system

Abstract

We provide the system. [Solution] Information acquisition methods for collecting disaster information, Information analysis tools for analyzing disaster situations based on acquired information, A means of formulating an evacuation plan that identifies the optimal evacuation route and shelter based on the analysis results, A means for generating individual responses that provide individual countermeasures according to the user's attribute data, A notification method for informing users of disaster response measures, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is 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 in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, large-scale natural disasters and pandemics have occurred frequently, and each time many people have suffered losses because they cannot respond quickly and appropriately. In conventional disaster response systems, it has been difficult to collect accurate data in real time and provide specific evacuation plans according to the individual situations of each user. In addition, due to the spread of information, there is also a possibility that fake news spreads and correct judgments cannot be made. In response to these problems, there is a need to provide a system that supports efficient and accurate disaster response.

Means for Solving the Problems

[0005] To address this challenge, we provide a system equipped with an information acquisition means for collecting disaster information and an information analysis means for analyzing the disaster situation based on the acquired information. Furthermore, by including an evacuation plan formulation means for identifying the optimal evacuation route and shelter based on the analysis results, we support users in taking quick and appropriate action. In addition, by combining an individual response generation means that provides individualized countermeasures according to the user's attribute data with a notification means that notifies the user of disaster response measures, it is possible to deliver information optimized for each individual immediately. Furthermore, by adding an information verification means that eliminates fake news and handles only accurate data, and a feedback processing means that aggregates user feedback information and reflects it in system updates, we improve the reliability of the information and the response accuracy of the system.

[0006] "Information acquisition means" refers to a mechanism for collecting information in real time from various data sources related to disasters.

[0007] An "information analysis tool" is a mechanism for analyzing acquired data to understand the situation and scope of impact of a disaster.

[0008] An "evacuation plan formulation mechanism" is a system for determining the optimal evacuation route and shelter based on the analysis results.

[0009] A "personalized response generation mechanism" is a system that takes into account attribute data such as the user's age and health status to present the most suitable response for each individual user.

[0010] A "notification system" is a mechanism for quickly communicating specific response measures to users during a disaster.

[0011] A "feedback processing mechanism" is a system that incorporates user feedback and new disaster data to continuously update and improve the system.

[0012] An "information verification tool" is a mechanism that eliminates inaccurate information from received information and selects and handles only the correct information. [Brief explanation of the drawing]

[0013] [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 when an emotion engine is combined. [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]

[0014] Next, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the labeled 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.

[0017] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the labeled 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, etc.

[0019] 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).

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention is a system that helps users take appropriate evacuation actions in the event of a large-scale natural disaster or pandemic. Specific embodiments are described below.

[0035] The server collects real-time disaster-related data from official government databases, weather agencies, and social media platforms. This includes user posts, official warnings, and map data. The server aggregates this information, removes noise, and prepares it for analysis.

[0036] Next, the server analyzes this data using machine learning algorithms. The server identifies the direction and extent of the disaster's impact and calculates a risk score for each area based on this. Based on this analysis, it identifies the optimal evacuation routes and shelters. For example, in areas where flooding is expected, it recommends evacuation sites on higher ground with a low risk of flooding.

[0037] The server stores data such as the age, health status, and location of pre-registered users. Based on this data, it develops individually optimized evacuation plans. For elderly users and users with certain chronic illnesses, evacuation shelters where medical support is available are suggested.

[0038] The device receives this evacuation information and notifies the user. Depending on the urgency of the disaster, the device immediately communicates countermeasures using voice alerts and push notifications. These notifications include details such as the shortest route to the evacuation center, recommended actions, and necessary items to bring.

[0039] Furthermore, the server is equipped with an information verification mechanism to ensure the reliability of disaster information. This eliminates false information and misinformation, allowing only accurate information to be provided to users.

[0040] Users can report their actual experiences and feedback via their devices after evacuation. The server collects this information and uses it to improve the system and develop countermeasures for future disasters. In this way, the system flexibly responds to the ever-changing disaster situation and continues to optimize itself.

[0041] This system configuration establishes a mechanism that allows users to evacuate quickly and accurately, minimizing damage caused by disasters.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server collects real-time disaster-related data from official databases and social media platforms. This includes weather warnings, disaster location information, and posts from residents.

[0045] Step 2:

[0046] The server filters the collected data and performs information verification to remove noise and fake news. Only reliable information is selected and passed on to the next analysis step.

[0047] Step 3:

[0048] The server uses deep learning algorithms to analyze the direction of disaster progression and the extent of its impact. Based on these analysis results, it calculates a risk score for the affected area.

[0049] Step 4:

[0050] The server identifies the optimal evacuation route and shelter based on individual user data such as age, health status, and location. Based on the analysis results, it develops a specific evacuation plan tailored to each user.

[0051] Step 5:

[0052] The device receives evacuation plans sent from the server and notifies the user. In emergencies, it uses voice alerts and push notifications to convey information visually and audibly.

[0053] Step 6:

[0054] Users receive notifications and begin safe evacuation actions according to the presented evacuation plan. After evacuation, they can also report their experience and provide feedback through their device.

[0055] Step 7:

[0056] The server aggregates user feedback and uses it to improve future disaster response measures and update the system. This feedback cycle ensures the system is always up-to-date and can respond to disasters more effectively.

[0057] (Example 1)

[0058] 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."

[0059] In emergencies such as natural disasters and pandemics, providing real-time information necessary for swift and accurate evacuation is a challenge. Existing systems sometimes have problems with the accuracy and reliability of the information they provide, and often fail to efficiently generate optimal evacuation plans tailored to individual users. Therefore, there is a need for a system that accurately provides optimized information according to the user's attributes.

[0060] 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.

[0061] In this invention, the server includes information acquisition means for collecting disaster-related data from an external database through multiple information sources, data formatting means for integrating the collected data, removing noise, and preparing it in an analyzable format, and information analysis means for identifying the direction of disaster progression and the scope of impact and calculating a risk score using a machine learning algorithm. This makes it possible to provide accurate and reliable information in real time and efficiently generate an optimal evacuation plan tailored to the individual user profile.

[0062] "Information acquisition means" refers to the function of collecting disaster-related data from external databases and multiple information sources.

[0063] "Data formatting methods" refer to functions that integrate collected data, remove noise, and prepare it in a format that can be analyzed.

[0064] "Information analysis means" refers to a function that uses machine learning algorithms to identify the direction of disaster progression and the scope of impact, and to calculate a risk score.

[0065] "Evacuation plan formulation means" refers to a function that identifies the optimal evacuation route and shelter based on analysis results and user attribute data.

[0066] The "individualized response generation method" refers to a function that generates an optimized evacuation plan based on the user's individual profile from the analysis results.

[0067] "Notification method" refers to a function that communicates evacuation plans to users via voice alerts or push notifications.

[0068] "Feedback processing means" refers to a function that collects feedback information from users and continuously improves the system's prediction accuracy using a generated AI model.

[0069] "Information verification means" refers to a function that, in collecting disaster-related information, eliminates false information and misinformation and analyzes only accurate information.

[0070] This invention is a system for supporting appropriate evacuation actions during disasters. Specific embodiments of this system are described below.

[0071] The server uses information acquisition methods to obtain real-time disaster-related data from multiple sources, including external databases. This process includes weather databases, social media platforms, and official government databases. This information is collected automatically via APIs.

[0072] Next, data formatting techniques are used to integrate the collected data and remove noise. The data is then formatted using string processing techniques to filter out unnecessary information and reconstructed as an analyzable dataset.

[0073] The server uses machine learning algorithms as a means of information analysis to analyze the collected data. This algorithm identifies the direction and extent of the disaster's progression and calculates a risk score for each region based on that. Specifically, it uses clustering techniques to perform a risk assessment of a particular region.

[0074] Using an evacuation planning system, the server proposes optimal evacuation routes and shelters that take into account the user's individual attributes. For elderly users or those with specific chronic illnesses, shelters with appropriate medical support are presented.

[0075] The terminal uses notification methods to inform the user of evacuation information received from the server. Depending on the urgency, the notification is provided as an audio alert or push notification and displayed on the user's terminal screen.

[0076] Furthermore, users provide feedback on their post-evacuation experiences and the system through a feedback processing mechanism. This information is aggregated on a server and used to update the system using a generated AI model, thereby improving prediction accuracy.

[0077] Furthermore, to ensure the reliability of disaster-related information, information verification methods will be used to eliminate false information and misinformation, and only accurate information will be used for analysis.

[0078] For example, if heavy snow is expected, the server analyzes weather data and traffic information to provide safe evacuation routes. The terminal then immediately notifies the user of this information and recommends preparing warm clothing and food.

[0079] An example of a prompt for a generative AI model is: "Analyze the extent of the earthquake last night and the areas where evacuation is recommended, and suggest the optimal evacuation route."

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

[0081] Step 1:

[0082] The server uses information acquisition methods to collect real-time disaster-related data from external databases, social media platforms, and official government databases. It sends automated queries using APIs to retrieve weather information, warning data, and user posts. The input is the API query, and the output is the collected raw data.

[0083] Step 2:

[0084] The server integrates the collected raw data using data formatting techniques, removes noise, and formats it into an analyzable format. Specifically, it removes duplicate data and filters out inappropriate information to generate structured data. The input is the raw data obtained in step 1, and the output is the formatted, clean data.

[0085] Step 3:

[0086] The server analyzes the formatted data using machine learning algorithms as information analysis tools. These algorithms employ clustering techniques to identify the extent of disaster impact and risk scores for each region. The input is the data formatted in step 2, and the output is the risk assessment result.

[0087] Step 4:

[0088] The server uses an evacuation plan formulation tool to propose optimal evacuation routes and shelters that take into account each user's individual attributes, based on the analysis results. Specifically, it generates an evacuation plan that takes into account the user's age and health condition. The input is the risk assessment results obtained in step 3 and user attribute data, and the output is an individualized evacuation plan.

[0089] Step 5:

[0090] The terminal uses notification methods to inform the user of the evacuation plan received from the server. Specifically, it uses voice alerts and push notifications to convey information such as evacuation routes and lists of items to bring. The input is the evacuation plan generated in step 4, and the output is the notification to the user.

[0091] Step 6:

[0092] Users report their post-evacuation experiences and suggestions to their terminals through a feedback processing mechanism. The server aggregates this feedback and uses a generated AI model to improve the system. The input is user feedback information, and the output is the system improvement plan.

[0093] Step 7:

[0094] The server uses information verification tools to verify the reliability of the collected information. To eliminate misinformation and false reports, it cross-checks the source of the information and uses only highly reliable information for analysis. The input is the information obtained in step 1, and the output is the data whose reliability has been verified.

[0095] (Application Example 1)

[0096] 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."

[0097] In emergencies such as natural disasters and pandemics, rapid and appropriate evacuation is essential. However, conventional evacuation support systems struggle to analyze information and provide individualized support in real time, and there is a lack of safe evacuation support, particularly for the elderly and people with disabilities. Furthermore, evacuation support using autonomous mobile devices is still in its early stages of development, and there is a problem in that the provision of effective evacuation routes tends to be slow.

[0098] 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.

[0099] In this invention, the server includes information acquisition means for collecting disaster information, information analysis means for analyzing the disaster situation based on the acquired information, evacuation plan formulation means for identifying the optimal evacuation route and shelter based on the analysis results, individual response generation means for providing individual measures according to the user's attribute data, notification means for notifying the user of disaster response measures, and route control means for the autonomous mobile device to move the user to a safe place. As a result, the user can receive rapid and appropriate evacuation support from the autonomous mobile device.

[0100] "Information acquisition means" refers to a device or system that has the function of efficiently collecting disaster information in real time.

[0101] "Information analysis tools" refer to functions that analyze collected disaster information to identify the progress and scope of the disaster.

[0102] An "evacuation plan formulation tool" is a device or system that has the function of determining the optimal evacuation route and shelter based on the analysis results.

[0103] The "individualized response generation method" is a function that provides customized evacuation plans and countermeasures based on the user's attribute data.

[0104] A "notification means" is a device or system that has the function of informing users in real time about disaster response measures.

[0105] "Route control means" refers to a function that sets the optimal travel route for an autonomous mobile device to guide the user to a safe location.

[0106] The system that realizes this invention consists of a server, a terminal, and an autonomous mobile device. The server plays a central role in collecting and analyzing disaster information and providing users with the optimal evacuation route.

[0107] The server first acquires real-time disaster information from government databases, weather agencies, and social media platforms. The hardware consists of server computers with powerful processors, and the software uses APIs for information gathering. Next, machine learning algorithms are used to analyze this information and identify optimal evacuation routes. During this process, noise is removed from the acquired data, and the data is processed to predict the direction of movement and the extent of impact.

[0108] The terminal is a device used by the user and is responsible for receiving disaster response notifications. The terminal immediately conveys acquired evacuation route information, recommended actions, and items to bring to the user via voice alerts and push notifications.

[0109] The autonomous mobile device uses route control means to autonomously guide the user to a safe evacuation shelter, their destination, according to the evacuation route provided by the server. In this way, the autonomous vehicle has the ability to flexibly respond to disaster situations that change in real time.

[0110] For example, in the event of a flood, the autonomous mobile device can safely evacuate users to higher ground with less risk of flooding. Furthermore, user experience data regarding this system is fed back to the server and used to optimize the system for future disaster response.

[0111] The following is an example of a prompt statement using a generative AI model.

