System

Abstract

A system is provided.SOLUTION: A system includes a means for receiving input information and position information from a disaster victim, a means for transmitting a push notification to the disaster victim when a disaster occurs, a means for analyzing the received information and automatically estimating the safety situation of the disaster victim, and a means for notifying a specific contact destination of the estimated safety situation.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 large-scale disaster occurs, it is difficult for victims and evacuees to obtain the necessary information quickly and accurately. In particular, the following challenges exist:

[0005] 1. It is not possible to quickly confirm the safety of victims.

[0006] 2. It is difficult to grasp the congestion situation at evacuation centers in real time.

[0007] 3. The reliability of disaster-related information is unclear, making it difficult for users to obtain accurate information.

[0008] 4. Foreigners face language barriers and find it difficult to obtain important information.

[0009] 5. It is difficult to allocate volunteers efficiently, reducing the effectiveness of relief efforts.

[0010] To solve these problems, existing communication and information processing technologies have limitations, and comprehensive information aggregation and multifunctional support systems are required. [Means for solving the problem]

[0011] In order to solve the above problems, the present invention provides the following means:

[0012] We provide a system that includes a means for receiving input information and location information from disaster victims, a means for sending push notifications to disaster victims when a disaster occurs, a means for analyzing the received information and automatically estimating the safety status of disaster victims, and a means for notifying specific contacts of the estimated safety status (Claim 1).

[0013] We provide a system that includes a means for receiving images from cameras installed at each evacuation shelter, a means for analyzing the received images and determining the congestion status of the evacuation shelter in real time, and a means for responding to user inquiries about the congestion status based on the analysis results (Claim 2).

[0014] A system is provided that includes a means for collecting disaster-related information from online social networks and official institutions, a means for evaluating the reliability of the collected information, and a means for providing users with reliable information based on the evaluation results (Claim 3).

[0015] A system is provided that includes a means for performing multilingual translation, a means for translating messages in the native language received from foreign users and generating appropriate responses, and a means for retranslating the generated responses and providing them to the foreign users (Claim 4).

[0016] A system is provided that includes a means for registering the skill sets and location information of volunteers, a means for matching requests for assistance with the skill sets and location information of volunteers, a means for selecting the most suitable volunteer and notifying them of the request for assistance, and a means for tracking the progress of volunteers (Claim 5).

[0017] "Victims" are people who are directly affected by a disaster.

[0018] "Location Information" means geographic coordinate information obtained through GPS or other location measurement technology.

[0019] "Push notification" is a real-time notification message that is proactively sent by a server to a user's device.

[0020] "Input information" refers to data such as text and images sent by a user through a terminal.

[0021] "Safety status" is information that indicates whether the victims are safe or not.

[0022] "Means for receiving" refers to the technical device or method by which the server obtains information from the user.

[0023] "Means for analysis" means the technical devices and methods used to analyze data within the server and determine its meaning and context.

[0024] "Notification means" refers to the technical device or method by which a server sends specific information to a user or other system.

[0025] A "camera" is a device that captures images and records the data in digital form.

[0026] "Video" refers to dynamic visual information data captured by a camera or other device.

[0027] "Crowding situation" is information that indicates the degree of crowding in evacuation shelters or specific areas.

[0028] An "enquiry" is a question or request sent by a user to the system.

[0029] An "online social network" is a platform for sharing information and making social connections over the Internet.

[0030] "Credibility assessment" is an analytical method for determining the accuracy and veracity of collected information.

[0031] "Translation" is the process of converting text written in one language into another language.

[0032] "Interpretation support" is support for translating conversations and messages into other languages ​​in real time to facilitate mutual understanding.

[0033] A "skill set" is a collection of skills and abilities required for a particular job or activity.

[0034] A "matching means" is a technical device or method for comparing different data and finding matching or compatible information.

[0035] "Tracking means" means any technological device or method for continuously monitoring and recording location information or the progress of an activity.

[0036] These definitions clarify the meaning of key terms in the claims. [Brief explanation of the drawings]

[0037] [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

[0038] 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.

[0039] First, the terms used in the following description will be explained.

[0040] 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).

[0041] 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.

[0042] 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.

[0043] 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.

[0044] 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."

[0045] [First embodiment]

[0046] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0047] 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.

[0048] 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).

[0049] 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.

[0050] 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.

[0051] 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.

[0052] 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.

[0053] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0054] 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.

[0055] 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.

[0056] 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.

[0057] 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."

[0058] The present invention provides a system for ensuring the safety of disaster victims and evacuees by enabling them to quickly and accurately obtain necessary information in the event of a disaster. Details of how to implement this system are described below.

[0059] 1. Confirming the safety of disaster victims

[0060] This system includes a function for checking the safety status of disaster victims when a disaster occurs. When a disaster occurs, the server sends a push notification to users in the affected area. Users respond to the notification received through their smartphone or other device and enter their safety status and current location. The device sends the entered information and location information to the server, which analyzes this and automatically estimates the safety status of the disaster victims. The estimated safety status is then notified to specific contacts.

[0061] Specific examples

[0062] For example, when an earthquake occurs, the server quickly sends a notification to all users in the affected area asking, "Are you safe?" Users who respond reply, "I'm safe," and this is sent along with their location information. Based on this information, the server analyzes the user's safety status and notifies their family and friends.

[0063] 2. Understanding the congestion situation at evacuation shelters

[0064] Cameras installed at evacuation centers regularly capture footage and upload it to a server. The server analyzes these images using AI image recognition technology to grasp the congestion status of each evacuation center in real time. When a user inquires about the congestion status of a shelter through the chatbot, the server provides the user with an answer based on the analysis results.

[0065] Specific examples

[0066] The server periodically analyzes the camera footage from shelter A and detects that the shelter is full. When a user asks the chatbot, "How crowded is the nearest shelter?", the server replies, "Shelter A is full. There is space available at shelter B."

[0067] 3. Collection of disaster-related information and reliability assessment

[0068] The server collects disaster-related information from social media and official sources. It then applies a reliability evaluation algorithm to the collected information to select the most reliable information. When a user requests the latest disaster information through the chatbot, the server provides the selected, reliable information.

[0069] Specific examples

[0070] When a tsunami warning is issued, the server collects information from social media and official organizations and evaluates its reliability. When a user asks, "Please tell me the latest disaster information," the server responds, "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately."

[0071] 4. Multilingual translation and interpretation support

[0072] The server has a multilingual translation function, so when a foreign user asks the chatbot a question in their native language, the server translates it into the appropriate language in real time, and the translated answer is provided to the user.

[0073] Specific examples

[0074] When an English-speaking user asks the chatbot, "What should I do now?", the server translates and replies, "Please evacuate now. There is an earthquake, so please stay safe."

[0075] 5. Matching volunteer skills and locations

[0076] The server registers the skill sets and location information of volunteers in a database, and in the event of a disaster, it compares the request for assistance with the skill sets and location information of the volunteers to select and notify the most suitable volunteers. It also tracks the progress of volunteer activities.

[0077] Specific examples

[0078] If a shelter needs medical assistance, the server notifies nearby registered volunteers with medical skills. When a volunteer responds, "I'm on my way to help," the server provides the specific location of the shelter and tracks the volunteer's progress.

[0079] As described above, the present invention is a system that enables quick and accurate provision of information and support to disaster victims and evacuees in the event of a disaster, thereby ensuring the safety of disaster-stricken areas and enabling quick response.

[0080] The processing flow will be explained below.

[0081] Confirming the safety of victims

[0082] Step 1:

[0083] When the server detects a disaster, it sends a push notification to users in the affected area.

[0084] Specific operation: The server references a database of affected areas and sends a message to all relevant users asking, "Are you safe?"

[0085] Step 2:

[0086] The user receives the notification and enters a response.

[0087] Specific action: The user types a message into the device, such as "I'm safe" or "I need help," and sends it.

[0088] Step 3:

[0089] The device sends input information and location information to the server.

[0090] Specific operation: The device's GPS function obtains the current location and sends it to the server along with the entered text message.

[0091] Step 4:

[0092] The server analyzes the received information and automatically estimates the safety status of the victims.

[0093] How it works: The server uses an AI model to analyze messages and location information to estimate the safety status of the person. The results are stored in a database.

[0094] Step 5:

[0095] The server notifies the specific contact of the estimation result.

[0096] Specific operation: Based on the estimated safety information, the server sends the information to pre-registered contacts (family, friends, etc.).

[0097] Grasping the congestion situation at evacuation centers

[0098] Step 1:

[0099] Cameras installed at evacuation centers regularly capture footage and upload it to a server.

[0100] Specific operation: The camera captures video at regular intervals and sends the data to the server.

[0101] Step 2:

[0102] The server analyzes the received video.

[0103] Specific operation: The server inputs the video into an AI image recognition model, counts the number of people, and determines the congestion level.

[0104] Step 3:

[0105] A user inquires about congestion status via a chatbot.

[0106] Specific operation: The user types a question into the chatbot on their smartphone, such as "How crowded is the nearest evacuation shelter?", and sends it.

[0107] Step 4:

[0108] The server provides the user with an answer based on the analysis results.

[0109] Specific operation: The server checks the analysis results of the AI ​​model, generates an answer such as "Shelter A is full. There is space available in shelter B," and sends it back to the user.

[0110] Collection and reliability assessment of disaster-related information

[0111] Step 1:

[0112] The server collects disaster-related information from social media and official organizations.

[0113] Specific operation: The server uses scraping tools and APIs to collect disaster information from social media and official organizations and stores it in a database.

[0114] Step 2:

[0115] The server applies a trustworthiness evaluation algorithm to the collected information.

[0116] What it does: The server uses text analysis and credibility assessment algorithms to score the credibility of each piece of information.

[0117] Step 3:

[0118] A user asks a chatbot for the latest disaster information.

[0119] Specific operation: The user types "Please tell me the latest disaster information" into the chatbot and sends it.

[0120] Step 4:

[0121] The server selects reliable disaster information and responds to the user.

[0122] Specific operation: The server selects information with high reliability, generates a message such as "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately," and sends it back to the user.

[0123] Multilingual translation and interpretation support

[0124] Step 1:

[0125] The server puts the multilingual translation module into standby mode.

[0126] Specific operation: The server initializes the real-time translation API and prepares for multilingual support.

[0127] Step 2:

[0128] Foreign users ask questions to the chatbot in their native language.

[0129] What happens: The user types a message in their native language and sends it to the chatbot.

[0130] Step 3:

[0131] The server translates the received message and generates an appropriate response.

[0132] Specific operation: The server calls the translation API to translate the message into Japanese, then generates an appropriate corresponding message, translates it again into the foreign language, and sends it.

[0133] Step 4:

[0134] The terminal displays the translated message to the user.

[0135] Specific operation: The message received by the user's device is displayed in the user's native language.

[0136] Matching volunteer skills and locations

[0137] Step 1:

[0138] Users register their skill set and location information.

[0139] Specific operation: Volunteers enter their skills and current location through the chatbot and register on the server.

[0140] Step 2:

[0141] The server stores the registered volunteer information in a database.

[0142] Specific operation: The server saves the entered information in a database and makes it available for verification.

[0143] Step 3:

[0144] When a request for assistance is received, the server selects the most suitable volunteer and notifies them.

[0145] Specific operation: The server compares the request for assistance with the volunteers' skill sets and location information, selects the most suitable volunteer, and sends a notification to the selected volunteer.

[0146] Step 4:

[0147] Volunteer users are notified and begin providing support.

[0148] Specific actions: The volunteer replies to the notification by saying "I'm heading to help" and receives information about the specific location of the help from the server.

[0149] Step 5:

[0150] The terminal reports the volunteer's progress to the server.

[0151] Specific operation: Volunteers' devices send GPS data to the server in real time and report the progress of their activities.

[0152] This enables the system to provide quick and accurate information and support to disaster victims and evacuees.

[0153] Example 1

[0154] 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."

[0155] When a disaster occurs, it is necessary to quickly and accurately collect information and provide it to victims and evacuees. However, conventional systems take time to collect, analyze, and provide information, and there is a possibility that the information may be unreliable. Furthermore, there are issues with insufficient multilingual support and appropriate coordination of volunteers. The present invention aims to solve these issues.

[0156] 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.

[0157] In this invention, the server includes means for receiving input information and location information from disaster victims, means for sending push notifications to disaster victims when a disaster occurs, means for analyzing the received information and automatically estimating the safety status of the disaster victims, means for notifying specific contacts of the estimated safety status, means for providing a multilingual translation function in real time, and means for selecting and notifying the most suitable volunteers by comparing the volunteers' skill sets and location information. This makes it possible to quickly collect and analyze reliable information when a disaster occurs, and to accurately respond to multiple languages ​​and coordinate volunteers.

[0158] "Input information from disaster victims" refers to information that disaster victims record about their situation and location during a disaster and send to the system.

[0159] "Location Information" means current geographic coordinate data obtained using GPS or other location-determining technology.

[0160] "Push notification" refers to an automatic notification message sent by a server to a user's device.

[0161] "Analysis" refers to the act of processing data to extract meaningful information.

[0162] "Safety status" refers to information indicating the status of life and safety of disaster victims, such as whether they are safe.

[0163] "Contact information" refers to the contact information of family members, friends, etc. who will be notified of the victim's safety.

[0164] "Multilingual Translation Functionality" means a system function that automatically translates text or messages between different languages.

[0165] "Volunteer skill set" refers to the specific skills and experience a volunteer possesses.

[0166] "Location matching" refers to the process of analyzing volunteers' location information and matching it with locations where assistance is needed.

[0167] "Camera footage" refers to images and video data captured using a camera device.

[0168] "AI image recognition technology" refers to technology that uses artificial intelligence to analyze the content of images and videos.

[0169] "Online social network" refers to a system for sharing information through internet services such as social networking sites.

[0170] "Official sources" refers to reliable sources provided by government agencies or authorized organizations.

[0171] A "trustworthiness assessment algorithm" refers to a logical method for assessing the reliability of acquired information based on numerical values ​​and criteria.

[0172] The present invention relates to a system for providing information quickly and accurately and supporting disaster victims in the event of a disaster. The details of implementing this system are described below.

[0173] 1. Hardware and software configuration

[0174] server

[0175] The server has the following features:

[0176] Database Management System (DBMS)

[0177] Push notification server

[0178] AI image recognition engine

[0179] Multilingual translation engine (such as Google Translate API)

[0180] Reliability Evaluation Algorithm

[0181] Volunteer Matching Algorithm

[0182] Terminal

[0183] The device used by the user has the following features:

[0184] GPS Modules

[0185] Camera Device

[0186] Wireless communication module (Wi-Fi, LTE / 5G)

[0187] Newspaper reception application

[0188] 2. Confirming the safety of disaster victims

[0189] The server uses earthquake sensors and weather data to detect the occurrence of a disaster. When a disaster occurs, the server sends a push notification to users in the affected area asking, "Are you safe?" Users receive the notification on their smartphones or other devices and respond by inputting their safety status (e.g., "safe," "injured," "unable to provide information") and location information. The devices then send this information to the server. The server analyzes the received information, estimates the safety status of the victims, and notifies specific contacts.

[0190] Specific examples

[0191] The server detects the occurrence of an earthquake and sends a push notification to all users in the affected area asking, "Are you safe?"

[0192] The user responds "I'm safe," and the system uses GPS to obtain their current location and sends the results to the server.

[0193] The server analyzes the received information and notifies the user's family that "the user is safe."

[0194] 3. Understanding the congestion situation at evacuation shelters

[0195] Cameras installed at evacuation centers regularly capture footage and upload it to a server. The server then analyzes the footage using AI image recognition technology to grasp the congestion status of each evacuation center in real time. When a user inquires about the congestion status of a shelter through the chatbot, the server provides the user with an answer based on the analysis results.

[0196] Specific examples

[0197] The camera takes video of the evacuation center every minute and uploads the data to a server.

[0198] The server analyzes the video and calculates the level of congestion, such as "Shelter A is currently 70% full."

[0199] When a user asks the chatbot, "How crowded is shelter A?", the server responds with the current congestion situation.

[0200] 4. Collection of disaster-related information and reliability assessment

[0201] The server collects disaster-related information from social media and official sources, applies a reliability evaluation algorithm to the collected information, and stores the most reliable information in a database. When a user requests the latest disaster information through the chatbot, the server extracts and provides the most reliable information from the database.

[0202] Specific examples

[0203] The server collects disaster information from the Twitter API and RSS feeds from official organizations.

[0204] A reliability assessment algorithm scores the reliability of the information and stores it in a database.

[0205] When a user asks, "Please tell me the latest tsunami information," the server will provide reliable information and reply, "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately."

[0206] 5. Multilingual translation and interpretation support

[0207] The server uses a multilingual translation engine to instantly translate questions from foreign users and provide answers in the appropriate language. When a user asks a question in their native language, the server automatically translates the question, generates an appropriate answer, translates it, and provides it to the user.

[0208] Specific examples

[0209] An English-speaking user types "What should I do now?" into the chatbot.

[0210] The server translates the question into Japanese as "What should I do now?" and generates an appropriate answer.

[0211] The generated answer is translated back into English and replied to the user, "Please evacuate immediately. Ensure your safety as an earthquake is occurring."

[0212] 6. Matching volunteer skillsets with location information

[0213] The server registers the skill sets and location information of volunteers in a database. In the event of a disaster, the server matches requests for assistance with the skill sets and location information of volunteers to select the most suitable volunteers. Selected volunteers are notified and the progress of the assistance is tracked.

[0214] Specific examples

[0215] Volunteers register their medical skills and current location on a web portal.

[0216] A server receives a request for medical assistance from an evacuation shelter.

[0217] The server searches the database and selects the nearest suitable volunteer.

[0218] A notification is sent to the selected volunteers saying, "Medical assistance is needed at shelter B. Can you go?"

[0219] When a volunteer responds, "I'm on my way to help," the server provides the location of the shelter and the type of assistance needed, and tracks their progress in real time.

[0220] This enables the present invention to provide rapid and accurate information and support in the event of a disaster, ensuring the safety of disaster-stricken areas and enabling rapid response.

[0221] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0222] 1. Confirming the safety of disaster victims

[0223] Step 1:

[0224] The server detects the occurrence of disasters based on earthquake sensor and meteorological data. As input, it receives real-time data from earthquake sensors and meteorological stations. As output, it generates information on the occurrence of a detected disaster.

[0225] Step 2:

[0226] When the server detects a disaster, it sends a push notification to users in the affected area. The input is the detected disaster information and the contact information of users in the affected area. The output is a generated push notification message that is sent to the user's device.

[0227] Specific behavior:

[0228] The server sends a push notification with the message "Are you OK?"

[0229] Step 3:

[0230] Users receive push notifications on their smartphones or other devices and enter their safety status and location information. The inputs include the safety status entered by the user through the device and location information obtained from the device's GPS function. The output is that the device sends the entered data to the server.

[0231] Specific behavior:

[0232] The user selects an option such as "I'm fine" or "I'm injured."

[0233] The device obtains location information from GPS and sends it to the server along with safety information.

[0234] Step 4:

[0235] The server analyzes the received information and estimates the safety status of the victims. The inputs are the safety status information and location information sent from the device. The output generates the safety status as an analysis result.

[0236] Specific behavior:

[0237] The server processes the data it receives using machine learning models and rule-based analysis algorithms to estimate the safety of victims.

[0238] Step 5:

[0239] The server notifies specific contacts (family and friends) of the estimated safety status. The inputs are the analyzed safety status and the victim's contact information. The output is a notification message sent to the contacts.

[0240] Specific behavior:

[0241] The server sends a message to family and friends saying "You are safe."

[0242] 2. Understanding the congestion situation at evacuation shelters

[0243] Step 1:

[0244] Cameras installed at evacuation shelters periodically capture video. The input is the video data captured by the camera device. The output is the generated video file that is saved.

[0245] Specific behavior:

[0246] The camera captures and stores footage every minute.

[0247] Step 2:

[0248] The device uploads the captured video to the server. The input is the video data obtained from the camera. The output is the video data that is sent to the server.

[0249] Specific behavior:

[0250] The device sends video data to the server via Wi-Fi or mobile network.

[0251] Step 3:

[0252] The server analyzes the received video using AI image recognition technology to grasp the congestion situation in real time. The input is the video data sent from the device. The output is an analyzed congestion level value.

[0253] Specific behavior:

[0254] The server uses a deep learning model to analyze the video data, count the number of people inside the shelter, and calculate the congestion rate.

[0255] Step 4:

[0256] A user inquires about the congestion status of a shelter through a chatbot. The input is a text question that the user enters into the chatbot. The output is a query request that is sent to the server.

[0257] Specific behavior:

[0258] A user asks the chatbot, "How crowded is shelter A?"

[0259] Step 5:

[0260] The server provides a response to the user based on the analysis results. The inputs are a user query request and the analyzed congestion data. The output is a response message that is sent to the user.

[0261] Specific behavior:

[0262] The server responds, "Shelter A is currently 70% full."

[0263] 3. Collection of disaster-related information and reliability assessment

[0264] Step 1:

[0265] The server periodically collects disaster-related information from social media and official organizations. The input data is from social media APIs and official RSS feeds. The output data is stored in a database.

[0266] Specific behavior:

[0267] The server collects disaster information using the Twitter API and RSS feeds from official organizations.

[0268] Step 2:

[0269] The server applies a reliability assessment algorithm to the collected information. The input is the collected disaster-related information. The output is the information with a reliability score.

[0270] Specific behavior:

[0271] A reliability assessment algorithm scores the reliability of the information and stores it in a database.

[0272] Step 3:

[0273] A user requests the latest disaster information through a chatbot. The input is a text question that the user types into the chatbot. The output is a query request that is sent to the server.

[0274] Specific behavior:

[0275] A user asks, "What is the latest tsunami information?"

[0276] Step 4:

[0277] The server extracts reliable information from the database and provides it to the user. The input is the query request and the information in the database with a high reliability score. The output is a response message that is sent to the user.

[0278] Specific behavior:

[0279] The server responds, "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately."

[0280] 4. Multilingual translation and interpretation support

[0281] Step 1:

[0282] The user asks the chatbot a question in their native language. The input is the text entered by the user in their native language. The output is a generated question request that is sent to the server.

[0283] Specific behavior:

[0284] A user asks in English, "What should I do now?"

[0285] Step 2:

[0286] The server automatically identifies the input question and passes it to the translation engine. The input is a question request from the user. The output is generated text data that is sent to the translation engine.

[0287] Specific behavior:

[0288] The server sends the question to the Google Translate API, which translates it from English to Japanese.

[0289] Step 3:

[0290] The translation engine translates the question into the appropriate language. It takes as input the text data sent from the server and produces as output the translated question text.

[0291] Specific behavior:

[0292] Google Translate API translates "What should I do now?" into Japanese as "What should you do now?"

[0293] Step 4:

[0294] The server generates answers to translated questions. As input, it has the translated question text. As output, it produces the generated answer text.

[0295] Specific behavior:

[0296] The server responds to the translated question with, "Evacuate now. There is an earthquake, please stay safe."

[0297] Step 5:

[0298] The server translates the answer back into the user's native language and sends a reply. The input is the generated answer text. The output is the translated answer message sent to the user.

[0299] Specific behavior:

[0300] The server then sends the generated response back to the Google Translate API, which translates it into English and replies to the user with "Please evacuate immediately. Ensure your safety as an earthquake is occurring."

