System

Abstract

A system is provided.SOLUTION: A system including a means for a user to input an inquiry about anxiety at the time of a disaster, a means for analyzing the content of the inquiry using a generative artificial intelligence, a means for specifying a cause of anxiety based on the analysis result, a means for extracting a related solution by referring to a database, a means for generating a mental care method or an evacuation action plan, and a means for transmitting the generated information to a terminal of the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] When a natural disaster occurs, many people feel anxious, but at the same time, a lack of appropriate countermeasures and information can lead to confusion. Conventional systems do not adequately provide mental care or specific evacuation actions during a disaster, making it difficult to effectively alleviate users' anxiety. In addition, there is a lack of systems that can respond to consultations tailored to individual situations, making it difficult to provide information that meets users' needs. [Means for solving the problem]

[0005] To solve this problem, the present invention provides the following means. Specifically, it includes means for a user to input an inquiry about anxiety during a disaster and means for analyzing the content of the inquiry using generative artificial intelligence. Furthermore, it provides a system including means for identifying the cause of anxiety based on the analysis results, means for referencing a database to extract relevant solutions, means for generating mental care methods and evacuation action plans, and means for transmitting the generated information to the user's terminal. This system allows users to obtain prompt and appropriate countermeasures and information regarding anxiety during a disaster, thereby alleviating anxiety and enabling safe evacuation actions.

[0006] In addition, by providing a means for acquiring the user's location information and a means for searching for nearby evacuation shelter information and evacuation routes based on the location information, it is possible to provide the optimal evacuation route and evacuation shelter information for each individual user. Furthermore, by providing a means for proposing an appropriate mental care method according to the content of the inquiry and a means for formatting and providing the mental care method using text generation technology, it is possible to simultaneously reduce the user's anxiety and provide psychological support.

[0007] "Users" refer to ordinary people who use this system to alleviate anxiety and seek appropriate guidelines for action in the event of a disaster.

[0008] "Disaster" refers to an emergency or dangerous situation caused by natural or man-made factors, such as earthquakes, floods, typhoons, and fires.

[0009] An "inquiry" refers to the text or question a user enters into the system to resolve their concerns or doubts.

[0010] "Terminal" refers to the device used by the user (smartphone, tablet, PC, etc.) that provides the interface for accessing the system.

[0011] "Generative artificial intelligence" refers to advanced algorithms and models that can analyze given text data and generate answers and advice in natural language.

[0012] "Database" refers to a collection of information including past disaster data, case studies, evacuation plans, and other related information.

[0013] "Solution" refers to specific methods or means for reducing the user's anxiety and suggesting appropriate actions.

[0014] "Mental care methods" refer to psychological support and relaxation techniques to reduce anxiety and stress during disasters.

[0015] An "evacuation action plan" refers to specific procedures and action plans for safe evacuation.

[0016] "Location information" refers to data that indicates a user's current geographic location.

[0017] "Shelter information" refers to information about facilities and locations where people can temporarily evacuate in the event of a disaster.

[0018] "Evacuation route" refers to information indicating the optimal route from the user's current location to an evacuation shelter.

[0019] A "natural language processing model" refers to algorithms and techniques for understanding and generating human language.

[0020] "Text generation technology" refers to algorithms and methods that generate meaningful sentences or explanations based on input data.

[0021] "Map Information API" refers to an application programming interface for obtaining and providing geographical information. [Brief explanation of the drawings]

[0022] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0023] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0024] First, the terms used in the following description will be explained.

[0025] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0026] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0027] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0028] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0029] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0033] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0034] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0035] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0036] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0037] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0040] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0041] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0042] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0043] This invention is a system for alleviating the anxiety felt by users during disasters and providing appropriate guidelines for action. This system includes a user terminal, a server, and generative artificial intelligence. Below, we will explain how this system operates and how it provides specific advice and information to users.

[0044] System Overview

[0045] Main components

[0046] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[0047] 2. Server: The core of the system, it connects with the generative AI and database, and transmits information to user devices.

[0048] 3. Generative artificial intelligence (AI): Analyzes user inquiries and generates appropriate solutions, mental care methods, and evacuation instructions.

[0049] DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] 1. Receiving inquiries from users

[0051] Users can launch the Emacon application on their own devices and input their concerns and questions in the chat window. For example, they might ask, "The earthquakes are continuing and I'm scared. What should I do?"

[0052] The terminal receives this inquiry and transmits it to the server as text data.

[0053] 2. Analysis of inquiry content

[0054] The server passes the received text data to a generative AI, which uses natural language processing technology to analyze the inquiry and identify the cause of the user's anxiety.

[0055] The server extracts keywords such as "earthquake," "anxiety," and "measures," and performs further analysis based on these.

[0056] 3. Proposing solutions and mental health care

[0057] The server accesses the database and searches for relevant solutions (e.g., information about earthquakes, past case studies, best practices for evacuation behavior, etc.) based on the extracted keywords.

[0058] Based on the search results, the generative AI generates appropriate solutions for the user in natural language, providing specific advice such as, "The current earthquake is likely an aftershock and is expected to gradually subside. Please secure your furniture and prepare an evacuation bag."

[0059] 4. Individual support

[0060] The server obtains the user's location information (if the user has given permission), searches for information on the nearest evacuation shelter and evacuation routes, and creates route guidance using the map information API.

[0061] The terminal displays information to guide the user, such as "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[0062] 5. Providing mental health care

[0063] The generative AI also suggests mental care methods (such as deep breathing, relaxation, and talking to friends and family) to reduce anxiety and stress during disasters.

[0064] The server generates this mental care method as a text and sends it to the user's device, which displays, "We recommend taking a deep breath and talking to a family member or friend for reassurance."

[0065] Specific examples

[0066] For example, consider the case where a user inputs a query such as "I'm worried about how long this earthquake will last."

[0067] The server uses generative AI to analyze the inquiry and extract keywords such as "worry," "earthquake," and "continue."

[0068] The generative AI references similar past cases from a database and generates answers such as, "Current seismic activity generally lasts for several weeks to several months, but aftershocks tend to gradually decrease."

[0069] The server then adds more specific evacuation measures and mental care methods and sends them to the user's device.

[0070] The device will display a message to the user saying, "Please check to see if your furniture is safe from tipping over and have your evacuation bag ready to go. Please also take note of how to take deep breaths and relax."

[0071] In this way, the system effectively reduces users' anxiety and provides specific and useful information to support disaster response.

[0072] The processing flow will be explained below.

[0073] Step 1:

[0074] Users launch the Emacon app on their devices and enter their concerns and questions about the disaster into the chat window. For example, they might ask, "The earthquakes are continuing and I'm scared. What should I do?"

[0075] Step 2:

[0076] The terminal acquires the inquiry entered by the user and sends it as text data to the server, where the data is securely transmitted using the HTTPS protocol.

[0077] Step 3:

[0078] The server passes the received text data to a generative artificial intelligence (AI) and instructs it to analyze it. The generative AI uses natural language processing technology to tokenize the user's inquiry and extract key keywords (e.g., "earthquake," "anxiety," and "measures").

[0079] Step 4:

[0080] Based on the tokenized text, the generative AI identifies the cause of the user's anxiety, for example, recognizing that the anxiety is about seismic activity.

[0081] Step 5:

[0082] The server then accesses a database based on the extracted keywords to search for relevant solutions and information, such as data on past earthquake cases, evacuation plans, and emergency response measures.

[0083] Step 6:

[0084] Based on the search results, generative AI generates specific solutions for users in natural language, such as "The current earthquake is likely an aftershock and is expected to gradually subside. Please secure your furniture and prepare an evacuation bag."

[0085] Step 7:

[0086] The server searches for nearby evacuation shelters and appropriate evacuation routes by acquiring the user's location information (if the user has given permission). Here, it uses a map information API to generate the optimal route from the user's current location to the evacuation shelter.

[0087] Step 8:

[0088] The generative AI will suggest mental health care methods based on the inquiry, such as deep breathing, relaxation techniques, and communication with friends and family.

[0089] Step 9:

[0090] The server integrates and packages the generated solutions, evacuation route information, and mental health advice, and then transmits this information to the user's device.

[0091] Step 10:

[0092] The device then displays the received information to the user. For example, a chat window could show specific instructions such as "The nearest evacuation shelter is X Park. Would you like to check the route from your current location?", as well as mental health care methods.

[0093] This system allows users to quickly reduce their anxiety during a disaster and obtain appropriate guidelines for action.

[0094] Example 1

[0095] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0096] When a natural disaster occurs, it is extremely important to quickly alleviate the anxiety and fear felt by users and provide appropriate guidelines for action and mental care methods. However, conventional systems have difficulty in quickly and accurately responding to users' anxiety, which can prevent users from taking appropriate action and potentially lead to greater damage. The present invention aims to solve these problems by providing a system that encourages appropriate evacuation behavior while providing users with a sense of security.

[0097] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0098] In this invention, the server includes means for allowing a user to input an inquiry about anxiety during a disaster, means for analyzing the content of the inquiry using generative artificial intelligence, means for identifying the cause of the anxiety based on the analysis results, means for referencing a database and extracting related solutions, means for generating mental care methods and evacuation action plans, means for acquiring location information and searching for information on the nearest evacuation shelter and evacuation routes, and means for transmitting the generated information to the user's terminal. This makes it possible to quickly analyze the user's anxiety and provide specific and useful information.

[0099] "User" refers to an individual or group that uses the system.

[0100] "Disaster" refers to natural phenomena such as earthquakes, floods, and typhoons, as well as events that include the man-made damage that accompanies them.

[0101] "Anxiety" refers to a state of psychological tension and worry caused by a disaster.

[0102] An "inquiry" refers to a question or matter of consultation that a user inputs into the system.

[0103] "Generative AI" refers to an AI system that uses natural language processing technology to analyze input from users and generate appropriate answers and advice.

[0104] "Analysis" refers to the process of understanding the user's inquiry and extracting the important information and keywords contained therein.

[0105] "Cause" refers to the reasons and factors behind the user's anxiety.

[0106] A "database" refers to a system that systematically organizes and stores past data and information, making it possible to search and reference it.

[0107] "Solution proposal" refers to specific courses of action or advice proposed to resolve the user's concerns or problems.

[0108] "Mental care" refers to methods and techniques for reducing users' psychological anxiety and stress.

[0109] "Evacuation action plan" refers to specific guidance and instructions to support the user's safe evacuation actions in the event of a disaster.

[0110] "Location information" refers to data that indicates a user's current geographic location.

[0111] "Evacuation shelter information" refers to information about locations and facilities where users can evacuate in the event of a disaster.

[0112] "Evacuation route" refers to route information for a user to safely move from their current location to an evacuation shelter.

[0113] "Terminal" refers to the device (smartphone, tablet, PC, etc.) that a User uses to access the System and receive and send information.

[0114] This invention is a system for alleviating the anxiety felt by users during disasters and providing appropriate guidelines for action. This system includes a user terminal, a server, and generative artificial intelligence. The following is a detailed description of how this system is implemented.

[0115] The system is configured with user devices such as smartphones, tablets, and PCs, and the generative artificial intelligence and database are placed on a server. The generative artificial intelligence is an AI model that uses natural language processing technology and is implemented using Python and TENSORFLOW (registered trademark). The database uses a relational database such as MySQL (registered trademark).

[0116] The user launches the Emacon application on their device and inputs their concerns or questions into the chat window. For example, they can make a query such as, "The earthquakes are continuing and I'm scared. What should I do?" The device then sends this query as text data to the server.

[0117] The server receives this text data and passes it to a generative AI, which uses natural language processing to analyze the text data and identify the cause of the user's anxiety. This analysis process includes extracting keywords such as "earthquake," "anxiety," and "measures."

[0118] Based on the extracted keywords, the server accesses a database to search for relevant solutions. This includes, for example, specific information about earthquakes, past case studies, and best practices for evacuation behavior. Based on the search results, the generative AI generates appropriate solutions for the user. For example, it creates advice such as, "The current earthquake is likely an aftershock and is expected to gradually subside. Secure your furniture and prepare an evacuation bag."

[0119] Furthermore, the server obtains location information from the user's device and uses the Google® Maps API to search for information on the nearest evacuation shelter and evacuation routes. For example, it generates information such as, "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[0120] The generative AI also suggests mental care methods, such as deep breathing, relaxation, or talking to friends or family. The server formats this information and sends it to the user's device, which then displays specific messages such as, "We recommend taking deep breaths and talking to family or friends to help you relax."

[0121] As a specific example, if a user inputs an inquiry such as "I'm worried about how long this earthquake will last," the following flow occurs.

[0122] The server uses generative AI to analyze the inquiry and extract keywords such as "worry," "earthquake," and "continue." The generative AI references a database of similar past cases and generates a response such as, "Current seismic activity generally continues for several weeks to several months, but aftershocks tend to gradually decrease." The server then adds specific evacuation measures (for example, "Please check to see if your furniture has been taken to prevent tipping, and have your evacuation bag ready to go") and mental health care methods ("Please also refer to methods for deep breathing and relaxation") and sends them to the user's device. This information is displayed on the device, providing the user with specific guidelines for action.

[0123] This system effectively reduces users' anxiety and supports disaster response by quickly providing specific and useful information.

[0124] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0125] Step 1:

[0126] Users launch the Emacon application on their smartphone or computer and enter their concerns or questions into the chat window. An example of input is a question like, "The earthquakes are continuing and I'm scared. What should I do?" This input is treated as text data, and the device sends this text data to the server.

[0127] Input: The text data that the user types into the chat window.

[0128] Output: Text data sent to the server

[0129] Specific operation:

[0130] The terminal receives user input

[0131] Convert text data to JSON format

[0132] sent to the server as an HTTP POST request

[0133] Step 2:

[0134] The server passes the received text data to a generative AI. The generative AI uses natural language processing technology to analyze the text data. During this analysis, keywords such as "earthquake," "anxiety," and "measures" are extracted. Preprocessing (tokenization, removal of stop words, etc.) is then performed to process the data.

[0135] Input: User's text data

[0136] Output: Extracted keywords

[0137] Specific operation:

[0138] The server passes the text data to the generative AI

[0139] Generative AI performs preprocessing

[0140] Extracting keywords using natural language processing models

[0141] Step 3:

[0142] Based on the extracted keywords, the server accesses a database to search for relevant solutions, specifically querying a MySQL database to retrieve information about earthquakes, past case studies, best practices for evacuation, and more.

[0143] Input: Extracted keywords

[0144] Output: Related solutions and information

[0145] Specific operation:

[0146] The server queries the database based on the keywords

[0147] Get the relevant information from the database

[0148] Formatting search results

[0149] Step 4:

[0150] Based on the search results, generative AI will generate appropriate solutions for users, such as advice like, "The current earthquake is likely an aftershock and is expected to gradually subside. Please secure your furniture and prepare an evacuation bag."

[0151] Input: Related solutions and information

[0152] Output: Specific solutions

[0153] Specific operation:

[0154] Generative AI receives search results

[0155] Generate solutions using natural language generation technology

[0156] Formatting the text data of the solution

[0157] Step 5:

[0158] The server obtains location information from the user's device and uses the Google Maps API to search for information about the nearest evacuation shelter and evacuation routes. For example, it generates information such as, "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[0159] Input: User's location

[0160] Output: Evacuation shelter information and evacuation routes

[0161] Specific operation:

[0162] The server obtains location information with the user's permission.

[0163] Send a request to the Google Maps API

[0164] Generate evacuation shelter information and route guidance

[0165] Step 6:

[0166] The generative AI suggests mental care methods, such as deep breathing, relaxation, or talking to friends or family. The server formats this information and sends it to the user's device.

[0167] Input: Mental care suggestions using generative AI

[0168] Output: Mental care information displayed on the user's device

[0169] Specific operation:

[0170] Generative AI generates mental care suggestions

[0171] Formatting suggestions (using natural language generation)

[0172] The server sends the formatted information to the terminal.

[0173] Step 7:

[0174] The device receives solutions, mental health care information, and evacuation shelter information from the server and displays specific messages to the user, such as "We recommend you take a deep breath and talk to family or friends to help you relax."

[0175] Input: Information sent from the server

[0176] Output: Information displayed on the user's terminal

[0177] Specific operation:

[0178] The device receives data from the server

[0179] Display your data in the right format

[0180] This allows users to quickly obtain specific and useful information, reducing anxiety and enabling them to take appropriate action.

[0181] (Application example 1)

[0182] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0183] In the event of a disaster, there is a need to quickly and accurately alleviate users' anxiety and provide specific guidelines for safe behavior. However, current systems often make it difficult for users to individually obtain appropriate information. Furthermore, they lack the ability to provide real-time advice, specific evacuation routes, and mental health support when a disaster occurs. The purpose of this invention is to solve these problems and enable users to act with peace of mind in the event of a disaster.

[0184] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0185] In this invention, the server includes means for a user to input an inquiry about anxiety in the event of a disaster, means for analyzing the content of the inquiry using generative artificial intelligence, means for identifying the cause of anxiety based on the analysis results, means for referencing a database and extracting related solutions, means for generating mental care methods and evacuation action plans, means for transmitting the generated information to the user's terminal, means for acquiring the user's location information, means for presenting evacuation shelter information and evacuation routes based on the approximate location, means for acquiring disaster information and immediately notifying the user and presenting emergency measures, and means for the AI ​​to generate appropriate advice in real time in response to the user's question, thereby enabling the user to take specific actions with peace of mind in the event of a disaster.

[0186] "User" refers to a person who accesses the system to receive information and support during a disaster.

[0187] "During a disaster" refers to the time when a natural or man-made disaster such as an earthquake, tsunami, or fire occurs.

[0188] "Inquiries about anxiety" refers to the act of users entering into the system in text format any anxieties or questions they may have in the event of a disaster.

[0189] "Generative AI" refers to an AI system that uses natural language processing technology to analyze user inquiries and generate appropriate solutions and advice.

[0190] "Analysis" refers to the process in which generative artificial intelligence analyzes the content of a user's inquiry and identifies the cause of the anxiety and appropriate countermeasures.

[0191] "Causes of anxiety" refers to the mental anxiety and fear that users feel during a disaster.

[0192] "Solutions" refer to specific measures and advice proposed by the generative artificial intelligence based on the causes of anxiety identified.

[0193] The "database" refers to a collection of information that includes information on various disasters, past case studies, and best practices for evacuation behavior.

[0194] "Mental care methods" refer to psychological support methods to reduce anxiety and stress during disasters.

[0195] "Evacuation action plan" refers to a specific action plan that a user should take in the event of a disaster.

[0196] "User's terminal" refers to the device (smartphone, tablet, PC, etc.) used by the user to access the system.

[0197] "Location information" refers to location data of the user's current location.

[0198] "Evacuation shelter information" refers to information about specific facilities and locations for evacuation in the event of a disaster.

[0199] "Evacuation route" refers to route information from the user's current location to the nearest evacuation shelter.

[0200] "Disaster information" refers to detailed information about disasters currently occurring.

[0201] "Notification" refers to messages that send disaster information or advice to the user's device.

[0202] "Emergency measures" refer to specific actions and preparations that should be taken immediately when a disaster occurs.

[0203] MODE FOR CARRYING OUT THE INVENTION

[0204] This invention is a system that provides appropriate guidelines for action and mental care methods to users who feel anxious during a disaster. The system mainly includes a user terminal, a server, and a generative artificial intelligence (AI).

[0205] User terminal

[0206] User terminals include a variety of devices, including smartphones, tablets, and PCs. Users use their terminals to launch the Emacon application and input their concerns and questions in the chat window. For example, a user might ask, "The earthquakes are continuing and I'm scared. What should I do?"

[0207] server

[0208] The server is the core of the system. It passes the received inquiry text data to the generative AI for analysis. Natural language processing technology is used for the analysis to extract specific keywords. For example, keywords such as "earthquake," "anxiety," and "measures" are extracted.

[0209] Generative artificial intelligence (AI)

[0210] The generative AI analyzes the user's inquiry to identify the cause of their anxiety, then consults a database of relevant solutions, such as information about earthquakes, past case studies, and best practices for evacuation.

[0211] Based on the extracted solutions, the generative AI generates appropriate solutions and mental care methods for the user in natural language. For example, it might provide specific advice such as, "The current earthquake is likely an aftershock and is expected to gradually subside. Please secure your furniture and prepare an evacuation bag."

[0212] Providing mental health care

[0213] The server generates mental care methods generated by generative AI as text and sends them to the user's device, such as "We recommend taking deep breaths and talking to family or friends to feel more at ease."

[0214] Use of location information

[0215] The user's device can obtain location information. The server uses this location information to search for information on the nearest evacuation shelter and evacuation routes. Route guidance is created using a map information API. The user is provided with information such as, "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[0216] Disaster Information and Emergency Notifications

[0217] The server acquires disaster information, immediately notifies users, and presents emergency measures. When a disaster occurs, generative AI generates advice in real time in response to user questions so that appropriate action can be taken quickly.

[0218] Specific examples

[0219] For example, consider the case where a user enters a query such as, "I'm worried about how long this earthquake will last." The server uses generative AI to analyze the query and extract keywords such as "worry," "earthquake," and "continue." The generative AI references past similar cases in a database and generates a response such as, "Current seismic activity generally lasts for several weeks to several months, but aftershocks tend to gradually decrease." It then adds specific evacuation measures and mental care methods and sends them to the user's device. The message displayed is, "Please check measures to prevent furniture from tipping over and have an evacuation bag ready to take immediately. Please also refer to techniques for deep breathing and relaxation."

[0220] Prompt Sentence Examples

[0221] What measures should be taken in the event of an earthquake?

[0222] Offer advice to concerned users.

[0223] For example, if the earthquake lasts for XX seconds, you should evacuate to a safe place for a while. Also, secure your furniture, prepare an evacuation bag, and check your evacuation route.

[0224] The above is a specific embodiment of this system. It is designed to use various hardware and software (such as Nominatim and OpenAI (registered trademark) API) to enable users to take action with confidence in the event of a disaster.

[0225] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0226] Step 1:

[0227] A user inputs an inquiry about anxiety during a disaster.

[0228] Specifically, the user launches the Emacon application installed on their smartphone or tablet and enters their concerns or questions into the chat window. For example, they might type, "The earthquakes are continuing and I'm scared. What should I do?"

[0229] Input: User query text

[0230] Output: Query text data

[0231] Step 2:

[0232] The terminal transmits the inquiry text data to the server.

[0233] Input: Inquiry text data

[0234] Output: Send data to the server

[0235] Step 3:

[0236] The text data received by the server is passed to the generative AI for analysis.

[0237] Specifically, the server analyzes the inquiry text data using natural language processing technology and extracts keywords, such as "earthquake," "anxiety," and "measures."

[0238] Input: Inquiry text data

[0239] Output: Extracted keywords

[0240] Step 4:

[0241] The server searches the database based on the keywords and extracts relevant solutions.

[0242] Specifically, the server searches a database for disaster information, past case studies, and best practices for evacuation procedures.

[0243] Input: Extracted keywords

[0244] Output: Related solutions

[0245] Step 5:

[0246] Based on relevant solutions, generative AI generates appropriate solutions and mental care methods for users.

[0247] As a specific action, it generates specific advice such as, "The current earthquake is likely to be an aftershock and is expected to gradually subside. Please secure furniture and prepare an evacuation bag."

