System

Abstract

A system is provided.SOLUTION: The system includes means for collecting up-to-date hazard information and support needs information from administrative, regional, and government databases, means for storing the collected information in an internal database, interface means for a user to input a question or support request, means for analyzing the user's input using a generative AI model and generating an appropriate answer, means for providing the generated answer to the user, means for a volunteer to upload an image or inventory list of support supplies, means for analyzing the uploaded supply information and collating it with current needs information of a specific area or municipality, and means for presenting an appropriate supply destination based on the collation result.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] This invention relates to a system that provides accurate and prompt information to disaster victims and those seeking assistance in the event of a large-scale disaster. Conventional disaster assistance systems often take time to collect and provide information, contributing to confusion at the scene. Furthermore, when volunteers wanted to send relief supplies, there was a lack of a contact point to determine where and what supplies were needed. Furthermore, there was also the problem of fake news and fraud, which undermined the credibility of relief activities. To solve these issues, a system is needed that efficiently collects and provides disaster information and assistance needs information, and provides users and volunteers with prompt and accurate information. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system that includes: means for collecting the latest disaster information and relief needs information from databases of administrative agencies, local organizations, and national agencies; means for storing the collected data in an internal database; an interface for users to input questions and requests for assistance; means for analyzing the user's input and generating appropriate answers using a generative AI model; means for providing the generated answers to the user; means for volunteers to upload images and inventory lists of relief supplies; means for analyzing the uploaded supply information and comparing it with current needs information for specific regions and municipalities; and means for presenting appropriate supply destinations based on the comparison results. This system enables quick and accurate information provision to disaster victims and those seeking assistance, preventing confusion. It also enables volunteers to efficiently identify destinations for relief supplies and carry out appropriate relief activities.

[0006] An "administrative agency" is an organization that carries out the business of the national and local governments.

[0007] A "regional agency" is an organization responsible for administrative affairs in a particular region, usually run by a local government.

[0008] A "government agency" is an organization that is part of the central government and that carries out policies to maintain the safety and welfare of the people.

[0009] A "database" is a collection of information that is systematically organized and made easy to search and use.

[0010] "Disaster Information" means real-time information on natural and man-made disasters and data on their impact.

[0011] "Support needs information" refers to information about supplies, services, and volunteer support needed by disaster victims and disaster areas.

[0012] "User" refers to an individual or entity that uses the System to enter questions or requests for assistance.

[0013] An "interface" refers to the means by which information is input and output between a user and a system.

[0014] A "generative AI model" is an artificial intelligence algorithm that generates information from given data in a format that is easy for humans to understand.

[0015] "Analysis" is the process of understanding input data and extracting or inferring relevant information.

[0016] "Volunteer" refers to a person or organization that voluntarily engages in disaster relief activities, either individually or as a group.

[0017] "Supplies" refers to items and their inventory provided for disaster relief purposes.

[0018] "Matching" is the process of comparing collected data and identifying matches or fits.

[0019] "Destination" refers to the specific location or organization to which the aid should be delivered. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] The present invention is a system for quickly and accurately providing necessary information in the event of a large-scale disaster and supporting the actions of victims and those seeking assistance. This system executes a series of processes to collect, store, analyze, and provide disaster information and assistance needs information to users from databases of administrative agencies, local agencies, and government agencies. An embodiment of the present invention is described in detail below.

[0042] System Overview

[0043] This system consists of the following main components:

[0044] 1. Data Collection Unit: This unit accesses the databases of administrative agencies, local agencies and government agencies to collect the latest disaster information and assistance needs information.

[0045] 2. Database unit: This unit stores the collected data and maintains the temporary database required for analysis.

[0046] 3. User interface unit: This unit provides an interface through which users can input their questions or requests for assistance.

[0047] 4. Generative AI model unit: This unit contains an AI model for analyzing user input and generating appropriate answers.

[0048] 5. Matching Unit: This unit analyzes information about relief supplies uploaded by volunteers and matches it with information about the needs of specific regions and municipalities.

[0049] 6. Answer providing unit: This unit provides answers to users based on the analysis results.

[0050] About program processing

[0051] Data Collection Phase

[0052] The server periodically calls the APIs of administrative agencies and government organizations to obtain the latest disaster information and assistance needs information, and the obtained data is stored in an internal database.

[0053] User Interface Phase

[0054] Users access the chatbot from their device and enter questions about disaster information and requests for assistance.

[0055] The terminal transmits the input data to the server.

[0056] The server passes the received data to the generative AI model and analyzes the content of the user's question.

[0057] The generative AI model analyzes the input question and generates the optimal answer, drawing on the necessary information from the server's database.

[0058] Answer provision phase

[0059] The server sends the answer generated by the generative AI model to the device to provide to the user.

[0060] The terminal displays the generated answers on a user interface.

[0061] Analysis and matching phase of supply support

[0062] The user uploads images or inventory lists of relief supplies from the terminal.

[0063] The terminal transmits the uploaded data to the server.

[0064] The server passes the uploaded material information to the generative AI model and begins analysis.

[0065] The generative AI model uses image recognition technology to identify the type and quantity of supplies.

[0066] The server compares the analysis results with the assistance needs database of administrative and government agencies to identify the appropriate destination.

[0067] Based on the result of the comparison, the server sends specific delivery address information to the terminal to provide to the volunteer.

[0068] The terminal displays the delivery destination information on the user interface.

[0069] Specific examples

[0070] Specific examples for disaster victims

[0071] 1. The user types into the chatbot on their device, "Where is the nearest evacuation shelter?"

[0072] 2. The device sends the query data to the server.

[0073] 3. The server retrieves the latest evacuation shelter information from the database and uses the generative AI model to generate an answer such as, "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA-shi."

[0074] 4. The server sends the generated answer to the device, where the user can view it on the interface.

[0075] Specific examples for volunteers

[0076] 1. The user types into the chatbot on their device, "I'd like to send 50 boxes of diapers. Where do I need them?"

[0077] 2. The device sends the query data to the server.

[0078] 3. The chatbot prompts the user to "upload an image of diapers or an inventory list."

[0079] 4. User uploads images and inventory list.

[0080] 5. The device sends the upload data to the server.

[0081] 6. The generative AI model analyzes the uploaded images and listings.

[0082] 7. The server compares the analysis results with the support needs database and identifies the necessary destination.

[0083] 8. The server generates a response such as "AA City Hall currently needs diapers. The delivery address is AA, AA-cho, AA, AA City, AAA-AAAA, AA City Hall Disaster Response Headquarters," and sends it to the terminal.

[0084] 9. Users can view the information on the interface and take specific action.

[0085] The above is the "Mode for carrying out the invention" of the chatbot system specialized for disaster relief in this invention. This system can provide quick and accurate information to disaster victims and those seeking support, and can significantly improve the efficiency and effectiveness of support activities.

[0086] The processing flow will be explained below.

[0087] Data Collection Phase

[0088] Step 1:

[0089] The server uses APIs to access public databases from government agencies, local authorities, and government agencies, and periodically (for example, every hour) sends requests to designated endpoints to retrieve the latest disaster and relief needs information.

[0090] Step 2:

[0091] The server parses and reads the collected data and extracts the necessary information (shelter information, assistance needs, disaster situation, etc.), which includes parsing the data in JSON and XML formats.