[0301] 5. Matching volunteer skills and locations

[0302] Step 1:

[0303] Volunteers register their skill sets and location information in a database. The input is the skill set and location information that the volunteer enters through a web portal. The output is a saved profile of the volunteer.

[0304] Specific behavior:

[0305] Volunteers register their medical skills and current location on a web portal.

[0306] Step 2:

[0307] When a disaster occurs, the server receives requests for assistance. The input is a request for assistance from an evacuation center. The output is a corresponding request for assistance.

[0308] Specific behavior:

[0309] The server receives a request from a shelter saying "medical assistance needed."

[0310] Step 3:

[0311] The server selects appropriate volunteers from a database based on the request for assistance. The inputs are the request for assistance and the skill sets and location information of the registered volunteers. The output is a list of selected volunteers.

[0312] Specific behavior:

[0313] The server searches the database and selects the nearest suitable volunteer.

[0314] Step 4:

[0315] The server sends notifications to selected volunteers. It takes as input the contact information of the selected volunteers. It generates the notification message as output.

[0316] Specific behavior:

[0317] The server sends a notification to the selected volunteer saying, "Medical assistance is needed at shelter B. Can you go?"

[0318] Step 5:

[0319] When a volunteer responds to help, the server provides the specific location of the help and detailed information. The input is the response from the volunteer and the evacuation shelter information. The output is a message that provides the location of the help and detailed information.

[0320] Specific behavior:

[0321] When a volunteer responds, "I'm on my way to help," the server provides the location of the evacuation shelter and the type of assistance needed.

[0322] Step 6:

[0323] The server tracks the progress of volunteer activities. It has as input the progress data of volunteers. It generates progress reports as output.

[0324] Specific behavior:

[0325] The server uses the volunteers' mobile GPS to track their progress in real time until they arrive at the destination.

[0326] (Application example 1)

[0327] 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."

[0328] When a disaster occurs, there are currently insufficient means for victims and evacuees to quickly and accurately obtain the necessary information and ensure their safety. There is also a need for more efficient confirmation of the safety of victims and evacuation guidance within factories and other facilities in disaster-stricken areas. In addition, there is a need for integrated provision of functions such as the collection and reliability evaluation of disaster-related information, the understanding of the congestion situation at evacuation centers, and multilingual support, but current technology makes it difficult to fully realize these needs.

[0329] 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.

[0330] In this invention, the server includes a means for receiving input information and location information from disaster victims, a means for sending push notifications to disaster victims when a disaster occurs, a means for analyzing the received information and automatically estimating the safety status of disaster victims, a means for notifying specific contacts of the estimated safety status, a means for confirming the safety of disaster victims within the factory, providing evacuation guidance and disaster-related information, and a means for installing these functions in factory robots. This ensures the safety of disaster victims and evacuees in the event of a disaster, and enables quick and efficient safety confirmation and evacuation guidance within the factory.

[0331] "Means for receiving input information and location information from disaster victims" refers to a device or software function that collects information on the safety and current location provided by disaster victims during a disaster and processes it within the system.

[0332] "Means for sending push notifications to disaster victims when a disaster occurs" refers to a technical means for immediately notifying disaster victims of important information when a disaster occurs.

[0333] "Means for analyzing received information and automatically estimating the safety status of disaster victims" refers to algorithms or systems for automatically determining the safety status of disaster victims based on information collected from the disaster victims.

[0334] "Means of notifying specific contacts of estimated safety status" refers to communication technology that quickly conveys the situation to the victims' families and other relevant parties based on the results of the analysis.

[0335] "Means for checking the safety of disaster victims, guiding evacuation, and providing disaster-related information within factories" refers to systems and devices that are used within factories and other facilities to check the safety of people in the event of a disaster, instruct them to evacuate safely, and provide necessary information.

[0336] "Means for installing these functions in factory robots" refers to methods and technologies for incorporating the various disaster response functions mentioned above into robots used in factories.

[0337] "Means for receiving images from cameras installed at each evacuation shelter" refers to devices and technologies for acquiring images in real time through cameras installed at evacuation shelters and transmitting them to the system.

[0338] "Means of analyzing received video and determining the congestion status of evacuation centers in real time" refers to algorithms and technology that analyze camera footage and automatically determine the number of people and the level of congestion in evacuation centers.

[0339] "Means of responding to user inquiries about congestion status based on analysis results" is a function that allows an appropriate reply based on analyzed data when a user asks about the congestion status of an evacuation shelter.

[0340] "Means of collecting disaster-related information from online social networks and official institutions" refers to systems and technologies for collecting the latest disaster information from sources such as social media and official institutions.

[0341] "Means for assessing the reliability of collected information" refers to algorithms and evaluation criteria for determining how accurate the collected disaster information is.

[0342] The "means for providing users with reliable information based on the evaluation results" refers to a system or function for providing users with appropriate information using the results of the reliability evaluation.

[0343] This invention relates to a system that enables disaster victims and evacuees to quickly and accurately obtain necessary information and ensure their safety during a disaster. This system includes the following components. First, a means for receiving input information and location information from disaster victims is provided. This is used by a server to receive information sent from smartphones and other mobile devices.

[0344] Next, a means for sending push notifications to disaster victims is provided. With this means, the system can immediately send notifications such as "Are you safe?" to users in the affected area when a disaster occurs.

[0345] The system also includes an algorithm that analyzes the received information and automatically estimates the safety status of disaster victims. This algorithm estimates whether a specific disaster victim is safe based on their location and input information.

[0346] Furthermore, it includes a means to notify specific contacts of the estimated safety status. This allows the analyzed safety information to be quickly communicated to the victims' families and related parties. The system also has functions to check the safety of victims within the factory, provide evacuation guidance, and provide disaster-related information. These functions are installed on robots used within the factory to implement appropriate responses.

[0347] The system also has a means of receiving video footage from cameras installed at each evacuation center. The server receives these images, analyzes them, and determines the congestion status of the evacuation center in real time. When a user inquires about the congestion status through a chatbot or other interface, the server provides an appropriate response based on the analysis results.

[0348] It also includes a means of collecting disaster-related information from online social networks and official organizations. This information is collected by a server, and the reliability of the information is evaluated. As a result of the evaluation, reliable information is provided to users.

[0349] Furthermore, the server is capable of handling multilingual translation. When a user speaking a different language asks a question in their native language, the question is translated in real time into the appropriate language and provided.

[0350] Finally, it also includes a means for matching volunteer skill sets with location information. The server manages the skill sets and location information of volunteers registered in the database, and in the event of a disaster, it selects and notifies the most suitable volunteer in response to a request for assistance. This function allows necessary assistance to be provided quickly and efficiently.

[0351] A concrete example of this system would be the following scenario. For example, when an earthquake occurs, the server sends a notification to all users in the affected area asking, "Are you safe?" If the user replies, "I'm safe," that information and their location are sent to the server, which then notifies their family and friends. It is also possible to analyze camera footage from evacuation shelters to determine the congestion situation and provide information such as, "Evacuation shelter A is full. There is space available at evacuation shelter B."

[0352] Furthermore, in the process of collecting disaster information and assessing its reliability, if you ask, "Please tell me the latest disaster information," you will receive highly reliable information. For example, you will receive a response such as, "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately."

[0353] Examples of prompt sentences include "A disaster has occurred. Are you safe?" and "Please tell me the latest disaster information." In this way, the present invention can ensure the safety of victims and evacuees and realize a prompt response in the event of a disaster.

[0354] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0355] Step 1:

[0356] The server sends a push notification when a disaster occurs. It sends a notification to smartphones of users in the affected area asking, "Are you safe?" The input is the trigger for the disaster occurrence, and the output is the notification to the user. Users who receive the push notification can enter a response message such as "I'm safe" on their smartphones.

[0357] Step 2:

[0358] The device (user's smartphone) responds to the received push notification and sends the device's location information to the server. The input is the user's response and location information, and the output is data sent to the server. The device provides real-time information by sending a response message and location data obtained from GPS to the server.

[0359] Step 3:

[0360] The server analyzes the received response message and location information and automatically estimates the safety status of the victim. The input is the response message and location information, and the output is the estimated safety status. The server uses a machine learning algorithm to analyze the response message and estimate the status, such as "safe" or "injured." In doing so, it also takes location information into account to comprehensively evaluate the situation.

[0361] Step 4:

[0362] The server notifies specific contacts of the estimated safety status. The input is the estimated safety status result and contact information, and the output is a notification to the contacts. Based on the analysis results, safety information is sent to the victim's family and friends via SMS or email.

[0363] Step 5:

[0364] The server periodically receives video from cameras installed at evacuation centers. The input is the camera video, and the output is the received video data. The video data is uploaded to the server and analyzed in the next step.

[0365] Step 6:

[0366] The server analyzes the received video data using image recognition technology and determines the congestion status of the evacuation shelter in real time. The input is the video data and the output is the evaluation result of the congestion status. The number of people is counted using image recognition technology and the fullness of the evacuation shelter is evaluated.

[0367] Step 7:

[0368] When a user inquires about the congestion situation, the server provides an answer based on the analysis results. The input is the user's inquiry, and the output is an answer based on the analysis results. For example, if a user asks, "How crowded is the nearest evacuation shelter?" the server will answer, "Shelter A is full. There is space available at shelter B."

[0369] Step 8:

[0370] The server collects disaster-related information from online social networks and official organizations. The input is a real-time information collection request, and the output is the collected information. The server uses APIs and web scraping to obtain the latest information from social networks and official websites.

[0371] Step 9:

[0372] The server evaluates the reliability of the collected disaster-related information. The input is the collected information, and the output is the reliability evaluation result. Using a generative AI model, the reliability of each piece of information is scored and the most reliable information is selected.

[0373] Step 10:

[0374] When a user requests the latest disaster information, the server provides highly reliable information. The input is the user's inquiry, and the output is highly reliable information. For example, in response to the prompt "Tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately."

[0375] Step 11:

[0376] The server manages the skill sets and location information of volunteers registered in the database, and selects and notifies the most suitable volunteers in the event of a disaster. The input is a request for assistance and volunteer information, and the output is a notification to the volunteer. For example, if medical assistance is needed, nearby volunteers with medical skills will be contacted and asked to provide assistance.

[0377] Step 12:

[0378] If the user is from a different country, the server uses a multilingual translation function to translate into the appropriate language in real time. The input is a question in a different language, and the output is a translated answer. For example, in response to the question "What should I do now?", the server translates and responds with "Please evacuate now. There is an earthquake, so please stay safe."

[0379] Through the above processing steps, this system achieves efficient information management and rapid response in the event of a disaster.

[0380] 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.

[0381] The present invention is a system that enables disaster victims and evacuees to quickly and accurately obtain necessary information and ensure their safety during a disaster, and in particular includes a function that recognizes the user's emotions and adjusts responses. Details for implementing this system are described below.

[0382] 1. Confirming the safety of disaster victims

[0383] This system includes a function for checking the safety status of disaster victims when a disaster occurs. When a disaster occurs, the server sends a push notification to users in the affected area. Users respond to the notification received through their smartphone or other device and enter their safety status and current location. The device sends the entered information and location information to the server, which analyzes this and automatically estimates the safety status of the disaster victims. Furthermore, an emotion engine analyzes the emotions from the user's input information and reflects them in the estimation results. The estimated safety status is then notified to specific contacts.

[0384] Specific examples

[0385] For example, when an earthquake occurs, the server quickly sends a notification to all users in the affected area asking, "Are you safe?" The user replies, "I'm safe," and the notification is sent along with their location information. Based on this information, the server analyzes the user's safety status, and the emotion engine analyzes the user's emotional state. As a result, family and friends are notified of detailed safety information such as, "They're safe, but they seem worried."

[0386] 2. Understanding the congestion situation at evacuation shelters

[0387] Cameras installed in evacuation centers regularly capture footage and upload it to a server. The server analyzes these images using AI image recognition technology to grasp the congestion status of each evacuation center in real time. When a user inquires about the congestion status of a shelter through the chatbot, the server provides the user with an answer based on the analysis results. The content and priority of notifications are adjusted taking into account the user's emotional state.

[0388] Specific examples

[0389] The server periodically analyzes the camera footage from shelter A and detects that the shelter is full. When a user asks the chatbot, "How crowded is the nearest shelter?", the server replies, "Shelter A is full. There is space available at shelter B." Depending on the user's emotional state, the response is adjusted to, "Please move to shelter B as soon as possible."

[0390] 3. Collection of disaster-related information and reliability assessment

[0391] The server collects disaster-related information from social media and official sources. It then applies a reliability evaluation algorithm to the collected information to select the most reliable information. When a user requests the latest disaster information through the chatbot, the server provides the selected, reliable information. Furthermore, the server adjusts the way the information is presented depending on the user's emotional state.

[0392] Specific examples

[0393] When a tsunami warning is issued, the server collects information from social media and official organizations and evaluates its reliability. When a user asks, "Please tell me the latest disaster information," the server responds, "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately." If the user feels uneasy, the server provides additional information and detailed evacuation instructions.

[0394] 4. Multilingual translation and interpretation support

[0395] The server has a multilingual translation function, so when a foreign user asks the chatbot a question in their native language, the server translates it into the appropriate language in real time. The translated answer is then provided to the user. The emotion engine also analyzes the foreign user's emotional state and adjusts the response accordingly.

[0396] Specific examples

[0397] When an English-speaking user asks the chatbot, "What should I do now?", the server translates and replies, "Evacuate now. An earthquake is occurring, so please stay safe." If the user expresses particular anxiety, the server provides detailed evacuation routes and additional safety information.

[0398] 5. Matching volunteer skills and locations

[0399] The server registers the skill sets and location information of volunteers in a database, and in the event of a disaster, it compares the request for assistance with the volunteer's skill set and location information to select and notify the most suitable volunteer. In addition, it tracks the progress of volunteer activities, and an emotion engine analyzes their emotional state as necessary to adjust the assistance content.

[0400] Specific examples

[0401] If medical assistance is needed at a shelter, the server notifies nearby registered volunteers with medical skills. When a volunteer responds, "I'm on my way to help," the server provides the specific location of the shelter and tracks the progress of their activities. An emotion engine analyzes the volunteer's emotional state and provides necessary notifications and advice if fatigue or stress is detected.

[0402] As described above, by combining an emotion engine, the present invention is a system that enables flexible responses according to the emotional states of disaster victims and evacuees during disasters, thereby further improving safety and rapid response in disaster-stricken areas.

[0403] The processing flow will be explained below.

[0404] Confirming the safety of victims

[0405] Step 1:

[0406] When the server detects a disaster, it sends a push notification to users in the affected area.

[0407] Specific operation: The server references a database of affected areas and sends a message to all relevant users asking, "Are you safe?"

[0408] Step 2:

[0409] The user receives the notification and enters a response.

[0410] Specific action: The user types a message into the device, such as "I'm safe" or "I need help," and sends it.

[0411] Step 3:

[0412] The device sends input information and location information to the server.

[0413] Specific operation: The device's GPS function obtains the current location and sends it to the server along with the entered text message.

[0414] Step 4:

[0415] The server analyzes the received information and automatically estimates the safety status of the victims.

[0416] How it works: The server uses an AI model to analyze messages and location information to estimate the safety status of the person. The results are stored in a database.

[0417] Step 5:

[0418] The server uses an emotion engine to analyze the user's emotion from the received message.

[0419] Specific operation: The emotion engine uses text analysis to identify the user's emotional state, such as "relieved," "anxious," or "tense."

[0420] Step 6:

[0421] The server notifies specific contacts of the estimation results and sentiment analysis results.

[0422] Specific operation: Based on the estimated safety information and emotion results, the server creates detailed safety information such as "You are safe, but you seem to be worried," and sends the information to pre-registered contacts (family, friends, etc.).

[0423] Grasping the congestion situation at evacuation centers

[0424] Step 1:

[0425] Cameras installed at evacuation centers regularly capture footage and upload it to a server.

[0426] Specific operation: The camera captures video at regular intervals and sends the data to the server.

[0427] Step 2:

[0428] The server analyzes the received video.

[0429] Specific operation: The server inputs the video into an AI image recognition model, counts the number of people, and determines the congestion level.

[0430] Step 3:

[0431] A user inquires about congestion status via a chatbot.

[0432] Specific operation: The user types a question into the chatbot on their smartphone, such as "How crowded is the nearest evacuation shelter?", and sends it.

[0433] Step 4:

[0434] The server analyzes the user's emotional state.

[0435] Specific operation: The server's emotion engine determines emotions from the user's input and identifies states such as "anxiety" or "impatience."

[0436] Step 5:

[0437] The server provides the user with an answer based on the analysis results.

[0438] Specific operation: The server checks the analysis results of the AI ​​model and generates an answer such as, "Shelter A is full. There is space available in shelter B." Depending on the user's emotional state, the server adjusts the response and sends it back, such as, "Please move to shelter B as soon as possible."

[0439] Collection and reliability assessment of disaster-related information

[0440] Step 1:

[0441] The server collects disaster-related information from social media and official organizations.

[0442] Specific operation: The server uses scraping tools and APIs to collect disaster information from social media and official organizations and stores it in a database.

[0443] Step 2:

[0444] The server applies a trustworthiness evaluation algorithm to the collected information.

[0445] What it does: The server uses text analysis and credibility assessment algorithms to score the credibility of each piece of information.

[0446] Step 3:

[0447] A user asks a chatbot for the latest disaster information.

[0448] Specific operation: The user types "Please tell me the latest disaster information" into the chatbot and sends it.

[0449] Step 4:

[0450] The server analyzes the user's emotional state.

[0451] Specific operation: The emotion engine analyzes emotions from the user's question and identifies emotional states such as "anxiety" or "panic."

[0452] Step 5:

[0453] The server selects reliable disaster information and responds to the user.

[0454] Specific operation: The server selects highly reliable information and, taking into account the user's emotional state, generates a message such as "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately," and provides detailed additional information and evacuation routes.

[0455] Multilingual translation and interpretation support

[0456] Step 1:

[0457] The server puts the multilingual translation module into standby mode.

[0458] Specific operation: The server initializes the real-time translation API and prepares for multilingual support.

[0459] Step 2:

[0460] Foreign users ask questions to the chatbot in their native language.

[0461] What happens: The user types a message in their native language and sends it to the chatbot.

[0462] Step 3:

[0463] The server translates the received message and generates an appropriate response.

[0464] Specific operation: The server calls the translation API to translate the message into Japanese, then generates an appropriate response message and translates it back into the user's native language.

[0465] Step 4:

[0466] The server analyzes the user's emotional state.

[0467] What it does: The server's emotion engine uses text analysis to identify the user's emotion.

[0468] Step 5:

[0469] The terminal displays the translated message to the user.

[0470] Specific operation: The server generates a message according to the user's emotional state and sends it to the device. The device receives the message and displays it in the user's native language.

[0471] Matching volunteer skills and locations

[0472] Step 1:

[0473] Users register their skill set and location information.

[0474] Specific operation: Volunteers enter their skills and current location through the chatbot and register on the server.

[0475] Step 2:

[0476] The server stores the registered volunteer information in a database.

[0477] Specific operation: The server saves the entered information in a database and makes it available for verification.

[0478] Step 3:

[0479] When a request for assistance is received, the server selects the most suitable volunteer and notifies them.

[0480] Specific operation: The server compares the request for assistance with the volunteers' skill sets and location information, selects the most suitable volunteer, and sends a notification to the selected volunteer.

[0481] Step 4:

[0482] The server analyzes the emotional state of the volunteer.

[0483] Specific operation: The emotion engine analyzes emotions from volunteers' responses and progress reports to identify "fatigue" and "stress."

[0484] Step 5:

[0485] Volunteer users are notified and begin providing support.

[0486] Specific action: The volunteer replies to the notification by saying "I'm on my way to help," and the server provides information about the specific location where the volunteer will help.

[0487] Step 6:

[0488] The terminal reports the volunteer's progress to the server.

[0489] Specific operation: The volunteer's device sends GPS data to the server in real time, reports the progress of the activity, and provides necessary notifications and advice according to the volunteer's emotional state.

[0490] This enables the system to provide quick and accurate information and support to disaster victims and evacuees, and utilizes an emotion engine to provide flexible responses to maintain users' mental stability.

[0491] Example 2

[0492] 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."

[0493] When a disaster occurs, it is important for victims and evacuees to obtain the necessary information quickly and accurately and ensure their safety. However, current systems do not adequately address the following: safety confirmation, understanding of the congestion situation at evacuation centers, providing reliable disaster information, multilingual support, skill matching with volunteers, and consideration of emotional state. This makes it difficult for victims and evacuees to receive appropriate support.

[0494] 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.

[0495] In this invention, the server includes means for sending push notifications to users when a disaster occurs, means for receiving response input information and location information from users, means for analyzing the received information and automatically estimating the user's safety status and emotional state, means for notifying specific contacts of the estimated safety status and emotional state, means for receiving camera footage and determining the congestion status of evacuation centers in real time, means for collecting disaster-related information from online social networks and official institutions, evaluating its reliability, and providing the user with reliable information, means for translating questions in the user's native language and providing the translated answers, and means for registering volunteers' skill sets and location information in a database and matching them with requests for assistance.

[0496] This will enable victims and evacuees to quickly and accurately obtain the information they need, ensure their safety, and receive appropriate support.

[0497] The "means for sending a push notification to a user when a disaster occurs" is a function that immediately sends a notification from the server to the user's device when a disaster is detected.

[0498] The "means for receiving response input information and location information from the user" is a function by which the server receives information in response to the notification from the user and the location information of the terminal.

[0499] "Means for analyzing received information and automatically estimating the user's safety status and emotional state" refers to a function that uses a specific algorithm to mechanically determine the user's safety and emotional state based on the response information and location information received by the server from the user.

[0500] "Means of notifying specific contacts of estimated safety status and emotional state" is a function in which the server notifies contacts previously set by the user based on the analysis results.

[0501] "Means of receiving camera footage and determining the congestion situation at evacuation centers in real time" refers to a function in which a server receives footage sent from cameras installed at evacuation centers, analyzes it, and determines the current congestion situation.

[0502] "Means of collecting disaster-related information from online social networks and official institutions, assessing its reliability, and providing users with reliable information" refers to a function in which a server collects disaster-related information from online social networking sites and government agencies, evaluates the reliability of that information using an algorithm, and delivers reliable information to users.

[0503] "Means for translating questions in the user's native language and providing translated answers" is a function that translates a user's question entered in a foreign language into the original language and returns the translation result to the user.

[0504] "Means of registering volunteer skill sets and location information in a database and matching them with requests for assistance" is a function that stores volunteers' skills and current locations in a database and automatically matches them with requests for assistance in the event of a disaster.

[0505] This invention is a system that allows disaster victims and evacuees to quickly and accurately obtain necessary information and ensure their safety in the event of a disaster. This system has the following main functions:

[0506] 1. Safety confirmation function for disaster victims

[0507] When a disaster occurs, the server sends a push notification to users who have been registered in the affected area in advance. Users who receive this notification enter their own safety status and current location via their device and send it to the server. When analyzing the received information, the server also uses an emotion engine to analyze the user's emotional state. As a result, the user's safety status and emotional state are notified to specific contacts. This series of steps allows the specific situation of the disaster victim to be quickly communicated to family members and those involved. For example, when an earthquake occurs, the server sends a notification to the user asking, "Are you safe?" and the user replies, "I'm safe." The server then analyzes this information and notifies the family, "You're safe, but it seems you're worried."