[0112] "Based on your current location, please propose a method to provide the fastest and safest evacuation route using autonomous vehicles."

[0113] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0114] Step 1:

[0115] The server collects disaster information from government databases, weather agencies, and social media platforms. The input is real-time data provided through APIs on various platforms, and the output is the raw data obtained.

[0116] Step 2:

[0117] The server filters the acquired raw data to remove noise. The input is the raw data obtained in step 1, and the output is the cleaned-up disaster information data. This process eliminates fake news and misinformation, preparing accurate material for analysis.

[0118] Step 3:

[0119] The server uses machine learning algorithms to analyze cleaned disaster information data. The input is clean disaster information data, and the output is the direction of disaster progression, the extent of impact, and the risk score for each region. In this step, a risk model is applied to derive disaster prediction information.

[0120] Step 4:

[0121] The server identifies the optimal evacuation route and shelter based on the analysis results. The input is the risk score obtained in step 3, and the output is an individual evacuation plan. At this stage, each user's location information is taken into consideration.

[0122] Step 5:

[0123] The device notifies the user of identified evacuation routes and shelter information. The input is the evacuation plan provided by the server, and the output is communicated to the user as voice alerts or push notifications. Here, the user immediately understands detailed response measures according to the urgency of the situation.

[0124] Step 6:

[0125] The autonomous mobile device controls its route according to evacuation route information obtained from the server, guiding the user to a safe destination. The input is the specified evacuation route, and the output is control information for the movement path. This mechanism allows for flexible responses to real-time changes in the situation.

[0126] Step 7:

[0127] After completing the evacuation, users send their experiences and feedback to the server via their terminals. The input is user feedback information, and the output is valuable data for future system improvements. This allows for the optimization of the system in preparation for future disasters.

[0128] 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.

[0129] This invention is a system that combines an emotion engine to help users take swift and accurate evacuation actions during disasters. The system consists of a server, a terminal, and an emotion engine, and in addition to real-time collection and analysis of disaster information and provision of countermeasures, it also provides information that takes into account the user's emotional state.

[0130] First, the server collects disaster information in real time from official databases, weather agencies, and social media platforms. This information is used to assess risks in each region and understand the progress of the disaster. The server also has an emotion engine that analyzes voice and text data provided by users through their devices to determine their emotional state.

[0131] Next, the server uses a deep learning algorithm to calculate a risk score based on the acquired disaster information. Furthermore, it identifies the optimal evacuation route and shelter, taking into account each user's age, health status, current location, and emotional state. During this process, psychological support messages are generated for users with high urgency and stress levels, providing assistance to help them maintain an emotionally stable state.

[0132] The device receives information sent from the server and notifies the user. This notification includes evacuation instructions that have been adjusted by an emotion engine to be most relatable to the user. For example, a user feeling anxious will receive a message using calming language, while a user who is hesitant to take action will receive a message emphasizing the importance of evacuation.

[0133] Furthermore, feedback provided by users after evacuation is sent to the server via the terminal. The server uses this feedback to improve the system and utilize it for future disaster response. In addition, data acquired by the emotion engine is used to track changes in the user's emotions during evacuation, enabling continuous support.

[0134] Thus, this system, equipped with an emotion engine, can provide information optimized for each user's individual state, enabling more effective and personalized disaster response.

[0135] The following describes the processing flow.

[0136] Step 1:

[0137] The server collects disaster information in real time from official databases and social media. It filters the data, including weather warnings and evacuation information, to extract only accurate information.

[0138] Step 2:

[0139] The server uses an emotion engine to analyze voice input and text messages sent by the user and assess the user's emotional state. This assessment includes indicators such as fear, anxiety, and calmness.

[0140] Step 3:

[0141] The server integrates the results of disaster information analysis with user sentiment evaluations to calculate a risk score for each user. The server uses machine learning algorithms to identify the optimal evacuation route and shelter for each user.

[0142] Step 4:

[0143] The server generates a personalized evacuation plan that takes into account the user's age, health status, location, and emotional state. This plan includes psychologically supportive messages and specific action instructions.

[0144] Step 5:

[0145] The device receives the evacuation plan sent from the server and notifies the user. The notification is tailored to the user's emotional state and is delivered as an audio alert or text message.

[0146] Step 6:

[0147] Users initiate safe evacuation actions based on notifications from their devices. During evacuation, they continuously report their emotional state and location to the server via their devices.

[0148] Step 7:

[0149] The server aggregates user feedback and identifies areas for improvement in the disaster response system. Based on the data collected by the emotion engine, system updates are implemented to aid in future disaster responses.

[0150] (Example 2)

[0151] 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".

[0152] In the event of a disaster, there is a need for a system that enables users to take swift and accurate evacuation actions. Such a system must not only rapidly collect and analyze disaster information, but also provide information optimized according to each user's individual circumstances and emotional state. However, current systems do not adequately address users' emotions, raising concerns about delays in action and errors in judgment under stressful circumstances.

[0153] 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.

[0154] In this invention, the server includes an information acquisition means for collecting disaster information, an information analysis means for analyzing the disaster situation based on the acquired information, and an individual response generation means for providing individual countermeasures according to the user's attribute data and emotional state. This makes it possible to provide information optimized for each user's situation and to support swift and accurate evacuation actions.

[0155] "Information acquisition means" refers to components intended for collecting disaster information in real time.

[0156] "Information analysis methods" refer to the process of analyzing collected information to assess the situation and risks of a disaster.

[0157] "Evacuation plan formulation tools" refer to the function of identifying the optimal evacuation route and destination based on analyzed information.

[0158] "Individualized response generation means" refers to technology that takes into account a user's attribute data and emotional state to provide evacuation instructions and countermeasures that are tailored to their individual needs.

[0159] "Notification means" refers to a device or function for transmitting optimized evacuation instructions or information to the user.

[0160] A "feedback processing method" is a means of collecting user feedback information and using it to improve the system.

[0161] "Emotional analysis methods" refer to the process of analyzing a user's emotional state and providing appropriate information and support.

[0162] This invention is a system developed to support rapid and accurate evacuation during disasters. Specific embodiments of the invention are described below.

[0163] The server collects disaster information in real time from official databases, meteorological agencies, and social media platforms. APIs are used for information retrieval, and after retrieval, information analysis tools are employed to precisely analyze the disaster situation. Specifically, high-performance computing servers are used as hardware, and the software utilizes Python and machine learning libraries such as TENSORFLOW®.

[0164] The server analyzes voice and text data entered by the user through the terminal to estimate their emotional state. It uses a generative AI model and deep learning algorithms to perform emotion analysis. Based on these analysis results, a personalized response generation system creates evacuation routes and psychological support messages tailored to the user.

[0165] The terminal notifies the user of evacuation instructions and psychological support messages sent from the server. The notification method provides information in language optimized for the user's emotional state. For example, a user feeling anxious might see a message such as, "Please stay calm. Here is the route to the nearest evacuation center."

[0166] Furthermore, users can provide feedback after evacuation, sending it to the server via their terminal. The server aggregates this feedback information using a feedback processing mechanism and incorporates it into system improvements. This enables the realization of more accurate sentiment analysis.

[0167] A concrete example of a prompt message is, "If the emotion engine determines that user A is stressed, generate a message to calm them down." This prompt allows the system to quickly generate appropriate support information and help ensure the user's safety.

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

[0169] Step 1:

[0170] The server collects disaster information in real time from official databases, weather agencies, and social media platforms. Input is data points via API, and output is a continuously updated stream of disaster-related information. This collection process utilizes data filtering to extract only the most relevant information, thereby improving the accuracy of the data.

[0171] Step 2:

[0172] The server analyzes the collected disaster information and assesses disaster risk. The input is the disaster information obtained in step 1, and the output is a risk score for each region. Here, the server uses a deep learning algorithm to perform pattern recognition on the data and identify high-risk areas.

[0173] Step 3:

[0174] The user inputs their current emotions via voice or text through the device. The input is the user's voice / text data, and the output is data for analysis sent to the server. The device performs emotion estimation locally, organizes the initial data, and then performs data processing operations to transfer it to the server.

[0175] Step 4:

[0176] The server uses a generative AI model to analyze the user's emotional state. The input is the user data obtained in step 3, and the output is the emotion analysis result. Here, an emotion determination algorithm is used to classify the user's emotions into categories such as "anxiety" and "tension."

[0177] Step 5:

[0178] The server generates the optimal evacuation route and psychological support message for each user based on risk scores and sentiment analysis results. The input is the output of steps 2 and 4, and the output is the evacuation order and support message. The server uses predictive models to process and provide each user with the most suitable action plan.

[0179] Step 6:

[0180] The terminal notifies the user of evacuation instructions and psychological support messages sent from the server. The input is the output data from step 5, and the output is a visual or audio notification to the user. The terminal converts the message into an easy-to-read format so that the information is conveyed in a way that is intuitively easy for the user to understand.

[0181] Step 7:

[0182] Users provide feedback via a terminal after evacuation. Input consists of the user's experience and opinions, and output is sent to the server as feedback data. This feedback collection process involves organizing user input into text format and sending it to the server.

[0183] Step 8:

[0184] The server analyzes the collected feedback and generates data for system improvement. The input is the feedback data from step 7, and the output is the proposed system improvements. Here, the system performs analysis based on the feedback and forms proposals to help with future disaster response.

[0185] (Application Example 2)

[0186] 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".

[0187] In modern society, natural disasters are increasing, and there is a need for swift and individualized evacuation support. However, conventional systems only provide uniform disaster information and fail to address the emotions and individual circumstances of users. As a result, appropriate evacuation actions are not taken, leading to unnecessary confusion and anxiety.

[0188] 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.

[0189] In this invention, the server includes data acquisition means for collecting disaster information, information analysis means for analyzing the disaster situation based on the acquired data, and emotion support generation means for generating psychological support messages based on emotional states. This makes it possible to provide users with evacuation information that is appropriate to their emotions in real time.

[0190] "Data acquisition means" refers to devices and methods for collecting various types of information related to disasters.

[0191] "Information analysis methods" refer to the process of analyzing collected data to assess the progress and risks of a disaster.

[0192] "Evacuation plan formulation methods" refer to methods for determining the optimal evacuation route and shelter based on analyzed data.

[0193] The "individualized response generation method" is a mechanism that generates individualized countermeasures corresponding to the user's attribute information.

[0194] "Emotional analysis methods" are technical techniques used to determine a user's emotional state.

[0195] "Emotional support generation means" refers to a function for creating psychological support messages that are tailored to the user's emotions.

[0196] "Information notification means" refers to the function of transmitting disaster information and evacuation orders to users.

[0197] A "feedback processing method" is a process for collecting user feedback and using it to improve the system.

[0198] "Information verification means" refers to a function that distinguishes accurate data from a large amount of disaster information and eliminates false information.

[0199] This invention is a system that improves the user experience in evacuation support during disasters. It mainly consists of a server, terminals, and an emotion analysis engine.

[0200] The server collects disaster information from multiple databases, weather agencies, and social media platforms. Based on this information, the server analyzes the situation in real time and calculates a risk score using deep learning algorithms. Software such as TensorFlow is used for this purpose. Furthermore, the server uses an emotion analysis engine to analyze voice and text data provided by users to determine their current emotional state. Google Cloud Natural Language API is used for this process.

[0201] The device receives information transmitted from the server and notifies the user. This notification includes information tailored to the user's emotional state, processed by an emotion analysis engine. If the user is feeling anxious, the device sends reassuring messages and provides instructions to encourage quick action when necessary. By using smart glasses or a smartphone, more detailed evacuation information can be obtained through voice guidance and augmented reality (AR) displays.

[0202] For example, consider a scenario where a heavy rain warning is issued. The system uses smart glasses to display augmented reality (AR) information indicating nearby safe shelters and provides messages such as, "Please stay calm. Evacuate to a safe place as quickly as possible." This allows users to take swift action with confidence.

[0203] Specific prompts for the AI ​​model include: "Based on the user's current location and weather data, display the safest evacuation route using AR. Also, dynamically generate a message to help the user stay calm."

[0204] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0205] Step 1:

[0206] The server collects disaster information from multiple data sources. This information includes weather data, social media information, and updates from official organizations. The input consists of information from each data source, and the output is integrated disaster information. The server retrieves data via database queries and APIs and processes it to standardize its format.

[0207] Step 2:

[0208] The server analyzes the collected disaster information. Based on the input disaster information, it calculates a risk score using a deep learning algorithm. The output is a risk score indicating the severity of the disaster in each region. Data is fed into the model using a framework such as TensorFlow to obtain the analysis results.

[0209] Step 3:

[0210] The server receives audio and text data sent from the user's device and performs sentiment analysis. The input is audio or text data, and the output is an evaluation indicating the emotional state. The Google Cloud Natural Language API is used to determine whether the emotion is positive or negative.

[0211] Step 4:

[0212] The server develops individualized evacuation plans based on analysis results and emotional states. Inputs include risk scores and emotional assessments, while outputs include optimal evacuation routes and psychological support messages. These are combined to create the most appropriate action plan for the user's situation.

[0213] Step 5:

[0214] The device receives notifications from the server and conveys evacuation instructions to the user. Inputs include optimized evacuation information and messages, while output is visual and audio notifications to the user. It utilizes smartphone screens and smart glasses displays to provide AR displays and audio guidance.

[0215] Step 6:

[0216] After the user has taken evacuation action, they input feedback into a terminal. The input is information about the user's evacuation experience, and the output is data used to improve the system. Feedback can be easily recorded and sent to the server through the user interface.