[0092] Step 3:

[0093] The server stores the extracted information in its internal database, overwriting any existing information with the latest information and deleting the old data.

[0094] User Interface Phase

[0095] Step 4:

[0096] Users access chatbots from their devices (smartphones or PCs), specifically by connecting to the chatbot's interface through a web page or dedicated app.

[0097] Step 5:

[0098] The user enters their question or request for assistance into the chatbot's input field.

[0099] Step 6:

[0100] The device sends the user's input data to the server, using the HTTPS communication protocol.

[0101] Step 7:

[0102] The server passes the received input data to the generative AI model and begins analysis. The generative AI model is then passed the user's question and desired assistance.

[0103] Step 8:

[0104] The generative AI model analyzes the input data and generates the best answer, specifically using natural language processing (NLP) techniques to understand the question and generate a corresponding answer.

[0105] Step 9:

[0106] The server sends the answer generated by the generative AI model to the device for return to the user.

[0107] Step 10:

[0108] The device will display the generated answer on the user interface, allowing the user to obtain the information they need through the chatbot.

[0109] Analysis and matching phase of supply support

[0110] Step 11:

[0111] Users upload images or inventory lists of relief supplies from their devices.

[0112] Step 12:

[0113] The device sends the uploaded data to the server.

[0114] Step 13:

[0115] The server passes the uploaded material information (images and text data) to the generative AI model and begins analysis.

[0116] Step 14:

[0117] The generative AI model uses image recognition and text analysis to identify the type and quantity of supplies. Specifically, it analyzes images of supplies and identifies their classification and quantity.

[0118] Step 15:

[0119] The server then compares the analysis results with the support needs databases of administrative and government agencies, comparing the information on needed supplies with current needs and identifying which regions and municipalities need those supplies.

[0120] Step 16:

[0121] The server then uses the results of the match to generate appropriate delivery information for the user, including specific addresses and contact information.

[0122] Step 17:

[0123] The server sends the generated delivery address information to the terminal.

[0124] Step 18:

[0125] The terminal displays the delivery destination information on the user interface, and users can send supplies based on this information.

[0126] This is the specific flow of the program processing for the disaster relief chatbot system. This processing step enables the prompt and accurate provision of information to disaster victims and those seeking support.

[0127] Example 1

[0128] 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."

[0129] In the event of a large-scale disaster, rapid and accurate information provision is required, but in conventional systems, information collection and analysis are often done manually, which takes time and effort, and can result in delays in providing appropriate information. Another issue is the inability to respond appropriately in real time to the information and needs of victims and supporters. Furthermore, there is a lack of mechanisms for volunteers to efficiently provide relief supplies. In these situations, a system is needed that can effectively support the actions of victims and those seeking support.

[0130] 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.

[0131] In this invention, the server includes: means for collecting disaster information and support needs information from databases of administrative agencies, local agencies, and government agencies; means for saving the collected data in an internal database; interface means for users to input questions and support requests; means for analyzing the user's input and generating appropriate answers using a generative AI model; means for providing the generated answers to the user; means for volunteers to upload the characteristics and quantities of relief supplies; means for analyzing the uploaded supply information and comparing it with local information; and means for presenting appropriate supply destinations based on the comparison results. This enables disaster victims and those seeking support to receive information quickly and accurately, significantly improving the efficiency and effectiveness of support activities.

[0132] "Administrative agencies" are organizations that provide public services, such as national and local governments.

[0133] "Local organizations" are organizations that carry out disaster response and support activities within local governments and communities.

[0134] "Government agencies" are public organizations such as central government ministries and agencies responsible for national administration.

[0135] A "database" is a collection of information that is structured to make it easy to manage and search.

[0136] "Disaster information" is detailed information about natural and man-made disasters.

[0137] "Support needs information" refers to information about the relief supplies and services needed by disaster-stricken areas and victims in the event of a disaster.

[0138] A "user interface" is the means by which a user interacts with a system.

[0139] A "generative AI model" is a computer program that uses artificial intelligence to analyze user input and generate appropriate answers.

[0140] "Volunteers" are individuals or groups who provide support activities free of charge.

[0141] "Relief supplies" are items such as food, medicine, and clothing provided to victims in the event of a disaster.

[0142] "Regional information" refers to information about the disaster situation and assistance needs in a specific region.

[0143] A "prompt" is text that contains questions or instructions to be input into a generative AI model.

[0144] The present invention provides a system for quickly and accurately providing necessary information during a large-scale disaster and supporting the actions of disaster victims and those seeking assistance. This system executes a series of processes to collect, store, and analyze disaster information and assistance needs information from databases of administrative agencies, local agencies, and government agencies, and provide the information to users. Specific embodiments for implementing the present invention are described in detail below.

[0145] System Overview

[0146] This system consists of the following main components:

[0147] 1. Data Collection Unit: This unit accesses the databases of administrative agencies, local agencies and government agencies to collect the latest disaster information and assistance needs information.

[0148] 2. Database unit: This unit stores the collected data and maintains the temporary database required for analysis. Specifically, a MySQL database is used.

[0149] 3. User interface unit: This unit provides an interface where users can enter questions or requests for assistance. It runs on a web browser.

[0150] 4. Generative AI model unit: This unit contains an AI model for analyzing user input and generating appropriate answers. Generative AI models such as GPT-3 are used.

[0151] 5. Matching Unit: This unit analyzes information about relief supplies uploaded by volunteers and matches it with information about the needs of specific regions and municipalities.

[0152] 6. Answer providing unit: This unit provides answers to users based on the analysis results.

[0153] About program processing

[0154] Data Collection Phase

[0155] The server periodically calls the APIs of government agencies and organizations to obtain the latest disaster and relief needs information. It connects to the API using Python's requests library and retrieves data in JSON format. The retrieved data is then stored in a MySQL database using Python's MySQL Connector.

[0156] User Interface Phase

[0157] A user accesses the chatbot from their device via a web browser and inputs a question or request for assistance. For example, they might input, "Where is the nearest evacuation shelter?" The device sends the input data to the server using WebSocket or an HTTP request. The server processes the received request using a web framework such as Flask and passes the prompt text to the generative AI model.

[0158] For example: "Where is the nearest shelter?"

[0159] Analysis of generative AI models

[0160] A generative AI model (e.g., GPT-3) analyzes the prompt sentence and generates an appropriate answer. In the analysis process, the necessary information is retrieved from the database using a SELECT statement, and an answer such as "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA, AA City" is generated.

[0161] Answer provision phase

[0162] The server sends the answers generated by the generative AI model to the device, which then displays the received answers on a web browser, allowing the user to view the information in real time.

[0163] Analysis and matching phase of supply support

[0164] The user uploads images of relief supplies and an inventory list. For example, they might type, "I'd like to send 50 boxes of diapers. Where do they need them?" and upload images of the supplies. The device then sends the uploaded file to the server via HTTP POST. The server saves the file in a temporary storage area and analyzes the image using Python's Pillow library or similar. The generative AI model uses TensorFlow or PyTorch to identify the supply data from the image, compares it with a MySQL database, and then generates specific delivery address information, such as, "AA City Hall is currently in need of diapers. The delivery address is AAA-AAAA, AA Town, AA City, AA City Hall Disaster Response Headquarters."