[0508] Example prompts for generative AI models

[0509] I would like to know more about the disaster victim safety confirmation system. I would like to know details about how notifications are sent to users and how the information entered is analyzed and used to send notifications.

[0510] 2. Function to grasp the congestion situation at evacuation shelters

[0511] Cameras installed at each shelter periodically capture footage of the shelter and send the video data to a server. The server uses AI image recognition technology to analyze the footage and understand the shelter's congestion status in real time. When a user inquires about the congestion status of a shelter via a chatbot, the server responds based on the latest analysis results. For example, if the server analyzes video from shelter A and detects congestion, when the user asks, "How crowded is the nearest shelter?" the server will reply, "Shelter A is full. There is space available at shelter B."

[0512] Example prompts for generative AI models

[0513] Please tell me about the system that monitors the congestion status of evacuation shelters in real time. I would like to know how the camera footage is analyzed and specific examples of notifications sent to users.

[0514] 3. Disaster-related information collection and reliability evaluation function

[0515] The server collects disaster-related information from social media and official organizations and selects highly reliable information by applying a reliability evaluation algorithm. When a user requests the latest disaster information through the chatbot, the server provides the selected, highly reliable information. For example, when a tsunami warning is issued, the server collects and evaluates information from social media and official organizations and notifies the user, "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately." Additional evacuation information is provided to users who are feeling anxious.

[0516] Example prompts for generative AI models

[0517] Please tell me about a system that provides reliable disaster-related information. I'd like some concrete examples of how the information is collected and evaluated.

[0518] 4. Multilingual translation and interpretation support functions

[0519] The server has a multilingual translation function, so when a foreign user asks the chatbot a question in their native language, it translates the question into the appropriate language in real time and provides the translated answer. An emotion engine also analyzes the foreign user's emotional state and provides additional information as needed. For example, if an English-speaking user asks, "What should I do now?", the server translates and replies, "Evacuate now. There is an earthquake, so please stay safe."

[0520] Example prompts for generative AI models

[0521] Please tell me about multilingual translation and interpretation support systems. I'd like to see some concrete examples of how they translate foreign languages ​​in real time and provide information to users.

[0522] 5. Matching volunteer skills and locations

[0523] The server registers the skill sets and location information of volunteers in a database, and in the event of a disaster, it compares the request for assistance with the skill sets and location information of the volunteers to select and notify the most suitable volunteer. For example, if medical assistance is needed at an evacuation shelter, the server will notify nearby volunteers with medical skills and provide the specific location information of the evacuation shelter to the volunteer who responds, "I'm on my way to help."

[0524] Example prompts for generative AI models

[0525] Please tell me about the system that matches volunteer skill sets with location information. I would like to see some concrete examples of how volunteers are selected and requests for assistance are made.

[0526] As described above, the present invention can achieve rapid and accurate information acquisition and safety assurance for disaster victims and evacuees in the event of a disaster, thereby further improving safety and rapid response in disaster-stricken areas.

[0527] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0528] Safety confirmation function for victims

[0529] Step 1:

[0530] When the server detects a disaster, it sends a push notification to users in the affected area.

[0531] Input: Disaster detection information

[0532] Data processing: Identifying affected areas and generating notification messages

[0533] Output: Sending a push notification to the user device

[0534] Specific operation: The server sends a notification to the user's device, such as a smartphone, saying, "Are you safe?"

[0535] Step 2:

[0536] The user receives the push notification and responds.

[0537] Input: Push notification

[0538] Data processing: Entering safety status and current location

[0539] Output: User response input information and location information

[0540] What happens: The user enters their current location and their situation, such as "I'm OK" or "I'm injured."

[0541] Step 3:

[0542] The terminal transmits the user's response input information and location information to the server.

[0543] Input: User response input information and location information

[0544] Data processing: Converting input information into transmission protocol

[0545] Output: Data sent to the server

[0546] Specific operation: The device sends information to the server using an encrypted communication protocol.

[0547] Step 4:

[0548] The server analyzes the received information and estimates the safety and emotional state of the victims.

[0549] Input: Response input information and location information

[0550] Data processing: Applying analysis algorithms for safety status and emotional state

[0551] Output: Estimated safety status and emotional state

[0552] What it does: The server uses an analysis algorithm to estimate the outcome of "safe" and the emotion of "anxiety."

[0553] Step 5:

[0554] The server notifies specific contacts of the estimated safety status and emotional state.

[0555] Input: Safety status and estimated emotional state

[0556] Data processing: generating and sending notification messages

[0557] Output: Contact notification

[0558] What happens: The server sends a notification to family and friends saying, "You're safe, but we have some concerns."

[0559] Function to grasp the congestion situation of evacuation shelters

[0560] Step 1:

[0561] Cameras installed at evacuation centers periodically capture images and send them to a server.

[0562] Input: Camera image data

[0563] Data processing: Converting video data into transmission protocol

[0564] Output: Data sent to the server

[0565] Specific operation: The camera captures video of the evacuation shelter and sends the data to the server.

[0566] Step 2:

[0567] The server receives the video data and analyzes it using AI image recognition technology.

[0568] Input: Video data

[0569] Data processing: Analysis of video data using AI image recognition technology

[0570] Output: Analysis results of congestion situation

[0571] Specific operation: The server analyzes the video data and grasps the congestion situation at the evacuation center in real time.

[0572] Step 3:

[0573] The user inquires about the congestion status of the evacuation shelter via the chatbot.

[0574] Input: User query

[0575] Data processing: Processing of inquiries

[0576] Output: Sends the query to the server

[0577] Specific behavior: The user asks the chatbot, "How crowded is the nearest evacuation shelter?"

[0578] Step 4:

[0579] The server responds to the user based on the analysis results.

[0580] Input: User inquiries and congestion analysis results

[0581] Data processing: Generate a response message based on the analysis results and the inquiry content

[0582] Output: Response message to the user

[0583] Specific behavior: The server replies, "Shelter A is full. There is space available in shelter B."

[0584] Disaster-related information collection and reliability evaluation function

[0585] Step 1:

[0586] The server collects disaster-related information from social media and official organizations.

[0587] Input: Information from online social networks and official sources

[0588] Data processing: collecting information and storing it in a database

[0589] Output: Collected information data

[0590] Specific operation: The server collects disaster information using APIs from social media and official organizations.

[0591] Step 2:

[0592] The server evaluates the reliability of the collected information.

[0593] Input: Collected information data

[0594] Data processing: Applying reliability evaluation algorithms

[0595] Output: Reliability evaluation result

[0596] Specific operation: The server applies a reliability evaluation algorithm to the information and scores its reliability.

[0597] Step 3:

[0598] Users request the latest disaster information via a chatbot.

[0599] Input: User query

[0600] Data processing: Processing of inquiries

[0601] Output: Sends the query to the server

[0602] Specific operation: The user asks the chatbot, "Please tell me the latest disaster information."

[0603] Step 4:

[0604] The server provides reliable information to the user.

[0605] Input: User query and reliability evaluation results

[0606] Data processing: Selecting information based on the evaluation results and generating response messages

[0607] Output: Response message to the user

[0608] Specific operation: The server responds, "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately."

[0609] Multilingual translation and interpretation support functions

[0610] Step 1:

[0611] Users ask the chatbot questions in their native language.

[0612] Input: Question in the user's native language

[0613] Data processing: Converting question content into text data

[0614] Output: Text data of the question

[0615] Specific behavior: The user asks the chatbot, "What should I do now?"

[0616] Step 2:

[0617] The server translates the question in real time.

[0618] Input: Text data of the question

[0619] Data processing: Applying real-time translation algorithms

[0620] Output: Translated question

[0621] Specific operation: The server translates the English question into Japanese.

[0622] Step 3:

[0623] The server provides the translated answer.

[0624] Input: translated question

[0625] Data processing: generating appropriate answers and translating

[0626] Output: The translated answer to the user

[0627] Specific behavior: The server sends a response to the user saying, "Evacuate now. An earthquake is occurring, so please stay safe."

[0628] Matching volunteer skills and locations

[0629] Step 1:

[0630] Volunteers register their skill set and location information.

[0631] Input: Volunteer skill set and location

[0632] Data processing: Registering information in a database

[0633] Output: Registration information data

[0634] What happens: Volunteers enter their skills and current location into the system.

[0635] Step 2:

[0636] The server stores the registration information in a database.

[0637] Input: Registration information data

[0638] Data processing: Saving to database

[0639] Output: Saved data

[0640] Specific operation: The server stores the volunteer's skill set and location information in a database.

[0641] Step 3:

[0642] In the event of a disaster, the server matches requests for assistance with volunteer information.

[0643] Input: Request for assistance information and volunteer information in the database

[0644] Data processing: Applying matching algorithms

[0645] Output: Optimal volunteer selection results

[0646] Specific operation: The server automatically selects the most suitable volunteer for the request for assistance.

[0647] Step 4:

[0648] The server sends a notification to the volunteer.

[0649] Input: Selection result

[0650] Data processing: Notification message generation

[0651] Output: Notification to volunteers

[0652] Specific operation: The server sends a notification to the selected volunteer saying "Assistance needed."

[0653] Step 5:

[0654] An emotion engine analyzes the emotional state of the volunteer.

[0655] Input: Volunteer responses and information during the activity

[0656] Data processing: Applying emotional state analysis algorithms

[0657] Output: Emotional state analysis results

[0658] How it works: The emotion engine analyzes the volunteer's responses and detects fatigue and stress levels.

[0659] The above processing steps have been described in detail to explain how the system of the present invention contributes to disaster victims and evacuees.

[0660] (Application example 2)

[0661] 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."

[0662] This invention relates to a system that enables disaster victims and evacuees to obtain prompt and appropriate information and ensure their safety in the event of a disaster. Current disaster response systems often have difficulty in confirming the safety of disaster victims and grasping the congestion status of evacuation centers in real time, and also have difficulty responding flexibly to users' emotional states. Furthermore, they have limited multilingual support and are unable to effectively match volunteer skill sets and location information with requests for assistance.

[0663] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0664] In this invention, the server includes means for receiving input information and location information from disaster victims, means for sending push notifications to disaster victims when a disaster occurs, means for analyzing the emotional state of disaster victims using an emotion engine and coordinating a response, means for analyzing the congestion status of evacuation shelters in real time from camera footage, means for providing the analyzed congestion status of evacuation shelters to users, means for collecting disaster-related information and evaluating its reliability, means for providing reliable disaster information to users, means for translating and answering user questions in real time using a multilingual translation function, and means for matching support requests by collating volunteer skill sets and location information. This enables disaster victims and evacuees to quickly and appropriately obtain information and ensure their safety when a disaster occurs.

[0665] "Victims" refers to people affected by a disaster.

[0666] A "push notification" refers to a notification message that a server actively sends to a user's device.

[0667] An "emotion engine" refers to an algorithm or program for analyzing a user's emotional state from input information.

[0668] "Camera footage" refers to video data from cameras installed in evacuation shelters and other locations to capture the situation at the shelter.

[0669] "Real-time" refers to data exchange and analysis occurring immediately and without delay.

[0670] "Disaster-related information" refers to information such as disaster-related news, warnings, and damage status.

[0671] "Reliability" refers to the criteria for assessing whether collected information is accurate.

[0672] "Multilingual translation function" refers to a function that enables automatic translation between multiple languages.

[0673] "Volunteers" refer to people who are registered to provide relief activities free of charge during disasters.

[0674] "Skill set" refers to the specific skills and qualifications that a volunteer possesses.

[0675] "Location information" refers to information that indicates a specific location using technology such as GPS.

[0676] "Request for assistance" refers to requests or demands for specific assistance activities from disaster victims or related organizations.

[0677] "Matching" means matching requests for assistance with volunteers' skill sets and location information to find the best match.

[0678] This invention is a system that allows disaster victims and evacuees to obtain prompt and appropriate information and ensure their safety during disasters. This system includes functions for checking the safety status of disaster victims, understanding the congestion status of evacuation centers, providing disaster-related information, providing multilingual support, and matching volunteers.

[0679] System Configuration

[0680] Hardware:

[0681] Smartphone: A device used by disaster victims and users.

[0682] Server: Processes and manages data for the entire system.

[0683] Cameras: Devices installed in evacuation centers to capture images of crowded areas.

[0684] software:

[0685] React Native: A development framework for smartphone applications.

[0686] Node.js, Express: Server-side frameworks.

[0687] MongoDB: A NoSQL database.

[0688] Google Cloud Vision: Image recognition API.

[0689] Microsoft Azure Text Analytics: Emotion recognition API.

[0690] Google Translate API: Multilingual translation API.

[0691] TensorFlow: An AI model for trustworthiness assessment.

[0692] Processing Overview

[0693] 1. Confirmation of the safety of victims:

[0694] When a disaster occurs, the server sends push notifications to users in the affected area. When users enter their safety status (e.g., "safe" or "injured") and location information on their smartphones, the information is sent to the server. The server analyzes this information and evaluates the user's emotional state using Microsoft Azure Text Analytics. The analysis results are then sent to specific contacts.

[0695] 2. Understanding the congestion situation at evacuation shelters:

[0696] Cameras installed at evacuation centers periodically send images to a server. The server analyzes the images using Google Cloud Vision and determines the congestion status of the evacuation center in real time. When a user inquires about the congestion status of the evacuation center through the chatbot, an answer is provided based on the analysis results. If necessary, the notification content is adjusted according to the user's emotional state.

[0697] 3. Providing disaster-related information:

[0698] The server collects disaster-related information from social media and official organizations, and evaluates its reliability using a TensorFlow model. Based on the evaluation results, reliable information is provided to the user. The method of providing information is adjusted according to the user's emotional state.

[0699] 4. Multilingual support:

[0700] The server uses the Google Translate API to translate questions written by users in their native language in real time, and provides appropriate answers based on the translated questions. The emotion engine also takes into account the emotional state of foreign users.

[0701] 5. Volunteer Matching:

[0702] The server registers the skills and location information of volunteers in a database and matches appropriate volunteers when a request for assistance is made. It also uses an emotion engine to analyze the emotional state of the volunteers and adjust the assistance content and notifications as needed.

[0703] Specific examples

[0704] 1. Examples of how to check on the safety of disaster victims:

[0705] When an earthquake occurs, the server quickly sends a notification to all users in the affected area asking, "Are you safe?" The user replies, "I'm safe," and the notification is sent along with their location information. Based on this information, the server analyzes the user's safety status, and the emotion engine analyzes the user's emotional state. As a result, detailed safety information such as "You're safe, but you seem worried" is sent to family and friends.

[0706] 2. Specific examples of grasping the congestion situation of evacuation shelters:

[0707] The server periodically analyzes the camera footage from shelter A and detects that the shelter is full. When a user asks the chatbot, "How crowded is the nearest shelter?", the server replies, "Shelter A is full. There is space available at shelter B." Depending on the user's emotional state, the response is adjusted to, "Please move to shelter B as soon as possible."

[0708] 3. Example prompt:

[0709] "Please let us know the latest tsunami information. Our users are very worried."

[0710] "Identify nearby locations seeking medical assistance and notify qualified volunteers. Analyze stress levels with our emotion engine and provide the necessary advice."

[0711] In this way, the present invention combines emotion recognition with disaster information, enabling highly flexible and rapid responses.

[0712] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0713] Step 1:

[0714] The server detects that a disaster has occurred and sends a push notification to users in the affected area.

[0715] Input: Disaster occurrence information

[0716] Output: Generate and send a push notification

[0717] Specific operation: The server receives disaster occurrence information from the disaster information database and sends a push notification asking "Are you safe?" to specific users based on a list of users in the affected area.

[0718] Step 2:

[0719] Users use their smartphones to input their safety status and location information and send it to the server.

[0720] Input: User's safety status and location information

[0721] Output: Send safety status data

[0722] Specific operation: The user selects an option such as "safe" or "injured" through a smartphone app and sends it along with their location information.

[0723] Step 3:

[0724] The server analyzes the received information and automatically estimates the safety status of the victims.

[0725] Input: User's safety status and location information

[0726] Output: Estimated safety status

[0727] How it works: The server analyzes safety status data and location information, evaluates the user's emotional state using Microsoft Azure Text Analytics, and automatically estimates the user's overall safety status.

[0728] Step 4:

[0729] The server notifies the specific contact person of the estimated safety status.

[0730] Input: Estimated safety status and emotional state

[0731] Output: Safety information notification

[0732] Specific operation: The server notifies the estimated safety status and emotional state to family and friend contacts.

[0733] Step 5:

[0734] The cameras at the shelter periodically send footage to a server, which then analyzes the footage.

[0735] Input: Shelter camera footage

[0736] Output: Congestion status judgment result

[0737] Specific operation: The server uses Google Cloud Vision to analyze the received video and determine the congestion status of the evacuation shelter in real time.

[0738] Step 6:

[0739] When a user asks the chatbot about the congestion situation at an evacuation shelter, the server provides an answer based on the analysis results.

[0740] Input: User inquiry about congestion status

[0741] Output: Response about congestion status

[0742] Specific operation: When a user asks the chatbot, "How crowded is the nearest evacuation shelter?", the server responds based on the latest analysis results and provides the congestion status. If necessary, it adjusts the response according to the user's emotional state.

[0743] Step 7:

[0744] The server collects disaster-related information from social media and official organizations and evaluates its reliability.

[0745] Input: Disaster-related information

[0746] Output: reliable information

[0747] Specific operation: The server collects disaster-related information from social media and official organizations on the Internet and evaluates the reliability of the information using a TensorFlow model.

[0748] Step 8:

[0749] The server provides the user with reliable information based on the evaluation results.

[0750] Input: Reliable information

[0751] Output: Provide information to the user

[0752] Specific behavior: The server provides reliable disaster information to users through push notifications and chatbots, adjusting the details of the information and additional instructions depending on the user's emotional state.

[0753] Step 9:

[0754] The server uses a multilingual translation function to translate the user's question in real time and provide an answer.

[0755] Input: User question (source language)

[0756] Output: Answer to user (translated language)

[0757] What happens: The server uses the Google Translate API to translate the question written by the user in their native language into the appropriate language and provides the translated answer to the user.

[0758] Step 10:

[0759] The server compares volunteers' skill sets and location information and matches requests for assistance.

[0760] Input: Volunteer skill set and location, request for assistance

[0761] Output: Notification to volunteer

[0762] What it does: The server retrieves the skillset and location information from the volunteer database, selects the best volunteer to respond to the request, and notifies them. It uses the emotion engine to adjust the assistance and notification as needed.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] [Second embodiment]

[0767] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0768] 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.

[0769] 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).

[0770] 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.

[0771] 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.

[0772] 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).

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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."

[0779] The present invention provides a system for ensuring the safety of disaster victims and evacuees by enabling them to quickly and accurately obtain necessary information in the event of a disaster. Details of how to implement this system are described below.

[0780] 1. Confirming the safety of disaster victims

[0781] This system includes a function for checking the safety status of disaster victims when a disaster occurs. When a disaster occurs, the server sends a push notification to users in the affected area. Users respond to the notification received through their smartphone or other device and enter their safety status and current location. The device sends the entered information and location information to the server, which analyzes this and automatically estimates the safety status of the disaster victims. The estimated safety status is then notified to specific contacts.

[0782] Specific examples

[0783] For example, when an earthquake occurs, the server quickly sends a notification to all users in the affected area asking, "Are you safe?" Users who respond reply, "I'm safe," and this is sent along with their location information. Based on this information, the server analyzes the user's safety status and notifies their family and friends.

[0784] 2. Understanding the congestion situation at evacuation shelters

[0785] Cameras installed at evacuation centers regularly capture footage and upload it to a server. The server analyzes these images using AI image recognition technology to grasp the congestion status of each evacuation center in real time. When a user inquires about the congestion status of a shelter through the chatbot, the server provides the user with an answer based on the analysis results.

[0786] Specific examples

[0787] The server periodically analyzes the camera footage from shelter A and detects that the shelter is full. When a user asks the chatbot, "How crowded is the nearest shelter?", the server replies, "Shelter A is full. There is space available at shelter B."

[0788] 3. Collection of disaster-related information and reliability assessment

[0789] The server collects disaster-related information from social media and official sources. It then applies a reliability evaluation algorithm to the collected information to select the most reliable information. When a user requests the latest disaster information through the chatbot, the server provides the selected, reliable information.

[0790] Specific examples

[0791] When a tsunami warning is issued, the server collects information from social media and official organizations and evaluates its reliability. When a user asks, "Please tell me the latest disaster information," the server responds, "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately."

[0792] 4. Multilingual translation and interpretation support

[0793] The server has a multilingual translation function, so when a foreign user asks the chatbot a question in their native language, the server translates it into the appropriate language in real time, and the translated answer is provided to the user.

[0794] Specific examples

[0795] When an English-speaking user asks the chatbot, "What should I do now?", the server translates and replies, "Please evacuate now. There is an earthquake, so please stay safe."

[0796] 5. Matching volunteer skills and locations

[0797] The server registers the skill sets and location information of volunteers in a database, and in the event of a disaster, it compares the request for assistance with the skill sets and location information of the volunteers to select and notify the most suitable volunteers. It also tracks the progress of volunteer activities.

[0798] Specific examples

[0799] If a shelter needs medical assistance, the server notifies nearby registered volunteers with medical skills. When a volunteer responds, "I'm on my way to help," the server provides the specific location of the shelter and tracks the volunteer's progress.

[0800] As described above, the present invention is a system that enables quick and accurate provision of information and support to disaster victims and evacuees in the event of a disaster, thereby ensuring the safety of disaster-stricken areas and enabling quick response.

[0801] The processing flow will be explained below.

[0802] Confirming the safety of victims

[0803] Step 1:

[0804] When the server detects a disaster, it sends a push notification to users in the affected area.

[0805] Specific operation: The server references a database of affected areas and sends a message to all relevant users asking, "Are you safe?"

[0806] Step 2:

[0807] The user receives the notification and enters a response.

[0808] Specific action: The user types a message into the device, such as "I'm safe" or "I need help," and sends it.

[0809] Step 3:

[0810] The device sends input information and location information to the server.

[0811] Specific operation: The device's GPS function obtains the current location and sends it to the server along with the entered text message.

[0812] Step 4:

[0813] The server analyzes the received information and automatically estimates the safety status of the victims.

[0814] How it works: The server uses an AI model to analyze messages and location information to estimate the safety status of the person. The results are stored in a database.

[0815] Step 5:

[0816] The server notifies the specific contact of the estimation result.

[0817] Specific operation: Based on the estimated safety information, the server sends the information to pre-registered contacts (family, friends, etc.).

[0818] Grasping the congestion situation at evacuation centers

[0819] Step 1:

[0820] Cameras installed at evacuation centers regularly capture footage and upload it to a server.

[0821] Specific operation: The camera captures video at regular intervals and sends the data to the server.

[0822] Step 2:

[0823] The server analyzes the received video.

[0824] Specific operation: The server inputs the video into an AI image recognition model, counts the number of people, and determines the congestion level.

[0825] Step 3:

[0826] A user inquires about congestion status via a chatbot.

[0827] Specific operation: The user types a question into the chatbot on their smartphone, such as "How crowded is the nearest evacuation shelter?", and sends it.

[0828] Step 4:

[0829] The server provides the user with an answer based on the analysis results.

[0830] Specific operation: The server checks the analysis results of the AI ​​model, generates an answer such as "Shelter A is full. There is space available in shelter B," and sends it back to the user.

