System

Abstract

A system is provided.SOLUTION: The system includes a means for collecting and analyzing disaster information by using generated AI, a means for receiving inquiries from users and providing corresponding disaster information, a means for automatically updating date in the background, and a means for performing short-range radio communication by using existing date at the time of a communication failure.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 disaster occurs, it is extremely difficult to gather accurate and timely information needed by victims and those involved. While a large amount of information is provided by government agencies, the media, social media, and other sources, it is not easy to select reliable information from that and provide it with information that will enable appropriate action. Furthermore, when communication network failures occur, there are limited ways for victims to share information with each other. A system that can solve these problems is needed. [Means for solving the problem]

[0005] To solve these problems, this invention proposes a system that uses generative AI to collect and analyze disaster information and provides relevant information quickly and accurately in response to user inquiries. Furthermore, it provides an automatic background data update mechanism, and even in the event of a communication failure, existing data can be used via short-range wireless communication to share the latest information between nearby devices. This system enables disaster victims and those involved to efficiently obtain the information they need and take appropriate action.

[0006] "Generative AI" is an artificial intelligence technology that uses natural language processing and machine learning to extract meaning from massive amounts of data and generate new information and answers.

[0007] "Disaster information" refers to emergency information provided when a disaster occurs, such as damage status, locations of evacuation shelters, evacuation routes, rescue operations, and weather information.

[0008] "Users" refer to victims, their associates, and supporters who use this system to obtain information during a disaster.

[0009] "Query" refers to a request for information or question that a user submits to the system.

[0010] "Means for automatically updating data in the background" refers to a function that allows the system to automatically obtain and update the latest data without user operation.

[0011] A "communication failure" refers to a situation in which communication infrastructure such as the Internet or mobile phone networks becomes unavailable for some reason.

[0012] "Near field wireless communication" refers to a communication method that uses Bluetooth, Wi-Fi Direct, etc. to send and receive data directly between devices over short distances.

[0013] "Server" refers to a computer system that processes requests from users and provides the necessary information using generative AI.

[0014] "Terminal" refers to a device such as a smartphone, tablet, or PC that a user uses to access the system. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] The present invention is a system that uses generative AI to provide accurate and prompt information in the event of a disaster, and shares information via short-range wireless communication in the event of a communication failure. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described below.

[0037] System Overview

[0038] 1. Server Functions

[0039] The server is equipped with a generation AI and has the ability to collect and analyze disaster information.

[0040] The server receives inquiries from users, uses a generation AI to generate optimal answers, and returns these to the terminal.

[0041] The server regularly collects new disaster information from government agencies, media, and social media, and updates the data in the background.

[0042] 2. Device Features

[0043] The terminal has the function of sending inquiries from the user to the server.

[0044] The terminal displays the information received from the server to the user.

[0045] The device receives updated data from the server in the background and saves the latest data.

[0046] In the event of a communication outage, the device will use data stored in the background to provide information to other devices via short-range wireless communication.

[0047] 3. User Operation

[0048] The user launches the app and queries for the required information.

[0049] Based on the questions the user enters, the system provides the necessary information.

[0050] Program processing explanation

[0051] Processing requests and providing information

[0052] User asks for information

[0053] The user launches the app and types, for example, "Please tell me where the evacuation shelter is."

[0054] The terminal receives the user's input and sends it to the server as an HTTP request.

[0055] The server generates the information

[0056] The server receives the request and passes the contents to the generation AI.

[0057] The generative AI analyzes data collected from government agencies, media, and social media to generate optimal answers.

[0058] For example, the generation AI returns information such as, "Currently, the nearest evacuation shelter is XX Elementary School, and the route is YYY."

[0059] The device displays the information

[0060] The terminal analyzes the information received from the server and displays it to the user.

[0061] The user can refer to the displayed information and take appropriate action.

[0062] Background data updates

[0063] The server collects new information

[0064] The server regularly collects new disaster information from government agencies, media, and social media.

[0065] The server analyzes the collected information and updates the database.

[0066] The device updates the data

[0067] The server sends new information to the device via push notification.

[0068] The device updates the latest data received in the background and stores it locally.

[0069] Response in the event of a communication failure

[0070] The device detects a communication failure

[0071] The device periodically checks the internet connection and detects any communication disruptions.

[0072] The device uses existing data

[0073] If a communication failure occurs, the device will access the latest data stored in the background.

[0074] The device sends the necessary information to other devices via short-range wireless communication (such as Bluetooth or Wi-Fi Direct).

[0075] The other terminal displays the received information to the user.

[0076] Specific examples

[0077] For example, consider the occurrence of a large-scale earthquake. A user opens the app and asks, "Where is the nearest evacuation shelter?" This request is sent from the device to the server. The server uses generative AI to collect the latest evacuation shelter information from government agencies and the media, and generates a response such as, "The nearest evacuation shelter is XX Park, 1 km away." This information is sent to the device and displayed to the user.

[0078] Furthermore, if the communication network is down, the device will use the latest evacuation shelter data in the background and send that information to other nearby devices via Bluetooth, allowing users to share necessary information even during communication disruptions.

[0079] As described above, the system of the present invention provides accurate and prompt information during disasters and enables information sharing even during communication disruptions, enabling victims and related parties to obtain necessary information with minimal effort and take safe action.

[0080] The processing flow will be explained below.

[0081] Program processing

[0082] Processing requests and providing information

[0083] User asks for information

[0084] Step 1:

[0085] The user launches the app and enters information. For example, they might enter, "Please tell me where the evacuation shelter is."

[0086] Step 2:

[0087] The terminal constructs the user's input as an HTTP request and sends it to the server.

[0088] The server generates the information

[0089] Step 3:

[0090] The server analyzes the request received from the terminal.

[0091] Step 4:

[0092] The server passes the request content to the generation AI and collects relevant information.

[0093] Step 5:

[0094] Generative AI collects and analyzes data from government agencies, media, and social media.

[0095] Step 6:

[0096] Based on the data collected, the generative AI generates the optimal answer to the user's request. For example, it generates information such as, "The nearest evacuation shelter is currently XX Elementary School, and the route is YYY."

[0097] Step 7:

[0098] The server constructs the generated answer as an HTTP response and sends it to the terminal.

[0099] The device displays the information

[0100] Step 8:

[0101] The terminal analyzes the response data received from the server.

[0102] Step 9:

[0103] The device displays the analysis results to the user, for example, "The nearest evacuation shelter is XX Elementary School."

[0104] Background data updates

[0105] The server collects new information

[0106] Step 1:

[0107] The server regularly collects new disaster information from government agencies, media, and social media.

[0108] Step 2:

[0109] The server analyzes the collected information and updates the database through a generative AI.

[0110] The device updates the data

[0111] Step 3:

[0112] The server sends new information to the device via push notification.

[0113] Step 4:

[0114] The device receives a push notification and saves the new data to local storage in the background.

[0115] Response in the event of a communication failure

[0116] The device detects a communication failure

[0117] Step 1:

[0118] The device periodically checks the internet connection to detect if there are any communication disruptions.

[0119] The device uses existing data

[0120] Step 2:

[0121] The device that detects the communication failure accesses the latest data stored in the background.

[0122] Step 3:

[0123] The device uses short-range wireless communication (such as Bluetooth or Wi-Fi Direct) to send the necessary information to other users' devices nearby.

[0124] Step 4:

[0125] The other user's device analyzes the received information and displays it to the user, for example, "The latest evacuation shelter is XX Elementary School."

[0126] Example 1

[0127] 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."

[0128] When a natural disaster occurs, it is important to provide accurate information quickly and in real time. However, conventional information provision systems have limitations in the speed and accuracy of information collection, making it difficult to provide information, especially when communication failures occur. In addition, when integrating necessary information from multiple sources and providing it to users, the organization and analysis of the information is often inefficient. There is a need for a system that can provide highly reliable information even in situations where the communication environment is unstable.

[0129] 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.

[0130] In this invention, the server includes means for collecting and analyzing disaster information using a generative AI model, means for receiving inquiries from users and providing relevant disaster information, and means for returning responses generated by the server to the terminal. This enables information to be provided quickly and accurately when a disaster occurs. Users can receive the necessary information from the server and take appropriate action. Furthermore, even if a communication failure occurs, the terminal can use the latest information stored in the background and share the information with other devices via short-range wireless communication. This enables reliable information provision even in unstable communication environments.

[0131] A "generative AI model" is an artificial intelligence system that uses machine learning techniques to learn patterns and relationships from large amounts of data and generate new information.

[0132] "Disaster information" refers to all data related to natural disasters, such as the current situation, forecasts, impacts, evacuation sites, and support information.

[0133] "User inquiries" refer to the act of a user sending information or questions that the user requests the system to provide via a communication means.

[0134] "Automatic background data updates" is a function that allows the system to collect new information periodically or under certain conditions, regardless of user operations, and keep the internal database up to date.

[0135] A "Communications Outage" is a temporary or permanent outage of the Internet or other communications network.

[0136] "Existing data" refers to information that the system has collected and stored in the past, and is data that is used in situations where it is difficult to obtain the latest information.

[0137] "Near-field wireless communication" is a technology that transmits and receives data wirelessly over short distances, such as Bluetooth and Wi-Fi Direct.

[0138] "Means of collection and analysis" refers to methods of obtaining disaster information from various sources, analyzing its relevance and importance, and deriving useful information.

[0139] The "means for providing" refers to a means for displaying, notifying, or transmitting the analyzed information to the user.

[0140] "Means for returning" refers to the process of returning the analysis results and necessary information to the user terminal via communication.

[0141] The system of the present invention consists of a server, a terminal, and a user. The server has the function of collecting and analyzing disaster information using a generative AI model and generating optimal answers to user inquiries. Users can use this system through their terminals. Specific embodiments are described below.

[0142] Server Features

[0143] The server is equipped with a generative AI model and has the ability to collect and analyze disaster information. The server receives inquiries from users and passes the details to the generative AI model. The generative AI model analyzes data collected from government agencies, media, and social media, and generates optimal answers. The server also periodically collects new disaster information and automatically updates the database in the background. For example, an API can be implemented using Python's Flask to call a generative AI model (e.g., GPT-4).

[0144] Device Features

[0145] The device has the function of sending user inquiries to the server and displaying information from the server to the user. When a user launches the app and types, for example, "Where is the nearest evacuation shelter?", the inquiry is sent from the device to the server. The information received from the server is displayed on the device screen. The device also has the function of receiving new data from the server via push notifications and storing it locally in the background. Furthermore, in the event of a communication failure, the device can use the stored data to provide information to other devices via short-range wireless communication (such as Bluetooth or Wi-Fi Direct).

[0146] User operations

[0147] The user launches the app and enters the necessary information into a text box. For example, "Where is the nearest evacuation shelter?" The input is sent to the server via the device. The server analyzes the information using a generative AI model and generates a response, such as "The nearest evacuation shelter is XX Elementary School, and the route is YYY," which is sent back to the device. The device then displays this information to the user, who can then take appropriate action based on that information.

[0148] Specific examples

[0149] In the event of a major earthquake, the user opens the app and asks, "Where is the nearest evacuation shelter?" The device sends this query to the server. The server uses a generative AI model to analyze the latest evacuation shelter information and generates the answer, "The nearest evacuation shelter is XX Park, 1 km away." This information is sent to the device and displayed to the user.

[0150] An example of a prompt to input to a generative AI model is as follows:

[0151] "Please tell me information about the nearest evacuation shelter based on the current disaster situation."

[0152] As described above, the system of the present invention provides rapid and accurate information during disasters and enables information sharing even during communication disruptions, allowing victims and related parties to quickly obtain the necessary information and take safe action.

[0153] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0154] Step 1:

[0155] User asks for information

[0156] The user launches the app and types "Where is the nearest shelter?" This is entered into the device as string data. The entered data is internally converted into a structured request object. This request object contains the key "query" and the query string "Where is the nearest shelter?".

[0157] Step 2:

[0158] The device sends a request to the server

[0159] The terminal receives the generated request object and sends it to the server as an HTTP request. Specifically, it uses the HTTP POST method to send a request to the endpoint URL. The input is the user's question, which is sent to the server as an HTTP request. The output is the process by which the request is sent.

[0160] Step 3:

[0161] The server receives the query

[0162] The server analyzes the HTTP request received from the device and passes the content to the generative AI model. The input is the HTTP request, and the content is analyzed and input to the generative AI model as a prompt. The output is the prompt sent to the generative AI model.

[0163] Step 4:

[0164] Generative AI models generate information

[0165] The generative AI model receives a prompt, collates and analyzes information from an accumulated database and external sources, and generates the optimal answer. The input is the prompt, and data processing and calculations are performed to combine information from the database. The output is the generated answer text.

[0166] Step 5:

[0167] The server generates a response and sends it back to the device.

[0168] The server returns the answer obtained from the generative AI model to the device as an HTTP response. The input is the answer text from the generative AI model, which is structured as an HTTP response. The output is the response text sent to the device.

[0169] Step 6:

[0170] The device receives the information and displays it to the user.

[0171] The terminal analyzes the response received from the server and displays it to the user. The input is the response from the server, and data processing is performed to convert it into a displayable format. The output is the information displayed on the user's screen. The user can take appropriate action based on the displayed information.

[0172] Step 7:

[0173] The server collects and updates new information in the background

[0174] The server periodically collects new disaster information from government agencies, media, and social media, and automatically updates the database. The input is new information from external sources, and data calculations are performed to add or update this information to the database. The output is the updated database.

[0175] Step 8:

[0176] Your device updates data in the background

[0177] The server sends new information to the device via push notification. The device updates the received data in the background and stores it locally. The input is notification data from the server, and data calculations are performed to update the device's local storage or database. The output is the latest disaster information stored on the device.

[0178] Step 9:

[0179] Devices use existing data in the event of a communication failure

[0180] The device periodically checks the Internet connection and detects communication disruptions. If a communication disruption occurs, the device accesses the latest data stored in the background and displays that information to the user. In addition, it provides information to other devices using short-range wireless communication (such as Bluetooth or Wi-Fi Direct). The input is the existing data and the results of the communication status check, and the output is the information displayed to the user and the information sent to other devices.

[0181] This is the specific processing flow of the program for this system. This makes it possible to provide fast and accurate information in the event of a disaster, and to share highly reliable information even in the event of a communication failure.

[0182] (Application example 1)

[0183] 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."

[0184] Challenges in providing fast and accurate information during disasters include the problem of information sharing when communication failures occur and the inability to provide appropriate responses to user inquiries. Furthermore, security staff and guards working on-site have limited means of obtaining the latest information in real time and taking appropriate action. There is a need for a system that can solve these issues and enable users to instantly obtain the information they need in an emergency and take action.

[0185] 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.

[0186] In this invention, the server includes means for collecting and analyzing disaster information using a generation AI, means for receiving inquiries from users and providing relevant disaster information, and means for automatically updating data in the background, thereby enabling users to obtain disaster information in real time.

[0187] It also includes a means for using existing data to perform short-range wireless communication in the event of a communication failure, a means for the generation AI to provide analysis results in response to inquiries entered by voice from the user when communication is possible, and a means for displaying disaster information in real time on the smart device. This allows information sharing to continue even in the event of a communication failure, and enables users to quickly obtain information from the generation AI through voice input and easily check that information on their smart device.

[0188] "Generative AI" is a type of artificial intelligence technology that automatically generates new information and answers based on collected data.

[0189] "Disaster information" refers to detailed data on the location, scale, extent of impact, evacuation sites, and other information related to natural and man-made disasters.

[0190] A "user query" is a question or request made by a user to the system for specific information.

[0191] "Means for automatically updating data in the background" refers to a function that allows the system to periodically obtain the latest information from the server and update the local database, regardless of user ingress.

[0192] "Communications Outage" means a condition in which the Internet connection is unstable or unavailable.

[0193] "Near field communication" is a method of exchanging data between nearby devices using short-range communication technologies such as Bluetooth and Wi-Fi Direct.

[0194] "Voice input" is a method in which a user gives instructions or queries to a system using voice.

[0195] "Smart devices" refer to electronic devices that can connect to the Internet and have advanced processing capabilities, such as smartphones and smart glasses.

[0196] "Display in real time" means that the acquired information is displayed immediately on the screen of the user's device.

[0197] "Means for summarizing analysis results" is a function that analyzes the information collected by the generation AI and provides it in a concise format that is easy for users to understand.

[0198] "Push notification" is a function that allows a server to automatically send new information to a user's device in real time.

[0199] The system of the present invention uses generative AI to collect and analyze information in order to provide users with fast and accurate information during disasters, and has the ability to share information via short-range wireless communication even in the event of communication failure.

[0200] System configuration

[0201] This system mainly consists of a server, a terminal, and a user. The server is equipped with a generation AI and is responsible for collecting and analyzing disaster information. The terminal also sends inquiries from users to the server and displays the information received from the server to the user. Users access the system through their terminal and obtain the information they need.

[0202] Server Features

[0203] The server periodically collects new disaster information from government agencies, the media, social media, etc., and analyzes the data using a generation AI. Based on the collected data, the generation AI generates the optimal answer to a user's inquiry. For example, in response to the inquiry "Where is the nearest evacuation shelter?", the generation AI will respond with "Currently, the nearest evacuation shelter is XX Park."

[0204] Device Features

[0205] The device sends user inquiries to the server, receives responses from the server, and displays them to the user. The device also has the ability to receive updated data from the server in the background and store the latest data locally. In the event of a communication failure, the device uses the latest data stored in the background and provides information to other devices via short-range wireless communication (such as Bluetooth or Wi-Fi Direct).

[0206] User operations

[0207] The user uses a smart device (such as a smartphone or smart glasses) to launch the app and request information. If the device is capable of communication, the generation AI will provide analysis results based on the user's voice or text input. For example, if the user voice-inputs, "Please tell me where the evacuation shelters are," the device will display the information analyzed by the generation AI.

[0208] Specific examples

[0209] For example, if a large-scale earthquake occurs, a user puts on smart glasses and asks, "Where is the nearest evacuation shelter?" This request is sent from the device to the server. The server uses generative AI to collect the latest evacuation shelter information from government agencies and the media, and generates a response such as, "The nearest evacuation shelter is XX Park, 1 km away." This information is sent to the device and displayed to the user on the smart glasses' display.

[0210] Furthermore, if the communication network is down, the device will transmit the latest evacuation shelter data stored in the background to other nearby devices via Bluetooth, allowing users to share necessary information even during communication disruptions.

[0211] Prompt Sentence Examples

[0212] "User: An earthquake has occurred. Where is the nearest safe haven?"

[0213] "Generator AI: Understood. Currently, the closest evacuation shelter is XX Park. It's about a 5-minute walk away. Please avoid collapsible buildings when evacuating."

[0214] The above is a specific example of how the system of the present invention provides information during a disaster. This system uses a generative AI model and prompts to provide optimal information to users, and is designed to enable continued information sharing even during communication disruptions.

[0215] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0216] Step 1:

[0217] User asks for information

[0218] Input: A user uses a smart device (smart glasses or smartphone), launches the app, and asks verbally, "Where is the nearest evacuation shelter?"

[0219] Data processing: The device converts the voice input into text and generates an HTTP request to send to the server.

[0220] Output: Text after audio data conversion and data in HTTP request format are generated.

[0221] What it does: It accepts voice input, converts it to text using speech recognition technology, packages this text data into an HTTP request, and sends it to the server.

[0222] Step 2:

[0223] The server generates the information

[0224] Input: HTTP request sent from the device (text data: "Where is the nearest evacuation shelter?").

[0225] Data calculation: Generative AI analyzes data collected from government agencies and the media to generate optimal answers.

[0226] Output: Generated answer text ("The nearest shelter is XX Park").

[0227] Operation: The server passes the query to the generation AI, which then analyzes and generates the most appropriate evacuation shelter information while checking various databases, and returns the answer text to the terminal.

[0228] Step 3:

[0229] The device displays the information

[0230] Input: Answer text received from the server ("The nearest shelter is XX Park").

[0231] Data processing: Format the received text data in a way that is compatible with the display format of the smart device.

[0232] Output: Information shown on the display of the user's smart device (smart glasses or smartphone).

[0233] Operation: Receives response data from the server, formats it into text for display, and displays it on the smart device's display.

[0234] Step 4:

[0235] The server collects new information

[0236] Input: A trigger based on a recurring schedule.

[0237] Data calculation: Collect the latest disaster information from government agencies, media, social media, etc. and update the database.

[0238] Output: Updated disaster information database.

[0239] How it works: The server periodically collects data from external sources, analyzes and categorizes the data using generative AI, and updates the disaster information database.

[0240] Step 5:

[0241] The device updates the data

[0242] Input: Push notification from the server (new disaster information).

[0243] Data processing: Received data is saved in a local database.

[0244] Output: The updated local database.

[0245] How it works: The device receives push notifications in the background and stores the latest data in a local database.

[0246] Step 6:

[0247] Response in the event of a communication failure

[0248] Input: Communication failure detected (unreliable internet connection).