[0248] Input: Related Solutions

[0249] Output: Generated solutions and mental health care methods

[0250] Step 6:

[0251] The server transmits the generated information to the user's terminal.

[0252] Specifically, the server sends the solutions and mental care methods generated by the generative AI to the user's device as text.

[0253] Input: Generated solutions and mental health care methods

[0254] Output: Data sent to the user terminal

[0255] Step 7:

[0256] The device acquires the user's location information.

[0257] Input: User location request

[0258] Output: Current location data

[0259] Step 8:

[0260] The server searches for information on the nearest evacuation shelter and evacuation routes based on location information.

[0261] Specifically, the server uses a map information API to create route guidance from the current location to the nearest evacuation shelter.

[0262] Input: Location data

[0263] Output: Evacuation shelter information and evacuation route guidance

[0264] Step 9:

[0265] The server obtains disaster information and immediately notifies users.

[0266] Specifically, when a disaster occurs, the server uses a dedicated API to obtain the latest disaster information and presents emergency measures to the user.

[0267] Input: Notification from disaster information API

[0268] Output: Urgent notification to the user

[0269] Step 10:

[0270] Generative AI generates advice in real time in response to user questions.

[0271] Specifically, the AI ​​generates an appropriate response based on the user's question and immediately sends it to the user's device.

[0272] Input: User question text

[0273] Output: Real-time consultation advice

[0274] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0275] This invention is a system for alleviating the anxiety felt by users during disasters and providing appropriate guidelines for action. This system includes a user terminal, a server, generative artificial intelligence, and an emotion engine. Below, we will explain how this system operates and how it provides specific advice and information to users.

[0276] System Overview

[0277] Main components

[0278] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[0279] 2. Server: The core of the system, it connects with the generative AI and database, and transmits information to user devices.

[0280] 3. Generative artificial intelligence (AI): Analyzes user inquiries and generates appropriate solutions, mental care methods, and evacuation instructions.

[0281] 4. Emotion engine: Recognizes emotions from the user's inquiry and generates appropriate responses based on those emotions.

[0282] DETAILED DESCRIPTION OF THE EMBODIMENTS

[0283] 1. Receiving inquiries from users

[0284] Users can launch the Emacon application on their own devices and input their concerns or questions in the chat window. For example, they might ask, "The earthquakes are continuing and I'm scared. What should I do?"

[0285] The terminal receives this inquiry and transmits it to the server as text data.

[0286] 2. Analysis of inquiry content

[0287] The server passes the received text data to an emotion engine to recognize the user's emotional state. The emotion engine uses natural language processing technology to extract emotions from the user's inquiry. For example, it can identify emotions such as anxiety or fear from the expression "scary."

[0288] The server then passes the recognized emotional state to a generative AI that analyzes the query. The generative AI then extracts key keywords from the tokenized text, such as "earthquake," "anxiety," and "measures."

[0289] 3. Proposing solutions and mental health care

[0290] Based on the extracted keywords and the recognized emotional state, the server accesses a database to search for relevant solutions and information, for example, data on past earthquake cases, evacuation plans, and emergency response measures.

[0291] Based on the search results, the generative AI generates specific solutions for the user in natural language. It reflects weighting based on the user's emotional state and adjusts the suggestions to convey a sense of kindness and security. For example, it creates advice such as, "The current earthquake is likely an aftershock and is expected to gradually subside. Don't be afraid, secure your furniture and prepare an evacuation bag."

[0292] 4. Individual support

[0293] The server searches for nearby evacuation shelters and appropriate evacuation routes by acquiring the user's location information (if the user has given permission), and generates the optimal route from the user's current location to the evacuation shelter using a map information API.

[0294] The terminal displays information to guide the user, such as "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[0295] 5. Providing mental health care

[0296] Generative AI also suggests mental care methods (deep breathing, relaxation techniques, communication with friends and family, etc.) to reduce anxiety and stress during disasters.

[0297] The server generates this mental care method as a text and sends it to the user's device, which displays, "We recommend taking a deep breath and talking to a family member or friend for reassurance."

[0298] Specific examples

[0299] For example, consider the case where a user inputs a query such as "I'm worried about how long this earthquake will last."

[0300] The server uses an emotion engine to analyze the query and extract keywords such as "worry," "earthquake," and "continue," as well as emotional states. The emotion engine determines that the user is feeling anxious based on the expression "worry."

[0301] The generative AI references similar past cases from a database and generates answers such as, "Current seismic activity generally lasts for several weeks to several months, but aftershocks tend to gradually decrease."

[0302] The server then adds more specific evacuation measures and mental care methods and sends them to the user's device.

[0303] The device will display a message to the user saying, "Please check to see if your furniture is safe from tipping over and have your evacuation bag ready to go. Please also take note of how to take deep breaths and relax."

[0304] In this way, the system effectively alleviates users' anxiety and provides specific and useful information for appropriate action. The combination of the emotion engine enables flexible responses according to the user's emotional state, realizing more personalized assistance.

[0305] The processing flow will be explained below.

[0306] Step 1:

[0307] Users launch the Emacon app on their devices and enter their concerns or questions in the chat window. For example, they can enter a question like, "The earthquakes are continuing and I'm scared. What should I do?"

[0308] Step 2:

[0309] The terminal receives the text data entered by the user and transmits it to the server using a communication protocol (e.g., HTTPS).

[0310] Step 3:

[0311] The server passes the received text data to the emotion engine, which uses natural language processing technology to extract emotions from the user's input. For example, it can identify that the user is feeling fearful based on the keyword "scary."

[0312] Step 4:

[0313] The server passes the emotional state extracted by the emotion engine to the generative AI, which then analyzes the user's inquiry. The generative AI tokenizes the input text and extracts key keywords (e.g., "earthquake," "anxiety," and "measures").

[0314] Step 5:

[0315] The server then queries the database based on the extracted keywords to retrieve relevant information, such as past earthquake cases, evacuation plans, and emergency response measures.

[0316] Step 6:

[0317] The generative AI generates specific solutions for users based on information obtained from the database. It adjusts the response depending on the emotional state identified by the emotion engine. For example, if a user is feeling fearful, it uses expressions that "provide a sense of security."

[0318] Step 7:

[0319] The server further customizes the solutions generated by the generative AI based on the user's location information, obtains the location information (if the user has permission), and uses a map information API to search for nearby evacuation shelters and evacuation routes.

[0320] Step 8:

[0321] The server integrates information on evacuation routes and shelters tailored to individual situations, as well as mental care methods, to create a final information package that includes specific guidelines for action and advice on mental care.

[0322] Step 9:

[0323] The server transmits the generated information package to the user's terminal.

[0324] Step 10:

[0325] The device then displays the received information package to the user. For example, it may provide specific instructions such as "The nearest evacuation shelter is X Park. Would you like to see the route from your current location?" or mental care advice such as "Take a deep breath and relax."

[0326] This process allows users to quickly and effectively reduce their anxiety during a disaster and provide specific guidelines for action. By combining this system with an emotion engine, the system provides flexible and personalized advice based on the user's emotional state.

[0327] Example 2

[0328] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0329] During disasters, users often feel anxious and scared, and it is necessary to quickly provide appropriate information and guidelines for action. However, conventional systems have difficulty responding flexibly to the user's emotional state, making it difficult to provide appropriate mental care or evacuation plans. They are also inadequate at suggesting individual responses or appropriate mental care methods based on the user's location information. Therefore, a system that can provide users with prompt and effective support is needed.

[0330] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0331] In this invention, the server includes means for a user to input an inquiry about anxiety during a disaster, means for analyzing the inquiry using generative artificial intelligence, means for identifying the cause of anxiety based on the analysis results, means for referencing a database and extracting related solutions, means for generating mental care methods and evacuation action plans, means for transmitting the generated information to the user's terminal, means for recognizing the user's emotional state, means for adjusting a response based on the emotional state, and means for providing specific guidelines for action to reduce anxiety during a disaster. This enables flexible responses and mental care to be provided according to the user's emotional state, thereby realizing anxiety reduction and the provision of appropriate guidelines for action during a disaster.

[0332] "User" refers to an individual who uses the system to input concerns or questions during a disaster.

[0333] "Terminals" refer to devices that users use to input their concerns and questions during a disaster and communicate with the system. Specifically, this includes smartphones, tablets, and PCs.

[0334] "Server" refers to the computer system that forms the core of the system, works in conjunction with generative artificial intelligence and databases, and transmits information to user terminals.

[0335] "Generative AI" refers to AI that analyzes user inquiries and generates appropriate solutions, mental care methods, and evacuation procedures.

[0336] An "emotion engine" refers to a system that recognizes emotions from the content of a user's inquiry and generates an appropriate response based on those emotions.

[0337] "Inquiry" refers to text data regarding concerns or questions that users input into the system.

[0338] "Analysis" refers to the process by which generative AI understands the content of a user's inquiry and extracts necessary keywords and emotional states.

[0339] "Causes of anxiety" refers to the specific reasons for the anxiety or fear that users feel during a disaster.

[0340] "Database" refers to an information system that stores information such as related solutions, mental care methods, and evacuation procedures.

[0341] "Solutions" refer to specific guidelines and measures to resolve users' concerns and questions.

[0342] "Mental care methods" refer to specific techniques for reducing anxiety and stress during a disaster, such as deep breathing, relaxation techniques, and communication suggestions.

[0343] "Evacuation action plan" refers to specific evacuation methods and guidelines for actions that users should take in the event of a disaster.

[0344] "Emotional state" refers to the specific emotion (e.g., anxiety, fear, worry) the user is feeling at the time of the inquiry.

[0345] "Response" refers to information such as solutions, mental care methods, and evacuation instructions that the system generates and provides to users.

[0346] "Location information" refers to the current geographic location obtained from the user's terminal.

[0347] "Evacuation shelter information" refers to information about locations and facilities where users can evacuate in the event of a disaster.

[0348] "Evacuation route" refers to route information for a user to travel safely from their current location to an evacuation shelter.

[0349] "Text generation technology" refers to the technology used by generative artificial intelligence to generate appropriate answers and advice in natural language.

[0350] A "prompt sentence" refers to an input sentence that causes a generative artificial intelligence to generate specific information or an answer.

[0351] This invention provides a system for alleviating anxiety felt by users during a disaster and providing appropriate guidelines for action. The system includes a user terminal, a server, a generative artificial intelligence (AI), and an emotion engine.

[0352] System Overview

[0353] Main components

[0354] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[0355] 2. Server: The core of the system, it connects with the generative AI and database, and transmits information to user devices.

[0356] 3. Generative artificial intelligence (AI): Analyzes user inquiries and generates appropriate solutions, mental care methods, and evacuation instructions.

[0357] 4. Emotion engine: Recognizes emotions from the user's inquiry and generates appropriate responses based on those emotions.

[0358] DETAILED DESCRIPTION OF THE EMBODIMENTS

[0359] 1. Receiving inquiries from users

[0360] Users can use their own devices to launch the Emacon application and input their concerns or questions into the chat window. For example, they might ask, "The earthquakes are continuing and I'm scared. What should I do?"

[0361] The terminal receives this inquiry and transmits it to the server as text data.

[0362] 2. Analysis of inquiry content

[0363] The server passes the received text data to the emotion engine, which recognizes the user's emotional state. The emotion engine uses natural language processing technology to extract emotions from the user's inquiry. For example, it can identify emotions such as anxiety or fear from the expression "scary."

[0364] The server then passes the recognized emotional state to a generative AI that analyzes the query. The generative AI then extracts key keywords from the tokenized text, such as "earthquake," "anxiety," and "measures."

[0365] 3. Proposing solutions and mental health care

[0366] Based on the extracted keywords and the recognized emotional state, the server accesses a database to search for relevant solutions and information, for example, data on past earthquake cases, evacuation plans, and emergency response measures.

[0367] Based on the search results, the generative AI generates specific solutions for the user in natural language. It reflects weighting based on the user's emotional state and adjusts the suggestions to convey a sense of kindness and security. For example, it creates advice such as, "The current earthquake is likely an aftershock and is expected to gradually subside. Don't be afraid, secure your furniture and prepare an evacuation bag."

[0368] 4. Individual support

[0369] The server provides a means to obtain the user's location information (if the user has given permission). Specifically, it obtains the current location using the device's location information API.

[0370] The server uses a map information API to search for and generate the optimal route from the user's current location to the nearest evacuation shelter. For example, it generates information such as "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[0371] The terminal displays the evacuation shelter information and route guidance sent from the server to the user.

[0372] 5. Providing mental health care

[0373] Generative AI will suggest mental care methods (deep breathing, relaxation techniques, communicating with friends and family, etc.) to reduce anxiety and stress during a disaster. For example, it will generate advice such as, "I recommend taking deep breaths and talking to family and friends."

[0374] The server sends this mental care method as a text to the user's device, which displays, "We recommend taking a deep breath and talking to family or friends to feel reassured."

[0375] Specific examples

[0376] For example, consider the case where a user inputs a query such as "I'm worried about how long this earthquake will last."

[0377] The server uses an emotion engine to analyze the query and extract keywords such as "worry," "earthquake," and "continue," as well as emotional states. The emotion engine determines that the user is feeling anxious based on the expression "worry."

[0378] The generative AI references similar past cases from a database and generates answers such as, "Current seismic activity generally lasts for several weeks to several months, but aftershocks tend to gradually decrease."

[0379] The server then adds more specific evacuation measures and mental care methods and sends them to the user's device.

[0380] The device will display a message to the user saying, "Please check measures to prevent furniture from tipping over and prepare an evacuation bag so that it can be taken out immediately. Please also refer to techniques for deep breathing and relaxation."

[0381] Examples of prompt statements

[0382] The prompt text is written as follows:

[0383] User question: "I'm worried about how long this earthquake will last."

[0384] Prompt to generative AI model: "The user is asking about the ongoing earthquake and their concerns. Please ease the user's concerns and provide appropriate courses of action. Include information based on past earthquakes and evacuation plans."

[0385] This allows the system to effectively alleviate the user's anxiety and provide appropriate guidelines for action.

[0386] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0387] Step 1:

[0388] The user launches the Emacon application on their device and enters their concerns or questions into the chat window. For example, they might type, "The earthquakes are continuing and I'm scared. What should I do?"

[0389] Input: Text data of user concerns and questions ("The earthquakes are continuing and I'm scared. What should I do?")

[0390] Output: Request to send text data from the terminal to the server

[0391] Specific operation: The device receives user input and sends text data to the server via the API.

[0392] Step 2:

[0393] The server passes the received text data to an emotion engine to recognize the user's emotional state.

[0394] Input: User's query text data sent from the terminal

[0395] Output: Text data sent to the emotion engine and the recognition result of emotional state data (e.g., "fear").

[0396] Specific operation: The server sends text data to the emotion engine API, and the emotion engine uses natural language processing technology to extract emotions from the text. For example, it identifies the emotion of "fear" from the expression "scary."

[0397] Step 3:

[0398] The server passes the recognized emotional state to a generative AI, which then analyzes the query.

[0399] Input: Emotional state data from the emotion engine (e.g., "fear") and user query text data

[0400] Output: Key keywords extracted by generative AI (e.g., "earthquake," "anxiety," "measures")

[0401] How it works: The server passes the query text and emotional state to the generative AI, which then extracts key keywords based on the tokenized text.

[0402] Step 4:

[0403] The server accesses a database to search for relevant solutions and information based on the extracted keywords and the recognized emotional state.

[0404] Input: Keywords from generative AI (e.g., "earthquake," "anxiety," "countermeasures") and emotional state data (e.g., "fear")

[0405] Output: Database search results (e.g., past earthquake cases, evacuation plans, emergency measures)

[0406] Specific operation: The server queries the database based on the extracted keywords and emotional state data to obtain relevant solutions and information.

[0407] Step 5:

[0408] Generative AI generates specific solutions for users in natural language based on search results.

[0409] Input: Search results from a database (e.g., past earthquake cases, evacuation plans, emergency measures) and emotional state data (e.g., "fear")

[0410] Output: Natural language suggestions to the user (e.g., "The current earthquake is likely an aftershock and is expected to subside gradually. Please secure furniture and prepare an evacuation bag.")

[0411] Specific operation: The generative AI generates answers in natural language based on information in the database, and reflects weighting in the response sentence according to the emotional state.

[0412] Step 6:

[0413] The server transmits the generated solutions and mental care methods to the user terminal.

[0414] Input: A solution in natural language from a generative AI

[0415] Output: Send the solution to the user's device

[0416] Specific operation: The server sends the solutions and mental care methods received from the generative AI to the user's device via the API.

[0417] Step 7:

[0418] The user's terminal displays the received information.

[0419] Input: Solutions and mental health care methods sent from the server

[0420] Output: Display to the user (e.g. "The current earthquake is likely an aftershock and is expected to gradually subside. Please secure furniture and prepare an evacuation bag.")

[0421] What it does: The device displays the received text in a chat window or notification for the user to view.

[0422] Through the above processing steps, the system can alleviate the user's anxiety in real time and provide appropriate guidelines for action.

[0423] (Application example 2)

[0424] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0425] Current disaster response systems lack the information needed to adequately alleviate users' psychological anxiety and encourage efficient and safe evacuation. Furthermore, real-time notifications and guidance on optimal evacuation routes can be delayed during emergencies, resulting in insufficient safety and psychological support for users. Given these circumstances, there is a need for systems that can alleviate users' anxiety while quickly and effectively supporting their actions.

[0426] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for a user to input an inquiry about anxiety in the event of a disaster, a means for analyzing the content of the inquiry using generative artificial intelligence, and a means for identifying the cause of the anxiety based on the analysis result. This makes it possible to quickly analyze the content of the user's inquiry and identify appropriate countermeasures.

[0427] Furthermore, the server includes a means for referencing the database and extracting relevant solutions, a means for generating mental care methods and evacuation action plans, a means for transmitting the generated information to the user's terminal, a means for transmitting emergency notifications in real time when a disaster occurs, and a means for generating and providing guidance on the optimal evacuation route based on location information, thereby making it possible to provide specific and useful information tailored to each individual user.

[0428] Furthermore, the server includes a means for acquiring location information of the user, a means for searching for and providing information on nearby evacuation shelters and evacuation routes based on the location information, and a means for analyzing the user's emotional state and suggesting appropriate mental care methods based on the analysis, thereby enabling effective evacuation support while reducing the user's psychological anxiety.

[0429] The server also includes a means for proposing an appropriate mental care method according to the content of the inquiry, a means for formatting the mental care method using text generation technology and providing it, and a means for generating a prompt sentence for the generative AI and creating a response based on the result. This makes it possible to provide flexible mental care according to the user's emotional state.

[0430] The "means for users to input inquiries about their concerns in the event of a disaster" is an interface that allows users to input their concerns and questions about the event of a disaster via a terminal.

[0431] "Means for analyzing the inquiry content using generative artificial intelligence" refers to a function that uses generative artificial intelligence to analyze the inquiry content entered by the user and understand its meaning and intent.

[0432] The "means for identifying the cause of anxiety based on the analysis results" refers to an algorithm or technology for identifying the cause of the user's anxiety from the analyzed content.

[0433] The "means for referencing a database and extracting relevant solutions" refers to a process of referencing information stored in a database and extracting appropriate solutions related to the user's concerns.

[0434] "Means for generating mental care methods and evacuation action proposals" refers to algorithms or systems for generating mental care methods and specific evacuation action proposals.

[0435] The "means for transmitting the generated information to the user's terminal" is a mechanism for transmitting the generated mental care suggestions and evacuation action plans to the user's terminal via a network.

[0436] "Means for sending emergency notifications in real time when a disaster occurs" refers to a system for immediately sending emergency notifications to users' terminals when a disaster occurs.

[0437] The "means for generating an optimal evacuation route based on location information and providing guidance thereto" is a technology that uses the user's current location information to calculate an optimal evacuation route and provides guidance thereto to the user.

[0438] "Means for obtaining user location information" refers to a function that obtains the user's current location using GPS or other location information services.

[0439] The "means for searching for and providing information on nearby evacuation shelters and evacuation routes based on the location information" is a system for searching for nearby evacuation shelters and safe evacuation routes from the user's current location and providing guidance thereto.

[0440] "Means for analyzing the user's emotional state and proposing appropriate mental care methods based on that" refers to technology that analyzes the user's input, identifies their emotional state, and proposes appropriate mental care methods.

[0441] The "means for proposing an appropriate mental care method in accordance with the content of the inquiry" is a system that proposes an appropriate mental care method for a user based on the content of the inquiry from the user.

[0442] The "means for providing the mental care method by formatting it using text generation technology" is a function for formatting the proposed mental care method into a natural text format using natural language processing technology and providing it to the user.

[0443] "Means for generating prompt sentences for generative AI and creating responses based on the results" refers to a technology that creates appropriate prompt sentences for generative AI and constructs responses to users based on the results of the generation.

[0444] Overall system configuration

[0445] The system of the present invention includes the following main components:

[0446] 1. User device: The device through which users input their concerns or questions. This includes smartphones, tablets, and computers.

[0447] 2. Server: The core of the system, containing the generative artificial intelligence, database, and emotion engine.

[0448] 3. Generative artificial intelligence (AI): Analyzes user inquiries and generates appropriate solutions, mental care methods, and evacuation instructions.

[0449] 4. Emotion engine: Analyzes the user's emotions and generates appropriate responses based on the analysis results.

[0450] 5. Database: Stores data on past disaster cases, evacuation route information, and mental care methods.

[0451] Program processing flow

[0452] 1. Receiving user inquiries

[0453] Users launch the application on their smartphone or tablet and input their concerns or questions in text. This input is sent from the device to the server. For example, a user might ask, "There have been a series of earthquakes and I'm scared. What should I do?"

[0454] 2. Analysis of inquiry content

[0455] The server uses an emotion engine to analyze the inquiry and determine the user's emotional state. The engine uses natural language processing technology to identify the emotion "fear" from the user's inquiry. Generative AI then tokenizes the text and extracts key keywords, such as "earthquake," "fear," and "measures."

[0456] 3. Proposing solutions and mental health care

[0457] The server references a database and searches for relevant solutions based on the extracted keywords. For example, it retrieves information about past earthquakes, evacuation plans, and emergency response measures. The generative AI uses this information to generate advice in natural language to ease the user's anxiety. For example, it could output something like, "The current earthquake is likely an aftershock and is expected to gradually subside. Don't be afraid, secure your furniture, and prepare an evacuation bag."

[0458] 4. Emergency notification and evacuation route provision

[0459] In the event of a disaster, the server will send emergency notifications to the user's device in real time. The notification will read, "An earthquake has just occurred. Please evacuate to a safe location." The server will then calculate the optimal evacuation route based on the user's location information and provide guidance. For example, the server will display a message saying, "The nearest evacuation shelter is XX Park. Please evacuate via this route."

[0460] 5. Providing mental health care

[0461] The emotion engine analyzes the user's emotional state, and the generative AI suggests appropriate mental care methods, such as "Take a deep breath and relax. If necessary, speak to a staff member."

[0462] Hardware and software used

[0463] User devices include iOS and Android smartphones and tablets. Cloud services such as Amazon Web Services (AWS) and Google Cloud Platform (GCP) can be used for the server. Generative AI models such as GPT-3, which has natural language processing technology, are used. The emotion engine uses an emotion recognition API (e.g., Microsoft Azure's Text Analytics API), which provides emotion analysis technology.