[0831] Collection and reliability assessment of disaster-related information

[0832] Step 1:

[0833] The server collects disaster-related information from social media and official organizations.

[0834] Specific operation: The server uses scraping tools and APIs to collect disaster information from social media and official organizations and stores it in a database.

[0835] Step 2:

[0836] The server applies a trustworthiness evaluation algorithm to the collected information.

[0837] What it does: The server uses text analysis and credibility assessment algorithms to score the credibility of each piece of information.

[0838] Step 3:

[0839] A user asks a chatbot for the latest disaster information.

[0840] Specific operation: The user types "Please tell me the latest disaster information" into the chatbot and sends it.

[0841] Step 4:

[0842] The server selects reliable disaster information and responds to the user.

[0843] Specific operation: The server selects information with high reliability, generates a message such as "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately," and sends it back to the user.

[0844] Multilingual translation and interpretation support

[0845] Step 1:

[0846] The server puts the multilingual translation module into standby mode.

[0847] Specific operation: The server initializes the real-time translation API and prepares for multilingual support.

[0848] Step 2:

[0849] Foreign users ask questions to the chatbot in their native language.

[0850] What happens: The user types a message in their native language and sends it to the chatbot.

[0851] Step 3:

[0852] The server translates the received message and generates an appropriate response.

[0853] Specific operation: The server calls the translation API to translate the message into Japanese, then generates an appropriate corresponding message, translates it again into the foreign language, and sends it.

[0854] Step 4:

[0855] The terminal displays the translated message to the user.

[0856] Specific operation: The message received by the user's device is displayed in the user's native language.

[0857] Matching volunteer skills and locations

[0858] Step 1:

[0859] Users register their skill set and location information.

[0860] Specific operation: Volunteers enter their skills and current location through the chatbot and register on the server.

[0861] Step 2:

[0862] The server stores the registered volunteer information in a database.

[0863] Specific operation: The server saves the entered information in a database and makes it available for verification.

[0864] Step 3:

[0865] When a request for assistance is received, the server selects the most suitable volunteer and notifies them.

[0866] Specific operation: The server compares the request for assistance with the volunteers' skill sets and location information, selects the most suitable volunteer, and sends a notification to the selected volunteer.

[0867] Step 4:

[0868] Volunteer users are notified and begin providing support.

[0869] Specific actions: The volunteer replies to the notification by saying "I'm heading to help" and receives information about the specific location of the help from the server.

[0870] Step 5:

[0871] The terminal reports the volunteer's progress to the server.

[0872] Specific operation: Volunteers' devices send GPS data to the server in real time and report the progress of their activities.

[0873] This enables the system to provide quick and accurate information and support to disaster victims and evacuees.

[0874] Example 1

[0875] 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."

[0876] When a disaster occurs, it is necessary to quickly and accurately collect information and provide it to victims and evacuees. However, conventional systems take time to collect, analyze, and provide information, and there is a possibility that the information may be unreliable. Furthermore, there are issues with insufficient multilingual support and appropriate coordination of volunteers. The present invention aims to solve these issues.

[0877] 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.

[0878] In this invention, the server includes means for receiving input information and location information from disaster victims, means for sending push notifications to disaster victims when a disaster occurs, means for analyzing the received information and automatically estimating the safety status of the disaster victims, means for notifying specific contacts of the estimated safety status, means for providing a multilingual translation function in real time, and means for selecting and notifying the most suitable volunteers by comparing the volunteers' skill sets and location information. This makes it possible to quickly collect and analyze reliable information when a disaster occurs, and to accurately respond to multiple languages ​​and coordinate volunteers.

[0879] "Input information from disaster victims" refers to information that disaster victims record about their situation and location during a disaster and send to the system.

[0880] "Location Information" means current geographic coordinate data obtained using GPS or other location-determining technology.

[0881] "Push notification" refers to an automatic notification message sent by a server to a user's device.

[0882] "Analysis" refers to the act of processing data to extract meaningful information.

[0883] "Safety status" refers to information indicating the status of life and safety of disaster victims, such as whether they are safe.

[0884] "Contact information" refers to the contact information of family members, friends, etc. who will be notified of the victim's safety.

[0885] "Multilingual Translation Functionality" means a system function that automatically translates text or messages between different languages.

[0886] "Volunteer skill set" refers to the specific skills and experience a volunteer possesses.

[0887] "Location matching" refers to the process of analyzing volunteers' location information and matching it with locations where assistance is needed.

[0888] "Camera footage" refers to images and video data captured using a camera device.

[0889] "AI image recognition technology" refers to technology that uses artificial intelligence to analyze the content of images and videos.

[0890] "Online social network" refers to a system for sharing information through internet services such as social networking sites.

[0891] "Official sources" refers to reliable sources provided by government agencies or authorized organizations.

[0892] A "trustworthiness assessment algorithm" refers to a logical method for assessing the reliability of acquired information based on numerical values ​​and criteria.

[0893] The present invention relates to a system for providing information quickly and accurately and supporting disaster victims in the event of a disaster. The details of implementing this system are described below.

[0894] 1. Hardware and software configuration

[0895] server

[0896] The server has the following features:

[0897] Database Management System (DBMS)

[0898] Push notification server

[0899] AI image recognition engine

[0900] Multilingual translation engine (such as Google Translate API)

[0901] Reliability Evaluation Algorithm

[0902] Volunteer Matching Algorithm

[0903] Terminal

[0904] The device used by the user has the following features:

[0905] GPS Modules

[0906] Camera Device

[0907] Wireless communication module (Wi-Fi, LTE / 5G)

[0908] Newspaper reception application

[0909] 2. Confirming the safety of disaster victims

[0910] The server uses earthquake sensors and weather data to detect the occurrence of a disaster. When a disaster occurs, the server sends a push notification to users in the affected area asking, "Are you safe?" Users receive the notification on their smartphones or other devices and respond by inputting their safety status (e.g., "safe," "injured," "unable to provide information") and location information. The devices then send this information to the server. The server analyzes the received information, estimates the safety status of the victims, and notifies specific contacts.

[0911] Specific examples

[0912] The server detects the occurrence of an earthquake and sends a push notification to all users in the affected area asking, "Are you safe?"

[0913] The user responds "I'm safe," and the system uses GPS to obtain their current location and sends the results to the server.

[0914] The server analyzes the received information and notifies the user's family that "the user is safe."

[0915] 3. Understanding the congestion situation at evacuation shelters

[0916] Cameras installed at evacuation centers regularly capture footage and upload it to a server. The server then analyzes the footage using AI image recognition technology to grasp the congestion status of each evacuation center in real time. When a user inquires about the congestion status of a shelter through the chatbot, the server provides the user with an answer based on the analysis results.

[0917] Specific examples

[0918] The camera takes video of the evacuation center every minute and uploads the data to a server.

[0919] The server analyzes the video and calculates the level of congestion, such as "Shelter A is currently 70% full."

[0920] When a user asks the chatbot, "How crowded is shelter A?", the server responds with the current congestion situation.

[0921] 4. Collection of disaster-related information and reliability assessment

[0922] The server collects disaster-related information from social media and official sources, applies a reliability evaluation algorithm to the collected information, and stores the most reliable information in a database. When a user requests the latest disaster information through the chatbot, the server extracts and provides the most reliable information from the database.

[0923] Specific examples

[0924] The server collects disaster information from the Twitter API and RSS feeds from official organizations.

[0925] A reliability assessment algorithm scores the reliability of the information and stores it in a database.

[0926] When a user asks, "Please tell me the latest tsunami information," the server will provide reliable information and reply, "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately."

[0927] 5. Multilingual translation and interpretation support

[0928] The server uses a multilingual translation engine to instantly translate questions from foreign users and provide answers in the appropriate language. When a user asks a question in their native language, the server automatically translates the question, generates an appropriate answer, translates it, and provides it to the user.

[0929] Specific examples

[0930] An English-speaking user types "What should I do now?" into the chatbot.

[0931] The server translates the question into Japanese as "What should I do now?" and generates an appropriate answer.

[0932] The generated answer is translated back into English and replied to the user, "Please evacuate immediately. Ensure your safety as an earthquake is occurring."

[0933] 6. Matching volunteer skillsets with location information

[0934] The server registers the skill sets and location information of volunteers in a database. In the event of a disaster, the server matches requests for assistance with the skill sets and location information of volunteers to select the most suitable volunteers. Selected volunteers are notified and the progress of the assistance is tracked.

[0935] Specific examples

[0936] Volunteers register their medical skills and current location on a web portal.

[0937] A server receives a request for medical assistance from an evacuation shelter.

[0938] The server searches the database and selects the nearest suitable volunteer.

[0939] A notification is sent to the selected volunteers saying, "Medical assistance is needed at shelter B. Can you go?"

[0940] When a volunteer responds, "I'm on my way to help," the server provides the location of the shelter and the type of assistance needed, and tracks their progress in real time.

[0941] This enables the present invention to provide rapid and accurate information and support in the event of a disaster, ensuring the safety of disaster-stricken areas and enabling rapid response.

[0942] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0943] 1. Confirming the safety of disaster victims

[0944] Step 1:

[0945] The server detects the occurrence of disasters based on earthquake sensor and meteorological data. As input, it receives real-time data from earthquake sensors and meteorological stations. As output, it generates information on the occurrence of a detected disaster.

[0946] Step 2:

[0947] When the server detects a disaster, it sends a push notification to users in the affected area. The input is the detected disaster information and the contact information of users in the affected area. The output is a generated push notification message that is sent to the user's device.

[0948] Specific behavior:

[0949] The server sends a push notification with the message "Are you OK?"

[0950] Step 3:

[0951] Users receive push notifications on their smartphones or other devices and enter their safety status and location information. The inputs include the safety status entered by the user through the device and location information obtained from the device's GPS function. The output is that the device sends the entered data to the server.

[0952] Specific behavior:

[0953] The user selects an option such as "I'm fine" or "I'm injured."

[0954] The device obtains location information from GPS and sends it to the server along with safety information.

[0955] Step 4:

[0956] The server analyzes the received information and estimates the safety status of the victims. The inputs are the safety status information and location information sent from the device. The output generates the safety status as an analysis result.

[0957] Specific behavior:

[0958] The server processes the data it receives using machine learning models and rule-based analysis algorithms to estimate the safety of victims.

[0959] Step 5:

[0960] The server notifies specific contacts (family and friends) of the estimated safety status. The inputs are the analyzed safety status and the victim's contact information. The output is a notification message sent to the contacts.

[0961] Specific behavior:

[0962] The server sends a message to family and friends saying "You are safe."

[0963] 2. Understanding the congestion situation at evacuation shelters

[0964] Step 1:

[0965] Cameras installed at evacuation shelters periodically capture video. The input is the video data captured by the camera device. The output is the generated video file that is saved.

[0966] Specific behavior:

[0967] The camera captures and stores footage every minute.

[0968] Step 2:

[0969] The device uploads the captured video to the server. The input is the video data obtained from the camera. The output is the video data that is sent to the server.

[0970] Specific behavior:

[0971] The device sends video data to the server via Wi-Fi or mobile network.

[0972] Step 3:

[0973] The server analyzes the received video using AI image recognition technology to grasp the congestion situation in real time. The input is the video data sent from the device. The output is an analyzed congestion level value.

[0974] Specific behavior:

[0975] The server uses a deep learning model to analyze the video data, count the number of people inside the shelter, and calculate the congestion rate.

[0976] Step 4:

[0977] A user inquires about the congestion status of a shelter through a chatbot. The input is a text question that the user enters into the chatbot. The output is a query request that is sent to the server.

[0978] Specific behavior:

[0979] A user asks the chatbot, "How crowded is shelter A?"

[0980] Step 5:

[0981] The server provides a response to the user based on the analysis results. The inputs are a user query request and the analyzed congestion data. The output is a response message that is sent to the user.

[0982] Specific behavior:

[0983] The server responds, "Shelter A is currently 70% full."

[0984] 3. Collection of disaster-related information and reliability assessment

[0985] Step 1:

[0986] The server periodically collects disaster-related information from social media and official organizations. The input data is from social media APIs and official RSS feeds. The output data is stored in a database.

[0987] Specific behavior:

[0988] The server collects disaster information using the Twitter API and RSS feeds from official organizations.

[0989] Step 2:

[0990] The server applies a reliability assessment algorithm to the collected information. The input is the collected disaster-related information. The output is the information with a reliability score.

[0991] Specific behavior:

[0992] A reliability assessment algorithm scores the reliability of the information and stores it in a database.

[0993] Step 3:

[0994] A user requests the latest disaster information through a chatbot. The input is a text question that the user types into the chatbot. The output is a query request that is sent to the server.

[0995] Specific behavior:

[0996] A user asks, "What is the latest tsunami information?"

[0997] Step 4:

[0998] The server extracts reliable information from the database and provides it to the user. The input is the query request and the information in the database with a high reliability score. The output is a response message that is sent to the user.

[0999] Specific behavior:

[1000] The server responds, "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately."

[1001] 4. Multilingual translation and interpretation support

[1002] Step 1:

[1003] The user asks the chatbot a question in their native language. The input is the text entered by the user in their native language. The output is a generated question request that is sent to the server.

[1004] Specific behavior:

[1005] A user asks in English, "What should I do now?"

[1006] Step 2:

[1007] The server automatically identifies the input question and passes it to the translation engine. The input is a question request from the user. The output is generated text data that is sent to the translation engine.

[1008] Specific behavior:

[1009] The server sends the question to the Google Translate API, which translates it from English to Japanese.

[1010] Step 3:

[1011] The translation engine translates the question into the appropriate language. It takes as input the text data sent from the server and produces as output the translated question text.

[1012] Specific behavior:

[1013] Google Translate API translates "What should I do now?" into Japanese as "What should you do now?"

[1014] Step 4:

[1015] The server generates answers to translated questions. As input, it has the translated question text. As output, it produces the generated answer text.

[1016] Specific behavior:

[1017] The server responds to the translated question with, "Evacuate now. There is an earthquake, please stay safe."

[1018] Step 5:

[1019] The server translates the answer back into the user's native language and sends a reply. The input is the generated answer text. The output is the translated answer message sent to the user.

[1020] Specific behavior:

[1021] The server then sends the generated response back to the Google Translate API, which translates it into English and replies to the user with "Please evacuate immediately. Ensure your safety as an earthquake is occurring."

[1022] 5. Matching volunteer skills and locations

[1023] Step 1:

[1024] Volunteers register their skill sets and location information in a database. The input is the skill set and location information that the volunteer enters through a web portal. The output is a saved profile of the volunteer.

[1025] Specific behavior:

[1026] Volunteers register their medical skills and current location on a web portal.

[1027] Step 2:

[1028] When a disaster occurs, the server receives requests for assistance. The input is a request for assistance from an evacuation center. The output is a corresponding request for assistance.

[1029] Specific behavior:

[1030] The server receives a request from a shelter saying "medical assistance needed."

[1031] Step 3:

[1032] The server selects appropriate volunteers from a database based on the request for assistance. The inputs are the request for assistance and the skill sets and location information of the registered volunteers. The output is a list of selected volunteers.

[1033] Specific behavior:

[1034] The server searches the database and selects the nearest suitable volunteer.

[1035] Step 4:

[1036] The server sends notifications to selected volunteers. It takes as input the contact information of the selected volunteers. It generates the notification message as output.

[1037] Specific behavior:

[1038] The server sends a notification to the selected volunteer saying, "Medical assistance is needed at shelter B. Can you go?"

[1039] Step 5:

[1040] When a volunteer responds to help, the server provides the specific location of the help and detailed information. The input is the response from the volunteer and the evacuation shelter information. The output is a message that provides the location of the help and detailed information.

[1041] Specific behavior:

[1042] When a volunteer responds, "I'm on my way to help," the server provides the location of the evacuation shelter and the type of assistance needed.

[1043] Step 6:

[1044] The server tracks the progress of volunteer activities. It has as input the progress data of volunteers. It generates progress reports as output.

[1045] Specific behavior:

[1046] The server uses the volunteers' mobile GPS to track their progress in real time until they arrive at the destination.

[1047] (Application example 1)

[1048] 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."

[1049] When a disaster occurs, there are currently insufficient means for victims and evacuees to quickly and accurately obtain the necessary information and ensure their safety. There is also a need for more efficient confirmation of the safety of victims and evacuation guidance within factories and other facilities in disaster-stricken areas. In addition, there is a need for integrated provision of functions such as the collection and reliability evaluation of disaster-related information, the understanding of the congestion situation at evacuation centers, and multilingual support, but current technology makes it difficult to fully realize these needs.

[1050] 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.

[1051] In this invention, the server includes a means for receiving input information and location information from disaster victims, a means for sending push notifications to disaster victims when a disaster occurs, a means for analyzing the received information and automatically estimating the safety status of disaster victims, a means for notifying specific contacts of the estimated safety status, a means for confirming the safety of disaster victims within the factory, providing evacuation guidance and disaster-related information, and a means for installing these functions in factory robots. This ensures the safety of disaster victims and evacuees in the event of a disaster, and enables quick and efficient safety confirmation and evacuation guidance within the factory.

[1052] "Means for receiving input information and location information from disaster victims" refers to a device or software function that collects information on the safety and current location provided by disaster victims during a disaster and processes it within the system.

[1053] "Means for sending push notifications to disaster victims when a disaster occurs" refers to a technical means for immediately notifying disaster victims of important information when a disaster occurs.

[1054] "Means for analyzing received information and automatically estimating the safety status of disaster victims" refers to algorithms or systems for automatically determining the safety status of disaster victims based on information collected from the disaster victims.

[1055] "Means of notifying specific contacts of estimated safety status" refers to communication technology that quickly conveys the situation to the victims' families and other relevant parties based on the results of the analysis.

[1056] "Means for checking the safety of disaster victims, guiding evacuation, and providing disaster-related information within factories" refers to systems and devices that are used within factories and other facilities to check the safety of people in the event of a disaster, instruct them to evacuate safely, and provide necessary information.

[1057] "Means for installing these functions in factory robots" refers to methods and technologies for incorporating the various disaster response functions mentioned above into robots used in factories.

[1058] "Means for receiving images from cameras installed at each evacuation shelter" refers to devices and technologies for acquiring images in real time through cameras installed at evacuation shelters and transmitting them to the system.

[1059] "Means of analyzing received video and determining the congestion status of evacuation centers in real time" refers to algorithms and technology that analyze camera footage and automatically determine the number of people and the level of congestion in evacuation centers.

[1060] "Means of responding to user inquiries about congestion status based on analysis results" is a function that allows an appropriate reply based on analyzed data when a user asks about the congestion status of an evacuation shelter.

[1061] "Means of collecting disaster-related information from online social networks and official institutions" refers to systems and technologies for collecting the latest disaster information from sources such as social media and official institutions.

[1062] "Means for assessing the reliability of collected information" refers to algorithms and evaluation criteria for determining how accurate the collected disaster information is.

[1063] The "means for providing users with reliable information based on the evaluation results" refers to a system or function for providing users with appropriate information using the results of the reliability evaluation.

[1064] This invention relates to a system that enables disaster victims and evacuees to quickly and accurately obtain necessary information and ensure their safety during a disaster. This system includes the following components. First, a means for receiving input information and location information from disaster victims is provided. This is used by a server to receive information sent from smartphones and other mobile devices.

[1065] Next, a means for sending push notifications to disaster victims is provided. With this means, the system can immediately send notifications such as "Are you safe?" to users in the affected area when a disaster occurs.

[1066] The system also includes an algorithm that analyzes the received information and automatically estimates the safety status of disaster victims. This algorithm estimates whether a specific disaster victim is safe based on their location and input information.

[1067] Furthermore, it includes a means to notify specific contacts of the estimated safety status. This allows the analyzed safety information to be quickly communicated to the victims' families and related parties. The system also has functions to check the safety of victims within the factory, provide evacuation guidance, and provide disaster-related information. These functions are installed on robots used within the factory to implement appropriate responses.

[1068] The system also has a means of receiving video footage from cameras installed at each evacuation center. The server receives these images, analyzes them, and determines the congestion status of the evacuation center in real time. When a user inquires about the congestion status through a chatbot or other interface, the server provides an appropriate response based on the analysis results.

[1069] It also includes a means of collecting disaster-related information from online social networks and official organizations. This information is collected by a server, and the reliability of the information is evaluated. As a result of the evaluation, reliable information is provided to users.

[1070] Furthermore, the server is capable of handling multilingual translation. When a user speaking a different language asks a question in their native language, the question is translated in real time into the appropriate language and provided.

[1071] Finally, it also includes a means for matching volunteer skill sets with location information. The server manages the skill sets and location information of volunteers registered in the database, and in the event of a disaster, it selects and notifies the most suitable volunteer in response to a request for assistance. This function allows necessary assistance to be provided quickly and efficiently.

[1072] A concrete example of this system would be the following scenario. For example, when an earthquake occurs, the server sends a notification to all users in the affected area asking, "Are you safe?" If the user replies, "I'm safe," that information and their location are sent to the server, which then notifies their family and friends. It is also possible to analyze camera footage from evacuation shelters to determine the congestion situation and provide information such as, "Evacuation shelter A is full. There is space available at evacuation shelter B."

[1073] Furthermore, in the process of collecting disaster information and assessing its reliability, if you ask, "Please tell me the latest disaster information," you will receive highly reliable information. For example, you will receive a response such as, "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately."

[1074] Examples of prompt sentences include "A disaster has occurred. Are you safe?" and "Please tell me the latest disaster information." In this way, the present invention can ensure the safety of victims and evacuees and realize a prompt response in the event of a disaster.

[1075] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1076] Step 1:

[1077] The server sends a push notification when a disaster occurs. It sends a notification to smartphones of users in the affected area asking, "Are you safe?" The input is the trigger for the disaster occurrence, and the output is the notification to the user. Users who receive the push notification can enter a response message such as "I'm safe" on their smartphones.

[1078] Step 2:

[1079] The device (user's smartphone) responds to the received push notification and sends the device's location information to the server. The input is the user's response and location information, and the output is data sent to the server. The device provides real-time information by sending a response message and location data obtained from GPS to the server.

[1080] Step 3:

[1081] The server analyzes the received response message and location information and automatically estimates the safety status of the victim. The input is the response message and location information, and the output is the estimated safety status. The server uses a machine learning algorithm to analyze the response message and estimate the status, such as "safe" or "injured." In doing so, it also takes location information into account to comprehensively evaluate the situation.

[1082] Step 4:

[1083] The server notifies specific contacts of the estimated safety status. The input is the estimated safety status result and contact information, and the output is a notification to the contacts. Based on the analysis results, safety information is sent to the victim's family and friends via SMS or email.

[1084] Step 5:

[1085] The server periodically receives video from cameras installed at evacuation centers. The input is the camera video, and the output is the received video data. The video data is uploaded to the server and analyzed in the next step.

[1086] Step 6:

[1087] The server analyzes the received video data using image recognition technology and determines the congestion status of the evacuation shelter in real time. The input is the video data and the output is the evaluation result of the congestion status. The number of people is counted using image recognition technology and the fullness of the evacuation shelter is evaluated.

[1088] Step 7:

[1089] When a user inquires about the congestion situation, the server provides an answer based on the analysis results. The input is the user's inquiry, and the output is an answer based on the analysis results. For example, if a user asks, "How crowded is the nearest evacuation shelter?" the server will answer, "Shelter A is full. There is space available at shelter B."