[0249] Data processing: Refer to existing local databases and extract the necessary data.

[0250] Output: Referenced data (e.g., shelter information).

[0251] Operation: The device periodically checks its internet connection and, if it detects a communication failure, continues to operate using data stored in the background.

[0252] Step 7:

[0253] Information sharing via short-range wireless communication

[0254] Input: Other devices nearby.

[0255] Data calculation: Send data using Bluetooth or Wi-Fi Direct.

[0256] Output: Data sent to other nearby devices.

[0257] How it works: The device sends information to other devices via short-range wireless communication, making it available to the user.

[0258] The above are the specific processing steps of the system.

[0259] 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.

[0260] The present invention is a system that uses generative AI to provide accurate and prompt information when a disaster occurs, and combines it with an emotion engine that recognizes the user's emotions to provide more appropriate support. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described below.

[0261] System Overview

[0262] 1. Server Functions

[0263] The server is equipped with a generative AI and emotion engine, and has the ability to collect and analyze disaster information.

[0264] The server receives inquiries from users and uses generation AI to generate optimal answers, analyzing the user's emotions with an emotion engine and adjusting the information provided.

[0265] The server regularly collects new disaster information from government agencies, media, and social media, and updates the data in the background.

[0266] 2. Device Features

[0267] The terminal has the function of sending inquiries from the user to the server.

[0268] The terminal displays the information received from the server to the user, and also displays additional support information based on the user's emotions.

[0269] The device receives updated data from the server in the background and saves the latest data.

[0270] In the event of a communication outage, the device will use data stored in the background to provide information to other devices via short-range wireless communication.

[0271] 3. User Operation

[0272] Users launch the app and ask for the information they need, and emotional input can be automatically analyzed using voice, text, or facial recognition.

[0273] The user's emotions are analyzed and support information is provided accordingly.

[0274] Program processing explanation

[0275] Processing requests and providing information

[0276] User asks for information

[0277] The user launches the app and types, "Please tell me the location of the evacuation shelter." The device sends the user's input along with emotion data analyzed by the emotion engine to the server.

[0278] The server generates the information

[0279] The server analyzes the received request and emotional data. The generation AI collects data from government agencies, media, and social media, and generates the analysis results. The emotion engine analyzes the user's emotions and passes the results to the generation AI, which then adjusts the information provided to suit the user's situation and emotions.

[0280] For example, if the emotion engine analyzes that the user is in a state of panic, the generative AI will provide information such as, "Currently, the nearest evacuation shelter is XX Elementary School. Please remain calm and evacuate. We will provide telephone support if necessary."

[0281] The device displays the information

[0282] The device analyzes the information received from the server and displays it to the user. In addition to the usual evacuation shelter information, it also provides additional support information based on the user's emotions.

[0283] Background data updates

[0284] The server collects new information

[0285] The server regularly collects the latest disaster information from government agencies, the media, and social media, analyzes it using generative AI, and updates the database.

[0286] The device updates the data

[0287] The server sends new information to the device via push notification, and the device updates the data in the background.

[0288] Response in the event of a communication failure

[0289] The device detects a communication failure

[0290] The device periodically checks the internet connection and detects communication disruptions.

[0291] The device uses existing data

[0292] In the event of a communication failure, the device will access the latest data stored in the background. Information will be provided to other users' devices using short-range wireless communication (Bluetooth, Wi-Fi Direct, etc.). For example, even if a communication failure occurs, a device can provide information such as "The nearest evacuation shelter is XX Elementary School" to other users' devices nearby.

[0293] As described above, by combining generative AI and an emotion engine, the system of the present invention can improve the accuracy and speed of information during disasters and provide support that responds to the user's emotions. This allows victims and those involved to quickly and appropriately obtain the information they need and take safe action.

[0294] The processing flow will be explained below.

[0295] Program processing

[0296] Processing requests and providing information

[0297] User asks for information

[0298] Step 1:

[0299] The user launches the app and types, "Please tell me where the evacuation shelter is."

[0300] Step 2:

[0301] The device receives user input and activates the emotion engine, collecting user emotion data through methods such as voice, text, and facial recognition.

[0302] Step 3:

[0303] The device sends the user's input and emotional data to the server as an HTTP request.

[0304] The server generates the information

[0305] Step 4:

[0306] The server analyzes the request content and emotion data received from the device.

[0307] Step 5:

[0308] The server passes the request content and emotion data to the generated AI, which then collects and analyzes related disaster information.

[0309] Step 6:

[0310] The generative AI collects data from government agencies, media, and social media, and generates analytical results.

[0311] Step 7:

[0312] The emotion engine feeds the results of the user's emotion analysis back to the generation AI, which then adjusts the information provided.

[0313] Step 8:

[0314] The server generates information such as "Currently, the nearest evacuation shelter is XX Elementary School, and the route is YYY."

[0315] Step 9:

[0316] The server sends the generated answer to the terminal as an HTTP response.

[0317] The device displays the information

[0318] Step 10:

[0319] The terminal analyzes the response data received from the server.

[0320] Step 11:

[0321] The device displays the analysis results to the user, for example, "The nearest evacuation shelter is XX Elementary School" and additional information such as "Please remain calm and evacuate. We will provide telephone support if necessary."

[0322] Background data updates

[0323] The server collects new information

[0324] Step 1:

[0325] The server regularly collects new disaster information from government agencies, media, and social media.

[0326] Step 2:

[0327] The server analyzes the collected information and updates the database using generative AI.

[0328] The device updates the data

[0329] Step 3:

[0330] The server sends new information to the device via push notification.

[0331] Step 4:

[0332] The device receives the push notification in the background and saves the new data to local storage.

[0333] Response in the event of a communication failure

[0334] The device detects a communication failure

[0335] Step 1:

[0336] The device periodically checks the Internet connection to detect whether any communication problems have occurred.

[0337] The device uses existing data

[0338] Step 2:

[0339] When a device detects a communication failure, it accesses the latest data stored in the background.

[0340] Step 3:

[0341] The device uses short-range wireless communication (Bluetooth, Wi-Fi Direct, etc.) to send necessary information to other users' devices nearby.

[0342] Step 4:

[0343] The information received by other users' devices is analyzed and displayed to the user. For example, it displays, "Even during a communication outage, the nearest evacuation shelter is XX Elementary School."

[0344] Example 2

[0345] 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."

[0346] Conventional disaster information systems are required to provide prompt and accurate information in response to user inquiries, but they lack support that takes into account the user's emotional state. Furthermore, effective information provision methods during communication disruptions are limited, making it difficult to provide useful information to users during disasters. Therefore, the objective of this invention is to provide a disaster information provision system that utilizes generative AI and emotion recognition technology to provide appropriate information according to the user's emotional state and that has effective information provision methods even during communication disruptions.

[0347] 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.

[0348] In this invention, the server includes means for collecting and analyzing disaster information using a generation AI, means for receiving inquiries from users and providing relevant disaster information, means for automatically updating data in the background, means for using existing data to perform short-range wireless communication during communication disruptions, and means for analyzing the user's emotions using an emotion recognition engine and adjusting the information provided by the generation AI. This enables prompt and accurate information provision even during disasters, and provides support tailored to the user's emotional state. As a result, disaster victims and their relatives can quickly and appropriately obtain the information they need and take safe action.

[0349] "Generative AI" is a system that uses artificial intelligence technology to collect and analyze data and generate optimal information in response to user requests.

[0350] "Disaster information" refers to various information related to disasters, such as the occurrence and progression of the disaster, the extent of the impact, and the location of evacuation shelters.

[0351] A "user inquiry" is an input made by a user to the system to request specific information or assistance, and may be in the form of text, voice, image, or the like.

[0352] "Automatically updating data in the background" means that the system has the function of periodically collecting the latest data and updating the database without requiring user operation.

[0353] "Communication failure" refers to a network malfunction or disruption that occurs when a system sends or receives data via the Internet or other means of communication.

[0354] "Existing data" refers to information that has been stored in the system in advance and is available even in the event of a communication failure.

[0355] "Near field wireless communication" refers to technologies such as Wi-Fi Direct and Bluetooth that enable data communication between devices over short distances.

[0356] An "emotion recognition engine" refers to a technology or system that analyzes emotions from a user's voice, text, facial expressions, etc., and determines the user's emotional state.

[0357] "Providing appropriate information" means providing information in a form that best suits the user's situation and emotional state, with the aim of improving the user's sense of security and appropriateness of behavior.

[0358] The present invention is a system that uses a generative AI model to provide accurate and prompt information when a disaster occurs, and combines it with an emotion recognition engine that recognizes user emotions to provide more appropriate support. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described in detail below.

[0359] System configuration

[0360] This system mainly consists of the following hardware and software components.

[0361] 1. Server

[0362] It is equipped with a generative AI model and has the ability to collect and analyze disaster information.

[0363] It is equipped with an emotion recognition engine that analyzes the user's emotions.

[0364] Regularly collect data from government agencies, media, and social networking services to update the database.

[0365] If communication is normal, the latest disaster information will be sent to the user's device via push notification.

[0366] 2. Terminal

[0367] It has the function of sending user inquiries to the server.

[0368] It has the function of displaying information received from the server to the user.

[0369] Data is updated in the background, and in the event of a communication failure, short-range wireless communication is performed using existing data.

[0370] 3. Users

[0371] Use a device such as a smartphone or tablet to inquire about the information you need.

[0372] Take appropriate action based on the information inquired.

[0373] Program processing explanation

[0374] The server receives inquiries from users and analyzes them using a generative AI model. It also analyzes the user's emotions using an emotion recognition engine and adjusts the information provided. The generative AI model is trained using a large dataset, allowing it to provide the latest information in real time. The specific processing flow is as follows:

[0375] 1. User operations

[0376] The user launches the app and asks for the required information by voice or text, for example, by entering a prompt such as "Please tell me the location of the evacuation shelter."

[0377] 2. Terminal Processing

[0378] The device converts the user's inquiry into text and uses an emotion recognition engine to analyze emotional data from the user's voice and facial expressions.

[0379] The analyzed data and the user's query are sent to the server.

[0380] 3. Server Processing

[0381] The server uses a generative AI model based on the received data to analyze the user's query and collect and compile the necessary disaster information.

[0382] The emotional state of the user is analyzed again using an emotion recognition engine, and the generated information is provided to the user in an optimal form.

[0383] For example, if the user is in a panic, a message such as "The nearest evacuation shelter is currently XX Elementary School. Please remain calm and evacuate" is generated.

[0384] 4. Display by terminal

[0385] The information received from the server is displayed to the user, and necessary support information is provided.

[0386] Examples of concrete examples and prompts

[0387] Specific examples

[0388] The user launches a smartphone app and speaks, "Is there a safe place nearby?"

[0389] The device converts the voice data into text and uses an emotion recognition engine to analyze whether the user is in a state of agitation.

[0390] The server analyzes the query using a generative AI model and generates information about the nearest evacuation shelter and a message such as "Please remain calm and evacuate."

[0391] The device displays this to the user, providing necessary information and a sense of security.

[0392] Prompt Sentence Examples

[0393] 1. "Please tell me where the evacuation shelter is."

[0394] 2. "Is there a safe place nearby?"

[0395] 3. "Can you give me an update on the current situation?"

[0396] As described above, by combining a generative AI model and an emotion recognition engine, the system of the present invention can provide prompt and accurate information during disasters and provide appropriate support according to the user's emotional state. This allows disaster victims and those involved to quickly and appropriately obtain the necessary information and take safe action.

[0397] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0398] System program processing flow

[0399] Step 1: User Enters Information

[0400] The user launches the app and speaks, "Please tell me the location of the evacuation shelter." This voice input is sent to the device and converted to text on the spot. The converted text becomes the input data for the information query.

[0401] Input: Audio input

[0402] Output: The query converted to text

[0403] Step 2: The device analyzes and transmits the emotion data.

[0404] The device analyzes the user's voice and facial expressions using an emotion recognition engine to generate emotional data about the user. The specific emotional state (e.g., panic, calm, etc.) is analyzed and sent to the server along with a text query.

[0405] Input: Text-converted query, user voice and facial expression data

[0406] Output: Parsed emotion data, sent to the server along with the query

[0407] Step 3: The server parses the information

[0408] The server uses a generative AI model to collect and analyze the necessary disaster information based on the received inquiry and emotion data. Specifically, it collects the latest disaster information from government agencies, media, and social media, and generates information appropriate for the user's inquiry.

[0409] Input: Text-converted query, emotion data

[0410] Output: Disaster information in response to user inquiries

[0411] Step 4: The server adjusts the information based on the emotion data

[0412] The server adjusts the disaster information it generates based on the user's emotional data analyzed by an emotion recognition engine. For example, if the user is in a panic, it generates information containing a message that gives a sense of security.

[0413] Input: Disaster information and emotion data in response to user inquiries

[0414] Output: Emotionally sensitive information

[0415] Step 5: The server sends the information to the device

[0416] The server then sends the adjusted disaster information to the terminal. Communication is performed using secure protocols such as SSL / TLS.

[0417] Input: Emotionally sensitive information

[0418] Output: Data sent to the terminal

[0419] Step 6: The device displays the information to the user

[0420] The device analyzes the information it receives and displays it in an optimal way for the user, including the location of evacuation shelters and sensitive messages.

[0421] Input: Adjusted information sent from the server

[0422] Output: The final information displayed to the user

[0423] Specific examples of operation

[0424] Step 1: User Enters Information

[0425] The user opens the app on their smartphone and says, "Tell me where the nearest safe place is." The speech is converted into text in real time and displayed on the device.

[0426] Step 2: The device analyzes and transmits the emotion data.

[0427] The device uses an emotion recognition engine to analyze the user's tone of voice and facial expressions to determine their emotional state. For example, the device sends a text query along with the analyzed emotional state, such as "anxiety," to the server.

[0428] Step 3: The server parses the information

[0429] Based on the received data, the server uses a generative AI model to collect and analyze the latest disaster information, including "nearby evacuation shelters." The information is extracted from the database and a list of the nearest currently available evacuation shelters is generated.

[0430] Step 4: The server adjusts the information based on the emotion data

[0431] The server takes into account the results of the emotion recognition engine and adjusts the information to suit a user in a state of panic. Specifically, it generates information containing a reassuring message such as, "XX Elementary School is the nearest evacuation shelter. Please remain calm and evacuate."

[0432] Step 5: The server sends the information to the device

[0433] The server sends the tailored information to the device, including a map of the evacuation center, its address, and a reassuring message.

[0434] Step 6: The device displays the information to the user

[0435] The device displays the received information to the user, who can then check the map on the app screen along with a message saying, "XX Elementary School is the nearest evacuation shelter. Please remain calm and evacuate."

[0436] Through the above processing, this system can provide appropriate information according to the user's emotional state and support safe behavior in the event of a disaster.

[0437] (Application example 2)

[0438] 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."

[0439] Existing disaster information systems struggle to provide accurate and timely information during disasters, and also to provide appropriate support that takes into account the user's emotions. It is particularly difficult to continue providing appropriate information when communication failures occur. Furthermore, there is a lack of methods to reduce the stress and anxiety users feel during disasters and encourage effective evacuation behavior.

[0440] 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 means for collecting and analyzing disaster information using a generation AI, means for receiving inquiries from users and providing corresponding disaster information, means for automatically updating data in the background, means for performing short-range wireless communication using existing data in the event of a communication failure, and means for analyzing the user's emotions using emotion recognition technology and adjusting the information to be provided based on the results. This makes it possible to provide accurate and prompt information even during a disaster and provide appropriate support according to the user's emotions.

[0441] "Generative AI" is an artificial intelligence technology that automatically generates information based on input data.

[0442] "Disaster information" refers to various information related to natural and man-made disasters, including the location of evacuation shelters, damage status, and first aid information.

[0443] "Analysis" is the process of breaking down and analyzing collected data to extract useful information.

[0444] "User" means any person or entity that uses the System.

[0445] An "inquiry" refers to a question or request made by a user to the system for information or assistance.

[0446] "Automatically updating data in the background" is a function that allows the system to automatically obtain and store the latest information even when the user is not operating the system.

[0447] "Communication outage" refers to a situation in which the Internet or other means of communication do not function properly.

[0448] "Existing Data" refers to data that has previously been collected and stored by the system.

[0449] "Near field wireless communication" refers to exchanging data using short-range wireless communication technologies such as Bluetooth and Wi-Fi Direct.

[0450] "Emotion recognition technology" is a technology that determines a user's emotions from the tone of their voice, facial expression, text content, etc.

[0451] The present invention is a system that uses generative AI and emotion recognition technology to provide accurate and prompt information in the event of a disaster, and provides appropriate support according to the user's emotions. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described below.

[0452] System Overview

[0453] 1. Server Functions

[0454] The server is equipped with generative AI and emotion recognition technology, and has the ability to collect and analyze disaster information, allowing it to retain accurate and up-to-date information and generate information in response to user inquiries.

[0455] The server receives inquiries from users and uses generative AI to generate the optimal answer. It also uses emotion recognition technology to analyze the user's emotions and adjust the information provided accordingly. For example, if the user is in a panic, it will provide information that includes reassuring words.

[0456] The server periodically collects new disaster information from government agencies, the media, social media, etc. and updates the data in the background, ensuring that users are always provided with the latest information.

[0457] 2. Device Features

[0458] The devices include smartphones, tablets, robots, etc., and have the ability to send inquiries from users to a server. Questions can be sent via voice input or text input.

[0459] The device receives the information from the server and displays it to the user. The displayed information is adjusted based on the user's emotions, providing more personalized assistance.

[0460] The device has the ability to receive updated data from the server in the background and store the latest data. Even if communication is interrupted, the stored data can be used to provide information to other devices via short-range wireless communication (Bluetooth, Wi-Fi Direct, etc.).

[0461] 3. User Operation

[0462] The user launches the application installed on the device and requests the necessary information. Inquiries are made via voice, text, facial recognition, etc. Emotions are automatically analyzed and appropriate support information is provided.

[0463] For example, if a user makes a voice inquiry such as "Please tell me where the evacuation shelter is," the device sends the voice to the server, which then uses emotion recognition technology to analyze the user's state. Based on the results, the AI ​​generates information such as "Currently, the nearest evacuation shelter is XX Elementary School. Please remain calm and evacuate. We will provide telephone support if necessary," and sends it to the device.

[0464] Hardware and software used

[0465] Hardware:

[0466] Camera: Used to capture facial images and recognize emotions. Use the built-in camera on your smartphone or robot.

[0467] Smartphone / Tablet / Robot: The primary device on which the application runs.

[0468] software:

[0469] OpenCV: A library for face recognition and image processing.

[0470] TensorFlow / Keras: Machine learning frameworks for running emotion recognition models.

[0471] Transformers (Hugging Face): A library that generates text using generative AI (GPT-2).

[0472] Requests: A library for retrieving data from the disaster information API.

[0473] Specific examples

[0474] Scenario: When a disaster occurs, a user looks into their smartphone camera and asks, "Where is the evacuation shelter?"

[0475] Example prompt: "User is feeling Fear. Provide the most relevant disaster information: Nearest shelter is at XX school. Please stay calm. We can provide phone support if needed."

[0476] Example response generated: "The nearest evacuation shelter is XX Elementary School. Please remain calm. Telephone assistance will be provided if necessary."

[0477] As described above, by combining generative AI and emotion recognition technology, the system of the present invention can improve the accuracy and speed of information during disasters, and can also provide support that is tailored to the user's emotions.

[0478] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0479] Step 1:

[0480] The server automatically collects and analyzes disaster information from government agencies, media, social media, etc. It collects new disaster information as input and analyzes it using a generative AI model. The analyzed data is stored in a database and is ready for user inquiries.

[0481] Step 2:

[0482] The user activates the device's camera function and has their face recognized. The user's facial image is provided as input, and the device detects the face using OpenCV and inputs the facial image into an emotion recognition model. Emotion recognition technology (TensorFlow / Keras) analyzes the user's emotion as "panic," "fear," etc. The output is the user's emotion data.

[0483] Step 3:

[0484] The user asks the terminal a question by voice, such as "Where is the evacuation shelter?" This voice data is input into the terminal and converted into text. The converted question content and emotion data are sent to the server.

[0485] Step 4:

[0486] The server generates an optimal response based on the received question content and emotion data. The question content and emotion data are provided as input, and an appropriate answer is generated using a generative AI model (Transformers). For example, a response such as "The nearest evacuation shelter is XX Elementary School. Please remain calm. We will provide telephone support if necessary" is generated. The output is response data to be sent back to the user.

[0487] Step 5:

[0488] The terminal receives the response data from the server and displays it to the user. The terminal receives the response data from the server as input and displays it on the screen. This gives the user information about the nearest evacuation shelter and a message encouraging reassurance.

[0489] Step 6:

[0490] The server periodically updates data in the background to maintain the latest disaster information. It receives new disaster information as input, analyzes it with the generative AI model, and updates the database. This ensures that the latest information is always available to users.