[0165] Specific examples

[0166] Specific examples for victims:

[0167] 1. User types, "Where is the nearest shelter?"

[0168] 2. The device sends the information to the server.

[0169] 3. The server retrieves the appropriate evacuation shelter information from the database and generates the information "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA-shi." through the generative AI model.

[0170] 4. The server sends the generated answer to the device, and the user views the information in the browser.

[0171] Examples for volunteers:

[0172] 1. A user types into the chatbot, "I'd like to send 50 boxes of diapers. Where do they need to go?"

[0173] 2. The device sends the information to the server.

[0174] 3. The chatbot will prompt you to "Upload an image of your diapers or an inventory list."

[0175] 4. The user uploads the image.

[0176] 5. The device sends the data to the server.

[0177] 6. The generative AI model analyzes the image to identify the type and quantity of supplies.

[0178] 7. The server identifies the appropriate delivery address based on the matching results and generates the information, "AA City Hall currently needs diapers. The delivery address is AAA-AAAA, AA-cho, AA City, AA City Disaster Response Headquarters."

[0179] 8. Users can view the information in their browser and take specific action.

[0180] The above is the specific processing and operation of the embodiment of the present invention. This system enables quick and accurate provision of information and support to disaster victims and those seeking support, significantly improving the efficiency and effectiveness of support activities.

[0181] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0182] Program processing steps

[0183] Step 1:

[0184] The server periodically calls the API of the administrative agency or government institution.

[0185] Input: API endpoint

[0186] Data processing: Use the Python requests library to connect to the API and retrieve data in JSON format.

[0187] Output: Retrieved JSON data

[0188] Specific behavior:

[0189] The server accesses the API endpoint using the requests.get() method and extracts the JSON data from the response object.

[0190] Step 2:

[0191] The server stores the acquired data in an internal database.

[0192] Input: JSON data

[0193] Data processing: Analyze the data to extract important information and store it in a MySQL database using INSERT statements.

[0194] Output: Disaster information and assistance needs information stored in a database

[0195] Specific behavior:

[0196] The server converts the JSON data into a dictionary using the json.loads() method, connects to the database using the MySQL Connector, and issues an INSERT statement using the cursor.execute() method.

[0197] Step 3:

[0198] The user accesses the chatbot from their device and enters their question or the assistance they would like.

[0199] Input: Question or request for assistance (e.g., "Where is the nearest evacuation center?")

[0200] Data processing: User input is obtained using HTML forms or JavaScript.

[0201] Output: Question data

[0202] Specific behavior:

[0203] The user accesses the chatbot's UI on a web browser, enters a question in the text box, and clicks the send button.

[0204] Step 4:

[0205] The terminal transmits the input data to the server.

[0206] Input: Question data

[0207] Data processing: Send the question data to the server as a WebSocket or HTTP POST request.

[0208] Output: The query data passed to the server

[0209] Specific behavior:

[0210] The device sends data to the server using the JavaScript fetch() method or the WebSocket.send() method.

[0211] Step 5:

[0212] The server passes the received data to the generative AI model for analysis.

[0213] Input: Question data

[0214] Data processing: The question data is passed to a generative AI model (e.g., GPT-3) as a prompt.

[0215] Output: The answer parsed by the generative AI model

[0216] Specific behavior:

[0217] The server uses Flask to process incoming requests and send them to the API of the generative AI model.

[0218] Step 6:

[0219] The generative AI model analyzes the input question and generates an appropriate answer.

[0220] Input: prompt statement

[0221] Data processing: Analyzes the prompt statement, retrieves the necessary information from the database using a SELECT statement, and generates an answer.

[0222] Output: The generated answer

[0223] Specific behavior:

[0224] The generative AI model receives the API request and generates an answer using its internal algorithm. The server receives the result and processes it again.

[0225] Step 7:

[0226] The server sends the answer generated by the generative AI model to the user's device.

[0227] Input: Generated answer

[0228] Data processing: The generated answer is sent to the device as an HTTP or WebSocket response.

[0229] Output: Answer data sent to the device

[0230] Specific behavior:

[0231] The server uses Flask's response object to generate the answer and send it back to the device.

[0232] Step 8:

[0233] The terminal displays the generated answer on a user interface.

[0234] Input: Generated response data

[0235] Data processing: The received data is formatted for display using HTML and JavaScript.

[0236] Output: The answer displayed in the user interface

[0237] Specific behavior:

[0238] The terminal uses JavaScript DOM manipulation methods to dynamically display the received response data on a web page.

[0239] Step 9:

[0240] Users upload images of relief supplies and inventory lists from their devices.

[0241] Input: Images and inventory list of relief supplies

[0242] Data processing: Taking user input from forms and uploading files.

[0243] Output: Uploaded file data

[0244] Specific behavior:

[0245] The user selects an image or list using a file input form on a web browser and clicks the upload button.

[0246] Step 10:

[0247] The device sends the uploaded data to the server.

[0248] Input: File data

[0249] Data processing: Send the file data to the server as an HTTP POST request.

[0250] Output: File data passed to the server

[0251] Specific behavior:

[0252] The device uses the JavaScript fetch() method to send the file data to the server.

[0253] Step 11:

[0254] The server passes the uploaded material information to the generative AI model and begins analysis.

[0255] Input: File data

[0256] Data processing: Save the file to a temporary storage area and read the data using the image analysis library.

[0257] Output: Image data or list data for analysis

[0258] Specific behavior:

[0259] The server uses an image analysis library such as Pillow or performs direct text analysis.

[0260] Step 12:

[0261] The generative AI model uses image recognition technology to identify the type and quantity of supplies.

[0262] Input: Image data or list data

[0263] Data processing: Image analysis algorithms are used to identify material information and count quantities.

[0264] Output: Identified material data

[0265] Specific behavior:

[0266] The generative AI model uses TensorFlow or PyTorch to analyze images and identify the type and quantity of supplies.

[0267] Step 13:

[0268] The server compares the analysis results with a database of assistance needs and identifies the appropriate destination.

[0269] Input: Identified material data

[0270] Data processing: Database matching is performed to find the optimal delivery destination.

[0271] Output: Proper shipping information

[0272] Specific behavior:

[0273] The server runs a SELECT statement against the MySQL database to match the needs data with the supplies data.

[0274] Step 14:

[0275] Based on the matching results, the server provides the terminal with the appropriate delivery address for the supplies.

[0276] Enter the appropriate shipping information

[0277] Data processing: The destination information is formatted in a user-friendly format and sent as an HTTP response.

[0278] Output: Shipping information sent to the terminal

[0279] Specific behavior:

[0280] The server uses Flask's response object to send the destination information to the terminal.

[0281] Step 15:

[0282] The terminal displays the delivery information on the user interface.

[0283] Input: Shipping information

[0284] Data processing: The received information is formatted for display using HTML and JavaScript.

[0285] Output: Shipping information displayed on the user interface

[0286] Specific behavior:

[0287] The terminal uses JavaScript DOM manipulation methods to dynamically display the delivery information on a web page.

[0288] (Application example 1)

[0289] 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."