[0217] Step 7:

[0218] The server improves the system based on the feedback it receives. Input is user feedback data, and output is updated analysis models and notification methods. The analysis results are reflected in improving prompts in the generating AI model, providing more effective support during future disasters.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] [Second Embodiment]

[0223] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0224] 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.

[0225] 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).

[0226] 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.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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".

[0235] This invention is a system that helps users take appropriate evacuation actions in the event of a large-scale natural disaster or pandemic. Specific embodiments are described below.

[0236] The server collects real-time disaster-related data from official government databases, weather agencies, and social media platforms. This includes user posts, official warnings, and map data. The server aggregates this information, removes noise, and prepares it for analysis.

[0237] Next, the server analyzes this data using machine learning algorithms. The server identifies the direction and extent of the disaster's impact and calculates a risk score for each area based on this. Based on this analysis, it identifies the optimal evacuation routes and shelters. For example, in areas where flooding is expected, it recommends evacuation sites on higher ground with a low risk of flooding.

[0238] The server stores data such as the age, health status, and location of pre-registered users. Based on this data, it develops individually optimized evacuation plans. For elderly users and users with certain chronic illnesses, evacuation shelters where medical support is available are suggested.

[0239] The device receives this evacuation information and notifies the user. Depending on the urgency of the disaster, the device immediately communicates countermeasures using voice alerts and push notifications. These notifications include details such as the shortest route to the evacuation center, recommended actions, and necessary items to bring.

[0240] Furthermore, the server is equipped with an information verification mechanism to ensure the reliability of disaster information. This eliminates false information and misinformation, allowing only accurate information to be provided to users.

[0241] Users can report their actual experiences and feedback via their devices after evacuation. The server collects this information and uses it to improve the system and develop countermeasures for future disasters. In this way, the system flexibly responds to the ever-changing disaster situation and continues to optimize itself.

[0242] This system configuration establishes a mechanism that allows users to evacuate quickly and accurately, minimizing damage caused by disasters.

[0243] The following describes the processing flow.

[0244] Step 1:

[0245] The server collects real-time disaster-related data from official databases and social media platforms. This includes weather warnings, disaster location information, and posts from residents.

[0246] Step 2:

[0247] The server filters the collected data and performs information verification to remove noise and fake news. Only reliable information is selected and passed on to the next analysis step.

[0248] Step 3:

[0249] The server uses deep learning algorithms to analyze the direction of disaster progression and the extent of its impact. Based on these analysis results, it calculates a risk score for the affected area.

[0250] Step 4:

[0251] The server identifies the optimal evacuation route and shelter based on individual user data such as age, health status, and location. Based on the analysis results, it develops a specific evacuation plan tailored to each user.

[0252] Step 5:

[0253] The device receives evacuation plans sent from the server and notifies the user. In emergencies, it uses voice alerts and push notifications to convey information visually and audibly.

[0254] Step 6:

[0255] Users receive notifications and begin safe evacuation actions according to the presented evacuation plan. After evacuation, they can also report their experience and provide feedback through their device.

[0256] Step 7:

[0257] The server aggregates user feedback and uses it to improve future disaster response measures and update the system. This feedback cycle ensures the system is always up-to-date and can respond to disasters more effectively.

[0258] (Example 1)

[0259] 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."

[0260] In emergencies such as natural disasters and pandemics, providing real-time information necessary for swift and accurate evacuation is a challenge. Existing systems sometimes have problems with the accuracy and reliability of the information they provide, and often fail to efficiently generate optimal evacuation plans tailored to individual users. Therefore, there is a need for a system that accurately provides optimized information according to the user's attributes.

[0261] 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.

[0262] In this invention, the server includes information acquisition means for collecting disaster-related data from an external database through multiple information sources, data formatting means for integrating the collected data, removing noise, and preparing it in an analyzable format, and information analysis means for identifying the direction of disaster progression and the scope of impact and calculating a risk score using a machine learning algorithm. This makes it possible to provide accurate and reliable information in real time and efficiently generate an optimal evacuation plan tailored to the individual user profile.

[0263] "Information acquisition means" refers to the function of collecting disaster-related data from external databases and multiple information sources.

[0264] "Data formatting methods" refer to functions that integrate collected data, remove noise, and prepare it in a format that can be analyzed.

[0265] "Information analysis means" refers to a function that uses machine learning algorithms to identify the direction of disaster progression and the scope of impact, and to calculate a risk score.

[0266] "Evacuation plan formulation means" refers to a function that identifies the optimal evacuation route and shelter based on analysis results and user attribute data.

[0267] The "individualized response generation method" refers to a function that generates an optimized evacuation plan based on the user's individual profile from the analysis results.

[0268] "Notification method" refers to a function that communicates evacuation plans to users via voice alerts or push notifications.

[0269] "Feedback processing means" refers to a function that collects feedback information from users and continuously improves the system's prediction accuracy using a generated AI model.

[0270] "Information verification means" refers to a function that, in collecting disaster-related information, eliminates false information and misinformation and analyzes only accurate information.

[0271] This invention is a system for supporting appropriate evacuation actions during disasters. Specific embodiments of this system are described below.

[0272] The server uses information acquisition methods to obtain real-time disaster-related data from multiple sources, including external databases. This process includes weather databases, social media platforms, and official government databases. This information is collected automatically via APIs.

[0273] Next, data formatting techniques are used to integrate the collected data and remove noise. The data is then formatted using string processing techniques to filter out unnecessary information and reconstructed as an analyzable dataset.

[0274] The server uses machine learning algorithms as a means of information analysis to analyze the collected data. This algorithm identifies the direction and extent of the disaster's progression and calculates a risk score for each region based on that. Specifically, it uses clustering techniques to perform a risk assessment of a particular region.

[0275] Using an evacuation planning system, the server proposes optimal evacuation routes and shelters that take into account the user's individual attributes. For elderly users or those with specific chronic illnesses, shelters with appropriate medical support are presented.

[0276] The terminal uses notification methods to inform the user of evacuation information received from the server. Depending on the urgency, the notification is provided as an audio alert or push notification and displayed on the user's terminal screen.

[0277] Furthermore, users provide feedback on their post-evacuation experiences and the system through a feedback processing mechanism. This information is aggregated on a server and used to update the system using a generated AI model, thereby improving prediction accuracy.

[0278] Furthermore, to ensure the reliability of disaster-related information, information verification methods will be used to eliminate false information and misinformation, and only accurate information will be used for analysis.

[0279] For example, if heavy snow is expected, the server analyzes weather data and traffic information to provide safe evacuation routes. The terminal then immediately notifies the user of this information and recommends preparing warm clothing and food.

[0280] An example of a prompt for a generative AI model is: "Analyze the extent of the earthquake last night and the areas where evacuation is recommended, and suggest the optimal evacuation route."

[0281] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0282] Step 1:

[0283] The server uses information acquisition means to collect real-time disaster-related data from external databases, SNS platforms, and government official databases. At this time, automated queries are sent using APIs to obtain meteorological information, warning data, residents' posted content, etc. The input is the API query, and the output is the collected raw data.

[0284] Step 2:

[0285] The server uses data formatting means to integrate the collected raw data, remove noise, and format it into an analyzable form. Specifically, duplicate data is removed and inappropriate information is filtered to generate structured data. The input is the raw data obtained in Step 1, and the output is the formatted clean data.

[0286] Step 3:

[0287] The server uses a machine learning algorithm as information analysis means to analyze the formatted data. This algorithm uses a clustering method to identify the disaster impact range and risk score for each region. The input is the data formatted in Step 2, and the output is the risk assessment result.

[0288] Step 4:

[0289] The server uses evacuation plan formulation means to propose an optimal evacuation route and evacuation shelter considering the individual attributes of each user based on the analysis results. Specifically, an evacuation plan considering the user's age and health status is generated. The input is the risk assessment result obtained in Step 3 and user attribute data, and the output is an individualized evacuation plan.

[0290] Step 5:

[0291] The terminal uses notification methods to inform the user of the evacuation plan received from the server. Specifically, it uses voice alerts and push notifications to convey information such as evacuation routes and lists of items to bring. The input is the evacuation plan generated in step 4, and the output is the notification to the user.

[0292] Step 6:

[0293] Users report their post-evacuation experiences and suggestions to their terminals through a feedback processing mechanism. The server aggregates this feedback and uses a generated AI model to improve the system. The input is user feedback information, and the output is the system improvement plan.

[0294] Step 7:

[0295] The server uses information verification tools to verify the reliability of the collected information. To eliminate misinformation and false reports, it cross-checks the source of the information and uses only highly reliable information for analysis. The input is the information obtained in step 1, and the output is the data whose reliability has been verified.

[0296] (Application Example 1)

[0297] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0298] In emergencies such as natural disasters and pandemics, rapid and appropriate evacuation is essential. However, conventional evacuation support systems struggle to analyze information and provide individualized support in real time, and there is a lack of safe evacuation support, particularly for the elderly and people with disabilities. Furthermore, evacuation support using autonomous mobile devices is still in its early stages of development, and there is a problem in that the provision of effective evacuation routes tends to be slow.

[0299] 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.

[0300] In this invention, the server includes information acquisition means for collecting disaster information, information analysis means for analyzing the disaster situation based on the acquired information, evacuation plan formulation means for identifying the optimal evacuation route and shelter based on the analysis results, individual response generation means for providing individual measures according to the user's attribute data, notification means for notifying the user of disaster response measures, and route control means for the autonomous mobile device to move the user to a safe place. As a result, the user can receive rapid and appropriate evacuation support from the autonomous mobile device.

[0301] "Information acquisition means" refers to a device or system that has the function of efficiently collecting disaster information in real time.

[0302] "Information analysis tools" refer to functions that analyze collected disaster information to identify the progress and scope of the disaster.

[0303] An "evacuation plan formulation tool" is a device or system that has the function of determining the optimal evacuation route and shelter based on the analysis results.

[0304] The "individualized response generation method" is a function that provides customized evacuation plans and countermeasures based on the user's attribute data.

[0305] A "notification means" is a device or system that has the function of informing users in real time about disaster response measures.

[0306] "Route control means" refers to a function that sets the optimal travel route for an autonomous mobile device to guide the user to a safe location.

[0307] The system that realizes this invention consists of a server, a terminal, and an autonomous mobile device. The server plays a central role in collecting and analyzing disaster information and providing users with the optimal evacuation route.

[0308] The server first obtains disaster information in real time from government databases, meteorological agencies, and social media platforms. As hardware, a server computer equipped with a powerful processor is used, and as software, an API for information collection is employed. Next, these pieces of information are analyzed using machine learning algorithms to identify the optimal evacuation route. In so doing, noise is removed from the acquired data, and data processing is performed to predict the direction of travel and the scope of the impact.

[0309] The terminal is the device used by the user and has the role of receiving disaster response notifications. At the terminal, the acquired evacuation route information, recommended actions, items to bring, etc. are immediately conveyed to the user by voice alerts and push notifications.

[0310] The autonomous mobile device uses route control means to autonomously guide the user to a safe evacuation site that is the destination according to the evacuation route provided by the server. In this way, the autonomous driving vehicle has the ability to flexibly respond to disaster situations that change in real time.

[0311] As a specific example, for instance, when a flood occurs, the autonomous mobile device can safely evacuate the user to a high place with less flood risk. Also, the user's experience data regarding this system is fed back to the server and utilized for optimizing the system in the next disaster response.

[0312] Examples of prompt sentences using the generative AI model are as follows.

[0313] "Please propose a method for an autonomous driving vehicle to provide the fastest and safest evacuation route based on the current location."

[0314] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0315] Step 1:

[0316] The server collects disaster information from government databases, weather agencies, and social media platforms. The input is real-time data provided through APIs on various platforms, and the output is the raw data obtained.

[0317] Step 2:

[0318] The server filters the acquired raw data to remove noise. The input is the raw data obtained in step 1, and the output is the cleaned-up disaster information data. This process eliminates fake news and misinformation, preparing accurate material for analysis.

[0319] Step 3:

[0320] The server uses machine learning algorithms to analyze cleaned disaster information data. The input is clean disaster information data, and the output is the direction of disaster progression, the extent of impact, and the risk score for each region. In this step, a risk model is applied to derive disaster prediction information.

[0321] Step 4:

[0322] The server identifies the optimal evacuation route and shelter based on the analysis results. The input is the risk score obtained in step 3, and the output is an individual evacuation plan. At this stage, each user's location information is taken into consideration.

[0323] Step 5:

[0324] The device notifies the user of identified evacuation routes and shelter information. The input is the evacuation plan provided by the server, and the output is communicated to the user as voice alerts or push notifications. Here, the user immediately understands detailed response measures according to the urgency of the situation.

[0325] Step 6:

[0326] The autonomous mobile device controls its route according to evacuation route information obtained from the server, guiding the user to a safe destination. The input is the specified evacuation route, and the output is control information for the movement path. This mechanism allows for flexible responses to real-time changes in the situation.

[0327] Step 7:

[0328] After completing the evacuation, users send their experiences and feedback to the server via their terminals. The input is user feedback information, and the output is valuable data for future system improvements. This allows for the optimization of the system in preparation for future disasters.

[0329] 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.

[0330] This invention is a system that combines an emotion engine to help users take swift and accurate evacuation actions during disasters. The system consists of a server, a terminal, and an emotion engine, and in addition to real-time collection and analysis of disaster information and provision of countermeasures, it also provides information that takes into account the user's emotional state.