[0491] Step 7:

[0492] In the event of a communication failure, the device will use the latest data stored in the background to communicate with other devices in the vicinity via short-range wireless communication (Bluetooth, Wi-Fi Direct, etc.) using the communication failure detection signal as input. This allows important information to be shared even when an internet connection is unavailable.

[0493] 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.

[0494] 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.

[0495] 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.

[0496] [Second embodiment]

[0497] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0498] 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.

[0499] 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).

[0500] 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.

[0501] 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.

[0502] 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).

[0503] 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.

[0504] 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.

[0505] 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.

[0506] 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.

[0507] 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.

[0508] 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."

[0509] The present invention is a system that uses generative AI to provide accurate and prompt information in the event of a disaster, and shares information via short-range wireless communication in the event of a communication failure. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described below.

[0510] System Overview

[0511] 1. Server Functions

[0512] The server is equipped with a generation AI and has the ability to collect and analyze disaster information.

[0513] The server receives inquiries from users, uses a generation AI to generate optimal answers, and returns these to the terminal.

[0514] The server regularly collects new disaster information from government agencies, media, and social media, and updates the data in the background.

[0515] 2. Device Features

[0516] The terminal has the function of sending inquiries from the user to the server.

[0517] The terminal displays the information received from the server to the user.

[0518] The device receives updated data from the server in the background and saves the latest data.

[0519] In the event of a communication outage, the device will use data stored in the background to provide information to other devices via short-range wireless communication.

[0520] 3. User Operation

[0521] The user launches the app and queries for the required information.

[0522] Based on the questions the user enters, the system provides the necessary information.

[0523] Program processing explanation

[0524] Processing requests and providing information

[0525] User asks for information

[0526] The user launches the app and types, for example, "Please tell me where the evacuation shelter is."

[0527] The terminal receives the user's input and sends it to the server as an HTTP request.

[0528] The server generates the information

[0529] The server receives the request and passes the contents to the generation AI.

[0530] The generative AI analyzes data collected from government agencies, media, and social media to generate optimal answers.

[0531] For example, the generation AI returns information such as, "Currently, the nearest evacuation shelter is XX Elementary School, and the route is YYY."

[0532] The device displays the information

[0533] The terminal analyzes the information received from the server and displays it to the user.

[0534] The user can refer to the displayed information and take appropriate action.

[0535] Background data updates

[0536] The server collects new information

[0537] The server regularly collects new disaster information from government agencies, media, and social media.

[0538] The server analyzes the collected information and updates the database.

[0539] The device updates the data

[0540] The server sends new information to the device via push notification.

[0541] The device updates the latest data received in the background and stores it locally.

[0542] Response in the event of a communication failure

[0543] The device detects a communication failure

[0544] The device periodically checks the internet connection and detects any communication disruptions.

[0545] The device uses existing data

[0546] If a communication failure occurs, the device will access the latest data stored in the background.

[0547] The device sends the necessary information to other devices via short-range wireless communication (such as Bluetooth or Wi-Fi Direct).

[0548] The other terminal displays the received information to the user.

[0549] Specific examples

[0550] For example, consider the occurrence of a large-scale earthquake. A user opens the app and asks, "Where is the nearest evacuation shelter?" This request is sent from the device to the server. The server uses generative AI to collect the latest evacuation shelter information from government agencies and the media, and generates a response such as, "The nearest evacuation shelter is XX Park, 1 km away." This information is sent to the device and displayed to the user.

[0551] Furthermore, if the communication network is down, the device will use the latest evacuation shelter data in the background and send that information to other nearby devices via Bluetooth, allowing users to share necessary information even during communication disruptions.

[0552] As described above, the system of the present invention provides accurate and prompt information during disasters and enables information sharing even during communication disruptions, enabling victims and related parties to obtain necessary information with minimal effort and take safe action.

[0553] The processing flow will be explained below.

[0554] Program processing

[0555] Processing requests and providing information

[0556] User asks for information

[0557] Step 1:

[0558] The user launches the app and enters information. For example, they might enter, "Please tell me where the evacuation shelter is."

[0559] Step 2:

[0560] The terminal constructs the user's input as an HTTP request and sends it to the server.

[0561] The server generates the information

[0562] Step 3:

[0563] The server analyzes the request received from the terminal.

[0564] Step 4:

[0565] The server passes the request content to the generation AI and collects relevant information.

[0566] Step 5:

[0567] Generative AI collects and analyzes data from government agencies, media, and social media.

[0568] Step 6:

[0569] Based on the data collected, the generative AI generates the optimal answer to the user's request. For example, it generates information such as, "The nearest evacuation shelter is currently XX Elementary School, and the route is YYY."

[0570] Step 7:

[0571] The server constructs the generated answer as an HTTP response and sends it to the terminal.

[0572] The device displays the information

[0573] Step 8:

[0574] The terminal analyzes the response data received from the server.

[0575] Step 9:

[0576] The device displays the analysis results to the user, for example, "The nearest evacuation shelter is XX Elementary School."

[0577] Background data updates

[0578] The server collects new information

[0579] Step 1:

[0580] The server regularly collects new disaster information from government agencies, media, and social media.

[0581] Step 2:

[0582] The server analyzes the collected information and updates the database through a generative AI.

[0583] The device updates the data

[0584] Step 3:

[0585] The server sends new information to the device via push notification.

[0586] Step 4:

[0587] The device receives a push notification and saves the new data to local storage in the background.

[0588] Response in the event of a communication failure

[0589] The device detects a communication failure

[0590] Step 1:

[0591] The device periodically checks the internet connection to detect if there are any communication disruptions.

[0592] The device uses existing data

[0593] Step 2:

[0594] The device that detects the communication failure accesses the latest data stored in the background.

[0595] Step 3:

[0596] The device uses short-range wireless communication (such as Bluetooth or Wi-Fi Direct) to send the necessary information to other users' devices nearby.

[0597] Step 4:

[0598] The other user's device analyzes the received information and displays it to the user, for example, "The latest evacuation shelter is XX Elementary School."

[0599] Example 1

[0600] 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."

[0601] When a natural disaster occurs, it is important to provide accurate information quickly and in real time. However, conventional information provision systems have limitations in the speed and accuracy of information collection, making it difficult to provide information, especially when communication failures occur. In addition, when integrating necessary information from multiple sources and providing it to users, the organization and analysis of the information is often inefficient. There is a need for a system that can provide highly reliable information even in situations where the communication environment is unstable.

[0602] 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.

[0603] In this invention, the server includes means for collecting and analyzing disaster information using a generative AI model, means for receiving inquiries from users and providing relevant disaster information, and means for returning responses generated by the server to the terminal. This enables information to be provided quickly and accurately when a disaster occurs. Users can receive the necessary information from the server and take appropriate action. Furthermore, even if a communication failure occurs, the terminal can use the latest information stored in the background and share the information with other devices via short-range wireless communication. This enables reliable information provision even in unstable communication environments.

[0604] A "generative AI model" is an artificial intelligence system that uses machine learning techniques to learn patterns and relationships from large amounts of data and generate new information.

[0605] "Disaster information" refers to all data related to natural disasters, such as the current situation, forecasts, impacts, evacuation sites, and support information.

[0606] "User inquiries" refer to the act of a user sending information or questions that the user requests the system to provide via a communication means.

[0607] "Automatic background data updates" is a function that allows the system to collect new information periodically or under certain conditions, regardless of user operations, and keep the internal database up to date.

[0608] A "Communications Outage" is a temporary or permanent outage of the Internet or other communications network.

[0609] "Existing data" refers to information that the system has collected and stored in the past, and is data that is used in situations where it is difficult to obtain the latest information.

[0610] "Near-field wireless communication" is a technology that transmits and receives data wirelessly over short distances, such as Bluetooth and Wi-Fi Direct.

[0611] "Means of collection and analysis" refers to methods of obtaining disaster information from various sources, analyzing its relevance and importance, and deriving useful information.

[0612] The "means for providing" refers to a means for displaying, notifying, or transmitting the analyzed information to the user.

[0613] "Means for returning" refers to the process of returning the analysis results and necessary information to the user terminal via communication.

[0614] The system of the present invention consists of a server, a terminal, and a user. The server has the function of collecting and analyzing disaster information using a generative AI model and generating optimal answers to user inquiries. Users can use this system through their terminals. Specific embodiments are described below.

[0615] Server Features

[0616] The server is equipped with a generative AI model and has the ability to collect and analyze disaster information. The server receives inquiries from users and passes the details to the generative AI model. The generative AI model analyzes data collected from government agencies, media, and social media, and generates optimal answers. The server also periodically collects new disaster information and automatically updates the database in the background. For example, an API can be implemented using Python's Flask to call a generative AI model (e.g., GPT-4).

[0617] Device Features

[0618] The device has the function of sending user inquiries to the server and displaying information from the server to the user. When a user launches the app and types, for example, "Where is the nearest evacuation shelter?", the inquiry is sent from the device to the server. The information received from the server is displayed on the device screen. The device also has the function of receiving new data from the server via push notifications and storing it locally in the background. Furthermore, in the event of a communication failure, the device can use the stored data to provide information to other devices via short-range wireless communication (such as Bluetooth or Wi-Fi Direct).

[0619] User operations

[0620] The user launches the app and enters the necessary information into a text box. For example, "Where is the nearest evacuation shelter?" The input is sent to the server via the device. The server analyzes the information using a generative AI model and generates a response, such as "The nearest evacuation shelter is XX Elementary School, and the route is YYY," which is sent back to the device. The device then displays this information to the user, who can then take appropriate action based on that information.

[0621] Specific examples

[0622] In the event of a major earthquake, the user opens the app and asks, "Where is the nearest evacuation shelter?" The device sends this query to the server. The server uses a generative AI model to analyze the latest evacuation shelter information and generates the answer, "The nearest evacuation shelter is XX Park, 1 km away." This information is sent to the device and displayed to the user.

[0623] An example of a prompt to input to a generative AI model is as follows:

[0624] "Please tell me information about the nearest evacuation shelter based on the current disaster situation."

[0625] As described above, the system of the present invention provides rapid and accurate information during disasters and enables information sharing even during communication disruptions, allowing victims and related parties to quickly obtain the necessary information and take safe action.

[0626] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0627] Step 1:

[0628] User asks for information

[0629] The user launches the app and types "Where is the nearest shelter?" This is entered into the device as string data. The entered data is internally converted into a structured request object. This request object contains the key "query" and the query string "Where is the nearest shelter?".

[0630] Step 2:

[0631] The device sends a request to the server

[0632] The terminal receives the generated request object and sends it to the server as an HTTP request. Specifically, it uses the HTTP POST method to send a request to the endpoint URL. The input is the user's question, which is sent to the server as an HTTP request. The output is the process by which the request is sent.

[0633] Step 3:

[0634] The server receives the query

[0635] The server analyzes the HTTP request received from the device and passes the content to the generative AI model. The input is the HTTP request, and the content is analyzed and input to the generative AI model as a prompt. The output is the prompt sent to the generative AI model.

[0636] Step 4:

[0637] Generative AI models generate information

[0638] The generative AI model receives a prompt, collates and analyzes information from an accumulated database and external sources, and generates the optimal answer. The input is the prompt, and data processing and calculations are performed to combine information from the database. The output is the generated answer text.

[0639] Step 5:

[0640] The server generates a response and sends it back to the device.

[0641] The server returns the answer obtained from the generative AI model to the device as an HTTP response. The input is the answer text from the generative AI model, which is structured as an HTTP response. The output is the response text sent to the device.

[0642] Step 6:

[0643] The device receives the information and displays it to the user.

[0644] The terminal analyzes the response received from the server and displays it to the user. The input is the response from the server, and data processing is performed to convert it into a displayable format. The output is the information displayed on the user's screen. The user can take appropriate action based on the displayed information.

[0645] Step 7:

[0646] The server collects and updates new information in the background

[0647] The server periodically collects new disaster information from government agencies, media, and social media, and automatically updates the database. The input is new information from external sources, and data calculations are performed to add or update this information to the database. The output is the updated database.

[0648] Step 8:

[0649] Your device updates data in the background

[0650] The server sends new information to the device via push notification. The device updates the received data in the background and stores it locally. The input is notification data from the server, and data calculations are performed to update the device's local storage or database. The output is the latest disaster information stored on the device.

[0651] Step 9:

[0652] Devices use existing data in the event of a communication failure

[0653] The device periodically checks the Internet connection and detects communication disruptions. If a communication disruption occurs, the device accesses the latest data stored in the background and displays that information to the user. In addition, it provides information to other devices using short-range wireless communication (such as Bluetooth or Wi-Fi Direct). The input is the existing data and the results of the communication status check, and the output is the information displayed to the user and the information sent to other devices.

[0654] This is the specific processing flow of the program for this system. This makes it possible to provide fast and accurate information in the event of a disaster, and to share highly reliable information even in the event of a communication failure.

[0655] (Application example 1)

[0656] 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."

[0657] Challenges in providing fast and accurate information during disasters include the problem of information sharing when communication failures occur and the inability to provide appropriate responses to user inquiries. Furthermore, security staff and guards working on-site have limited means of obtaining the latest information in real time and taking appropriate action. There is a need for a system that can solve these issues and enable users to instantly obtain the information they need in an emergency and take action.

[0658] 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.

[0659] In this invention, the server includes means for collecting and analyzing disaster information using a generation AI, means for receiving inquiries from users and providing relevant disaster information, and means for automatically updating data in the background, thereby enabling users to obtain disaster information in real time.

[0660] It also includes a means for using existing data to perform short-range wireless communication in the event of a communication failure, a means for the generation AI to provide analysis results in response to inquiries entered by voice from the user when communication is possible, and a means for displaying disaster information in real time on the smart device. This allows information sharing to continue even in the event of a communication failure, and enables users to quickly obtain information from the generation AI through voice input and easily check that information on their smart device.

[0661] "Generative AI" is a type of artificial intelligence technology that automatically generates new information and answers based on collected data.

[0662] "Disaster information" refers to detailed data on the location, scale, extent of impact, evacuation sites, and other information related to natural and man-made disasters.

[0663] A "user query" is a question or request made by a user to the system for specific information.

[0664] "Means for automatically updating data in the background" refers to a function that allows the system to periodically obtain the latest information from the server and update the local database, regardless of user ingress.

[0665] "Communications Outage" means a condition in which the Internet connection is unstable or unavailable.

[0666] "Near field communication" is a method of exchanging data between nearby devices using short-range communication technologies such as Bluetooth and Wi-Fi Direct.

[0667] "Voice input" is a method in which a user gives instructions or queries to a system using voice.

[0668] "Smart devices" refer to electronic devices that can connect to the Internet and have advanced processing capabilities, such as smartphones and smart glasses.

[0669] "Display in real time" means that the acquired information is displayed immediately on the screen of the user's device.

[0670] "Means for summarizing analysis results" is a function that analyzes the information collected by the generation AI and provides it in a concise format that is easy for users to understand.

[0671] "Push notification" is a function that allows a server to automatically send new information to a user's device in real time.

[0672] The system of the present invention uses generative AI to collect and analyze information in order to provide users with fast and accurate information during disasters, and has the ability to share information via short-range wireless communication even in the event of communication failure.

[0673] System configuration

[0674] This system mainly consists of a server, a terminal, and a user. The server is equipped with a generation AI and is responsible for collecting and analyzing disaster information. The terminal also sends inquiries from users to the server and displays the information received from the server to the user. Users access the system through their terminal and obtain the information they need.

[0675] Server Features

[0676] The server periodically collects new disaster information from government agencies, the media, social media, etc., and analyzes the data using a generation AI. Based on the collected data, the generation AI generates the optimal answer to a user's inquiry. For example, in response to the inquiry "Where is the nearest evacuation shelter?", the generation AI will respond with "Currently, the nearest evacuation shelter is XX Park."

[0677] Device Features

[0678] The device sends user inquiries to the server, receives responses from the server, and displays them to the user. The device also has the ability to receive updated data from the server in the background and store the latest data locally. In the event of a communication failure, the device uses the latest data stored in the background and provides information to other devices via short-range wireless communication (such as Bluetooth or Wi-Fi Direct).

[0679] User operations

[0680] The user uses a smart device (such as a smartphone or smart glasses) to launch the app and request information. If the device is capable of communication, the generation AI will provide analysis results based on the user's voice or text input. For example, if the user voice-inputs, "Please tell me where the evacuation shelters are," the device will display the information analyzed by the generation AI.

[0681] Specific examples

[0682] For example, if a large-scale earthquake occurs, a user puts on smart glasses and asks, "Where is the nearest evacuation shelter?" This request is sent from the device to the server. The server uses generative AI to collect the latest evacuation shelter information from government agencies and the media, and generates a response such as, "The nearest evacuation shelter is XX Park, 1 km away." This information is sent to the device and displayed to the user on the smart glasses' display.

[0683] Furthermore, if the communication network is down, the device will transmit the latest evacuation shelter data stored in the background to other nearby devices via Bluetooth, allowing users to share necessary information even during communication disruptions.

[0684] Prompt Sentence Examples

[0685] "User: An earthquake has occurred. Where is the nearest safe haven?"

[0686] "Generator AI: Understood. Currently, the closest evacuation shelter is XX Park. It's about a 5-minute walk away. Please avoid collapsible buildings when evacuating."

[0687] The above is a specific example of how the system of the present invention provides information during a disaster. This system uses a generative AI model and prompts to provide optimal information to users, and is designed to enable continued information sharing even during communication disruptions.

[0688] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0689] Step 1:

[0690] User asks for information

[0691] Input: A user uses a smart device (smart glasses or smartphone), launches the app, and asks verbally, "Where is the nearest evacuation shelter?"

[0692] Data processing: The device converts the voice input into text and generates an HTTP request to send to the server.

[0693] Output: Text after audio data conversion and data in HTTP request format are generated.

[0694] What it does: It accepts voice input, converts it to text using speech recognition technology, packages this text data into an HTTP request, and sends it to the server.

[0695] Step 2:

[0696] The server generates the information

[0697] Input: HTTP request sent from the device (text data: "Where is the nearest evacuation shelter?").

[0698] Data calculation: Generative AI analyzes data collected from government agencies and the media to generate optimal answers.

[0699] Output: Generated answer text ("The nearest shelter is XX Park").

[0700] Operation: The server passes the query to the generation AI, which then analyzes and generates the most appropriate evacuation shelter information while checking various databases, and returns the answer text to the terminal.

[0701] Step 3:

[0702] The device displays the information

[0703] Input: Answer text received from the server ("The nearest shelter is XX Park").

[0704] Data processing: Format the received text data in a way that is compatible with the display format of the smart device.

[0705] Output: Information shown on the display of the user's smart device (smart glasses or smartphone).

[0706] Operation: Receives response data from the server, formats it into text for display, and displays it on the smart device's display.

[0707] Step 4:

[0708] The server collects new information

[0709] Input: A trigger based on a recurring schedule.

[0710] Data calculation: Collect the latest disaster information from government agencies, media, social media, etc. and update the database.

[0711] Output: Updated disaster information database.

[0712] How it works: The server periodically collects data from external sources, analyzes and categorizes the data using generative AI, and updates the disaster information database.

[0713] Step 5:

[0714] The device updates the data

[0715] Input: Push notification from the server (new disaster information).

[0716] Data processing: Received data is saved in a local database.

[0717] Output: The updated local database.

[0718] How it works: The device receives push notifications in the background and stores the latest data in a local database.

[0719] Step 6:

[0720] Response in the event of a communication failure

[0721] Input: Communication failure detected (unreliable internet connection).

[0722] Data processing: Refer to existing local databases and extract the necessary data.

[0723] Output: Referenced data (e.g., shelter information).

[0724] Operation: The device periodically checks its internet connection and, if it detects a communication failure, continues to operate using data stored in the background.

[0725] Step 7:

[0726] Information sharing via short-range wireless communication

[0727] Input: Other devices nearby.

[0728] Data calculation: Send data using Bluetooth or Wi-Fi Direct.

[0729] Output: Data sent to other nearby devices.

[0730] How it works: The device sends information to other devices via short-range wireless communication, making it available to the user.

[0731] The above are the specific processing steps of the system.

[0732] 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.

[0733] The present invention is a system that uses generative AI to provide accurate and prompt information when a disaster occurs, and combines it with an emotion engine that recognizes the user's emotions to provide more appropriate support. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described below.

[0734] System Overview

[0735] 1. Server Functions

[0736] The server is equipped with a generative AI and emotion engine, and has the ability to collect and analyze disaster information.

[0737] The server receives inquiries from users and uses generation AI to generate optimal answers, analyzing the user's emotions with an emotion engine and adjusting the information provided.

[0738] The server regularly collects new disaster information from government agencies, media, and social media, and updates the data in the background.

[0739] 2. Device Features

[0740] The terminal has the function of sending inquiries from the user to the server.

[0741] The terminal displays the information received from the server to the user, and also displays additional support information based on the user's emotions.

[0742] The device receives updated data from the server in the background and saves the latest data.

[0743] In the event of a communication outage, the device will use data stored in the background to provide information to other devices via short-range wireless communication.

