and emotion analysis algorithms to perform data calculations that generate alarm messages and evacuation instructions appropriate to the user's emotional state. The output is the adjusted alarm message and evacuation instruction.

[0369] Step 5:

[0370] The terminal notifies the user of a customized alarm message sent from the server. The input is the message generated in step 4. The terminal performs specific actions to convey the message to the user in visual and auditory ways. The output is information and instructions that the user can intuitively understand.

[0371] Through this step, evacuation instructions that take into account the user's emotional state are provided, promoting appropriate and swift action.

[0372] (Application Example 2)

[0373] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0374] Natural disasters are difficult to predict, requiring the provision of appropriate warnings and evacuation orders based on risk assessments. Furthermore, during disasters, responses that are sensitive to the emotional state of recipients are essential. However, current systems do not provide warnings or orders that take recipients' emotions into account, posing challenges to accelerating evacuation and ensuring safety.

[0375] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0376] In this invention, the server includes means for collecting environmental information from a plurality of sensing devices installed in each area; means for having an information processing device that receives and analyzes the environmental information, including machine learning; means for evaluating the degree of disaster risk and generating warnings and evacuation orders based on the analysis results; and means for evaluating the emotional state of the recipient and adjusting the warnings and evacuation orders according to the evaluation results. This makes it possible to provide optimized warnings and evacuation orders for the recipient.

[0377] A "sensing device" is a device that measures and collects information on the state of the global environment in real time, providing diverse environmental data such as precipitation, crustal movement, water level, and wind speed.

[0378] An "information processing device" is a computing device that receives collected environmental data and analyzes it using machine learning algorithms, and is responsible for assessing the risk of disasters and generating warnings.

[0379] "Machine learning" is a technology that learns patterns derived from past disaster and weather data and continuously improves disaster prediction models.

[0380] "Risk assessment" is the process of quantifying the likelihood of a natural disaster occurring based on analysis results and determining its severity.

[0381] A "warning and evacuation order" is an official message issued when there is a risk of disaster, intended to alert recipients and instruct them on safe actions.

[0382] A "recipient" is a person or community that receives a warning and evacuation order notification.

[0383] "Emotional state" refers to information that indicates the recipient's psychological and physiological responses, such as emotions like stress or relief, and is measured accordingly.

[0384] The system for carrying out this invention comprises multiple sensing devices, an information processing device, a user terminal, an emotion evaluation engine, and a communication infrastructure. The sensing devices are installed in each area and measure environmental information such as precipitation, crustal movement, wind speed, and water level in real time. The collected information is transmitted to the information processing device.

[0385] The information processing system incorporates machine learning technology, built using, for example, Python libraries and the Google Cloud AI platform. This allows for comparison and analysis of past disaster and weather data to assess the risk of disasters. Furthermore, warnings and evacuation orders are generated based on these analysis results.

[0386] The user terminal has a built-in camera and microphone, and analyzes the user's facial expressions and voice tone based on warning messages received from the server. Image analysis software such as OpenCV is used for this purpose. An emotion evaluation engine that assesses the user's emotional state integrates the results of facial recognition and voice analysis to determine whether the user is experiencing stress or tension.

[0387] In this way, the device displays warnings and instructions optimized for the user's emotions, prompting the user to take quick and effective action. For example, if a typhoon is approaching and the device determines that the user is feeling stressed, it will send a reassuring message such as, "Please stay calm. Please move to the nearest shelter."

[0388] As an implementation example, the following is an example of a prompt statement used when generating a response message during a disaster.

[0389] "Create messages that suggest safe and calming actions based on user sentiment data."

[0390] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0391] Step 1:

[0392] The server receives environmental information (precipitation, crustal movement, wind speed, water level, etc.) in real time from sensing devices installed in each region. The received data is preprocessed and filtered to remove unwanted noise. The input here is raw data from the sensing devices, and the output is clean environmental information.

[0393] Step 2:

[0394] The server inputs pre-processed environmental information into an information processing unit and applies a machine learning algorithm. This process uses a model that evaluates the risk of disasters using historical disaster data and generates prediction results. The server's input is clean environmental information, and its output is disaster risk and prediction information.

[0395] Step 3:

[0396] The server generates standard warnings and evacuation orders based on the risk assessment and prediction results. This phase utilizes an AI model to create optimal warning messages for disaster situations through the generated AI model. The input is the risk assessment results, and the output is the warnings and evacuation orders.

[0397] Step 4:

[0398] The terminal, along with receiving warnings and evacuation instructions from the server, uses the user's camera and microphone to assess the user's emotional state based on facial expressions and voice tone. An emotion assessment engine analyzes this data to determine the user's stress level. Input is video and audio data, and output is the user's emotional state.

[0399] Step 5:

[0400] The server receives output from the emotion assessment engine and adjusts warning messages and evacuation instructions according to the user's emotional state. Specifically, it generates simpler, more reassuring messages when the user is stressed, and includes more detailed instructions when the user is calm. The input here is the user's emotional state and a standard warning message, while the output is the adjusted warning message.

[0401] Step 6:

[0402] The device notifies the user of a tailored warning message. This notification is delivered both visually and audibly, ensuring intuitive understanding. The input here is the tailored warning message, and the output is the effective notification to the user.

[0403] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0404] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0405] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0406] [Third Embodiment]

[0407] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0408] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0409] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0410] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0411] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0412] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0413] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0414] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0415] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0416] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0417] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0418] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0419] This invention is implemented as a system that predicts the risk of natural disasters and enables rapid response by using environmental data acquired from observation devices installed in each region. Specifically, the system includes observation devices, a server, terminals, and users.

[0420] The server receives data such as rainfall, ground movement, water level, and wind speed from observation devices in real time. This allows for constant monitoring of the current situation in each region. The server then transfers the received data to an AI agent for analysis.

[0421] The AI ​​agent performs an analysis process, comparing it with past disaster data to assess the risk of disaster occurrence. In this process, the artificial intelligence uses statistical models to calculate the most probable risks from the data.

[0422] The server receives analysis results from the AI ​​agent and generates warning messages and evacuation orders if the risk is high. These messages are automatically created in clear and understandable natural language by the generating AI.

[0423] The generated alarms and evacuation orders are delivered to users via terminals. These terminals include smartphones and other communication devices that have the ability to alert users with voice and vibration. This allows users to receive important information in a timely manner.

[0424] The server will also present specific disaster response plans to each local government. These plans will include suggestions for optimal evacuation routes and detailed instructions regarding preventative measures. Local governments are expected to make swift decisions based on this information and take action to ensure the safety of their residents.

[0425] Furthermore, the system has the capability to continuously update the AI ​​agent's model by utilizing new data collected after a disaster occurs. This feedback loop improves prediction accuracy, thereby enhancing the system's ability to respond to future disasters.

[0426] As a concrete example, considering a scenario where there is a risk of landslides due to heavy rain, when the observation equipment detects abnormal rainfall and unstable ground movement, the server quickly processes the information, and the AI ​​agent determines it to be a high-risk situation. At this point, appropriate evacuation orders are immediately issued to the local government and residents, allowing for faster disaster preparedness than before.

[0427] The following describes the processing flow.

[0428] Step 1:

[0429] The server receives environmental data in real time from observation devices installed in each region. This includes information such as rainfall, ground movement, water level, and wind speed obtained via sensors. The server records and temporarily stores this data in a database.

[0430] Step 2:

[0431] The server transfers the collected data to the AI ​​agent. The AI ​​agent receives this data and performs analysis using historical disaster and weather data. Machine learning algorithms are used in the analysis to calculate the probability of a disaster occurring.

[0432] Step 3:

[0433] Once the AI ​​agent completes its analysis, the server assesses the disaster risk based on the results. If it determines that the risk exceeds a set threshold, it sets a flag for use in the next step.

[0434] Step 4:

[0435] The server uses AI to automatically generate warning messages and evacuation orders. The generated messages include specific details such as the likelihood of a disaster, recommended emergency measures, and evacuation routes.