[0331] First, the server collects disaster information in real time from official databases, weather agencies, and social media platforms. This information is used to assess risks in each region and understand the progress of the disaster. The server also has an emotion engine that analyzes voice and text data provided by users through their devices to determine their emotional state.

[0332] Next, the server uses a deep learning algorithm to calculate a risk score based on the acquired disaster information. Furthermore, it identifies the optimal evacuation route and shelter, taking into account each user's age, health status, current location, and emotional state. During this process, psychological support messages are generated for users with high urgency and stress levels, providing assistance to help them maintain an emotionally stable state.

[0333] The device receives information sent from the server and notifies the user. This notification includes evacuation instructions that have been adjusted by an emotion engine to be most relatable to the user. For example, a user feeling anxious will receive a message using calming language, while a user who is hesitant to take action will receive a message emphasizing the importance of evacuation.

[0334] Furthermore, feedback provided by users after evacuation is sent to the server via the terminal. The server uses this feedback to improve the system and utilize it for future disaster response. In addition, data acquired by the emotion engine is used to track changes in the user's emotions during evacuation, enabling continuous support.

[0335] Thus, this system, equipped with an emotion engine, can provide information optimized for each user's individual state, enabling more effective and personalized disaster response.

[0336] The following describes the processing flow.

[0337] Step 1:

[0338] The server collects disaster information in real time from official databases and social media. It filters the data, including weather warnings and evacuation information, to extract only accurate information.

[0339] Step 2:

[0340] The server uses an emotion engine to analyze voice input and text messages sent by the user and assess the user's emotional state. This assessment includes indicators such as fear, anxiety, and calmness.

[0341] Step 3:

[0342] The server integrates the results of disaster information analysis with user sentiment evaluations to calculate a risk score for each user. The server uses machine learning algorithms to identify the optimal evacuation route and shelter for each user.

[0343] Step 4:

[0344] The server generates a personalized evacuation plan that takes into account the user's age, health status, location, and emotional state. This plan includes psychologically supportive messages and specific action instructions.

[0345] Step 5:

[0346] The device receives the evacuation plan sent from the server and notifies the user. The notification is tailored to the user's emotional state and is delivered as an audio alert or text message.

[0347] Step 6:

[0348] Users initiate safe evacuation actions based on notifications from their devices. During evacuation, they continuously report their emotional state and location to the server via their devices.

[0349] Step 7:

[0350] The server aggregates user feedback and identifies areas for improvement in the disaster response system. Based on the data collected by the emotion engine, system updates are implemented to aid in future disaster responses.

[0351] (Example 2)

[0352] 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".

[0353] In the event of a disaster, there is a need for a system that enables users to take swift and accurate evacuation actions. Such a system must not only rapidly collect and analyze disaster information, but also provide information optimized according to each user's individual circumstances and emotional state. However, current systems do not adequately address users' emotions, raising concerns about delays in action and errors in judgment under stressful circumstances.

[0354] 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.

[0355] In this invention, the server includes an information acquisition means for collecting disaster information, an information analysis means for analyzing the disaster situation based on the acquired information, and an individual response generation means for providing individual countermeasures according to the user's attribute data and emotional state. This makes it possible to provide information optimized for each user's situation and to support swift and accurate evacuation actions.

[0356] "Information acquisition means" refers to components intended for collecting disaster information in real time.

[0357] "Information analysis methods" refer to the process of analyzing collected information to assess the situation and risks of a disaster.

[0358] "Evacuation plan formulation tools" refer to the function of identifying the optimal evacuation route and destination based on analyzed information.

[0359] "Individualized response generation means" refers to technology that takes into account a user's attribute data and emotional state to provide evacuation instructions and countermeasures that are tailored to their individual needs.

[0360] "Notification means" refers to a device or function for transmitting optimized evacuation instructions or information to the user.

[0361] A "feedback processing method" is a means of collecting user feedback information and using it to improve the system.

[0362] "Emotional analysis methods" refer to the process of analyzing a user's emotional state and providing appropriate information and support.

[0363] This invention is a system developed to support rapid and accurate evacuation during disasters. Specific embodiments of the invention are described below.

[0364] The server collects disaster information in real time from official databases, weather agencies, and social media platforms. APIs are used for information retrieval, and after retrieval, information analysis tools are employed to precisely analyze the disaster situation. Specifically, high-performance computing servers are used as hardware, and the software utilizes machine learning libraries such as Python and TensorFlow.

[0365] The server analyzes voice and text data entered by the user through the terminal to estimate their emotional state. It uses a generative AI model and deep learning algorithms to perform emotion analysis. Based on these analysis results, a personalized response generation system creates evacuation routes and psychological support messages tailored to the user.

[0366] The terminal notifies the user of evacuation instructions and psychological support messages sent from the server. The notification method provides information in language optimized for the user's emotional state. For example, a user feeling anxious might see a message such as, "Please stay calm. Here is the route to the nearest evacuation center."

[0367] Furthermore, users can provide feedback after evacuation, sending it to the server via their terminal. The server aggregates this feedback information using a feedback processing mechanism and incorporates it into system improvements. This enables the realization of more accurate sentiment analysis.

[0368] A concrete example of a prompt message is, "If the emotion engine determines that user A is stressed, generate a message to calm them down." This prompt allows the system to quickly generate appropriate support information and help ensure the user's safety.

[0369] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0370] Step 1:

[0371] The server collects disaster information in real time from official databases, weather agencies, and social media platforms. Input is data points via API, and output is a continuously updated stream of disaster-related information. This collection process utilizes data filtering to extract only the most relevant information, thereby improving the accuracy of the data.

[0372] Step 2:

[0373] The server analyzes the collected disaster information and assesses disaster risk. The input is the disaster information obtained in step 1, and the output is a risk score for each region. Here, the server uses a deep learning algorithm to perform pattern recognition on the data and identify high-risk areas.

[0374] Step 3:

[0375] The user inputs their current emotions via voice or text through the device. The input is the user's voice / text data, and the output is data for analysis sent to the server. The device performs emotion estimation locally, organizes the initial data, and then performs data processing operations to transfer it to the server.

[0376] Step 4:

[0377] The server uses a generative AI model to analyze the user's emotional state. The input is the user data obtained in step 3, and the output is the emotion analysis result. Here, an emotion determination algorithm is used to classify the user's emotions into categories such as "anxiety" and "tension."

[0378] Step 5:

[0379] The server generates the optimal evacuation route and psychological support message for each user based on risk scores and sentiment analysis results. The input is the output of steps 2 and 4, and the output is the evacuation order and support message. The server uses predictive models to process and provide each user with the most suitable action plan.

[0380] Step 6:

[0381] The terminal notifies the user of evacuation instructions and psychological support messages sent from the server. The input is the output data from step 5, and the output is a visual or audio notification to the user. The terminal converts the message into an easy-to-read format so that the information is conveyed in a way that is intuitively easy for the user to understand.

[0382] Step 7:

[0383] Users provide feedback via a terminal after evacuation. Input consists of the user's experience and opinions, and output is sent to the server as feedback data. This feedback collection process involves organizing user input into text format and sending it to the server.

[0384] Step 8:

[0385] The server analyzes the collected feedback and generates data for system improvement. The input is the feedback data from step 7, and the output is the proposed system improvements. Here, the system performs analysis based on the feedback and forms proposals to help with future disaster response.

[0386] (Application Example 2)

[0387] 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."

[0388] In modern society, natural disasters are increasing, and there is a need for swift and individualized evacuation support. However, conventional systems only provide uniform disaster information and fail to address the emotions and individual circumstances of users. As a result, appropriate evacuation actions are not taken, leading to unnecessary confusion and anxiety.

[0389] 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.

[0390] In this invention, the server includes data acquisition means for collecting disaster information, information analysis means for analyzing the disaster situation based on the acquired data, and emotion support generation means for generating psychological support messages based on emotional states. This makes it possible to provide users with evacuation information that is appropriate to their emotions in real time.

[0391] "Data acquisition means" refers to devices and methods for collecting various types of information related to disasters.

[0392] "Information analysis methods" refer to the process of analyzing collected data to assess the progress and risks of a disaster.

[0393] "Evacuation plan formulation methods" refer to methods for determining the optimal evacuation route and shelter based on analyzed data.

[0394] The "individualized response generation method" is a mechanism that generates individualized countermeasures corresponding to the user's attribute information.

[0395] "Emotional analysis methods" are technical techniques used to determine a user's emotional state.

[0396] "Emotional support generation means" refers to a function for creating psychological support messages that are tailored to the user's emotions.

[0397] "Information notification means" refers to the function of transmitting disaster information and evacuation orders to users.

[0398] A "feedback processing method" is a process for collecting user feedback and using it to improve the system.

[0399] "Information verification means" refers to a function that distinguishes accurate data from a large amount of disaster information and eliminates false information.

[0400] This invention is a system that improves the user experience in evacuation support during disasters. It mainly consists of a server, terminals, and an emotion analysis engine.

[0401] The server collects disaster information from multiple databases, weather agencies, and social media platforms. Based on this information, the server analyzes the situation in real time and calculates a risk score using deep learning algorithms. Software such as TensorFlow is used for this purpose. Furthermore, the server uses an emotion analysis engine to analyze voice and text data provided by users to determine their current emotional state. Google Cloud Natural Language API is used for this process.

[0402] The device receives information transmitted from the server and notifies the user. This notification includes information tailored to the user's emotional state, processed by an emotion analysis engine. If the user is feeling anxious, the device sends reassuring messages and provides instructions to encourage quick action when necessary. By using smart glasses or a smartphone, more detailed evacuation information can be obtained through voice guidance and augmented reality (AR) displays.

[0403] For example, consider a scenario where a heavy rain warning is issued. The system uses smart glasses to display augmented reality (AR) information indicating nearby safe shelters and provides messages such as, "Please stay calm. Evacuate to a safe place as quickly as possible." This allows users to take swift action with confidence.

[0404] Specific prompts for the AI ​​model include: "Based on the user's current location and weather data, display the safest evacuation route using AR. Also, dynamically generate a message to help the user stay calm."

[0405] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0406] Step 1:

[0407] The server collects disaster information from multiple data sources. This information includes weather data, social media information, and updates from official organizations. The input consists of information from each data source, and the output is integrated disaster information. The server retrieves data via database queries and APIs and processes it to standardize its format.

[0408] Step 2:

[0409] The server analyzes the collected disaster information. Based on the input disaster information, it calculates a risk score using a deep learning algorithm. The output is a risk score indicating the severity of the disaster in each region. Data is fed into the model using a framework such as TensorFlow to obtain the analysis results.

[0410] Step 3:

[0411] The server receives audio and text data sent from the user's device and performs sentiment analysis. The input is audio or text data, and the output is an evaluation indicating the emotional state. The Google Cloud Natural Language API is used to determine whether the emotion is positive or negative.

[0412] Step 4:

[0413] The server develops individualized evacuation plans based on analysis results and emotional states. Inputs include risk scores and emotional assessments, while outputs include optimal evacuation routes and psychological support messages. These are combined to create the most appropriate action plan for the user's situation.

[0414] Step 5:

[0415] The device receives notifications from the server and conveys evacuation instructions to the user. Inputs include optimized evacuation information and messages, while output is visual and audio notifications to the user. It utilizes smartphone screens and smart glasses displays to provide AR displays and audio guidance.

[0416] Step 6:

[0417] After the user has taken evacuation action, they input feedback into a terminal. The input is information about the user's evacuation experience, and the output is data used to improve the system. Feedback can be easily recorded and sent to the server through the user interface.

[0418] Step 7:

[0419] The server improves the system based on the feedback it receives. Input is user feedback data, and output is updated analysis models and notification methods. The analysis results are reflected in improving prompts in the generating AI model, providing more effective support during future disasters.

[0420] 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.

[0421] 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.

[0422] 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.

[0423] [Third Embodiment]

[0424] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0425] 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.

[0426] 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).

[0427] 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.

[0428] 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.

[0429] 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).

[0430] 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.

[0431] 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.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] 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".

[0436] This invention is a system that helps users take appropriate evacuation actions in the event of a large-scale natural disaster or pandemic. Specific embodiments are described below.

[0437] The server collects real-time disaster-related data from official government databases, weather agencies, and social media platforms. This includes user posts, official warnings, and map data. The server aggregates this information, removes noise, and prepares it for analysis.

[0438] Next, the server analyzes this data using machine learning algorithms. The server identifies the direction and extent of the disaster's impact and calculates a risk score for each area based on this. Based on this analysis, it identifies the optimal evacuation routes and shelters. For example, in areas where flooding is expected, it recommends evacuation sites on higher ground with a low risk of flooding.

[0439] The server stores data such as the age, health status, and location of pre-registered users. Based on this data, it develops individually optimized evacuation plans. For elderly users and users with certain chronic illnesses, evacuation shelters where medical support is available are suggested.

[0440] The device receives this evacuation information and notifies the user. Depending on the urgency of the disaster, the device immediately communicates countermeasures using voice alerts and push notifications. These notifications include details such as the shortest route to the evacuation center, recommended actions, and necessary items to bring.

[0441] Furthermore, the server is equipped with an information verification mechanism to ensure the reliability of disaster information. This eliminates false information and misinformation, allowing only accurate information to be provided to users.