[0744] 3. User Operation

[0745] Users launch the app and ask for the information they need, and emotional input can be automatically analyzed using voice, text, or facial recognition.

[0746] The user's emotions are analyzed and support information is provided accordingly.

[0747] Program processing explanation

[0748] Processing requests and providing information

[0749] User asks for information

[0750] The user launches the app and types, "Please tell me the location of the evacuation shelter." The device sends the user's input along with emotion data analyzed by the emotion engine to the server.

[0751] The server generates the information

[0752] The server analyzes the received request and emotional data. The generation AI collects data from government agencies, media, and social media, and generates the analysis results. The emotion engine analyzes the user's emotions and passes the results to the generation AI, which then adjusts the information provided to suit the user's situation and emotions.

[0753] For example, if the emotion engine analyzes that the user is in a state of panic, the generative AI will provide information such as, "Currently, the nearest evacuation shelter is XX Elementary School. Please remain calm and evacuate. We will provide telephone support if necessary."

[0754] The device displays the information

[0755] The device analyzes the information received from the server and displays it to the user. In addition to the usual evacuation shelter information, it also provides additional support information based on the user's emotions.

[0756] Background data updates

[0757] The server collects new information

[0758] The server regularly collects the latest disaster information from government agencies, the media, and social media, analyzes it using generative AI, and updates the database.

[0759] The device updates the data

[0760] The server sends new information to the device via push notification, and the device updates the data in the background.

[0761] Response in the event of a communication failure

[0762] The device detects a communication failure

[0763] The device periodically checks the internet connection and detects communication disruptions.

[0764] The device uses existing data

[0765] In the event of a communication failure, the device will access the latest data stored in the background. Information will be provided to other users' devices using short-range wireless communication (Bluetooth, Wi-Fi Direct, etc.). For example, even if a communication failure occurs, a device can provide information such as "The nearest evacuation shelter is XX Elementary School" to other users' devices nearby.

[0766] As described above, by combining generative AI and an emotion engine, the system of the present invention can improve the accuracy and speed of information during disasters and provide support that responds to the user's emotions. This allows victims and those involved to quickly and appropriately obtain the information they need and take safe action.

[0767] The processing flow will be explained below.

[0768] Program processing

[0769] Processing requests and providing information

[0770] User asks for information

[0771] Step 1:

[0772] The user launches the app and types, "Please tell me where the evacuation shelter is."

[0773] Step 2:

[0774] The device receives user input and activates the emotion engine, collecting user emotion data through methods such as voice, text, and facial recognition.

[0775] Step 3:

[0776] The device sends the user's input and emotional data to the server as an HTTP request.

[0777] The server generates the information

[0778] Step 4:

[0779] The server analyzes the request content and emotion data received from the device.

[0780] Step 5:

[0781] The server passes the request content and emotion data to the generated AI, which then collects and analyzes related disaster information.

[0782] Step 6:

[0783] The generative AI collects data from government agencies, media, and social media, and generates analytical results.

[0784] Step 7:

[0785] The emotion engine feeds the results of the user's emotion analysis back to the generation AI, which then adjusts the information provided.

[0786] Step 8:

[0787] The server generates information such as "Currently, the nearest evacuation shelter is XX Elementary School, and the route is YYY."

[0788] Step 9:

[0789] The server sends the generated answer to the terminal as an HTTP response.

[0790] The device displays the information

[0791] Step 10:

[0792] The terminal analyzes the response data received from the server.

[0793] Step 11:

[0794] The device displays the analysis results to the user, for example, "The nearest evacuation shelter is XX Elementary School" and additional information such as "Please remain calm and evacuate. We will provide telephone support if necessary."

[0795] Background data updates

[0796] The server collects new information

[0797] Step 1:

[0798] The server regularly collects new disaster information from government agencies, media, and social media.

[0799] Step 2:

[0800] The server analyzes the collected information and updates the database using generative AI.

[0801] The device updates the data

[0802] Step 3:

[0803] The server sends new information to the device via push notification.

[0804] Step 4:

[0805] The device receives the push notification in the background and saves the new data to local storage.

[0806] Response in the event of a communication failure

[0807] The device detects a communication failure

[0808] Step 1:

[0809] The device periodically checks the Internet connection to detect whether any communication problems have occurred.

[0810] The device uses existing data

[0811] Step 2:

[0812] When a device detects a communication failure, it accesses the latest data stored in the background.

[0813] Step 3:

[0814] The device uses short-range wireless communication (Bluetooth, Wi-Fi Direct, etc.) to send necessary information to other users' devices nearby.

[0815] Step 4:

[0816] The information received by other users' devices is analyzed and displayed to the user. For example, it displays, "Even during a communication outage, the nearest evacuation shelter is XX Elementary School."

[0817] Example 2

[0818] 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."

[0819] Conventional disaster information systems are required to provide prompt and accurate information in response to user inquiries, but they lack support that takes into account the user's emotional state. Furthermore, effective information provision methods during communication disruptions are limited, making it difficult to provide useful information to users during disasters. Therefore, the objective of this invention is to provide a disaster information provision system that utilizes generative AI and emotion recognition technology to provide appropriate information according to the user's emotional state and that has effective information provision methods even during communication disruptions.

[0820] 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.

[0821] In this invention, the server includes means for collecting and analyzing disaster information using a generation AI, means for receiving inquiries from users and providing relevant disaster information, means for automatically updating data in the background, means for using existing data to perform short-range wireless communication during communication disruptions, and means for analyzing the user's emotions using an emotion recognition engine and adjusting the information provided by the generation AI. This enables prompt and accurate information provision even during disasters, and provides support tailored to the user's emotional state. As a result, disaster victims and their relatives can quickly and appropriately obtain the information they need and take safe action.

[0822] "Generative AI" is a system that uses artificial intelligence technology to collect and analyze data and generate optimal information in response to user requests.

[0823] "Disaster information" refers to various information related to disasters, such as the occurrence and progression of the disaster, the extent of the impact, and the location of evacuation shelters.

[0824] A "user inquiry" is an input made by a user to the system to request specific information or assistance, and may be in the form of text, voice, image, or the like.

[0825] "Automatically updating data in the background" means that the system has the function of periodically collecting the latest data and updating the database without requiring user operation.

[0826] "Communication failure" refers to a network malfunction or disruption that occurs when a system sends or receives data via the Internet or other means of communication.

[0827] "Existing data" refers to information that has been stored in the system in advance and is available even in the event of a communication failure.

[0828] "Near field wireless communication" refers to technologies such as Wi-Fi Direct and Bluetooth that enable data communication between devices over short distances.

[0829] An "emotion recognition engine" refers to a technology or system that analyzes emotions from a user's voice, text, facial expressions, etc., and determines the user's emotional state.

[0830] "Providing appropriate information" means providing information in a form that best suits the user's situation and emotional state, with the aim of improving the user's sense of security and appropriateness of behavior.

[0831] The present invention is a system that uses a generative AI model to provide accurate and prompt information when a disaster occurs, and combines it with an emotion recognition engine that recognizes user emotions to provide more appropriate support. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described in detail below.

[0832] System configuration

[0833] This system mainly consists of the following hardware and software components.

[0834] 1. Server

[0835] It is equipped with a generative AI model and has the ability to collect and analyze disaster information.

[0836] It is equipped with an emotion recognition engine that analyzes the user's emotions.

[0837] Regularly collect data from government agencies, media, and social networking services to update the database.

[0838] If communication is normal, the latest disaster information will be sent to the user's device via push notification.

[0839] 2. Terminal

[0840] It has the function of sending user inquiries to the server.

[0841] It has the function of displaying information received from the server to the user.

[0842] Data is updated in the background, and in the event of a communication failure, short-range wireless communication is performed using existing data.

[0843] 3. Users

[0844] Use a device such as a smartphone or tablet to inquire about the information you need.

[0845] Take appropriate action based on the information inquired.

[0846] Program processing explanation

[0847] The server receives inquiries from users and analyzes them using a generative AI model. It also analyzes the user's emotions using an emotion recognition engine and adjusts the information provided. The generative AI model is trained using a large dataset, allowing it to provide the latest information in real time. The specific processing flow is as follows:

[0848] 1. User operations

[0849] The user launches the app and asks for the required information by voice or text, for example, by entering a prompt such as "Please tell me the location of the evacuation shelter."

[0850] 2. Terminal Processing

[0851] The device converts the user's inquiry into text and uses an emotion recognition engine to analyze emotional data from the user's voice and facial expressions.

[0852] The analyzed data and the user's query are sent to the server.

[0853] 3. Server Processing

[0854] The server uses a generative AI model based on the received data to analyze the user's query and collect and compile the necessary disaster information.

[0855] The emotional state of the user is analyzed again using an emotion recognition engine, and the generated information is provided to the user in an optimal form.

[0856] For example, if the user is in a panic, a message such as "The nearest evacuation shelter is currently XX Elementary School. Please remain calm and evacuate" is generated.

[0857] 4. Display by terminal

[0858] The information received from the server is displayed to the user, and necessary support information is provided.

[0859] Examples of concrete examples and prompts

[0860] Specific examples

[0861] The user launches a smartphone app and speaks, "Is there a safe place nearby?"

[0862] The device converts the voice data into text and uses an emotion recognition engine to analyze whether the user is in a state of agitation.

[0863] The server analyzes the query using a generative AI model and generates information about the nearest evacuation shelter and a message such as "Please remain calm and evacuate."

[0864] The device displays this to the user, providing necessary information and a sense of security.

[0865] Prompt Sentence Examples

[0866] 1. "Please tell me where the evacuation shelter is."

[0867] 2. "Is there a safe place nearby?"

[0868] 3. "Can you give me an update on the current situation?"

[0869] As described above, by combining a generative AI model and an emotion recognition engine, the system of the present invention can provide prompt and accurate information during disasters and provide appropriate support according to the user's emotional state. This allows disaster victims and those involved to quickly and appropriately obtain the necessary information and take safe action.

[0870] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0871] System program processing flow

[0872] Step 1: User Enters Information

[0873] The user launches the app and speaks, "Please tell me the location of the evacuation shelter." This voice input is sent to the device and converted to text on the spot. The converted text becomes the input data for the information query.

[0874] Input: Audio input

[0875] Output: The query converted to text

[0876] Step 2: The device analyzes and transmits the emotion data.

[0877] The device analyzes the user's voice and facial expressions using an emotion recognition engine to generate emotional data about the user. The specific emotional state (e.g., panic, calm, etc.) is analyzed and sent to the server along with a text query.

[0878] Input: Text-converted query, user voice and facial expression data

[0879] Output: Parsed emotion data, sent to the server along with the query

[0880] Step 3: The server parses the information

[0881] The server uses a generative AI model to collect and analyze the necessary disaster information based on the received inquiry and emotion data. Specifically, it collects the latest disaster information from government agencies, media, and social media, and generates information appropriate for the user's inquiry.

[0882] Input: Text-converted query, emotion data

[0883] Output: Disaster information in response to user inquiries

[0884] Step 4: The server adjusts the information based on the emotion data

[0885] The server adjusts the disaster information it generates based on the user's emotional data analyzed by an emotion recognition engine. For example, if the user is in a panic, it generates information containing a message that gives a sense of security.

[0886] Input: Disaster information and emotion data in response to user inquiries

[0887] Output: Emotionally sensitive information

[0888] Step 5: The server sends the information to the device

[0889] The server then sends the adjusted disaster information to the terminal. Communication is performed using secure protocols such as SSL / TLS.

[0890] Input: Emotionally sensitive information

[0891] Output: Data sent to the terminal

[0892] Step 6: The device displays the information to the user

[0893] The device analyzes the information it receives and displays it in an optimal way for the user, including the location of evacuation shelters and sensitive messages.

[0894] Input: Adjusted information sent from the server

[0895] Output: The final information displayed to the user

[0896] Specific examples of operation

[0897] Step 1: User Enters Information

[0898] The user opens the app on their smartphone and says, "Tell me where the nearest safe place is." The speech is converted into text in real time and displayed on the device.

[0899] Step 2: The device analyzes and transmits the emotion data.

[0900] The device uses an emotion recognition engine to analyze the user's tone of voice and facial expressions to determine their emotional state. For example, the device sends a text query along with the analyzed emotional state, such as "anxiety," to the server.

[0901] Step 3: The server parses the information

[0902] Based on the received data, the server uses a generative AI model to collect and analyze the latest disaster information, including "nearby evacuation shelters." The information is extracted from the database and a list of the nearest currently available evacuation shelters is generated.

[0903] Step 4: The server adjusts the information based on the emotion data

[0904] The server takes into account the results of the emotion recognition engine and adjusts the information to suit a user in a state of panic. Specifically, it generates information containing a reassuring message such as, "XX Elementary School is the nearest evacuation shelter. Please remain calm and evacuate."

[0905] Step 5: The server sends the information to the device

[0906] The server sends the tailored information to the device, including a map of the evacuation center, its address, and a reassuring message.

[0907] Step 6: The device displays the information to the user

[0908] The device displays the received information to the user, who can then check the map on the app screen along with a message saying, "XX Elementary School is the nearest evacuation shelter. Please remain calm and evacuate."

[0909] Through the above processing, this system can provide appropriate information according to the user's emotional state and support safe behavior in the event of a disaster.

[0910] (Application example 2)

[0911] 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."

[0912] Existing disaster information systems struggle to provide accurate and timely information during disasters, and also to provide appropriate support that takes into account the user's emotions. It is particularly difficult to continue providing appropriate information when communication failures occur. Furthermore, there is a lack of methods to reduce the stress and anxiety users feel during disasters and encourage effective evacuation behavior.

[0913] 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 means for collecting and analyzing disaster information using a generation AI, means for receiving inquiries from users and providing corresponding disaster information, means for automatically updating data in the background, means for performing short-range wireless communication using existing data in the event of a communication failure, and means for analyzing the user's emotions using emotion recognition technology and adjusting the information to be provided based on the results. This makes it possible to provide accurate and prompt information even during a disaster and provide appropriate support according to the user's emotions.

[0914] "Generative AI" is an artificial intelligence technology that automatically generates information based on input data.

[0915] "Disaster information" refers to various information related to natural and man-made disasters, including the location of evacuation shelters, damage status, and first aid information.

[0916] "Analysis" is the process of breaking down and analyzing collected data to extract useful information.

[0917] "User" means any person or entity that uses the System.

[0918] An "inquiry" refers to a question or request made by a user to the system for information or assistance.

[0919] "Automatically updating data in the background" is a function that allows the system to automatically obtain and store the latest information even when the user is not operating the system.

[0920] "Communication outage" refers to a situation in which the Internet or other means of communication do not function properly.

[0921] "Existing Data" refers to data that has previously been collected and stored by the system.

[0922] "Near field wireless communication" refers to exchanging data using short-range wireless communication technologies such as Bluetooth and Wi-Fi Direct.

[0923] "Emotion recognition technology" is a technology that determines a user's emotions from the tone of their voice, facial expression, text content, etc.

[0924] The present invention is a system that uses generative AI and emotion recognition technology to provide accurate and prompt information in the event of a disaster, and provides appropriate support according to the user's emotions. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described below.

[0925] System Overview

[0926] 1. Server Functions

[0927] The server is equipped with generative AI and emotion recognition technology, and has the ability to collect and analyze disaster information, allowing it to retain accurate and up-to-date information and generate information in response to user inquiries.

[0928] The server receives inquiries from users and uses generative AI to generate the optimal answer. It also uses emotion recognition technology to analyze the user's emotions and adjust the information provided accordingly. For example, if the user is in a panic, it will provide information that includes reassuring words.

[0929] The server periodically collects new disaster information from government agencies, the media, social media, etc. and updates the data in the background, ensuring that users are always provided with the latest information.

[0930] 2. Device Features

[0931] The devices include smartphones, tablets, robots, etc., and have the ability to send inquiries from users to a server. Questions can be sent via voice input or text input.

[0932] The device receives the information from the server and displays it to the user. The displayed information is adjusted based on the user's emotions, providing more personalized assistance.

[0933] The device has the ability to receive updated data from the server in the background and store the latest data. Even if communication is interrupted, the stored data can be used to provide information to other devices via short-range wireless communication (Bluetooth, Wi-Fi Direct, etc.).

[0934] 3. User Operation

[0935] The user launches the application installed on the device and requests the necessary information. Inquiries are made via voice, text, facial recognition, etc. Emotions are automatically analyzed and appropriate support information is provided.

[0936] For example, if a user makes a voice inquiry such as "Please tell me where the evacuation shelter is," the device sends the voice to the server, which then uses emotion recognition technology to analyze the user's state. Based on the results, the AI ​​generates information such as "Currently, the nearest evacuation shelter is XX Elementary School. Please remain calm and evacuate. We will provide telephone support if necessary," and sends it to the device.

[0937] Hardware and software used

[0938] Hardware:

[0939] Camera: Used to capture facial images and recognize emotions. Use the built-in camera on your smartphone or robot.

[0940] Smartphone / Tablet / Robot: The primary device on which the application runs.

[0941] software:

[0942] OpenCV: A library for face recognition and image processing.

[0943] TensorFlow / Keras: Machine learning frameworks for running emotion recognition models.

[0944] Transformers (Hugging Face): A library that generates text using generative AI (GPT-2).

[0945] Requests: A library for retrieving data from the disaster information API.

[0946] Specific examples

[0947] Scenario: When a disaster occurs, a user looks into their smartphone camera and asks, "Where is the evacuation shelter?"

[0948] Example prompt: "User is feeling Fear. Provide the most relevant disaster information: Nearest shelter is at XX school. Please stay calm. We can provide phone support if needed."

[0949] Example response generated: "The nearest evacuation shelter is XX Elementary School. Please remain calm. Telephone assistance will be provided if necessary."

[0950] As described above, by combining generative AI and emotion recognition technology, the system of the present invention can improve the accuracy and speed of information during disasters, and can also provide support that is tailored to the user's emotions.

[0951] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0952] Step 1:

[0953] The server automatically collects and analyzes disaster information from government agencies, media, social media, etc. It collects new disaster information as input and analyzes it using a generative AI model. The analyzed data is stored in a database and is ready for user inquiries.

[0954] Step 2:

[0955] The user activates the device's camera function and has their face recognized. The user's facial image is provided as input, and the device detects the face using OpenCV and inputs the facial image into an emotion recognition model. Emotion recognition technology (TensorFlow / Keras) analyzes the user's emotion as "panic," "fear," etc. The output is the user's emotion data.

[0956] Step 3:

[0957] The user asks the terminal a question by voice, such as "Where is the evacuation shelter?" This voice data is input into the terminal and converted into text. The converted question content and emotion data are sent to the server.

[0958] Step 4:

[0959] The server generates an optimal response based on the received question content and emotion data. The question content and emotion data are provided as input, and an appropriate answer is generated using a generative AI model (Transformers). For example, a response such as "The nearest evacuation shelter is XX Elementary School. Please remain calm. We will provide telephone support if necessary" is generated. The output is response data to be sent back to the user.

[0960] Step 5:

[0961] The terminal receives the response data from the server and displays it to the user. The terminal receives the response data from the server as input and displays it on the screen. This gives the user information about the nearest evacuation shelter and a message encouraging reassurance.

[0962] Step 6:

[0963] The server periodically updates data in the background to maintain the latest disaster information. It receives new disaster information as input, analyzes it with the generative AI model, and updates the database. This ensures that the latest information is always available to users.

[0964] Step 7:

[0965] In the event of a communication failure, the device will use the latest data stored in the background to communicate with other devices in the vicinity via short-range wireless communication (Bluetooth, Wi-Fi Direct, etc.) using the communication failure detection signal as input. This allows important information to be shared even when an internet connection is unavailable.

[0966] 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.

[0967] 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.

[0968] 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.

[0969] [Third embodiment]

[0970] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0971] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0972] 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).

[0973] 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.

[0974] 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.

[0975] 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).

[0976] 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.

[0977] 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.

[0978] 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.

[0979] 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.

[0980] 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.

[0981] 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."

[0982] The present invention is a system that uses generative AI to provide accurate and prompt information in the event of a disaster, and shares information via short-range wireless communication in the event of a communication failure. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described below.

[0983] System Overview

[0984] 1. Server Functions

[0985] The server is equipped with a generation AI and has the ability to collect and analyze disaster information.

[0986] The server receives inquiries from users, uses a generation AI to generate optimal answers, and returns these to the terminal.

[0987] The server regularly collects new disaster information from government agencies, media, and social media, and updates the data in the background.

[0988] 2. Device Features

[0989] The terminal has the function of sending inquiries from the user to the server.

[0990] The terminal displays the information received from the server to the user.

[0991] The device receives updated data from the server in the background and saves the latest data.

[0992] In the event of a communication outage, the device will use data stored in the background to provide information to other devices via short-range wireless communication.

[0993] 3. User Operation

[0994] The user launches the app and queries for the required information.

[0995] Based on the questions the user enters, the system provides the necessary information.