[0436] Step 5:

[0437] The server sends the generated alarms and evacuation instructions to the terminal. The terminal receives them and provides the information to the user as visual and auditory alerts.

[0438] Step 6:

[0439] Based on the alarms and instructions received by the user, evacuation actions will be initiated. The server will continuously monitor the latest relevant data and will be ready to send additional instructions as needed.

[0440] Step 7:

[0441] When a disaster occurs, the server sends subsequent observation results back to the AI ​​agent to update the model. This enhances the system's ability to respond to future disasters and improves prediction accuracy.

[0442] (Example 1)

[0443] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0444] In modern society, accurate and rapid risk prediction and information provision are essential to minimize damage from natural disasters. However, current systems struggle to immediately analyze detailed environmental information for each region and provide warnings and evacuation orders in a timely manner. Therefore, a more accurate and real-time warning system is needed.

[0445] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0446] In this invention, the server includes means for collecting environmental information from a plurality of sensor devices installed in each region, means for having a processing device that includes a generative algorithm for receiving and analyzing the environmental information, and means for evaluating the risk of natural disasters and generating alerts and evacuation orders based on the analysis results. This enables highly accurate risk assessment based on environmental data for each region and the provision of rapid warnings and evacuation orders.

[0447] A "sensor device" is a device used to detect and measure environmental information in real time, and has the function of measuring precipitation, crustal movement, water level, and wind speed, among other things.

[0448] "Environmental information" refers to various data related to nature and weather measured by sensor devices, including information such as precipitation, crustal movement, water level, and wind speed.

[0449] "Generative algorithms" refer to computational methods for processing environmental information and conducting natural disaster risk assessments and generating alerts, utilizing artificial intelligence and machine learning models.

[0450] A "processing device" is a computer system that uses generative algorithms to analyze environmental information, assess disaster risks based on the results, and generate necessary alerts and evacuation orders.

[0451] "Natural disaster risk" is an evaluation index that predicts disaster events that may occur under specific environmental conditions and indicates the probability of their occurrence.

[0452] An "alert" is a warning or notification message issued to users or relevant organizations to draw their attention when a specific risk is identified.

[0453] An "evacuation order" is a message that instructs users on what actions they should take to ensure their safety, based on a specific natural disaster risk.

[0454] "Public institutions" refer to organizations responsible for disaster response, such as local governments and government agencies, which provide guidance and support to ensure the safety of local residents.

[0455] This invention describes an embodiment of a system that acquires environmental information in real time, predicts the risk of natural disasters, and provides rapid warnings and evacuation orders.

[0456] The server collects environmental information from sensor devices installed in each region. Specifically, it receives data from rain sensors, accelerometers that detect ground movement, water level sensors, and wind speed sensors. This data is stored in a database on the server via the internet.

[0457] Based on the received environmental information, the server analyzes the data using generative algorithms. Deep learning frameworks such as TensorFlow and PyTorch are used for this analysis. This allows the server to compare past disaster information with current environmental information and assess the risk of natural disasters. The analysis results indicate when a disaster is predicted if a certain threshold is exceeded.

[0458] Upon receiving the analysis results, the server uses a generative AI model to generate alert messages and evacuation orders in natural language. These messages are provided in a format that is easy for users to understand. For example, a notification might read, "The risk of landslides due to heavy rain is increasing in area A. Please evacuate immediately to ensure your safety."

[0459] The generated alerts and evacuation orders are delivered to users via a terminal. This terminal can be a smartphone, tablet, or communication device including a local disaster prevention radio system. This allows users to receive warnings via voice or vibration.

[0460] The server also provides information to public authorities. This information includes specific disaster prevention measures, such as detailed instructions on optimal evacuation routes and preventative measures. Public authorities can use this information to implement appropriate measures to ensure the safety of local residents.

[0461] Furthermore, after a disaster occurs, the server updates the generative algorithm model using newly collected data. This feedback loop improves the accuracy of future predictions and strengthens the system's responsiveness.

[0462] For example, suppose in an area where heavy rainfall is predicted, a sensor device detects higher-than-usual rainfall, and related data indicating unstable ground conditions is recorded. Based on this information, the server recognizes that the risk of landslides has increased and generates appropriate instructions using pre-prepared prompts.

[0463] An example of a prompt message could be: "A prompt for a generative AI model that detects the risk of landslides due to heavy rain and sends evacuation instructions to a smartphone." By entering this prompt, the server can quickly and appropriately create and provide an alert.

[0464] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0465] Step 1:

[0466] The server collects environmental information in real time from sensor devices installed in each region. Inputs include digital data from precipitation sensors, crustal motion sensors, water level sensors, and wind speed sensors. This data is sent to the server's database via the network. Outputs include environmental data organized in chronological order. This data is stored for use in subsequent analysis steps.

[0467] Step 2:

[0468] The server inputs the collected environmental information into a generative algorithm and analyzes the data. This process references past disaster datasets and compares them with current data. Data processing includes noise reduction and normalization to prepare the dataset for the generative AI model to perform risk assessment. The output generates a risk score, quantifying specific disaster risks.

[0469] Step 3:

[0470] The server automatically generates alert messages and evacuation orders using a generation AI model based on the generated risk score. Instructions are given to the model using prompts to construct natural language messages. The input includes the risk score and prompts, and the output is a specific and clear warning message. A message in the format of, "The risk of landslides due to heavy rain is high in area A. Please evacuate immediately to ensure your safety," is generated.

[0471] Step 4:

[0472] The device receives alert messages and evacuation instructions sent from the server. Input is message data from the server, and output is alarm notifications via the device's display screen, audio, and vibration. Specifically, the smartphone emits an emergency notification sound, and the screen displays instructions for the necessary actions.

[0473] Step 5:

[0474] The server sends generated alerts and evacuation orders to public authorities and provides specific disaster prevention measures. Input includes detailed data on disaster risk, and output generates detailed guidelines on optimal evacuation routes and preventative measures. This information is distributed to public authorities via email and a dedicated communication system.

[0475] Step 6:

[0476] The server updates its generative algorithm model using new environmental data obtained after a disaster. In this process, the latest disaster data is used as input, and the generative AI model is retrained through a feedback loop. The output is a newly constructed model with improved prediction accuracy, thereby enhancing future predictive capabilities.

[0477] (Application Example 1)

[0478] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0479] Predicting and responding quickly to natural disasters is a critical challenge, especially in densely populated urban areas. Existing methods are insufficient for real-time, comprehensive situation assessment and for issuing appropriate and timely evacuation orders to residents, resulting in loss of life and property. This invention aims to improve the accuracy of disaster risk prediction based on observational data and to provide local governments and residents with quick and accurate information.

[0480] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0481] In this invention, the server includes means for collecting and analyzing observation data in real time, means for evaluating the risk of disaster using artificial intelligence and generating warnings and evacuation orders, and means for notifying users of information via terminal devices and allowing them to confirm evacuation routes. This enables highly accurate disaster prediction based on observation data and rapid information transmission.

[0482] An "observation device" is a device installed in each region to measure and collect environmental data in real time.

[0483] "Environmental data" refers to information about natural phenomena necessary for assessing disaster risk, such as rainfall, ground movement, water level, and wind speed.

[0484] A "processing device" is a computer device that receives environmental data and analyzes it using artificial intelligence.

[0485] "Artificial intelligence" is a technology that uses statistical models and historical disaster information to predict the risk of disaster from environmental data.

[0486] A "warning" is a message intended to inform users of the occurrence of a disaster or the danger it poses, and to urge them to take precautions.

[0487] An "evacuation order" is a set of specific action guidelines provided to users to ensure their safety during a disaster.

[0488] A "terminal device" refers to a smartphone or other communication device used by a user to receive notifications of alarms or evacuation orders.

[0489] A "local government" is a local public entity that has jurisdiction over a specific area and is responsible for ensuring the safety of residents in the event of a disaster.