[0442] Users can report their actual experiences and feedback via their devices after evacuation. The server collects this information and uses it to improve the system and develop countermeasures for future disasters. In this way, the system flexibly responds to the ever-changing disaster situation and continues to optimize itself.

[0443] This system configuration establishes a mechanism that allows users to evacuate quickly and accurately, minimizing damage caused by disasters.

[0444] The following describes the processing flow.

[0445] Step 1:

[0446] The server collects real-time disaster-related data from official databases and social media platforms. This includes weather warnings, disaster location information, and posts from residents.

[0447] Step 2:

[0448] The server filters the collected data and performs information verification to remove noise and fake news. Only reliable information is selected and passed on to the next analysis step.

[0449] Step 3:

[0450] The server uses deep learning algorithms to analyze the direction of disaster progression and the extent of its impact. Based on these analysis results, it calculates a risk score for the affected area.

[0451] Step 4:

[0452] The server identifies the optimal evacuation route and shelter based on individual user data such as age, health status, and location. Based on the analysis results, it develops a specific evacuation plan tailored to each user.

[0453] Step 5:

[0454] The device receives evacuation plans sent from the server and notifies the user. In emergencies, it uses voice alerts and push notifications to convey information visually and audibly.

[0455] Step 6:

[0456] Users receive notifications and begin safe evacuation actions according to the presented evacuation plan. After evacuation, they can also report their experience and provide feedback through their device.

[0457] Step 7:

[0458] The server aggregates user feedback and uses it to improve future disaster response measures and update the system. This feedback cycle ensures the system is always up-to-date and can respond to disasters more effectively.

[0459] (Example 1)

[0460] 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."

[0461] In emergencies such as natural disasters and pandemics, providing real-time information necessary for swift and accurate evacuation is a challenge. Existing systems sometimes have problems with the accuracy and reliability of the information they provide, and often fail to efficiently generate optimal evacuation plans tailored to individual users. Therefore, there is a need for a system that accurately provides optimized information according to the user's attributes.

[0462] 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.

[0463] In this invention, the server includes information acquisition means for collecting disaster-related data from an external database through multiple information sources, data formatting means for integrating the collected data, removing noise, and preparing it in an analyzable format, and information analysis means for identifying the direction of disaster progression and the scope of impact and calculating a risk score using a machine learning algorithm. This makes it possible to provide accurate and reliable information in real time and efficiently generate an optimal evacuation plan tailored to the individual user profile.

[0464] "Information acquisition means" refers to the function of collecting disaster-related data from external databases and multiple information sources.

[0465] "Data formatting methods" refer to functions that integrate collected data, remove noise, and prepare it in a format that can be analyzed.

[0466] "Information analysis means" refers to a function that uses machine learning algorithms to identify the direction of disaster progression and the scope of impact, and to calculate a risk score.

[0467] "Evacuation plan formulation means" refers to a function that identifies the optimal evacuation route and shelter based on analysis results and user attribute data.

[0468] The "individualized response generation method" refers to a function that generates an optimized evacuation plan based on the user's individual profile from the analysis results.

[0469] "Notification method" refers to a function that communicates evacuation plans to users via voice alerts or push notifications.

[0470] "Feedback processing means" refers to a function that collects feedback information from users and continuously improves the system's prediction accuracy using a generated AI model.

[0471] "Information verification means" refers to a function that, in collecting disaster-related information, eliminates false information and misinformation and analyzes only accurate information.

[0472] This invention is a system for supporting appropriate evacuation actions during disasters. Specific embodiments of this system are described below.

[0473] The server uses information acquisition methods to obtain real-time disaster-related data from multiple sources, including external databases. This process includes weather databases, social media platforms, and official government databases. This information is collected automatically via APIs.

[0474] Next, data formatting techniques are used to integrate the collected data and remove noise. The data is then formatted using string processing techniques to filter out unnecessary information and reconstructed as an analyzable dataset.

[0475] The server uses machine learning algorithms as a means of information analysis to analyze the collected data. This algorithm identifies the direction and extent of the disaster's progression and calculates a risk score for each region based on that. Specifically, it uses clustering techniques to perform a risk assessment of a particular region.

[0476] Using an evacuation planning system, the server proposes optimal evacuation routes and shelters that take into account the user's individual attributes. For elderly users or those with specific chronic illnesses, shelters with appropriate medical support are presented.

[0477] The terminal uses notification methods to inform the user of evacuation information received from the server. Depending on the urgency, the notification is provided as an audio alert or push notification and displayed on the user's terminal screen.

[0478] Furthermore, users provide feedback on their post-evacuation experiences and the system through a feedback processing mechanism. This information is aggregated on a server and used to update the system using a generated AI model, thereby improving prediction accuracy.

[0479] Furthermore, to ensure the reliability of disaster-related information, information verification methods will be used to eliminate false information and misinformation, and only accurate information will be used for analysis.

[0480] For example, if heavy snow is expected, the server analyzes weather data and traffic information to provide safe evacuation routes. The terminal then immediately notifies the user of this information and recommends preparing warm clothing and food.

[0481] An example of a prompt for a generative AI model is: "Analyze the extent of the earthquake last night and the areas where evacuation is recommended, and suggest the optimal evacuation route."

[0482] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0483] Step 1:

[0484] The server uses information acquisition methods to collect real-time disaster-related data from external databases, social media platforms, and official government databases. It sends automated queries using APIs to retrieve weather information, warning data, and user posts. The input is the API query, and the output is the collected raw data.

[0485] Step 2:

[0486] The server integrates the collected raw data using data formatting techniques, removes noise, and formats it into an analyzable format. Specifically, it removes duplicate data and filters out inappropriate information to generate structured data. The input is the raw data obtained in step 1, and the output is the formatted, clean data.

[0487] Step 3:

[0488] The server analyzes the formatted data using machine learning algorithms as information analysis tools. These algorithms employ clustering techniques to identify the extent of disaster impact and risk scores for each region. The input is the data formatted in step 2, and the output is the risk assessment result.

[0489] Step 4:

[0490] The server uses an evacuation plan formulation tool to propose optimal evacuation routes and shelters that take into account each user's individual attributes, based on the analysis results. Specifically, it generates an evacuation plan that takes into account the user's age and health condition. The input is the risk assessment results obtained in step 3 and user attribute data, and the output is an individualized evacuation plan.

[0491] Step 5:

[0492] The terminal uses notification methods to inform the user of the evacuation plan received from the server. Specifically, it uses voice alerts and push notifications to convey information such as evacuation routes and lists of items to bring. The input is the evacuation plan generated in step 4, and the output is the notification to the user.

[0493] Step 6:

[0494] Users report their post-evacuation experiences and suggestions to their terminals through a feedback processing mechanism. The server aggregates this feedback and uses a generated AI model to improve the system. The input is user feedback information, and the output is the system improvement plan.

[0495] Step 7:

[0496] The server uses information verification tools to verify the reliability of the collected information. To eliminate misinformation and false reports, it cross-checks the source of the information and uses only highly reliable information for analysis. The input is the information obtained in step 1, and the output is the data whose reliability has been verified.

[0497] (Application Example 1)

[0498] 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."

[0499] In emergencies such as natural disasters and pandemics, rapid and appropriate evacuation is essential. However, conventional evacuation support systems struggle to analyze information and provide individualized support in real time, and there is a lack of safe evacuation support, particularly for the elderly and people with disabilities. Furthermore, evacuation support using autonomous mobile devices is still in its early stages of development, and there is a problem in that the provision of effective evacuation routes tends to be slow.

[0500] 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.

[0501] In this invention, the server includes information acquisition means for collecting disaster information, information analysis means for analyzing the disaster situation based on the acquired information, evacuation plan formulation means for identifying the optimal evacuation route and shelter based on the analysis results, individual response generation means for providing individual measures according to the user's attribute data, notification means for notifying the user of disaster response measures, and route control means for the autonomous mobile device to move the user to a safe place. As a result, the user can receive rapid and appropriate evacuation support from the autonomous mobile device.

[0502] "Information acquisition means" refers to a device or system that has the function of efficiently collecting disaster information in real time.

[0503] "Information analysis tools" refer to functions that analyze collected disaster information to identify the progress and scope of the disaster.

[0504] An "evacuation plan formulation tool" is a device or system that has the function of determining the optimal evacuation route and shelter based on the analysis results.

[0505] The "individualized response generation method" is a function that provides customized evacuation plans and countermeasures based on the user's attribute data.

[0506] A "notification means" is a device or system that has the function of informing users in real time about disaster response measures.

[0507] "Route control means" refers to a function that sets the optimal travel route for an autonomous mobile device to guide the user to a safe location.

[0508] The system that realizes this invention consists of a server, a terminal, and an autonomous mobile device. The server plays a central role in collecting and analyzing disaster information and providing users with the optimal evacuation route.

[0509] The server first acquires real-time disaster information from government databases, weather agencies, and social media platforms. The hardware consists of server computers with powerful processors, and the software uses APIs for information gathering. Next, machine learning algorithms are used to analyze this information and identify optimal evacuation routes. During this process, noise is removed from the acquired data, and the data is processed to predict the direction of movement and the extent of impact.

[0510] The terminal is a device used by the user and is responsible for receiving disaster response notifications. The terminal immediately conveys acquired evacuation route information, recommended actions, and items to bring to the user via voice alerts and push notifications.

[0511] The autonomous mobile device uses route control means to autonomously guide the user to a safe evacuation shelter, their destination, according to the evacuation route provided by the server. In this way, the autonomous vehicle has the ability to flexibly respond to disaster situations that change in real time.

[0512] For example, in the event of a flood, the autonomous mobile device can safely evacuate users to higher ground with less risk of flooding. Furthermore, user experience data regarding this system is fed back to the server and used to optimize the system for future disaster response.

[0513] The following is an example of a prompt statement using a generative AI model.

[0514] "Based on your current location, please propose a method to provide the fastest and safest evacuation route using autonomous vehicles."

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

[0516] Step 1:

[0517] The server collects disaster information from government databases, weather agencies, and social media platforms. The input is real-time data provided through APIs on various platforms, and the output is the raw data obtained.

[0518] Step 2:

[0519] The server filters the acquired raw data to remove noise. The input is the raw data obtained in step 1, and the output is the cleaned-up disaster information data. This process eliminates fake news and misinformation, preparing accurate material for analysis.

[0520] Step 3:

[0521] The server uses machine learning algorithms to analyze cleaned disaster information data. The input is clean disaster information data, and the output is the direction of disaster progression, the extent of impact, and the risk score for each region. In this step, a risk model is applied to derive disaster prediction information.

[0522] Step 4:

[0523] The server identifies the optimal evacuation route and shelter based on the analysis results. The input is the risk score obtained in step 3, and the output is an individual evacuation plan. At this stage, each user's location information is taken into consideration.

[0524] Step 5:

[0525] The device notifies the user of identified evacuation routes and shelter information. The input is the evacuation plan provided by the server, and the output is communicated to the user as voice alerts or push notifications. Here, the user immediately understands detailed response measures according to the urgency of the situation.

[0526] Step 6:

[0527] The autonomous mobile device controls its route according to evacuation route information obtained from the server, guiding the user to a safe destination. The input is the specified evacuation route, and the output is control information for the movement path. This mechanism allows for flexible responses to real-time changes in the situation.

[0528] Step 7:

[0529] After completing the evacuation, users send their experiences and feedback to the server via their terminals. The input is user feedback information, and the output is valuable data for future system improvements. This allows for the optimization of the system in preparation for future disasters.

[0530] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0531] This invention is a system that combines an emotion engine to help users take swift and accurate evacuation actions during disasters. The system consists of a server, a terminal, and an emotion engine, and in addition to real-time collection and analysis of disaster information and provision of countermeasures, it also provides information that takes into account the user's emotional state.

[0532] First, the server collects disaster information in real time from official databases, weather agencies, and social media platforms. This information is used to assess risks in each region and understand the progress of the disaster. The server also has an emotion engine that analyzes voice and text data provided by users through their devices to determine their emotional state.

[0533] Next, the server uses a deep learning algorithm to calculate a risk score based on the acquired disaster information. Furthermore, it identifies the optimal evacuation route and shelter, taking into account each user's age, health status, current location, and emotional state. During this process, psychological support messages are generated for users with high urgency and stress levels, providing assistance to help them maintain an emotionally stable state.

[0534] The device receives information sent from the server and notifies the user. This notification includes evacuation instructions that have been adjusted by an emotion engine to be most relatable to the user. For example, a user feeling anxious will receive a message using calming language, while a user who is hesitant to take action will receive a message emphasizing the importance of evacuation.

[0535] Furthermore, feedback provided by users after evacuation is sent to the server via the terminal. The server uses this feedback to improve the system and utilize it for future disaster response. In addition, data acquired by the emotion engine is used to track changes in the user's emotions during evacuation, enabling continuous support.

[0536] Thus, this system, equipped with an emotion engine, can provide information optimized for each user's individual state, enabling more effective and personalized disaster response.

[0537] The following describes the processing flow.

[0538] Step 1:

[0539] The server collects disaster information in real time from official databases and social media. It filters the data, including weather warnings and evacuation information, to extract only accurate information.

[0540] Step 2:

[0541] The server uses an emotion engine to analyze voice input and text messages sent by the user and assess the user's emotional state. This assessment includes indicators such as fear, anxiety, and calmness.

[0542] Step 3:

[0543] The server integrates the results of disaster information analysis with user sentiment evaluations to calculate a risk score for each user. The server uses machine learning algorithms to identify the optimal evacuation route and shelter for each user.