[0464] Examples and prompts

[0465] For example, consider the case where a user inputs "I'm worried about how long this earthquake will last." The server uses an emotion engine to extract keywords such as "worry," "earthquake," and "continue," and identifies the emotional state as "anxiety." The generative AI then references similar past cases in a database,

[0466] The model generates an answer such as, "Current seismic activity generally lasts for several weeks to several months, but aftershocks tend to gradually decrease." Examples of prompts for the model include:

[0467] "Users are worried about how long this earthquake will last. Please suggest appropriate mental care methods and guidelines for action."

[0468] Examples include:

[0469] This effectively reduces the user's anxiety and allows them to take necessary action quickly.

[0470] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0471] Step 1:

[0472] The user launches the application on their smartphone or tablet and inputs their concerns or questions in text. The input is sent from the device to the server. For example, the input data could be "There have been a series of earthquakes and I'm scared. What should I do?"

[0473] Step 2:

[0474] The server sends the text data sent by the user to the emotion engine. The emotion engine uses natural language processing technology to analyze the text and identify emotional states such as anxiety, fear, and worry. For example, the emotion of fear is identified from the expression "scared." The output data is emotional information (e.g., "fear").

[0475] Step 3:

[0476] The server provides the output (emotional information) from the emotion engine to a generative artificial intelligence (AI). The generative AI performs tokenization based on the inquiry content and the identified emotional information, and extracts key keywords (e.g., "earthquake," "fear," and "measures"). The generative AI then references a database to search for relevant solutions (e.g., "The earthquake is an aftershock and is expected to gradually subside"). The output data is the generated solution.

[0477] Step 4:

[0478] The server generates mental care methods and evacuation action suggestions based on the solutions provided by the generative AI. The generated solutions are written in natural language and are adjusted to take into account the user's emotional state. For example, advice such as "Don't be afraid, secure your furniture and prepare an evacuation bag" is generated. The output is a specific solution for the user.

[0479] Step 5:

[0480] If the user's location information is required, the server obtains it from the user's device. Based on the location information, the server uses a map information API to search for nearby evacuation shelters and evacuation routes. For example, it generates guidance such as, "The nearest evacuation shelter is XX Park, and this is the best route from your current location." The output is evacuation route information.

[0481] Step 6:

[0482] The server sends solutions and evacuation route information to the user's device. The device displays the received information to the user. For example, a message such as "The nearest evacuation shelter is XX Park. Please evacuate via this route" is displayed. The output is the displayed message.

[0483] Step 7:

[0484] When a disaster occurs, the server sends an emergency notification to the user's device in real time. The notification includes the message "An earthquake has occurred. Please evacuate to a safe place." The output is the emergency notification message.

[0485] Step 8:

[0486] The server constantly monitors the user's emotional state and suggests additional mental care methods as needed. For example, it provides messages such as, "Take a deep breath and relax. If necessary, please speak to a staff member." The output is mental care advice.

[0487] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0488] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0489] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0490] [Second embodiment]

[0491] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0492] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0493] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0494] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0495] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0496] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0497] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0498] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0499] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0500] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0501] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0502] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0503] This invention is a system for alleviating the anxiety felt by users during disasters and providing appropriate guidelines for action. This system includes a user terminal, a server, and generative artificial intelligence. Below, we will explain how this system operates and how it provides specific advice and information to users.

[0504] System Overview

[0505] Main components

[0506] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[0507] 2. Server: The core of the system, it connects with the generative AI and database, and transmits information to user devices.

[0508] 3. Generative artificial intelligence (AI): Analyzes user inquiries and generates appropriate solutions, mental care methods, and evacuation instructions.

[0509] DETAILED DESCRIPTION OF THE EMBODIMENTS

[0510] 1. Receiving inquiries from users

[0511] Users can launch the Emacon application on their own devices and input their concerns and questions in the chat window. For example, they might ask, "The earthquakes are continuing and I'm scared. What should I do?"

[0512] The terminal receives this inquiry and transmits it to the server as text data.

[0513] 2. Analysis of inquiry content

[0514] The server passes the received text data to a generative AI, which uses natural language processing technology to analyze the inquiry and identify the cause of the user's anxiety.

[0515] The server extracts keywords such as "earthquake," "anxiety," and "measures," and performs further analysis based on these.

[0516] 3. Proposing solutions and mental health care

[0517] The server accesses the database and searches for relevant solutions (e.g., information about earthquakes, past case studies, best practices for evacuation behavior, etc.) based on the extracted keywords.

[0518] Based on the search results, the generative AI generates appropriate solutions for the user in natural language, providing specific advice such as, "The current earthquake is likely an aftershock and is expected to gradually subside. Please secure your furniture and prepare an evacuation bag."

[0519] 4. Individual support

[0520] The server obtains the user's location information (if the user has given permission), searches for information on the nearest evacuation shelter and evacuation routes, and creates route guidance using the map information API.

[0521] The terminal displays information to guide the user, such as "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[0522] 5. Providing mental health care

[0523] The generative AI also suggests mental care methods (such as deep breathing, relaxation, and talking to friends and family) to reduce anxiety and stress during disasters.

[0524] The server generates this mental care method as a text and sends it to the user's device, which displays, "We recommend taking a deep breath and talking to a family member or friend for reassurance."

[0525] Specific examples

[0526] For example, consider the case where a user inputs a query such as "I'm worried about how long this earthquake will last."

[0527] The server uses generative AI to analyze the inquiry and extract keywords such as "worry," "earthquake," and "continue."

[0528] The generative AI references similar past cases from a database and generates answers such as, "Current seismic activity generally lasts for several weeks to several months, but aftershocks tend to gradually decrease."

[0529] The server then adds more specific evacuation measures and mental care methods and sends them to the user's device.

[0530] The device will display a message to the user saying, "Please check to see if your furniture is safe from tipping over and have your evacuation bag ready to go. Please also take note of how to take deep breaths and relax."

[0531] In this way, the system effectively reduces users' anxiety and provides specific and useful information to support disaster response.

[0532] The processing flow will be explained below.

[0533] Step 1:

[0534] Users launch the Emacon app on their devices and enter their concerns and questions about the disaster into the chat window. For example, they might ask, "The earthquakes are continuing and I'm scared. What should I do?"

[0535] Step 2:

[0536] The terminal acquires the inquiry entered by the user and sends it as text data to the server, where the data is securely transmitted using the HTTPS protocol.

[0537] Step 3:

[0538] The server passes the received text data to a generative artificial intelligence (AI) and instructs it to analyze it. The generative AI uses natural language processing technology to tokenize the user's inquiry and extract key keywords (e.g., "earthquake," "anxiety," and "measures").

[0539] Step 4:

[0540] Based on the tokenized text, the generative AI identifies the cause of the user's anxiety, for example, recognizing that the anxiety is about seismic activity.

[0541] Step 5:

[0542] The server then accesses a database based on the extracted keywords to search for relevant solutions and information, such as data on past earthquake cases, evacuation plans, and emergency response measures.

[0543] Step 6:

[0544] Based on the search results, generative AI generates specific solutions for users in natural language, such as "The current earthquake is likely an aftershock and is expected to gradually subside. Please secure your furniture and prepare an evacuation bag."

[0545] Step 7:

[0546] The server searches for nearby evacuation shelters and appropriate evacuation routes by acquiring the user's location information (if the user has given permission). Here, it uses a map information API to generate the optimal route from the user's current location to the evacuation shelter.

[0547] Step 8:

[0548] The generative AI will suggest mental health care methods based on the inquiry, such as deep breathing, relaxation techniques, and communication with friends and family.

[0549] Step 9:

[0550] The server integrates and packages the generated solutions, evacuation route information, and mental health advice, and then transmits this information to the user's device.

[0551] Step 10:

[0552] The device then displays the received information to the user. For example, a chat window could show specific instructions such as "The nearest evacuation shelter is X Park. Would you like to check the route from your current location?", as well as mental health care methods.

[0553] This system allows users to quickly reduce their anxiety during a disaster and obtain appropriate guidelines for action.

[0554] Example 1

[0555] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0556] When a natural disaster occurs, it is extremely important to quickly alleviate the anxiety and fear felt by users and provide appropriate guidelines for action and mental care methods. However, conventional systems have difficulty in quickly and accurately responding to users' anxiety, which can prevent users from taking appropriate action and potentially lead to greater damage. The present invention aims to solve these problems by providing a system that encourages appropriate evacuation behavior while providing users with a sense of security.

[0557] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0558] In this invention, the server includes means for allowing a user to input an inquiry about anxiety during a disaster, means for analyzing the content of the inquiry using generative artificial intelligence, means for identifying the cause of the anxiety based on the analysis results, means for referencing a database and extracting related solutions, means for generating mental care methods and evacuation action plans, means for acquiring location information and searching for information on the nearest evacuation shelter and evacuation routes, and means for transmitting the generated information to the user's terminal. This makes it possible to quickly analyze the user's anxiety and provide specific and useful information.

[0559] "User" refers to an individual or group that uses the system.

[0560] "Disaster" refers to natural phenomena such as earthquakes, floods, and typhoons, as well as events that include the man-made damage that accompanies them.

[0561] "Anxiety" refers to a state of psychological tension and worry caused by a disaster.

[0562] An "inquiry" refers to a question or matter of consultation that a user inputs into the system.

[0563] "Generative AI" refers to an AI system that uses natural language processing technology to analyze input from users and generate appropriate answers and advice.

[0564] "Analysis" refers to the process of understanding the user's inquiry and extracting the important information and keywords contained therein.

[0565] "Cause" refers to the reasons and factors behind the user's anxiety.

[0566] A "database" refers to a system that systematically organizes and stores past data and information, making it possible to search and reference it.

[0567] "Solution proposal" refers to specific courses of action or advice proposed to resolve the user's concerns or problems.

[0568] "Mental care" refers to methods and techniques for reducing users' psychological anxiety and stress.

[0569] "Evacuation action plan" refers to specific guidance and instructions to support the user's safe evacuation actions in the event of a disaster.

[0570] "Location information" refers to data that indicates a user's current geographic location.

[0571] "Evacuation shelter information" refers to information about locations and facilities where users can evacuate in the event of a disaster.

[0572] "Evacuation route" refers to route information for a user to safely move from their current location to an evacuation shelter.

[0573] "Terminal" refers to the device (smartphone, tablet, PC, etc.) that a User uses to access the System and receive and send information.

[0574] This invention is a system for alleviating the anxiety felt by users during disasters and providing appropriate guidelines for action. This system includes a user terminal, a server, and generative artificial intelligence. The following is a detailed description of how this system is implemented.

[0575] The system is configured with smartphones, tablets, PCs, etc. as user devices, and the generative AI and database are placed on the server. The generative AI is an AI model that uses natural language processing technology and is implemented using Python and TensorFlow. The database uses a relational database such as MySQL.

[0576] The user launches the Emacon application on their device and inputs their concerns or questions into the chat window. For example, they can make a query such as, "The earthquakes are continuing and I'm scared. What should I do?" The device then sends this query as text data to the server.

[0577] The server receives this text data and passes it to a generative AI, which uses natural language processing to analyze the text data and identify the cause of the user's anxiety. This analysis process includes extracting keywords such as "earthquake," "anxiety," and "measures."

[0578] Based on the extracted keywords, the server accesses a database to search for relevant solutions. This includes, for example, specific information about earthquakes, past case studies, and best practices for evacuation behavior. Based on the search results, the generative AI generates appropriate solutions for the user. For example, it creates advice such as, "The current earthquake is likely an aftershock and is expected to gradually subside. Secure your furniture and prepare an evacuation bag."

[0579] Furthermore, the server obtains location information from the user's device and uses the Google Maps API to search for information on the nearest evacuation shelter and evacuation routes. For example, it generates information such as, "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[0580] The generative AI also suggests mental care methods, such as deep breathing, relaxation, or talking to friends or family. The server formats this information and sends it to the user's device, which then displays specific messages such as, "We recommend taking deep breaths and talking to family or friends to help you relax."

[0581] As a specific example, if a user inputs an inquiry such as "I'm worried about how long this earthquake will last," the following flow occurs.

[0582] The server uses generative AI to analyze the inquiry and extract keywords such as "worry," "earthquake," and "continue." The generative AI references a database of similar past cases and generates a response such as, "Current seismic activity generally continues for several weeks to several months, but aftershocks tend to gradually decrease." The server then adds specific evacuation measures (for example, "Please check to see if your furniture has been taken to prevent tipping, and have your evacuation bag ready to go") and mental health care methods ("Please also refer to methods for deep breathing and relaxation") and sends them to the user's device. This information is displayed on the device, providing the user with specific guidelines for action.

[0583] This system effectively reduces users' anxiety and supports disaster response by quickly providing specific and useful information.

[0584] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0585] Step 1:

[0586] Users launch the Emacon application on their smartphone or computer and enter their concerns or questions into the chat window. An example of input is a question like, "The earthquakes are continuing and I'm scared. What should I do?" This input is treated as text data, and the device sends this text data to the server.

[0587] Input: The text data that the user types into the chat window.

[0588] Output: Text data sent to the server

[0589] Specific operation:

[0590] The terminal receives user input

[0591] Convert text data to JSON format

[0592] sent to the server as an HTTP POST request

[0593] Step 2:

[0594] The server passes the received text data to a generative AI. The generative AI uses natural language processing technology to analyze the text data. During this analysis, keywords such as "earthquake," "anxiety," and "measures" are extracted. Preprocessing (tokenization, removal of stop words, etc.) is then performed to process the data.

[0595] Input: User's text data

[0596] Output: Extracted keywords

[0597] Specific operation:

[0598] The server passes the text data to the generative AI

[0599] Generative AI performs preprocessing

[0600] Extracting keywords using natural language processing models

[0601] Step 3:

[0602] Based on the extracted keywords, the server accesses a database to search for relevant solutions, specifically querying a MySQL database to retrieve information about earthquakes, past case studies, best practices for evacuation, and more.

[0603] Input: Extracted keywords

[0604] Output: Related solutions and information

[0605] Specific operation:

[0606] The server queries the database based on the keywords

[0607] Get the relevant information from the database

[0608] Formatting search results

[0609] Step 4:

[0610] Based on the search results, generative AI will generate appropriate solutions for users, such as advice like, "The current earthquake is likely an aftershock and is expected to gradually subside. Please secure your furniture and prepare an evacuation bag."

[0611] Input: Related solutions and information

[0612] Output: Specific solutions

[0613] Specific operation:

[0614] Generative AI receives search results

[0615] Generate solutions using natural language generation technology

[0616] Formatting the text data of the solution

[0617] Step 5:

[0618] The server obtains location information from the user's device and uses the Google Maps API to search for information about the nearest evacuation shelter and evacuation routes. For example, it generates information such as, "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[0619] Input: User's location

[0620] Output: Evacuation shelter information and evacuation routes

[0621] Specific operation:

[0622] The server obtains location information with the user's permission.

[0623] Send a request to the Google Maps API

[0624] Generate evacuation shelter information and route guidance

[0625] Step 6:

[0626] The generative AI suggests mental care methods, such as deep breathing, relaxation, or talking to friends or family. The server formats this information and sends it to the user's device.

[0627] Input: Mental care suggestions using generative AI

[0628] Output: Mental care information displayed on the user's device

[0629] Specific operation:

[0630] Generative AI generates mental care suggestions

[0631] Formatting suggestions (using natural language generation)

[0632] The server sends the formatted information to the terminal.

[0633] Step 7:

[0634] The device receives solutions, mental health care information, and evacuation shelter information from the server and displays specific messages to the user, such as "We recommend you take a deep breath and talk to family or friends to help you relax."

[0635] Input: Information sent from the server

[0636] Output: Information displayed on the user's terminal

[0637] Specific operation:

[0638] The device receives data from the server

[0639] Display your data in the right format

[0640] This allows users to quickly obtain specific and useful information, reducing anxiety and enabling them to take appropriate action.

[0641] (Application example 1)

[0642] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0643] In the event of a disaster, there is a need to quickly and accurately alleviate users' anxiety and provide specific guidelines for safe behavior. However, current systems often make it difficult for users to individually obtain appropriate information. Furthermore, they lack the ability to provide real-time advice, specific evacuation routes, and mental health support when a disaster occurs. The purpose of this invention is to solve these problems and enable users to act with peace of mind in the event of a disaster.

[0644] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0645] In this invention, the server includes means for a user to input an inquiry about anxiety in the event of a disaster, means for analyzing the content of the inquiry using generative artificial intelligence, means for identifying the cause of anxiety based on the analysis results, means for referencing a database and extracting related solutions, means for generating mental care methods and evacuation action plans, means for transmitting the generated information to the user's terminal, means for acquiring the user's location information, means for presenting evacuation shelter information and evacuation routes based on the approximate location, means for acquiring disaster information and immediately notifying the user and presenting emergency measures, and means for the AI ​​to generate appropriate advice in real time in response to the user's question, thereby enabling the user to take specific actions with peace of mind in the event of a disaster.

[0646] "User" refers to a person who accesses the system to receive information and support during a disaster.

[0647] "During a disaster" refers to the time when a natural or man-made disaster such as an earthquake, tsunami, or fire occurs.

[0648] "Inquiries about anxiety" refers to the act of users entering into the system in text format any anxieties or questions they may have in the event of a disaster.

[0649] "Generative AI" refers to an AI system that uses natural language processing technology to analyze user inquiries and generate appropriate solutions and advice.

[0650] "Analysis" refers to the process in which generative artificial intelligence analyzes the content of a user's inquiry and identifies the cause of the anxiety and appropriate countermeasures.

[0651] "Causes of anxiety" refers to the mental anxiety and fear that users feel during a disaster.

[0652] "Solutions" refer to specific measures and advice proposed by the generative artificial intelligence based on the causes of anxiety identified.

[0653] The "database" refers to a collection of information that includes information on various disasters, past case studies, and best practices for evacuation behavior.

[0654] "Mental care methods" refer to psychological support methods to reduce anxiety and stress during disasters.

[0655] "Evacuation action plan" refers to a specific action plan that a user should take in the event of a disaster.

[0656] "User's terminal" refers to the device (smartphone, tablet, PC, etc.) used by the user to access the system.

[0657] "Location information" refers to location data of the user's current location.

[0658] "Evacuation shelter information" refers to information about specific facilities and locations for evacuation in the event of a disaster.

[0659] "Evacuation route" refers to route information from the user's current location to the nearest evacuation shelter.

[0660] "Disaster information" refers to detailed information about disasters currently occurring.

[0661] "Notification" refers to messages that send disaster information or advice to the user's device.

[0662] "Emergency measures" refer to specific actions and preparations that should be taken immediately when a disaster occurs.

[0663] MODE FOR CARRYING OUT THE INVENTION

[0664] This invention is a system that provides appropriate guidelines for action and mental care methods to users who feel anxious during a disaster. The system mainly includes a user terminal, a server, and a generative artificial intelligence (AI).

[0665] User terminal

[0666] User terminals include a variety of devices, including smartphones, tablets, and PCs. Users use their terminals to launch the Emacon application and input their concerns and questions in the chat window. For example, a user might ask, "The earthquakes are continuing and I'm scared. What should I do?"

[0667] server

[0668] The server is the core of the system. It passes the received inquiry text data to the generative AI for analysis. Natural language processing technology is used for the analysis to extract specific keywords. For example, keywords such as "earthquake," "anxiety," and "measures" are extracted.

[0669] Generative artificial intelligence (AI)

[0670] The generative AI analyzes the user's inquiry to identify the cause of their anxiety, then consults a database of relevant solutions, such as information about earthquakes, past case studies, and best practices for evacuation.

[0671] Based on the extracted solutions, the generative AI generates appropriate solutions and mental care methods for the user in natural language. For example, it might provide specific advice such as, "The current earthquake is likely an aftershock and is expected to gradually subside. Please secure your furniture and prepare an evacuation bag."

[0672] Providing mental health care

[0673] The server generates mental care methods generated by generative AI as text and sends them to the user's device, such as "We recommend taking deep breaths and talking to family or friends to feel more at ease."

[0674] Use of location information

[0675] The user's device can obtain location information. The server uses this location information to search for information on the nearest evacuation shelter and evacuation routes. Route guidance is created using a map information API. The user is provided with information such as, "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[0676] Disaster Information and Emergency Notifications

[0677] The server acquires disaster information, immediately notifies users, and presents emergency measures. When a disaster occurs, generative AI generates advice in real time in response to user questions so that appropriate action can be taken quickly.

[0678] Specific examples

[0679] For example, consider the case where a user enters a query such as, "I'm worried about how long this earthquake will last." The server uses generative AI to analyze the query and extract keywords such as "worry," "earthquake," and "continue." The generative AI references past similar cases in a database and generates a response such as, "Current seismic activity generally lasts for several weeks to several months, but aftershocks tend to gradually decrease." It then adds specific evacuation measures and mental care methods and sends them to the user's device. The message displayed is, "Please check measures to prevent furniture from tipping over and have an evacuation bag ready to take immediately. Please also refer to techniques for deep breathing and relaxation."

[0680] Prompt Sentence Examples

[0681] What measures should be taken in the event of an earthquake?

[0682] Offer advice to concerned users.

[0683] For example, if the earthquake lasts for XX seconds, you should evacuate to a safe place for a while. Also, secure your furniture, prepare an evacuation bag, and check your evacuation route.

[0684] The above is a specific implementation of this system. It is designed to use various hardware and software (such as Nominatim and OpenAI APIs) to enable users to take action with confidence in the event of a disaster.

[0685] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0686] Step 1:

[0687] A user inputs an inquiry about anxiety during a disaster.

[0688] Specifically, the user launches the Emacon application installed on their smartphone or tablet and enters their concerns or questions into the chat window. For example, they might type, "The earthquakes are continuing and I'm scared. What should I do?"

[0689] Input: User query text

[0690] Output: Query text data

[0691] Step 2:

[0692] The terminal transmits the inquiry text data to the server.

[0693] Input: Inquiry text data

[0694] Output: Send data to the server

[0695] Step 3:

[0696] The text data received by the server is passed to the generative AI for analysis.

[0697] Specifically, the server analyzes the inquiry text data using natural language processing technology and extracts keywords, such as "earthquake," "anxiety," and "measures."

[0698] Input: Inquiry text data

[0699] Output: Extracted keywords

[0700] Step 4:

[0701] The server searches the database based on the keywords and extracts relevant solutions.

[0702] Specifically, the server searches a database for disaster information, past case studies, and best practices for evacuation procedures.

[0703] Input: Extracted keywords

[0704] Output: Related solutions

[0705] Step 5:

[0706] Based on relevant solutions, generative AI generates appropriate solutions and mental care methods for users.

[0707] As a specific action, it generates specific advice such as, "The current earthquake is likely to be an aftershock and is expected to gradually subside. Please secure furniture and prepare an evacuation bag."

[0708] Input: Related Solutions

[0709] Output: Generated solutions and mental health care methods

[0710] Step 6:

[0711] The server transmits the generated information to the user's terminal.

[0712] Specifically, the server sends the solutions and mental care methods generated by the generative AI to the user's device as text.

[0713] Input: Generated solutions and mental health care methods

[0714] Output: Data sent to the user terminal

[0715] Step 7:

[0716] The device acquires the user's location information.

[0717] Input: User location request

[0718] Output: Current location data

[0719] Step 8:

[0720] The server searches for information on the nearest evacuation shelter and evacuation routes based on location information.

[0721] Specifically, the server uses a map information API to create route guidance from the current location to the nearest evacuation shelter.