[0490] A "disaster response plan" refers to specific proposals for actions and measures that local governments should take depending on the risk of disaster.

[0491] The system that realizes this invention includes observation devices, a server, a terminal, and a user. The server receives environmental data in real time from multiple observation devices. These observation devices are installed in the area and measure environmental data such as rainfall, ground movement, water level, and wind speed. The server sends the received data to an AI agent, which performs data analysis using TensorFlow or similar software. This analysis compares the data with past disaster information and evaluates the risk of disaster based on a statistical model.

[0492] Based on the analysis results, the server uses a generative AI to create warnings and evacuation instructions in natural language. The generative AI uses a natural language generation tool. The generated results are sent to the device via Google Firebase. The device, such as the user's smartphone, notifies the user of the warnings and evacuation instructions via voice and vibration. Furthermore, the device also provides the user with information on evacuation routes.

[0493] As a concrete example, consider a scenario where heavy rainfall poses a risk of landslides. When the observation device detects abnormal rainfall and unstable ground movement, the server quickly processes the information, and the AI ​​agent determines that the risk is high. At this point, the AI ​​generates a prompt message such as, "There is a risk of landslides due to heavy rainfall. Begin evacuation immediately and check the designated evacuation route." This allows users to receive important information in real time and take swift action.

[0494] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0495] Step 1:

[0496] The server collects environmental data in real time from observation devices installed in each region. The data transmitted from these devices includes information such as rainfall, ground movement, water level, and wind speed. The input environmental data is stored in a database.

[0497] Step 2:

[0498] The server transfers the collected environmental data to the AI ​​agent for analysis. The AI ​​agent uses TensorFlow to calculate the risk of damage by comparing it with past disaster data. In this process, the input is the environmental data, and the output is the result of the risk assessment. As part of the data processing, data cleansing is performed using an anomaly detection algorithm.

[0499] Step 3:

[0500] The server generates alarms and evacuation instructions using a generative AI model based on the analysis results from the AI ​​agent. The generative AI model converts the analysis results into natural language and outputs a message to be notified to the user. At this time, a natural language generation algorithm based on the prompt text is in operation.

[0501] Step 4:

[0502] The terminal notifies the user of alarms and evacuation orders received from the server. Notifications are sent via smartphone, using voice and vibration to alert the user. Input is the generated message, and output is the user's recognition. Google Firebase is used as the notification protocol.

[0503] Step 5:

[0504] Based on the information received through the device, the user confirms the designated evacuation route and initiates appropriate evacuation actions. The prompt messages clearly define the actions the user should take, enabling rapid safety assurance.

[0505] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0506] This invention provides a system that offers more effective warnings and evacuation instructions by taking user emotions into account in the prediction and risk assessment of natural disasters. The system includes observation devices, a server, terminals, a user, and an emotion engine.

[0507] First, the server receives environmental data in real time from observation devices installed in each region. This includes information such as rainfall, ground movement, water level, and wind speed. The server records this data in a database and sends it to an AI agent. The AI ​​agent uses historical disaster data and weather data to analyze the data and assess the risk of disaster.

[0508] Upon receiving the analysis results, the server first generates standard alarm messages and evacuation instructions. During this process, an emotion engine intervenes to recognize the user's stress level and emotional state. For example, it analyzes the user's facial expressions, voice tone, and touch behavior through the device's built-in camera and sensors to determine their emotional status.

[0509] The emotion engine analyzes the user's emotional state and customizes warning messages and evacuation instructions accordingly. Specifically, if the user is in a high-stress state, a more concise and reassuring message is sent. On the other hand, users in a calm state are provided with more detailed information and clearer instructions.

[0510] The device displays this personalized message to the user, notifying them through visual and auditory means for intuitive understanding. This allows users to receive evacuation instructions in a way that best suits their emotional state, enabling them to take swift action.

[0511] Furthermore, disaster response plans are also adjusted by the emotion engine. The server adjusts the response plans provided to local governments, taking into account the overall sentiment data of residents, to be useful for local communication strategies. In this way, utilizing sentiment information can enhance the overall responsiveness and effectiveness of the system.

[0512] For example, if the system determines there is a risk of flooding due to a typhoon, it will send a general warning via a standard communication protocol. However, if the emotion engine detects that the user is under high stress, it will send an additional message with specific instructions such as, "Avoid panicking and head to the nearest shelter." This approach is expected to reduce user stress and increase the rate of safety.

[0513] The following describes the processing flow.

[0514] Step 1:

[0515] The server receives environmental data in real time from observation devices installed in each region. The observation devices collect information such as rainfall, ground movement, water level, and wind speed, and this data is recorded in the server's database.

[0516] Step 2:

[0517] The server sends the collected data to the AI ​​agent. The AI ​​agent uses historical disaster data and weather data to analyze and assess disaster risk. The assessment results quantify the degree of risk and are used in the next step.

[0518] Step 3:

[0519] The server generates standard alarm messages and evacuation instructions based on the analysis results of the AI ​​agent. The generating AI uses natural language processing technology to convert the alarms into easily understandable text.

[0520] Step 4:

[0521] The device uses its built-in camera and microphone to input the user's facial expressions and voice tone into the emotion engine. Based on the data obtained, the system determines the user's stress level and emotional state.

[0522] Step 5:

[0523] The server uses the results of the emotion engine's analysis to modify or refine alarm messages and evacuation instructions according to the user's emotional state. For example, simple and reassuring language is used for users in a high-stress state.

[0524] Step 6:

[0525] The device notifies the user of coordinated alarm messages and evacuation instructions. Notifications are delivered via visual display, audio message, or vibration, and are designed to allow the user to quickly understand the content.

[0526] Step 7:

[0527] Users act based on the instructions they receive. Emotionally sensitive information provision enables users to take calm and appropriate evacuation actions.

[0528] Step 8:

[0529] The server uses new emotional data collected after the disaster to update the AI ​​agent's model. The updated model will be used to provide even more accurate risk assessment and emotional response during the next disaster.

[0530] (Example 2)

[0531] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0532] In recent years, the increasing frequency of natural disasters has highlighted the need for safe and effective evacuation plans and warning systems. However, conventional systems send uniform warnings without considering the emotional state of users, which can lead to panic and make it difficult to convey accurate information. Furthermore, the lack of community-based disaster countermeasures that take into account the emotions of the entire population is also a challenge.

[0533] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0534] In this invention, the server includes means for collecting environmental information from multiple observation devices installed in each region, means for having an analysis device including artificial intelligence that receives and analyzes the environmental information, and means for recognizing the emotional state of the user and adjusting the warnings and evacuation orders according to the emotion. This provides personalized warnings and orders that take into account the user's emotions, minimizes confusion during disasters, and enables effective disaster countermeasures that take into account the emotions of the entire community.

[0535] "Observation equipment" refers to devices deployed in each region to collect environmental information in real time.

[0536] "Environmental information" refers to data such as precipitation, land deformation, water levels, and wind speed used to detect signs of natural disasters.

[0537] "Artificial intelligence" is an advanced information processing technology used to analyze received environmental information and assess disaster risks.

[0538] An "analysis device" is a computing device used to predict disasters based on environmental information and historical data.

[0539] A "user" is an individual or group that receives warnings and evacuation orders from this system.

[0540] "Emotional state" refers to the user's psychological state and includes information such as stress levels and emotional status.

[0541] A "personalized alert" is an alert message that is tailored to the user's emotional state and optimized for their individual needs.

[0542] "Disaster countermeasures" is a general term for plans and actions taken to prepare for natural disasters and minimize damage.

[0543] A "local government" is a public institution that carries out administrative and disaster response measures within a specific region.

[0544] This invention is a system that provides warnings and evacuation instructions that take into account the user's emotional state during a disaster. The system mainly consists of a server, terminals, an emotion engine, and various observation devices.