[0544] Step 4:

[0545] The server generates a personalized evacuation plan that takes into account the user's age, health status, location, and emotional state. This plan includes psychologically supportive messages and specific action instructions.

[0546] Step 5:

[0547] The device receives the evacuation plan sent from the server and notifies the user. The notification is tailored to the user's emotional state and is delivered as an audio alert or text message.

[0548] Step 6:

[0549] Users initiate safe evacuation actions based on notifications from their devices. During evacuation, they continuously report their emotional state and location to the server via their devices.

[0550] Step 7:

[0551] The server aggregates user feedback and identifies areas for improvement in the disaster response system. Based on the data collected by the emotion engine, system updates are implemented to aid in future disaster responses.

[0552] (Example 2)

[0553] 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."

[0554] In the event of a disaster, there is a need for a system that enables users to take swift and accurate evacuation actions. Such a system must not only rapidly collect and analyze disaster information, but also provide information optimized according to each user's individual circumstances and emotional state. However, current systems do not adequately address users' emotions, raising concerns about delays in action and errors in judgment under stressful circumstances.

[0555] 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.

[0556] In this invention, the server includes an information acquisition means for collecting disaster information, an information analysis means for analyzing the disaster situation based on the acquired information, and an individual response generation means for providing individual countermeasures according to the user's attribute data and emotional state. This makes it possible to provide information optimized for each user's situation and to support swift and accurate evacuation actions.

[0557] "Information acquisition means" refers to components intended for collecting disaster information in real time.

[0558] "Information analysis methods" refer to the process of analyzing collected information to assess the situation and risks of a disaster.

[0559] "Evacuation plan formulation tools" refer to the function of identifying the optimal evacuation route and destination based on analyzed information.

[0560] "Individualized response generation means" refers to technology that takes into account a user's attribute data and emotional state to provide evacuation instructions and countermeasures that are tailored to their individual needs.

[0561] "Notification means" refers to a device or function for transmitting optimized evacuation instructions or information to the user.

[0562] A "feedback processing method" is a means of collecting user feedback information and using it to improve the system.

[0563] "Emotional analysis methods" refer to the process of analyzing a user's emotional state and providing appropriate information and support.

[0564] This invention is a system developed to support rapid and accurate evacuation during disasters. Specific embodiments of the invention are described below.

[0565] The server collects disaster information in real time from official databases, weather agencies, and social media platforms. APIs are used for information retrieval, and after retrieval, information analysis tools are employed to precisely analyze the disaster situation. Specifically, high-performance computing servers are used as hardware, and the software utilizes machine learning libraries such as Python and TensorFlow.

[0566] The server analyzes voice and text data entered by the user through the terminal to estimate their emotional state. It uses a generative AI model and deep learning algorithms to perform emotion analysis. Based on these analysis results, a personalized response generation system creates evacuation routes and psychological support messages tailored to the user.

[0567] The terminal notifies the user of evacuation instructions and psychological support messages sent from the server. The notification method provides information in language optimized for the user's emotional state. For example, a user feeling anxious might see a message such as, "Please stay calm. Here is the route to the nearest evacuation center."

[0568] Furthermore, users can provide feedback after evacuation, sending it to the server via their terminal. The server aggregates this feedback information using a feedback processing mechanism and incorporates it into system improvements. This enables the realization of more accurate sentiment analysis.

[0569] A concrete example of a prompt message is, "If the emotion engine determines that user A is stressed, generate a message to calm them down." This prompt allows the system to quickly generate appropriate support information and help ensure the user's safety.

[0570] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0571] Step 1:

[0572] The server collects disaster information in real time from official databases, weather agencies, and social media platforms. Input is data points via API, and output is a continuously updated stream of disaster-related information. This collection process utilizes data filtering to extract only the most relevant information, thereby improving the accuracy of the data.

[0573] Step 2:

[0574] The server analyzes the collected disaster information and assesses disaster risk. The input is the disaster information obtained in step 1, and the output is a risk score for each region. Here, the server uses a deep learning algorithm to perform pattern recognition on the data and identify high-risk areas.

[0575] Step 3:

[0576] The user inputs their current emotions via voice or text through the device. The input is the user's voice / text data, and the output is data for analysis sent to the server. The device performs emotion estimation locally, organizes the initial data, and then performs data processing operations to transfer it to the server.

[0577] Step 4:

[0578] The server uses a generative AI model to analyze the user's emotional state. The input is the user data obtained in step 3, and the output is the emotion analysis result. Here, an emotion determination algorithm is used to classify the user's emotions into categories such as "anxiety" and "tension."

[0579] Step 5:

[0580] The server generates the optimal evacuation route and psychological support message for each user based on risk scores and sentiment analysis results. The input is the output of steps 2 and 4, and the output is the evacuation order and support message. The server uses predictive models to process and provide each user with the most suitable action plan.

[0581] Step 6:

[0582] The terminal notifies the user of evacuation instructions and psychological support messages sent from the server. The input is the output data from step 5, and the output is a visual or audio notification to the user. The terminal converts the message into an easy-to-read format so that the information is conveyed in a way that is intuitively easy for the user to understand.

[0583] Step 7:

[0584] Users provide feedback via a terminal after evacuation. Input consists of the user's experience and opinions, and output is sent to the server as feedback data. This feedback collection process involves organizing user input into text format and sending it to the server.

[0585] Step 8:

[0586] The server analyzes the collected feedback and generates data for system improvement. The input is the feedback data from step 7, and the output is the proposed system improvements. Here, the system performs analysis based on the feedback and forms proposals to help with future disaster response.

[0587] (Application Example 2)

[0588] 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."

[0589] In modern society, natural disasters are increasing, and there is a need for swift and individualized evacuation support. However, conventional systems only provide uniform disaster information and fail to address the emotions and individual circumstances of users. As a result, appropriate evacuation actions are not taken, leading to unnecessary confusion and anxiety.

[0590] 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.

[0591] In this invention, the server includes data acquisition means for collecting disaster information, information analysis means for analyzing the disaster situation based on the acquired data, and emotion support generation means for generating psychological support messages based on emotional states. This makes it possible to provide users with evacuation information that is appropriate to their emotions in real time.

[0592] "Data acquisition means" refers to devices and methods for collecting various types of information related to disasters.

[0593] "Information analysis methods" refer to the process of analyzing collected data to assess the progress and risks of a disaster.

[0594] "Evacuation plan formulation methods" refer to methods for determining the optimal evacuation route and shelter based on analyzed data.

[0595] The "individualized response generation method" is a mechanism that generates individualized countermeasures corresponding to the user's attribute information.

[0596] "Emotional analysis methods" are technical techniques used to determine a user's emotional state.

[0597] "Emotional support generation means" refers to a function for creating psychological support messages that are tailored to the user's emotions.

[0598] "Information notification means" refers to the function of transmitting disaster information and evacuation orders to users.

[0599] A "feedback processing method" is a process for collecting user feedback and using it to improve the system.

[0600] "Information verification means" refers to a function that distinguishes accurate data from a large amount of disaster information and eliminates false information.

[0601] This invention is a system that improves the user experience in evacuation support during disasters. It mainly consists of a server, terminals, and an emotion analysis engine.

[0602] The server collects disaster information from multiple databases, weather agencies, and social media platforms. Based on this information, the server analyzes the situation in real time and calculates a risk score using deep learning algorithms. Software such as TensorFlow is used for this purpose. Furthermore, the server uses an emotion analysis engine to analyze voice and text data provided by users to determine their current emotional state. Google Cloud Natural Language API is used for this process.

[0603] The device receives information transmitted from the server and notifies the user. This notification includes information tailored to the user's emotional state, processed by an emotion analysis engine. If the user is feeling anxious, the device sends reassuring messages and provides instructions to encourage quick action when necessary. By using smart glasses or a smartphone, more detailed evacuation information can be obtained through voice guidance and augmented reality (AR) displays.

[0604] For example, consider a scenario where a heavy rain warning is issued. The system uses smart glasses to display augmented reality (AR) information indicating nearby safe shelters and provides messages such as, "Please stay calm. Evacuate to a safe place as quickly as possible." This allows users to take swift action with confidence.

[0605] Specific prompts for the AI ​​model include: "Based on the user's current location and weather data, display the safest evacuation route using AR. Also, dynamically generate a message to help the user stay calm."

[0606] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0607] Step 1:

[0608] The server collects disaster information from multiple data sources. This information includes weather data, social media information, and updates from official organizations. The input consists of information from each data source, and the output is integrated disaster information. The server retrieves data via database queries and APIs and processes it to standardize its format.

[0609] Step 2:

[0610] The server analyzes the collected disaster information. Based on the input disaster information, it calculates a risk score using a deep learning algorithm. The output is a risk score indicating the severity of the disaster in each region. Data is fed into the model using a framework such as TensorFlow to obtain the analysis results.

[0611] Step 3:

[0612] The server receives audio and text data sent from the user's device and performs sentiment analysis. The input is audio or text data, and the output is an evaluation indicating the emotional state. The Google Cloud Natural Language API is used to determine whether the emotion is positive or negative.

[0613] Step 4:

[0614] The server develops individualized evacuation plans based on analysis results and emotional states. Inputs include risk scores and emotional assessments, while outputs include optimal evacuation routes and psychological support messages. These are combined to create the most appropriate action plan for the user's situation.

[0615] Step 5:

[0616] The device receives notifications from the server and conveys evacuation instructions to the user. Inputs include optimized evacuation information and messages, while output is visual and audio notifications to the user. It utilizes smartphone screens and smart glasses displays to provide AR displays and audio guidance.

[0617] Step 6:

[0618] After the user has taken evacuation action, they input feedback into a terminal. The input is information about the user's evacuation experience, and the output is data used to improve the system. Feedback can be easily recorded and sent to the server through the user interface.

[0619] Step 7:

[0620] The server improves the system based on the feedback it receives. Input is user feedback data, and output is updated analysis models and notification methods. The analysis results are reflected in improving prompts in the generating AI model, providing more effective support during future disasters.

[0621] 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.

[0622] 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.

[0623] 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.

[0624] [Fourth Embodiment]

[0625] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0626] 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.

[0627] 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).

[0628] 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.

[0629] 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.

[0630] 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).

[0631] 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.

[0632] 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.

[0633] 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.

[0634] 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.

[0635] 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.

[0636] 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.

[0637] 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".

[0638] This invention is a system that helps users take appropriate evacuation actions in the event of a large-scale natural disaster or pandemic. Specific embodiments are described below.

[0639] The server collects real-time disaster-related data from official government databases, weather agencies, and social media platforms. This includes user posts, official warnings, and map data. The server aggregates this information, removes noise, and prepares it for analysis.

[0640] Next, the server analyzes this data using machine learning algorithms. The server identifies the direction and extent of the disaster's impact and calculates a risk score for each area based on this. Based on this analysis, it identifies the optimal evacuation routes and shelters. For example, in areas where flooding is expected, it recommends evacuation sites on higher ground with a low risk of flooding.

[0641] The server stores data such as the age, health status, and location of pre-registered users. Based on this data, it develops individually optimized evacuation plans. For elderly users and users with certain chronic illnesses, evacuation shelters where medical support is available are suggested.

[0642] The device receives this evacuation information and notifies the user. Depending on the urgency of the disaster, the device immediately communicates countermeasures using voice alerts and push notifications. These notifications include details such as the shortest route to the evacuation center, recommended actions, and necessary items to bring.

[0643] Furthermore, the server is equipped with an information verification mechanism to ensure the reliability of disaster information. This eliminates false information and misinformation, allowing only accurate information to be provided to users.

[0644] Users can report their actual experiences and feedback via their devices after evacuation. The server collects this information and uses it to improve the system and develop countermeasures for future disasters. In this way, the system flexibly responds to the ever-changing disaster situation and continues to optimize itself.

[0645] This system configuration establishes a mechanism that allows users to evacuate quickly and accurately, minimizing damage caused by disasters.

[0646] The following describes the processing flow.

[0647] Step 1:

[0648] The server collects real-time disaster-related data from official databases and social media platforms. This includes weather warnings, disaster location information, and posts from residents.

[0649] Step 2:

[0650] The server filters the collected data and performs information verification to remove noise and fake news. Only reliable information is selected and passed on to the next analysis step.

[0651] Step 3:

[0652] The server uses deep learning algorithms to analyze the direction of disaster progression and the extent of its impact. Based on these analysis results, it calculates a risk score for the affected area.

[0653] Step 4:

[0654] The server identifies the optimal evacuation route and shelter based on individual user data such as age, health status, and location. Based on the analysis results, it develops a specific evacuation plan tailored to each user.

[0655] Step 5:

[0656] The device receives evacuation plans sent from the server and notifies the user. In emergencies, it uses voice alerts and push notifications to convey information visually and audibly.

[0657] Step 6:

[0658] Users receive notifications and begin safe evacuation actions according to the presented evacuation plan. After evacuation, they can also report their experience and provide feedback through their device.

[0659] Step 7:

[0660] The server aggregates user feedback and uses it to improve future disaster response measures and update the system. This feedback cycle ensures the system is always up-to-date and can respond to disasters more effectively.

[0661] (Example 1)

[0662] 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".