[0996] Program processing explanation

[0997] Processing requests and providing information

[0998] User asks for information

[0999] The user launches the app and types, for example, "Please tell me where the evacuation shelter is."

[1000] The terminal receives the user's input and sends it to the server as an HTTP request.

[1001] The server generates the information

[1002] The server receives the request and passes the contents to the generation AI.

[1003] The generative AI analyzes data collected from government agencies, media, and social media to generate optimal answers.

[1004] For example, the generation AI returns information such as, "Currently, the nearest evacuation shelter is XX Elementary School, and the route is YYY."

[1005] The device displays the information

[1006] The terminal analyzes the information received from the server and displays it to the user.

[1007] The user can refer to the displayed information and take appropriate action.

[1008] Background data updates

[1009] The server collects new information

[1010] The server regularly collects new disaster information from government agencies, media, and social media.

[1011] The server analyzes the collected information and updates the database.

[1012] The device updates the data

[1013] The server sends new information to the device via push notification.

[1014] The device updates the latest data received in the background and stores it locally.

[1015] Response in the event of a communication failure

[1016] The device detects a communication failure

[1017] The device periodically checks the internet connection and detects any communication disruptions.

[1018] The device uses existing data

[1019] If a communication failure occurs, the device will access the latest data stored in the background.

[1020] The device sends the necessary information to other devices via short-range wireless communication (such as Bluetooth or Wi-Fi Direct).

[1021] The other terminal displays the received information to the user.

[1022] Specific examples

[1023] For example, consider the occurrence of a large-scale earthquake. A user opens the app and asks, "Where is the nearest evacuation shelter?" This request is sent from the device to the server. The server uses generative AI to collect the latest evacuation shelter information from government agencies and the media, and generates a response such as, "The nearest evacuation shelter is XX Park, 1 km away." This information is sent to the device and displayed to the user.

[1024] Furthermore, if the communication network is down, the device will use the latest evacuation shelter data in the background and send that information to other nearby devices via Bluetooth, allowing users to share necessary information even during communication disruptions.

[1025] As described above, the system of the present invention provides accurate and prompt information during disasters and enables information sharing even during communication disruptions, enabling victims and related parties to obtain necessary information with minimal effort and take safe action.

[1026] The processing flow will be explained below.

[1027] Program processing

[1028] Processing requests and providing information

[1029] User asks for information

[1030] Step 1:

[1031] The user launches the app and enters information. For example, they might enter, "Please tell me where the evacuation shelter is."

[1032] Step 2:

[1033] The terminal constructs the user's input as an HTTP request and sends it to the server.

[1034] The server generates the information

[1035] Step 3:

[1036] The server analyzes the request received from the terminal.

[1037] Step 4:

[1038] The server passes the request content to the generation AI and collects relevant information.

[1039] Step 5:

[1040] Generative AI collects and analyzes data from government agencies, media, and social media.

[1041] Step 6:

[1042] Based on the data collected, the generative AI generates the optimal answer to the user's request. For example, it generates information such as, "The nearest evacuation shelter is currently XX Elementary School, and the route is YYY."

[1043] Step 7:

[1044] The server constructs the generated answer as an HTTP response and sends it to the terminal.

[1045] The device displays the information

[1046] Step 8:

[1047] The terminal analyzes the response data received from the server.

[1048] Step 9:

[1049] The device displays the analysis results to the user, for example, "The nearest evacuation shelter is XX Elementary School."

[1050] Background data updates

[1051] The server collects new information

[1052] Step 1:

[1053] The server regularly collects new disaster information from government agencies, media, and social media.

[1054] Step 2:

[1055] The server analyzes the collected information and updates the database through a generative AI.

[1056] The device updates the data

[1057] Step 3:

[1058] The server sends new information to the device via push notification.

[1059] Step 4:

[1060] The device receives a push notification and saves the new data to local storage in the background.

[1061] Response in the event of a communication failure

[1062] The device detects a communication failure

[1063] Step 1:

[1064] The device periodically checks the internet connection to detect if there are any communication disruptions.

[1065] The device uses existing data

[1066] Step 2:

[1067] The device that detects the communication failure accesses the latest data stored in the background.

[1068] Step 3:

[1069] The device uses short-range wireless communication (such as Bluetooth or Wi-Fi Direct) to send the necessary information to other users' devices nearby.

[1070] Step 4:

[1071] The other user's device analyzes the received information and displays it to the user, for example, "The latest evacuation shelter is XX Elementary School."

[1072] Example 1

[1073] 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."

[1074] When a natural disaster occurs, it is important to provide accurate information quickly and in real time. However, conventional information provision systems have limitations in the speed and accuracy of information collection, making it difficult to provide information, especially when communication failures occur. In addition, when integrating necessary information from multiple sources and providing it to users, the organization and analysis of the information is often inefficient. There is a need for a system that can provide highly reliable information even in situations where the communication environment is unstable.

[1075] 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.

[1076] In this invention, the server includes means for collecting and analyzing disaster information using a generative AI model, means for receiving inquiries from users and providing relevant disaster information, and means for returning responses generated by the server to the terminal. This enables information to be provided quickly and accurately when a disaster occurs. Users can receive the necessary information from the server and take appropriate action. Furthermore, even if a communication failure occurs, the terminal can use the latest information stored in the background and share the information with other devices via short-range wireless communication. This enables reliable information provision even in unstable communication environments.

[1077] A "generative AI model" is an artificial intelligence system that uses machine learning techniques to learn patterns and relationships from large amounts of data and generate new information.

[1078] "Disaster information" refers to all data related to natural disasters, such as the current situation, forecasts, impacts, evacuation sites, and support information.

[1079] "User inquiries" refer to the act of a user sending information or questions that the user requests the system to provide via a communication means.

[1080] "Automatic background data updates" is a function that allows the system to collect new information periodically or under certain conditions, regardless of user operations, and keep the internal database up to date.

[1081] A "Communications Outage" is a temporary or permanent outage of the Internet or other communications network.

[1082] "Existing data" refers to information that the system has collected and stored in the past, and is data that is used in situations where it is difficult to obtain the latest information.

[1083] "Near-field wireless communication" is a technology that transmits and receives data wirelessly over short distances, such as Bluetooth and Wi-Fi Direct.

[1084] "Means of collection and analysis" refers to methods of obtaining disaster information from various sources, analyzing its relevance and importance, and deriving useful information.

[1085] The "means for providing" refers to a means for displaying, notifying, or transmitting the analyzed information to the user.

[1086] "Means for returning" refers to the process of returning the analysis results and necessary information to the user terminal via communication.

[1087] The system of the present invention consists of a server, a terminal, and a user. The server has the function of collecting and analyzing disaster information using a generative AI model and generating optimal answers to user inquiries. Users can use this system through their terminals. Specific embodiments are described below.

[1088] Server Features

[1089] The server is equipped with a generative AI model and has the ability to collect and analyze disaster information. The server receives inquiries from users and passes the details to the generative AI model. The generative AI model analyzes data collected from government agencies, media, and social media, and generates optimal answers. The server also periodically collects new disaster information and automatically updates the database in the background. For example, an API can be implemented using Python's Flask to call a generative AI model (e.g., GPT-4).

[1090] Device Features

[1091] The device has the function of sending user inquiries to the server and displaying information from the server to the user. When a user launches the app and types, for example, "Where is the nearest evacuation shelter?", the inquiry is sent from the device to the server. The information received from the server is displayed on the device screen. The device also has the function of receiving new data from the server via push notifications and storing it locally in the background. Furthermore, in the event of a communication failure, the device can use the stored data to provide information to other devices via short-range wireless communication (such as Bluetooth or Wi-Fi Direct).

[1092] User operations

[1093] The user launches the app and enters the necessary information into a text box. For example, "Where is the nearest evacuation shelter?" The input is sent to the server via the device. The server analyzes the information using a generative AI model and generates a response, such as "The nearest evacuation shelter is XX Elementary School, and the route is YYY," which is sent back to the device. The device then displays this information to the user, who can then take appropriate action based on that information.

[1094] Specific examples

[1095] In the event of a major earthquake, the user opens the app and asks, "Where is the nearest evacuation shelter?" The device sends this query to the server. The server uses a generative AI model to analyze the latest evacuation shelter information and generates the answer, "The nearest evacuation shelter is XX Park, 1 km away." This information is sent to the device and displayed to the user.

[1096] An example of a prompt to input to a generative AI model is as follows:

[1097] "Please tell me information about the nearest evacuation shelter based on the current disaster situation."

[1098] As described above, the system of the present invention provides rapid and accurate information during disasters and enables information sharing even during communication disruptions, allowing victims and related parties to quickly obtain the necessary information and take safe action.

[1099] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1100] Step 1:

[1101] User asks for information

[1102] The user launches the app and types "Where is the nearest shelter?" This is entered into the device as string data. The entered data is internally converted into a structured request object. This request object contains the key "query" and the query string "Where is the nearest shelter?".

[1103] Step 2:

[1104] The device sends a request to the server

[1105] The terminal receives the generated request object and sends it to the server as an HTTP request. Specifically, it uses the HTTP POST method to send a request to the endpoint URL. The input is the user's question, which is sent to the server as an HTTP request. The output is the process by which the request is sent.

[1106] Step 3:

[1107] The server receives the query

[1108] The server analyzes the HTTP request received from the device and passes the content to the generative AI model. The input is the HTTP request, and the content is analyzed and input to the generative AI model as a prompt. The output is the prompt sent to the generative AI model.

[1109] Step 4:

[1110] Generative AI models generate information

[1111] The generative AI model receives a prompt, collates and analyzes information from an accumulated database and external sources, and generates the optimal answer. The input is the prompt, and data processing and calculations are performed to combine information from the database. The output is the generated answer text.

[1112] Step 5:

[1113] The server generates a response and sends it back to the device.

[1114] The server returns the answer obtained from the generative AI model to the device as an HTTP response. The input is the answer text from the generative AI model, which is structured as an HTTP response. The output is the response text sent to the device.

[1115] Step 6:

[1116] The device receives the information and displays it to the user.

[1117] The terminal analyzes the response received from the server and displays it to the user. The input is the response from the server, and data processing is performed to convert it into a displayable format. The output is the information displayed on the user's screen. The user can take appropriate action based on the displayed information.

[1118] Step 7:

[1119] The server collects and updates new information in the background

[1120] The server periodically collects new disaster information from government agencies, media, and social media, and automatically updates the database. The input is new information from external sources, and data calculations are performed to add or update this information to the database. The output is the updated database.

[1121] Step 8:

[1122] Your device updates data in the background

[1123] The server sends new information to the device via push notification. The device updates the received data in the background and stores it locally. The input is notification data from the server, and data calculations are performed to update the device's local storage or database. The output is the latest disaster information stored on the device.

[1124] Step 9:

[1125] Devices use existing data in the event of a communication failure

[1126] The device periodically checks the Internet connection and detects communication disruptions. If a communication disruption occurs, the device accesses the latest data stored in the background and displays that information to the user. In addition, it provides information to other devices using short-range wireless communication (such as Bluetooth or Wi-Fi Direct). The input is the existing data and the results of the communication status check, and the output is the information displayed to the user and the information sent to other devices.

[1127] This is the specific processing flow of the program for this system. This makes it possible to provide fast and accurate information in the event of a disaster, and to share highly reliable information even in the event of a communication failure.

[1128] (Application example 1)

[1129] 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."

[1130] Challenges in providing fast and accurate information during disasters include the problem of information sharing when communication failures occur and the inability to provide appropriate responses to user inquiries. Furthermore, security staff and guards working on-site have limited means of obtaining the latest information in real time and taking appropriate action. There is a need for a system that can solve these issues and enable users to instantly obtain the information they need in an emergency and take action.

[1131] 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.

[1132] In this invention, the server includes means for collecting and analyzing disaster information using a generation AI, means for receiving inquiries from users and providing relevant disaster information, and means for automatically updating data in the background, thereby enabling users to obtain disaster information in real time.

[1133] It also includes a means for using existing data to perform short-range wireless communication in the event of a communication failure, a means for the generation AI to provide analysis results in response to inquiries entered by voice from the user when communication is possible, and a means for displaying disaster information in real time on the smart device. This allows information sharing to continue even in the event of a communication failure, and enables users to quickly obtain information from the generation AI through voice input and easily check that information on their smart device.

[1134] "Generative AI" is a type of artificial intelligence technology that automatically generates new information and answers based on collected data.

[1135] "Disaster information" refers to detailed data on the location, scale, extent of impact, evacuation sites, and other information related to natural and man-made disasters.

[1136] A "user query" is a question or request made by a user to the system for specific information.

[1137] "Means for automatically updating data in the background" refers to a function that allows the system to periodically obtain the latest information from the server and update the local database, regardless of user ingress.

[1138] "Communications Outage" means a condition in which the Internet connection is unstable or unavailable.

[1139] "Near field communication" is a method of exchanging data between nearby devices using short-range communication technologies such as Bluetooth and Wi-Fi Direct.

[1140] "Voice input" is a method in which a user gives instructions or queries to a system using voice.

[1141] "Smart devices" refer to electronic devices that can connect to the Internet and have advanced processing capabilities, such as smartphones and smart glasses.

[1142] "Display in real time" means that the acquired information is displayed immediately on the screen of the user's device.

[1143] "Means for summarizing analysis results" is a function that analyzes the information collected by the generation AI and provides it in a concise format that is easy for users to understand.

[1144] "Push notification" is a function that allows a server to automatically send new information to a user's device in real time.

[1145] The system of the present invention uses generative AI to collect and analyze information in order to provide users with fast and accurate information during disasters, and has the ability to share information via short-range wireless communication even in the event of communication failure.

[1146] System configuration

[1147] This system mainly consists of a server, a terminal, and a user. The server is equipped with a generation AI and is responsible for collecting and analyzing disaster information. The terminal also sends inquiries from users to the server and displays the information received from the server to the user. Users access the system through their terminal and obtain the information they need.

[1148] Server Features

[1149] The server periodically collects new disaster information from government agencies, the media, social media, etc., and analyzes the data using a generation AI. Based on the collected data, the generation AI generates the optimal answer to a user's inquiry. For example, in response to the inquiry "Where is the nearest evacuation shelter?", the generation AI will respond with "Currently, the nearest evacuation shelter is XX Park."

[1150] Device Features

[1151] The device sends user inquiries to the server, receives responses from the server, and displays them to the user. The device also has the ability to receive updated data from the server in the background and store the latest data locally. In the event of a communication failure, the device uses the latest data stored in the background and provides information to other devices via short-range wireless communication (such as Bluetooth or Wi-Fi Direct).

[1152] User operations

[1153] The user uses a smart device (such as a smartphone or smart glasses) to launch the app and request information. If the device is capable of communication, the generation AI will provide analysis results based on the user's voice or text input. For example, if the user voice-inputs, "Please tell me where the evacuation shelters are," the device will display the information analyzed by the generation AI.

[1154] Specific examples

[1155] For example, if a large-scale earthquake occurs, a user puts on smart glasses and asks, "Where is the nearest evacuation shelter?" This request is sent from the device to the server. The server uses generative AI to collect the latest evacuation shelter information from government agencies and the media, and generates a response such as, "The nearest evacuation shelter is XX Park, 1 km away." This information is sent to the device and displayed to the user on the smart glasses' display.

[1156] Furthermore, if the communication network is down, the device will transmit the latest evacuation shelter data stored in the background to other nearby devices via Bluetooth, allowing users to share necessary information even during communication disruptions.

[1157] Prompt Sentence Examples

[1158] "User: An earthquake has occurred. Where is the nearest safe haven?"

[1159] "Generator AI: Understood. Currently, the closest evacuation shelter is XX Park. It's about a 5-minute walk away. Please avoid collapsible buildings when evacuating."

[1160] The above is a specific example of how the system of the present invention provides information during a disaster. This system uses a generative AI model and prompts to provide optimal information to users, and is designed to enable continued information sharing even during communication disruptions.

[1161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1162] Step 1:

[1163] User asks for information

[1164] Input: A user uses a smart device (smart glasses or smartphone), launches the app, and asks verbally, "Where is the nearest evacuation shelter?"

[1165] Data processing: The device converts the voice input into text and generates an HTTP request to send to the server.

[1166] Output: Text after audio data conversion and data in HTTP request format are generated.

[1167] What it does: It accepts voice input, converts it to text using speech recognition technology, packages this text data into an HTTP request, and sends it to the server.

[1168] Step 2:

[1169] The server generates the information

[1170] Input: HTTP request sent from the device (text data: "Where is the nearest evacuation shelter?").

[1171] Data calculation: Generative AI analyzes data collected from government agencies and the media to generate optimal answers.

[1172] Output: Generated answer text ("The nearest shelter is XX Park").

[1173] Operation: The server passes the query to the generation AI, which then analyzes and generates the most appropriate evacuation shelter information while checking various databases, and returns the answer text to the terminal.

[1174] Step 3:

[1175] The device displays the information

[1176] Input: Answer text received from the server ("The nearest shelter is XX Park").

[1177] Data processing: Format the received text data in a way that is compatible with the display format of the smart device.

[1178] Output: Information shown on the display of the user's smart device (smart glasses or smartphone).

[1179] Operation: Receives response data from the server, formats it into text for display, and displays it on the smart device's display.

[1180] Step 4:

[1181] The server collects new information

[1182] Input: A trigger based on a recurring schedule.

[1183] Data calculation: Collect the latest disaster information from government agencies, media, social media, etc. and update the database.

[1184] Output: Updated disaster information database.

[1185] How it works: The server periodically collects data from external sources, analyzes and categorizes the data using generative AI, and updates the disaster information database.

[1186] Step 5:

[1187] The device updates the data

[1188] Input: Push notification from the server (new disaster information).

[1189] Data processing: Received data is saved in a local database.

[1190] Output: The updated local database.

[1191] How it works: The device receives push notifications in the background and stores the latest data in a local database.

[1192] Step 6:

[1193] Response in the event of a communication failure

[1194] Input: Communication failure detected (unreliable internet connection).

[1195] Data processing: Refer to existing local databases and extract the necessary data.

[1196] Output: Referenced data (e.g., shelter information).

[1197] Operation: The device periodically checks its internet connection and, if it detects a communication failure, continues to operate using data stored in the background.

[1198] Step 7:

[1199] Information sharing via short-range wireless communication

[1200] Input: Other devices nearby.

[1201] Data calculation: Send data using Bluetooth or Wi-Fi Direct.

[1202] Output: Data sent to other nearby devices.

[1203] How it works: The device sends information to other devices via short-range wireless communication, making it available to the user.

[1204] The above are the specific processing steps of the system.

[1205] 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.

[1206] The present invention is a system that uses generative AI to provide accurate and prompt information when a disaster occurs, and combines it with an emotion engine that recognizes the user's emotions to provide more appropriate support. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described below.

[1207] System Overview

[1208] 1. Server Functions

[1209] The server is equipped with a generative AI and emotion engine, and has the ability to collect and analyze disaster information.

[1210] The server receives inquiries from users and uses generation AI to generate optimal answers, analyzing the user's emotions with an emotion engine and adjusting the information provided.

[1211] The server regularly collects new disaster information from government agencies, media, and social media, and updates the data in the background.

[1212] 2. Device Features

[1213] The terminal has the function of sending inquiries from the user to the server.

[1214] The terminal displays the information received from the server to the user, and also displays additional support information based on the user's emotions.

[1215] The device receives updated data from the server in the background and saves the latest data.

[1216] In the event of a communication outage, the device will use data stored in the background to provide information to other devices via short-range wireless communication.

[1217] 3. User Operation

[1218] Users launch the app and ask for the information they need, and emotional input can be automatically analyzed using voice, text, or facial recognition.

[1219] The user's emotions are analyzed and support information is provided accordingly.

[1220] Program processing explanation

[1221] Processing requests and providing information

[1222] User asks for information

[1223] The user launches the app and types, "Please tell me the location of the evacuation shelter." The device sends the user's input along with emotion data analyzed by the emotion engine to the server.

[1224] The server generates the information

[1225] The server analyzes the received request and emotional data. The generation AI collects data from government agencies, media, and social media, and generates the analysis results. The emotion engine analyzes the user's emotions and passes the results to the generation AI, which then adjusts the information provided to suit the user's situation and emotions.

[1226] For example, if the emotion engine analyzes that the user is in a state of panic, the generative AI will provide information such as, "Currently, the nearest evacuation shelter is XX Elementary School. Please remain calm and evacuate. We will provide telephone support if necessary."

[1227] The device displays the information

[1228] The device analyzes the information received from the server and displays it to the user. In addition to the usual evacuation shelter information, it also provides additional support information based on the user's emotions.

[1229] Background data updates

[1230] The server collects new information

[1231] The server regularly collects the latest disaster information from government agencies, the media, and social media, analyzes it using generative AI, and updates the database.

[1232] The device updates the data

[1233] The server sends new information to the device via push notification, and the device updates the data in the background.

[1234] Response in the event of a communication failure

[1235] The device detects a communication failure

[1236] The device periodically checks the internet connection and detects communication disruptions.