[0290] When a large-scale disaster occurs, it is difficult for victims and those seeking aid to quickly and accurately obtain the information they need. Furthermore, insufficient management of relief supplies and matching of appropriate delivery destinations reduces the efficiency and effectiveness of relief activities. Conventional systems have limited user interfaces and make it difficult to respond in real time, making it difficult to provide disaster information immediately.

[0291] 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.

[0292] In this invention, the server includes: means for collecting the latest disaster information and assistance needs information from databases of administrative agencies, local agencies, and national agencies; means for storing the collected data in an internal database; interface means for users to input questions and assistance requests; means for analyzing user input and generating appropriate answers using a generative AI model; means for providing the generated answers to users; means for volunteers to upload images of relief supplies and inventory lists; means for analyzing the uploaded supply information and comparing it with current needs information for specific regions and municipalities; means for presenting appropriate supply destinations based on the comparison results; means for providing responses in real time based on user input information and questions; and means for providing evacuation center information and emergency contact information via a smartphone application. This allows disaster victims and assistance seekers to quickly and accurately obtain information, improving the efficiency and effectiveness of assistance activities.

[0293] "Administrative agencies" refer to public institutions such as national and local governments and similar organizations.

[0294] A "local agency" is an agency or organization that provides public services or functions in a particular geographic area.

[0295] "Government agencies" refer to various agencies of the central government responsible for the administration of the country.

[0296] A "database" is a mechanism or system for systematically storing and managing digital information.

[0297] "Disaster information" refers to information such as forecasts, occurrence status, damage status, and response measures regarding emergencies such as natural disasters and accidents.

[0298] "Support needs information" refers to information on specific needs, such as relief supplies, services, and information, required by disaster-stricken areas and disaster victims.

[0299] An "interface" refers to the operation screen, input means, and output means that users use to use a system.

[0300] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and automatically generate answers to user questions.

[0301] An "answer" is information or instructions provided in response to a user's question.

[0302] "Volunteers" are individuals or groups who voluntarily engage in activities such as disaster relief and social contribution.

[0303] "Supply information" refers to specific information such as the type and quantity of relief supplies provided.

[0304] "Verification" is the process of comparing information to see if it matches.

[0305] "Destination" refers to the place where supplies, information, etc. should be delivered or the recipient.

[0306] "Real-time" refers to information processing and system response occurring immediately and without delay.

[0307] A "smartphone application" is a software program that runs on a smartphone.

[0308] "Evacuation shelter information" refers to information about facilities and locations for evacuation in the event of a disaster.

[0309] "Emergency contact information" refers to contact information for use in the event of a disaster or emergency.

[0310] This invention relates to a system that provides necessary information quickly and accurately in the event of a large-scale disaster, and supports the actions of victims and those seeking assistance. This system is composed of the following main components:

[0311] Data Acquisition Unit

[0312] The server periodically accesses the databases of administrative agencies, local agencies, and government agencies to collect the latest disaster information and assistance needs information, which is then stored in an internal database.

[0313] Database Unit

[0314] The server's internal database stores collected disaster and assistance needs information, and is updated in real time to enable prompt responses to user questions and requests.

[0315] User Interface Unit

[0316] Users access the system using a smartphone application, which provides an interface for inputting questions about disaster information and requests for assistance.

[0317] Generative AI Model Unit

[0318] The server analyzes the user's input data using a generative AI model, such as OpenAI's GPT-3, to generate an appropriate answer. The generated answer is then provided to the user by the server.

[0319] Answer Providing Unit

[0320] The server provides the answers generated by the generative AI model to the user through a smartphone application, allowing the user to obtain the information they need in real time.

[0321] Logistics Support Analysis and Matching Unit

[0322] When users upload images of relief supplies and inventory lists, the server analyzes this data and compares it with information on relief needs. TensorFlow is used for image recognition technology. Based on the results of the comparison, the server identifies the appropriate delivery address for the supplies and presents it to the user.

[0323] Examples:

[0324] Specific examples for victims:

[0325] 1. The user types "Where is the nearest evacuation shelter?" into the smartphone application.

[0326] 2. The application sends the query data to the server.

[0327] 3. The server retrieves the latest evacuation shelter information from the database and uses the generative AI model to generate an answer such as, "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA-shi."

[0328] 4. The server sends the generated answer to the application, where the user can view it on the interface.

[0329] Examples for volunteers:

[0330] 1. A user types in a smartphone application, "I'd like to send 50 boxes of diapers. Where do I need them?"

[0331] 2. The application sends the query data to the server.

[0332] 3. The chatbot instructs the user to "upload an image of diapers or an inventory list."

[0333] 4. User uploads images and inventory list.

[0334] 5. The application sends the upload data to the server.

[0335] 6. The generative AI model analyzes the uploaded images and listings.

[0336] 7. The server compares the analysis results with the support needs database and identifies the necessary destination.

[0337] 8. The server generates a response such as "AA City Hall currently needs diapers. The delivery address is AA, AA-cho, AA, AA City, AAA-AAAA, AA City Hall Disaster Response Headquarters." and sends it to the application.

[0338] 9. Users can view the information on the interface and take specific action.

[0339] Hardware and software used:

[0340] Server: Cloud server (e.g. Google Cloud, AWS EC2)

[0341] Software: Python, Firebase Admin SDK, React Native, Django, OpenAI API, TensorFlow

[0342] Device: Smartphone

[0343] Example prompt sentence:

[0344] "Where is the nearest shelter?"

[0345] "I'd like to send 50 boxes of diapers. Where do you need them?"

[0346] Please tell me the current disaster situation.

[0347] "I would like to know the list of relief supplies in demand."

[0348] The above is an embodiment of the present invention. This system makes it possible to provide quick and accurate information to disaster victims and those seeking support, significantly improving the efficiency and effectiveness of support activities.

[0349] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0350] Step 1:

[0351] The server periodically calls the APIs of administrative agencies, local agencies, and government agencies to obtain the latest disaster information and assistance needs information. The API requests are input, and the disaster information and assistance needs information obtained as output is saved in an internal database. This ensures that the server always has the latest information.

[0352] Step 2:

[0353] Users use a smartphone application to input questions about disaster information and requests for assistance. Input includes text input and image uploads, and output is sent to the server via the device. This input data includes the user's needs and questions.

[0354] Step 3:

[0355] The device sends the received user input data to the server. The input is the user's text data or image data, and the output is sent in a format that can be analyzed by the server. This prepares the server for the next step of processing.

[0356] Step 4:

[0357] The server passes the user's input data to the generative AI model and generates an appropriate answer. The input is the user's question, and the output is the answer to the question generated by the generative AI model. The AI ​​model, for example, uses OpenAI's GPT-3, which analyzes the user's question using natural language processing.

[0358] Step 5:

[0359] The server sends the generated answer back to the smartphone application, which takes the generated answer as input and sends it to the device in a format that the user can use as output, allowing the user to receive the answer quickly.

[0360] Step 6:

[0361] The user checks the answer displayed on the device through the smartphone application. The answer from the server is input, and the information provided to the user is output. This allows the user to decide what to do based on the necessary information.

[0362] Step 7:

[0363] When a user uploads images of relief supplies or an inventory list, the device sends that information to the server. The input is the user's image data and list data, and the output is sent in a format that can be analyzed by the server. This data includes information about the relief supplies.