[0663] In emergencies such as natural disasters and pandemics, providing real-time information necessary for swift and accurate evacuation is a challenge. Existing systems sometimes have problems with the accuracy and reliability of the information they provide, and often fail to efficiently generate optimal evacuation plans tailored to individual users. Therefore, there is a need for a system that accurately provides optimized information according to the user's attributes.

[0664] 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.

[0665] In this invention, the server includes information acquisition means for collecting disaster-related data from an external database through multiple information sources, data formatting means for integrating the collected data, removing noise, and preparing it in an analyzable format, and information analysis means for identifying the direction of disaster progression and the scope of impact and calculating a risk score using a machine learning algorithm. This makes it possible to provide accurate and reliable information in real time and efficiently generate an optimal evacuation plan tailored to the individual user profile.

[0666] "Information acquisition means" refers to the function of collecting disaster-related data from external databases and multiple information sources.

[0667] "Data formatting methods" refer to functions that integrate collected data, remove noise, and prepare it in a format that can be analyzed.

[0668] "Information analysis means" refers to a function that uses machine learning algorithms to identify the direction of disaster progression and the scope of impact, and to calculate a risk score.

[0669] "Evacuation plan formulation means" refers to a function that identifies the optimal evacuation route and shelter based on analysis results and user attribute data.

[0670] The "individualized response generation method" refers to a function that generates an optimized evacuation plan based on the user's individual profile from the analysis results.

[0671] "Notification method" refers to a function that communicates evacuation plans to users via voice alerts or push notifications.

[0672] "Feedback processing means" refers to a function that collects feedback information from users and continuously improves the system's prediction accuracy using a generated AI model.

[0673] "Information verification means" refers to a function that, in collecting disaster-related information, eliminates false information and misinformation and analyzes only accurate information.

[0674] This invention is a system for supporting appropriate evacuation actions during disasters. Specific embodiments of this system are described below.

[0675] The server uses information acquisition methods to obtain real-time disaster-related data from multiple sources, including external databases. This process includes weather databases, social media platforms, and official government databases. This information is collected automatically via APIs.

[0676] Next, data formatting techniques are used to integrate the collected data and remove noise. The data is then formatted using string processing techniques to filter out unnecessary information and reconstructed as an analyzable dataset.

[0677] The server uses machine learning algorithms as a means of information analysis to analyze the collected data. This algorithm identifies the direction and extent of the disaster's progression and calculates a risk score for each region based on that. Specifically, it uses clustering techniques to perform a risk assessment of a particular region.

[0678] Using an evacuation planning system, the server proposes optimal evacuation routes and shelters that take into account the user's individual attributes. For elderly users or those with specific chronic illnesses, shelters with appropriate medical support are presented.

[0679] The terminal uses notification methods to inform the user of evacuation information received from the server. Depending on the urgency, the notification is provided as an audio alert or push notification and displayed on the user's terminal screen.

[0680] Furthermore, users provide feedback on their post-evacuation experiences and the system through a feedback processing mechanism. This information is aggregated on a server and used to update the system using a generated AI model, thereby improving prediction accuracy.

[0681] Furthermore, to ensure the reliability of disaster-related information, information verification methods will be used to eliminate false information and misinformation, and only accurate information will be used for analysis.

[0682] For example, if heavy snow is expected, the server analyzes weather data and traffic information to provide safe evacuation routes. The terminal then immediately notifies the user of this information and recommends preparing warm clothing and food.

[0683] An example of a prompt for a generative AI model is: "Analyze the extent of the earthquake last night and the areas where evacuation is recommended, and suggest the optimal evacuation route."

[0684] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0685] Step 1:

[0686] The server uses information acquisition methods to collect real-time disaster-related data from external databases, social media platforms, and official government databases. It sends automated queries using APIs to retrieve weather information, warning data, and user posts. The input is the API query, and the output is the collected raw data.

[0687] Step 2:

[0688] The server integrates the collected raw data using data formatting techniques, removes noise, and formats it into an analyzable format. Specifically, it removes duplicate data and filters out inappropriate information to generate structured data. The input is the raw data obtained in step 1, and the output is the formatted, clean data.

[0689] Step 3:

[0690] The server analyzes the formatted data using machine learning algorithms as information analysis tools. These algorithms employ clustering techniques to identify the extent of disaster impact and risk scores for each region. The input is the data formatted in step 2, and the output is the risk assessment result.

[0691] Step 4:

[0692] The server uses an evacuation plan formulation tool to propose optimal evacuation routes and shelters that take into account each user's individual attributes, based on the analysis results. Specifically, it generates an evacuation plan that takes into account the user's age and health condition. The input is the risk assessment results obtained in step 3 and user attribute data, and the output is an individualized evacuation plan.

[0693] Step 5:

[0694] The terminal uses notification methods to inform the user of the evacuation plan received from the server. Specifically, it uses voice alerts and push notifications to convey information such as evacuation routes and lists of items to bring. The input is the evacuation plan generated in step 4, and the output is the notification to the user.

[0695] Step 6:

[0696] Users report their post-evacuation experiences and suggestions to their terminals through a feedback processing mechanism. The server aggregates this feedback and uses a generated AI model to improve the system. The input is user feedback information, and the output is the system improvement plan.

[0697] Step 7:

[0698] The server uses information verification tools to verify the reliability of the collected information. To eliminate misinformation and false reports, it cross-checks the source of the information and uses only highly reliable information for analysis. The input is the information obtained in step 1, and the output is the data whose reliability has been verified.

[0699] (Application Example 1)

[0700] 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".

[0701] In emergencies such as natural disasters and pandemics, rapid and appropriate evacuation is essential. However, conventional evacuation support systems struggle to analyze information and provide individualized support in real time, and there is a lack of safe evacuation support, particularly for the elderly and people with disabilities. Furthermore, evacuation support using autonomous mobile devices is still in its early stages of development, and there is a problem in that the provision of effective evacuation routes tends to be slow.

[0702] 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.

[0703] In this invention, the server includes information acquisition means for collecting disaster information, information analysis means for analyzing the disaster situation based on the acquired information, evacuation plan formulation means for identifying the optimal evacuation route and shelter based on the analysis results, individual response generation means for providing individual measures according to the user's attribute data, notification means for notifying the user of disaster response measures, and route control means for the autonomous mobile device to move the user to a safe place. As a result, the user can receive rapid and appropriate evacuation support from the autonomous mobile device.

[0704] "Information acquisition means" refers to a device or system that has the function of efficiently collecting disaster information in real time.

[0705] "Information analysis tools" refer to functions that analyze collected disaster information to identify the progress and scope of the disaster.

[0706] An "evacuation plan formulation tool" is a device or system that has the function of determining the optimal evacuation route and shelter based on the analysis results.

[0707] The "individualized response generation method" is a function that provides customized evacuation plans and countermeasures based on the user's attribute data.

[0708] A "notification means" is a device or system that has the function of informing users in real time about disaster response measures.

[0709] "Route control means" refers to a function that sets the optimal travel route for an autonomous mobile device to guide the user to a safe location.

[0710] The system that realizes this invention consists of a server, a terminal, and an autonomous mobile device. The server plays a central role in collecting and analyzing disaster information and providing users with the optimal evacuation route.

[0711] The server first acquires real-time disaster information from government databases, weather agencies, and social media platforms. The hardware consists of server computers with powerful processors, and the software uses APIs for information gathering. Next, machine learning algorithms are used to analyze this information and identify optimal evacuation routes. During this process, noise is removed from the acquired data, and the data is processed to predict the direction of movement and the extent of impact.

[0712] The terminal is a device used by the user and is responsible for receiving disaster response notifications. The terminal immediately conveys acquired evacuation route information, recommended actions, and items to bring to the user via voice alerts and push notifications.

[0713] The autonomous mobile device uses route control means to autonomously guide the user to a safe evacuation shelter, their destination, according to the evacuation route provided by the server. In this way, the autonomous vehicle has the ability to flexibly respond to disaster situations that change in real time.

[0714] For example, in the event of a flood, the autonomous mobile device can safely evacuate users to higher ground with less risk of flooding. Furthermore, user experience data regarding this system is fed back to the server and used to optimize the system for future disaster response.

[0715] The following is an example of a prompt statement using a generative AI model.

[0716] "Based on your current location, please propose a method to provide the fastest and safest evacuation route using autonomous vehicles."

[0717] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0718] Step 1:

[0719] The server collects disaster information from government databases, weather agencies, and social media platforms. The input is real-time data provided through APIs on various platforms, and the output is the raw data obtained.

[0720] Step 2:

[0721] The server filters the acquired raw data to remove noise. The input is the raw data obtained in step 1, and the output is the cleaned-up disaster information data. This process eliminates fake news and misinformation, preparing accurate material for analysis.

[0722] Step 3:

[0723] The server uses machine learning algorithms to analyze cleaned disaster information data. The input is clean disaster information data, and the output is the direction of disaster progression, the extent of impact, and the risk score for each region. In this step, a risk model is applied to derive disaster prediction information.

[0724] Step 4:

[0725] The server identifies the optimal evacuation route and shelter based on the analysis results. The input is the risk score obtained in step 3, and the output is an individual evacuation plan. At this stage, each user's location information is taken into consideration.

[0726] Step 5:

[0727] The device notifies the user of identified evacuation routes and shelter information. The input is the evacuation plan provided by the server, and the output is communicated to the user as voice alerts or push notifications. Here, the user immediately understands detailed response measures according to the urgency of the situation.

[0728] Step 6:

[0729] The autonomous mobile device controls its route according to evacuation route information obtained from the server, guiding the user to a safe destination. The input is the specified evacuation route, and the output is control information for the movement path. This mechanism allows for flexible responses to real-time changes in the situation.

[0730] Step 7:

[0731] After completing the evacuation, users send their experiences and feedback to the server via their terminals. The input is user feedback information, and the output is valuable data for future system improvements. This allows for the optimization of the system in preparation for future disasters.

[0732] 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.

[0733] This invention is a system that combines an emotion engine to help users take swift and accurate evacuation actions during disasters. The system consists of a server, a terminal, and an emotion engine, and in addition to real-time collection and analysis of disaster information and provision of countermeasures, it also provides information that takes into account the user's emotional state.

[0734] First, the server collects disaster information in real time from official databases, weather agencies, and social media platforms. This information is used to assess risks in each region and understand the progress of the disaster. The server also has an emotion engine that analyzes voice and text data provided by users through their devices to determine their emotional state.

[0735] Next, the server uses a deep learning algorithm to calculate a risk score based on the acquired disaster information. Furthermore, it identifies the optimal evacuation route and shelter, taking into account each user's age, health status, current location, and emotional state. During this process, psychological support messages are generated for users with high urgency and stress levels, providing assistance to help them maintain an emotionally stable state.

[0736] The device receives information sent from the server and notifies the user. This notification includes evacuation instructions that have been adjusted by an emotion engine to be most relatable to the user. For example, a user feeling anxious will receive a message using calming language, while a user who is hesitant to take action will receive a message emphasizing the importance of evacuation.

[0737] Furthermore, feedback provided by users after evacuation is sent to the server via the terminal. The server uses this feedback to improve the system and utilize it for future disaster response. In addition, data acquired by the emotion engine is used to track changes in the user's emotions during evacuation, enabling continuous support.

[0738] Thus, this system, equipped with an emotion engine, can provide information optimized for each user's individual state, enabling more effective and personalized disaster response.

[0739] The following describes the processing flow.

[0740] Step 1:

[0741] The server collects disaster information in real time from official databases and social media. It filters the data, including weather warnings and evacuation information, to extract only accurate information.

[0742] Step 2:

[0743] The server uses an emotion engine to analyze voice input and text messages sent by the user and assess the user's emotional state. This assessment includes indicators such as fear, anxiety, and calmness.

[0744] Step 3:

[0745] The server integrates the results of disaster information analysis with user sentiment evaluations to calculate a risk score for each user. The server uses machine learning algorithms to identify the optimal evacuation route and shelter for each user.

[0746] Step 4:

[0747] The server generates a personalized evacuation plan that takes into account the user's age, health status, location, and emotional state. This plan includes psychologically supportive messages and specific action instructions.

[0748] Step 5:

[0749] The device receives the evacuation plan sent from the server and notifies the user. The notification is tailored to the user's emotional state and is delivered as an audio alert or text message.

[0750] Step 6:

[0751] Users initiate safe evacuation actions based on notifications from their devices. During evacuation, they continuously report their emotional state and location to the server via their devices.

[0752] Step 7:

[0753] The server aggregates user feedback and identifies areas for improvement in the disaster response system. Based on the data collected by the emotion engine, system updates are implemented to aid in future disaster responses.

[0754] (Example 2)

[0755] 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".

[0756] In the event of a disaster, there is a need for a system that enables users to take swift and accurate evacuation actions. Such a system must not only rapidly collect and analyze disaster information, but also provide information optimized according to each user's individual circumstances and emotional state. However, current systems do not adequately address users' emotions, raising concerns about delays in action and errors in judgment under stressful circumstances.

[0757] 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.

[0758] In this invention, the server includes an information acquisition means for collecting disaster information, an information analysis means for analyzing the disaster situation based on the acquired information, and an individual response generation means for providing individual countermeasures according to the user's attribute data and emotional state. This makes it possible to provide information optimized for each user's situation and to support swift and accurate evacuation actions.

[0759] "Information acquisition means" refers to components intended for collecting disaster information in real time.

[0760] "Information analysis methods" refer to the process of analyzing collected information to assess the situation and risks of a disaster.

[0761] "Evacuation plan formulation tools" refer to the function of identifying the optimal evacuation route and destination based on analyzed information.