[0722] Input: Location data

[0723] Output: Evacuation shelter information and evacuation route guidance

[0724] Step 9:

[0725] The server obtains disaster information and immediately notifies users.

[0726] Specifically, when a disaster occurs, the server uses a dedicated API to obtain the latest disaster information and presents emergency measures to the user.

[0727] Input: Notification from disaster information API

[0728] Output: Urgent notification to the user

[0729] Step 10:

[0730] Generative AI generates advice in real time in response to user questions.

[0731] Specifically, the AI ​​generates an appropriate response based on the user's question and immediately sends it to the user's device.

[0732] Input: User question text

[0733] Output: Real-time consultation advice

[0734] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0735] This invention is a system for alleviating the anxiety felt by users during disasters and providing appropriate guidelines for action. This system includes a user terminal, a server, generative artificial intelligence, and an emotion engine. Below, we will explain how this system operates and how it provides specific advice and information to users.

[0736] System Overview

[0737] Main components

[0738] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[0739] 2. Server: The core of the system, it connects with the generative AI and database, and transmits information to user devices.

[0740] 3. Generative artificial intelligence (AI): Analyzes user inquiries and generates appropriate solutions, mental care methods, and evacuation instructions.

[0741] 4. Emotion engine: Recognizes emotions from the user's inquiry and generates appropriate responses based on those emotions.

[0742] DETAILED DESCRIPTION OF THE EMBODIMENTS

[0743] 1. Receiving inquiries from users

[0744] Users can launch the Emacon application on their own devices and input their concerns or questions in the chat window. For example, they might ask, "The earthquakes are continuing and I'm scared. What should I do?"

[0745] The terminal receives this inquiry and transmits it to the server as text data.

[0746] 2. Analysis of inquiry content

[0747] The server passes the received text data to an emotion engine to recognize the user's emotional state. The emotion engine uses natural language processing technology to extract emotions from the user's inquiry. For example, it can identify emotions such as anxiety or fear from the expression "scary."

[0748] The server then passes the recognized emotional state to a generative AI that analyzes the query. The generative AI then extracts key keywords from the tokenized text, such as "earthquake," "anxiety," and "measures."

[0749] 3. Proposing solutions and mental health care

[0750] Based on the extracted keywords and the recognized emotional state, the server accesses a database to search for relevant solutions and information, for example, data on past earthquake cases, evacuation plans, and emergency response measures.

[0751] Based on the search results, the generative AI generates specific solutions for the user in natural language. It reflects weighting based on the user's emotional state and adjusts the suggestions to convey a sense of kindness and security. For example, it creates advice such as, "The current earthquake is likely an aftershock and is expected to gradually subside. Don't be afraid, secure your furniture and prepare an evacuation bag."

[0752] 4. Individual support

[0753] The server searches for nearby evacuation shelters and appropriate evacuation routes by acquiring the user's location information (if the user has given permission), and generates the optimal route from the user's current location to the evacuation shelter using a map information API.

[0754] The terminal displays information to guide the user, such as "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[0755] 5. Providing mental health care

[0756] Generative AI also suggests mental care methods (deep breathing, relaxation techniques, communication with friends and family, etc.) to reduce anxiety and stress during disasters.

[0757] The server generates this mental care method as a text and sends it to the user's device, which displays, "We recommend taking a deep breath and talking to a family member or friend for reassurance."

[0758] Specific examples

[0759] For example, consider the case where a user inputs a query such as "I'm worried about how long this earthquake will last."

[0760] The server uses an emotion engine to analyze the query and extract keywords such as "worry," "earthquake," and "continue," as well as emotional states. The emotion engine determines that the user is feeling anxious based on the expression "worry."

[0761] The generative AI references similar past cases from a database and generates answers such as, "Current seismic activity generally lasts for several weeks to several months, but aftershocks tend to gradually decrease."

[0762] The server then adds more specific evacuation measures and mental care methods and sends them to the user's device.

[0763] The device will display a message to the user saying, "Please check to see if your furniture is safe from tipping over and have your evacuation bag ready to go. Please also take note of how to take deep breaths and relax."

[0764] In this way, the system effectively alleviates users' anxiety and provides specific and useful information for appropriate action. The combination of the emotion engine enables flexible responses according to the user's emotional state, realizing more personalized assistance.

[0765] The processing flow will be explained below.

[0766] Step 1:

[0767] Users launch the Emacon app on their devices and enter their concerns or questions in the chat window. For example, they can enter a question like, "The earthquakes are continuing and I'm scared. What should I do?"

[0768] Step 2:

[0769] The terminal receives the text data entered by the user and transmits it to the server using a communication protocol (e.g., HTTPS).

[0770] Step 3:

[0771] The server passes the received text data to the emotion engine, which uses natural language processing technology to extract emotions from the user's input. For example, it can identify that the user is feeling fearful based on the keyword "scary."

[0772] Step 4:

[0773] The server passes the emotional state extracted by the emotion engine to the generative AI, which then analyzes the user's inquiry. The generative AI tokenizes the input text and extracts key keywords (e.g., "earthquake," "anxiety," and "measures").

[0774] Step 5:

[0775] The server then queries the database based on the extracted keywords to retrieve relevant information, such as past earthquake cases, evacuation plans, and emergency response measures.

[0776] Step 6:

[0777] The generative AI generates specific solutions for users based on information obtained from the database. It adjusts the response depending on the emotional state identified by the emotion engine. For example, if a user is feeling fearful, it uses expressions that "provide a sense of security."

[0778] Step 7:

[0779] The server further customizes the solutions generated by the generative AI based on the user's location information, obtains the location information (if the user has permission), and uses a map information API to search for nearby evacuation shelters and evacuation routes.

[0780] Step 8:

[0781] The server integrates information on evacuation routes and shelters tailored to individual situations, as well as mental care methods, to create a final information package that includes specific guidelines for action and advice on mental care.

[0782] Step 9:

[0783] The server transmits the generated information package to the user's terminal.

[0784] Step 10:

[0785] The device then displays the received information package to the user. For example, it may provide specific instructions such as "The nearest evacuation shelter is X Park. Would you like to see the route from your current location?" or mental care advice such as "Take a deep breath and relax."

[0786] This process allows users to quickly and effectively reduce their anxiety during a disaster and provide specific guidelines for action. By combining this system with an emotion engine, the system provides flexible and personalized advice based on the user's emotional state.

[0787] Example 2

[0788] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0789] During disasters, users often feel anxious and scared, and it is necessary to quickly provide appropriate information and guidelines for action. However, conventional systems have difficulty responding flexibly to the user's emotional state, making it difficult to provide appropriate mental care or evacuation plans. They are also inadequate at suggesting individual responses or appropriate mental care methods based on the user's location information. Therefore, a system that can provide users with prompt and effective support is needed.

[0790] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0791] In this invention, the server includes means for a user to input an inquiry about anxiety during a disaster, means for analyzing the inquiry using generative artificial intelligence, means for identifying the cause of anxiety based on the analysis results, means for referencing a database and extracting related solutions, means for generating mental care methods and evacuation action plans, means for transmitting the generated information to the user's terminal, means for recognizing the user's emotional state, means for adjusting a response based on the emotional state, and means for providing specific guidelines for action to reduce anxiety during a disaster. This enables flexible responses and mental care to be provided according to the user's emotional state, thereby realizing anxiety reduction and the provision of appropriate guidelines for action during a disaster.

[0792] "User" refers to an individual who uses the system to input concerns or questions during a disaster.

[0793] "Terminals" refer to devices that users use to input their concerns and questions during a disaster and communicate with the system. Specifically, this includes smartphones, tablets, and PCs.

[0794] "Server" refers to the computer system that forms the core of the system, works in conjunction with generative artificial intelligence and databases, and transmits information to user terminals.

[0795] "Generative AI" refers to AI that analyzes user inquiries and generates appropriate solutions, mental care methods, and evacuation procedures.

[0796] An "emotion engine" refers to a system that recognizes emotions from the content of a user's inquiry and generates an appropriate response based on those emotions.

[0797] "Inquiry" refers to text data regarding concerns or questions that users input into the system.

[0798] "Analysis" refers to the process by which generative AI understands the content of a user's inquiry and extracts necessary keywords and emotional states.

[0799] "Causes of anxiety" refers to the specific reasons for the anxiety or fear that users feel during a disaster.

[0800] "Database" refers to an information system that stores information such as related solutions, mental care methods, and evacuation procedures.

[0801] "Solutions" refer to specific guidelines and measures to resolve users' concerns and questions.

[0802] "Mental care methods" refer to specific techniques for reducing anxiety and stress during a disaster, such as deep breathing, relaxation techniques, and communication suggestions.

[0803] "Evacuation action plan" refers to specific evacuation methods and guidelines for actions that users should take in the event of a disaster.

[0804] "Emotional state" refers to the specific emotion (e.g., anxiety, fear, worry) the user is feeling at the time of the inquiry.

[0805] "Response" refers to information such as solutions, mental care methods, and evacuation instructions that the system generates and provides to users.

[0806] "Location information" refers to the current geographic location obtained from the user's terminal.

[0807] "Evacuation shelter information" refers to information about locations and facilities where users can evacuate in the event of a disaster.

[0808] "Evacuation route" refers to route information for a user to travel safely from their current location to an evacuation shelter.

[0809] "Text generation technology" refers to the technology used by generative artificial intelligence to generate appropriate answers and advice in natural language.

[0810] A "prompt sentence" refers to an input sentence that causes a generative artificial intelligence to generate specific information or an answer.

[0811] This invention provides a system for alleviating anxiety felt by users during a disaster and providing appropriate guidelines for action. The system includes a user terminal, a server, a generative artificial intelligence (AI), and an emotion engine.

[0812] System Overview

[0813] Main components

[0814] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[0815] 2. Server: The core of the system, it connects with the generative AI and database, and transmits information to user devices.

[0816] 3. Generative artificial intelligence (AI): Analyzes user inquiries and generates appropriate solutions, mental care methods, and evacuation instructions.

[0817] 4. Emotion engine: Recognizes emotions from the user's inquiry and generates appropriate responses based on those emotions.

[0818] DETAILED DESCRIPTION OF THE EMBODIMENTS

[0819] 1. Receiving inquiries from users

[0820] Users can use their own devices to launch the Emacon application and input their concerns or questions into the chat window. For example, they might ask, "The earthquakes are continuing and I'm scared. What should I do?"

[0821] The terminal receives this inquiry and transmits it to the server as text data.

[0822] 2. Analysis of inquiry content

[0823] The server passes the received text data to the emotion engine, which recognizes the user's emotional state. The emotion engine uses natural language processing technology to extract emotions from the user's inquiry. For example, it can identify emotions such as anxiety or fear from the expression "scary."

[0824] The server then passes the recognized emotional state to a generative AI that analyzes the query. The generative AI then extracts key keywords from the tokenized text, such as "earthquake," "anxiety," and "measures."

[0825] 3. Proposing solutions and mental health care

[0826] Based on the extracted keywords and the recognized emotional state, the server accesses a database to search for relevant solutions and information, for example, data on past earthquake cases, evacuation plans, and emergency response measures.

[0827] Based on the search results, the generative AI generates specific solutions for the user in natural language. It reflects weighting based on the user's emotional state and adjusts the suggestions to convey a sense of kindness and security. For example, it creates advice such as, "The current earthquake is likely an aftershock and is expected to gradually subside. Don't be afraid, secure your furniture and prepare an evacuation bag."

[0828] 4. Individual support

[0829] The server provides a means to obtain the user's location information (if the user has given permission). Specifically, it obtains the current location using the device's location information API.

[0830] The server uses a map information API to search for and generate the optimal route from the user's current location to the nearest evacuation shelter. For example, it generates information such as "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[0831] The terminal displays the evacuation shelter information and route guidance sent from the server to the user.

[0832] 5. Providing mental health care

[0833] Generative AI will suggest mental care methods (deep breathing, relaxation techniques, communicating with friends and family, etc.) to reduce anxiety and stress during a disaster. For example, it will generate advice such as, "I recommend taking deep breaths and talking to family and friends."

[0834] The server sends this mental care method as a text to the user's device, which displays, "We recommend taking a deep breath and talking to family or friends to feel reassured."

[0835] Specific examples

[0836] For example, consider the case where a user inputs a query such as "I'm worried about how long this earthquake will last."

[0837] The server uses an emotion engine to analyze the query and extract keywords such as "worry," "earthquake," and "continue," as well as emotional states. The emotion engine determines that the user is feeling anxious based on the expression "worry."

[0838] The generative AI references similar past cases from a database and generates answers such as, "Current seismic activity generally lasts for several weeks to several months, but aftershocks tend to gradually decrease."

[0839] The server then adds more specific evacuation measures and mental care methods and sends them to the user's device.

[0840] The device will display a message to the user saying, "Please check measures to prevent furniture from tipping over and prepare an evacuation bag so that it can be taken out immediately. Please also refer to techniques for deep breathing and relaxation."

[0841] Examples of prompt statements

[0842] The prompt text is written as follows:

[0843] User question: "I'm worried about how long this earthquake will last."

[0844] Prompt to generative AI model: "The user is asking about the ongoing earthquake and their concerns. Please ease the user's concerns and provide appropriate courses of action. Include information based on past earthquakes and evacuation plans."

[0845] This allows the system to effectively alleviate the user's anxiety and provide appropriate guidelines for action.

[0846] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0847] Step 1:

[0848] The user launches the Emacon application on their device and enters their concerns or questions into the chat window. For example, they might type, "The earthquakes are continuing and I'm scared. What should I do?"

[0849] Input: Text data of user concerns and questions ("The earthquakes are continuing and I'm scared. What should I do?")

[0850] Output: Request to send text data from the terminal to the server

[0851] Specific operation: The device receives user input and sends text data to the server via the API.

[0852] Step 2:

[0853] The server passes the received text data to an emotion engine to recognize the user's emotional state.

[0854] Input: User's query text data sent from the terminal

[0855] Output: Text data sent to the emotion engine and the recognition result of emotional state data (e.g., "fear").

[0856] Specific operation: The server sends text data to the emotion engine API, and the emotion engine uses natural language processing technology to extract emotions from the text. For example, it identifies the emotion of "fear" from the expression "scary."

[0857] Step 3:

[0858] The server passes the recognized emotional state to a generative AI, which then analyzes the query.

[0859] Input: Emotional state data from the emotion engine (e.g., "fear") and user query text data

[0860] Output: Key keywords extracted by generative AI (e.g., "earthquake," "anxiety," "measures")

[0861] How it works: The server passes the query text and emotional state to the generative AI, which then extracts key keywords based on the tokenized text.

[0862] Step 4:

[0863] The server accesses a database to search for relevant solutions and information based on the extracted keywords and the recognized emotional state.

[0864] Input: Keywords from generative AI (e.g., "earthquake," "anxiety," "countermeasures") and emotional state data (e.g., "fear")

[0865] Output: Database search results (e.g., past earthquake cases, evacuation plans, emergency measures)

[0866] Specific operation: The server queries the database based on the extracted keywords and emotional state data to obtain relevant solutions and information.

[0867] Step 5:

[0868] Generative AI generates specific solutions for users in natural language based on search results.

[0869] Input: Search results from a database (e.g., past earthquake cases, evacuation plans, emergency measures) and emotional state data (e.g., "fear")

[0870] Output: Natural language suggestions to the user (e.g., "The current earthquake is likely an aftershock and is expected to subside gradually. Please secure furniture and prepare an evacuation bag.")

[0871] Specific operation: The generative AI generates answers in natural language based on information in the database, and reflects weighting in the response sentence according to the emotional state.

[0872] Step 6:

[0873] The server transmits the generated solutions and mental care methods to the user terminal.

[0874] Input: A solution in natural language from a generative AI

[0875] Output: Send the solution to the user's device

[0876] Specific operation: The server sends the solutions and mental care methods received from the generative AI to the user's device via the API.

[0877] Step 7:

[0878] The user's terminal displays the received information.

[0879] Input: Solutions and mental health care methods sent from the server

[0880] Output: Display to the user (e.g. "The current earthquake is likely an aftershock and is expected to gradually subside. Please secure furniture and prepare an evacuation bag.")

[0881] What it does: The device displays the received text in a chat window or notification for the user to view.

[0882] Through the above processing steps, the system can alleviate the user's anxiety in real time and provide appropriate guidelines for action.

[0883] (Application example 2)

[0884] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0885] Current disaster response systems lack the information needed to adequately alleviate users' psychological anxiety and encourage efficient and safe evacuation. Furthermore, real-time notifications and guidance on optimal evacuation routes can be delayed during emergencies, resulting in insufficient safety and psychological support for users. Given these circumstances, there is a need for systems that can alleviate users' anxiety while quickly and effectively supporting their actions.

[0886] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for a user to input an inquiry about anxiety in the event of a disaster, a means for analyzing the content of the inquiry using generative artificial intelligence, and a means for identifying the cause of the anxiety based on the analysis result. This makes it possible to quickly analyze the content of the user's inquiry and identify appropriate countermeasures.

[0887] Furthermore, the server includes a means for referencing the database and extracting relevant solutions, a means for generating mental care methods and evacuation action plans, a means for transmitting the generated information to the user's terminal, a means for transmitting emergency notifications in real time when a disaster occurs, and a means for generating and providing guidance on the optimal evacuation route based on location information, thereby making it possible to provide specific and useful information tailored to each individual user.

[0888] Furthermore, the server includes a means for acquiring location information of the user, a means for searching for and providing information on nearby evacuation shelters and evacuation routes based on the location information, and a means for analyzing the user's emotional state and suggesting appropriate mental care methods based on the analysis, thereby enabling effective evacuation support while reducing the user's psychological anxiety.

[0889] The server also includes a means for proposing an appropriate mental care method according to the content of the inquiry, a means for formatting the mental care method using text generation technology and providing it, and a means for generating a prompt sentence for the generative AI and creating a response based on the result. This makes it possible to provide flexible mental care according to the user's emotional state.

[0890] The "means for users to input inquiries about their concerns in the event of a disaster" is an interface that allows users to input their concerns and questions about the event of a disaster via a terminal.

[0891] "Means for analyzing the inquiry content using generative artificial intelligence" refers to a function that uses generative artificial intelligence to analyze the inquiry content entered by the user and understand its meaning and intent.

[0892] The "means for identifying the cause of anxiety based on the analysis results" refers to an algorithm or technology for identifying the cause of the user's anxiety from the analyzed content.

[0893] The "means for referencing a database and extracting relevant solutions" refers to a process of referencing information stored in a database and extracting appropriate solutions related to the user's concerns.

[0894] "Means for generating mental care methods and evacuation action proposals" refers to algorithms or systems for generating mental care methods and specific evacuation action proposals.

[0895] The "means for transmitting the generated information to the user's terminal" is a mechanism for transmitting the generated mental care suggestions and evacuation action plans to the user's terminal via a network.

[0896] "Means for sending emergency notifications in real time when a disaster occurs" refers to a system for immediately sending emergency notifications to users' terminals when a disaster occurs.

[0897] The "means for generating an optimal evacuation route based on location information and providing guidance thereto" is a technology that uses the user's current location information to calculate an optimal evacuation route and provides guidance thereto to the user.

[0898] "Means for obtaining user location information" refers to a function that obtains the user's current location using GPS or other location information services.

[0899] The "means for searching for and providing information on nearby evacuation shelters and evacuation routes based on the location information" is a system for searching for nearby evacuation shelters and safe evacuation routes from the user's current location and providing guidance thereto.

[0900] "Means for analyzing the user's emotional state and proposing appropriate mental care methods based on that" refers to technology that analyzes the user's input, identifies their emotional state, and proposes appropriate mental care methods.

[0901] The "means for proposing an appropriate mental care method in accordance with the content of the inquiry" is a system that proposes an appropriate mental care method for a user based on the content of the inquiry from the user.

[0902] The "means for providing the mental care method by formatting it using text generation technology" is a function for formatting the proposed mental care method into a natural text format using natural language processing technology and providing it to the user.

[0903] "Means for generating prompt sentences for generative AI and creating responses based on the results" refers to a technology that creates appropriate prompt sentences for generative AI and constructs responses to users based on the results of the generation.

[0904] Overall system configuration

[0905] The system of the present invention includes the following main components:

[0906] 1. User device: The device through which users input their concerns or questions. This includes smartphones, tablets, and computers.

[0907] 2. Server: The core of the system, containing the generative artificial intelligence, database, and emotion engine.

[0908] 3. Generative artificial intelligence (AI): Analyzes user inquiries and generates appropriate solutions, mental care methods, and evacuation instructions.

[0909] 4. Emotion engine: Analyzes the user's emotions and generates appropriate responses based on the analysis results.

[0910] 5. Database: Stores data on past disaster cases, evacuation route information, and mental care methods.

[0911] Program processing flow

[0912] 1. Receiving user inquiries

[0913] Users launch the application on their smartphone or tablet and input their concerns or questions in text. This input is sent from the device to the server. For example, a user might ask, "There have been a series of earthquakes and I'm scared. What should I do?"

[0914] 2. Analysis of inquiry content

[0915] The server uses an emotion engine to analyze the inquiry and determine the user's emotional state. The engine uses natural language processing technology to identify the emotion "fear" from the user's inquiry. Generative AI then tokenizes the text and extracts key keywords, such as "earthquake," "fear," and "measures."

[0916] 3. Proposing solutions and mental health care

[0917] The server references a database and searches for relevant solutions based on the extracted keywords. For example, it retrieves information about past earthquakes, evacuation plans, and emergency response measures. The generative AI uses this information to generate advice in natural language to ease the user's anxiety. For example, it could output something like, "The current earthquake is likely an aftershock and is expected to gradually subside. Don't be afraid, secure your furniture, and prepare an evacuation bag."

[0918] 4. Emergency notification and evacuation route provision

[0919] In the event of a disaster, the server will send emergency notifications to the user's device in real time. The notification will read, "An earthquake has just occurred. Please evacuate to a safe location." The server will then calculate the optimal evacuation route based on the user's location information and provide guidance. For example, the server will display a message saying, "The nearest evacuation shelter is XX Park. Please evacuate via this route."

[0920] 5. Providing mental health care

[0921] The emotion engine analyzes the user's emotional state, and the generative AI suggests appropriate mental care methods, such as "Take a deep breath and relax. If necessary, speak to a staff member."

[0922] Hardware and software used

[0923] User devices include iOS and Android smartphones and tablets. Cloud services such as Amazon Web Services (AWS) and Google Cloud Platform (GCP) can be used for servers. Generative AI models such as GPT-3, which have natural language processing technology, are used. The emotion engine uses emotion recognition APIs (e.g., Microsoft Azure's Text Analytics API) that provide emotion analysis technology.

[0924] Examples and prompts

[0925] For example, consider the case where a user inputs "I'm worried about how long this earthquake will last." The server uses an emotion engine to extract keywords such as "worry," "earthquake," and "continue," and identifies the emotional state as "anxiety." The generative AI then references similar past cases in a database,

[0926] The model generates an answer such as, "Current seismic activity generally lasts for several weeks to several months, but aftershocks tend to gradually decrease." Examples of prompts for the model include:

[0927] "Users are worried about how long this earthquake will last. Please suggest appropriate mental care methods and guidelines for action."

[0928] Examples include:

[0929] This effectively reduces the user's anxiety and allows them to take necessary action quickly.