[0364] Step 8:

[0365] The server uses a generative AI model to analyze the uploaded images and lists of relief supplies and identify the type and quantity of supplies. Image data and list data are input, and the analysis results are obtained as output. Image recognition technology such as TensorFlow is used for the analysis.

[0366] Step 9:

[0367] The server compares the analysis results with the support needs information stored in its internal database and identifies appropriate delivery destinations that meet those needs. The inputs are the analysis results and support needs information, and the output is appropriate delivery destination information. As a result of the comparison, areas and facilities in need of relief supplies are identified.

[0368] Step 10:

[0369] The server provides the user with appropriate delivery information through a smartphone application. The delivery information is input and sent to the device in a format that the user can use as output, allowing the user to take specific supportive actions.

[0370] 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.

[0371] The present invention is a system that responds quickly and accurately to victims and those seeking assistance in the event of a large-scale disaster. This system collects disaster information and assistance needs information from databases of administrative agencies, local organizations, and government agencies, and combines a generative AI model and an emotion engine to provide users with appropriate information and assistance. An embodiment of the present invention is described in detail below.

[0372] System Overview

[0373] This system consists of the following main components:

[0374] 1. Data Collection Unit: This unit accesses the databases of administrative agencies, local agencies and government agencies to collect the latest disaster information and assistance needs information.

[0375] 2. Database unit: This unit stores the collected data and maintains the temporary database required for analysis.

[0376] 3. User interface unit: This unit provides an interface through which users can input their questions or requests for assistance.

[0377] 4. Generative AI model unit: This unit contains an AI model for analyzing user input and generating appropriate answers.

[0378] 5. Emotion Engine Unit: This unit analyzes emotions from user input and adjusts the tone and expression of the generated answers based on the results.

[0379] 6. Matching Unit: This unit analyzes information about relief supplies uploaded by volunteers and matches it with information about the needs of specific regions and municipalities.

[0380] 7. Answer providing unit: This unit provides answers to users based on the analysis results.

[0381] About program processing

[0382] Data Collection Phase

[0383] The server retrieves the latest disaster and assistance needs information through APIs from administrative, local, and government agencies. This data is parsed into an appropriate format and then stored in an internal database.

[0384] User Interface Phase

[0385] Users access the chatbot from their device (smartphone or PC) and ask questions about disaster information or enter the details of the assistance they would like to receive.

[0386] The device sends user input to the server, which passes the data to the generative AI model and emotion engine unit.

[0387] The server uses the emotion engine unit to analyze the user's emotional state. Depending on the emotional state, additional information is provided for the generative AI model unit to generate an optimal answer. For example, if the user is in great distress, a more careful and reassuring answer will be generated.

[0388] Answer provision phase

[0389] The server then sends the generated answer to the user's device, adjusting the tone and expression of the answer based on the information analyzed by the emotion engine.

[0390] The device displays the generated answer on the user interface, allowing users to not only get the information they need through the chatbot, but also receive emotionally sensitive responses.

[0391] Analysis and matching phase of supply support

[0392] The user uploads images or inventory lists of relief supplies from the terminal.

[0393] The device sends the uploaded information about the supplies to the server, which then passes it to the generative AI model and emotion engine unit to begin analysis.

[0394] The generative AI model uses image recognition and text analysis to identify the type and quantity of supplies. The server then compares this information with a database of government and administrative agencies' needs. An emotion engine then provides additional information to determine the urgency of the need.

[0395] Based on the matching results, the server generates appropriate delivery information for the user, providing specific contact details and addresses for the delivery destination.

[0396] The server sends the generated delivery destination information to the terminal, which displays this information on the user interface, allowing the user to quickly deliver the relief supplies.

[0397] Specific examples

[0398] Specific examples for disaster victims

[0399] 1. The user types "Where is the nearest evacuation shelter?" into the device.

[0400] 2. The device sends the question data to the server.

[0401] 3. The server retrieves the latest evacuation shelter information from the database and uses the generative AI model and emotion engine to respond, "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA-shi."

[0402] 4. The server generates a response and sends it to the terminal, where the user can view the response on the interface.

[0403] Specific examples for volunteers

[0404] 1. The user types into the chatbot on their device, "I'd like to send 50 boxes of diapers. Where do I need them?"

[0405] 2. The device sends the question data to the server.

[0406] 3. The chatbot prompts the user to "upload an image of diapers or an inventory list."

[0407] 4. User uploads images and inventory list.

[0408] 5. The device sends the upload data to the server.

[0409] 6. Generative AI models and emotion engines analyze images and lists.

[0410] 7. The server compares the analysis results with the assistance needs database and identifies the necessary destination.

[0411] 8. The server generates a response saying, "AA City Hall currently needs diapers. The delivery address is AAA-AAAA, AA-cho, AA City, AA City Hall Disaster Response Headquarters." and sends it to the terminal.

[0412] 9. Users can view the information on the interface and take specific action.

[0413] The above is the "Mode for carrying out the invention" of the chatbot system specialized for disaster relief in this invention. This system makes it possible to provide quick and accurate information to disaster victims and those seeking support while taking into consideration their feelings.

[0414] The processing flow will be explained below.

[0415] Data Collection Phase

[0416] Step 1:

[0417] The server uses APIs to access public databases from administrative, local, and government agencies. It periodically (for example, every hour) sends requests to designated endpoints to retrieve the latest disaster and relief needs information.

[0418] Step 2:

[0419] The server parses the data it receives and extracts the necessary information (e.g., evacuation shelter information, assistance needs, disaster status, etc.). This includes parsing data in JSON and XML format.

[0420] Step 3:

[0421] The server stores the extracted information in its internal database, overwriting any existing information with the latest information and deleting the old data.

[0422] User Interface Phase

[0423] Step 4:

[0424] Users access chatbots from their devices (smartphones or PCs), specifically by connecting to the chatbot's interface through a web page or dedicated app.

[0425] Step 5:

[0426] Users enter their question or request for assistance into the chatbot's input field, for example, "Where is the nearest evacuation center?"

[0427] Step 6:

[0428] The device sends the user's input data to the server, using the HTTPS communication protocol.

[0429] Step 7:

[0430] The server passes the received input data to the generative AI model and emotion engine to begin analysis. The user's question is analyzed.

[0431] Step 8:

[0432] The emotional engine analyzes the user's emotional state, for example, by determining the emotional state from the content of the text, the speed of typing, and the structure of the text.

[0433] Step 9:

[0434] The generative AI model refers to the analysis results of the emotion engine and generates an appropriate response. If the emotion engine detects "anxiety," it will generate a response that provides a sense of security.

[0435] Step 10:

[0436] The server then sends the generated answer to the device for delivery to the user, with the tone and expression influenced by the emotion engine.

[0437] Step 11:

[0438] The device displays the generated answers in a user interface, allowing the user to view and act on the answers.

[0439] Analysis and matching phase of supply support

[0440] Step 12:

[0441] Users upload images or inventory lists of relief supplies from their devices. For example, they can upload images or lists of diapers.

[0442] Step 13:

[0443] The device sends the uploaded data to the server using HTTPS as the communication protocol.