[1090] Step 8:

[1091] The server collects disaster-related information from online social networks and official organizations. The input is a real-time information collection request, and the output is the collected information. The server uses APIs and web scraping to obtain the latest information from social networks and official websites.

[1092] Step 9:

[1093] The server evaluates the reliability of the collected disaster-related information. The input is the collected information, and the output is the reliability evaluation result. Using a generative AI model, the reliability of each piece of information is scored and the most reliable information is selected.

[1094] Step 10:

[1095] When a user requests the latest disaster information, the server provides highly reliable information. The input is the user's inquiry, and the output is highly reliable information. For example, in response to the prompt "Tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately."

[1096] Step 11:

[1097] The server manages the skill sets and location information of volunteers registered in the database, and selects and notifies the most suitable volunteers in the event of a disaster. The input is a request for assistance and volunteer information, and the output is a notification to the volunteer. For example, if medical assistance is needed, nearby volunteers with medical skills will be contacted and asked to provide assistance.

[1098] Step 12:

[1099] If the user is from a different country, the server uses a multilingual translation function to translate into the appropriate language in real time. The input is a question in a different language, and the output is a translated answer. For example, in response to the question "What should I do now?", the server translates and responds with "Please evacuate now. There is an earthquake, so please stay safe."

[1100] Through the above processing steps, this system achieves efficient information management and rapid response in the event of a disaster.

[1101] 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.

[1102] The present invention is a system that enables disaster victims and evacuees to quickly and accurately obtain necessary information and ensure their safety during a disaster, and in particular includes a function that recognizes the user's emotions and adjusts responses. Details for implementing this system are described below.

[1103] 1. Confirming the safety of disaster victims

[1104] This system includes a function for checking the safety status of disaster victims when a disaster occurs. When a disaster occurs, the server sends a push notification to users in the affected area. Users respond to the notification received through their smartphone or other device and enter their safety status and current location. The device sends the entered information and location information to the server, which analyzes this and automatically estimates the safety status of the disaster victims. Furthermore, an emotion engine analyzes the emotions from the user's input information and reflects them in the estimation results. The estimated safety status is then notified to specific contacts.

[1105] Specific examples

[1106] For example, when an earthquake occurs, the server quickly sends a notification to all users in the affected area asking, "Are you safe?" The user replies, "I'm safe," and the notification is sent along with their location information. Based on this information, the server analyzes the user's safety status, and the emotion engine analyzes the user's emotional state. As a result, family and friends are notified of detailed safety information such as, "They're safe, but they seem worried."

[1107] 2. Understanding the congestion situation at evacuation shelters

[1108] Cameras installed in evacuation centers regularly capture footage and upload it to a server. The server analyzes these images using AI image recognition technology to grasp the congestion status of each evacuation center in real time. When a user inquires about the congestion status of a shelter through the chatbot, the server provides the user with an answer based on the analysis results. The content and priority of notifications are adjusted taking into account the user's emotional state.

[1109] Specific examples

[1110] The server periodically analyzes the camera footage from shelter A and detects that the shelter is full. When a user asks the chatbot, "How crowded is the nearest shelter?", the server replies, "Shelter A is full. There is space available at shelter B." Depending on the user's emotional state, the response is adjusted to, "Please move to shelter B as soon as possible."

[1111] 3. Collection of disaster-related information and reliability assessment

[1112] The server collects disaster-related information from social media and official sources. It then applies a reliability evaluation algorithm to the collected information to select the most reliable information. When a user requests the latest disaster information through the chatbot, the server provides the selected, reliable information. Furthermore, the server adjusts the way the information is presented depending on the user's emotional state.

[1113] Specific examples

[1114] When a tsunami warning is issued, the server collects information from social media and official organizations and evaluates its reliability. When a user asks, "Please tell me the latest disaster information," the server responds, "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately." If the user feels uneasy, the server provides additional information and detailed evacuation instructions.

[1115] 4. Multilingual translation and interpretation support

[1116] The server has a multilingual translation function, so when a foreign user asks the chatbot a question in their native language, the server translates it into the appropriate language in real time. The translated answer is then provided to the user. The emotion engine also analyzes the foreign user's emotional state and adjusts the response accordingly.

[1117] Specific examples

[1118] When an English-speaking user asks the chatbot, "What should I do now?", the server translates and replies, "Evacuate now. An earthquake is occurring, so please stay safe." If the user expresses particular anxiety, the server provides detailed evacuation routes and additional safety information.

[1119] 5. Matching volunteer skills and locations

[1120] The server registers the skill sets and location information of volunteers in a database, and in the event of a disaster, it compares the request for assistance with the volunteer's skill set and location information to select and notify the most suitable volunteer. In addition, it tracks the progress of volunteer activities, and an emotion engine analyzes their emotional state as necessary to adjust the assistance content.

[1121] Specific examples

[1122] If medical assistance is needed at a shelter, the server notifies nearby registered volunteers with medical skills. When a volunteer responds, "I'm on my way to help," the server provides the specific location of the shelter and tracks the progress of their activities. An emotion engine analyzes the volunteer's emotional state and provides necessary notifications and advice if fatigue or stress is detected.

[1123] As described above, by combining an emotion engine, the present invention is a system that enables flexible responses according to the emotional states of disaster victims and evacuees during disasters, thereby further improving safety and rapid response in disaster-stricken areas.

[1124] The processing flow will be explained below.

[1125] Confirming the safety of victims

[1126] Step 1:

[1127] When the server detects a disaster, it sends a push notification to users in the affected area.

[1128] Specific operation: The server references a database of affected areas and sends a message to all relevant users asking, "Are you safe?"

[1129] Step 2:

[1130] The user receives the notification and enters a response.

[1131] Specific action: The user types a message into the device, such as "I'm safe" or "I need help," and sends it.

[1132] Step 3:

[1133] The device sends input information and location information to the server.

[1134] Specific operation: The device's GPS function obtains the current location and sends it to the server along with the entered text message.

[1135] Step 4:

[1136] The server analyzes the received information and automatically estimates the safety status of the victims.

[1137] How it works: The server uses an AI model to analyze messages and location information to estimate the safety status of the person. The results are stored in a database.

[1138] Step 5:

[1139] The server uses an emotion engine to analyze the user's emotion from the received message.

[1140] Specific operation: The emotion engine uses text analysis to identify the user's emotional state, such as "relieved," "anxious," or "tense."

[1141] Step 6:

[1142] The server notifies specific contacts of the estimation results and sentiment analysis results.

[1143] Specific operation: Based on the estimated safety information and emotion results, the server creates detailed safety information such as "You are safe, but you seem to be worried," and sends the information to pre-registered contacts (family, friends, etc.).

[1144] Grasping the congestion situation at evacuation centers

[1145] Step 1:

[1146] Cameras installed at evacuation centers regularly capture footage and upload it to a server.

[1147] Specific operation: The camera captures video at regular intervals and sends the data to the server.

[1148] Step 2:

[1149] The server analyzes the received video.

[1150] Specific operation: The server inputs the video into an AI image recognition model, counts the number of people, and determines the congestion level.

[1151] Step 3:

[1152] A user inquires about congestion status via a chatbot.

[1153] Specific operation: The user types a question into the chatbot on their smartphone, such as "How crowded is the nearest evacuation shelter?", and sends it.

[1154] Step 4:

[1155] The server analyzes the user's emotional state.

[1156] Specific operation: The server's emotion engine determines emotions from the user's input and identifies states such as "anxiety" or "impatience."

[1157] Step 5:

[1158] The server provides the user with an answer based on the analysis results.

[1159] Specific operation: The server checks the analysis results of the AI ​​model and generates an answer such as, "Shelter A is full. There is space available in shelter B." Depending on the user's emotional state, the server adjusts the response and sends it back, such as, "Please move to shelter B as soon as possible."

[1160] Collection and reliability assessment of disaster-related information

[1161] Step 1:

[1162] The server collects disaster-related information from social media and official organizations.

[1163] Specific operation: The server uses scraping tools and APIs to collect disaster information from social media and official organizations and stores it in a database.

[1164] Step 2:

[1165] The server applies a trustworthiness evaluation algorithm to the collected information.

[1166] What it does: The server uses text analysis and credibility assessment algorithms to score the credibility of each piece of information.

[1167] Step 3:

[1168] A user asks a chatbot for the latest disaster information.

[1169] Specific operation: The user types "Please tell me the latest disaster information" into the chatbot and sends it.

[1170] Step 4:

[1171] The server analyzes the user's emotional state.

[1172] Specific operation: The emotion engine analyzes emotions from the user's question and identifies emotional states such as "anxiety" or "panic."

[1173] Step 5:

[1174] The server selects reliable disaster information and responds to the user.

[1175] Specific operation: The server selects highly reliable information and, taking into account the user's emotional state, generates a message such as "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately," and provides detailed additional information and evacuation routes.

[1176] Multilingual translation and interpretation support

[1177] Step 1:

[1178] The server puts the multilingual translation module into standby mode.

[1179] Specific operation: The server initializes the real-time translation API and prepares for multilingual support.

[1180] Step 2:

[1181] Foreign users ask questions to the chatbot in their native language.

[1182] What happens: The user types a message in their native language and sends it to the chatbot.

[1183] Step 3:

[1184] The server translates the received message and generates an appropriate response.

[1185] Specific operation: The server calls the translation API to translate the message into Japanese, then generates an appropriate response message and translates it back into the user's native language.

[1186] Step 4:

[1187] The server analyzes the user's emotional state.

[1188] What it does: The server's emotion engine uses text analysis to identify the user's emotion.

[1189] Step 5:

[1190] The terminal displays the translated message to the user.

[1191] Specific operation: The server generates a message according to the user's emotional state and sends it to the device. The device receives the message and displays it in the user's native language.

[1192] Matching volunteer skills and locations

[1193] Step 1:

[1194] Users register their skill set and location information.

[1195] Specific operation: Volunteers enter their skills and current location through the chatbot and register on the server.

[1196] Step 2:

[1197] The server stores the registered volunteer information in a database.

[1198] Specific operation: The server saves the entered information in a database and makes it available for verification.

[1199] Step 3:

[1200] When a request for assistance is received, the server selects the most suitable volunteer and notifies them.

[1201] Specific operation: The server compares the request for assistance with the volunteers' skill sets and location information, selects the most suitable volunteer, and sends a notification to the selected volunteer.

[1202] Step 4:

[1203] The server analyzes the emotional state of the volunteer.

[1204] Specific operation: The emotion engine analyzes emotions from volunteers' responses and progress reports to identify "fatigue" and "stress."

[1205] Step 5:

[1206] Volunteer users are notified and begin providing support.

[1207] Specific action: The volunteer replies to the notification by saying "I'm on my way to help," and the server provides information about the specific location where the volunteer will help.

[1208] Step 6:

[1209] The terminal reports the volunteer's progress to the server.

[1210] Specific operation: The volunteer's device sends GPS data to the server in real time, reports the progress of the activity, and provides necessary notifications and advice according to the volunteer's emotional state.

[1211] This enables the system to provide quick and accurate information and support to disaster victims and evacuees, and utilizes an emotion engine to provide flexible responses to maintain users' mental stability.

[1212] Example 2

[1213] 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."

[1214] When a disaster occurs, it is important for victims and evacuees to obtain the necessary information quickly and accurately and ensure their safety. However, current systems do not adequately address the following: safety confirmation, understanding of the congestion situation at evacuation centers, providing reliable disaster information, multilingual support, skill matching with volunteers, and consideration of emotional state. This makes it difficult for victims and evacuees to receive appropriate support.

[1215] 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.

[1216] In this invention, the server includes means for sending push notifications to users when a disaster occurs, means for receiving response input information and location information from users, means for analyzing the received information and automatically estimating the user's safety status and emotional state, means for notifying specific contacts of the estimated safety status and emotional state, means for receiving camera footage and determining the congestion status of evacuation centers in real time, means for collecting disaster-related information from online social networks and official institutions, evaluating its reliability, and providing the user with reliable information, means for translating questions in the user's native language and providing the translated answers, and means for registering volunteers' skill sets and location information in a database and matching them with requests for assistance.

[1217] This will enable victims and evacuees to quickly and accurately obtain the information they need, ensure their safety, and receive appropriate support.

[1218] The "means for sending a push notification to a user when a disaster occurs" is a function that immediately sends a notification from the server to the user's device when a disaster is detected.

[1219] The "means for receiving response input information and location information from the user" is a function by which the server receives information in response to the notification from the user and the location information of the terminal.

[1220] "Means for analyzing received information and automatically estimating the user's safety status and emotional state" refers to a function that uses a specific algorithm to mechanically determine the user's safety and emotional state based on the response information and location information received by the server from the user.

[1221] "Means of notifying specific contacts of estimated safety status and emotional state" is a function in which the server notifies contacts previously set by the user based on the analysis results.

[1222] "Means of receiving camera footage and determining the congestion situation at evacuation centers in real time" refers to a function in which a server receives footage sent from cameras installed at evacuation centers, analyzes it, and determines the current congestion situation.

[1223] "Means of collecting disaster-related information from online social networks and official institutions, assessing its reliability, and providing users with reliable information" refers to a function in which a server collects disaster-related information from online social networking sites and government agencies, evaluates the reliability of that information using an algorithm, and delivers reliable information to users.

[1224] "Means for translating questions in the user's native language and providing translated answers" is a function that translates a user's question entered in a foreign language into the original language and returns the translation result to the user.

[1225] "Means of registering volunteer skill sets and location information in a database and matching them with requests for assistance" is a function that stores volunteers' skills and current locations in a database and automatically matches them with requests for assistance in the event of a disaster.

[1226] This invention is a system that allows disaster victims and evacuees to quickly and accurately obtain necessary information and ensure their safety in the event of a disaster. This system has the following main functions:

[1227] 1. Safety confirmation function for disaster victims

[1228] When a disaster occurs, the server sends a push notification to users who have been registered in the affected area in advance. Users who receive this notification enter their own safety status and current location via their device and send it to the server. When analyzing the received information, the server also uses an emotion engine to analyze the user's emotional state. As a result, the user's safety status and emotional state are notified to specific contacts. This series of steps allows the specific situation of the disaster victim to be quickly communicated to family members and those involved. For example, when an earthquake occurs, the server sends a notification to the user asking, "Are you safe?" and the user replies, "I'm safe." The server then analyzes this information and notifies the family, "You're safe, but it seems you're worried."

[1229] Example prompts for generative AI models

[1230] I would like to know more about the disaster victim safety confirmation system. I would like to know details about how notifications are sent to users and how the information entered is analyzed and used to send notifications.

[1231] 2. Function to grasp the congestion situation at evacuation shelters

[1232] Cameras installed at each shelter periodically capture footage of the shelter and send the video data to a server. The server uses AI image recognition technology to analyze the footage and understand the shelter's congestion status in real time. When a user inquires about the congestion status of a shelter via a chatbot, the server responds based on the latest analysis results. For example, if the server analyzes video from shelter A and detects congestion, when the user asks, "How crowded is the nearest shelter?" the server will reply, "Shelter A is full. There is space available at shelter B."

[1233] Example prompts for generative AI models

[1234] Please tell me about the system that monitors the congestion status of evacuation shelters in real time. I would like to know how the camera footage is analyzed and specific examples of notifications sent to users.

[1235] 3. Disaster-related information collection and reliability evaluation function

[1236] The server collects disaster-related information from social media and official organizations and selects highly reliable information by applying a reliability evaluation algorithm. When a user requests the latest disaster information through the chatbot, the server provides the selected, highly reliable information. For example, when a tsunami warning is issued, the server collects and evaluates information from social media and official organizations and notifies the user, "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately." Additional evacuation information is provided to users who are feeling anxious.

[1237] Example prompts for generative AI models

[1238] Please tell me about a system that provides reliable disaster-related information. I'd like some concrete examples of how the information is collected and evaluated.

[1239] 4. Multilingual translation and interpretation support functions

[1240] The server has a multilingual translation function, so when a foreign user asks the chatbot a question in their native language, it translates the question into the appropriate language in real time and provides the translated answer. An emotion engine also analyzes the foreign user's emotional state and provides additional information as needed. For example, if an English-speaking user asks, "What should I do now?", the server translates and replies, "Evacuate now. There is an earthquake, so please stay safe."

[1241] Example prompts for generative AI models

[1242] Please tell me about multilingual translation and interpretation support systems. I'd like to see some concrete examples of how they translate foreign languages ​​in real time and provide information to users.

[1243] 5. Matching volunteer skills and locations

[1244] The server registers the skill sets and location information of volunteers in a database, and in the event of a disaster, it compares the request for assistance with the skill sets and location information of the volunteers to select and notify the most suitable volunteer. For example, if medical assistance is needed at an evacuation shelter, the server will notify nearby volunteers with medical skills and provide the specific location information of the evacuation shelter to the volunteer who responds, "I'm on my way to help."

[1245] Example prompts for generative AI models

[1246] Please tell me about the system that matches volunteer skill sets with location information. I would like to see some concrete examples of how volunteers are selected and requests for assistance are made.

[1247] As described above, the present invention can achieve rapid and accurate information acquisition and safety assurance for disaster victims and evacuees in the event of a disaster, thereby further improving safety and rapid response in disaster-stricken areas.

[1248] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1249] Safety confirmation function for victims

[1250] Step 1:

[1251] When the server detects a disaster, it sends a push notification to users in the affected area.

[1252] Input: Disaster detection information

[1253] Data processing: Identifying affected areas and generating notification messages

[1254] Output: Sending a push notification to the user device

[1255] Specific operation: The server sends a notification to the user's device, such as a smartphone, saying, "Are you safe?"

[1256] Step 2:

[1257] The user receives the push notification and responds.

[1258] Input: Push notification

[1259] Data processing: Entering safety status and current location

[1260] Output: User response input information and location information

[1261] What happens: The user enters their current location and their situation, such as "I'm OK" or "I'm injured."

[1262] Step 3:

[1263] The terminal transmits the user's response input information and location information to the server.

[1264] Input: User response input information and location information

[1265] Data processing: Converting input information into transmission protocol

[1266] Output: Data sent to the server

[1267] Specific operation: The device sends information to the server using an encrypted communication protocol.

[1268] Step 4:

[1269] The server analyzes the received information and estimates the safety and emotional state of the victims.

[1270] Input: Response input information and location information

[1271] Data processing: Applying analysis algorithms for safety status and emotional state

[1272] Output: Estimated safety status and emotional state

[1273] What it does: The server uses an analysis algorithm to estimate the outcome of "safe" and the emotion of "anxiety."

[1274] Step 5:

[1275] The server notifies specific contacts of the estimated safety status and emotional state.

[1276] Input: Safety status and estimated emotional state

[1277] Data processing: generating and sending notification messages

[1278] Output: Contact notification

[1279] What happens: The server sends a notification to family and friends saying, "You're safe, but we have some concerns."

[1280] Function to grasp the congestion situation of evacuation shelters

[1281] Step 1:

[1282] Cameras installed at evacuation centers periodically capture images and send them to a server.

[1283] Input: Camera image data

[1284] Data processing: Converting video data into transmission protocol

[1285] Output: Data sent to the server

[1286] Specific operation: The camera captures video of the evacuation shelter and sends the data to the server.

[1287] Step 2:

[1288] The server receives the video data and analyzes it using AI image recognition technology.

[1289] Input: Video data

[1290] Data processing: Analysis of video data using AI image recognition technology

[1291] Output: Analysis results of congestion situation

[1292] Specific operation: The server analyzes the video data and grasps the congestion situation at the evacuation center in real time.

[1293] Step 3:

[1294] The user inquires about the congestion status of the evacuation shelter via the chatbot.

[1295] Input: User query

[1296] Data processing: Processing of inquiries

[1297] Output: Sends the query to the server

[1298] Specific behavior: The user asks the chatbot, "How crowded is the nearest evacuation shelter?"

[1299] Step 4:

[1300] The server responds to the user based on the analysis results.

[1301] Input: User inquiries and congestion analysis results

[1302] Data processing: Generate a response message based on the analysis results and the inquiry content

[1303] Output: Response message to the user

[1304] Specific behavior: The server replies, "Shelter A is full. There is space available in shelter B."

[1305] Disaster-related information collection and reliability evaluation function

[1306] Step 1:

[1307] The server collects disaster-related information from social media and official organizations.

[1308] Input: Information from online social networks and official sources

[1309] Data processing: collecting information and storing it in a database

[1310] Output: Collected information data

[1311] Specific operation: The server collects disaster information using APIs from social media and official organizations.

[1312] Step 2:

[1313] The server evaluates the reliability of the collected information.

[1314] Input: Collected information data

[1315] Data processing: Applying reliability evaluation algorithms

[1316] Output: Reliability evaluation result

[1317] Specific operation: The server applies a reliability evaluation algorithm to the information and scores its reliability.

[1318] Step 3:

[1319] Users request the latest disaster information via a chatbot.

[1320] Input: User query

[1321] Data processing: Processing of inquiries

[1322] Output: Sends the query to the server

[1323] Specific operation: The user asks the chatbot, "Please tell me the latest disaster information."

[1324] Step 4:

[1325] The server provides reliable information to the user.

[1326] Input: User query and reliability evaluation results

[1327] Data processing: Selecting information based on the evaluation results and generating response messages

[1328] Output: Response message to the user

[1329] Specific operation: The server responds, "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately."

[1330] Multilingual translation and interpretation support functions

[1331] Step 1:

[1332] Users ask the chatbot questions in their native language.

[1333] Input: Question in the user's native language

[1334] Data processing: Converting question content into text data

[1335] Output: Text data of the question

[1336] Specific behavior: The user asks the chatbot, "What should I do now?"

[1337] Step 2:

[1338] The server translates the question in real time.

[1339] Input: Text data of the question

[1340] Data processing: Applying real-time translation algorithms

[1341] Output: Translated question

[1342] Specific operation: The server translates the English question into Japanese.

[1343] Step 3:

[1344] The server provides the translated answer.

[1345] Input: translated question

[1346] Data processing: generating appropriate answers and translating

[1347] Output: The translated answer to the user

[1348] Specific behavior: The server sends a response to the user saying, "Evacuate now. An earthquake is occurring, so please stay safe."

[1349] Matching volunteer skills and locations

[1350] Step 1:

[1351] Volunteers register their skill set and location information.

[1352] Input: Volunteer skill set and location

[1353] Data processing: Registering information in a database

[1354] Output: Registration information data

[1355] What happens: Volunteers enter their skills and current location into the system.

[1356] Step 2:

[1357] The server stores the registration information in a database.

[1358] Input: Registration information data

[1359] Data processing: Saving to database

[1360] Output: Saved data

[1361] Specific operation: The server stores the volunteer's skill set and location information in a database.

[1362] Step 3:

[1363] In the event of a disaster, the server matches requests for assistance with volunteer information.

[1364] Input: Request for assistance information and volunteer information in the database

[1365] Data processing: Applying matching algorithms

[1366] Output: Optimal volunteer selection results

[1367] Specific operation: The server automatically selects the most suitable volunteer for the request for assistance.

[1368] Step 4:

[1369] The server sends a notification to the volunteer.

[1370] Input: Selection result

[1371] Data processing: Notification message generation

[1372] Output: Notification to volunteers

[1373] Specific operation: The server sends a notification to the selected volunteer saying "Assistance needed."

[1374] Step 5:

[1375] An emotion engine analyzes the emotional state of the volunteer.

[1376] Input: Volunteer responses and information during the activity

[1377] Data processing: Applying emotional state analysis algorithms

[1378] Output: Emotional state analysis results

[1379] How it works: The emotion engine analyzes the volunteer's responses and detects fatigue and stress levels.