[1237] The device uses existing data

[1238] In the event of a communication failure, the device will access the latest data stored in the background. Information will be provided to other users' devices using short-range wireless communication (Bluetooth, Wi-Fi Direct, etc.). For example, even if a communication failure occurs, a device can provide information such as "The nearest evacuation shelter is XX Elementary School" to other users' devices nearby.

[1239] As described above, by combining generative AI and an emotion engine, the system of the present invention can improve the accuracy and speed of information during disasters and provide support that responds to the user's emotions. This allows victims and those involved to quickly and appropriately obtain the information they need and take safe action.

[1240] The processing flow will be explained below.

[1241] Program processing

[1242] Processing requests and providing information

[1243] User asks for information

[1244] Step 1:

[1245] The user launches the app and types, "Please tell me where the evacuation shelter is."

[1246] Step 2:

[1247] The device receives user input and activates the emotion engine, collecting user emotion data through methods such as voice, text, and facial recognition.

[1248] Step 3:

[1249] The device sends the user's input and emotional data to the server as an HTTP request.

[1250] The server generates the information

[1251] Step 4:

[1252] The server analyzes the request content and emotion data received from the device.

[1253] Step 5:

[1254] The server passes the request content and emotion data to the generated AI, which then collects and analyzes related disaster information.

[1255] Step 6:

[1256] The generative AI collects data from government agencies, media, and social media, and generates analytical results.

[1257] Step 7:

[1258] The emotion engine feeds the results of the user's emotion analysis back to the generation AI, which then adjusts the information provided.

[1259] Step 8:

[1260] The server generates information such as "Currently, the nearest evacuation shelter is XX Elementary School, and the route is YYY."

[1261] Step 9:

[1262] The server sends the generated answer to the terminal as an HTTP response.

[1263] The device displays the information

[1264] Step 10:

[1265] The terminal analyzes the response data received from the server.

[1266] Step 11:

[1267] The device displays the analysis results to the user, for example, "The nearest evacuation shelter is XX Elementary School" and additional information such as "Please remain calm and evacuate. We will provide telephone support if necessary."

[1268] Background data updates

[1269] The server collects new information

[1270] Step 1:

[1271] The server regularly collects new disaster information from government agencies, media, and social media.

[1272] Step 2:

[1273] The server analyzes the collected information and updates the database using generative AI.

[1274] The device updates the data

[1275] Step 3:

[1276] The server sends new information to the device via push notification.

[1277] Step 4:

[1278] The device receives the push notification in the background and saves the new data to local storage.

[1279] Response in the event of a communication failure

[1280] The device detects a communication failure

[1281] Step 1:

[1282] The device periodically checks the Internet connection to detect whether any communication problems have occurred.

[1283] The device uses existing data

[1284] Step 2:

[1285] When a device detects a communication failure, it accesses the latest data stored in the background.

[1286] Step 3:

[1287] The device uses short-range wireless communication (Bluetooth, Wi-Fi Direct, etc.) to send necessary information to other users' devices nearby.

[1288] Step 4:

[1289] The information received by other users' devices is analyzed and displayed to the user. For example, it displays, "Even during a communication outage, the nearest evacuation shelter is XX Elementary School."

[1290] Example 2

[1291] 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."

[1292] Conventional disaster information systems are required to provide prompt and accurate information in response to user inquiries, but they lack support that takes into account the user's emotional state. Furthermore, effective information provision methods during communication disruptions are limited, making it difficult to provide useful information to users during disasters. Therefore, the objective of this invention is to provide a disaster information provision system that utilizes generative AI and emotion recognition technology to provide appropriate information according to the user's emotional state and that has effective information provision methods even during communication disruptions.

[1293] 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.

[1294] In this invention, the server includes means for collecting and analyzing disaster information using a generation AI, means for receiving inquiries from users and providing relevant disaster information, means for automatically updating data in the background, means for using existing data to perform short-range wireless communication during communication disruptions, and means for analyzing the user's emotions using an emotion recognition engine and adjusting the information provided by the generation AI. This enables prompt and accurate information provision even during disasters, and provides support tailored to the user's emotional state. As a result, disaster victims and their relatives can quickly and appropriately obtain the information they need and take safe action.

[1295] "Generative AI" is a system that uses artificial intelligence technology to collect and analyze data and generate optimal information in response to user requests.

[1296] "Disaster information" refers to various information related to disasters, such as the occurrence and progression of the disaster, the extent of the impact, and the location of evacuation shelters.

[1297] A "user inquiry" is an input made by a user to the system to request specific information or assistance, and may be in the form of text, voice, image, or the like.

[1298] "Automatically updating data in the background" means that the system has the function of periodically collecting the latest data and updating the database without requiring user operation.

[1299] "Communication failure" refers to a network malfunction or disruption that occurs when a system sends or receives data via the Internet or other means of communication.

[1300] "Existing data" refers to information that has been stored in the system in advance and is available even in the event of a communication failure.

[1301] "Near field wireless communication" refers to technologies such as Wi-Fi Direct and Bluetooth that enable data communication between devices over short distances.

[1302] An "emotion recognition engine" refers to a technology or system that analyzes emotions from a user's voice, text, facial expressions, etc., and determines the user's emotional state.

[1303] "Providing appropriate information" means providing information in a form that best suits the user's situation and emotional state, with the aim of improving the user's sense of security and appropriateness of behavior.

[1304] The present invention is a system that uses a generative AI model to provide accurate and prompt information when a disaster occurs, and combines it with an emotion recognition engine that recognizes user emotions to provide more appropriate support. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described in detail below.

[1305] System configuration

[1306] This system mainly consists of the following hardware and software components.

[1307] 1. Server

[1308] It is equipped with a generative AI model and has the ability to collect and analyze disaster information.

[1309] It is equipped with an emotion recognition engine that analyzes the user's emotions.

[1310] Regularly collect data from government agencies, media, and social networking services to update the database.

[1311] If communication is normal, the latest disaster information will be sent to the user's device via push notification.

[1312] 2. Terminal

[1313] It has the function of sending user inquiries to the server.

[1314] It has the function of displaying information received from the server to the user.

[1315] Data is updated in the background, and in the event of a communication failure, short-range wireless communication is performed using existing data.

[1316] 3. Users

[1317] Use a device such as a smartphone or tablet to inquire about the information you need.

[1318] Take appropriate action based on the information inquired.

[1319] Program processing explanation

[1320] The server receives inquiries from users and analyzes them using a generative AI model. It also analyzes the user's emotions using an emotion recognition engine and adjusts the information provided. The generative AI model is trained using a large dataset, allowing it to provide the latest information in real time. The specific processing flow is as follows:

[1321] 1. User operations

[1322] The user launches the app and asks for the required information by voice or text, for example, by entering a prompt such as "Please tell me the location of the evacuation shelter."

[1323] 2. Terminal Processing

[1324] The device converts the user's inquiry into text and uses an emotion recognition engine to analyze emotional data from the user's voice and facial expressions.

[1325] The analyzed data and the user's query are sent to the server.

[1326] 3. Server Processing

[1327] The server uses a generative AI model based on the received data to analyze the user's query and collect and compile the necessary disaster information.

[1328] The emotional state of the user is analyzed again using an emotion recognition engine, and the generated information is provided to the user in an optimal form.

[1329] For example, if the user is in a panic, a message such as "The nearest evacuation shelter is currently XX Elementary School. Please remain calm and evacuate" is generated.

[1330] 4. Display by terminal

[1331] The information received from the server is displayed to the user, and necessary support information is provided.

[1332] Examples of concrete examples and prompts

[1333] Specific examples

[1334] The user launches a smartphone app and speaks, "Is there a safe place nearby?"

[1335] The device converts the voice data into text and uses an emotion recognition engine to analyze whether the user is in a state of agitation.

[1336] The server analyzes the query using a generative AI model and generates information about the nearest evacuation shelter and a message such as "Please remain calm and evacuate."

[1337] The device displays this to the user, providing necessary information and a sense of security.

[1338] Prompt Sentence Examples

[1339] 1. "Please tell me where the evacuation shelter is."

[1340] 2. "Is there a safe place nearby?"

[1341] 3. "Can you give me an update on the current situation?"

[1342] As described above, by combining a generative AI model and an emotion recognition engine, the system of the present invention can provide prompt and accurate information during disasters and provide appropriate support according to the user's emotional state. This allows disaster victims and those involved to quickly and appropriately obtain the necessary information and take safe action.

[1343] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1344] System program processing flow

[1345] Step 1: User Enters Information

[1346] The user launches the app and speaks, "Please tell me the location of the evacuation shelter." This voice input is sent to the device and converted to text on the spot. The converted text becomes the input data for the information query.

[1347] Input: Audio input

[1348] Output: The query converted to text

[1349] Step 2: The device analyzes and transmits the emotion data.

[1350] The device analyzes the user's voice and facial expressions using an emotion recognition engine to generate emotional data about the user. The specific emotional state (e.g., panic, calm, etc.) is analyzed and sent to the server along with a text query.

[1351] Input: Text-converted query, user voice and facial expression data

[1352] Output: Parsed emotion data, sent to the server along with the query

[1353] Step 3: The server parses the information

[1354] The server uses a generative AI model to collect and analyze the necessary disaster information based on the received inquiry and emotion data. Specifically, it collects the latest disaster information from government agencies, media, and social media, and generates information appropriate for the user's inquiry.

[1355] Input: Text-converted query, emotion data

[1356] Output: Disaster information in response to user inquiries

[1357] Step 4: The server adjusts the information based on the emotion data

[1358] The server adjusts the disaster information it generates based on the user's emotional data analyzed by an emotion recognition engine. For example, if the user is in a panic, it generates information containing a message that gives a sense of security.

[1359] Input: Disaster information and emotion data in response to user inquiries

[1360] Output: Emotionally sensitive information

[1361] Step 5: The server sends the information to the device

[1362] The server then sends the adjusted disaster information to the terminal. Communication is performed using secure protocols such as SSL / TLS.

[1363] Input: Emotionally sensitive information

[1364] Output: Data sent to the terminal

[1365] Step 6: The device displays the information to the user

[1366] The device analyzes the information it receives and displays it in an optimal way for the user, including the location of evacuation shelters and sensitive messages.

[1367] Input: Adjusted information sent from the server

[1368] Output: The final information displayed to the user

[1369] Specific examples of operation

[1370] Step 1: User Enters Information

[1371] The user opens the app on their smartphone and says, "Tell me where the nearest safe place is." The speech is converted into text in real time and displayed on the device.

[1372] Step 2: The device analyzes and transmits the emotion data.

[1373] The device uses an emotion recognition engine to analyze the user's tone of voice and facial expressions to determine their emotional state. For example, the device sends a text query along with the analyzed emotional state, such as "anxiety," to the server.

[1374] Step 3: The server parses the information

[1375] Based on the received data, the server uses a generative AI model to collect and analyze the latest disaster information, including "nearby evacuation shelters." The information is extracted from the database and a list of the nearest currently available evacuation shelters is generated.

[1376] Step 4: The server adjusts the information based on the emotion data

[1377] The server takes into account the results of the emotion recognition engine and adjusts the information to suit a user in a state of panic. Specifically, it generates information containing a reassuring message such as, "XX Elementary School is the nearest evacuation shelter. Please remain calm and evacuate."

[1378] Step 5: The server sends the information to the device

[1379] The server sends the tailored information to the device, including a map of the evacuation center, its address, and a reassuring message.

[1380] Step 6: The device displays the information to the user

[1381] The device displays the received information to the user, who can then check the map on the app screen along with a message saying, "XX Elementary School is the nearest evacuation shelter. Please remain calm and evacuate."

[1382] Through the above processing, this system can provide appropriate information according to the user's emotional state and support safe behavior in the event of a disaster.

[1383] (Application example 2)

[1384] 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."

[1385] Existing disaster information systems struggle to provide accurate and timely information during disasters, and also to provide appropriate support that takes into account the user's emotions. It is particularly difficult to continue providing appropriate information when communication failures occur. Furthermore, there is a lack of methods to reduce the stress and anxiety users feel during disasters and encourage effective evacuation behavior.

[1386] 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 means for collecting and analyzing disaster information using a generation AI, means for receiving inquiries from users and providing corresponding disaster information, means for automatically updating data in the background, means for performing short-range wireless communication using existing data in the event of a communication failure, and means for analyzing the user's emotions using emotion recognition technology and adjusting the information to be provided based on the results. This makes it possible to provide accurate and prompt information even during a disaster and provide appropriate support according to the user's emotions.

[1387] "Generative AI" is an artificial intelligence technology that automatically generates information based on input data.

[1388] "Disaster information" refers to various information related to natural and man-made disasters, including the location of evacuation shelters, damage status, and first aid information.

[1389] "Analysis" is the process of breaking down and analyzing collected data to extract useful information.

[1390] "User" means any person or entity that uses the System.

[1391] An "inquiry" refers to a question or request made by a user to the system for information or assistance.

[1392] "Automatically updating data in the background" is a function that allows the system to automatically obtain and store the latest information even when the user is not operating the system.

[1393] "Communication outage" refers to a situation in which the Internet or other means of communication do not function properly.

[1394] "Existing Data" refers to data that has previously been collected and stored by the system.

[1395] "Near field wireless communication" refers to exchanging data using short-range wireless communication technologies such as Bluetooth and Wi-Fi Direct.

[1396] "Emotion recognition technology" is a technology that determines a user's emotions from the tone of their voice, facial expression, text content, etc.

[1397] The present invention is a system that uses generative AI and emotion recognition technology to provide accurate and prompt information in the event of a disaster, and provides appropriate support according to the user's emotions. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described below.

[1398] System Overview

[1399] 1. Server Functions

[1400] The server is equipped with generative AI and emotion recognition technology, and has the ability to collect and analyze disaster information, allowing it to retain accurate and up-to-date information and generate information in response to user inquiries.

[1401] The server receives inquiries from users and uses generative AI to generate the optimal answer. It also uses emotion recognition technology to analyze the user's emotions and adjust the information provided accordingly. For example, if the user is in a panic, it will provide information that includes reassuring words.

[1402] The server periodically collects new disaster information from government agencies, the media, social media, etc. and updates the data in the background, ensuring that users are always provided with the latest information.

[1403] 2. Device Features

[1404] The devices include smartphones, tablets, robots, etc., and have the ability to send inquiries from users to a server. Questions can be sent via voice input or text input.

[1405] The device receives the information from the server and displays it to the user. The displayed information is adjusted based on the user's emotions, providing more personalized assistance.

[1406] The device has the ability to receive updated data from the server in the background and store the latest data. Even if communication is interrupted, the stored data can be used to provide information to other devices via short-range wireless communication (Bluetooth, Wi-Fi Direct, etc.).

[1407] 3. User Operation

[1408] The user launches the application installed on the device and requests the necessary information. Inquiries are made via voice, text, facial recognition, etc. Emotions are automatically analyzed and appropriate support information is provided.

[1409] For example, if a user makes a voice inquiry such as "Please tell me where the evacuation shelter is," the device sends the voice to the server, which then uses emotion recognition technology to analyze the user's state. Based on the results, the AI ​​generates information such as "Currently, the nearest evacuation shelter is XX Elementary School. Please remain calm and evacuate. We will provide telephone support if necessary," and sends it to the device.

[1410] Hardware and software used

[1411] Hardware:

[1412] Camera: Used to capture facial images and recognize emotions. Use the built-in camera on your smartphone or robot.

[1413] Smartphone / Tablet / Robot: The primary device on which the application runs.

[1414] software:

[1415] OpenCV: A library for face recognition and image processing.

[1416] TensorFlow / Keras: Machine learning frameworks for running emotion recognition models.

[1417] Transformers (Hugging Face): A library that generates text using generative AI (GPT-2).

[1418] Requests: A library for retrieving data from the disaster information API.

[1419] Specific examples

[1420] Scenario: When a disaster occurs, a user looks into their smartphone camera and asks, "Where is the evacuation shelter?"

[1421] Example prompt: "User is feeling Fear. Provide the most relevant disaster information: Nearest shelter is at XX school. Please stay calm. We can provide phone support if needed."

[1422] Example response generated: "The nearest evacuation shelter is XX Elementary School. Please remain calm. Telephone assistance will be provided if necessary."

[1423] As described above, by combining generative AI and emotion recognition technology, the system of the present invention can improve the accuracy and speed of information during disasters, and can also provide support that is tailored to the user's emotions.

[1424] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1425] Step 1:

[1426] The server automatically collects and analyzes disaster information from government agencies, media, social media, etc. It collects new disaster information as input and analyzes it using a generative AI model. The analyzed data is stored in a database and is ready for user inquiries.

[1427] Step 2:

[1428] The user activates the device's camera function and has their face recognized. The user's facial image is provided as input, and the device detects the face using OpenCV and inputs the facial image into an emotion recognition model. Emotion recognition technology (TensorFlow / Keras) analyzes the user's emotion as "panic," "fear," etc. The output is the user's emotion data.

[1429] Step 3:

[1430] The user asks the terminal a question by voice, such as "Where is the evacuation shelter?" This voice data is input into the terminal and converted into text. The converted question content and emotion data are sent to the server.

[1431] Step 4:

[1432] The server generates an optimal response based on the received question content and emotion data. The question content and emotion data are provided as input, and an appropriate answer is generated using a generative AI model (Transformers). For example, a response such as "The nearest evacuation shelter is XX Elementary School. Please remain calm. We will provide telephone support if necessary" is generated. The output is response data to be sent back to the user.

[1433] Step 5:

[1434] The terminal receives the response data from the server and displays it to the user. The terminal receives the response data from the server as input and displays it on the screen. This gives the user information about the nearest evacuation shelter and a message encouraging reassurance.

[1435] Step 6:

[1436] The server periodically updates data in the background to maintain the latest disaster information. It receives new disaster information as input, analyzes it with the generative AI model, and updates the database. This ensures that the latest information is always available to users.

[1437] Step 7:

[1438] In the event of a communication failure, the device will use the latest data stored in the background to communicate with other devices in the vicinity via short-range wireless communication (Bluetooth, Wi-Fi Direct, etc.) using the communication failure detection signal as input. This allows important information to be shared even when an internet connection is unavailable.

[1439] 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.

[1440] 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.

[1441] 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.

[1442] [Fourth embodiment]

[1443] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1444] 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.

[1445] 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).

[1446] 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.

[1447] 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.

[1448] 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).

[1449] 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.

[1450] 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.

[1451] 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.

[1452] 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.

[1453] 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.

[1454] 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.

[1455] 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."

[1456] The present invention is a system that uses generative AI to provide accurate and prompt information in the event of a disaster, and shares information via short-range wireless communication in the event of a communication failure. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described below.

[1457] System Overview

[1458] 1. Server Functions

[1459] The server is equipped with a generation AI and has the ability to collect and analyze disaster information.

[1460] The server receives inquiries from users, uses a generation AI to generate optimal answers, and returns these to the terminal.

[1461] The server regularly collects new disaster information from government agencies, media, and social media, and updates the data in the background.

[1462] 2. Device Features

[1463] The terminal has the function of sending inquiries from the user to the server.

[1464] The terminal displays the information received from the server to the user.

[1465] The device receives updated data from the server in the background and saves the latest data.

[1466] In the event of a communication outage, the device will use data stored in the background to provide information to other devices via short-range wireless communication.

[1467] 3. User Operation

[1468] The user launches the app and queries for the required information.

[1469] Based on the questions the user enters, the system provides the necessary information.

[1470] Program processing explanation

[1471] Processing requests and providing information

[1472] User asks for information

[1473] The user launches the app and types, for example, "Please tell me where the evacuation shelter is."

[1474] The terminal receives the user's input and sends it to the server as an HTTP request.

[1475] The server generates the information

[1476] The server receives the request and passes the contents to the generation AI.

[1477] The generative AI analyzes data collected from government agencies, media, and social media to generate optimal answers.

[1478] For example, the generation AI returns information such as, "Currently, the nearest evacuation shelter is XX Elementary School, and the route is YYY."

[1479] The device displays the information

[1480] The terminal analyzes the information received from the server and displays it to the user.

[1481] The user can refer to the displayed information and take appropriate action.

[1482] Background data updates

[1483] The server collects new information

[1484] The server regularly collects new disaster information from government agencies, media, and social media.

[1485] The server analyzes the collected information and updates the database.

[1486] The device updates the data

[1487] The server sends new information to the device via push notification.

[1488] The device updates the latest data received in the background and stores it locally.

[1489] Response in the event of a communication failure

[1490] The device detects a communication failure

[1491] The device periodically checks the internet connection and detects any communication disruptions.

[1492] The device uses existing data

[1493] If a communication failure occurs, the device will access the latest data stored in the background.

[1494] The device sends the necessary information to other devices via short-range wireless communication (such as Bluetooth or Wi-Fi Direct).

[1495] The other terminal displays the received information to the user.