[0545] First, the server receives environmental information from multiple observation devices installed in each region to collect data such as precipitation, ground movement, water level, and wind speed. These observation devices utilize sensor technology to enable real-time data collection. The received data is stored on the server and analyzed by analytical devices, including artificial intelligence. This analysis uses historical disaster data and weather patterns to build predictive models for assessing future disaster risks.

[0546] The device then uses its built-in camera and microphone to analyze the user's facial expressions and voice tone, collecting emotional data. This allows for real-time assessment of the user's stress level and emotional state. The collected data is immediately transmitted to the server.

[0547] The emotion engine operates on the server and analyzes the user's emotional state. Utilizing natural language processing and emotion analysis techniques, the emotion engine generates the most appropriate warning messages and evacuation instructions for the user. For users experiencing high stress levels, it generates concise and reassuring messages, while for calm users, it creates messages with detailed instructions.

[0548] For example, when a typhoon approaches and the risk of flooding is deemed high, the server generates a standard warning message. However, if the emotion engine analyzes the user's emotional data and finds that their stress level is high, the message is adjusted to a more emotionally sensitive message such as, "Please remain calm. Move safely to the nearest shelter."

[0549] In this way, by providing warnings and instructions tailored to the individual emotional state of users, it is possible to promote appropriate actions during disasters.

[0550] Example of a prompt:

[0551] "Please customize typhoon flood warnings based on user sentiment data. Provide reassuring messages to highly stressed users and include detailed information for calmer users."

[0552] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0553] Step 1:

[0554] The server receives real-time environmental information regarding precipitation, ground movement, water level, and wind speed from observation devices installed in each region. The input consists of data streams from each sensor. The server aggregates this data and processes it by recording it in a database in a compatible format. The output is an environmental information dataset in an analyzable format.

[0555] Step 2:

[0556] The server transmits the collected environmental data to an analysis device that includes artificial intelligence. The input is the environmental information dataset obtained in Step 1. The AI ​​model performs data calculations to analyze the current data in comparison with past disaster data and assess disaster risk. During this process, machine learning algorithms are used, and the predictive model is updated. The output is the disaster risk assessment result for each region.

[0557] Step 3:

[0558] The device uses the user's built-in camera and microphone to collect emotional data such as facial expressions and voice tone. The input is the user's real-time visual and auditory emotional signals. The device analyzes this data and processes it to quantify the emotional state. The output is digital data of the user's stress level and emotional state.

[0559] Step 4:

[0560] The server sends the emotional data obtained in step 3 to the emotion engine for analysis. The input is digital data of the user's emotional state. The emotion engine uses natural language processing and emotion analysis algorithms to perform data calculations that generate alarm messages and evacuation instructions appropriate to the user's emotional state. The output is the adjusted alarm message and evacuation instruction.

[0561] Step 5:

[0562] The terminal notifies the user of a customized alarm message sent from the server. The input is the message generated in step 4. The terminal performs specific actions to convey the message to the user in visual and auditory ways. The output is information and instructions that the user can intuitively understand.

[0563] Through this step, evacuation instructions that take into account the user's emotional state are provided, promoting appropriate and swift action.

[0564] (Application Example 2)

[0565] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0566] Natural disasters are difficult to predict, requiring the provision of appropriate warnings and evacuation orders based on risk assessments. Furthermore, during disasters, responses that are sensitive to the emotional state of recipients are essential. However, current systems do not provide warnings or orders that take recipients' emotions into account, posing challenges to accelerating evacuation and ensuring safety.

[0567] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0568] In this invention, the server includes means for collecting environmental information from a plurality of sensing devices installed in each area; means for having an information processing device that receives and analyzes the environmental information, including machine learning; means for evaluating the degree of disaster risk and generating warnings and evacuation orders based on the analysis results; and means for evaluating the emotional state of the recipient and adjusting the warnings and evacuation orders according to the evaluation results. This makes it possible to provide optimized warnings and evacuation orders for the recipient.

[0569] A "sensing device" is a device that measures and collects information on the state of the global environment in real time, providing diverse environmental data such as precipitation, crustal movement, water level, and wind speed.

[0570] An "information processing device" is a computing device that receives collected environmental data and analyzes it using machine learning algorithms, and is responsible for assessing the risk of disasters and generating warnings.

[0571] "Machine learning" is a technology that learns patterns derived from past disaster and weather data and continuously improves disaster prediction models.

[0572] "Risk assessment" is the process of quantifying the likelihood of a natural disaster occurring based on analysis results and determining its severity.

[0573] A "warning and evacuation order" is an official message issued when there is a risk of disaster, intended to alert recipients and instruct them on safe actions.

[0574] A "recipient" is a person or community that receives a warning and evacuation order notification.

[0575] "Emotional state" refers to information that indicates the recipient's psychological and physiological responses, such as emotions like stress or relief, and is measured accordingly.

[0576] The system for carrying out this invention comprises multiple sensing devices, an information processing device, a user terminal, an emotion evaluation engine, and a communication infrastructure. The sensing devices are installed in each area and measure environmental information such as precipitation, crustal movement, wind speed, and water level in real time. The collected information is transmitted to the information processing device.

[0577] The information processing system incorporates machine learning technology, built using, for example, Python libraries and the Google Cloud AI platform. This allows for comparison and analysis of past disaster and weather data to assess the risk of disasters. Furthermore, warnings and evacuation orders are generated based on these analysis results.

[0578] The user terminal has a built-in camera and microphone, and analyzes the user's facial expressions and voice tone based on warning messages received from the server. Image analysis software such as OpenCV is used for this purpose. An emotion evaluation engine that assesses the user's emotional state integrates the results of facial recognition and voice analysis to determine whether the user is experiencing stress or tension.

[0579] In this way, the device displays warnings and instructions optimized for the user's emotions, prompting the user to take quick and effective action. For example, if a typhoon is approaching and the device determines that the user is feeling stressed, it will send a reassuring message such as, "Please stay calm. Please move to the nearest shelter."

[0580] As an implementation example, the following is an example of a prompt statement used when generating a response message during a disaster.

[0581] "Create messages that suggest safe and calming actions based on user sentiment data."

[0582] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0583] Step 1:

[0584] The server receives environmental information (precipitation, crustal movement, wind speed, water level, etc.) in real time from sensing devices installed in each region. The received data is preprocessed and filtered to remove unwanted noise. The input here is raw data from the sensing devices, and the output is clean environmental information.

[0585] Step 2:

[0586] The server inputs pre-processed environmental information into an information processing unit and applies a machine learning algorithm. This process uses a model that evaluates the risk of disasters using historical disaster data and generates prediction results. The server's input is clean environmental information, and its output is disaster risk and prediction information.

[0587] Step 3:

[0588] The server generates standard warnings and evacuation orders based on the risk assessment and prediction results. This phase utilizes an AI model to create optimal warning messages for disaster situations through the generated AI model. The input is the risk assessment results, and the output is the warnings and evacuation orders.

[0589] Step 4:

[0590] The terminal, along with receiving warnings and evacuation instructions from the server, uses the user's camera and microphone to assess the user's emotional state based on facial expressions and voice tone. An emotion assessment engine analyzes this data to determine the user's stress level. Input is video and audio data, and output is the user's emotional state.

[0591] Step 5:

[0592] The server receives output from the emotion assessment engine and adjusts warning messages and evacuation instructions according to the user's emotional state. Specifically, it generates simpler, more reassuring messages when the user is stressed, and includes more detailed instructions when the user is calm. The input here is the user's emotional state and a standard warning message, while the output is the adjusted warning message.

[0593] Step 6:

[0594] The device notifies the user of a tailored warning message. This notification is delivered both visually and audibly, ensuring intuitive understanding. The input here is the tailored warning message, and the output is the effective notification to the user.

[0595] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0596] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0597] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0598] [Fourth Embodiment]

[0599] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0600] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0601] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0602] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0603] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0604] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0605] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0606] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0607] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0608] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0609] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0610] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0611] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0612] This invention is implemented as a system that predicts the risk of natural disasters and enables rapid response by using environmental data acquired from observation devices installed in each region. Specifically, the system includes observation devices, a server, terminals, and users.