[1380] The above processing steps have been described in detail to explain how the system of the present invention contributes to disaster victims and evacuees.

[1381] (Application example 2)

[1382] 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."

[1383] This invention relates to a system that enables disaster victims and evacuees to obtain prompt and appropriate information and ensure their safety in the event of a disaster. Current disaster response systems often have difficulty in confirming the safety of disaster victims and grasping the congestion status of evacuation centers in real time, and also have difficulty responding flexibly to users' emotional states. Furthermore, they have limited multilingual support and are unable to effectively match volunteer skill sets and location information with requests for assistance.

[1384] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1385] In this invention, the server includes means for receiving input information and location information from disaster victims, means for sending push notifications to disaster victims when a disaster occurs, means for analyzing the emotional state of disaster victims using an emotion engine and coordinating a response, means for analyzing the congestion status of evacuation shelters in real time from camera footage, means for providing the analyzed congestion status of evacuation shelters to users, means for collecting disaster-related information and evaluating its reliability, means for providing reliable disaster information to users, means for translating and answering user questions in real time using a multilingual translation function, and means for matching support requests by collating volunteer skill sets and location information. This enables disaster victims and evacuees to quickly and appropriately obtain information and ensure their safety when a disaster occurs.

[1386] "Victims" refers to people affected by a disaster.

[1387] A "push notification" refers to a notification message that a server actively sends to a user's device.

[1388] An "emotion engine" refers to an algorithm or program for analyzing a user's emotional state from input information.

[1389] "Camera footage" refers to video data from cameras installed in evacuation shelters and other locations to capture the situation at the shelter.

[1390] "Real-time" refers to data exchange and analysis occurring immediately and without delay.

[1391] "Disaster-related information" refers to information such as disaster-related news, warnings, and damage status.

[1392] "Reliability" refers to the criteria for assessing whether collected information is accurate.

[1393] "Multilingual translation function" refers to a function that enables automatic translation between multiple languages.

[1394] "Volunteers" refer to people who are registered to provide relief activities free of charge during disasters.

[1395] "Skill set" refers to the specific skills and qualifications that a volunteer possesses.

[1396] "Location information" refers to information that indicates a specific location using technology such as GPS.

[1397] "Request for assistance" refers to requests or demands for specific assistance activities from disaster victims or related organizations.

[1398] "Matching" means matching requests for assistance with volunteers' skill sets and location information to find the best match.

[1399] This invention is a system that allows disaster victims and evacuees to obtain prompt and appropriate information and ensure their safety during disasters. This system includes functions for checking the safety status of disaster victims, understanding the congestion status of evacuation centers, providing disaster-related information, providing multilingual support, and matching volunteers.

[1400] System Configuration

[1401] Hardware:

[1402] Smartphone: A device used by disaster victims and users.

[1403] Server: Processes and manages data for the entire system.

[1404] Cameras: Devices installed in evacuation centers to capture images of crowded areas.

[1405] software:

[1406] React Native: A development framework for smartphone applications.

[1407] Node.js, Express: Server-side frameworks.

[1408] MongoDB: A NoSQL database.

[1409] Google Cloud Vision: Image recognition API.

[1410] Microsoft Azure Text Analytics: Emotion recognition API.

[1411] Google Translate API: Multilingual translation API.

[1412] TensorFlow: An AI model for trustworthiness assessment.

[1413] Processing Overview

[1414] 1. Confirmation of the safety of victims:

[1415] When a disaster occurs, the server sends push notifications to users in the affected area. When users enter their safety status (e.g., "safe" or "injured") and location information on their smartphones, the information is sent to the server. The server analyzes this information and evaluates the user's emotional state using Microsoft Azure Text Analytics. The analysis results are then sent to specific contacts.

[1416] 2. Understanding the congestion situation at evacuation shelters:

[1417] Cameras installed at evacuation centers periodically send images to a server. The server analyzes the images using Google Cloud Vision and determines the congestion status of the evacuation center in real time. When a user inquires about the congestion status of the evacuation center through the chatbot, an answer is provided based on the analysis results. If necessary, the notification content is adjusted according to the user's emotional state.

[1418] 3. Providing disaster-related information:

[1419] The server collects disaster-related information from social media and official organizations, and evaluates its reliability using a TensorFlow model. Based on the evaluation results, reliable information is provided to the user. The method of providing information is adjusted according to the user's emotional state.

[1420] 4. Multilingual support:

[1421] The server uses the Google Translate API to translate questions written by users in their native language in real time, and provides appropriate answers based on the translated questions. The emotion engine also takes into account the emotional state of foreign users.

[1422] 5. Volunteer Matching:

[1423] The server registers the skills and location information of volunteers in a database and matches appropriate volunteers when a request for assistance is made. It also uses an emotion engine to analyze the emotional state of the volunteers and adjust the assistance content and notifications as needed.

[1424] Specific examples

[1425] 1. Examples of how to check on the safety of disaster victims:

[1426] When an earthquake occurs, the server quickly sends a notification to all users in the affected area asking, "Are you safe?" The user replies, "I'm safe," and the notification is sent along with their location information. Based on this information, the server analyzes the user's safety status, and the emotion engine analyzes the user's emotional state. As a result, detailed safety information such as "You're safe, but you seem worried" is sent to family and friends.

[1427] 2. Specific examples of grasping the congestion situation of evacuation shelters:

[1428] The server periodically analyzes the camera footage from shelter A and detects that the shelter is full. When a user asks the chatbot, "How crowded is the nearest shelter?", the server replies, "Shelter A is full. There is space available at shelter B." Depending on the user's emotional state, the response is adjusted to, "Please move to shelter B as soon as possible."

[1429] 3. Example prompt:

[1430] "Please let us know the latest tsunami information. Our users are very worried."

[1431] "Identify nearby locations seeking medical assistance and notify qualified volunteers. Analyze stress levels with our emotion engine and provide the necessary advice."

[1432] In this way, the present invention combines emotion recognition with disaster information, enabling highly flexible and rapid responses.

[1433] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1434] Step 1:

[1435] The server detects that a disaster has occurred and sends a push notification to users in the affected area.

[1436] Input: Disaster occurrence information

[1437] Output: Generate and send a push notification

[1438] Specific operation: The server receives disaster occurrence information from the disaster information database and sends a push notification asking "Are you safe?" to specific users based on a list of users in the affected area.

[1439] Step 2:

[1440] Users use their smartphones to input their safety status and location information and send it to the server.

[1441] Input: User's safety status and location information

[1442] Output: Send safety status data

[1443] Specific operation: The user selects an option such as "safe" or "injured" through a smartphone app and sends it along with their location information.

[1444] Step 3:

[1445] The server analyzes the received information and automatically estimates the safety status of the victims.

[1446] Input: User's safety status and location information

[1447] Output: Estimated safety status

[1448] How it works: The server analyzes safety status data and location information, evaluates the user's emotional state using Microsoft Azure Text Analytics, and automatically estimates the user's overall safety status.

[1449] Step 4:

[1450] The server notifies the specific contact person of the estimated safety status.

[1451] Input: Estimated safety status and emotional state

[1452] Output: Safety information notification

[1453] Specific operation: The server notifies the estimated safety status and emotional state to family and friend contacts.

[1454] Step 5:

[1455] The cameras at the shelter periodically send footage to a server, which then analyzes the footage.

[1456] Input: Shelter camera footage

[1457] Output: Congestion status judgment result

[1458] Specific operation: The server uses Google Cloud Vision to analyze the received video and determine the congestion status of the evacuation shelter in real time.

[1459] Step 6:

[1460] When a user asks the chatbot about the congestion situation at an evacuation shelter, the server provides an answer based on the analysis results.

[1461] Input: User inquiry about congestion status

[1462] Output: Response about congestion status

[1463] Specific operation: When a user asks the chatbot, "How crowded is the nearest evacuation shelter?", the server responds based on the latest analysis results and provides the congestion status. If necessary, it adjusts the response according to the user's emotional state.

[1464] Step 7:

[1465] The server collects disaster-related information from social media and official organizations and evaluates its reliability.

[1466] Input: Disaster-related information

[1467] Output: reliable information

[1468] Specific operation: The server collects disaster-related information from social media and official organizations on the Internet and evaluates the reliability of the information using a TensorFlow model.

[1469] Step 8:

[1470] The server provides the user with reliable information based on the evaluation results.

[1471] Input: Reliable information

[1472] Output: Provide information to the user

[1473] Specific behavior: The server provides reliable disaster information to users through push notifications and chatbots, adjusting the details of the information and additional instructions depending on the user's emotional state.

[1474] Step 9:

[1475] The server uses a multilingual translation function to translate the user's question in real time and provide an answer.

[1476] Input: User question (source language)

[1477] Output: Answer to user (translated language)

[1478] What happens: The server uses the Google Translate API to translate the question written by the user in their native language into the appropriate language and provides the translated answer to the user.

[1479] Step 10:

[1480] The server compares volunteers' skill sets and location information and matches requests for assistance.

[1481] Input: Volunteer skill set and location, request for assistance

[1482] Output: Notification to volunteer

[1483] What it does: The server retrieves the skillset and location information from the volunteer database, selects the best volunteer to respond to the request, and notifies them. It uses the emotion engine to adjust the assistance and notification as needed.

[1484] 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.

[1485] 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.

[1486] 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.

[1487] [Third embodiment]

[1488] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1489] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1490] 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).

[1491] 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.

[1492] 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.

[1493] 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).

[1494] 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.

[1495] 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.

[1496] 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.

[1497] 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.

[1498] 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.

[1499] 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."

[1500] The present invention provides a system for ensuring the safety of disaster victims and evacuees by enabling them to quickly and accurately obtain necessary information in the event of a disaster. Details of how to implement this system are described below.

[1501] 1. Confirming the safety of disaster victims

[1502] This system includes a function for checking the safety status of disaster victims when a disaster occurs. When a disaster occurs, the server sends a push notification to users in the affected area. Users respond to the notification received through their smartphone or other device and enter their safety status and current location. The device sends the entered information and location information to the server, which analyzes this and automatically estimates the safety status of the disaster victims. The estimated safety status is then notified to specific contacts.

[1503] Specific examples

[1504] For example, when an earthquake occurs, the server quickly sends a notification to all users in the affected area asking, "Are you safe?" Users who respond reply, "I'm safe," and this is sent along with their location information. Based on this information, the server analyzes the user's safety status and notifies their family and friends.

[1505] 2. Understanding the congestion situation at evacuation shelters

[1506] Cameras installed at evacuation centers regularly capture footage and upload it to a server. The server analyzes these images using AI image recognition technology to grasp the congestion status of each evacuation center in real time. When a user inquires about the congestion status of a shelter through the chatbot, the server provides the user with an answer based on the analysis results.

[1507] Specific examples

[1508] The server periodically analyzes the camera footage from shelter A and detects that the shelter is full. When a user asks the chatbot, "How crowded is the nearest shelter?", the server replies, "Shelter A is full. There is space available at shelter B."

[1509] 3. Collection of disaster-related information and reliability assessment

[1510] The server collects disaster-related information from social media and official sources. It then applies a reliability evaluation algorithm to the collected information to select the most reliable information. When a user requests the latest disaster information through the chatbot, the server provides the selected, reliable information.

[1511] Specific examples

[1512] When a tsunami warning is issued, the server collects information from social media and official organizations and evaluates its reliability. When a user asks, "Please tell me the latest disaster information," the server responds, "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately."

[1513] 4. Multilingual translation and interpretation support

[1514] The server has a multilingual translation function, so when a foreign user asks the chatbot a question in their native language, the server translates it into the appropriate language in real time, and the translated answer is provided to the user.

[1515] Specific examples

[1516] When an English-speaking user asks the chatbot, "What should I do now?", the server translates and replies, "Please evacuate now. There is an earthquake, so please stay safe."

[1517] 5. Matching volunteer skills and locations

[1518] The server registers the skill sets and location information of volunteers in a database, and in the event of a disaster, it compares the request for assistance with the skill sets and location information of the volunteers to select and notify the most suitable volunteers. It also tracks the progress of volunteer activities.

[1519] Specific examples

[1520] If a shelter needs medical assistance, the server notifies nearby registered volunteers with medical skills. When a volunteer responds, "I'm on my way to help," the server provides the specific location of the shelter and tracks the volunteer's progress.

[1521] As described above, the present invention is a system that enables quick and accurate provision of information and support to disaster victims and evacuees in the event of a disaster, thereby ensuring the safety of disaster-stricken areas and enabling quick response.

[1522] The processing flow will be explained below.

[1523] Confirming the safety of victims

[1524] Step 1:

[1525] When the server detects a disaster, it sends a push notification to users in the affected area.

[1526] Specific operation: The server references a database of affected areas and sends a message to all relevant users asking, "Are you safe?"

[1527] Step 2:

[1528] The user receives the notification and enters a response.

[1529] Specific action: The user types a message into the device, such as "I'm safe" or "I need help," and sends it.

[1530] Step 3:

[1531] The device sends input information and location information to the server.

[1532] Specific operation: The device's GPS function obtains the current location and sends it to the server along with the entered text message.

[1533] Step 4:

[1534] The server analyzes the received information and automatically estimates the safety status of the victims.

[1535] How it works: The server uses an AI model to analyze messages and location information to estimate the safety status of the person. The results are stored in a database.

[1536] Step 5:

[1537] The server notifies the specific contact of the estimation result.

[1538] Specific operation: Based on the estimated safety information, the server sends the information to pre-registered contacts (family, friends, etc.).

[1539] Grasping the congestion situation at evacuation centers

[1540] Step 1:

[1541] Cameras installed at evacuation centers regularly capture footage and upload it to a server.

[1542] Specific operation: The camera captures video at regular intervals and sends the data to the server.

[1543] Step 2:

[1544] The server analyzes the received video.

[1545] Specific operation: The server inputs the video into an AI image recognition model, counts the number of people, and determines the congestion level.

[1546] Step 3:

[1547] A user inquires about congestion status via a chatbot.

[1548] Specific operation: The user types a question into the chatbot on their smartphone, such as "How crowded is the nearest evacuation shelter?", and sends it.

[1549] Step 4:

[1550] The server provides the user with an answer based on the analysis results.

[1551] Specific operation: The server checks the analysis results of the AI ​​model, generates an answer such as "Shelter A is full. There is space available in shelter B," and sends it back to the user.

[1552] Collection and reliability assessment of disaster-related information

[1553] Step 1:

[1554] The server collects disaster-related information from social media and official organizations.

[1555] Specific operation: The server uses scraping tools and APIs to collect disaster information from social media and official organizations and stores it in a database.

[1556] Step 2:

[1557] The server applies a trustworthiness evaluation algorithm to the collected information.

[1558] What it does: The server uses text analysis and credibility assessment algorithms to score the credibility of each piece of information.

[1559] Step 3:

[1560] A user asks a chatbot for the latest disaster information.

[1561] Specific operation: The user types "Please tell me the latest disaster information" into the chatbot and sends it.

[1562] Step 4:

[1563] The server selects reliable disaster information and responds to the user.

[1564] Specific operation: The server selects information with high reliability, generates a message such as "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately," and sends it back to the user.

[1565] Multilingual translation and interpretation support

[1566] Step 1:

[1567] The server puts the multilingual translation module into standby mode.

[1568] Specific operation: The server initializes the real-time translation API and prepares for multilingual support.

[1569] Step 2:

[1570] Foreign users ask questions to the chatbot in their native language.

[1571] What happens: The user types a message in their native language and sends it to the chatbot.

[1572] Step 3:

[1573] The server translates the received message and generates an appropriate response.

[1574] Specific operation: The server calls the translation API to translate the message into Japanese, then generates an appropriate corresponding message, translates it again into the foreign language, and sends it.

[1575] Step 4:

[1576] The terminal displays the translated message to the user.

[1577] Specific operation: The message received by the user's device is displayed in the user's native language.

[1578] Matching volunteer skills and locations

[1579] Step 1:

[1580] Users register their skill set and location information.

[1581] Specific operation: Volunteers enter their skills and current location through the chatbot and register on the server.

[1582] Step 2:

[1583] The server stores the registered volunteer information in a database.

[1584] Specific operation: The server saves the entered information in a database and makes it available for verification.

[1585] Step 3:

[1586] When a request for assistance is received, the server selects the most suitable volunteer and notifies them.

[1587] Specific operation: The server compares the request for assistance with the volunteers' skill sets and location information, selects the most suitable volunteer, and sends a notification to the selected volunteer.

[1588] Step 4:

[1589] Volunteer users are notified and begin providing support.

[1590] Specific actions: The volunteer replies to the notification by saying "I'm heading to help" and receives information about the specific location of the help from the server.

[1591] Step 5:

[1592] The terminal reports the volunteer's progress to the server.

[1593] Specific operation: Volunteers' devices send GPS data to the server in real time and report the progress of their activities.

[1594] This enables the system to provide quick and accurate information and support to disaster victims and evacuees.

[1595] Example 1

[1596] 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."

[1597] When a disaster occurs, it is necessary to quickly and accurately collect information and provide it to victims and evacuees. However, conventional systems take time to collect, analyze, and provide information, and there is a possibility that the information may be unreliable. Furthermore, there are issues with insufficient multilingual support and appropriate coordination of volunteers. The present invention aims to solve these issues.

[1598] 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.

[1599] In this invention, the server includes means for receiving input information and location information from disaster victims, means for sending push notifications to disaster victims when a disaster occurs, means for analyzing the received information and automatically estimating the safety status of the disaster victims, means for notifying specific contacts of the estimated safety status, means for providing a multilingual translation function in real time, and means for selecting and notifying the most suitable volunteers by comparing the volunteers' skill sets and location information. This makes it possible to quickly collect and analyze reliable information when a disaster occurs, and to accurately respond to multiple languages ​​and coordinate volunteers.

[1600] "Input information from disaster victims" refers to information that disaster victims record about their situation and location during a disaster and send to the system.

[1601] "Location Information" means current geographic coordinate data obtained using GPS or other location-determining technology.

[1602] "Push notification" refers to an automatic notification message sent by a server to a user's device.

[1603] "Analysis" refers to the act of processing data to extract meaningful information.

[1604] "Safety status" refers to information indicating the status of life and safety of disaster victims, such as whether they are safe.

[1605] "Contact information" refers to the contact information of family members, friends, etc. who will be notified of the victim's safety.

[1606] "Multilingual Translation Functionality" means a system function that automatically translates text or messages between different languages.

[1607] "Volunteer skill set" refers to the specific skills and experience a volunteer possesses.

[1608] "Location matching" refers to the process of analyzing volunteers' location information and matching it with locations where assistance is needed.

[1609] "Camera footage" refers to images and video data captured using a camera device.

[1610] "AI image recognition technology" refers to technology that uses artificial intelligence to analyze the content of images and videos.

[1611] "Online social network" refers to a system for sharing information through internet services such as social networking sites.

[1612] "Official sources" refers to reliable sources provided by government agencies or authorized organizations.

[1613] A "trustworthiness assessment algorithm" refers to a logical method for assessing the reliability of acquired information based on numerical values ​​and criteria.

[1614] The present invention relates to a system for providing information quickly and accurately and supporting disaster victims in the event of a disaster. The details of implementing this system are described below.

[1615] 1. Hardware and software configuration

[1616] server

[1617] The server has the following features:

[1618] Database Management System (DBMS)

[1619] Push notification server

[1620] AI image recognition engine

[1621] Multilingual translation engine (such as Google Translate API)

[1622] Reliability Evaluation Algorithm

[1623] Volunteer Matching Algorithm

[1624] Terminal

[1625] The device used by the user has the following features:

[1626] GPS Modules

[1627] Camera Device

[1628] Wireless communication module (Wi-Fi, LTE / 5G)

[1629] Newspaper reception application

[1630] 2. Confirming the safety of disaster victims

[1631] The server uses earthquake sensors and weather data to detect the occurrence of a disaster. When a disaster occurs, the server sends a push notification to users in the affected area asking, "Are you safe?" Users receive the notification on their smartphones or other devices and respond by inputting their safety status (e.g., "safe," "injured," "unable to provide information") and location information. The devices then send this information to the server. The server analyzes the received information, estimates the safety status of the victims, and notifies specific contacts.

[1632] Specific examples

[1633] The server detects the occurrence of an earthquake and sends a push notification to all users in the affected area asking, "Are you safe?"

[1634] The user responds "I'm safe," and the system uses GPS to obtain their current location and sends the results to the server.

[1635] The server analyzes the received information and notifies the user's family that "the user is safe."

[1636] 3. Understanding the congestion situation at evacuation shelters

[1637] Cameras installed at evacuation centers regularly capture footage and upload it to a server. The server then analyzes the footage using AI image recognition technology to grasp the congestion status of each evacuation center in real time. When a user inquires about the congestion status of a shelter through the chatbot, the server provides the user with an answer based on the analysis results.

[1638] Specific examples

[1639] The camera takes video of the evacuation center every minute and uploads the data to a server.

[1640] The server analyzes the video and calculates the level of congestion, such as "Shelter A is currently 70% full."

[1641] When a user asks the chatbot, "How crowded is shelter A?", the server responds with the current congestion situation.

[1642] 4. Collection of disaster-related information and reliability assessment

[1643] The server collects disaster-related information from social media and official sources, applies a reliability evaluation algorithm to the collected information, and stores the most reliable information in a database. When a user requests the latest disaster information through the chatbot, the server extracts and provides the most reliable information from the database.

[1644] Specific examples

[1645] The server collects disaster information from the Twitter API and RSS feeds from official organizations.

[1646] A reliability assessment algorithm scores the reliability of the information and stores it in a database.

[1647] When a user asks, "Please tell me the latest tsunami information," the server will provide reliable information and reply, "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately."

[1648] 5. Multilingual translation and interpretation support

[1649] The server uses a multilingual translation engine to instantly translate questions from foreign users and provide answers in the appropriate language. When a user asks a question in their native language, the server automatically translates the question, generates an appropriate answer, translates it, and provides it to the user.

[1650] Specific examples

[1651] An English-speaking user types "What should I do now?" into the chatbot.

[1652] The server translates the question into Japanese as "What should I do now?" and generates an appropriate answer.

[1653] The generated answer is translated back into English and replied to the user, "Please evacuate immediately. Ensure your safety as an earthquake is occurring."

[1654] 6. Matching volunteer skillsets with location information

[1655] The server registers the skill sets and location information of volunteers in a database. In the event of a disaster, the server matches requests for assistance with the skill sets and location information of volunteers to select the most suitable volunteers. Selected volunteers are notified and the progress of the assistance is tracked.

[1656] Specific examples

[1657] Volunteers register their medical skills and current location on a web portal.

[1658] A server receives a request for medical assistance from an evacuation shelter.

[1659] The server searches the database and selects the nearest suitable volunteer.

[1660] A notification is sent to the selected volunteers saying, "Medical assistance is needed at shelter B. Can you go?"

[1661] When a volunteer responds, "I'm on my way to help," the server provides the location of the shelter and the type of assistance needed, and tracks their progress in real time.

[1662] This enables the present invention to provide rapid and accurate information and support in the event of a disaster, ensuring the safety of disaster-stricken areas and enabling rapid response.

[1663] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1664] 1. Confirming the safety of disaster victims

[1665] Step 1:

[1666] The server detects the occurrence of disasters based on earthquake sensor and meteorological data. As input, it receives real-time data from earthquake sensors and meteorological stations. As output, it generates information on the occurrence of a detected disaster.