[0930] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0931] Step 1:

[0932] The user launches the application on their smartphone or tablet and inputs their concerns or questions in text. The input is sent from the device to the server. For example, the input data could be "There have been a series of earthquakes and I'm scared. What should I do?"

[0933] Step 2:

[0934] The server sends the text data sent by the user to the emotion engine. The emotion engine uses natural language processing technology to analyze the text and identify emotional states such as anxiety, fear, and worry. For example, the emotion of fear is identified from the expression "scared." The output data is emotional information (e.g., "fear").

[0935] Step 3:

[0936] The server provides the output (emotional information) from the emotion engine to a generative artificial intelligence (AI). The generative AI performs tokenization based on the inquiry content and the identified emotional information, and extracts key keywords (e.g., "earthquake," "fear," and "measures"). The generative AI then references a database to search for relevant solutions (e.g., "The earthquake is an aftershock and is expected to gradually subside"). The output data is the generated solution.

[0937] Step 4:

[0938] The server generates mental care methods and evacuation action suggestions based on the solutions provided by the generative AI. The generated solutions are written in natural language and are adjusted to take into account the user's emotional state. For example, advice such as "Don't be afraid, secure your furniture and prepare an evacuation bag" is generated. The output is a specific solution for the user.

[0939] Step 5:

[0940] If the user's location information is required, the server obtains it from the user's device. Based on the location information, the server uses a map information API to search for nearby evacuation shelters and evacuation routes. For example, it generates guidance such as, "The nearest evacuation shelter is XX Park, and this is the best route from your current location." The output is evacuation route information.

[0941] Step 6:

[0942] The server sends solutions and evacuation route information to the user's device. The device displays the received information to the user. For example, a message such as "The nearest evacuation shelter is XX Park. Please evacuate via this route" is displayed. The output is the displayed message.

[0943] Step 7:

[0944] When a disaster occurs, the server sends an emergency notification to the user's device in real time. The notification includes the message "An earthquake has occurred. Please evacuate to a safe place." The output is the emergency notification message.

[0945] Step 8:

[0946] The server constantly monitors the user's emotional state and suggests additional mental care methods as needed. For example, it provides messages such as, "Take a deep breath and relax. If necessary, please speak to a staff member." The output is mental care advice.

[0947] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0948] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0949] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0950] [Third embodiment]

[0951] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0952] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0953] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0954] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0955] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0956] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0957] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0958] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0959] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0960] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0961] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0962] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0963] This invention is a system for alleviating the anxiety felt by users during disasters and providing appropriate guidelines for action. This system includes a user terminal, a server, and generative artificial intelligence. Below, we will explain how this system operates and how it provides specific advice and information to users.

[0964] System Overview

[0965] Main components

[0966] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[0967] 2. Server: The core of the system, it connects with the generative AI and database, and transmits information to user devices.

[0968] 3. Generative artificial intelligence (AI): Analyzes user inquiries and generates appropriate solutions, mental care methods, and evacuation instructions.

[0969] DETAILED DESCRIPTION OF THE EMBODIMENTS

[0970] 1. Receiving inquiries from users

[0971] Users can launch the Emacon application on their own devices and input their concerns and questions in the chat window. For example, they might ask, "The earthquakes are continuing and I'm scared. What should I do?"

[0972] The terminal receives this inquiry and transmits it to the server as text data.

[0973] 2. Analysis of inquiry content

[0974] The server passes the received text data to a generative AI, which uses natural language processing technology to analyze the inquiry and identify the cause of the user's anxiety.

[0975] The server extracts keywords such as "earthquake," "anxiety," and "measures," and performs further analysis based on these.

[0976] 3. Proposing solutions and mental health care

[0977] The server accesses the database and searches for relevant solutions (e.g., information about earthquakes, past case studies, best practices for evacuation behavior, etc.) based on the extracted keywords.

[0978] Based on the search results, the generative AI generates appropriate solutions for the user in natural language, providing specific advice such as, "The current earthquake is likely an aftershock and is expected to gradually subside. Please secure your furniture and prepare an evacuation bag."

[0979] 4. Individual support

[0980] The server obtains the user's location information (if the user has given permission), searches for information on the nearest evacuation shelter and evacuation routes, and creates route guidance using the map information API.

[0981] The terminal displays information to guide the user, such as "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[0982] 5. Providing mental health care

[0983] The generative AI also suggests mental care methods (such as deep breathing, relaxation, and talking to friends and family) to reduce anxiety and stress during disasters.

[0984] The server generates this mental care method as a text and sends it to the user's device, which displays, "We recommend taking a deep breath and talking to a family member or friend for reassurance."

[0985] Specific examples

[0986] For example, consider the case where a user inputs a query such as "I'm worried about how long this earthquake will last."

[0987] The server uses generative AI to analyze the inquiry and extract keywords such as "worry," "earthquake," and "continue."

[0988] The generative AI references similar past cases from a database and generates answers such as, "Current seismic activity generally lasts for several weeks to several months, but aftershocks tend to gradually decrease."

[0989] The server then adds more specific evacuation measures and mental care methods and sends them to the user's device.

[0990] The device will display a message to the user saying, "Please check to see if your furniture is safe from tipping over and have your evacuation bag ready to go. Please also take note of how to take deep breaths and relax."

[0991] In this way, the system effectively reduces users' anxiety and provides specific and useful information to support disaster response.

[0992] The processing flow will be explained below.

[0993] Step 1:

[0994] Users launch the Emacon app on their devices and enter their concerns and questions about the disaster into the chat window. For example, they might ask, "The earthquakes are continuing and I'm scared. What should I do?"

[0995] Step 2:

[0996] The terminal acquires the inquiry entered by the user and sends it as text data to the server, where the data is securely transmitted using the HTTPS protocol.

[0997] Step 3:

[0998] The server passes the received text data to a generative artificial intelligence (AI) and instructs it to analyze it. The generative AI uses natural language processing technology to tokenize the user's inquiry and extract key keywords (e.g., "earthquake," "anxiety," and "measures").

[0999] Step 4:

[1000] Based on the tokenized text, the generative AI identifies the cause of the user's anxiety, for example, recognizing that the anxiety is about seismic activity.

[1001] Step 5:

[1002] The server then accesses a database based on the extracted keywords to search for relevant solutions and information, such as data on past earthquake cases, evacuation plans, and emergency response measures.

[1003] Step 6:

[1004] Based on the search results, generative AI generates specific solutions for users in natural language, such as "The current earthquake is likely an aftershock and is expected to gradually subside. Please secure your furniture and prepare an evacuation bag."

[1005] Step 7:

[1006] The server searches for nearby evacuation shelters and appropriate evacuation routes by acquiring the user's location information (if the user has given permission). Here, it uses a map information API to generate the optimal route from the user's current location to the evacuation shelter.

[1007] Step 8:

[1008] The generative AI will suggest mental health care methods based on the inquiry, such as deep breathing, relaxation techniques, and communication with friends and family.

[1009] Step 9:

[1010] The server integrates and packages the generated solutions, evacuation route information, and mental health advice, and then transmits this information to the user's device.

[1011] Step 10:

[1012] The device then displays the received information to the user. For example, a chat window could show specific instructions such as "The nearest evacuation shelter is X Park. Would you like to check the route from your current location?", as well as mental health care methods.

[1013] This system allows users to quickly reduce their anxiety during a disaster and obtain appropriate guidelines for action.

[1014] Example 1

[1015] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1016] When a natural disaster occurs, it is extremely important to quickly alleviate the anxiety and fear felt by users and provide appropriate guidelines for action and mental care methods. However, conventional systems have difficulty in quickly and accurately responding to users' anxiety, which can prevent users from taking appropriate action and potentially lead to greater damage. The present invention aims to solve these problems by providing a system that encourages appropriate evacuation behavior while providing users with a sense of security.

[1017] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1018] In this invention, the server includes means for allowing a user to input an inquiry about anxiety during a disaster, means for analyzing the content of the inquiry using generative artificial intelligence, means for identifying the cause of the anxiety based on the analysis results, means for referencing a database and extracting related solutions, means for generating mental care methods and evacuation action plans, means for acquiring location information and searching for information on the nearest evacuation shelter and evacuation routes, and means for transmitting the generated information to the user's terminal. This makes it possible to quickly analyze the user's anxiety and provide specific and useful information.

[1019] "User" refers to an individual or group that uses the system.

[1020] "Disaster" refers to natural phenomena such as earthquakes, floods, and typhoons, as well as events that include the man-made damage that accompanies them.

[1021] "Anxiety" refers to a state of psychological tension and worry caused by a disaster.

[1022] An "inquiry" refers to a question or matter of consultation that a user inputs into the system.

[1023] "Generative AI" refers to an AI system that uses natural language processing technology to analyze input from users and generate appropriate answers and advice.

[1024] "Analysis" refers to the process of understanding the user's inquiry and extracting the important information and keywords contained therein.

[1025] "Cause" refers to the reasons and factors behind the user's anxiety.

[1026] A "database" refers to a system that systematically organizes and stores past data and information, making it possible to search and reference it.

[1027] "Solution proposal" refers to specific courses of action or advice proposed to resolve the user's concerns or problems.

[1028] "Mental care" refers to methods and techniques for reducing users' psychological anxiety and stress.

[1029] "Evacuation action plan" refers to specific guidance and instructions to support the user's safe evacuation actions in the event of a disaster.

[1030] "Location information" refers to data that indicates a user's current geographic location.

[1031] "Evacuation shelter information" refers to information about locations and facilities where users can evacuate in the event of a disaster.

[1032] "Evacuation route" refers to route information for a user to safely move from their current location to an evacuation shelter.

[1033] "Terminal" refers to the device (smartphone, tablet, PC, etc.) that a User uses to access the System and receive and send information.

[1034] This invention is a system for alleviating the anxiety felt by users during disasters and providing appropriate guidelines for action. This system includes a user terminal, a server, and generative artificial intelligence. The following is a detailed description of how this system is implemented.

[1035] The system is configured with smartphones, tablets, PCs, etc. as user devices, and the generative AI and database are placed on the server. The generative AI is an AI model that uses natural language processing technology and is implemented using Python and TensorFlow. The database uses a relational database such as MySQL.

[1036] The user launches the Emacon application on their device and inputs their concerns or questions into the chat window. For example, they can make a query such as, "The earthquakes are continuing and I'm scared. What should I do?" The device then sends this query as text data to the server.

[1037] The server receives this text data and passes it to a generative AI, which uses natural language processing to analyze the text data and identify the cause of the user's anxiety. This analysis process includes extracting keywords such as "earthquake," "anxiety," and "measures."

[1038] Based on the extracted keywords, the server accesses a database to search for relevant solutions. This includes, for example, specific information about earthquakes, past case studies, and best practices for evacuation behavior. Based on the search results, the generative AI generates appropriate solutions for the user. For example, it creates advice such as, "The current earthquake is likely an aftershock and is expected to gradually subside. Secure your furniture and prepare an evacuation bag."

[1039] Furthermore, the server obtains location information from the user's device and uses the Google Maps API to search for information on the nearest evacuation shelter and evacuation routes. For example, it generates information such as, "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[1040] The generative AI also suggests mental care methods, such as deep breathing, relaxation, or talking to friends or family. The server formats this information and sends it to the user's device, which then displays specific messages such as, "We recommend taking deep breaths and talking to family or friends to help you relax."

[1041] As a specific example, if a user inputs an inquiry such as "I'm worried about how long this earthquake will last," the following flow occurs.

[1042] The server uses generative AI to analyze the inquiry and extract keywords such as "worry," "earthquake," and "continue." The generative AI references a database of similar past cases and generates a response such as, "Current seismic activity generally continues for several weeks to several months, but aftershocks tend to gradually decrease." The server then adds specific evacuation measures (for example, "Please check to see if your furniture has been taken to prevent tipping, and have your evacuation bag ready to go") and mental health care methods ("Please also refer to methods for deep breathing and relaxation") and sends them to the user's device. This information is displayed on the device, providing the user with specific guidelines for action.

[1043] This system effectively reduces users' anxiety and supports disaster response by quickly providing specific and useful information.

[1044] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1045] Step 1:

[1046] Users launch the Emacon application on their smartphone or computer and enter their concerns or questions into the chat window. An example of input is a question like, "The earthquakes are continuing and I'm scared. What should I do?" This input is treated as text data, and the device sends this text data to the server.

[1047] Input: The text data that the user types into the chat window.

[1048] Output: Text data sent to the server

[1049] Specific operation:

[1050] The terminal receives user input

[1051] Convert text data to JSON format

[1052] sent to the server as an HTTP POST request

[1053] Step 2:

[1054] The server passes the received text data to a generative AI. The generative AI uses natural language processing technology to analyze the text data. During this analysis, keywords such as "earthquake," "anxiety," and "measures" are extracted. Preprocessing (tokenization, removal of stop words, etc.) is then performed to process the data.

[1055] Input: User's text data

[1056] Output: Extracted keywords

[1057] Specific operation:

[1058] The server passes the text data to the generative AI

[1059] Generative AI performs preprocessing

[1060] Extracting keywords using natural language processing models

[1061] Step 3:

[1062] Based on the extracted keywords, the server accesses a database to search for relevant solutions, specifically querying a MySQL database to retrieve information about earthquakes, past case studies, best practices for evacuation, and more.

[1063] Input: Extracted keywords

[1064] Output: Related solutions and information

[1065] Specific operation:

[1066] The server queries the database based on the keywords

[1067] Get the relevant information from the database

[1068] Formatting search results

[1069] Step 4:

[1070] Based on the search results, generative AI will generate appropriate solutions for users, such as advice like, "The current earthquake is likely an aftershock and is expected to gradually subside. Please secure your furniture and prepare an evacuation bag."

[1071] Input: Related solutions and information

[1072] Output: Specific solutions

[1073] Specific operation:

[1074] Generative AI receives search results

[1075] Generate solutions using natural language generation technology

[1076] Formatting the text data of the solution

[1077] Step 5:

[1078] The server obtains location information from the user's device and uses the Google Maps API to search for information about the nearest evacuation shelter and evacuation routes. For example, it generates information such as, "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[1079] Input: User's location

[1080] Output: Evacuation shelter information and evacuation routes

[1081] Specific operation:

[1082] The server obtains location information with the user's permission.

[1083] Send a request to the Google Maps API

[1084] Generate evacuation shelter information and route guidance

[1085] Step 6:

[1086] The generative AI suggests mental care methods, such as deep breathing, relaxation, or talking to friends or family. The server formats this information and sends it to the user's device.

[1087] Input: Mental care suggestions using generative AI

[1088] Output: Mental care information displayed on the user's device

[1089] Specific operation:

[1090] Generative AI generates mental care suggestions

[1091] Formatting suggestions (using natural language generation)

[1092] The server sends the formatted information to the terminal.

[1093] Step 7:

[1094] The device receives solutions, mental health care information, and evacuation shelter information from the server and displays specific messages to the user, such as "We recommend you take a deep breath and talk to family or friends to help you relax."

[1095] Input: Information sent from the server

[1096] Output: Information displayed on the user's terminal

[1097] Specific operation:

[1098] The device receives data from the server

[1099] Display your data in the right format

[1100] This allows users to quickly obtain specific and useful information, reducing anxiety and enabling them to take appropriate action.

[1101] (Application example 1)

[1102] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1103] In the event of a disaster, there is a need to quickly and accurately alleviate users' anxiety and provide specific guidelines for safe behavior. However, current systems often make it difficult for users to individually obtain appropriate information. Furthermore, they lack the ability to provide real-time advice, specific evacuation routes, and mental health support when a disaster occurs. The purpose of this invention is to solve these problems and enable users to act with peace of mind in the event of a disaster.

[1104] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1105] In this invention, the server includes means for a user to input an inquiry about anxiety in the event of a disaster, means for analyzing the content of the inquiry using generative artificial intelligence, means for identifying the cause of anxiety based on the analysis results, means for referencing a database and extracting related solutions, means for generating mental care methods and evacuation action plans, means for transmitting the generated information to the user's terminal, means for acquiring the user's location information, means for presenting evacuation shelter information and evacuation routes based on the approximate location, means for acquiring disaster information and immediately notifying the user and presenting emergency measures, and means for the AI ​​to generate appropriate advice in real time in response to the user's question, thereby enabling the user to take specific actions with peace of mind in the event of a disaster.

[1106] "User" refers to a person who accesses the system to receive information and support during a disaster.

[1107] "During a disaster" refers to the time when a natural or man-made disaster such as an earthquake, tsunami, or fire occurs.

[1108] "Inquiries about anxiety" refers to the act of users entering into the system in text format any anxieties or questions they may have in the event of a disaster.

[1109] "Generative AI" refers to an AI system that uses natural language processing technology to analyze user inquiries and generate appropriate solutions and advice.

[1110] "Analysis" refers to the process in which generative artificial intelligence analyzes the content of a user's inquiry and identifies the cause of the anxiety and appropriate countermeasures.

[1111] "Causes of anxiety" refers to the mental anxiety and fear that users feel during a disaster.

[1112] "Solutions" refer to specific measures and advice proposed by the generative artificial intelligence based on the causes of anxiety identified.

[1113] The "database" refers to a collection of information that includes information on various disasters, past case studies, and best practices for evacuation behavior.

[1114] "Mental care methods" refer to psychological support methods to reduce anxiety and stress during disasters.

[1115] "Evacuation action plan" refers to a specific action plan that a user should take in the event of a disaster.

[1116] "User's terminal" refers to the device (smartphone, tablet, PC, etc.) used by the user to access the system.

[1117] "Location information" refers to location data of the user's current location.

[1118] "Evacuation shelter information" refers to information about specific facilities and locations for evacuation in the event of a disaster.

[1119] "Evacuation route" refers to route information from the user's current location to the nearest evacuation shelter.

[1120] "Disaster information" refers to detailed information about disasters currently occurring.

[1121] "Notification" refers to messages that send disaster information or advice to the user's device.

[1122] "Emergency measures" refer to specific actions and preparations that should be taken immediately when a disaster occurs.

[1123] MODE FOR CARRYING OUT THE INVENTION

[1124] This invention is a system that provides appropriate guidelines for action and mental care methods to users who feel anxious during a disaster. The system mainly includes a user terminal, a server, and a generative artificial intelligence (AI).

[1125] User terminal

[1126] User terminals include a variety of devices, including smartphones, tablets, and PCs. Users use their terminals to launch the Emacon application and input their concerns and questions in the chat window. For example, a user might ask, "The earthquakes are continuing and I'm scared. What should I do?"

[1127] server

[1128] The server is the core of the system. It passes the received inquiry text data to the generative AI for analysis. Natural language processing technology is used for the analysis to extract specific keywords. For example, keywords such as "earthquake," "anxiety," and "measures" are extracted.

[1129] Generative artificial intelligence (AI)

[1130] The generative AI analyzes the user's inquiry to identify the cause of their anxiety, then consults a database of relevant solutions, such as information about earthquakes, past case studies, and best practices for evacuation.

[1131] Based on the extracted solutions, the generative AI generates appropriate solutions and mental care methods for the user in natural language. For example, it might provide specific advice such as, "The current earthquake is likely an aftershock and is expected to gradually subside. Please secure your furniture and prepare an evacuation bag."

[1132] Providing mental health care

[1133] The server generates mental care methods generated by generative AI as text and sends them to the user's device, such as "We recommend taking deep breaths and talking to family or friends to feel more at ease."

[1134] Use of location information

[1135] The user's device can obtain location information. The server uses this location information to search for information on the nearest evacuation shelter and evacuation routes. Route guidance is created using a map information API. The user is provided with information such as, "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[1136] Disaster Information and Emergency Notifications

[1137] The server acquires disaster information, immediately notifies users, and presents emergency measures. When a disaster occurs, generative AI generates advice in real time in response to user questions so that appropriate action can be taken quickly.

[1138] Specific examples

[1139] For example, consider the case where a user enters a query such as, "I'm worried about how long this earthquake will last." The server uses generative AI to analyze the query and extract keywords such as "worry," "earthquake," and "continue." The generative AI references past similar cases in a database and generates a response such as, "Current seismic activity generally lasts for several weeks to several months, but aftershocks tend to gradually decrease." It then adds specific evacuation measures and mental care methods and sends them to the user's device. The message displayed is, "Please check measures to prevent furniture from tipping over and have an evacuation bag ready to take immediately. Please also refer to techniques for deep breathing and relaxation."

[1140] Prompt Sentence Examples

[1141] What measures should be taken in the event of an earthquake?

[1142] Offer advice to concerned users.

[1143] For example, if the earthquake lasts for XX seconds, you should evacuate to a safe place for a while. Also, secure your furniture, prepare an evacuation bag, and check your evacuation route.

[1144] The above is a specific implementation of this system. It is designed to use various hardware and software (such as Nominatim and OpenAI APIs) to enable users to take action with confidence in the event of a disaster.

[1145] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1146] Step 1:

[1147] A user inputs an inquiry about anxiety during a disaster.

[1148] Specifically, the user launches the Emacon application installed on their smartphone or tablet and enters their concerns or questions into the chat window. For example, they might type, "The earthquakes are continuing and I'm scared. What should I do?"

[1149] Input: User query text

[1150] Output: Query text data

[1151] Step 2:

[1152] The terminal transmits the inquiry text data to the server.

[1153] Input: Inquiry text data

[1154] Output: Send data to the server

[1155] Step 3:

[1156] The text data received by the server is passed to the generative AI for analysis.

[1157] Specifically, the server analyzes the inquiry text data using natural language processing technology and extracts keywords, such as "earthquake," "anxiety," and "measures."

[1158] Input: Inquiry text data

[1159] Output: Extracted keywords

[1160] Step 4:

[1161] The server searches the database based on the keywords and extracts relevant solutions.

[1162] Specifically, the server searches a database for disaster information, past case studies, and best practices for evacuation procedures.

[1163] Input: Extracted keywords

[1164] Output: Related solutions

[1165] Step 5:

[1166] Based on relevant solutions, generative AI generates appropriate solutions and mental care methods for users.

[1167] As a specific action, it generates specific advice such as, "The current earthquake is likely to be an aftershock and is expected to gradually subside. Please secure furniture and prepare an evacuation bag."

[1168] Input: Related Solutions

[1169] Output: Generated solutions and mental health care methods

[1170] Step 6:

[1171] The server transmits the generated information to the user's terminal.

[1172] Specifically, the server sends the solutions and mental care methods generated by the generative AI to the user's device as text.

[1173] Input: Generated solutions and mental health care methods

[1174] Output: Data sent to the user terminal

[1175] Step 7:

[1176] The device acquires the user's location information.

[1177] Input: User location request

[1178] Output: Current location data

[1179] Step 8:

[1180] The server searches for information on the nearest evacuation shelter and evacuation routes based on location information.

[1181] Specifically, the server uses a map information API to create route guidance from the current location to the nearest evacuation shelter.

[1182] Input: Location data

[1183] Output: Evacuation shelter information and evacuation route guidance

[1184] Step 9:

[1185] The server obtains disaster information and immediately notifies users.

[1186] Specifically, when a disaster occurs, the server uses a dedicated API to obtain the latest disaster information and presents emergency measures to the user.

[1187] Input: Notification from disaster information API

[1188] Output: Urgent notification to the user

[1189] Step 10:

[1190] Generative AI generates advice in real time in response to user questions.

[1191] Specifically, the AI ​​generates an appropriate response based on the user's question and immediately sends it to the user's device.