[0613] The server receives data such as rainfall, ground movement, water level, and wind speed from observation devices in real time. This allows for constant monitoring of the current situation in each region. The server then transfers the received data to an AI agent for analysis.

[0614] The AI ​​agent performs an analysis process, comparing it with past disaster data to assess the risk of disaster occurrence. In this process, the artificial intelligence uses statistical models to calculate the most probable risks from the data.

[0615] The server receives analysis results from the AI ​​agent and generates warning messages and evacuation orders if the risk is high. These messages are automatically created in clear and understandable natural language by the generating AI.

[0616] The generated alarms and evacuation orders are delivered to users via terminals. These terminals include smartphones and other communication devices that have the ability to alert users with voice and vibration. This allows users to receive important information in a timely manner.

[0617] The server will also present specific disaster response plans to each local government. These plans will include suggestions for optimal evacuation routes and detailed instructions regarding preventative measures. Local governments are expected to make swift decisions based on this information and take action to ensure the safety of their residents.

[0618] Furthermore, the system has the capability to continuously update the AI ​​agent's model by utilizing new data collected after a disaster occurs. This feedback loop improves prediction accuracy, thereby enhancing the system's ability to respond to future disasters.

[0619] As a concrete example, considering a scenario where there is a risk of landslides due to heavy rain, when the observation equipment detects abnormal rainfall and unstable ground movement, the server quickly processes the information, and the AI ​​agent determines it to be a high-risk situation. At this point, appropriate evacuation orders are immediately issued to the local government and residents, allowing for faster disaster preparedness than before.

[0620] The following describes the processing flow.

[0621] Step 1:

[0622] The server receives environmental data in real time from observation devices installed in each region. This includes information such as rainfall, ground movement, water level, and wind speed obtained via sensors. The server records and temporarily stores this data in a database.

[0623] Step 2:

[0624] The server transfers the collected data to the AI ​​agent. The AI ​​agent receives this data and performs analysis using historical disaster and weather data. Machine learning algorithms are used in the analysis to calculate the probability of a disaster occurring.

[0625] Step 3:

[0626] Once the AI ​​agent completes its analysis, the server assesses the disaster risk based on the results. If it determines that the risk exceeds a set threshold, it sets a flag for use in the next step.

[0627] Step 4:

[0628] The server uses AI to automatically generate warning messages and evacuation orders. The generated messages include specific details such as the likelihood of a disaster, recommended emergency measures, and evacuation routes.

[0629] Step 5:

[0630] The server sends the generated alarms and evacuation instructions to the terminal. The terminal receives them and provides the information to the user as visual and auditory alerts.

[0631] Step 6:

[0632] Based on the alarms and instructions received by the user, evacuation actions will be initiated. The server will continuously monitor the latest relevant data and will be ready to send additional instructions as needed.

[0633] Step 7:

[0634] When a disaster occurs, the server sends subsequent observation results back to the AI ​​agent to update the model. This enhances the system's ability to respond to future disasters and improves prediction accuracy.

[0635] (Example 1)

[0636] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0637] In modern society, accurate and rapid risk prediction and information provision are essential to minimize damage from natural disasters. However, current systems struggle to immediately analyze detailed environmental information for each region and provide warnings and evacuation orders in a timely manner. Therefore, a more accurate and real-time warning system is needed.

[0638] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0639] In this invention, the server includes means for collecting environmental information from a plurality of sensor devices installed in each region, means for having a processing device that includes a generative algorithm for receiving and analyzing the environmental information, and means for evaluating the risk of natural disasters and generating alerts and evacuation orders based on the analysis results. This enables highly accurate risk assessment based on environmental data for each region and the provision of rapid warnings and evacuation orders.

[0640] A "sensor device" is a device used to detect and measure environmental information in real time, and has the function of measuring precipitation, crustal movement, water level, and wind speed, among other things.

[0641] "Environmental information" refers to various data related to nature and weather measured by sensor devices, including information such as precipitation, crustal movement, water level, and wind speed.

[0642] "Generative algorithms" refer to computational methods for processing environmental information and conducting natural disaster risk assessments and generating alerts, utilizing artificial intelligence and machine learning models.

[0643] A "processing device" is a computer system that uses generative algorithms to analyze environmental information, assess disaster risks based on the results, and generate necessary alerts and evacuation orders.

[0644] "Natural disaster risk" is an evaluation index that predicts disaster events that may occur under specific environmental conditions and indicates the probability of their occurrence.

[0645] An "alert" is a warning or notification message issued to users or relevant organizations to draw their attention when a specific risk is identified.

[0646] An "evacuation order" is a message that instructs users on what actions they should take to ensure their safety, based on a specific natural disaster risk.

[0647] "Public institutions" refer to organizations responsible for disaster response, such as local governments and government agencies, which provide guidance and support to ensure the safety of local residents.

[0648] This invention describes an embodiment of a system that acquires environmental information in real time, predicts the risk of natural disasters, and provides rapid warnings and evacuation orders.

[0649] The server collects environmental information from sensor devices installed in each region. Specifically, it receives data from rain sensors, accelerometers that detect ground movement, water level sensors, and wind speed sensors. This data is stored in a database on the server via the internet.

[0650] Based on the received environmental information, the server analyzes the data using generative algorithms. Deep learning frameworks such as TensorFlow and PyTorch are used for this analysis. This allows the server to compare past disaster information with current environmental information and assess the risk of natural disasters. The analysis results indicate when a disaster is predicted if a certain threshold is exceeded.

[0651] Upon receiving the analysis results, the server uses a generative AI model to generate alert messages and evacuation orders in natural language. These messages are provided in a format that is easy for users to understand. For example, a notification might read, "The risk of landslides due to heavy rain is increasing in area A. Please evacuate immediately to ensure your safety."

[0652] The generated alerts and evacuation orders are delivered to users via a terminal. This terminal can be a smartphone, tablet, or communication device including a local disaster prevention radio system. This allows users to receive warnings via voice or vibration.

[0653] The server also provides information to public authorities. This information includes specific disaster prevention measures, such as detailed instructions on optimal evacuation routes and preventative measures. Public authorities can use this information to implement appropriate measures to ensure the safety of local residents.

[0654] Furthermore, after a disaster occurs, the server updates the generative algorithm model using newly collected data. This feedback loop improves the accuracy of future predictions and strengthens the system's responsiveness.

[0655] For example, suppose in an area where heavy rainfall is predicted, a sensor device detects higher-than-usual rainfall, and related data indicating unstable ground conditions is recorded. Based on this information, the server recognizes that the risk of landslides has increased and generates appropriate instructions using pre-prepared prompts.

[0656] An example of a prompt message could be: "A prompt for a generative AI model that detects the risk of landslides due to heavy rain and sends evacuation instructions to a smartphone." By entering this prompt, the server can quickly and appropriately create and provide an alert.

[0657] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0658] Step 1:

[0659] The server collects environmental information in real time from sensor devices installed in each region. Inputs include digital data from precipitation sensors, crustal motion sensors, water level sensors, and wind speed sensors. This data is sent to the server's database via the network. Outputs include environmental data organized in chronological order. This data is stored for use in subsequent analysis steps.

[0660] Step 2:

[0661] The server inputs the collected environmental information into a generative algorithm and analyzes the data. This process references past disaster datasets and compares them with current data. Data processing includes noise reduction and normalization to prepare the dataset for the generative AI model to perform risk assessment. The output generates a risk score, quantifying specific disaster risks.

[0662] Step 3:

[0663] The server automatically generates alert messages and evacuation orders using a generation AI model based on the generated risk score. Instructions are given to the model using prompts to construct natural language messages. The input includes the risk score and prompts, and the output is a specific and clear warning message. A message in the format of, "The risk of landslides due to heavy rain is high in area A. Please evacuate immediately to ensure your safety," is generated.