[1667] Step 2:

[1668] When the server detects a disaster, it sends a push notification to users in the affected area. The input is the detected disaster information and the contact information of users in the affected area. The output is a generated push notification message that is sent to the user's device.

[1669] Specific behavior:

[1670] The server sends a push notification with the message "Are you OK?"

[1671] Step 3:

[1672] Users receive push notifications on their smartphones or other devices and enter their safety status and location information. The inputs include the safety status entered by the user through the device and location information obtained from the device's GPS function. The output is that the device sends the entered data to the server.

[1673] Specific behavior:

[1674] The user selects an option such as "I'm fine" or "I'm injured."

[1675] The device obtains location information from GPS and sends it to the server along with safety information.

[1676] Step 4:

[1677] The server analyzes the received information and estimates the safety status of the victims. The inputs are the safety status information and location information sent from the device. The output generates the safety status as an analysis result.

[1678] Specific behavior:

[1679] The server processes the data it receives using machine learning models and rule-based analysis algorithms to estimate the safety of victims.

[1680] Step 5:

[1681] The server notifies specific contacts (family and friends) of the estimated safety status. The inputs are the analyzed safety status and the victim's contact information. The output is a notification message sent to the contacts.

[1682] Specific behavior:

[1683] The server sends a message to family and friends saying "You are safe."

[1684] 2. Understanding the congestion situation at evacuation shelters

[1685] Step 1:

[1686] Cameras installed at evacuation shelters periodically capture video. The input is the video data captured by the camera device. The output is the generated video file that is saved.

[1687] Specific behavior:

[1688] The camera captures and stores footage every minute.

[1689] Step 2:

[1690] The device uploads the captured video to the server. The input is the video data obtained from the camera. The output is the video data that is sent to the server.

[1691] Specific behavior:

[1692] The device sends video data to the server via Wi-Fi or mobile network.

[1693] Step 3:

[1694] The server analyzes the received video using AI image recognition technology to grasp the congestion situation in real time. The input is the video data sent from the device. The output is an analyzed congestion level value.

[1695] Specific behavior:

[1696] The server uses a deep learning model to analyze the video data, count the number of people inside the shelter, and calculate the congestion rate.

[1697] Step 4:

[1698] A user inquires about the congestion status of a shelter through a chatbot. The input is a text question that the user enters into the chatbot. The output is a query request that is sent to the server.

[1699] Specific behavior:

[1700] A user asks the chatbot, "How crowded is shelter A?"

[1701] Step 5:

[1702] The server provides a response to the user based on the analysis results. The inputs are a user query request and the analyzed congestion data. The output is a response message that is sent to the user.

[1703] Specific behavior:

[1704] The server responds, "Shelter A is currently 70% full."

[1705] 3. Collection of disaster-related information and reliability assessment

[1706] Step 1:

[1707] The server periodically collects disaster-related information from social media and official organizations. The input data is from social media APIs and official RSS feeds. The output data is stored in a database.

[1708] Specific behavior:

[1709] The server collects disaster information using the Twitter API and RSS feeds from official organizations.

[1710] Step 2:

[1711] The server applies a reliability assessment algorithm to the collected information. The input is the collected disaster-related information. The output is the information with a reliability score.

[1712] Specific behavior:

[1713] A reliability assessment algorithm scores the reliability of the information and stores it in a database.

[1714] Step 3:

[1715] A user requests the latest disaster information through a chatbot. The input is a text question that the user types into the chatbot. The output is a query request that is sent to the server.

[1716] Specific behavior:

[1717] A user asks, "What is the latest tsunami information?"

[1718] Step 4:

[1719] The server extracts reliable information from the database and provides it to the user. The input is the query request and the information in the database with a high reliability score. The output is a response message that is sent to the user.

[1720] Specific behavior:

[1721] The server responds, "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately."

[1722] 4. Multilingual translation and interpretation support

[1723] Step 1:

[1724] The user asks the chatbot a question in their native language. The input is the text entered by the user in their native language. The output is a generated question request that is sent to the server.

[1725] Specific behavior:

[1726] A user asks in English, "What should I do now?"

[1727] Step 2:

[1728] The server automatically identifies the input question and passes it to the translation engine. The input is a question request from the user. The output is generated text data that is sent to the translation engine.

[1729] Specific behavior:

[1730] The server sends the question to the Google Translate API, which translates it from English to Japanese.

[1731] Step 3:

[1732] The translation engine translates the question into the appropriate language. It takes as input the text data sent from the server and produces as output the translated question text.

[1733] Specific behavior:

[1734] Google Translate API translates "What should I do now?" into Japanese as "What should you do now?"

[1735] Step 4:

[1736] The server generates answers to translated questions. As input, it has the translated question text. As output, it produces the generated answer text.

[1737] Specific behavior:

[1738] The server responds to the translated question with, "Evacuate now. There is an earthquake, please stay safe."

[1739] Step 5:

[1740] The server translates the answer back into the user's native language and sends a reply. The input is the generated answer text. The output is the translated answer message sent to the user.

[1741] Specific behavior:

[1742] The server then sends the generated response back to the Google Translate API, which translates it into English and replies to the user with "Please evacuate immediately. Ensure your safety as an earthquake is occurring."

[1743] 5. Matching volunteer skills and locations

[1744] Step 1:

[1745] Volunteers register their skill sets and location information in a database. The input is the skill set and location information that the volunteer enters through a web portal. The output is a saved profile of the volunteer.

[1746] Specific behavior:

[1747] Volunteers register their medical skills and current location on a web portal.

[1748] Step 2:

[1749] When a disaster occurs, the server receives requests for assistance. The input is a request for assistance from an evacuation center. The output is a corresponding request for assistance.

[1750] Specific behavior:

[1751] The server receives a request from a shelter saying "medical assistance needed."

[1752] Step 3:

[1753] The server selects appropriate volunteers from a database based on the request for assistance. The inputs are the request for assistance and the skill sets and location information of the registered volunteers. The output is a list of selected volunteers.

[1754] Specific behavior:

[1755] The server searches the database and selects the nearest suitable volunteer.

[1756] Step 4:

[1757] The server sends notifications to selected volunteers. It takes as input the contact information of the selected volunteers. It generates the notification message as output.

[1758] Specific behavior:

[1759] The server sends a notification to the selected volunteer saying, "Medical assistance is needed at shelter B. Can you go?"

[1760] Step 5:

[1761] When a volunteer responds to help, the server provides the specific location of the help and detailed information. The input is the response from the volunteer and the evacuation shelter information. The output is a message that provides the location of the help and detailed information.

[1762] Specific behavior:

[1763] When a volunteer responds, "I'm on my way to help," the server provides the location of the evacuation shelter and the type of assistance needed.

[1764] Step 6:

[1765] The server tracks the progress of volunteer activities. It has as input the progress data of volunteers. It generates progress reports as output.

[1766] Specific behavior:

[1767] The server uses the volunteers' mobile GPS to track their progress in real time until they arrive at the destination.

[1768] (Application example 1)

[1769] 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."

[1770] When a disaster occurs, there are currently insufficient means for victims and evacuees to quickly and accurately obtain the necessary information and ensure their safety. There is also a need for more efficient confirmation of the safety of victims and evacuation guidance within factories and other facilities in disaster-stricken areas. In addition, there is a need for integrated provision of functions such as the collection and reliability evaluation of disaster-related information, the understanding of the congestion situation at evacuation centers, and multilingual support, but current technology makes it difficult to fully realize these needs.

[1771] 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.

[1772] In this invention, the server includes a means for receiving input information and location information from disaster victims, a means for sending push notifications to disaster victims when a disaster occurs, a means for analyzing the received information and automatically estimating the safety status of disaster victims, a means for notifying specific contacts of the estimated safety status, a means for confirming the safety of disaster victims within the factory, providing evacuation guidance and disaster-related information, and a means for installing these functions in factory robots. This ensures the safety of disaster victims and evacuees in the event of a disaster, and enables quick and efficient safety confirmation and evacuation guidance within the factory.

[1773] "Means for receiving input information and location information from disaster victims" refers to a device or software function that collects information on the safety and current location provided by disaster victims during a disaster and processes it within the system.

[1774] "Means for sending push notifications to disaster victims when a disaster occurs" refers to a technical means for immediately notifying disaster victims of important information when a disaster occurs.

[1775] "Means for analyzing received information and automatically estimating the safety status of disaster victims" refers to algorithms or systems for automatically determining the safety status of disaster victims based on information collected from the disaster victims.

[1776] "Means of notifying specific contacts of estimated safety status" refers to communication technology that quickly conveys the situation to the victims' families and other relevant parties based on the results of the analysis.

[1777] "Means for checking the safety of disaster victims, guiding evacuation, and providing disaster-related information within factories" refers to systems and devices that are used within factories and other facilities to check the safety of people in the event of a disaster, instruct them to evacuate safely, and provide necessary information.

[1778] "Means for installing these functions in factory robots" refers to methods and technologies for incorporating the various disaster response functions mentioned above into robots used in factories.

[1779] "Means for receiving images from cameras installed at each evacuation shelter" refers to devices and technologies for acquiring images in real time through cameras installed at evacuation shelters and transmitting them to the system.

[1780] "Means of analyzing received video and determining the congestion status of evacuation centers in real time" refers to algorithms and technology that analyze camera footage and automatically determine the number of people and the level of congestion in evacuation centers.

[1781] "Means of responding to user inquiries about congestion status based on analysis results" is a function that allows an appropriate reply based on analyzed data when a user asks about the congestion status of an evacuation shelter.

[1782] "Means of collecting disaster-related information from online social networks and official institutions" refers to systems and technologies for collecting the latest disaster information from sources such as social media and official institutions.

[1783] "Means for assessing the reliability of collected information" refers to algorithms and evaluation criteria for determining how accurate the collected disaster information is.

[1784] The "means for providing users with reliable information based on the evaluation results" refers to a system or function for providing users with appropriate information using the results of the reliability evaluation.

[1785] This invention relates to a system that enables disaster victims and evacuees to quickly and accurately obtain necessary information and ensure their safety during a disaster. This system includes the following components. First, a means for receiving input information and location information from disaster victims is provided. This is used by a server to receive information sent from smartphones and other mobile devices.

[1786] Next, a means for sending push notifications to disaster victims is provided. With this means, the system can immediately send notifications such as "Are you safe?" to users in the affected area when a disaster occurs.

[1787] The system also includes an algorithm that analyzes the received information and automatically estimates the safety status of disaster victims. This algorithm estimates whether a specific disaster victim is safe based on their location and input information.

[1788] Furthermore, it includes a means to notify specific contacts of the estimated safety status. This allows the analyzed safety information to be quickly communicated to the victims' families and related parties. The system also has functions to check the safety of victims within the factory, provide evacuation guidance, and provide disaster-related information. These functions are installed on robots used within the factory to implement appropriate responses.

[1789] The system also has a means of receiving video footage from cameras installed at each evacuation center. The server receives these images, analyzes them, and determines the congestion status of the evacuation center in real time. When a user inquires about the congestion status through a chatbot or other interface, the server provides an appropriate response based on the analysis results.

[1790] It also includes a means of collecting disaster-related information from online social networks and official organizations. This information is collected by a server, and the reliability of the information is evaluated. As a result of the evaluation, reliable information is provided to users.

[1791] Furthermore, the server is capable of handling multilingual translation. When a user speaking a different language asks a question in their native language, the question is translated in real time into the appropriate language and provided.

[1792] Finally, it also includes a means for matching volunteer skill sets with location information. The server manages the skill sets and location information of volunteers registered in the database, and in the event of a disaster, it selects and notifies the most suitable volunteer in response to a request for assistance. This function allows necessary assistance to be provided quickly and efficiently.

[1793] A concrete example of this system would be the following scenario. For example, when an earthquake occurs, the server sends a notification to all users in the affected area asking, "Are you safe?" If the user replies, "I'm safe," that information and their location are sent to the server, which then notifies their family and friends. It is also possible to analyze camera footage from evacuation shelters to determine the congestion situation and provide information such as, "Evacuation shelter A is full. There is space available at evacuation shelter B."

[1794] Furthermore, in the process of collecting disaster information and assessing its reliability, if you ask, "Please tell me the latest disaster information," you will receive highly reliable information. For example, you will receive a response such as, "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately."

[1795] Examples of prompt sentences include "A disaster has occurred. Are you safe?" and "Please tell me the latest disaster information." In this way, the present invention can ensure the safety of victims and evacuees and realize a prompt response in the event of a disaster.

[1796] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1797] Step 1:

[1798] The server sends a push notification when a disaster occurs. It sends a notification to smartphones of users in the affected area asking, "Are you safe?" The input is the trigger for the disaster occurrence, and the output is the notification to the user. Users who receive the push notification can enter a response message such as "I'm safe" on their smartphones.

[1799] Step 2:

[1800] The device (user's smartphone) responds to the received push notification and sends the device's location information to the server. The input is the user's response and location information, and the output is data sent to the server. The device provides real-time information by sending a response message and location data obtained from GPS to the server.

[1801] Step 3:

[1802] The server analyzes the received response message and location information and automatically estimates the safety status of the victim. The input is the response message and location information, and the output is the estimated safety status. The server uses a machine learning algorithm to analyze the response message and estimate the status, such as "safe" or "injured." In doing so, it also takes location information into account to comprehensively evaluate the situation.

[1803] Step 4:

[1804] The server notifies specific contacts of the estimated safety status. The input is the estimated safety status result and contact information, and the output is a notification to the contacts. Based on the analysis results, safety information is sent to the victim's family and friends via SMS or email.

[1805] Step 5:

[1806] The server periodically receives video from cameras installed at evacuation centers. The input is the camera video, and the output is the received video data. The video data is uploaded to the server and analyzed in the next step.

[1807] Step 6:

[1808] The server analyzes the received video data using image recognition technology and determines the congestion status of the evacuation shelter in real time. The input is the video data and the output is the evaluation result of the congestion status. The number of people is counted using image recognition technology and the fullness of the evacuation shelter is evaluated.

[1809] Step 7:

[1810] When a user inquires about the congestion situation, the server provides an answer based on the analysis results. The input is the user's inquiry, and the output is an answer based on the analysis results. For example, if a user asks, "How crowded is the nearest evacuation shelter?" the server will answer, "Shelter A is full. There is space available at shelter B."

[1811] Step 8:

[1812] The server collects disaster-related information from online social networks and official organizations. The input is a real-time information collection request, and the output is the collected information. The server uses APIs and web scraping to obtain the latest information from social networks and official websites.

[1813] Step 9:

[1814] The server evaluates the reliability of the collected disaster-related information. The input is the collected information, and the output is the reliability evaluation result. Using a generative AI model, the reliability of each piece of information is scored and the most reliable information is selected.

[1815] Step 10:

[1816] When a user requests the latest disaster information, the server provides highly reliable information. The input is the user's inquiry, and the output is highly reliable information. For example, in response to the prompt "Tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately."

[1817] Step 11:

[1818] The server manages the skill sets and location information of volunteers registered in the database, and selects and notifies the most suitable volunteers in the event of a disaster. The input is a request for assistance and volunteer information, and the output is a notification to the volunteer. For example, if medical assistance is needed, nearby volunteers with medical skills will be contacted and asked to provide assistance.

[1819] Step 12:

[1820] If the user is from a different country, the server uses a multilingual translation function to translate into the appropriate language in real time. The input is a question in a different language, and the output is a translated answer. For example, in response to the question "What should I do now?", the server translates and responds with "Please evacuate now. There is an earthquake, so please stay safe."

[1821] Through the above processing steps, this system achieves efficient information management and rapid response in the event of a disaster.

[1822] 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.

[1823] The present invention is a system that enables disaster victims and evacuees to quickly and accurately obtain necessary information and ensure their safety during a disaster, and in particular includes a function that recognizes the user's emotions and adjusts responses. Details for implementing this system are described below.

[1824] 1. Confirming the safety of disaster victims

[1825] This system includes a function for checking the safety status of disaster victims when a disaster occurs. When a disaster occurs, the server sends a push notification to users in the affected area. Users respond to the notification received through their smartphone or other device and enter their safety status and current location. The device sends the entered information and location information to the server, which analyzes this and automatically estimates the safety status of the disaster victims. Furthermore, an emotion engine analyzes the emotions from the user's input information and reflects them in the estimation results. The estimated safety status is then notified to specific contacts.

[1826] Specific examples

[1827] For example, when an earthquake occurs, the server quickly sends a notification to all users in the affected area asking, "Are you safe?" The user replies, "I'm safe," and the notification is sent along with their location information. Based on this information, the server analyzes the user's safety status, and the emotion engine analyzes the user's emotional state. As a result, family and friends are notified of detailed safety information such as, "They're safe, but they seem worried."

[1828] 2. Understanding the congestion situation at evacuation shelters

[1829] Cameras installed in evacuation centers regularly capture footage and upload it to a server. The server analyzes these images using AI image recognition technology to grasp the congestion status of each evacuation center in real time. When a user inquires about the congestion status of a shelter through the chatbot, the server provides the user with an answer based on the analysis results. The content and priority of notifications are adjusted taking into account the user's emotional state.

[1830] Specific examples

[1831] The server periodically analyzes the camera footage from shelter A and detects that the shelter is full. When a user asks the chatbot, "How crowded is the nearest shelter?", the server replies, "Shelter A is full. There is space available at shelter B." Depending on the user's emotional state, the response is adjusted to, "Please move to shelter B as soon as possible."

[1832] 3. Collection of disaster-related information and reliability assessment

[1833] The server collects disaster-related information from social media and official sources. It then applies a reliability evaluation algorithm to the collected information to select the most reliable information. When a user requests the latest disaster information through the chatbot, the server provides the selected, reliable information. Furthermore, the server adjusts the way the information is presented depending on the user's emotional state.

[1834] Specific examples

[1835] When a tsunami warning is issued, the server collects information from social media and official organizations and evaluates its reliability. When a user asks, "Please tell me the latest disaster information," the server responds, "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately." If the user feels uneasy, the server provides additional information and detailed evacuation instructions.

[1836] 4. Multilingual translation and interpretation support

[1837] The server has a multilingual translation function, so when a foreign user asks the chatbot a question in their native language, the server translates it into the appropriate language in real time. The translated answer is then provided to the user. The emotion engine also analyzes the foreign user's emotional state and adjusts the response accordingly.

[1838] Specific examples

[1839] When an English-speaking user asks the chatbot, "What should I do now?", the server translates and replies, "Evacuate now. An earthquake is occurring, so please stay safe." If the user expresses particular anxiety, the server provides detailed evacuation routes and additional safety information.

[1840] 5. Matching volunteer skills and locations

[1841] The server registers the skill sets and location information of volunteers in a database, and in the event of a disaster, it compares the request for assistance with the volunteer's skill set and location information to select and notify the most suitable volunteer. In addition, it tracks the progress of volunteer activities, and an emotion engine analyzes their emotional state as necessary to adjust the assistance content.

[1842] Specific examples

[1843] If medical assistance is needed at a shelter, the server notifies nearby registered volunteers with medical skills. When a volunteer responds, "I'm on my way to help," the server provides the specific location of the shelter and tracks the progress of their activities. An emotion engine analyzes the volunteer's emotional state and provides necessary notifications and advice if fatigue or stress is detected.

[1844] As described above, by combining an emotion engine, the present invention is a system that enables flexible responses according to the emotional states of disaster victims and evacuees during disasters, thereby further improving safety and rapid response in disaster-stricken areas.

[1845] The processing flow will be explained below.

[1846] Confirming the safety of victims

[1847] Step 1:

[1848] When the server detects a disaster, it sends a push notification to users in the affected area.

[1849] Specific operation: The server references a database of affected areas and sends a message to all relevant users asking, "Are you safe?"

[1850] Step 2:

[1851] The user receives the notification and enters a response.

[1852] Specific action: The user types a message into the device, such as "I'm safe" or "I need help," and sends it.

[1853] Step 3:

[1854] The device sends input information and location information to the server.

[1855] Specific operation: The device's GPS function obtains the current location and sends it to the server along with the entered text message.

[1856] Step 4:

[1857] The server analyzes the received information and automatically estimates the safety status of the victims.

[1858] How it works: The server uses an AI model to analyze messages and location information to estimate the safety status of the person. The results are stored in a database.

[1859] Step 5:

[1860] The server uses an emotion engine to analyze the user's emotion from the received message.

[1861] Specific operation: The emotion engine uses text analysis to identify the user's emotional state, such as "relieved," "anxious," or "tense."

[1862] Step 6:

[1863] The server notifies specific contacts of the estimation results and sentiment analysis results.

[1864] Specific operation: Based on the estimated safety information and emotion results, the server creates detailed safety information such as "You are safe, but you seem to be worried," and sends the information to pre-registered contacts (family, friends, etc.).

[1865] Grasping the congestion situation at evacuation centers

[1866] Step 1:

[1867] Cameras installed at evacuation centers regularly capture footage and upload it to a server.

[1868] Specific operation: The camera captures video at regular intervals and sends the data to the server.

[1869] Step 2:

[1870] The server analyzes the received video.

[1871] Specific operation: The server inputs the video into an AI image recognition model, counts the number of people, and determines the congestion level.

[1872] Step 3:

[1873] A user inquires about congestion status via a chatbot.

[1874] Specific operation: The user types a question into the chatbot on their smartphone, such as "How crowded is the nearest evacuation shelter?", and sends it.

[1875] Step 4:

[1876] The server analyzes the user's emotional state.

[1877] Specific operation: The server's emotion engine determines emotions from the user's input and identifies states such as "anxiety" or "impatience."

[1878] Step 5:

[1879] The server provides the user with an answer based on the analysis results.

[1880] Specific operation: The server checks the analysis results of the AI ​​model and generates an answer such as, "Shelter A is full. There is space available in shelter B." Depending on the user's emotional state, the server adjusts the response and sends it back, such as, "Please move to shelter B as soon as possible."

[1881] Collection and reliability assessment of disaster-related information

[1882] Step 1:

[1883] The server collects disaster-related information from social media and official organizations.

[1884] Specific operation: The server uses scraping tools and APIs to collect disaster information from social media and official organizations and stores it in a database.

[1885] Step 2:

[1886] The server applies a trustworthiness evaluation algorithm to the collected information.

[1887] What it does: The server uses text analysis and credibility assessment algorithms to score the credibility of each piece of information.

[1888] Step 3:

[1889] A user asks a chatbot for the latest disaster information.

[1890] Specific operation: The user types "Please tell me the latest disaster information" into the chatbot and sends it.

[1891] Step 4:

[1892] The server analyzes the user's emotional state.

[1893] Specific operation: The emotion engine analyzes emotions from the user's question and identifies emotional states such as "anxiety" or "panic."

[1894] Step 5:

[1895] The server selects reliable disaster information and responds to the user.

[1896] Specific operation: The server selects highly reliable information and, taking into account the user's emotional state, generates a message such as "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately," and provides detailed additional information and evacuation routes.

[1897] Multilingual translation and interpretation support

[1898] Step 1:

[1899] The server puts the multilingual translation module into standby mode.

[1900] Specific operation: The server initializes the real-time translation API and prepares for multilingual support.

[1901] Step 2:

[1902] Foreign users ask questions to the chatbot in their native language.

[1903] What happens: The user types a message in their native language and sends it to the chatbot.