[0444] Step 14:

[0445] The server passes the uploaded information on supplies to the generative AI model and emotion engine, and begins analysis. The type and quantity of supplies are identified.

[0446] Step 15:

[0447] The generative AI model uses image recognition technology and text analysis to identify the type and quantity of supplies.

[0448] Step 16:

[0449] The server then compares the identified supply information with the support needs databases of administrative and government agencies, comparing the required supplies with current needs and identifying which regions and municipalities need the supplies.

[0450] Step 17:

[0451] The emotion engine determines the urgency of the support. For example, if there is a high urgent need for a particular item, that information will be reflected in the matching results.

[0452] Step 18:

[0453] Based on the results of the matching, the server generates appropriate delivery information for the user, providing specific addresses and contact information.

[0454] Step 19:

[0455] The server sends the generated destination information to the terminal, using HTTPS as the communication protocol.

[0456] Step 20:

[0457] The terminal displays delivery destination information on the user interface, and users can send supplies based on this information.

[0458] Specific examples

[0459] Specific examples for disaster victims

[0460] Step 1:

[0461] A user types into a device, "Where is the nearest shelter?"

[0462] Step 2:

[0463] The terminal transmits the question data to the server.

[0464] Step 3:

[0465] The server retrieves the latest evacuation shelter information from the database.

[0466] Step 4:

[0467] The emotion engine analyzes the user's emotional state and detects "anxiety."

[0468] Step 5:

[0469] The generative AI model references the results of the emotion engine and generates a reassuring response: "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA-shi. Please stay safe."

[0470] Step 6:

[0471] The server generates a response and sends it to the device.

[0472] Step 7:

[0473] The device displays the answer on the user interface, where the user can confirm the answer.

[0474] Specific examples for volunteers

[0475] Step 1:

[0476] The user types into the chatbot on their device, "I'd like to send 50 boxes of diapers. Where do they need to be?"

[0477] Step 2:

[0478] The terminal transmits the question data to the server.

[0479] Step 3:

[0480] The chatbot instructs the user to "upload an image of diapers or an inventory list."

[0481] Step 4:

[0482] Users upload images and inventory lists.

[0483] Step 5:

[0484] The device sends the upload data to the server.

[0485] Step 6:

[0486] A generative AI model and an emotion engine analyze images and lists. The generative AI model identifies supply information, and the emotion engine determines the urgency of assistance.

[0487] Step 7:

[0488] The server compares the analysis results with the support needs database to identify the necessary recipients and evaluates the urgency of the identified recipients.

[0489] Step 8:

[0490] The server generates a response saying, "AA City Hall is currently in need of diapers. The delivery address is AAA-AAAA, AA-cho, AA city, AA City Hall Disaster Response Headquarters," and sends it to the terminal.

[0491] Step 9:

[0492] Users can view the information on the interface and take specific action.

[0493] The above is the "Mode for carrying out the invention" of the chatbot system specialized for disaster relief in this invention. This system realizes the provision of fast and accurate information to disaster victims and those seeking support, and enables responses that take into consideration emotions.

[0494] Example 2

[0495] 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."

[0496] In modern disaster response, it is difficult to provide victims and those seeking assistance with prompt and appropriate information and match them with relief supplies. Disaster sites, in particular, require appropriate responses amidst emotional turmoil. Conventional systems often lack consideration for emotions, resulting in low user satisfaction. Furthermore, efficient matching of relief supplies by volunteers is also lacking.

[0497] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting the latest disaster information and support needs information from databases of administrative agencies, local agencies, and government agencies; means for saving the collected data in an internal database; interface means for users to input questions and support requests; means for analyzing the user's input and generating an appropriate answer using a generative AI model; means for analyzing the user's emotional state and adjusting the tone and expression of the generated answer using an emotion engine; means for providing the generated answer to the user; means for volunteers to upload images and inventory lists of relief supplies; means for analyzing the uploaded supply information and comparing it with current needs information for specific regions and municipalities; and means for presenting appropriate supply destinations based on the comparison results. This allows users to receive fast and accurate information that takes emotions into consideration, and also enables volunteers to efficiently match relief supplies.

[0498] "Administrative, local and governmental agencies" refers to central administrative agencies, local governments and local community organizations that manage and provide disaster information and assistance needs information.

[0499] "Database" refers to a collection of digital data for systematically collecting, storing, and managing disaster information and assistance needs information.

[0500] "Internal Database" means a dedicated database managed for temporary or long-term storage of collected data and for use in analysis and query.

[0501] "Interface means" refers to the interactive user interface through which a user inputs information and receives information from the system.

[0502] "Generative AI model" refers to an artificial intelligence model used to analyze user input and generate appropriate responses.

[0503] An "emotion engine" is an engine that has the ability to analyze the emotional state of a user's input and adjust the tone and expression of the answers it generates based on the results.

[0504] "Relief supplies" refers to goods and resources provided as support to disaster-stricken areas.

[0505] "Analysis" refers to the process of breaking down collected data or uploaded information and converting it into an understandable format.

[0506] "Current needs information" refers to information regarding the support needs and shortages of supplies that specific regions and local governments are currently facing.

[0507] "Delivery information" refers to the specific address and contact information for sending relief supplies.

[0508] "System" refers to a collection of hardware and software for integrally managing and executing a series of functions provided by the present invention.

[0509] The present invention is a system that responds quickly and accurately to victims and those seeking assistance in the event of a large-scale disaster. This system collects disaster information and assistance needs information from databases of administrative agencies, local organizations, and government agencies, and combines a generative AI model and an emotion engine to provide users with appropriate information and assistance. An embodiment of the present invention is described in detail below.

[0510] System Overview

[0511] This system consists of the following main components:

[0512] 1. Data Collection Unit: This unit accesses the databases of administrative agencies, local agencies and government agencies to collect the latest disaster information and assistance needs information.

[0513] 2. Database unit: This unit stores the collected data and maintains the temporary database required for analysis.

[0514] 3. User interface unit: This unit provides an interface through which users can input their questions or requests for assistance.

[0515] 4. Generative AI model unit: This unit contains an AI model for analyzing user input and generating appropriate answers.

[0516] 5. Emotion Engine Unit: This unit analyzes emotions from user input and adjusts the tone and expression of the generated answers based on the results.

[0517] 6. Matching Unit: This unit analyzes information about relief supplies uploaded by volunteers and matches it with information about the needs of specific regions and municipalities.

[0518] 7. Answer providing unit: This unit provides answers to users based on the analysis results.

[0519] About program processing

[0520] Data Collection Phase

[0521] The server obtains the latest disaster and assistance needs information through APIs from administrative, local, and government agencies. This data is parsed into an appropriate format and stored in an internal database. For example, it sends an HTTP request to the API endpoint of the Cabinet Office disaster response site and parses the returned JSON data.

[0522] User Interface Phase

[0523] Users access the chatbot from their devices (smartphones or PCs) and ask questions about disaster information or input their desired assistance. For example, a user might input, "Where is the nearest evacuation shelter?"

[0524] The device sends the user's input to the server. The sent data is passed to the generative AI model and emotion engine unit. Specifically, the device sends data to the server via an Ajax request by pressing the submit button on the form.

[0525] The server uses the emotion engine unit to analyze the user's emotional state, and based on the analyzed emotion data, provides additional information for the generative AI model unit to generate the optimal answer.