[0664] Step 4:

[0665] The device receives alert messages and evacuation instructions sent from the server. Input is message data from the server, and output is alarm notifications via the device's display screen, audio, and vibration. Specifically, the smartphone emits an emergency notification sound, and the screen displays instructions for the necessary actions.

[0666] Step 5:

[0667] The server sends generated alerts and evacuation orders to public authorities and provides specific disaster prevention measures. Input includes detailed data on disaster risk, and output generates detailed guidelines on optimal evacuation routes and preventative measures. This information is distributed to public authorities via email and a dedicated communication system.

[0668] Step 6:

[0669] The server updates its generative algorithm model using new environmental data obtained after a disaster. In this process, the latest disaster data is used as input, and the generative AI model is retrained through a feedback loop. The output is a newly constructed model with improved prediction accuracy, thereby enhancing future predictive capabilities.

[0670] (Application Example 1)

[0671] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0672] Predicting and responding quickly to natural disasters is a critical challenge, especially in densely populated urban areas. Existing methods are insufficient for real-time, comprehensive situation assessment and for issuing appropriate and timely evacuation orders to residents, resulting in loss of life and property. This invention aims to improve the accuracy of disaster risk prediction based on observational data and to provide local governments and residents with quick and accurate information.

[0673] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0674] In this invention, the server includes means for collecting and analyzing observation data in real time, means for evaluating the risk of disaster using artificial intelligence and generating warnings and evacuation orders, and means for notifying users of information via terminal devices and allowing them to confirm evacuation routes. This enables highly accurate disaster prediction based on observation data and rapid information transmission.

[0675] An "observation device" is a device installed in each region to measure and collect environmental data in real time.

[0676] "Environmental data" refers to information about natural phenomena necessary for assessing disaster risk, such as rainfall, ground movement, water level, and wind speed.

[0677] A "processing device" is a computer device that receives environmental data and analyzes it using artificial intelligence.

[0678] "Artificial intelligence" is a technology that uses statistical models and historical disaster information to predict the risk of disaster from environmental data.

[0679] A "warning" is a message intended to inform users of the occurrence of a disaster or the danger it poses, and to urge them to take precautions.

[0680] An "evacuation order" is a set of specific action guidelines provided to users to ensure their safety during a disaster.

[0681] A "terminal device" refers to a smartphone or other communication device used by a user to receive notifications of alarms or evacuation orders.

[0682] A "local government" is a local public entity that has jurisdiction over a specific area and is responsible for ensuring the safety of residents in the event of a disaster.

[0683] A "disaster response plan" refers to specific proposals for actions and measures that local governments should take depending on the risk of disaster.

[0684] The system that realizes this invention includes observation devices, a server, a terminal, and a user. The server receives environmental data in real time from multiple observation devices. These observation devices are installed in the area and measure environmental data such as rainfall, ground movement, water level, and wind speed. The server sends the received data to an AI agent, which performs data analysis using TensorFlow or similar software. This analysis compares the data with past disaster information and evaluates the risk of disaster based on a statistical model.

[0685] Based on the analysis results, the server uses a generative AI to create warnings and evacuation instructions in natural language. The generative AI uses a natural language generation tool. The generated results are sent to the device via Google Firebase. The device, such as the user's smartphone, notifies the user of the warnings and evacuation instructions via voice and vibration. Furthermore, the device also provides the user with information on evacuation routes.

[0686] As a concrete example, consider a scenario where heavy rainfall poses a risk of landslides. When the observation device detects abnormal rainfall and unstable ground movement, the server quickly processes the information, and the AI ​​agent determines that the risk is high. At this point, the AI ​​generates a prompt message such as, "There is a risk of landslides due to heavy rainfall. Begin evacuation immediately and check the designated evacuation route." This allows users to receive important information in real time and take swift action.

[0687] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0688] Step 1:

[0689] The server collects environmental data in real time from observation devices installed in each region. The data transmitted from these devices includes information such as rainfall, ground movement, water level, and wind speed. The input environmental data is stored in a database.

[0690] Step 2:

[0691] The server transfers the collected environmental data to the AI ​​agent for analysis. The AI ​​agent uses TensorFlow to calculate the risk of damage by comparing it with past disaster data. In this process, the input is the environmental data, and the output is the result of the risk assessment. As part of the data processing, data cleansing is performed using an anomaly detection algorithm.

[0692] Step 3:

[0693] The server generates alarms and evacuation instructions using a generative AI model based on the analysis results from the AI ​​agent. The generative AI model converts the analysis results into natural language and outputs a message to be notified to the user. At this time, a natural language generation algorithm based on the prompt text is in operation.

[0694] Step 4:

[0695] The terminal notifies the user of alarms and evacuation orders received from the server. Notifications are sent via smartphone, using voice and vibration to alert the user. Input is the generated message, and output is the user's recognition. Google Firebase is used as the notification protocol.

[0696] Step 5:

[0697] Based on the information received through the device, the user confirms the designated evacuation route and initiates appropriate evacuation actions. The prompt messages clearly define the actions the user should take, enabling rapid safety assurance.

[0698] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0699] This invention provides a system that offers more effective warnings and evacuation instructions by taking user emotions into account in the prediction and risk assessment of natural disasters. The system includes observation devices, a server, terminals, a user, and an emotion engine.

[0700] First, the server receives environmental data in real time from observation devices installed in each region. This includes information such as rainfall, ground movement, water level, and wind speed. The server records this data in a database and sends it to an AI agent. The AI ​​agent uses historical disaster data and weather data to analyze the data and assess the risk of disaster.

[0701] Upon receiving the analysis results, the server first generates standard alarm messages and evacuation instructions. During this process, an emotion engine intervenes to recognize the user's stress level and emotional state. For example, it analyzes the user's facial expressions, voice tone, and touch behavior through the device's built-in camera and sensors to determine their emotional status.

[0702] The emotion engine analyzes the user's emotional state and customizes warning messages and evacuation instructions accordingly. Specifically, if the user is in a high-stress state, a more concise and reassuring message is sent. On the other hand, users in a calm state are provided with more detailed information and clearer instructions.

[0703] The device displays this personalized message to the user, notifying them through visual and auditory means for intuitive understanding. This allows users to receive evacuation instructions in a way that best suits their emotional state, enabling them to take swift action.

[0704] Furthermore, disaster response plans are also adjusted by the emotion engine. The server adjusts the response plans provided to local governments, taking into account the overall sentiment data of residents, to be useful for local communication strategies. In this way, utilizing sentiment information can enhance the overall responsiveness and effectiveness of the system.

[0705] For example, if the system determines there is a risk of flooding due to a typhoon, it will send a general warning via a standard communication protocol. However, if the emotion engine detects that the user is under high stress, it will send an additional message with specific instructions such as, "Avoid panicking and head to the nearest shelter." This approach is expected to reduce user stress and increase the rate of safety.

[0706] The following describes the processing flow.

[0707] Step 1:

[0708] The server receives environmental data in real time from observation devices installed in each region. The observation devices collect information such as rainfall, ground movement, water level, and wind speed, and this data is recorded in the server's database.

[0709] Step 2:

[0710] The server sends the collected data to the AI ​​agent. The AI ​​agent uses historical disaster data and weather data to analyze and assess disaster risk. The assessment results quantify the degree of risk and are used in the next step.

[0711] Step 3:

[0712] The server generates standard alarm messages and evacuation instructions based on the analysis results of the AI ​​agent. The generating AI uses natural language processing technology to convert the alarms into easily understandable text.

[0713] Step 4:

[0714] The device uses its built-in camera and microphone to input the user's facial expressions and voice tone into the emotion engine. Based on the data obtained, the system determines the user's stress level and emotional state.

[0715] Step 5:

[0716] The server uses the results of the emotion engine's analysis to modify or refine alarm messages and evacuation instructions according to the user's emotional state. For example, simple and reassuring language is used for users in a high-stress state.