[1496] Specific examples

[1497] For example, consider the occurrence of a large-scale earthquake. A user opens the app and asks, "Where is the nearest evacuation shelter?" This request is sent from the device to the server. The server uses generative AI to collect the latest evacuation shelter information from government agencies and the media, and generates a response such as, "The nearest evacuation shelter is XX Park, 1 km away." This information is sent to the device and displayed to the user.

[1498] Furthermore, if the communication network is down, the device will use the latest evacuation shelter data in the background and send that information to other nearby devices via Bluetooth, allowing users to share necessary information even during communication disruptions.

[1499] As described above, the system of the present invention provides accurate and prompt information during disasters and enables information sharing even during communication disruptions, enabling victims and related parties to obtain necessary information with minimal effort and take safe action.

[1500] The processing flow will be explained below.

[1501] Program processing

[1502] Processing requests and providing information

[1503] User asks for information

[1504] Step 1:

[1505] The user launches the app and enters information. For example, they might enter, "Please tell me where the evacuation shelter is."

[1506] Step 2:

[1507] The terminal constructs the user's input as an HTTP request and sends it to the server.

[1508] The server generates the information

[1509] Step 3:

[1510] The server analyzes the request received from the terminal.

[1511] Step 4:

[1512] The server passes the request content to the generation AI and collects relevant information.

[1513] Step 5:

[1514] Generative AI collects and analyzes data from government agencies, media, and social media.

[1515] Step 6:

[1516] Based on the data collected, the generative AI generates the optimal answer to the user's request. For example, it generates information such as, "The nearest evacuation shelter is currently XX Elementary School, and the route is YYY."

[1517] Step 7:

[1518] The server constructs the generated answer as an HTTP response and sends it to the terminal.

[1519] The device displays the information

[1520] Step 8:

[1521] The terminal analyzes the response data received from the server.

[1522] Step 9:

[1523] The device displays the analysis results to the user, for example, "The nearest evacuation shelter is XX Elementary School."

[1524] Background data updates

[1525] The server collects new information

[1526] Step 1:

[1527] The server regularly collects new disaster information from government agencies, media, and social media.

[1528] Step 2:

[1529] The server analyzes the collected information and updates the database through a generative AI.

[1530] The device updates the data

[1531] Step 3:

[1532] The server sends new information to the device via push notification.

[1533] Step 4:

[1534] The device receives a push notification and saves the new data to local storage in the background.

[1535] Response in the event of a communication failure

[1536] The device detects a communication failure

[1537] Step 1:

[1538] The device periodically checks the internet connection to detect if there are any communication disruptions.

[1539] The device uses existing data

[1540] Step 2:

[1541] The device that detects the communication failure accesses the latest data stored in the background.

[1542] Step 3:

[1543] The device uses short-range wireless communication (such as Bluetooth or Wi-Fi Direct) to send the necessary information to other users' devices nearby.

[1544] Step 4:

[1545] The other user's device analyzes the received information and displays it to the user, for example, "The latest evacuation shelter is XX Elementary School."

[1546] Example 1

[1547] 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."

[1548] When a natural disaster occurs, it is important to provide accurate information quickly and in real time. However, conventional information provision systems have limitations in the speed and accuracy of information collection, making it difficult to provide information, especially when communication failures occur. In addition, when integrating necessary information from multiple sources and providing it to users, the organization and analysis of the information is often inefficient. There is a need for a system that can provide highly reliable information even in situations where the communication environment is unstable.

[1549] 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.

[1550] In this invention, the server includes means for collecting and analyzing disaster information using a generative AI model, means for receiving inquiries from users and providing relevant disaster information, and means for returning responses generated by the server to the terminal. This enables information to be provided quickly and accurately when a disaster occurs. Users can receive the necessary information from the server and take appropriate action. Furthermore, even if a communication failure occurs, the terminal can use the latest information stored in the background and share the information with other devices via short-range wireless communication. This enables reliable information provision even in unstable communication environments.

[1551] A "generative AI model" is an artificial intelligence system that uses machine learning techniques to learn patterns and relationships from large amounts of data and generate new information.

[1552] "Disaster information" refers to all data related to natural disasters, such as the current situation, forecasts, impacts, evacuation sites, and support information.

[1553] "User inquiries" refer to the act of a user sending information or questions that the user requests the system to provide via a communication means.

[1554] "Automatic background data updates" is a function that allows the system to collect new information periodically or under certain conditions, regardless of user operations, and keep the internal database up to date.

[1555] A "Communications Outage" is a temporary or permanent outage of the Internet or other communications network.

[1556] "Existing data" refers to information that the system has collected and stored in the past, and is data that is used in situations where it is difficult to obtain the latest information.

[1557] "Near-field wireless communication" is a technology that transmits and receives data wirelessly over short distances, such as Bluetooth and Wi-Fi Direct.

[1558] "Means of collection and analysis" refers to methods of obtaining disaster information from various sources, analyzing its relevance and importance, and deriving useful information.

[1559] The "means for providing" refers to a means for displaying, notifying, or transmitting the analyzed information to the user.

[1560] "Means for returning" refers to the process of returning the analysis results and necessary information to the user terminal via communication.

[1561] The system of the present invention consists of a server, a terminal, and a user. The server has the function of collecting and analyzing disaster information using a generative AI model and generating optimal answers to user inquiries. Users can use this system through their terminals. Specific embodiments are described below.

[1562] Server Features

[1563] The server is equipped with a generative AI model and has the ability to collect and analyze disaster information. The server receives inquiries from users and passes the details to the generative AI model. The generative AI model analyzes data collected from government agencies, media, and social media, and generates optimal answers. The server also periodically collects new disaster information and automatically updates the database in the background. For example, an API can be implemented using Python's Flask to call a generative AI model (e.g., GPT-4).

[1564] Device Features

[1565] The device has the function of sending user inquiries to the server and displaying information from the server to the user. When a user launches the app and types, for example, "Where is the nearest evacuation shelter?", the inquiry is sent from the device to the server. The information received from the server is displayed on the device screen. The device also has the function of receiving new data from the server via push notifications and storing it locally in the background. Furthermore, in the event of a communication failure, the device can use the stored data to provide information to other devices via short-range wireless communication (such as Bluetooth or Wi-Fi Direct).

[1566] User operations

[1567] The user launches the app and enters the necessary information into a text box. For example, "Where is the nearest evacuation shelter?" The input is sent to the server via the device. The server analyzes the information using a generative AI model and generates a response, such as "The nearest evacuation shelter is XX Elementary School, and the route is YYY," which is sent back to the device. The device then displays this information to the user, who can then take appropriate action based on that information.

[1568] Specific examples

[1569] In the event of a major earthquake, the user opens the app and asks, "Where is the nearest evacuation shelter?" The device sends this query to the server. The server uses a generative AI model to analyze the latest evacuation shelter information and generates the answer, "The nearest evacuation shelter is XX Park, 1 km away." This information is sent to the device and displayed to the user.

[1570] An example of a prompt to input to a generative AI model is as follows:

[1571] "Please tell me information about the nearest evacuation shelter based on the current disaster situation."

[1572] As described above, the system of the present invention provides rapid and accurate information during disasters and enables information sharing even during communication disruptions, allowing victims and related parties to quickly obtain the necessary information and take safe action.

[1573] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1574] Step 1:

[1575] User asks for information

[1576] The user launches the app and types "Where is the nearest shelter?" This is entered into the device as string data. The entered data is internally converted into a structured request object. This request object contains the key "query" and the query string "Where is the nearest shelter?".

[1577] Step 2:

[1578] The device sends a request to the server

[1579] The terminal receives the generated request object and sends it to the server as an HTTP request. Specifically, it uses the HTTP POST method to send a request to the endpoint URL. The input is the user's question, which is sent to the server as an HTTP request. The output is the process by which the request is sent.

[1580] Step 3:

[1581] The server receives the query

[1582] The server analyzes the HTTP request received from the device and passes the content to the generative AI model. The input is the HTTP request, and the content is analyzed and input to the generative AI model as a prompt. The output is the prompt sent to the generative AI model.

[1583] Step 4:

[1584] Generative AI models generate information

[1585] The generative AI model receives a prompt, collates and analyzes information from an accumulated database and external sources, and generates the optimal answer. The input is the prompt, and data processing and calculations are performed to combine information from the database. The output is the generated answer text.

[1586] Step 5:

[1587] The server generates a response and sends it back to the device.

[1588] The server returns the answer obtained from the generative AI model to the device as an HTTP response. The input is the answer text from the generative AI model, which is structured as an HTTP response. The output is the response text sent to the device.

[1589] Step 6:

[1590] The device receives the information and displays it to the user.

[1591] The terminal analyzes the response received from the server and displays it to the user. The input is the response from the server, and data processing is performed to convert it into a displayable format. The output is the information displayed on the user's screen. The user can take appropriate action based on the displayed information.

[1592] Step 7:

[1593] The server collects and updates new information in the background

[1594] The server periodically collects new disaster information from government agencies, media, and social media, and automatically updates the database. The input is new information from external sources, and data calculations are performed to add or update this information to the database. The output is the updated database.

[1595] Step 8:

[1596] Your device updates data in the background

[1597] The server sends new information to the device via push notification. The device updates the received data in the background and stores it locally. The input is notification data from the server, and data calculations are performed to update the device's local storage or database. The output is the latest disaster information stored on the device.

[1598] Step 9:

[1599] Devices use existing data in the event of a communication failure

[1600] The device periodically checks the Internet connection and detects communication disruptions. If a communication disruption occurs, the device accesses the latest data stored in the background and displays that information to the user. In addition, it provides information to other devices using short-range wireless communication (such as Bluetooth or Wi-Fi Direct). The input is the existing data and the results of the communication status check, and the output is the information displayed to the user and the information sent to other devices.

[1601] This is the specific processing flow of the program for this system. This makes it possible to provide fast and accurate information in the event of a disaster, and to share highly reliable information even in the event of a communication failure.

[1602] (Application example 1)

[1603] 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."

[1604] Challenges in providing fast and accurate information during disasters include the problem of information sharing when communication failures occur and the inability to provide appropriate responses to user inquiries. Furthermore, security staff and guards working on-site have limited means of obtaining the latest information in real time and taking appropriate action. There is a need for a system that can solve these issues and enable users to instantly obtain the information they need in an emergency and take action.

[1605] 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.

[1606] In this invention, the server includes means for collecting and analyzing disaster information using a generation AI, means for receiving inquiries from users and providing relevant disaster information, and means for automatically updating data in the background, thereby enabling users to obtain disaster information in real time.

[1607] It also includes a means for using existing data to perform short-range wireless communication in the event of a communication failure, a means for the generation AI to provide analysis results in response to inquiries entered by voice from the user when communication is possible, and a means for displaying disaster information in real time on the smart device. This allows information sharing to continue even in the event of a communication failure, and enables users to quickly obtain information from the generation AI through voice input and easily check that information on their smart device.

[1608] "Generative AI" is a type of artificial intelligence technology that automatically generates new information and answers based on collected data.

[1609] "Disaster information" refers to detailed data on the location, scale, extent of impact, evacuation sites, and other information related to natural and man-made disasters.

[1610] A "user query" is a question or request made by a user to the system for specific information.

[1611] "Means for automatically updating data in the background" refers to a function that allows the system to periodically obtain the latest information from the server and update the local database, regardless of user ingress.

[1612] "Communications Outage" means a condition in which the Internet connection is unstable or unavailable.

[1613] "Near field communication" is a method of exchanging data between nearby devices using short-range communication technologies such as Bluetooth and Wi-Fi Direct.

[1614] "Voice input" is a method in which a user gives instructions or queries to a system using voice.

[1615] "Smart devices" refer to electronic devices that can connect to the Internet and have advanced processing capabilities, such as smartphones and smart glasses.

[1616] "Display in real time" means that the acquired information is displayed immediately on the screen of the user's device.

[1617] "Means for summarizing analysis results" is a function that analyzes the information collected by the generation AI and provides it in a concise format that is easy for users to understand.

[1618] "Push notification" is a function that allows a server to automatically send new information to a user's device in real time.

[1619] The system of the present invention uses generative AI to collect and analyze information in order to provide users with fast and accurate information during disasters, and has the ability to share information via short-range wireless communication even in the event of communication failure.

[1620] System configuration

[1621] This system mainly consists of a server, a terminal, and a user. The server is equipped with a generation AI and is responsible for collecting and analyzing disaster information. The terminal also sends inquiries from users to the server and displays the information received from the server to the user. Users access the system through their terminal and obtain the information they need.

[1622] Server Features

[1623] The server periodically collects new disaster information from government agencies, the media, social media, etc., and analyzes the data using a generation AI. Based on the collected data, the generation AI generates the optimal answer to a user's inquiry. For example, in response to the inquiry "Where is the nearest evacuation shelter?", the generation AI will respond with "Currently, the nearest evacuation shelter is XX Park."

[1624] Device Features

[1625] The device sends user inquiries to the server, receives responses from the server, and displays them to the user. The device also has the ability to receive updated data from the server in the background and store the latest data locally. In the event of a communication failure, the device uses the latest data stored in the background and provides information to other devices via short-range wireless communication (such as Bluetooth or Wi-Fi Direct).

[1626] User operations

[1627] The user uses a smart device (such as a smartphone or smart glasses) to launch the app and request information. If the device is capable of communication, the generation AI will provide analysis results based on the user's voice or text input. For example, if the user voice-inputs, "Please tell me where the evacuation shelters are," the device will display the information analyzed by the generation AI.

[1628] Specific examples

[1629] For example, if a large-scale earthquake occurs, a user puts on smart glasses and asks, "Where is the nearest evacuation shelter?" This request is sent from the device to the server. The server uses generative AI to collect the latest evacuation shelter information from government agencies and the media, and generates a response such as, "The nearest evacuation shelter is XX Park, 1 km away." This information is sent to the device and displayed to the user on the smart glasses' display.

[1630] Furthermore, if the communication network is down, the device will transmit the latest evacuation shelter data stored in the background to other nearby devices via Bluetooth, allowing users to share necessary information even during communication disruptions.

[1631] Prompt Sentence Examples

[1632] "User: An earthquake has occurred. Where is the nearest safe haven?"

[1633] "Generator AI: Understood. Currently, the closest evacuation shelter is XX Park. It's about a 5-minute walk away. Please avoid collapsible buildings when evacuating."

[1634] The above is a specific example of how the system of the present invention provides information during a disaster. This system uses a generative AI model and prompts to provide optimal information to users, and is designed to enable continued information sharing even during communication disruptions.

[1635] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1636] Step 1:

[1637] User asks for information

[1638] Input: A user uses a smart device (smart glasses or smartphone), launches the app, and asks verbally, "Where is the nearest evacuation shelter?"

[1639] Data processing: The device converts the voice input into text and generates an HTTP request to send to the server.

[1640] Output: Text after audio data conversion and data in HTTP request format are generated.

[1641] What it does: It accepts voice input, converts it to text using speech recognition technology, packages this text data into an HTTP request, and sends it to the server.

[1642] Step 2:

[1643] The server generates the information

[1644] Input: HTTP request sent from the device (text data: "Where is the nearest evacuation shelter?").

[1645] Data calculation: Generative AI analyzes data collected from government agencies and the media to generate optimal answers.

[1646] Output: Generated answer text ("The nearest shelter is XX Park").

[1647] Operation: The server passes the query to the generation AI, which then analyzes and generates the most appropriate evacuation shelter information while checking various databases, and returns the answer text to the terminal.

[1648] Step 3:

[1649] The device displays the information

[1650] Input: Answer text received from the server ("The nearest shelter is XX Park").

[1651] Data processing: Format the received text data in a way that is compatible with the display format of the smart device.

[1652] Output: Information shown on the display of the user's smart device (smart glasses or smartphone).

[1653] Operation: Receives response data from the server, formats it into text for display, and displays it on the smart device's display.

[1654] Step 4:

[1655] The server collects new information

[1656] Input: A trigger based on a recurring schedule.

[1657] Data calculation: Collect the latest disaster information from government agencies, media, social media, etc. and update the database.

[1658] Output: Updated disaster information database.

[1659] How it works: The server periodically collects data from external sources, analyzes and categorizes the data using generative AI, and updates the disaster information database.

[1660] Step 5:

[1661] The device updates the data

[1662] Input: Push notification from the server (new disaster information).

[1663] Data processing: Received data is saved in a local database.

[1664] Output: The updated local database.

[1665] How it works: The device receives push notifications in the background and stores the latest data in a local database.

[1666] Step 6:

[1667] Response in the event of a communication failure

[1668] Input: Communication failure detected (unreliable internet connection).

[1669] Data processing: Refer to existing local databases and extract the necessary data.

[1670] Output: Referenced data (e.g., shelter information).

[1671] Operation: The device periodically checks its internet connection and, if it detects a communication failure, continues to operate using data stored in the background.

[1672] Step 7:

[1673] Information sharing via short-range wireless communication

[1674] Input: Other devices nearby.

[1675] Data calculation: Send data using Bluetooth or Wi-Fi Direct.

[1676] Output: Data sent to other nearby devices.

[1677] How it works: The device sends information to other devices via short-range wireless communication, making it available to the user.

[1678] The above are the specific processing steps of the system.

[1679] 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.

[1680] The present invention is a system that uses generative AI to provide accurate and prompt information when a disaster occurs, and combines it with an emotion engine that recognizes the user's emotions to provide more appropriate support. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described below.

[1681] System Overview

[1682] 1. Server Functions

[1683] The server is equipped with a generative AI and emotion engine, and has the ability to collect and analyze disaster information.

[1684] The server receives inquiries from users and uses generation AI to generate optimal answers, analyzing the user's emotions with an emotion engine and adjusting the information provided.

[1685] The server regularly collects new disaster information from government agencies, media, and social media, and updates the data in the background.

[1686] 2. Device Features

[1687] The terminal has the function of sending inquiries from the user to the server.

[1688] The terminal displays the information received from the server to the user, and also displays additional support information based on the user's emotions.

[1689] The device receives updated data from the server in the background and saves the latest data.

[1690] In the event of a communication outage, the device will use data stored in the background to provide information to other devices via short-range wireless communication.

[1691] 3. User Operation

[1692] Users launch the app and ask for the information they need, and emotional input can be automatically analyzed using voice, text, or facial recognition.

[1693] The user's emotions are analyzed and support information is provided accordingly.

[1694] Program processing explanation

[1695] Processing requests and providing information

[1696] User asks for information

[1697] The user launches the app and types, "Please tell me the location of the evacuation shelter." The device sends the user's input along with emotion data analyzed by the emotion engine to the server.

[1698] The server generates the information

[1699] The server analyzes the received request and emotional data. The generation AI collects data from government agencies, media, and social media, and generates the analysis results. The emotion engine analyzes the user's emotions and passes the results to the generation AI, which then adjusts the information provided to suit the user's situation and emotions.

[1700] For example, if the emotion engine analyzes that the user is in a state of panic, the generative AI will provide information such as, "Currently, the nearest evacuation shelter is XX Elementary School. Please remain calm and evacuate. We will provide telephone support if necessary."

[1701] The device displays the information

[1702] The device analyzes the information received from the server and displays it to the user. In addition to the usual evacuation shelter information, it also provides additional support information based on the user's emotions.

[1703] Background data updates

[1704] The server collects new information

[1705] The server regularly collects the latest disaster information from government agencies, the media, and social media, analyzes it using generative AI, and updates the database.

[1706] The device updates the data

[1707] The server sends new information to the device via push notification, and the device updates the data in the background.

[1708] Response in the event of a communication failure

[1709] The device detects a communication failure

[1710] The device periodically checks the internet connection and detects communication disruptions.

[1711] The device uses existing data

[1712] In the event of a communication failure, the device will access the latest data stored in the background. Information will be provided to other users' devices using short-range wireless communication (Bluetooth, Wi-Fi Direct, etc.). For example, even if a communication failure occurs, a device can provide information such as "The nearest evacuation shelter is XX Elementary School" to other users' devices nearby.

[1713] As described above, by combining generative AI and an emotion engine, the system of the present invention can improve the accuracy and speed of information during disasters and provide support that responds to the user's emotions. This allows victims and those involved to quickly and appropriately obtain the information they need and take safe action.

[1714] The processing flow will be explained below.

[1715] Program processing

[1716] Processing requests and providing information

[1717] User asks for information

[1718] Step 1:

[1719] The user launches the app and types, "Please tell me where the evacuation shelter is."

[1720] Step 2:

[1721] The device receives user input and activates the emotion engine, collecting user emotion data through methods such as voice, text, and facial recognition.

[1722] Step 3:

[1723] The device sends the user's input and emotional data to the server as an HTTP request.

[1724] The server generates the information

[1725] Step 4:

[1726] The server analyzes the request content and emotion data received from the device.

[1727] Step 5:

[1728] The server passes the request content and emotion data to the generated AI, which then collects and analyzes related disaster information.

[1729] Step 6:

[1730] The generative AI collects data from government agencies, media, and social media, and generates analytical results.

[1731] Step 7:

[1732] The emotion engine feeds the results of the user's emotion analysis back to the generation AI, which then adjusts the information provided.