[1192] Input: User question text

[1193] Output: Real-time consultation advice

[1194] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1195] This invention is a system for alleviating the anxiety felt by users during disasters and providing appropriate guidelines for action. This system includes a user terminal, a server, generative artificial intelligence, and an emotion engine. Below, we will explain how this system operates and how it provides specific advice and information to users.

[1196] System Overview

[1197] Main components

[1198] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[1199] 2. Server: The core of the system, it connects with the generative AI and database, and transmits information to user devices.

[1200] 3. Generative artificial intelligence (AI): Analyzes user inquiries and generates appropriate solutions, mental care methods, and evacuation instructions.

[1201] 4. Emotion engine: Recognizes emotions from the user's inquiry and generates appropriate responses based on those emotions.

[1202] DETAILED DESCRIPTION OF THE EMBODIMENTS

[1203] 1. Receiving inquiries from users

[1204] Users can launch the Emacon application on their own devices and input their concerns or questions in the chat window. For example, they might ask, "The earthquakes are continuing and I'm scared. What should I do?"

[1205] The terminal receives this inquiry and transmits it to the server as text data.

[1206] 2. Analysis of inquiry content

[1207] The server passes the received text data to an emotion engine to recognize the user's emotional state. The emotion engine uses natural language processing technology to extract emotions from the user's inquiry. For example, it can identify emotions such as anxiety or fear from the expression "scary."

[1208] The server then passes the recognized emotional state to a generative AI that analyzes the query. The generative AI then extracts key keywords from the tokenized text, such as "earthquake," "anxiety," and "measures."

[1209] 3. Proposing solutions and mental health care

[1210] Based on the extracted keywords and the recognized emotional state, the server accesses a database to search for relevant solutions and information, for example, data on past earthquake cases, evacuation plans, and emergency response measures.

[1211] Based on the search results, the generative AI generates specific solutions for the user in natural language. It reflects weighting based on the user's emotional state and adjusts the suggestions to convey a sense of kindness and security. For example, it creates advice such as, "The current earthquake is likely an aftershock and is expected to gradually subside. Don't be afraid, secure your furniture and prepare an evacuation bag."

[1212] 4. Individual support

[1213] The server searches for nearby evacuation shelters and appropriate evacuation routes by acquiring the user's location information (if the user has given permission), and generates the optimal route from the user's current location to the evacuation shelter using a map information API.

[1214] The terminal displays information to guide the user, such as "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[1215] 5. Providing mental health care

[1216] Generative AI also suggests mental care methods (deep breathing, relaxation techniques, communication with friends and family, etc.) to reduce anxiety and stress during disasters.

[1217] The server generates this mental care method as a text and sends it to the user's device, which displays, "We recommend taking a deep breath and talking to a family member or friend for reassurance."

[1218] Specific examples

[1219] For example, consider the case where a user inputs a query such as "I'm worried about how long this earthquake will last."

[1220] The server uses an emotion engine to analyze the query and extract keywords such as "worry," "earthquake," and "continue," as well as emotional states. The emotion engine determines that the user is feeling anxious based on the expression "worry."

[1221] The generative AI references similar past cases from a database and generates answers such as, "Current seismic activity generally lasts for several weeks to several months, but aftershocks tend to gradually decrease."

[1222] The server then adds more specific evacuation measures and mental care methods and sends them to the user's device.

[1223] The device will display a message to the user saying, "Please check to see if your furniture is safe from tipping over and have your evacuation bag ready to go. Please also take note of how to take deep breaths and relax."

[1224] In this way, the system effectively alleviates users' anxiety and provides specific and useful information for appropriate action. The combination of the emotion engine enables flexible responses according to the user's emotional state, realizing more personalized assistance.

[1225] The processing flow will be explained below.

[1226] Step 1:

[1227] Users launch the Emacon app on their devices and enter their concerns or questions in the chat window. For example, they can enter a question like, "The earthquakes are continuing and I'm scared. What should I do?"

[1228] Step 2:

[1229] The terminal receives the text data entered by the user and transmits it to the server using a communication protocol (e.g., HTTPS).

[1230] Step 3:

[1231] The server passes the received text data to the emotion engine, which uses natural language processing technology to extract emotions from the user's input. For example, it can identify that the user is feeling fearful based on the keyword "scary."

[1232] Step 4:

[1233] The server passes the emotional state extracted by the emotion engine to the generative AI, which then analyzes the user's inquiry. The generative AI tokenizes the input text and extracts key keywords (e.g., "earthquake," "anxiety," and "measures").

[1234] Step 5:

[1235] The server then queries the database based on the extracted keywords to retrieve relevant information, such as past earthquake cases, evacuation plans, and emergency response measures.

[1236] Step 6:

[1237] The generative AI generates specific solutions for users based on information obtained from the database. It adjusts the response depending on the emotional state identified by the emotion engine. For example, if a user is feeling fearful, it uses expressions that "provide a sense of security."

[1238] Step 7:

[1239] The server further customizes the solutions generated by the generative AI based on the user's location information, obtains the location information (if the user has permission), and uses a map information API to search for nearby evacuation shelters and evacuation routes.

[1240] Step 8:

[1241] The server integrates information on evacuation routes and shelters tailored to individual situations, as well as mental care methods, to create a final information package that includes specific guidelines for action and advice on mental care.

[1242] Step 9:

[1243] The server transmits the generated information package to the user's terminal.

[1244] Step 10:

[1245] The device then displays the received information package to the user. For example, it may provide specific instructions such as "The nearest evacuation shelter is X Park. Would you like to see the route from your current location?" or mental care advice such as "Take a deep breath and relax."

[1246] This process allows users to quickly and effectively reduce their anxiety during a disaster and provide specific guidelines for action. By combining this system with an emotion engine, the system provides flexible and personalized advice based on the user's emotional state.

[1247] Example 2

[1248] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1249] During disasters, users often feel anxious and scared, and it is necessary to quickly provide appropriate information and guidelines for action. However, conventional systems have difficulty responding flexibly to the user's emotional state, making it difficult to provide appropriate mental care or evacuation plans. They are also inadequate at suggesting individual responses or appropriate mental care methods based on the user's location information. Therefore, a system that can provide users with prompt and effective support is needed.

[1250] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1251] In this invention, the server includes means for a user to input an inquiry about anxiety during a disaster, means for analyzing the inquiry using generative artificial intelligence, means for identifying the cause of anxiety based on the analysis results, means for referencing a database and extracting related solutions, means for generating mental care methods and evacuation action plans, means for transmitting the generated information to the user's terminal, means for recognizing the user's emotional state, means for adjusting a response based on the emotional state, and means for providing specific guidelines for action to reduce anxiety during a disaster. This enables flexible responses and mental care to be provided according to the user's emotional state, thereby realizing anxiety reduction and the provision of appropriate guidelines for action during a disaster.

[1252] "User" refers to an individual who uses the system to input concerns or questions during a disaster.

[1253] "Terminals" refer to devices that users use to input their concerns and questions during a disaster and communicate with the system. Specifically, this includes smartphones, tablets, and PCs.

[1254] "Server" refers to the computer system that forms the core of the system, works in conjunction with generative artificial intelligence and databases, and transmits information to user terminals.

[1255] "Generative AI" refers to AI that analyzes user inquiries and generates appropriate solutions, mental care methods, and evacuation procedures.

[1256] An "emotion engine" refers to a system that recognizes emotions from the content of a user's inquiry and generates an appropriate response based on those emotions.

[1257] "Inquiry" refers to text data regarding concerns or questions that users input into the system.

[1258] "Analysis" refers to the process by which generative AI understands the content of a user's inquiry and extracts necessary keywords and emotional states.

[1259] "Causes of anxiety" refers to the specific reasons for the anxiety or fear that users feel during a disaster.

[1260] "Database" refers to an information system that stores information such as related solutions, mental care methods, and evacuation procedures.

[1261] "Solutions" refer to specific guidelines and measures to resolve users' concerns and questions.

[1262] "Mental care methods" refer to specific techniques for reducing anxiety and stress during a disaster, such as deep breathing, relaxation techniques, and communication suggestions.

[1263] "Evacuation action plan" refers to specific evacuation methods and guidelines for actions that users should take in the event of a disaster.

[1264] "Emotional state" refers to the specific emotion (e.g., anxiety, fear, worry) the user is feeling at the time of the inquiry.

[1265] "Response" refers to information such as solutions, mental care methods, and evacuation instructions that the system generates and provides to users.

[1266] "Location information" refers to the current geographic location obtained from the user's terminal.

[1267] "Evacuation shelter information" refers to information about locations and facilities where users can evacuate in the event of a disaster.

[1268] "Evacuation route" refers to route information for a user to travel safely from their current location to an evacuation shelter.

[1269] "Text generation technology" refers to the technology used by generative artificial intelligence to generate appropriate answers and advice in natural language.

[1270] A "prompt sentence" refers to an input sentence that causes a generative artificial intelligence to generate specific information or an answer.

[1271] This invention provides a system for alleviating anxiety felt by users during a disaster and providing appropriate guidelines for action. The system includes a user terminal, a server, a generative artificial intelligence (AI), and an emotion engine.

[1272] System Overview

[1273] Main components

[1274] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[1275] 2. Server: The core of the system, it connects with the generative AI and database, and transmits information to user devices.

[1276] 3. Generative artificial intelligence (AI): Analyzes user inquiries and generates appropriate solutions, mental care methods, and evacuation instructions.

[1277] 4. Emotion engine: Recognizes emotions from the user's inquiry and generates appropriate responses based on those emotions.

[1278] DETAILED DESCRIPTION OF THE EMBODIMENTS

[1279] 1. Receiving inquiries from users

[1280] Users can use their own devices to launch the Emacon application and input their concerns or questions into the chat window. For example, they might ask, "The earthquakes are continuing and I'm scared. What should I do?"

[1281] The terminal receives this inquiry and transmits it to the server as text data.

[1282] 2. Analysis of inquiry content

[1283] The server passes the received text data to the emotion engine, which recognizes the user's emotional state. The emotion engine uses natural language processing technology to extract emotions from the user's inquiry. For example, it can identify emotions such as anxiety or fear from the expression "scary."

[1284] The server then passes the recognized emotional state to a generative AI that analyzes the query. The generative AI then extracts key keywords from the tokenized text, such as "earthquake," "anxiety," and "measures."

[1285] 3. Proposing solutions and mental health care

[1286] Based on the extracted keywords and the recognized emotional state, the server accesses a database to search for relevant solutions and information, for example, data on past earthquake cases, evacuation plans, and emergency response measures.

[1287] Based on the search results, the generative AI generates specific solutions for the user in natural language. It reflects weighting based on the user's emotional state and adjusts the suggestions to convey a sense of kindness and security. For example, it creates advice such as, "The current earthquake is likely an aftershock and is expected to gradually subside. Don't be afraid, secure your furniture and prepare an evacuation bag."

[1288] 4. Individual support

[1289] The server provides a means to obtain the user's location information (if the user has given permission). Specifically, it obtains the current location using the device's location information API.

[1290] The server uses a map information API to search for and generate the optimal route from the user's current location to the nearest evacuation shelter. For example, it generates information such as "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[1291] The terminal displays the evacuation shelter information and route guidance sent from the server to the user.

[1292] 5. Providing mental health care

[1293] Generative AI will suggest mental care methods (deep breathing, relaxation techniques, communicating with friends and family, etc.) to reduce anxiety and stress during a disaster. For example, it will generate advice such as, "I recommend taking deep breaths and talking to family and friends."

[1294] The server sends this mental care method as a text to the user's device, which displays, "We recommend taking a deep breath and talking to family or friends to feel reassured."

[1295] Specific examples

[1296] For example, consider the case where a user inputs a query such as "I'm worried about how long this earthquake will last."

[1297] The server uses an emotion engine to analyze the query and extract keywords such as "worry," "earthquake," and "continue," as well as emotional states. The emotion engine determines that the user is feeling anxious based on the expression "worry."

[1298] The generative AI references similar past cases from a database and generates answers such as, "Current seismic activity generally lasts for several weeks to several months, but aftershocks tend to gradually decrease."

[1299] The server then adds more specific evacuation measures and mental care methods and sends them to the user's device.

[1300] The device will display a message to the user saying, "Please check measures to prevent furniture from tipping over and prepare an evacuation bag so that it can be taken out immediately. Please also refer to techniques for deep breathing and relaxation."

[1301] Examples of prompt statements

[1302] The prompt text is written as follows:

[1303] User question: "I'm worried about how long this earthquake will last."

[1304] Prompt to generative AI model: "The user is asking about the ongoing earthquake and their concerns. Please ease the user's concerns and provide appropriate courses of action. Include information based on past earthquakes and evacuation plans."

[1305] This allows the system to effectively alleviate the user's anxiety and provide appropriate guidelines for action.

[1306] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1307] Step 1:

[1308] The user launches the Emacon application on their device and enters their concerns or questions into the chat window. For example, they might type, "The earthquakes are continuing and I'm scared. What should I do?"

[1309] Input: Text data of user concerns and questions ("The earthquakes are continuing and I'm scared. What should I do?")

[1310] Output: Request to send text data from the terminal to the server

[1311] Specific operation: The device receives user input and sends text data to the server via the API.

[1312] Step 2:

[1313] The server passes the received text data to an emotion engine to recognize the user's emotional state.

[1314] Input: User's query text data sent from the terminal

[1315] Output: Text data sent to the emotion engine and the recognition result of emotional state data (e.g., "fear").

[1316] Specific operation: The server sends text data to the emotion engine API, and the emotion engine uses natural language processing technology to extract emotions from the text. For example, it identifies the emotion of "fear" from the expression "scary."

[1317] Step 3:

[1318] The server passes the recognized emotional state to a generative AI, which then analyzes the query.

[1319] Input: Emotional state data from the emotion engine (e.g., "fear") and user query text data

[1320] Output: Key keywords extracted by generative AI (e.g., "earthquake," "anxiety," "measures")

[1321] How it works: The server passes the query text and emotional state to the generative AI, which then extracts key keywords based on the tokenized text.

[1322] Step 4:

[1323] The server accesses a database to search for relevant solutions and information based on the extracted keywords and the recognized emotional state.

[1324] Input: Keywords from generative AI (e.g., "earthquake," "anxiety," "countermeasures") and emotional state data (e.g., "fear")

[1325] Output: Database search results (e.g., past earthquake cases, evacuation plans, emergency measures)

[1326] Specific operation: The server queries the database based on the extracted keywords and emotional state data to obtain relevant solutions and information.

[1327] Step 5:

[1328] Generative AI generates specific solutions for users in natural language based on search results.

[1329] Input: Search results from a database (e.g., past earthquake cases, evacuation plans, emergency measures) and emotional state data (e.g., "fear")

[1330] Output: Natural language suggestions to the user (e.g., "The current earthquake is likely an aftershock and is expected to subside gradually. Please secure furniture and prepare an evacuation bag.")

[1331] Specific operation: The generative AI generates answers in natural language based on information in the database, and reflects weighting in the response sentence according to the emotional state.

[1332] Step 6:

[1333] The server transmits the generated solutions and mental care methods to the user terminal.

[1334] Input: A solution in natural language from a generative AI

[1335] Output: Send the solution to the user's device

[1336] Specific operation: The server sends the solutions and mental care methods received from the generative AI to the user's device via the API.

[1337] Step 7:

[1338] The user's terminal displays the received information.

[1339] Input: Solutions and mental health care methods sent from the server

[1340] Output: Display to the user (e.g. "The current earthquake is likely an aftershock and is expected to gradually subside. Please secure furniture and prepare an evacuation bag.")

[1341] What it does: The device displays the received text in a chat window or notification for the user to view.

[1342] Through the above processing steps, the system can alleviate the user's anxiety in real time and provide appropriate guidelines for action.

[1343] (Application example 2)

[1344] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1345] Current disaster response systems lack the information needed to adequately alleviate users' psychological anxiety and encourage efficient and safe evacuation. Furthermore, real-time notifications and guidance on optimal evacuation routes can be delayed during emergencies, resulting in insufficient safety and psychological support for users. Given these circumstances, there is a need for systems that can alleviate users' anxiety while quickly and effectively supporting their actions.

[1346] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for a user to input an inquiry about anxiety in the event of a disaster, a means for analyzing the content of the inquiry using generative artificial intelligence, and a means for identifying the cause of the anxiety based on the analysis result. This makes it possible to quickly analyze the content of the user's inquiry and identify appropriate countermeasures.

[1347] Furthermore, the server includes a means for referencing the database and extracting relevant solutions, a means for generating mental care methods and evacuation action plans, a means for transmitting the generated information to the user's terminal, a means for transmitting emergency notifications in real time when a disaster occurs, and a means for generating and providing guidance on the optimal evacuation route based on location information, thereby making it possible to provide specific and useful information tailored to each individual user.

[1348] Furthermore, the server includes a means for acquiring location information of the user, a means for searching for and providing information on nearby evacuation shelters and evacuation routes based on the location information, and a means for analyzing the user's emotional state and suggesting appropriate mental care methods based on the analysis, thereby enabling effective evacuation support while reducing the user's psychological anxiety.

[1349] The server also includes a means for proposing an appropriate mental care method according to the content of the inquiry, a means for formatting the mental care method using text generation technology and providing it, and a means for generating a prompt sentence for the generative AI and creating a response based on the result. This makes it possible to provide flexible mental care according to the user's emotional state.

[1350] The "means for users to input inquiries about their concerns in the event of a disaster" is an interface that allows users to input their concerns and questions about the event of a disaster via a terminal.

[1351] "Means for analyzing the inquiry content using generative artificial intelligence" refers to a function that uses generative artificial intelligence to analyze the inquiry content entered by the user and understand its meaning and intent.

[1352] The "means for identifying the cause of anxiety based on the analysis results" refers to an algorithm or technology for identifying the cause of the user's anxiety from the analyzed content.

[1353] The "means for referencing a database and extracting relevant solutions" refers to a process of referencing information stored in a database and extracting appropriate solutions related to the user's concerns.

[1354] "Means for generating mental care methods and evacuation action proposals" refers to algorithms or systems for generating mental care methods and specific evacuation action proposals.

[1355] The "means for transmitting the generated information to the user's terminal" is a mechanism for transmitting the generated mental care suggestions and evacuation action plans to the user's terminal via a network.

[1356] "Means for sending emergency notifications in real time when a disaster occurs" refers to a system for immediately sending emergency notifications to users' terminals when a disaster occurs.

[1357] The "means for generating an optimal evacuation route based on location information and providing guidance thereto" is a technology that uses the user's current location information to calculate an optimal evacuation route and provides guidance thereto to the user.

[1358] "Means for obtaining user location information" refers to a function that obtains the user's current location using GPS or other location information services.

[1359] The "means for searching for and providing information on nearby evacuation shelters and evacuation routes based on the location information" is a system for searching for nearby evacuation shelters and safe evacuation routes from the user's current location and providing guidance thereto.

[1360] "Means for analyzing the user's emotional state and proposing appropriate mental care methods based on that" refers to technology that analyzes the user's input, identifies their emotional state, and proposes appropriate mental care methods.

[1361] The "means for proposing an appropriate mental care method in accordance with the content of the inquiry" is a system that proposes an appropriate mental care method for a user based on the content of the inquiry from the user.

[1362] The "means for providing the mental care method by formatting it using text generation technology" is a function for formatting the proposed mental care method into a natural text format using natural language processing technology and providing it to the user.

[1363] "Means for generating prompt sentences for generative AI and creating responses based on the results" refers to a technology that creates appropriate prompt sentences for generative AI and constructs responses to users based on the results of the generation.

[1364] Overall system configuration

[1365] The system of the present invention includes the following main components:

[1366] 1. User device: The device through which users input their concerns or questions. This includes smartphones, tablets, and computers.

[1367] 2. Server: The core of the system, containing the generative artificial intelligence, database, and emotion engine.

[1368] 3. Generative artificial intelligence (AI): Analyzes user inquiries and generates appropriate solutions, mental care methods, and evacuation instructions.

[1369] 4. Emotion engine: Analyzes the user's emotions and generates appropriate responses based on the analysis results.

[1370] 5. Database: Stores data on past disaster cases, evacuation route information, and mental care methods.

[1371] Program processing flow

[1372] 1. Receiving user inquiries

[1373] Users launch the application on their smartphone or tablet and input their concerns or questions in text. This input is sent from the device to the server. For example, a user might ask, "There have been a series of earthquakes and I'm scared. What should I do?"

[1374] 2. Analysis of inquiry content

[1375] The server uses an emotion engine to analyze the inquiry and determine the user's emotional state. The engine uses natural language processing technology to identify the emotion "fear" from the user's inquiry. Generative AI then tokenizes the text and extracts key keywords, such as "earthquake," "fear," and "measures."

[1376] 3. Proposing solutions and mental health care

[1377] The server references a database and searches for relevant solutions based on the extracted keywords. For example, it retrieves information about past earthquakes, evacuation plans, and emergency response measures. The generative AI uses this information to generate advice in natural language to ease the user's anxiety. For example, it could output something like, "The current earthquake is likely an aftershock and is expected to gradually subside. Don't be afraid, secure your furniture, and prepare an evacuation bag."

[1378] 4. Emergency notification and evacuation route provision

[1379] In the event of a disaster, the server will send emergency notifications to the user's device in real time. The notification will read, "An earthquake has just occurred. Please evacuate to a safe location." The server will then calculate the optimal evacuation route based on the user's location information and provide guidance. For example, the server will display a message saying, "The nearest evacuation shelter is XX Park. Please evacuate via this route."

[1380] 5. Providing mental health care

[1381] The emotion engine analyzes the user's emotional state, and the generative AI suggests appropriate mental care methods, such as "Take a deep breath and relax. If necessary, speak to a staff member."

[1382] Hardware and software used

[1383] User devices include iOS and Android smartphones and tablets. Cloud services such as Amazon Web Services (AWS) and Google Cloud Platform (GCP) can be used for servers. Generative AI models such as GPT-3, which have natural language processing technology, are used. The emotion engine uses emotion recognition APIs (e.g., Microsoft Azure's Text Analytics API) that provide emotion analysis technology.

[1384] Examples and prompts

[1385] For example, consider the case where a user inputs "I'm worried about how long this earthquake will last." The server uses an emotion engine to extract keywords such as "worry," "earthquake," and "continue," and identifies the emotional state as "anxiety." The generative AI then references similar past cases in a database,

[1386] The model generates an answer such as, "Current seismic activity generally lasts for several weeks to several months, but aftershocks tend to gradually decrease." Examples of prompts for the model include:

[1387] "Users are worried about how long this earthquake will last. Please suggest appropriate mental care methods and guidelines for action."

[1388] Examples include:

[1389] This effectively reduces the user's anxiety and allows them to take necessary action quickly.

[1390] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1391] Step 1:

[1392] The user launches the application on their smartphone or tablet and inputs their concerns or questions in text. The input is sent from the device to the server. For example, the input data could be "There have been a series of earthquakes and I'm scared. What should I do?"

[1393] Step 2:

[1394] The server sends the text data sent by the user to the emotion engine. The emotion engine uses natural language processing technology to analyze the text and identify emotional states such as anxiety, fear, and worry. For example, the emotion of fear is identified from the expression "scared." The output data is emotional information (e.g., "fear").