[0717] Step 6:

[0718] The device notifies the user of coordinated alarm messages and evacuation instructions. Notifications are delivered via visual display, audio message, or vibration, and are designed to allow the user to quickly understand the content.

[0719] Step 7:

[0720] Users act based on the instructions they receive. Emotionally sensitive information provision enables users to take calm and appropriate evacuation actions.

[0721] Step 8:

[0722] The server uses new emotional data collected after the disaster to update the AI ​​agent's model. The updated model will be used to provide even more accurate risk assessment and emotional response during the next disaster.

[0723] (Example 2)

[0724] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0725] In recent years, the increasing frequency of natural disasters has highlighted the need for safe and effective evacuation plans and warning systems. However, conventional systems send uniform warnings without considering the emotional state of users, which can lead to panic and make it difficult to convey accurate information. Furthermore, the lack of community-based disaster countermeasures that take into account the emotions of the entire population is also a challenge.

[0726] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0727] In this invention, the server includes means for collecting environmental information from multiple observation devices installed in each region, means for having an analysis device including artificial intelligence that receives and analyzes the environmental information, and means for recognizing the emotional state of the user and adjusting the warnings and evacuation orders according to the emotion. This provides personalized warnings and orders that take into account the user's emotions, minimizes confusion during disasters, and enables effective disaster countermeasures that take into account the emotions of the entire community.

[0728] "Observation equipment" refers to devices deployed in each region to collect environmental information in real time.

[0729] "Environmental information" refers to data such as precipitation, land deformation, water levels, and wind speed used to detect signs of natural disasters.

[0730] "Artificial intelligence" is an advanced information processing technology used to analyze received environmental information and assess disaster risks.

[0731] An "analysis device" is a computing device used to predict disasters based on environmental information and historical data.

[0732] A "user" is an individual or group that receives warnings and evacuation orders from this system.

[0733] "Emotional state" refers to the user's psychological state and includes information such as stress levels and emotional status.

[0734] A "personalized alert" is an alert message that is tailored to the user's emotional state and optimized for their individual needs.

[0735] "Disaster countermeasures" is a general term for plans and actions taken to prepare for natural disasters and minimize damage.

[0736] A "local government" is a public institution that carries out administrative and disaster response measures within a specific region.

[0737] This invention is a system that provides warnings and evacuation instructions that take into account the user's emotional state during a disaster. The system mainly consists of a server, terminals, an emotion engine, and various observation devices.

[0738] First, the server receives environmental information from multiple observation devices installed in each region to collect data such as precipitation, ground movement, water level, and wind speed. These observation devices utilize sensor technology to enable real-time data collection. The received data is stored on the server and analyzed by analytical devices, including artificial intelligence. This analysis uses historical disaster data and weather patterns to build predictive models for assessing future disaster risks.

[0739] The device then uses its built-in camera and microphone to analyze the user's facial expressions and voice tone, collecting emotional data. This allows for real-time assessment of the user's stress level and emotional state. The collected data is immediately transmitted to the server.

[0740] The emotion engine operates on the server and analyzes the user's emotional state. Utilizing natural language processing and emotion analysis techniques, the emotion engine generates the most appropriate warning messages and evacuation instructions for the user. For users experiencing high stress levels, it generates concise and reassuring messages, while for calm users, it creates messages with detailed instructions.

[0741] For example, when a typhoon approaches and the risk of flooding is deemed high, the server generates a standard warning message. However, if the emotion engine analyzes the user's emotional data and finds that their stress level is high, the message is adjusted to a more emotionally sensitive message such as, "Please remain calm. Move safely to the nearest shelter."

[0742] In this way, by providing warnings and instructions tailored to the individual emotional state of users, it is possible to promote appropriate actions during disasters.

[0743] Example of a prompt:

[0744] "Please customize typhoon flood warnings based on user sentiment data. Provide reassuring messages to highly stressed users and include detailed information for calmer users."

[0745] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0746] Step 1:

[0747] The server receives real-time environmental information regarding precipitation, ground movement, water level, and wind speed from observation devices installed in each region. The input consists of data streams from each sensor. The server aggregates this data and processes it by recording it in a database in a compatible format. The output is an environmental information dataset in an analyzable format.

[0748] Step 2:

[0749] The server transmits the collected environmental data to an analysis device that includes artificial intelligence. The input is the environmental information dataset obtained in Step 1. The AI ​​model performs data calculations to analyze the current data in comparison with past disaster data and assess disaster risk. During this process, machine learning algorithms are used, and the predictive model is updated. The output is the disaster risk assessment result for each region.

[0750] Step 3:

[0751] The device uses the user's built-in camera and microphone to collect emotional data such as facial expressions and voice tone. The input is the user's real-time visual and auditory emotional signals. The device analyzes this data and processes it to quantify the emotional state. The output is digital data of the user's stress level and emotional state.

[0752] Step 4:

[0753] The server sends the emotional data obtained in step 3 to the emotion engine for analysis. The input is digital data of the user's emotional state. The emotion engine uses natural language processing and emotion analysis algorithms to perform data calculations that generate alarm messages and evacuation instructions appropriate to the user's emotional state. The output is the adjusted alarm message and evacuation instruction.

[0754] Step 5:

[0755] The terminal notifies the user of a customized alarm message sent from the server. The input is the message generated in step 4. The terminal performs specific actions to convey the message to the user in visual and auditory ways. The output is information and instructions that the user can intuitively understand.

[0756] Through this step, evacuation instructions that take into account the user's emotional state are provided, promoting appropriate and swift action.

[0757] (Application Example 2)

[0758] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0759] Natural disasters are difficult to predict, requiring the provision of appropriate warnings and evacuation orders based on risk assessments. Furthermore, during disasters, responses that are sensitive to the emotional state of recipients are essential. However, current systems do not provide warnings or orders that take recipients' emotions into account, posing challenges to accelerating evacuation and ensuring safety.

[0760] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0761] In this invention, the server includes means for collecting environmental information from a plurality of sensing devices installed in each area; means for having an information processing device that receives and analyzes the environmental information, including machine learning; means for evaluating the degree of disaster risk and generating warnings and evacuation orders based on the analysis results; and means for evaluating the emotional state of the recipient and adjusting the warnings and evacuation orders according to the evaluation results. This makes it possible to provide optimized warnings and evacuation orders for the recipient.

[0762] A "sensing device" is a device that measures and collects information on the state of the global environment in real time, providing diverse environmental data such as precipitation, crustal movement, water level, and wind speed.

[0763] An "information processing device" is a computing device that receives collected environmental data and analyzes it using machine learning algorithms, and is responsible for assessing the risk of disasters and generating warnings.

[0764] "Machine learning" is a technology that learns patterns derived from past disaster and weather data and continuously improves disaster prediction models.

[0765] "Risk assessment" is the process of quantifying the likelihood of a natural disaster occurring based on analysis results and determining its severity.

[0766] A "warning and evacuation order" is an official message issued when there is a risk of disaster, intended to alert recipients and instruct them on safe actions.

[0767] A "recipient" is a person or community that receives a warning and evacuation order notification.

[0768] "Emotional state" refers to information that indicates the recipient's psychological and physiological responses, such as emotions like stress or relief, and is measured accordingly.

[0769] The system for carrying out this invention comprises multiple sensing devices, an information processing device, a user terminal, an emotion evaluation engine, and a communication infrastructure. The sensing devices are installed in each area and measure environmental information such as precipitation, crustal movement, wind speed, and water level in real time. The collected information is transmitted to the information processing device.

[0770] The information processing system incorporates machine learning technology, built using, for example, Python libraries and the Google Cloud AI platform. This allows for comparison and analysis of past disaster and weather data to assess the risk of disasters. Furthermore, warnings and evacuation orders are generated based on these analysis results.