[1733] Step 8:

[1734] The server generates information such as "Currently, the nearest evacuation shelter is XX Elementary School, and the route is YYY."

[1735] Step 9:

[1736] The server sends the generated answer to the terminal as an HTTP response.

[1737] The device displays the information

[1738] Step 10:

[1739] The terminal analyzes the response data received from the server.

[1740] Step 11:

[1741] The device displays the analysis results to the user, for example, "The nearest evacuation shelter is XX Elementary School" and additional information such as "Please remain calm and evacuate. We will provide telephone support if necessary."

[1742] Background data updates

[1743] The server collects new information

[1744] Step 1:

[1745] The server regularly collects new disaster information from government agencies, media, and social media.

[1746] Step 2:

[1747] The server analyzes the collected information and updates the database using generative AI.

[1748] The device updates the data

[1749] Step 3:

[1750] The server sends new information to the device via push notification.

[1751] Step 4:

[1752] The device receives the push notification in the background and saves the new data to local storage.

[1753] Response in the event of a communication failure

[1754] The device detects a communication failure

[1755] Step 1:

[1756] The device periodically checks the Internet connection to detect whether any communication problems have occurred.

[1757] The device uses existing data

[1758] Step 2:

[1759] When a device detects a communication failure, it accesses the latest data stored in the background.

[1760] Step 3:

[1761] The device uses short-range wireless communication (Bluetooth, Wi-Fi Direct, etc.) to send necessary information to other users' devices nearby.

[1762] Step 4:

[1763] The information received by other users' devices is analyzed and displayed to the user. For example, it displays, "Even during a communication outage, the nearest evacuation shelter is XX Elementary School."

[1764] Example 2

[1765] 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."

[1766] Conventional disaster information systems are required to provide prompt and accurate information in response to user inquiries, but they lack support that takes into account the user's emotional state. Furthermore, effective information provision methods during communication disruptions are limited, making it difficult to provide useful information to users during disasters. Therefore, the objective of this invention is to provide a disaster information provision system that utilizes generative AI and emotion recognition technology to provide appropriate information according to the user's emotional state and that has effective information provision methods even during communication disruptions.

[1767] 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.

[1768] In this invention, the server includes means for collecting and analyzing disaster information using a generation AI, means for receiving inquiries from users and providing relevant disaster information, means for automatically updating data in the background, means for using existing data to perform short-range wireless communication during communication disruptions, and means for analyzing the user's emotions using an emotion recognition engine and adjusting the information provided by the generation AI. This enables prompt and accurate information provision even during disasters, and provides support tailored to the user's emotional state. As a result, disaster victims and their relatives can quickly and appropriately obtain the information they need and take safe action.

[1769] "Generative AI" is a system that uses artificial intelligence technology to collect and analyze data and generate optimal information in response to user requests.

[1770] "Disaster information" refers to various information related to disasters, such as the occurrence and progression of the disaster, the extent of the impact, and the location of evacuation shelters.

[1771] A "user inquiry" is an input made by a user to the system to request specific information or assistance, and may be in the form of text, voice, image, or the like.

[1772] "Automatically updating data in the background" means that the system has the function of periodically collecting the latest data and updating the database without requiring user operation.

[1773] "Communication failure" refers to a network malfunction or disruption that occurs when a system sends or receives data via the Internet or other means of communication.

[1774] "Existing data" refers to information that has been stored in the system in advance and is available even in the event of a communication failure.

[1775] "Near field wireless communication" refers to technologies such as Wi-Fi Direct and Bluetooth that enable data communication between devices over short distances.

[1776] An "emotion recognition engine" refers to a technology or system that analyzes emotions from a user's voice, text, facial expressions, etc., and determines the user's emotional state.

[1777] "Providing appropriate information" means providing information in a form that best suits the user's situation and emotional state, with the aim of improving the user's sense of security and appropriateness of behavior.

[1778] The present invention is a system that uses a generative AI model to provide accurate and prompt information when a disaster occurs, and combines it with an emotion recognition engine that recognizes user emotions to provide more appropriate support. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described in detail below.

[1779] System configuration

[1780] This system mainly consists of the following hardware and software components.

[1781] 1. Server

[1782] It is equipped with a generative AI model and has the ability to collect and analyze disaster information.

[1783] It is equipped with an emotion recognition engine that analyzes the user's emotions.

[1784] Regularly collect data from government agencies, media, and social networking services to update the database.

[1785] If communication is normal, the latest disaster information will be sent to the user's device via push notification.

[1786] 2. Terminal

[1787] It has the function of sending user inquiries to the server.

[1788] It has the function of displaying information received from the server to the user.

[1789] Data is updated in the background, and in the event of a communication failure, short-range wireless communication is performed using existing data.

[1790] 3. Users

[1791] Use a device such as a smartphone or tablet to inquire about the information you need.

[1792] Take appropriate action based on the information inquired.

[1793] Program processing explanation

[1794] The server receives inquiries from users and analyzes them using a generative AI model. It also analyzes the user's emotions using an emotion recognition engine and adjusts the information provided. The generative AI model is trained using a large dataset, allowing it to provide the latest information in real time. The specific processing flow is as follows:

[1795] 1. User operations

[1796] The user launches the app and asks for the required information by voice or text, for example, by entering a prompt such as "Please tell me the location of the evacuation shelter."

[1797] 2. Terminal Processing

[1798] The device converts the user's inquiry into text and uses an emotion recognition engine to analyze emotional data from the user's voice and facial expressions.

[1799] The analyzed data and the user's query are sent to the server.

[1800] 3. Server Processing

[1801] The server uses a generative AI model based on the received data to analyze the user's query and collect and compile the necessary disaster information.

[1802] The emotional state of the user is analyzed again using an emotion recognition engine, and the generated information is provided to the user in an optimal form.

[1803] For example, if the user is in a panic, a message such as "The nearest evacuation shelter is currently XX Elementary School. Please remain calm and evacuate" is generated.

[1804] 4. Display by terminal

[1805] The information received from the server is displayed to the user, and necessary support information is provided.

[1806] Examples of concrete examples and prompts

[1807] Specific examples

[1808] The user launches a smartphone app and speaks, "Is there a safe place nearby?"

[1809] The device converts the voice data into text and uses an emotion recognition engine to analyze whether the user is in a state of agitation.

[1810] The server analyzes the query using a generative AI model and generates information about the nearest evacuation shelter and a message such as "Please remain calm and evacuate."

[1811] The device displays this to the user, providing necessary information and a sense of security.

[1812] Prompt Sentence Examples

[1813] 1. "Please tell me where the evacuation shelter is."

[1814] 2. "Is there a safe place nearby?"

[1815] 3. "Can you give me an update on the current situation?"

[1816] As described above, by combining a generative AI model and an emotion recognition engine, the system of the present invention can provide prompt and accurate information during disasters and provide appropriate support according to the user's emotional state. This allows disaster victims and those involved to quickly and appropriately obtain the necessary information and take safe action.

[1817] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1818] System program processing flow

[1819] Step 1: User Enters Information

[1820] The user launches the app and speaks, "Please tell me the location of the evacuation shelter." This voice input is sent to the device and converted to text on the spot. The converted text becomes the input data for the information query.

[1821] Input: Audio input

[1822] Output: The query converted to text

[1823] Step 2: The device analyzes and transmits the emotion data.

[1824] The device analyzes the user's voice and facial expressions using an emotion recognition engine to generate emotional data about the user. The specific emotional state (e.g., panic, calm, etc.) is analyzed and sent to the server along with a text query.

[1825] Input: Text-converted query, user voice and facial expression data

[1826] Output: Parsed emotion data, sent to the server along with the query

[1827] Step 3: The server parses the information

[1828] The server uses a generative AI model to collect and analyze the necessary disaster information based on the received inquiry and emotion data. Specifically, it collects the latest disaster information from government agencies, media, and social media, and generates information appropriate for the user's inquiry.

[1829] Input: Text-converted query, emotion data

[1830] Output: Disaster information in response to user inquiries

[1831] Step 4: The server adjusts the information based on the emotion data

[1832] The server adjusts the disaster information it generates based on the user's emotional data analyzed by an emotion recognition engine. For example, if the user is in a panic, it generates information containing a message that gives a sense of security.

[1833] Input: Disaster information and emotion data in response to user inquiries

[1834] Output: Emotionally sensitive information

[1835] Step 5: The server sends the information to the device

[1836] The server then sends the adjusted disaster information to the terminal. Communication is performed using secure protocols such as SSL / TLS.

[1837] Input: Emotionally sensitive information

[1838] Output: Data sent to the terminal

[1839] Step 6: The device displays the information to the user

[1840] The device analyzes the information it receives and displays it in an optimal way for the user, including the location of evacuation shelters and sensitive messages.

[1841] Input: Adjusted information sent from the server

[1842] Output: The final information displayed to the user

[1843] Specific examples of operation

[1844] Step 1: User Enters Information

[1845] The user opens the app on their smartphone and says, "Tell me where the nearest safe place is." The speech is converted into text in real time and displayed on the device.

[1846] Step 2: The device analyzes and transmits the emotion data.

[1847] The device uses an emotion recognition engine to analyze the user's tone of voice and facial expressions to determine their emotional state. For example, the device sends a text query along with the analyzed emotional state, such as "anxiety," to the server.

[1848] Step 3: The server parses the information

[1849] Based on the received data, the server uses a generative AI model to collect and analyze the latest disaster information, including "nearby evacuation shelters." The information is extracted from the database and a list of the nearest currently available evacuation shelters is generated.

[1850] Step 4: The server adjusts the information based on the emotion data

[1851] The server takes into account the results of the emotion recognition engine and adjusts the information to suit a user in a state of panic. Specifically, it generates information containing a reassuring message such as, "XX Elementary School is the nearest evacuation shelter. Please remain calm and evacuate."

[1852] Step 5: The server sends the information to the device

[1853] The server sends the tailored information to the device, including a map of the evacuation center, its address, and a reassuring message.

[1854] Step 6: The device displays the information to the user

[1855] The device displays the received information to the user, who can then check the map on the app screen along with a message saying, "XX Elementary School is the nearest evacuation shelter. Please remain calm and evacuate."

[1856] Through the above processing, this system can provide appropriate information according to the user's emotional state and support safe behavior in the event of a disaster.

[1857] (Application example 2)

[1858] 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."

[1859] Existing disaster information systems struggle to provide accurate and timely information during disasters, and also to provide appropriate support that takes into account the user's emotions. It is particularly difficult to continue providing appropriate information when communication failures occur. Furthermore, there is a lack of methods to reduce the stress and anxiety users feel during disasters and encourage effective evacuation behavior.

[1860] 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 means for collecting and analyzing disaster information using a generation AI, means for receiving inquiries from users and providing corresponding disaster information, means for automatically updating data in the background, means for performing short-range wireless communication using existing data in the event of a communication failure, and means for analyzing the user's emotions using emotion recognition technology and adjusting the information to be provided based on the results. This makes it possible to provide accurate and prompt information even during a disaster and provide appropriate support according to the user's emotions.

[1861] "Generative AI" is an artificial intelligence technology that automatically generates information based on input data.

[1862] "Disaster information" refers to various information related to natural and man-made disasters, including the location of evacuation shelters, damage status, and first aid information.

[1863] "Analysis" is the process of breaking down and analyzing collected data to extract useful information.

[1864] "User" means any person or entity that uses the System.

[1865] An "inquiry" refers to a question or request made by a user to the system for information or assistance.

[1866] "Automatically updating data in the background" is a function that allows the system to automatically obtain and store the latest information even when the user is not operating the system.

[1867] "Communication outage" refers to a situation in which the Internet or other means of communication do not function properly.

[1868] "Existing Data" refers to data that has previously been collected and stored by the system.

[1869] "Near field wireless communication" refers to exchanging data using short-range wireless communication technologies such as Bluetooth and Wi-Fi Direct.

[1870] "Emotion recognition technology" is a technology that determines a user's emotions from the tone of their voice, facial expression, text content, etc.

[1871] The present invention is a system that uses generative AI and emotion recognition technology to provide accurate and prompt information in the event of a disaster, and provides appropriate support according to the user's emotions. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described below.

[1872] System Overview

[1873] 1. Server Functions

[1874] The server is equipped with generative AI and emotion recognition technology, and has the ability to collect and analyze disaster information, allowing it to retain accurate and up-to-date information and generate information in response to user inquiries.

[1875] The server receives inquiries from users and uses generative AI to generate the optimal answer. It also uses emotion recognition technology to analyze the user's emotions and adjust the information provided accordingly. For example, if the user is in a panic, it will provide information that includes reassuring words.

[1876] The server periodically collects new disaster information from government agencies, the media, social media, etc. and updates the data in the background, ensuring that users are always provided with the latest information.

[1877] 2. Device Features

[1878] The devices include smartphones, tablets, robots, etc., and have the ability to send inquiries from users to a server. Questions can be sent via voice input or text input.

[1879] The device receives the information from the server and displays it to the user. The displayed information is adjusted based on the user's emotions, providing more personalized assistance.

[1880] The device has the ability to receive updated data from the server in the background and store the latest data. Even if communication is interrupted, the stored data can be used to provide information to other devices via short-range wireless communication (Bluetooth, Wi-Fi Direct, etc.).

[1881] 3. User Operation

[1882] The user launches the application installed on the device and requests the necessary information. Inquiries are made via voice, text, facial recognition, etc. Emotions are automatically analyzed and appropriate support information is provided.

[1883] For example, if a user makes a voice inquiry such as "Please tell me where the evacuation shelter is," the device sends the voice to the server, which then uses emotion recognition technology to analyze the user's state. Based on the results, the AI ​​generates information such as "Currently, the nearest evacuation shelter is XX Elementary School. Please remain calm and evacuate. We will provide telephone support if necessary," and sends it to the device.

[1884] Hardware and software used

[1885] Hardware:

[1886] Camera: Used to capture facial images and recognize emotions. Use the built-in camera on your smartphone or robot.

[1887] Smartphone / Tablet / Robot: The primary device on which the application runs.

[1888] software:

[1889] OpenCV: A library for face recognition and image processing.

[1890] TensorFlow / Keras: Machine learning frameworks for running emotion recognition models.

[1891] Transformers (Hugging Face): A library that generates text using generative AI (GPT-2).

[1892] Requests: A library for retrieving data from the disaster information API.

[1893] Specific examples

[1894] Scenario: When a disaster occurs, a user looks into their smartphone camera and asks, "Where is the evacuation shelter?"

[1895] Example prompt: "User is feeling Fear. Provide the most relevant disaster information: Nearest shelter is at XX school. Please stay calm. We can provide phone support if needed."

[1896] Example response generated: "The nearest evacuation shelter is XX Elementary School. Please remain calm. Telephone assistance will be provided if necessary."

[1897] As described above, by combining generative AI and emotion recognition technology, the system of the present invention can improve the accuracy and speed of information during disasters, and can also provide support that is tailored to the user's emotions.

[1898] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1899] Step 1:

[1900] The server automatically collects and analyzes disaster information from government agencies, media, social media, etc. It collects new disaster information as input and analyzes it using a generative AI model. The analyzed data is stored in a database and is ready for user inquiries.

[1901] Step 2:

[1902] The user activates the device's camera function and has their face recognized. The user's facial image is provided as input, and the device detects the face using OpenCV and inputs the facial image into an emotion recognition model. Emotion recognition technology (TensorFlow / Keras) analyzes the user's emotion as "panic," "fear," etc. The output is the user's emotion data.

[1903] Step 3:

[1904] The user asks the terminal a question by voice, such as "Where is the evacuation shelter?" This voice data is input into the terminal and converted into text. The converted question content and emotion data are sent to the server.

[1905] Step 4:

[1906] The server generates an optimal response based on the received question content and emotion data. The question content and emotion data are provided as input, and an appropriate answer is generated using a generative AI model (Transformers). For example, a response such as "The nearest evacuation shelter is XX Elementary School. Please remain calm. We will provide telephone support if necessary" is generated. The output is response data to be sent back to the user.

[1907] Step 5:

[1908] The terminal receives the response data from the server and displays it to the user. The terminal receives the response data from the server as input and displays it on the screen. This gives the user information about the nearest evacuation shelter and a message encouraging reassurance.

[1909] Step 6:

[1910] The server periodically updates data in the background to maintain the latest disaster information. It receives new disaster information as input, analyzes it with the generative AI model, and updates the database. This ensures that the latest information is always available to users.

[1911] Step 7:

[1912] In the event of a communication failure, the device will use the latest data stored in the background to communicate with other devices in the vicinity via short-range wireless communication (Bluetooth, Wi-Fi Direct, etc.) using the communication failure detection signal as input. This allows important information to be shared even when an internet connection is unavailable.

[1913] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1914] 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.

[1915] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1916] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1917] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1918] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1919] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1920] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1921] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1922] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1923] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1924] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1925] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1926] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1927] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1928] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1929] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1930] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1931] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1932] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1933] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1934] The following is further disclosed regarding the above embodiment.

[1935] (Claim 1)

[1936] A means of collecting and analyzing disaster information using generative AI,

[1937] means for receiving inquiries from users and providing relevant disaster information;

[1938] A means of automatically updating data in the background,

[1939] A means for performing short-range wireless communication using existing data when communication is interrupted;

[1940] A system including:

[1941] (Claim 2)

[1942] The system of claim 1, wherein the generation AI summarizes and provides analysis results in response to inquiries from users.

[1943] (Claim 3)

[1944] 2. The system according to claim 1, wherein when communication is normal, the server sends the latest information to the user terminal via push notification.

[1945] "Example 1"

[1946] (Claim 1)

[1947] A means of collecting and analyzing disaster information using generative AI models;

[1948] means for receiving inquiries from users and providing relevant disaster information;

[1949] means for returning a response generated by the server to the terminal;

[1950] means for displaying the received information to a user at the terminal;

[1951] A means for automatically updating background data by a server;

[1952] means for receiving and updating background data by the terminal;

[1953] a means for detecting communication failures and utilizing existing data;

[1954] means for performing short-range wireless communication;

[1955] A system including:

[1956] (Claim 2)

[1957] The system of claim 1, wherein the generative AI model summarizes and provides analysis results in response to user inquiries.

[1958] (Claim 3)

[1959] 2. The system according to claim 1, wherein when communication is normal, the server sends the latest information to the terminal via push notification.

[1960] "Application Example 1"

[1961] (Claim 1)

[1962] A means of collecting and analyzing disaster information using generative AI,

[1963] means for receiving inquiries from users and providing relevant disaster information;

[1964] A means of automatically updating data in the background,

[1965] A means for performing short-range wireless communication using existing data when communication is interrupted;

[1966] When communication is possible, the generation AI will provide analysis results in response to inquiries entered by voice by the user.

[1967] A means to display disaster information in real time on smart devices,

[1968] A system including:

[1969] (Claim 2)

[1970] The system of claim 1, wherein the generation AI summarizes and provides analysis results in response to inquiries from users.

[1971] (Claim 3)

[1972] 2. The system according to claim 1, wherein when communication is normal, the server sends the latest information to the user terminal via push notification.

[1973] "Example 2: Combining Emotion Engines"

[1974] (Claim 1)

[1975] A means of collecting and analyzing disaster information using generative AI,

[1976] means for receiving inquiries from users and providing relevant disaster information;

[1977] A means of automatically updating data in the background,

[1978] A means for performing short-range wireless communication using existing data when communication is interrupted;

[1979] A means for analyzing the user's emotions using an emotion recognition engine and adjusting the information provided by the generation AI;

[1980] A system including:

[1981] (Claim 2)

[1982] The system of claim 1, wherein the generation AI summarizes and provides analysis results in response to inquiries from users.

[1983] (Claim 3)

[1984] 2. The system according to claim 1, wherein when communication is normal, the server sends the latest information to the user terminal via push notification.

[1985] "Application example 2 when combining emotion engines"

[1986] (Claim 1)

[1987] A means of collecting and analyzing disaster information using generative AI,

[1988] means for receiving inquiries from users and providing relevant disaster information;

[1989] A means of automatically updating data in the background,

[1990] A means for performing short-range wireless communication using existing data when communication is interrupted;

[1991] A means for analyzing a user's emotions using emotion recognition technology and adjusting information to be provided based on the results of the analysis;

[1992] A system including:

[1993] (Claim 2)

[1994] The system of claim 1, wherein the generating AI generates and provides appropriate support information based on the user's emotions.

[1995] (Claim 3)

[1996] 2. The system according to claim 1, wherein when communication is normal, the server sends the latest information based on the user's emotions to the user terminal via push notification. [Explanation of symbols]

[1997] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting and analyzing disaster information using generative AI, means for receiving inquiries from users and providing relevant disaster information; A means of automatically updating data in the background, A means for performing short-range wireless communication using existing data when communication is interrupted; A system including:

2. The system according to claim 1, wherein the generation AI summarizes and provides analysis results in response to inquiries from users.

3. The system according to claim 1, wherein when communication is normal, the server sends the latest information to the user terminal by push notification.

Images