[0526] Answer provision phase

[0527] The server then sends the generated answer to the user's device. The tone and expression of the answer are adjusted based on the information analyzed by the emotion engine. For example, the answer text might be something like, "The nearest evacuation shelter is AA Elementary School. Don't worry."

[0528] The device displays the generated answer on the user interface, allowing users to not only get the information they need through the chatbot, but also receive emotionally sensitive responses.

[0529] Specific examples

[0530] Specific examples for disaster victims

[0531] 1. The user types "Where is the nearest evacuation shelter?" into the device.

[0532] 2. The device sends the question data to the server.

[0533] 3. The server retrieves the latest evacuation shelter information from the database and uses the generative AI model and emotion engine to respond, "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA-shi."

[0534] 4. The server generates a response and sends it to the terminal, where the user can view the response on the interface.

[0535] Specific examples for volunteers

[0536] 1. The user types into the chatbot on their device, "I'd like to send 50 boxes of diapers. Where do I need them?"

[0537] 2. The device sends the question data to the server.

[0538] 3. The chatbot prompts the user to "upload an image of diapers or an inventory list."

[0539] 4. User uploads images and inventory list.

[0540] 5. The device sends the upload data to the server.

[0541] 6. Generative AI models and emotion engines analyze images and lists.

[0542] 7. The server compares the analysis results with the assistance needs database and identifies the necessary destination.

[0543] 8. The server generates a response saying, "AA City Hall currently needs diapers. The delivery address is AAA-AAAA, AA-cho, AA City, AA City Hall Disaster Response Headquarters." and sends it to the terminal.

[0544] 9. Users can view the information on the interface and take specific action.

[0545] The above is the "Mode for carrying out the invention" of the chatbot system specialized for disaster relief in this invention. This system makes it possible to provide quick and accurate information to disaster victims and those seeking support while taking into consideration their feelings.

[0546] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0547] Step 1: Collect data

[0548] The server calls the API of a government agency, local agency, or government organization. For example, it sends an HTTP request to the API endpoint of the Cabinet Office disaster response site.

[0549] Parse the raw data returned by the server. Analyze the JSON format data and extract the necessary items (e.g., shelter address and emergency contact information).

[0550] The server stores the parsed data in an internal database, and then inserts the data into a table using a database management system (e.g., PostgreSQL).

[0551] Input: JSON data returned from government API

[0552] Output: Parsed data stored in an internal database

[0553] Step 2: Accept user access

[0554] Users access the chatbot from their smartphone or PC by accessing a dedicated URL or launching a dedicated app.

[0555] Input: User's access request

[0556] Output: Chatbot launch and interface display

[0557] Step 3: Accepting user questions

[0558] The user inputs a question or request for assistance through the device interface, for example, "Where is the nearest evacuation center?"

[0559] The terminal sends the user's input data to the server. By pressing the submit button on the form, the data is sent to the server via an Ajax request.

[0560] Input: User's question or request for assistance

[0561] Output: The input data sent to the server

[0562] Step 4: Sentiment Analysis

[0563] The server passes the received data to the emotion engine, which uses NLP models to analyze the text data and identify the user's emotional state.

[0564] The emotion engine analyzes the emotional tone of the user's input text and determines, for example, "high stress."

[0565] Input: User-entered text

[0566] Output: Analyzed emotion data (e.g., high stress)

[0567] Step 5: Generate an answer

[0568] The generative AI model generates the optimal answer based on the analyzed emotional data. For example, if the user is in great distress, it will generate a more thoughtful and reassuring answer. The answer text might be something like, "The nearest evacuation shelter is AA Elementary School. Please rest assured."

[0569] Input: Analyzed emotion data and user questions

[0570] Output: Generated answer text

[0571] Step 6: Provide your answers

[0572] The server sends the generated answer to the device for delivery to the user, and sends the answer text to the device in an HTTP response.

[0573] The device displays the generated answer on the user interface, and the answer text is automatically displayed in the display area for the user to see.

[0574] Input: Generated answer text

[0575] Output: The answer displayed on the interface

[0576] Step 7: Upload your supplies

[0577] The user uploads an image or inventory list of relief supplies from their device and sends it using the "Upload" button.

[0578] The device sends the uploaded data to the server as an HTTP POST request.

[0579] Input: Images or inventory list of relief supplies

[0580] Output: Upload data sent to the server

[0581] Step 8: Analyze material data

[0582] The server passes the uploaded material data to the generative AI model, which then transfers it to the analysis endpoint and begins analysis.

[0583] A generative AI model uses image recognition technology and text analysis to identify the type and quantity of supplies.

[0584] Input: Uploaded material data

[0585] Output: Analyzed material information (type and quantity)

[0586] Step 9: Matching with needs information

[0587] The server compares the analysis results with the support needs database, and matches the required supply data with the support needs by executing a search query.

[0588] Input: Parsed material information

[0589] Output: Matching results with the needs database

[0590] Step 10: Generate and provide shipping information

[0591] The server generates appropriate delivery address information for the goods, for example, "AA City Hall, 〒AAA-AAAA."

[0592] The server sends the destination information to the terminal, which then sends the destination data to the terminal as an HTTP response.

[0593] The terminal displays the information in the user interface. The delivery information is automatically displayed in the display area.

[0594] Input: Matching result

[0595] Output: Shipping information displayed on the terminal

[0596] These are the specific processing steps of this system's program. This allows users to receive prompt and accurate information that takes their emotions into consideration, and also enables efficient matching of relief supplies by volunteers.

[0597] (Application example 2)

[0598] 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."

[0599] The lack of a support system that can respond quickly and accurately to victims and those seeking support during large-scale disasters is an issue. Specifically, there is a lack of appropriate information provision and matching of relief supplies to quickly deliver the food and relief supplies needed by victims. Furthermore, there is a lack of consideration for users' emotions, and psychological support for victims is insufficient.

[0600] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting the latest disaster information and support needs information from databases of administrative agencies, local agencies, and government agencies, means for saving the collected data in an internal database, interface means for users to input questions and support requests, means for analyzing user input and generating appropriate answers using a generative AI model, means for providing the generated answers to users, means for volunteers to upload images and inventory lists of relief supplies, means for analyzing the uploaded supply information and comparing it with current needs information for specific regions or municipalities, means for presenting appropriate supply destinations based on the comparison results, means for analyzing emotions from user input and adjusting the tone and expression of the generated answers based on the results, and means for quickly and accurately delivering food and other items to disaster victims in the event of a disaster. This enables the provision of information and matching of supplies to disaster victims and those seeking support quickly and accurately, and also enables responses that take emotions into consideration.

[0601] "Administrative, local and government agency databases" refers to information systems provided by public agencies that manage and store disaster information and assistance needs information.

[0602] "Data collection instruments" means mechanisms for obtaining required information from administrative, regional and government agency databases.

[0603] "Internal database" refers to data storage for storing collected disaster information and assistance needs information.

[0604] The "interface means" is a user interface through which a user inputs questions or requests for assistance.

[0605] A "generative AI model" is an artificial intelligence algorithm that analyzes user input and generates appropriate answers.

[0606] The "answer providing means" is a system component for providing the generated answer to the user.