[0771] The user terminal has a built-in camera and microphone, and analyzes the user's facial expressions and voice tone based on warning messages received from the server. Image analysis software such as OpenCV is used for this purpose. An emotion evaluation engine that assesses the user's emotional state integrates the results of facial recognition and voice analysis to determine whether the user is experiencing stress or tension.

[0772] In this way, the device displays warnings and instructions optimized for the user's emotions, prompting the user to take quick and effective action. For example, if a typhoon is approaching and the device determines that the user is feeling stressed, it will send a reassuring message such as, "Please stay calm. Please move to the nearest shelter."

[0773] As an implementation example, the following is an example of a prompt statement used when generating a response message during a disaster.

[0774] "Create messages that suggest safe and calming actions based on user sentiment data."

[0775] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0776] Step 1:

[0777] The server receives environmental information (precipitation, crustal movement, wind speed, water level, etc.) in real time from sensing devices installed in each region. The received data is preprocessed and filtered to remove unwanted noise. The input here is raw data from the sensing devices, and the output is clean environmental information.

[0778] Step 2:

[0779] The server inputs pre-processed environmental information into an information processing unit and applies a machine learning algorithm. This process uses a model that evaluates the risk of disasters using historical disaster data and generates prediction results. The server's input is clean environmental information, and its output is disaster risk and prediction information.

[0780] Step 3:

[0781] The server generates standard warnings and evacuation orders based on the risk assessment and prediction results. This phase utilizes an AI model to create optimal warning messages for disaster situations through the generated AI model. The input is the risk assessment results, and the output is the warnings and evacuation orders.

[0782] Step 4:

[0783] The terminal, along with receiving warnings and evacuation instructions from the server, uses the user's camera and microphone to assess the user's emotional state based on facial expressions and voice tone. An emotion assessment engine analyzes this data to determine the user's stress level. Input is video and audio data, and output is the user's emotional state.

[0784] Step 5:

[0785] The server receives output from the emotion assessment engine and adjusts warning messages and evacuation instructions according to the user's emotional state. Specifically, it generates simpler, more reassuring messages when the user is stressed, and includes more detailed instructions when the user is calm. The input here is the user's emotional state and a standard warning message, while the output is the adjusted warning message.

[0786] Step 6:

[0787] The device notifies the user of a tailored warning message. This notification is delivered both visually and audibly, ensuring intuitive understanding. The input here is the tailored warning message, and the output is the effective notification to the user.

[0788] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0789] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0790] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0791] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0792] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0793] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0794] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0795] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0796] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0797] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0798] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0799] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0800] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0801] 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.

[0802] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0803] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0804] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0805] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0806] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0807] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0808] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0809] The following is further disclosed regarding the embodiments described above.

[0810] (Claim 1)

[0811] A means of collecting environmental data from multiple observation devices installed in each region,

[0812] A means having a computing device including artificial intelligence that receives and analyzes the aforementioned environmental data,

[0813] Based on the aforementioned analysis results, a means for evaluating the risk of disaster and generating warnings and evacuation orders,

[0814] A means for notifying the user of the generated alarm and evacuation order,

[0815] A system that includes means of providing local governments with concrete disaster countermeasures proposals.

[0816] (Claim 2)

[0817] The system according to claim 1, wherein the computing device includes means for updating the model using past disaster data and weather data to improve the accuracy of disaster prediction.

[0818] (Claim 3)

[0819] The system according to claim 1, wherein the observation device comprises means for measuring multiple environmental data, including rainfall, ground movement, water level, and wind speed, in real time.

[0820] "Example 1"

[0821] (Claim 1)

[0822] A means for collecting environmental information from multiple sensor devices installed in each region,

[0823] A means having a processing device that includes a generative algorithm for receiving and analyzing the aforementioned environmental information,

[0824] Based on the aforementioned analysis results, a means for evaluating the risk of natural disasters and generating alerts and evacuation orders,

[0825] A means for notifying the user of the generated alert and evacuation order via a receiving device,

[0826] A system that includes means of providing specific disaster prevention measures to public institutions.

[0827] (Claim 2)

[0828] The system according to claim 1, wherein the processing device includes means for updating a prediction model using past disaster information and weather information to improve the accuracy of natural disaster predictions.

[0829] (Claim 3)

[0830] The system according to claim 1, wherein the sensor device comprises means for measuring multiple environmental information, including precipitation, crustal movement, water level, and wind speed, in real time.

[0831] "Application Example 1"

[0832] (Claim 1)

[0833] A means of collecting environmental data from multiple observation devices installed in each region,

[0834] A means having a processing device including artificial intelligence that receives and analyzes the aforementioned environmental data,

[0835] Based on the aforementioned analysis results, a means for evaluating the risk of disaster and generating warnings and evacuation orders,

[0836] A means for notifying users of the generated alarms and evacuation orders,

[0837] A means of confirming evacuation routes through terminal devices,

[0838] A system that includes means of providing local governments with concrete disaster countermeasures proposals.

[0839] (Claim 2)

[0840] The system according to claim 1, wherein the processing device includes means for updating a model using past disaster information and weather information to improve the accuracy of disaster prediction.

[0841] (Claim 3)

[0842] The system according to claim 1, wherein the observation device comprises means for measuring multiple environmental data, including rainfall, ground movement, water level, and wind speed, in real time.

[0843] "Example 2 of combining an emotion engine"

[0844] (Claim 1)

[0845] A means of collecting environmental information from multiple observation devices installed in each region,

[0846] Means having an analytical device including artificial intelligence that receives and analyzes the aforementioned environmental information,

[0847] Based on the aforementioned analysis results, a means for evaluating the risk of disaster and generating warnings and evacuation orders,

[0848] A means having a display device that notifies the user of the generated alarm and evacuation order,

[0849] Means for recognizing the emotional state of the user and adjusting the aforementioned alarms and evacuation orders according to that emotion,

[0850] A system that provides local governments with concrete disaster response plans and includes means for developing communication strategies that take into account the sentiment data of local residents.

[0851] (Claim 2)

[0852] The system according to claim 1, wherein the analysis device includes means for updating the model using past disaster information and weather information to improve the accuracy of disaster prediction.

[0853] (Claim 3)

[0854] The system according to claim 1, wherein the observation device comprises means for measuring multiple environmental information, including precipitation, land deformation, water level, and wind speed, in real time.

[0855] "Application example 2 when combining with an emotional engine"

[0856] (Claim 1)

[0857] A means of collecting environmental information from multiple sensing devices installed in each region,

[0858] A means having an information processing device that includes machine learning for receiving and analyzing the aforementioned environmental information,

[0859] Based on the aforementioned analysis results, a means for evaluating the degree of disaster risk and generating warnings and evacuation orders,

[0860] Means for notifying recipients of the generated warnings and evacuation orders,

[0861] A means for evaluating the emotional state of the recipient and adjusting warnings and evacuation orders according to the evaluation results,

[0862] A system that includes means of providing communities with concrete disaster response plans.

[0863] (Claim 2)

[0864] The system according to claim 1, wherein the information processing device includes means for updating a model using past disaster information and weather information to improve the accuracy of disaster prediction.

[0865] (Claim 3)

[0866] The system according to claim 1, wherein the sensing device comprises means for measuring a plurality of environmental information, including precipitation, crustal movement, water level, and wind speed, in real time. [Explanation of symbols]

[0867] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting environmental data from multiple observation devices installed in each region, A means having a computing device including artificial intelligence that receives and analyzes the aforementioned environmental data, Based on the aforementioned analysis results, a means for evaluating the risk of disaster and generating warnings and evacuation orders, A means for notifying the user of the generated alarm and evacuation order, A system that includes means of providing local governments with concrete disaster countermeasures proposals.

2. The system according to claim 1, wherein the computing device includes means for updating the model using past disaster data and weather data to improve the accuracy of disaster prediction.

3. The system according to claim 1, wherein the observation device comprises means for measuring multiple environmental data, including rainfall, ground movement, water level, and wind speed, in real time.

Images