[0762] "Individualized response generation means" refers to technology that takes into account a user's attribute data and emotional state to provide evacuation instructions and countermeasures that are tailored to their individual needs.

[0763] "Notification means" refers to a device or function for transmitting optimized evacuation instructions or information to the user.

[0764] A "feedback processing method" is a means of collecting user feedback information and using it to improve the system.

[0765] "Emotional analysis methods" refer to the process of analyzing a user's emotional state and providing appropriate information and support.

[0766] This invention is a system developed to support rapid and accurate evacuation during disasters. Specific embodiments of the invention are described below.

[0767] The server collects disaster information in real time from official databases, weather agencies, and social media platforms. APIs are used for information retrieval, and after retrieval, information analysis tools are employed to precisely analyze the disaster situation. Specifically, high-performance computing servers are used as hardware, and the software utilizes machine learning libraries such as Python and TensorFlow.

[0768] The server analyzes voice and text data entered by the user through the terminal to estimate their emotional state. It uses a generative AI model and deep learning algorithms to perform emotion analysis. Based on these analysis results, a personalized response generation system creates evacuation routes and psychological support messages tailored to the user.

[0769] The terminal notifies the user of evacuation instructions and psychological support messages sent from the server. The notification method provides information in language optimized for the user's emotional state. For example, a user feeling anxious might see a message such as, "Please stay calm. Here is the route to the nearest evacuation center."

[0770] Furthermore, users can provide feedback after evacuation, sending it to the server via their terminal. The server aggregates this feedback information using a feedback processing mechanism and incorporates it into system improvements. This enables the realization of more accurate sentiment analysis.

[0771] A concrete example of a prompt message is, "If the emotion engine determines that user A is stressed, generate a message to calm them down." This prompt allows the system to quickly generate appropriate support information and help ensure the user's safety.

[0772] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0773] Step 1:

[0774] The server collects disaster information in real time from official databases, weather agencies, and social media platforms. Input is data points via API, and output is a continuously updated stream of disaster-related information. This collection process utilizes data filtering to extract only the most relevant information, thereby improving the accuracy of the data.

[0775] Step 2:

[0776] The server analyzes the collected disaster information and assesses disaster risk. The input is the disaster information obtained in step 1, and the output is a risk score for each region. Here, the server uses a deep learning algorithm to perform pattern recognition on the data and identify high-risk areas.

[0777] Step 3:

[0778] The user inputs their current emotions via voice or text through the device. The input is the user's voice / text data, and the output is data for analysis sent to the server. The device performs emotion estimation locally, organizes the initial data, and then performs data processing operations to transfer it to the server.

[0779] Step 4:

[0780] The server uses a generative AI model to analyze the user's emotional state. The input is the user data obtained in step 3, and the output is the emotion analysis result. Here, an emotion determination algorithm is used to classify the user's emotions into categories such as "anxiety" and "tension."

[0781] Step 5:

[0782] The server generates the optimal evacuation route and psychological support message for each user based on risk scores and sentiment analysis results. The input is the output of steps 2 and 4, and the output is the evacuation order and support message. The server uses predictive models to process and provide each user with the most suitable action plan.

[0783] Step 6:

[0784] The terminal notifies the user of evacuation instructions and psychological support messages sent from the server. The input is the output data from step 5, and the output is a visual or audio notification to the user. The terminal converts the message into an easy-to-read format so that the information is conveyed in a way that is intuitively easy for the user to understand.

[0785] Step 7:

[0786] Users provide feedback via a terminal after evacuation. Input consists of the user's experience and opinions, and output is sent to the server as feedback data. This feedback collection process involves organizing user input into text format and sending it to the server.

[0787] Step 8:

[0788] The server analyzes the collected feedback and generates data for system improvement. The input is the feedback data from step 7, and the output is the proposed system improvements. Here, the system performs analysis based on the feedback and forms proposals to help with future disaster response.

[0789] (Application Example 2)

[0790] 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".

[0791] In modern society, natural disasters are increasing, and there is a need for swift and individualized evacuation support. However, conventional systems only provide uniform disaster information and fail to address the emotions and individual circumstances of users. As a result, appropriate evacuation actions are not taken, leading to unnecessary confusion and anxiety.

[0792] 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.

[0793] In this invention, the server includes data acquisition means for collecting disaster information, information analysis means for analyzing the disaster situation based on the acquired data, and emotion support generation means for generating psychological support messages based on emotional states. This makes it possible to provide users with evacuation information that is appropriate to their emotions in real time.

[0794] "Data acquisition means" refers to devices and methods for collecting various types of information related to disasters.

[0795] "Information analysis methods" refer to the process of analyzing collected data to assess the progress and risks of a disaster.

[0796] "Evacuation plan formulation methods" refer to methods for determining the optimal evacuation route and shelter based on analyzed data.

[0797] The "individualized response generation method" is a mechanism that generates individualized countermeasures corresponding to the user's attribute information.

[0798] "Emotional analysis methods" are technical techniques used to determine a user's emotional state.

[0799] "Emotional support generation means" refers to a function for creating psychological support messages that are tailored to the user's emotions.

[0800] "Information notification means" refers to the function of transmitting disaster information and evacuation orders to users.

[0801] A "feedback processing method" is a process for collecting user feedback and using it to improve the system.

[0802] "Information verification means" refers to a function that distinguishes accurate data from a large amount of disaster information and eliminates false information.

[0803] This invention is a system that improves the user experience in evacuation support during disasters. It mainly consists of a server, terminals, and an emotion analysis engine.

[0804] The server collects disaster information from multiple databases, weather agencies, and social media platforms. Based on this information, the server analyzes the situation in real time and calculates a risk score using deep learning algorithms. Software such as TensorFlow is used for this purpose. Furthermore, the server uses an emotion analysis engine to analyze voice and text data provided by users to determine their current emotional state. Google Cloud Natural Language API is used for this process.

[0805] The device receives information transmitted from the server and notifies the user. This notification includes information tailored to the user's emotional state, processed by an emotion analysis engine. If the user is feeling anxious, the device sends reassuring messages and provides instructions to encourage quick action when necessary. By using smart glasses or a smartphone, more detailed evacuation information can be obtained through voice guidance and augmented reality (AR) displays.

[0806] For example, consider a scenario where a heavy rain warning is issued. The system uses smart glasses to display augmented reality (AR) information indicating nearby safe shelters and provides messages such as, "Please stay calm. Evacuate to a safe place as quickly as possible." This allows users to take swift action with confidence.

[0807] Specific prompts for the AI ​​model include: "Based on the user's current location and weather data, display the safest evacuation route using AR. Also, dynamically generate a message to help the user stay calm."

[0808] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0809] Step 1:

[0810] The server collects disaster information from multiple data sources. This information includes weather data, social media information, and updates from official organizations. The input consists of information from each data source, and the output is integrated disaster information. The server retrieves data via database queries and APIs and processes it to standardize its format.

[0811] Step 2:

[0812] The server analyzes the collected disaster information. Based on the input disaster information, it calculates a risk score using a deep learning algorithm. The output is a risk score indicating the severity of the disaster in each region. Data is fed into the model using a framework such as TensorFlow to obtain the analysis results.

[0813] Step 3:

[0814] The server receives audio and text data sent from the user's device and performs sentiment analysis. The input is audio or text data, and the output is an evaluation indicating the emotional state. The Google Cloud Natural Language API is used to determine whether the emotion is positive or negative.

[0815] Step 4:

[0816] The server develops individualized evacuation plans based on analysis results and emotional states. Inputs include risk scores and emotional assessments, while outputs include optimal evacuation routes and psychological support messages. These are combined to create the most appropriate action plan for the user's situation.

[0817] Step 5:

[0818] The device receives notifications from the server and conveys evacuation instructions to the user. Inputs include optimized evacuation information and messages, while output is visual and audio notifications to the user. It utilizes smartphone screens and smart glasses displays to provide AR displays and audio guidance.

[0819] Step 6:

[0820] After the user has taken evacuation action, they input feedback into a terminal. The input is information about the user's evacuation experience, and the output is data used to improve the system. Feedback can be easily recorded and sent to the server through the user interface.

[0821] Step 7:

[0822] The server improves the system based on the feedback it receives. Input is user feedback data, and output is updated analysis models and notification methods. The analysis results are reflected in improving prompts in the generating AI model, providing more effective support during future disasters.

[0823] 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.

[0824] 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.

[0825] 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 robot 414.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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."

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] The following is further disclosed regarding the embodiments described above.

[0845] (Claim 1)

[0846] Information acquisition methods for collecting disaster information,

[0847] Information analysis tools for analyzing disaster situations based on acquired information,

[0848] A means of formulating an evacuation plan that identifies the optimal evacuation route and shelter based on the analysis results,

[0849] A means for generating individual responses that provide individual countermeasures according to the user's attribute data,

[0850] A notification method for informing users of disaster response measures,

[0851] A system that includes this.

[0852] (Claim 2)

[0853] The system according to claim 1, further comprising a feedback processing means for aggregating user feedback information and reflecting it in system updates.

[0854] (Claim 3)

[0855] The system according to claim 1 or 2, further comprising information verification means for filtering out fake news and handling only accurate data when a large amount of disaster information is generated.

[0856] "Example 1"

[0857] (Claim 1)

[0858] Information acquisition means for collecting disaster-related data from external databases through multiple information sources,

[0859] A data formatting method that integrates collected data, removes noise, and prepares it in a format suitable for analysis,

[0860] An information analysis means that uses a machine learning algorithm to identify the direction of disaster progression and the extent of its impact, and to calculate a risk score,

[0861] A means for formulating an evacuation plan that identifies the optimal evacuation route and shelter based on analysis results and user attribute data,

[0862] A means for generating an optimized evacuation plan based on the user's individual profile from the analysis results,

[0863] A notification method that communicates evacuation plans to users via voice alerts and push notifications,

[0864] A system that includes this.

[0865] (Claim 2)

[0866] The system according to claim 1, further comprising a feedback processing means for collecting user feedback information and continuously improving the system's prediction accuracy using a generated AI model.

[0867] (Claim 3)

[0868] The system according to claim 1, further comprising information verification means for eliminating false information and misinformation and analyzing only accurate information in the collection of disaster-related information.

[0869] "Application Example 1"

[0870] (Claim 1)

[0871] Information acquisition methods for collecting disaster information,

[0872] Information analysis tools for analyzing disaster situations based on acquired information,

[0873] A means of formulating an evacuation plan that identifies the optimal evacuation route and shelter based on the analysis results,

[0874] A means for generating individual responses that provide individual countermeasures according to the user's attribute data,

[0875] A notification method for informing users of disaster response measures,

[0876] A path control means for an autonomous mobile device to move the user to a safe location,

[0877] A system that includes this.

[0878] (Claim 2)

[0879] The system according to claim 1, further comprising a feedback processing means for aggregating user feedback information and reflecting it in system updates.

[0880] (Claim 3)

[0881] The system according to claim 1, further comprising information verification means for eliminating fake news and handling only accurate data when a large amount of disaster information is generated.

[0882] "Example 2 of combining an emotion engine"

[0883] (Claim 1)

[0884] Information acquisition methods for collecting disaster information,

[0885] Information analysis tools for analyzing disaster situations based on acquired information,

[0886] A means of formulating an evacuation plan that identifies the optimal evacuation route and evacuation facility based on the analysis results,

[0887] A means for generating individual responses that provides individualized countermeasures according to the user's attribute data and emotional state,

[0888] A notification means that notifies the user of information including evacuation instructions optimized for their emotional state,

[0889] A system that includes this.

[0890] (Claim 2)

[0891] The system according to claim 1, further comprising a feedback processing means for aggregating user feedback information and improving the system based on the feedback.

[0892] (Claim 3)

[0893] The system according to claim 1, further comprising an emotion analysis means for providing information that takes into account the user's emotional state and for continuously providing psychological support to the user.

[0894] "Application example 2 when combining with an emotional engine"

[0895] (Claim 1)

[0896] Data acquisition methods for collecting disaster information,

[0897] An information analysis tool that analyzes the disaster situation based on acquired data,

[0898] A means of formulating an evacuation plan that determines the optimal evacuation route based on the analysis results,

[0899] A means for generating individual responses that create individual countermeasures according to the user's attribute information,

[0900] An emotion analysis tool for determining the emotional state of a user,

[0901] An emotional support generation means that generates psychological support messages based on emotional state,

[0902] A means of notifying users of disaster response measures,

[0903] A system that includes this.

[0904] (Claim 2)

[0905] The system according to claim 1, further comprising a feedback processing means for collecting user feedback information and reflecting it in system improvements.

[0906] (Claim 3)

[0907] The system according to claim 1, further comprising information verification means for filtering out false information and processing only accurate data when a large amount of disaster information is generated. [Explanation of Symbols]

[0908] 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. Information acquisition methods for collecting disaster information, Information analysis tools for analyzing disaster situations based on acquired information, A means of formulating an evacuation plan that identifies the optimal evacuation route and shelter based on the analysis results, A means for generating individual responses that provide individual countermeasures according to the user's attribute data, A notification method for informing users of disaster response measures, A system that includes this.

2. The system according to claim 1, further comprising a feedback processing means for aggregating user feedback information and reflecting it in system updates.

3. The system according to claim 1 or 2, further comprising information verification means for eliminating fake news and handling only accurate data when a large amount of disaster information is generated.

Images