[1395] Step 3:

[1396] The server provides the output (emotional information) from the emotion engine to a generative artificial intelligence (AI). The generative AI performs tokenization based on the inquiry content and the identified emotional information, and extracts key keywords (e.g., "earthquake," "fear," and "measures"). The generative AI then references a database to search for relevant solutions (e.g., "The earthquake is an aftershock and is expected to gradually subside"). The output data is the generated solution.

[1397] Step 4:

[1398] The server generates mental care methods and evacuation action suggestions based on the solutions provided by the generative AI. The generated solutions are written in natural language and are adjusted to take into account the user's emotional state. For example, advice such as "Don't be afraid, secure your furniture and prepare an evacuation bag" is generated. The output is a specific solution for the user.

[1399] Step 5:

[1400] If the user's location information is required, the server obtains it from the user's device. Based on the location information, the server uses a map information API to search for nearby evacuation shelters and evacuation routes. For example, it generates guidance such as, "The nearest evacuation shelter is XX Park, and this is the best route from your current location." The output is evacuation route information.

[1401] Step 6:

[1402] The server sends solutions and evacuation route information to the user's device. The device displays the received information to the user. For example, a message such as "The nearest evacuation shelter is XX Park. Please evacuate via this route" is displayed. The output is the displayed message.

[1403] Step 7:

[1404] When a disaster occurs, the server sends an emergency notification to the user's device in real time. The notification includes the message "An earthquake has occurred. Please evacuate to a safe place." The output is the emergency notification message.

[1405] Step 8:

[1406] The server constantly monitors the user's emotional state and suggests additional mental care methods as needed. For example, it provides messages such as, "Take a deep breath and relax. If necessary, please speak to a staff member." The output is mental care advice.

[1407] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1408] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1409] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1410] [Fourth embodiment]

[1411] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1412] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1413] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1414] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1415] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1416] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1417] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1418] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1419] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1420] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1421] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1422] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1423] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1424] This invention is a system for alleviating the anxiety felt by users during disasters and providing appropriate guidelines for action. This system includes a user terminal, a server, and generative artificial intelligence. Below, we will explain how this system operates and how it provides specific advice and information to users.

[1425] System Overview

[1426] Main components

[1427] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[1428] 2. Server: The core of the system, it connects with the generative AI and database, and transmits information to user devices.

[1429] 3. Generative artificial intelligence (AI): Analyzes user inquiries and generates appropriate solutions, mental care methods, and evacuation instructions.

[1430] DETAILED DESCRIPTION OF THE EMBODIMENTS

[1431] 1. Receiving inquiries from users

[1432] Users can launch the Emacon application on their own devices and input their concerns and questions in the chat window. For example, they might ask, "The earthquakes are continuing and I'm scared. What should I do?"

[1433] The terminal receives this inquiry and transmits it to the server as text data.

[1434] 2. Analysis of inquiry content

[1435] The server passes the received text data to a generative AI, which uses natural language processing technology to analyze the inquiry and identify the cause of the user's anxiety.

[1436] The server extracts keywords such as "earthquake," "anxiety," and "measures," and performs further analysis based on these.

[1437] 3. Proposing solutions and mental health care

[1438] The server accesses the database and searches for relevant solutions (e.g., information about earthquakes, past case studies, best practices for evacuation behavior, etc.) based on the extracted keywords.

[1439] Based on the search results, the generative AI generates appropriate solutions for the user in natural language, providing specific advice such as, "The current earthquake is likely an aftershock and is expected to gradually subside. Please secure your furniture and prepare an evacuation bag."

[1440] 4. Individual support

[1441] The server obtains the user's location information (if the user has given permission), searches for information on the nearest evacuation shelter and evacuation routes, and creates route guidance using the map information API.

[1442] The terminal displays information to guide the user, such as "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[1443] 5. Providing mental health care

[1444] The generative AI also suggests mental care methods (such as deep breathing, relaxation, and talking to friends and family) to reduce anxiety and stress during disasters.

[1445] The server generates this mental care method as a text and sends it to the user's device, which displays, "We recommend taking a deep breath and talking to a family member or friend for reassurance."

[1446] Specific examples

[1447] For example, consider the case where a user inputs a query such as "I'm worried about how long this earthquake will last."

[1448] The server uses generative AI to analyze the inquiry and extract keywords such as "worry," "earthquake," and "continue."

[1449] The generative AI references similar past cases from a database and generates answers such as, "Current seismic activity generally lasts for several weeks to several months, but aftershocks tend to gradually decrease."

[1450] The server then adds more specific evacuation measures and mental care methods and sends them to the user's device.

[1451] The device will display a message to the user saying, "Please check to see if your furniture is safe from tipping over and have your evacuation bag ready to go. Please also take note of how to take deep breaths and relax."

[1452] In this way, the system effectively reduces users' anxiety and provides specific and useful information to support disaster response.

[1453] The processing flow will be explained below.

[1454] Step 1:

[1455] Users launch the Emacon app on their devices and enter their concerns and questions about the disaster into the chat window. For example, they might ask, "The earthquakes are continuing and I'm scared. What should I do?"

[1456] Step 2:

[1457] The terminal acquires the inquiry entered by the user and sends it as text data to the server, where the data is securely transmitted using the HTTPS protocol.

[1458] Step 3:

[1459] The server passes the received text data to a generative artificial intelligence (AI) and instructs it to analyze it. The generative AI uses natural language processing technology to tokenize the user's inquiry and extract key keywords (e.g., "earthquake," "anxiety," and "measures").

[1460] Step 4:

[1461] Based on the tokenized text, the generative AI identifies the cause of the user's anxiety, for example, recognizing that the anxiety is about seismic activity.

[1462] Step 5:

[1463] The server then accesses a database based on the extracted keywords to search for relevant solutions and information, such as data on past earthquake cases, evacuation plans, and emergency response measures.

[1464] Step 6:

[1465] Based on the search results, generative AI generates specific solutions for users in natural language, such as "The current earthquake is likely an aftershock and is expected to gradually subside. Please secure your furniture and prepare an evacuation bag."

[1466] Step 7:

[1467] The server searches for nearby evacuation shelters and appropriate evacuation routes by acquiring the user's location information (if the user has given permission). Here, it uses a map information API to generate the optimal route from the user's current location to the evacuation shelter.

[1468] Step 8:

[1469] The generative AI will suggest mental health care methods based on the inquiry, such as deep breathing, relaxation techniques, and communication with friends and family.

[1470] Step 9:

[1471] The server integrates and packages the generated solutions, evacuation route information, and mental health advice, and then transmits this information to the user's device.

[1472] Step 10:

[1473] The device then displays the received information to the user. For example, a chat window could show specific instructions such as "The nearest evacuation shelter is X Park. Would you like to check the route from your current location?", as well as mental health care methods.

[1474] This system allows users to quickly reduce their anxiety during a disaster and obtain appropriate guidelines for action.

[1475] Example 1

[1476] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1477] When a natural disaster occurs, it is extremely important to quickly alleviate the anxiety and fear felt by users and provide appropriate guidelines for action and mental care methods. However, conventional systems have difficulty in quickly and accurately responding to users' anxiety, which can prevent users from taking appropriate action and potentially lead to greater damage. The present invention aims to solve these problems by providing a system that encourages appropriate evacuation behavior while providing users with a sense of security.

[1478] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1479] In this invention, the server includes means for allowing a user to input an inquiry about anxiety during a disaster, means for analyzing the content of the inquiry using generative artificial intelligence, means for identifying the cause of the anxiety based on the analysis results, means for referencing a database and extracting related solutions, means for generating mental care methods and evacuation action plans, means for acquiring location information and searching for information on the nearest evacuation shelter and evacuation routes, and means for transmitting the generated information to the user's terminal. This makes it possible to quickly analyze the user's anxiety and provide specific and useful information.

[1480] "User" refers to an individual or group that uses the system.

[1481] "Disaster" refers to natural phenomena such as earthquakes, floods, and typhoons, as well as events that include the man-made damage that accompanies them.

[1482] "Anxiety" refers to a state of psychological tension and worry caused by a disaster.

[1483] An "inquiry" refers to a question or matter of consultation that a user inputs into the system.

[1484] "Generative AI" refers to an AI system that uses natural language processing technology to analyze input from users and generate appropriate answers and advice.

[1485] "Analysis" refers to the process of understanding the user's inquiry and extracting the important information and keywords contained therein.

[1486] "Cause" refers to the reasons and factors behind the user's anxiety.

[1487] A "database" refers to a system that systematically organizes and stores past data and information, making it possible to search and reference it.

[1488] "Solution proposal" refers to specific courses of action or advice proposed to resolve the user's concerns or problems.

[1489] "Mental care" refers to methods and techniques for reducing users' psychological anxiety and stress.

[1490] "Evacuation action plan" refers to specific guidance and instructions to support the user's safe evacuation actions in the event of a disaster.

[1491] "Location information" refers to data that indicates a user's current geographic location.

[1492] "Evacuation shelter information" refers to information about locations and facilities where users can evacuate in the event of a disaster.

[1493] "Evacuation route" refers to route information for a user to safely move from their current location to an evacuation shelter.

[1494] "Terminal" refers to the device (smartphone, tablet, PC, etc.) that a User uses to access the System and receive and send information.

[1495] This invention is a system for alleviating the anxiety felt by users during disasters and providing appropriate guidelines for action. This system includes a user terminal, a server, and generative artificial intelligence. The following is a detailed description of how this system is implemented.

[1496] The system is configured with smartphones, tablets, PCs, etc. as user devices, and the generative AI and database are placed on the server. The generative AI is an AI model that uses natural language processing technology and is implemented using Python and TensorFlow. The database uses a relational database such as MySQL.

[1497] The user launches the Emacon application on their device and inputs their concerns or questions into the chat window. For example, they can make a query such as, "The earthquakes are continuing and I'm scared. What should I do?" The device then sends this query as text data to the server.

[1498] The server receives this text data and passes it to a generative AI, which uses natural language processing to analyze the text data and identify the cause of the user's anxiety. This analysis process includes extracting keywords such as "earthquake," "anxiety," and "measures."

[1499] Based on the extracted keywords, the server accesses a database to search for relevant solutions. This includes, for example, specific information about earthquakes, past case studies, and best practices for evacuation behavior. Based on the search results, the generative AI generates appropriate solutions for the user. For example, it creates advice such as, "The current earthquake is likely an aftershock and is expected to gradually subside. Secure your furniture and prepare an evacuation bag."

[1500] Furthermore, the server obtains location information from the user's device and uses the Google Maps API to search for information on the nearest evacuation shelter and evacuation routes. For example, it generates information such as, "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[1501] The generative AI also suggests mental care methods, such as deep breathing, relaxation, or talking to friends or family. The server formats this information and sends it to the user's device, which then displays specific messages such as, "We recommend taking deep breaths and talking to family or friends to help you relax."

[1502] As a specific example, if a user inputs an inquiry such as "I'm worried about how long this earthquake will last," the following flow occurs.

[1503] The server uses generative AI to analyze the inquiry and extract keywords such as "worry," "earthquake," and "continue." The generative AI references a database of similar past cases and generates a response such as, "Current seismic activity generally continues for several weeks to several months, but aftershocks tend to gradually decrease." The server then adds specific evacuation measures (for example, "Please check to see if your furniture has been taken to prevent tipping, and have your evacuation bag ready to go") and mental health care methods ("Please also refer to methods for deep breathing and relaxation") and sends them to the user's device. This information is displayed on the device, providing the user with specific guidelines for action.

[1504] This system effectively reduces users' anxiety and supports disaster response by quickly providing specific and useful information.

[1505] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1506] Step 1:

[1507] Users launch the Emacon application on their smartphone or computer and enter their concerns or questions into the chat window. An example of input is a question like, "The earthquakes are continuing and I'm scared. What should I do?" This input is treated as text data, and the device sends this text data to the server.

[1508] Input: The text data that the user types into the chat window.

[1509] Output: Text data sent to the server

[1510] Specific operation:

[1511] The terminal receives user input

[1512] Convert text data to JSON format

[1513] sent to the server as an HTTP POST request

[1514] Step 2:

[1515] The server passes the received text data to a generative AI. The generative AI uses natural language processing technology to analyze the text data. During this analysis, keywords such as "earthquake," "anxiety," and "measures" are extracted. Preprocessing (tokenization, removal of stop words, etc.) is then performed to process the data.

[1516] Input: User's text data

[1517] Output: Extracted keywords

[1518] Specific operation:

[1519] The server passes the text data to the generative AI

[1520] Generative AI performs preprocessing

[1521] Extracting keywords using natural language processing models

[1522] Step 3:

[1523] Based on the extracted keywords, the server accesses a database to search for relevant solutions, specifically querying a MySQL database to retrieve information about earthquakes, past case studies, best practices for evacuation, and more.

[1524] Input: Extracted keywords

[1525] Output: Related solutions and information

[1526] Specific operation:

[1527] The server queries the database based on the keywords

[1528] Get the relevant information from the database

[1529] Formatting search results

[1530] Step 4:

[1531] Based on the search results, generative AI will generate appropriate solutions for users, such as advice like, "The current earthquake is likely an aftershock and is expected to gradually subside. Please secure your furniture and prepare an evacuation bag."

[1532] Input: Related solutions and information

[1533] Output: Specific solutions

[1534] Specific operation:

[1535] Generative AI receives search results

[1536] Generate solutions using natural language generation technology

[1537] Formatting the text data of the solution

[1538] Step 5:

[1539] The server obtains location information from the user's device and uses the Google Maps API to search for information about the nearest evacuation shelter and evacuation routes. For example, it generates information such as, "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[1540] Input: User's location

[1541] Output: Evacuation shelter information and evacuation routes

[1542] Specific operation:

[1543] The server obtains location information with the user's permission.

[1544] Send a request to the Google Maps API

[1545] Generate evacuation shelter information and route guidance

[1546] Step 6:

[1547] The generative AI suggests mental care methods, such as deep breathing, relaxation, or talking to friends or family. The server formats this information and sends it to the user's device.

[1548] Input: Mental care suggestions using generative AI

[1549] Output: Mental care information displayed on the user's device

[1550] Specific operation:

[1551] Generative AI generates mental care suggestions

[1552] Formatting suggestions (using natural language generation)

[1553] The server sends the formatted information to the terminal.

[1554] Step 7:

[1555] The device receives solutions, mental health care information, and evacuation shelter information from the server and displays specific messages to the user, such as "We recommend you take a deep breath and talk to family or friends to help you relax."

[1556] Input: Information sent from the server

[1557] Output: Information displayed on the user's terminal

[1558] Specific operation:

[1559] The device receives data from the server

[1560] Display your data in the right format

[1561] This allows users to quickly obtain specific and useful information, reducing anxiety and enabling them to take appropriate action.

[1562] (Application example 1)

[1563] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1564] In the event of a disaster, there is a need to quickly and accurately alleviate users' anxiety and provide specific guidelines for safe behavior. However, current systems often make it difficult for users to individually obtain appropriate information. Furthermore, they lack the ability to provide real-time advice, specific evacuation routes, and mental health support when a disaster occurs. The purpose of this invention is to solve these problems and enable users to act with peace of mind in the event of a disaster.

[1565] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1566] In this invention, the server includes means for a user to input an inquiry about anxiety in the event of a disaster, means for analyzing the content of the inquiry using generative artificial intelligence, means for identifying the cause of anxiety based on the analysis results, means for referencing a database and extracting related solutions, means for generating mental care methods and evacuation action plans, means for transmitting the generated information to the user's terminal, means for acquiring the user's location information, means for presenting evacuation shelter information and evacuation routes based on the approximate location, means for acquiring disaster information and immediately notifying the user and presenting emergency measures, and means for the AI ​​to generate appropriate advice in real time in response to the user's question, thereby enabling the user to take specific actions with peace of mind in the event of a disaster.

[1567] "User" refers to a person who accesses the system to receive information and support during a disaster.

[1568] "During a disaster" refers to the time when a natural or man-made disaster such as an earthquake, tsunami, or fire occurs.

[1569] "Inquiries about anxiety" refers to the act of users entering into the system in text format any anxieties or questions they may have in the event of a disaster.

[1570] "Generative AI" refers to an AI system that uses natural language processing technology to analyze user inquiries and generate appropriate solutions and advice.

[1571] "Analysis" refers to the process in which generative artificial intelligence analyzes the content of a user's inquiry and identifies the cause of the anxiety and appropriate countermeasures.

[1572] "Causes of anxiety" refers to the mental anxiety and fear that users feel during a disaster.

[1573] "Solutions" refer to specific measures and advice proposed by the generative artificial intelligence based on the causes of anxiety identified.

[1574] The "database" refers to a collection of information that includes information on various disasters, past case studies, and best practices for evacuation behavior.

[1575] "Mental care methods" refer to psychological support methods to reduce anxiety and stress during disasters.

[1576] "Evacuation action plan" refers to a specific action plan that a user should take in the event of a disaster.

[1577] "User's terminal" refers to the device (smartphone, tablet, PC, etc.) used by the user to access the system.

[1578] "Location information" refers to location data of the user's current location.

[1579] "Evacuation shelter information" refers to information about specific facilities and locations for evacuation in the event of a disaster.

[1580] "Evacuation route" refers to route information from the user's current location to the nearest evacuation shelter.

[1581] "Disaster information" refers to detailed information about disasters currently occurring.

[1582] "Notification" refers to messages that send disaster information or advice to the user's device.

[1583] "Emergency measures" refer to specific actions and preparations that should be taken immediately when a disaster occurs.

[1584] MODE FOR CARRYING OUT THE INVENTION

[1585] This invention is a system that provides appropriate guidelines for action and mental care methods to users who feel anxious during a disaster. The system mainly includes a user terminal, a server, and a generative artificial intelligence (AI).

[1586] User terminal

[1587] User terminals include a variety of devices, including smartphones, tablets, and PCs. Users use their terminals to launch the Emacon application and input their concerns and questions in the chat window. For example, a user might ask, "The earthquakes are continuing and I'm scared. What should I do?"

[1588] server

[1589] The server is the core of the system. It passes the received inquiry text data to the generative AI for analysis. Natural language processing technology is used for the analysis to extract specific keywords. For example, keywords such as "earthquake," "anxiety," and "measures" are extracted.

[1590] Generative artificial intelligence (AI)

[1591] The generative AI analyzes the user's inquiry to identify the cause of their anxiety, then consults a database of relevant solutions, such as information about earthquakes, past case studies, and best practices for evacuation.

[1592] Based on the extracted solutions, the generative AI generates appropriate solutions and mental care methods for the user in natural language. For example, it might provide specific advice such as, "The current earthquake is likely an aftershock and is expected to gradually subside. Please secure your furniture and prepare an evacuation bag."

[1593] Providing mental health care

[1594] The server generates mental care methods generated by generative AI as text and sends them to the user's device, such as "We recommend taking deep breaths and talking to family or friends to feel more at ease."

[1595] Use of location information

[1596] The user's device can obtain location information. The server uses this location information to search for information on the nearest evacuation shelter and evacuation routes. Route guidance is created using a map information API. The user is provided with information such as, "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[1597] Disaster Information and Emergency Notifications

[1598] The server acquires disaster information, immediately notifies users, and presents emergency measures. When a disaster occurs, generative AI generates advice in real time in response to user questions so that appropriate action can be taken quickly.

[1599] Specific examples

[1600] For example, consider the case where a user enters a query such as, "I'm worried about how long this earthquake will last." The server uses generative AI to analyze the query and extract keywords such as "worry," "earthquake," and "continue." The generative AI references past similar cases in a database and generates a response such as, "Current seismic activity generally lasts for several weeks to several months, but aftershocks tend to gradually decrease." It then adds specific evacuation measures and mental care methods and sends them to the user's device. The message displayed is, "Please check measures to prevent furniture from tipping over and have an evacuation bag ready to take immediately. Please also refer to techniques for deep breathing and relaxation."

[1601] Prompt Sentence Examples

[1602] What measures should be taken in the event of an earthquake?

[1603] Offer advice to concerned users.

[1604] For example, if the earthquake lasts for XX seconds, you should evacuate to a safe place for a while. Also, secure your furniture, prepare an evacuation bag, and check your evacuation route.

[1605] The above is a specific implementation of this system. It is designed to use various hardware and software (such as Nominatim and OpenAI APIs) to enable users to take action with confidence in the event of a disaster.

[1606] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1607] Step 1:

[1608] A user inputs an inquiry about anxiety during a disaster.

[1609] Specifically, the user launches the Emacon application installed on their smartphone or tablet and enters their concerns or questions into the chat window. For example, they might type, "The earthquakes are continuing and I'm scared. What should I do?"

[1610] Input: User query text

[1611] Output: Query text data

[1612] Step 2:

[1613] The terminal transmits the inquiry text data to the server.

[1614] Input: Inquiry text data

[1615] Output: Send data to the server

[1616] Step 3:

[1617] The text data received by the server is passed to the generative AI for analysis.

[1618] Specifically, the server analyzes the inquiry text data using natural language processing technology and extracts keywords, such as "earthquake," "anxiety," and "measures."

[1619] Input: Inquiry text data

[1620] Output: Extracted keywords

[1621] Step 4:

[1622] The server searches the database based on the keywords and extracts relevant solutions.

[1623] Specifically, the server searches a database for disaster information, past case studies, and best practices for evacuation procedures.

[1624] Input: Extracted keywords

[1625] Output: Related solutions

[1626] Step 5:

[1627] Based on relevant solutions, generative AI generates appropriate solutions and mental care methods for users.

[1628] As a specific action, it generates specific advice such as, "The current earthquake is likely to be an aftershock and is expected to gradually subside. Please secure furniture and prepare an evacuation bag."

[1629] Input: Related Solutions

[1630] Output: Generated solutions and mental health care methods

[1631] Step 6:

[1632] The server transmits the generated information to the user's terminal.

[1633] Specifically, the server sends the solutions and mental care methods generated by the generative AI to the user's device as text.

[1634] Input: Generated solutions and mental health care methods

[1635] Output: Data sent to the user terminal

[1636] Step 7:

[1637] The device acquires the user's location information.

[1638] Input: User location request

[1639] Output: Current location data

[1640] Step 8:

[1641] The server searches for information on the nearest evacuation shelter and evacuation routes based on location information.

[1642] Specifically, the server uses a map information API to create route guidance from the current location to the nearest evacuation shelter.

[1643] Input: Location data

[1644] Output: Evacuation shelter information and evacuation route guidance

[1645] Step 9:

[1646] The server obtains disaster information and immediately notifies users.

[1647] Specifically, when a disaster occurs, the server uses a dedicated API to obtain the latest disaster information and presents emergency measures to the user.

[1648] Input: Notification from disaster information API

[1649] Output: Urgent notification to the user

[1650] Step 10:

[1651] Generative AI generates advice in real time in response to user questions.

[1652] Specifically, the AI ​​generates an appropriate response based on the user's question and immediately sends it to the user's device.

[1653] Input: User question text

[1654] Output: Real-time consultation advice

[1655] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1656] This invention is a system for alleviating the anxiety felt by users during disasters and providing appropriate guidelines for action. This system includes a user terminal, a server, generative artificial intelligence, and an emotion engine. Below, we will explain how this system operates and how it provides specific advice and information to users.

[1657] System Overview

[1658] Main components

[1659] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[1660] 2. Server: The core of the system, it connects with the generative AI and database, and transmits information to user devices.

[1661] 3. Generative artificial intelligence (AI): Analyzes user inquiries and generates appropriate solutions, mental care methods, and evacuation instructions.