[1904] Step 3:

[1905] The server translates the received message and generates an appropriate response.

[1906] Specific operation: The server calls the translation API to translate the message into Japanese, then generates an appropriate response message and translates it back into the user's native language.

[1907] Step 4:

[1908] The server analyzes the user's emotional state.

[1909] What it does: The server's emotion engine uses text analysis to identify the user's emotion.

[1910] Step 5:

[1911] The terminal displays the translated message to the user.

[1912] Specific operation: The server generates a message according to the user's emotional state and sends it to the device. The device receives the message and displays it in the user's native language.

[1913] Matching volunteer skills and locations

[1914] Step 1:

[1915] Users register their skill set and location information.

[1916] Specific operation: Volunteers enter their skills and current location through the chatbot and register on the server.

[1917] Step 2:

[1918] The server stores the registered volunteer information in a database.

[1919] Specific operation: The server saves the entered information in a database and makes it available for verification.

[1920] Step 3:

[1921] When a request for assistance is received, the server selects the most suitable volunteer and notifies them.

[1922] Specific operation: The server compares the request for assistance with the volunteers' skill sets and location information, selects the most suitable volunteer, and sends a notification to the selected volunteer.

[1923] Step 4:

[1924] The server analyzes the emotional state of the volunteer.

[1925] Specific operation: The emotion engine analyzes emotions from volunteers' responses and progress reports to identify "fatigue" and "stress."

[1926] Step 5:

[1927] Volunteer users are notified and begin providing support.

[1928] Specific action: The volunteer replies to the notification by saying "I'm on my way to help," and the server provides information about the specific location where the volunteer will help.

[1929] Step 6:

[1930] The terminal reports the volunteer's progress to the server.

[1931] Specific operation: The volunteer's device sends GPS data to the server in real time, reports the progress of the activity, and provides necessary notifications and advice according to the volunteer's emotional state.

[1932] This enables the system to provide quick and accurate information and support to disaster victims and evacuees, and utilizes an emotion engine to provide flexible responses to maintain users' mental stability.

[1933] Example 2

[1934] 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."

[1935] When a disaster occurs, it is important for victims and evacuees to obtain the necessary information quickly and accurately and ensure their safety. However, current systems do not adequately address the following: safety confirmation, understanding of the congestion situation at evacuation centers, providing reliable disaster information, multilingual support, skill matching with volunteers, and consideration of emotional state. This makes it difficult for victims and evacuees to receive appropriate support.

[1936] 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.

[1937] In this invention, the server includes means for sending push notifications to users when a disaster occurs, means for receiving response input information and location information from users, means for analyzing the received information and automatically estimating the user's safety status and emotional state, means for notifying specific contacts of the estimated safety status and emotional state, means for receiving camera footage and determining the congestion status of evacuation centers in real time, means for collecting disaster-related information from online social networks and official institutions, evaluating its reliability, and providing the user with reliable information, means for translating questions in the user's native language and providing the translated answers, and means for registering volunteers' skill sets and location information in a database and matching them with requests for assistance.

[1938] This will enable victims and evacuees to quickly and accurately obtain the information they need, ensure their safety, and receive appropriate support.

[1939] The "means for sending a push notification to a user when a disaster occurs" is a function that immediately sends a notification from the server to the user's device when a disaster is detected.

[1940] The "means for receiving response input information and location information from the user" is a function by which the server receives information in response to the notification from the user and the location information of the terminal.

[1941] "Means for analyzing received information and automatically estimating the user's safety status and emotional state" refers to a function that uses a specific algorithm to mechanically determine the user's safety and emotional state based on the response information and location information received by the server from the user.

[1942] "Means of notifying specific contacts of estimated safety status and emotional state" is a function in which the server notifies contacts previously set by the user based on the analysis results.

[1943] "Means of receiving camera footage and determining the congestion situation at evacuation centers in real time" refers to a function in which a server receives footage sent from cameras installed at evacuation centers, analyzes it, and determines the current congestion situation.

[1944] "Means of collecting disaster-related information from online social networks and official institutions, assessing its reliability, and providing users with reliable information" refers to a function in which a server collects disaster-related information from online social networking sites and government agencies, evaluates the reliability of that information using an algorithm, and delivers reliable information to users.

[1945] "Means for translating questions in the user's native language and providing translated answers" is a function that translates a user's question entered in a foreign language into the original language and returns the translation result to the user.

[1946] "Means of registering volunteer skill sets and location information in a database and matching them with requests for assistance" is a function that stores volunteers' skills and current locations in a database and automatically matches them with requests for assistance in the event of a disaster.

[1947] This invention is a system that allows disaster victims and evacuees to quickly and accurately obtain necessary information and ensure their safety in the event of a disaster. This system has the following main functions:

[1948] 1. Safety confirmation function for disaster victims

[1949] When a disaster occurs, the server sends a push notification to users who have been registered in the affected area in advance. Users who receive this notification enter their own safety status and current location via their device and send it to the server. When analyzing the received information, the server also uses an emotion engine to analyze the user's emotional state. As a result, the user's safety status and emotional state are notified to specific contacts. This series of steps allows the specific situation of the disaster victim to be quickly communicated to family members and those involved. For example, when an earthquake occurs, the server sends a notification to the user asking, "Are you safe?" and the user replies, "I'm safe." The server then analyzes this information and notifies the family, "You're safe, but it seems you're worried."

[1950] Example prompts for generative AI models

[1951] I would like to know more about the disaster victim safety confirmation system. I would like to know details about how notifications are sent to users and how the information entered is analyzed and used to send notifications.

[1952] 2. Function to grasp the congestion situation at evacuation shelters

[1953] Cameras installed at each shelter periodically capture footage of the shelter and send the video data to a server. The server uses AI image recognition technology to analyze the footage and understand the shelter's congestion status in real time. When a user inquires about the congestion status of a shelter via a chatbot, the server responds based on the latest analysis results. For example, if the server analyzes video from shelter A and detects congestion, when the user asks, "How crowded is the nearest shelter?" the server will reply, "Shelter A is full. There is space available at shelter B."

[1954] Example prompts for generative AI models

[1955] Please tell me about the system that monitors the congestion status of evacuation shelters in real time. I would like to know how the camera footage is analyzed and specific examples of notifications sent to users.

[1956] 3. Disaster-related information collection and reliability evaluation function

[1957] The server collects disaster-related information from social media and official organizations and selects highly reliable information by applying a reliability evaluation algorithm. When a user requests the latest disaster information through the chatbot, the server provides the selected, highly reliable information. For example, when a tsunami warning is issued, the server collects and evaluates information from social media and official organizations and notifies the user, "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately." Additional evacuation information is provided to users who are feeling anxious.

[1958] Example prompts for generative AI models

[1959] Please tell me about a system that provides reliable disaster-related information. I'd like some concrete examples of how the information is collected and evaluated.

[1960] 4. Multilingual translation and interpretation support functions

[1961] The server has a multilingual translation function, so when a foreign user asks the chatbot a question in their native language, it translates the question into the appropriate language in real time and provides the translated answer. An emotion engine also analyzes the foreign user's emotional state and provides additional information as needed. For example, if an English-speaking user asks, "What should I do now?", the server translates and replies, "Evacuate now. There is an earthquake, so please stay safe."

[1962] Example prompts for generative AI models

[1963] Please tell me about multilingual translation and interpretation support systems. I'd like to see some concrete examples of how they translate foreign languages ​​in real time and provide information to users.

[1964] 5. Matching volunteer skills and locations

[1965] The server registers the skill sets and location information of volunteers in a database, and in the event of a disaster, it compares the request for assistance with the skill sets and location information of the volunteers to select and notify the most suitable volunteer. For example, if medical assistance is needed at an evacuation shelter, the server will notify nearby volunteers with medical skills and provide the specific location information of the evacuation shelter to the volunteer who responds, "I'm on my way to help."

[1966] Example prompts for generative AI models

[1967] Please tell me about the system that matches volunteer skill sets with location information. I would like to see some concrete examples of how volunteers are selected and requests for assistance are made.

[1968] As described above, the present invention can achieve rapid and accurate information acquisition and safety assurance for disaster victims and evacuees in the event of a disaster, thereby further improving safety and rapid response in disaster-stricken areas.

[1969] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1970] Safety confirmation function for victims

[1971] Step 1:

[1972] When the server detects a disaster, it sends a push notification to users in the affected area.

[1973] Input: Disaster detection information

[1974] Data processing: Identifying affected areas and generating notification messages

[1975] Output: Sending a push notification to the user device

[1976] Specific operation: The server sends a notification to the user's device, such as a smartphone, saying, "Are you safe?"

[1977] Step 2:

[1978] The user receives the push notification and responds.

[1979] Input: Push notification

[1980] Data processing: Entering safety status and current location

[1981] Output: User response input information and location information

[1982] What happens: The user enters their current location and their situation, such as "I'm OK" or "I'm injured."

[1983] Step 3:

[1984] The terminal transmits the user's response input information and location information to the server.

[1985] Input: User response input information and location information

[1986] Data processing: Converting input information into transmission protocol

[1987] Output: Data sent to the server

[1988] Specific operation: The device sends information to the server using an encrypted communication protocol.

[1989] Step 4:

[1990] The server analyzes the received information and estimates the safety and emotional state of the victims.

[1991] Input: Response input information and location information

[1992] Data processing: Applying analysis algorithms for safety status and emotional state

[1993] Output: Estimated safety status and emotional state

[1994] What it does: The server uses an analysis algorithm to estimate the outcome of "safe" and the emotion of "anxiety."

[1995] Step 5:

[1996] The server notifies specific contacts of the estimated safety status and emotional state.

[1997] Input: Safety status and estimated emotional state

[1998] Data processing: generating and sending notification messages

[1999] Output: Contact notification

[2000] What happens: The server sends a notification to family and friends saying, "You're safe, but we have some concerns."

[2001] Function to grasp the congestion situation of evacuation shelters

[2002] Step 1:

[2003] Cameras installed at evacuation centers periodically capture images and send them to a server.

[2004] Input: Camera image data

[2005] Data processing: Converting video data into transmission protocol

[2006] Output: Data sent to the server

[2007] Specific operation: The camera captures video of the evacuation shelter and sends the data to the server.

[2008] Step 2:

[2009] The server receives the video data and analyzes it using AI image recognition technology.

[2010] Input: Video data

[2011] Data processing: Analysis of video data using AI image recognition technology

[2012] Output: Analysis results of congestion situation

[2013] Specific operation: The server analyzes the video data and grasps the congestion situation at the evacuation center in real time.

[2014] Step 3:

[2015] The user inquires about the congestion status of the evacuation shelter via the chatbot.

[2016] Input: User query

[2017] Data processing: Processing of inquiries

[2018] Output: Sends the query to the server

[2019] Specific behavior: The user asks the chatbot, "How crowded is the nearest evacuation shelter?"

[2020] Step 4:

[2021] The server responds to the user based on the analysis results.

[2022] Input: User inquiries and congestion analysis results

[2023] Data processing: Generate a response message based on the analysis results and the inquiry content

[2024] Output: Response message to the user

[2025] Specific behavior: The server replies, "Shelter A is full. There is space available in shelter B."

[2026] Disaster-related information collection and reliability evaluation function

[2027] Step 1:

[2028] The server collects disaster-related information from social media and official organizations.

[2029] Input: Information from online social networks and official sources

[2030] Data processing: collecting information and storing it in a database

[2031] Output: Collected information data

[2032] Specific operation: The server collects disaster information using APIs from social media and official organizations.

[2033] Step 2:

[2034] The server evaluates the reliability of the collected information.

[2035] Input: Collected information data

[2036] Data processing: Applying reliability evaluation algorithms

[2037] Output: Reliability evaluation result

[2038] Specific operation: The server applies a reliability evaluation algorithm to the information and scores its reliability.

[2039] Step 3:

[2040] Users request the latest disaster information via a chatbot.

[2041] Input: User query

[2042] Data processing: Processing of inquiries

[2043] Output: Sends the query to the server

[2044] Specific operation: The user asks the chatbot, "Please tell me the latest disaster information."

[2045] Step 4:

[2046] The server provides reliable information to the user.

[2047] Input: User query and reliability evaluation results

[2048] Data processing: Selecting information based on the evaluation results and generating response messages

[2049] Output: Response message to the user

[2050] Specific operation: The server responds, "A tsunami warning has been issued for the Tokai region. Please evacuate to higher ground immediately."

[2051] Multilingual translation and interpretation support functions

[2052] Step 1:

[2053] Users ask the chatbot questions in their native language.

[2054] Input: Question in the user's native language

[2055] Data processing: Converting question content into text data

[2056] Output: Text data of the question

[2057] Specific behavior: The user asks the chatbot, "What should I do now?"

[2058] Step 2:

[2059] The server translates the question in real time.

[2060] Input: Text data of the question

[2061] Data processing: Applying real-time translation algorithms

[2062] Output: Translated question

[2063] Specific operation: The server translates the English question into Japanese.

[2064] Step 3:

[2065] The server provides the translated answer.

[2066] Input: translated question

[2067] Data processing: generating appropriate answers and translating

[2068] Output: The translated answer to the user

[2069] Specific behavior: The server sends a response to the user saying, "Evacuate now. An earthquake is occurring, so please stay safe."

[2070] Matching volunteer skills and locations

[2071] Step 1:

[2072] Volunteers register their skill set and location information.

[2073] Input: Volunteer skill set and location

[2074] Data processing: Registering information in a database

[2075] Output: Registration information data

[2076] What happens: Volunteers enter their skills and current location into the system.

[2077] Step 2:

[2078] The server stores the registration information in a database.

[2079] Input: Registration information data

[2080] Data processing: Saving to database

[2081] Output: Saved data

[2082] Specific operation: The server stores the volunteer's skill set and location information in a database.

[2083] Step 3:

[2084] In the event of a disaster, the server matches requests for assistance with volunteer information.

[2085] Input: Request for assistance information and volunteer information in the database

[2086] Data processing: Applying matching algorithms

[2087] Output: Optimal volunteer selection results

[2088] Specific operation: The server automatically selects the most suitable volunteer for the request for assistance.

[2089] Step 4:

[2090] The server sends a notification to the volunteer.

[2091] Input: Selection result

[2092] Data processing: Notification message generation

[2093] Output: Notification to volunteers

[2094] Specific operation: The server sends a notification to the selected volunteer saying "Assistance needed."

[2095] Step 5:

[2096] An emotion engine analyzes the emotional state of the volunteer.

[2097] Input: Volunteer responses and information during the activity

[2098] Data processing: Applying emotional state analysis algorithms

[2099] Output: Emotional state analysis results

[2100] How it works: The emotion engine analyzes the volunteer's responses and detects fatigue and stress levels.

[2101] The above processing steps have been described in detail to explain how the system of the present invention contributes to disaster victims and evacuees.

[2102] (Application example 2)

[2103] 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."

[2104] This invention relates to a system that enables disaster victims and evacuees to obtain prompt and appropriate information and ensure their safety in the event of a disaster. Current disaster response systems often have difficulty in confirming the safety of disaster victims and grasping the congestion status of evacuation centers in real time, and also have difficulty responding flexibly to users' emotional states. Furthermore, they have limited multilingual support and are unable to effectively match volunteer skill sets and location information with requests for assistance.

[2105] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2106] In this invention, the server includes means for receiving input information and location information from disaster victims, means for sending push notifications to disaster victims when a disaster occurs, means for analyzing the emotional state of disaster victims using an emotion engine and coordinating a response, means for analyzing the congestion status of evacuation shelters in real time from camera footage, means for providing the analyzed congestion status of evacuation shelters to users, means for collecting disaster-related information and evaluating its reliability, means for providing reliable disaster information to users, means for translating and answering user questions in real time using a multilingual translation function, and means for matching support requests by collating volunteer skill sets and location information. This enables disaster victims and evacuees to quickly and appropriately obtain information and ensure their safety when a disaster occurs.

[2107] "Victims" refers to people affected by a disaster.

[2108] A "push notification" refers to a notification message that a server actively sends to a user's device.

[2109] An "emotion engine" refers to an algorithm or program for analyzing a user's emotional state from input information.

[2110] "Camera footage" refers to video data from cameras installed in evacuation shelters and other locations to capture the situation at the shelter.

[2111] "Real-time" refers to data exchange and analysis occurring immediately and without delay.

[2112] "Disaster-related information" refers to information such as disaster-related news, warnings, and damage status.

[2113] "Reliability" refers to the criteria for assessing whether collected information is accurate.

[2114] "Multilingual translation function" refers to a function that enables automatic translation between multiple languages.

[2115] "Volunteers" refer to people who are registered to provide relief activities free of charge during disasters.

[2116] "Skill set" refers to the specific skills and qualifications that a volunteer possesses.

[2117] "Location information" refers to information that indicates a specific location using technology such as GPS.

[2118] "Request for assistance" refers to requests or demands for specific assistance activities from disaster victims or related organizations.

[2119] "Matching" means matching requests for assistance with volunteers' skill sets and location information to find the best match.

[2120] This invention is a system that allows disaster victims and evacuees to obtain prompt and appropriate information and ensure their safety during disasters. This system includes functions for checking the safety status of disaster victims, understanding the congestion status of evacuation centers, providing disaster-related information, providing multilingual support, and matching volunteers.

[2121] System Configuration

[2122] Hardware:

[2123] Smartphone: A device used by disaster victims and users.

[2124] Server: Processes and manages data for the entire system.

[2125] Cameras: Devices installed in evacuation centers to capture images of crowded areas.

[2126] software:

[2127] React Native: A development framework for smartphone applications.

[2128] Node.js, Express: Server-side frameworks.

[2129] MongoDB: A NoSQL database.

[2130] Google Cloud Vision: Image recognition API.

[2131] Microsoft Azure Text Analytics: Emotion recognition API.

[2132] Google Translate API: Multilingual translation API.

[2133] TensorFlow: An AI model for trustworthiness assessment.

[2134] Processing Overview

[2135] 1. Confirmation of the safety of victims:

[2136] When a disaster occurs, the server sends push notifications to users in the affected area. When users enter their safety status (e.g., "safe" or "injured") and location information on their smartphones, the information is sent to the server. The server analyzes this information and evaluates the user's emotional state using Microsoft Azure Text Analytics. The analysis results are then sent to specific contacts.

[2137] 2. Understanding the congestion situation at evacuation shelters:

[2138] Cameras installed at evacuation centers periodically send images to a server. The server analyzes the images using Google Cloud Vision and determines the congestion status of the evacuation center in real time. When a user inquires about the congestion status of the evacuation center through the chatbot, an answer is provided based on the analysis results. If necessary, the notification content is adjusted according to the user's emotional state.

[2139] 3. Providing disaster-related information:

[2140] The server collects disaster-related information from social media and official organizations, and evaluates its reliability using a TensorFlow model. Based on the evaluation results, reliable information is provided to the user. The method of providing information is adjusted according to the user's emotional state.

[2141] 4. Multilingual support:

[2142] The server uses the Google Translate API to translate questions written by users in their native language in real time, and provides appropriate answers based on the translated questions. The emotion engine also takes into account the emotional state of foreign users.

[2143] 5. Volunteer Matching:

[2144] The server registers the skills and location information of volunteers in a database and matches appropriate volunteers when a request for assistance is made. It also uses an emotion engine to analyze the emotional state of the volunteers and adjust the assistance content and notifications as needed.

[2145] Specific examples

[2146] 1. Examples of how to check on the safety of disaster victims:

[2147] When an earthquake occurs, the server quickly sends a notification to all users in the affected area asking, "Are you safe?" The user replies, "I'm safe," and the notification is sent along with their location information. Based on this information, the server analyzes the user's safety status, and the emotion engine analyzes the user's emotional state. As a result, detailed safety information such as "You're safe, but you seem worried" is sent to family and friends.

[2148] 2. Specific examples of grasping the congestion situation of evacuation shelters:

[2149] The server periodically analyzes the camera footage from shelter A and detects that the shelter is full. When a user asks the chatbot, "How crowded is the nearest shelter?", the server replies, "Shelter A is full. There is space available at shelter B." Depending on the user's emotional state, the response is adjusted to, "Please move to shelter B as soon as possible."

[2150] 3. Example prompt:

[2151] "Please let us know the latest tsunami information. Our users are very worried."

[2152] "Identify nearby locations seeking medical assistance and notify qualified volunteers. Analyze stress levels with our emotion engine and provide the necessary advice."

[2153] In this way, the present invention combines emotion recognition with disaster information, enabling highly flexible and rapid responses.

[2154] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2155] Step 1:

[2156] The server detects that a disaster has occurred and sends a push notification to users in the affected area.

[2157] Input: Disaster occurrence information

[2158] Output: Generate and send a push notification

[2159] Specific operation: The server receives disaster occurrence information from the disaster information database and sends a push notification asking "Are you safe?" to specific users based on a list of users in the affected area.

[2160] Step 2:

[2161] Users use their smartphones to input their safety status and location information and send it to the server.

[2162] Input: User's safety status and location information

[2163] Output: Send safety status data

[2164] Specific operation: The user selects an option such as "safe" or "injured" through a smartphone app and sends it along with their location information.

[2165] Step 3:

[2166] The server analyzes the received information and automatically estimates the safety status of the victims.

[2167] Input: User's safety status and location information

[2168] Output: Estimated safety status

[2169] How it works: The server analyzes safety status data and location information, evaluates the user's emotional state using Microsoft Azure Text Analytics, and automatically estimates the user's overall safety status.

[2170] Step 4:

[2171] The server notifies the specific contact person of the estimated safety status.

[2172] Input: Estimated safety status and emotional state

[2173] Output: Safety information notification

[2174] Specific operation: The server notifies the estimated safety status and emotional state to family and friend contacts.

[2175] Step 5:

[2176] The cameras at the shelter periodically send footage to a server, which then analyzes the footage.

[2177] Input: Shelter camera footage

[2178] Output: Congestion status judgment result

[2179] Specific operation: The server uses Google Cloud Vision to analyze the received video and determine the congestion status of the evacuation shelter in real time.

[2180] Step 6:

[2181] When a user asks the chatbot about the congestion situation at an evacuation shelter, the server provides an answer based on the analysis results.

[2182] Input: User inquiry about congestion status

[2183] Output: Response about congestion status

[2184] Specific operation: When a user asks the chatbot, "How crowded is the nearest evacuation shelter?", the server ...

Claims

1. means for receiving input information and location information from the disaster victims; A means of sending push notifications to disaster victims when a disaster occurs; A means for analyzing the received information and automatically estimating the safety status of disaster victims; A system that includes a means for notifying specific contacts of the estimated safety status.

2. A means for receiving images from cameras installed at each evacuation shelter; A means of analyzing the received video and determining the congestion status of evacuation centers in real time, 2. The system according to claim 1, further comprising means for responding to a user's inquiry about the congestion situation based on the analysis results.

3. means of collecting disaster-related information from online social networks and official institutions; a means of assessing the reliability of the information collected; 2. The system according to claim 1, further comprising means for providing a user with reliable information based on the evaluation results.

4. a means for performing multilingual translation; means for translating messages received from foreign users in their native language and generating appropriate responses; 2. The system according to claim 1, further comprising means for retranslating the generated answers and providing them to foreign users.

5. A means to register volunteer skill sets and location information, a means for matching requests for assistance with the skill sets and location information of volunteers; A means of selecting the most suitable volunteers and notifying them of requests for assistance; 10. The system of claim 1, further comprising means for tracking the progress of the volunteer.

Images