[1662] 4. Emotion engine: Recognizes emotions from the user's inquiry and generates appropriate responses based on those emotions.

[1663] DETAILED DESCRIPTION OF THE EMBODIMENTS

[1664] 1. Receiving inquiries from users

[1665] Users can launch the Emacon application on their own devices and input their concerns or questions in the chat window. For example, they might ask, "The earthquakes are continuing and I'm scared. What should I do?"

[1666] The terminal receives this inquiry and transmits it to the server as text data.

[1667] 2. Analysis of inquiry content

[1668] The server passes the received text data to an emotion engine to recognize the user's emotional state. The emotion engine uses natural language processing technology to extract emotions from the user's inquiry. For example, it can identify emotions such as anxiety or fear from the expression "scary."

[1669] The server then passes the recognized emotional state to a generative AI that analyzes the query. The generative AI then extracts key keywords from the tokenized text, such as "earthquake," "anxiety," and "measures."

[1670] 3. Proposing solutions and mental health care

[1671] Based on the extracted keywords and the recognized emotional state, the server accesses a database to search for relevant solutions and information, for example, data on past earthquake cases, evacuation plans, and emergency response measures.

[1672] Based on the search results, the generative AI generates specific solutions for the user in natural language. It reflects weighting based on the user's emotional state and adjusts the suggestions to convey a sense of kindness and security. For example, it creates advice such as, "The current earthquake is likely an aftershock and is expected to gradually subside. Don't be afraid, secure your furniture and prepare an evacuation bag."

[1673] 4. Individual support

[1674] The server searches for nearby evacuation shelters and appropriate evacuation routes by acquiring the user's location information (if the user has given permission), and generates the optimal route from the user's current location to the evacuation shelter using a map information API.

[1675] The terminal displays information to guide the user, such as "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[1676] 5. Providing mental health care

[1677] Generative AI also suggests mental care methods (deep breathing, relaxation techniques, communication with friends and family, etc.) to reduce anxiety and stress during disasters.

[1678] The server generates this mental care method as a text and sends it to the user's device, which displays, "We recommend taking a deep breath and talking to a family member or friend for reassurance."

[1679] Specific examples

[1680] For example, consider the case where a user inputs a query such as "I'm worried about how long this earthquake will last."

[1681] The server uses an emotion engine to analyze the query and extract keywords such as "worry," "earthquake," and "continue," as well as emotional states. The emotion engine determines that the user is feeling anxious based on the expression "worry."

[1682] The generative AI references similar past cases from a database and generates answers such as, "Current seismic activity generally lasts for several weeks to several months, but aftershocks tend to gradually decrease."

[1683] The server then adds more specific evacuation measures and mental care methods and sends them to the user's device.

[1684] The device will display a message to the user saying, "Please check to see if your furniture is safe from tipping over and have your evacuation bag ready to go. Please also take note of how to take deep breaths and relax."

[1685] In this way, the system effectively alleviates users' anxiety and provides specific and useful information for appropriate action. The combination of the emotion engine enables flexible responses according to the user's emotional state, realizing more personalized assistance.

[1686] The processing flow will be explained below.

[1687] Step 1:

[1688] Users launch the Emacon app on their devices and enter their concerns or questions in the chat window. For example, they can enter a question like, "The earthquakes are continuing and I'm scared. What should I do?"

[1689] Step 2:

[1690] The terminal receives the text data entered by the user and transmits it to the server using a communication protocol (e.g., HTTPS).

[1691] Step 3:

[1692] The server passes the received text data to the emotion engine, which uses natural language processing technology to extract emotions from the user's input. For example, it can identify that the user is feeling fearful based on the keyword "scary."

[1693] Step 4:

[1694] The server passes the emotional state extracted by the emotion engine to the generative AI, which then analyzes the user's inquiry. The generative AI tokenizes the input text and extracts key keywords (e.g., "earthquake," "anxiety," and "measures").

[1695] Step 5:

[1696] The server then queries the database based on the extracted keywords to retrieve relevant information, such as past earthquake cases, evacuation plans, and emergency response measures.

[1697] Step 6:

[1698] The generative AI generates specific solutions for users based on information obtained from the database. It adjusts the response depending on the emotional state identified by the emotion engine. For example, if a user is feeling fearful, it uses expressions that "provide a sense of security."

[1699] Step 7:

[1700] The server further customizes the solutions generated by the generative AI based on the user's location information, obtains the location information (if the user has permission), and uses a map information API to search for nearby evacuation shelters and evacuation routes.

[1701] Step 8:

[1702] The server integrates information on evacuation routes and shelters tailored to individual situations, as well as mental care methods, to create a final information package that includes specific guidelines for action and advice on mental care.

[1703] Step 9:

[1704] The server transmits the generated information package to the user's terminal.

[1705] Step 10:

[1706] The device then displays the received information package to the user. For example, it may provide specific instructions such as "The nearest evacuation shelter is X Park. Would you like to see the route from your current location?" or mental care advice such as "Take a deep breath and relax."

[1707] This process allows users to quickly and effectively reduce their anxiety during a disaster and provide specific guidelines for action. By combining this system with an emotion engine, the system provides flexible and personalized advice based on the user's emotional state.

[1708] Example 2

[1709] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1710] During disasters, users often feel anxious and scared, and it is necessary to quickly provide appropriate information and guidelines for action. However, conventional systems have difficulty responding flexibly to the user's emotional state, making it difficult to provide appropriate mental care or evacuation plans. They are also inadequate at suggesting individual responses or appropriate mental care methods based on the user's location information. Therefore, a system that can provide users with prompt and effective support is needed.

[1711] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1712] In this invention, the server includes means for a user to input an inquiry about anxiety during a disaster, means for analyzing the inquiry using generative artificial intelligence, means for identifying the cause of anxiety based on the analysis results, means for referencing a database and extracting related solutions, means for generating mental care methods and evacuation action plans, means for transmitting the generated information to the user's terminal, means for recognizing the user's emotional state, means for adjusting a response based on the emotional state, and means for providing specific guidelines for action to reduce anxiety during a disaster. This enables flexible responses and mental care to be provided according to the user's emotional state, thereby realizing anxiety reduction and the provision of appropriate guidelines for action during a disaster.

[1713] "User" refers to an individual who uses the system to input concerns or questions during a disaster.

[1714] "Terminals" refer to devices that users use to input their concerns and questions during a disaster and communicate with the system. Specifically, this includes smartphones, tablets, and PCs.

[1715] "Server" refers to the computer system that forms the core of the system, works in conjunction with generative artificial intelligence and databases, and transmits information to user terminals.

[1716] "Generative AI" refers to AI that analyzes user inquiries and generates appropriate solutions, mental care methods, and evacuation procedures.

[1717] An "emotion engine" refers to a system that recognizes emotions from the content of a user's inquiry and generates an appropriate response based on those emotions.

[1718] "Inquiry" refers to text data regarding concerns or questions that users input into the system.

[1719] "Analysis" refers to the process by which generative AI understands the content of a user's inquiry and extracts necessary keywords and emotional states.

[1720] "Causes of anxiety" refers to the specific reasons for the anxiety or fear that users feel during a disaster.

[1721] "Database" refers to an information system that stores information such as related solutions, mental care methods, and evacuation procedures.

[1722] "Solutions" refer to specific guidelines and measures to resolve users' concerns and questions.

[1723] "Mental care methods" refer to specific techniques for reducing anxiety and stress during a disaster, such as deep breathing, relaxation techniques, and communication suggestions.

[1724] "Evacuation action plan" refers to specific evacuation methods and guidelines for actions that users should take in the event of a disaster.

[1725] "Emotional state" refers to the specific emotion (e.g., anxiety, fear, worry) the user is feeling at the time of the inquiry.

[1726] "Response" refers to information such as solutions, mental care methods, and evacuation instructions that the system generates and provides to users.

[1727] "Location information" refers to the current geographic location obtained from the user's terminal.

[1728] "Evacuation shelter information" refers to information about locations and facilities where users can evacuate in the event of a disaster.

[1729] "Evacuation route" refers to route information for a user to travel safely from their current location to an evacuation shelter.

[1730] "Text generation technology" refers to the technology used by generative artificial intelligence to generate appropriate answers and advice in natural language.

[1731] A "prompt sentence" refers to an input sentence that causes a generative artificial intelligence to generate specific information or an answer.

[1732] This invention provides a system for alleviating anxiety felt by users during a disaster and providing appropriate guidelines for action. The system includes a user terminal, a server, a generative artificial intelligence (AI), and an emotion engine.

[1733] System Overview

[1734] Main components

[1735] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[1736] 2. Server: The core of the system, it connects with the generative AI and database, and transmits information to user devices.

[1737] 3. Generative artificial intelligence (AI): Analyzes user inquiries and generates appropriate solutions, mental care methods, and evacuation instructions.

[1738] 4. Emotion engine: Recognizes emotions from the user's inquiry and generates appropriate responses based on those emotions.

[1739] DETAILED DESCRIPTION OF THE EMBODIMENTS

[1740] 1. Receiving inquiries from users

[1741] Users can use their own devices to launch the Emacon application and input their concerns or questions into the chat window. For example, they might ask, "The earthquakes are continuing and I'm scared. What should I do?"

[1742] The terminal receives this inquiry and transmits it to the server as text data.

[1743] 2. Analysis of inquiry content

[1744] The server passes the received text data to the emotion engine, which recognizes the user's emotional state. The emotion engine uses natural language processing technology to extract emotions from the user's inquiry. For example, it can identify emotions such as anxiety or fear from the expression "scary."

[1745] The server then passes the recognized emotional state to a generative AI that analyzes the query. The generative AI then extracts key keywords from the tokenized text, such as "earthquake," "anxiety," and "measures."

[1746] 3. Proposing solutions and mental health care

[1747] Based on the extracted keywords and the recognized emotional state, the server accesses a database to search for relevant solutions and information, for example, data on past earthquake cases, evacuation plans, and emergency response measures.

[1748] Based on the search results, the generative AI generates specific solutions for the user in natural language. It reflects weighting based on the user's emotional state and adjusts the suggestions to convey a sense of kindness and security. For example, it creates advice such as, "The current earthquake is likely an aftershock and is expected to gradually subside. Don't be afraid, secure your furniture and prepare an evacuation bag."

[1749] 4. Individual support

[1750] The server provides a means to obtain the user's location information (if the user has given permission). Specifically, it obtains the current location using the device's location information API.

[1751] The server uses a map information API to search for and generate the optimal route from the user's current location to the nearest evacuation shelter. For example, it generates information such as "The nearest evacuation shelter is XX Park. Would you like to see the route from your current location?"

[1752] The terminal displays the evacuation shelter information and route guidance sent from the server to the user.

[1753] 5. Providing mental health care

[1754] Generative AI will suggest mental care methods (deep breathing, relaxation techniques, communicating with friends and family, etc.) to reduce anxiety and stress during a disaster. For example, it will generate advice such as, "I recommend taking deep breaths and talking to family and friends."

[1755] The server sends this mental care method as a text to the user's device, which displays, "We recommend taking a deep breath and talking to family or friends to feel reassured."

[1756] Specific examples

[1757] For example, consider the case where a user inputs a query such as "I'm worried about how long this earthquake will last."

[1758] The server uses an emotion engine to analyze the query and extract keywords such as "worry," "earthquake," and "continue," as well as emotional states. The emotion engine determines that the user is feeling anxious based on the expression "worry."

[1759] The generative AI references similar past cases from a database and generates answers such as, "Current seismic activity generally lasts for several weeks to several months, but aftershocks tend to gradually decrease."

[1760] The server then adds more specific evacuation measures and mental care methods and sends them to the user's device.

[1761] The device will display a message to the user saying, "Please check measures to prevent furniture from tipping over and prepare an evacuation bag so that it can be taken out immediately. Please also refer to techniques for deep breathing and relaxation."

[1762] Examples of prompt statements

[1763] The prompt text is written as follows:

[1764] User question: "I'm worried about how long this earthquake will last."

[1765] Prompt to generative AI model: "The user is asking about the ongoing earthquake and their concerns. Please ease the user's concerns and provide appropriate courses of action. Include information based on past earthquakes and evacuation plans."

[1766] This allows the system to effectively alleviate the user's anxiety and provide appropriate guidelines for action.

[1767] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1768] Step 1:

[1769] The user launches the Emacon application on their device and enters their concerns or questions into the chat window. For example, they might type, "The earthquakes are continuing and I'm scared. What should I do?"

[1770] Input: Text data of user concerns and questions ("The earthquakes are continuing and I'm scared. What should I do?")

[1771] Output: Request to send text data from the terminal to the server

[1772] Specific operation: The device receives user input and sends text data to the server via the API.

[1773] Step 2:

[1774] The server passes the received text data to an emotion engine to recognize the user's emotional state.

[1775] Input: User's query text data sent from the terminal

[1776] Output: Text data sent to the emotion engine and the recognition result of emotional state data (e.g., "fear").

[1777] Specific operation: The server sends text data to the emotion engine API, and the emotion engine uses natural language processing technology to extract emotions from the text. For example, it identifies the emotion of "fear" from the expression "scary."

[1778] Step 3:

[1779] The server passes the recognized emotional state to a generative AI, which then analyzes the query.

[1780] Input: Emotional state data from the emotion engine (e.g., "fear") and user query text data

[1781] Output: Key keywords extracted by generative AI (e.g., "earthquake," "anxiety," "measures")

[1782] How it works: The server passes the query text and emotional state to the generative AI, which then extracts key keywords based on the tokenized text.

[1783] Step 4:

[1784] The server accesses a database to search for relevant solutions and information based on the extracted keywords and the recognized emotional state.

[1785] Input: Keywords from generative AI (e.g., "earthquake," "anxiety," "countermeasures") and emotional state data (e.g., "fear")

[1786] Output: Database search results (e.g., past earthquake cases, evacuation plans, emergency measures)

[1787] Specific operation: The server queries the database based on the extracted keywords and emotional state data to obtain relevant solutions and information.

[1788] Step 5:

[1789] Generative AI generates specific solutions for users in natural language based on search results.

[1790] Input: Search results from a database (e.g., past earthquake cases, evacuation plans, emergency measures) and emotional state data (e.g., "fear")

[1791] Output: Natural language suggestions to the user (e.g., "The current earthquake is likely an aftershock and is expected to subside gradually. Please secure furniture and prepare an evacuation bag.")

[1792] Specific operation: The generative AI generates answers in natural language based on information in the database, and reflects weighting in the response sentence according to the emotional state.

[1793] Step 6:

[1794] The server transmits the generated solutions and mental care methods to the user terminal.

[1795] Input: A solution in natural language from a generative AI

[1796] Output: Send the solution to the user's device

[1797] Specific operation: The server sends the solutions and mental care methods received from the generative AI to the user's device via the API.

[1798] Step 7:

[1799] The user's terminal displays the received information.

[1800] Input: Solutions and mental health care methods sent from the server

[1801] Output: Display to the user (e.g. "The current earthquake is likely an aftershock and is expected to gradually subside. Please secure furniture and prepare an evacuation bag.")

[1802] What it does: The device displays the received text in a chat window or notification for the user to view.

[1803] Through the above processing steps, the system can alleviate the user's anxiety in real time and provide appropriate guidelines for action.

[1804] (Application example 2)

[1805] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1806] Current disaster response systems lack the information needed to adequately alleviate users' psychological anxiety and encourage efficient and safe evacuation. Furthermore, real-time notifications and guidance on optimal evacuation routes can be delayed during emergencies, resulting in insufficient safety and psychological support for users. Given these circumstances, there is a need for systems that can alleviate users' anxiety while quickly and effectively supporting their actions.

[1807] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for a user to input an inquiry about anxiety in the event of a disaster, a means for analyzing the content of the inquiry using generative artificial intelligence, and a means for identifying the cause of the anxiety based on the analysis result. This makes it possible to quickly analyze the content of the user's inquiry and identify appropriate countermeasures.

[1808] Furthermore, the server includes a means for referencing the database and extracting relevant solutions, a means for generating mental care methods and evacuation action plans, a means for transmitting the generated information to the user's terminal, a means for transmitting emergency notifications in real time when a disaster occurs, and a means for generating and providing guidance on the optimal evacuation route based on location information, thereby making it possible to provide specific and useful information tailored to each individual user.

[1809] Furthermore, the server includes a means for acquiring location information of the user, a means for searching for and providing information on nearby evacuation shelters and evacuation routes based on the location information, and a means for analyzing the user's emotional state and suggesting appropriate mental care methods based on the analysis, thereby enabling effective evacuation support while reducing the user's psychological anxiety.

[1810] The server also includes a means for proposing an appropriate mental care method according to the content of the inquiry, a means for formatting the mental care method using text generation technology and providing it, and a means for generating a prompt sentence for the generative AI and creating a response based on the result. This makes it possible to provide flexible mental care according to the user's emotional state.

[1811] The "means for users to input inquiries about their concerns in the event of a disaster" is an interface that allows users to input their concerns and questions about the event of a disaster via a terminal.

[1812] "Means for analyzing the inquiry content using generative artificial intelligence" refers to a function that uses generative artificial intelligence to analyze the inquiry content entered by the user and understand its meaning and intent.

[1813] The "means for identifying the cause of anxiety based on the analysis results" refers to an algorithm or technology for identifying the cause of the user's anxiety from the analyzed content.

[1814] The "means for referencing a database and extracting relevant solutions" refers to a process of referencing information stored in a database and extracting appropriate solutions related to the user's concerns.

[1815] "Means for generating mental care methods and evacuation action proposals" refers to algorithms or systems for generating mental care methods and specific evacuation action proposals.

[1816] The "means for transmitting the generated information to the user's terminal" is a mechanism for transmitting the generated mental care suggestions and evacuation action plans to the user's terminal via a network.

[1817] "Means for sending emergency notifications in real time when a disaster occurs" refers to a system for immediately sending emergency notifications to users' terminals when a disaster occurs.

[1818] The "means for generating an optimal evacuation route based on location information and providing guidance thereto" is a technology that uses the user's current location information to calculate an optimal evacuation route and provides guidance thereto to the user.

[1819] "Means for obtaining user location information" refers to a function that obtains the user's current location using GPS or other location information services.

[1820] The "means for searching for and providing information on nearby evacuation shelters and evacuation routes based on the location information" is a system for searching for nearby evacuation shelters and safe evacuation routes from the user's current location and providing guidance thereto.

[1821] "Means for analyzing the user's emotional state and proposing appropriate mental care methods based on that" refers to technology that analyzes the user's input, identifies their emotional state, and proposes appropriate mental care methods.

[1822] The "means for proposing an appropriate mental care method in accordance with the content of the inquiry" is a system that proposes an appropriate mental care method for a user based on the content of the inquiry from the user.

[1823] The "means for providing the mental care method by formatting it using text generation technology" is a function for formatting the proposed mental care method into a natural text format using natural language processing technology and providing it to the user.

[1824] "Means for generating prompt sentences for generative AI and creating responses based on the results" refers to a technology that creates appropriate prompt sentences for generative AI and constructs responses to users based on the results of the generation.

[1825] Overall system configuration

[1826] The system of the present invention includes the following main components:

[1827] 1. User device: The device through which users input their concerns or questions. This includes smartphones, tablets, and computers.

[1828] 2. Server: The core of the system, containing the generative artificial intelligence, database, and emotion engine.

[1829] 3. Generative artificial intelligence (AI): Analyzes user inquiries and generates appropriate solutions, mental care methods, and evacuation instructions.

[1830] 4. Emotion engine: Analyzes the user's emotions and generates appropriate responses based on the analysis results.

[1831] 5. Database: Stores data on past disaster cases, evacuation route information, and mental care methods.

[1832] Program processing flow

[1833] 1. Receiving user inquiries

[1834] Users launch the application on their smartphone or tablet and input their concerns or questions in text. This input is sent from the device to the server. For example, a user might ask, "There have been a series of earthquakes and I'm scared. What should I do?"

[1835] 2. Analysis of inquiry content

[1836] The server uses an emotion engine to analyze the inquiry and determine the user's emotional state. The engine uses natural language processing technology to identify the emotion "fear" from the user's inquiry. Generative AI then tokenizes the text and extracts key keywords, such as "earthquake," "fear," and "measures."

[1837] 3. Proposing solutions and mental health care

[1838] The server references a database and searches for relevant solutions based on the extracted keywords. For example, it retrieves information about past earthquakes, evacuation plans, and emergency response measures. The generative AI uses this information to generate advice in natural language to ease the user's anxiety. For example, it could output something like, "The current earthquake is likely an aftershock and is expected to gradually subside. Don't be afraid, secure your furniture, and prepare an evacuation bag."

[1839] 4. Emergency notification and evacuation route provision

[1840] In the event of a disaster, the server will send emergency notifications to the user's device in real time. The notification will read, "An earthquake has just occurred. Please evacuate to a safe location." The server will then calculate the optimal evacuation route based on the user's location information and provide guidance. For example, the server will display a message saying, "The nearest evacuation shelter is XX Park. Please evacuate via this route."

[1841] 5. Providing mental health care

[1842] The emotion engine analyzes the user's emotional state, and the generative AI suggests appropriate mental care methods, such as "Take a deep breath and relax. If necessary, speak to a staff member."

[1843] Hardware and software used

[1844] User devices include iOS and Android smartphones and tablets. Cloud services such as Amazon Web Services (AWS) and Google Cloud Platform (GCP) can be used for servers. Generative AI models such as GPT-3, which have natural language processing technology, are used. The emotion engine uses emotion recognition APIs (e.g., Microsoft Azure's Text Analytics API) that provide emotion analysis technology.

[1845] Examples and prompts

[1846] For example, consider the case where a user inputs "I'm worried about how long this earthquake will last." The server uses an emotion engine to extract keywords such as "worry," "earthquake," and "continue," and identifies the emotional state as "anxiety." The generative AI then references similar past cases in a database,

[1847] The model generates an answer such as, "Current seismic activity generally lasts for several weeks to several months, but aftershocks tend to gradually decrease." Examples of prompts for the model include:

[1848] "Users are worried about how long this earthquake will last. Please suggest appropriate mental care methods and guidelines for action."

[1849] Examples include:

[1850] This effectively reduces the user's anxiety and allows them to take necessary action quickly.

[1851] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1852] Step 1:

[1853] The user launches the application on their smartphone or tablet and inputs their concerns or questions in text. The input is sent from the device to the server. For example, the input data could be "There have been a series of earthquakes and I'm scared. What should I do?"

[1854] Step 2:

[1855] The server sends the text data sent by the user to the emotion engine. The emotion engine uses natural language processing technology to analyze the text and identify emotional states such as anxiety, fear, and worry. For example, the emotion of fear is identified from the expression "scared." The output data is...

Claims

1. A means for a user to input inquiries regarding concerns in the event of a disaster; means for analyzing the content of the inquiry using generative artificial intelligence; A means for identifying the cause of anxiety based on the analysis results; a means for referencing the database and extracting relevant solutions; A means for generating mental care methods and evacuation action plans; means for transmitting the generated information to a user terminal; A system including:

2. A means for acquiring user location information; A means for searching for nearby evacuation shelter information and evacuation routes based on the location information; The system of claim 1 , comprising:

3. A means for proposing an appropriate mental care method in accordance with the content of the inquiry; a means for formatting and providing the mental care method using a text generation technology; The system of claim 1 , comprising:

Images