[0607] "Supply upload method" refers to the mechanism by which volunteers submit images and inventory lists of supplies to the system.

[0608] The "supply information analysis means" is a mechanism for analyzing information on uploaded relief supplies and comparing it with information on current needs in specific regions or municipalities.

[0609] The "supply delivery destination presentation means" is a system component that notifies volunteers of the appropriate delivery destination for supplies based on the matching results.

[0610] A "sentiment analysis means" is a mechanism for analyzing emotions from user input and adjusting the tone and expression of the generated response based on the results.

[0611] "Delivery support means" is a system component that provides prompt and accurate delivery support for food and other items to disaster victims in the event of a disaster.

[0612] This invention is a system that responds quickly and accurately to victims and those seeking assistance in the event of a large-scale disaster. This system collects disaster information and assistance needs information, and provides appropriate information and assistance by combining a generative AI model and an emotion engine.

[0613] System Overview

[0614] This system consists of the following main components:

[0615] 1. Data collection unit:

[0616] - Access databases of administrative, local and government agencies to collect the latest disaster and assistance needs information.

[0617] 2. Database Unit:

[0618] - Store the collected data and maintain a temporary database for analysis.

[0619] 3. User Interface Unit:

[0620] - Provide an interface for users to enter questions or requests for assistance.

[0621] 4. Generative AI model unit:

[0622] - Includes AI models to analyze user input and generate appropriate answers.

[0623] 5. Emotion Engine Unit:

[0624] - Analyze the sentiment of user input and adjust the tone and wording of the generated answers accordingly.

[0625] 6. Matching Unit:

[0626] - Analyze information about relief supplies uploaded by volunteers and match it with information about the needs of specific regions and municipalities.

[0627] 7. Answer Providing Unit:

[0628] - Providing answers to users based on the analysis results.

[0629] Generating a Program

[0630] A natural language description of the process

[0631] Data collection phase:

[0632] The server retrieves the latest disaster and assistance needs information through APIs from administrative, local, and government agencies. This is achieved by using the Python requests library to retrieve data from the APIs and store it in MongoDB.

[0633] User Interface Phase:

[0634] Users access the app from their devices (smartphones or PCs) and ask questions about disaster information or enter requests for assistance. This data is sent to the server via a RESTful API. The front end is built using JavaScript (React, Vue.js, etc.).

[0635] Linking generative AI models with emotion engines:

[0636] The server uses an emotion engine (such as Azure Cognitive Services' Text Analytics API) to analyze the user's emotional state. The results are fed into a generative AI model (such as OpenAI's GPT-3) to generate an appropriate response. The emotion engine analyzes the user's input and adjusts the tone and expression of the response based on the user's emotional state.

[0637] Answer provision phase:

[0638] The server then provides the generated answer to the user, adjusting the tone and expression of the answer based on the information analyzed by the emotion engine. This data is then sent to the front-end application and displayed on the user interface.

[0639] Specific examples

[0640] 1. Example for disaster victims:

[0641] A user types into a device, "Where is the nearest shelter?"

[0642] The terminal sends the query data to the server, and the server retrieves the latest evacuation shelter information from the database.

[0643] Using a generative AI model and emotion engine, the answer is generated: "The nearest evacuation shelter is AA Elementary School. The address is AA, AA Town, AA City."

[0644] The server generates a response and sends it to the terminal, where the user can view the response on the interface.

[0645] 2. Example for volunteers:

[0646] The user types into the chatbot on their device, "I'd like to send 50 boxes of diapers. Where do I need them?"

[0647] The device sends the question data to the server, and the chatbot prompts the user to upload an image or inventory list.

[0648] Users upload images and inventory lists, and the device sends the data to a server.

[0649] A generative AI model and emotion engine analyze images and lists, and the server compares them with a database of assistance needs to identify the destination.

[0650] The server generates a response saying, "AA City Hall is currently in need of diapers. The delivery address is AAA-AAAA, AA-cho, AA city, AA City Hall Disaster Response Headquarters," and sends it to the terminal.

[0651] Users can view the information on the interface and take specific action.

[0652] Prompt Sentence Examples

[0653] Example for disaster victims: "Where is the nearest evacuation center?"

[0654] Example for volunteers: "I'd like to send 50 boxes of diapers. Where do you need them?"

[0655] This will enable quick and accurate provision of information and matching of supplies to disaster victims and those seeking assistance, and will also enable responses that take into consideration emotions.

[0656] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0657] Step 1:

[0658] The server accesses APIs provided by administrative agencies, local organizations, and government agencies to obtain the latest disaster information and assistance needs information. The data obtained from the API is in JSON format, which is parsed and stored in MongoDB. This allows the latest disaster information and assistance needs information to be accumulated in an internal database.

[0659] Step 2:

[0660] Users access the app from their devices (smartphones or PCs) and input their questions or requests for assistance through the interface. This user-entered data is sent to the server using a RESTful API. The input information is passed to the server in text format.

[0661] Step 3:

[0662] The server performs sentiment analysis on the received user input data using the Text Analytics API of Azure Cognitive Services, identifying the user's emotional state (e.g., joy, anxiety, anger, etc.) and receiving the results in JSON format.

[0663] Step 4:

[0664] Based on the results of the sentiment analysis, the server generates a prompt for a generative AI model (such as OpenAI's GPT-3) and asks for an appropriate answer. The generative AI model generates text that is adapted to the input prompt, and that text is returned to the server as the answer.

[0665] Step 5:

[0666] The server further adjusts the answer received from the generative AI model. Based on the results of the emotion engine, it adjusts the tone and expression of the answer to be more dignified and emotionally relevant. Using this adjusted answer text, it prepares to provide appropriate information to the user.

[0667] Step 6:

[0668] The server returns the adjusted answer to the device via a RESTful API. The device receives this data and displays it on its user interface, where the user can view the generated answer.

[0669] Step 7:

[0670] Volunteers upload images of relief supplies and inventory lists from their devices. The devices then send the uploaded data to the server. The data format is JPEG or PNG for images, and CSV or JSON for lists.

[0671] Step 8:

[0672] The server uses a generative AI model to perform image recognition and text analysis of the uploaded relief supplies, identifying the type and quantity of supplies and matching this with relief needs information in an internal database. As a result of the matching, the required supply information is identified.

[0673] Step 9:

[0674] Based on the matching results, the server generates appropriate delivery information for the goods, including specific contact details and addresses, and sends it to the terminal and displays it on the user interface.

[0675] Step 10:

[0676] The user can check the delivery destination information provided from the terminal and quickly deliver the relief supplies to the specified location.

[0677] 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.

[0678] 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.

[0679] 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.

[0680] [Second embodiment]

[0681] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0682] 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.

[0683] 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).

[0684] 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.

[0685] 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.

[0686] 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).

[0687] 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.

[0688] 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.

[0689] 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.

[0690] 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.

[0691] 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.

[0692] 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."

[0693] The present invention is a system for quickly and accurately providing necessary information in the event of a large-scale disaster and supporting the actions of victims and those seeking assistance. This system executes a series of processes to collect, store, analyze, and provide disaster information and assistance needs information to users from databases of administrative agencies, local agencies, and government agencies. An embodiment of the present invention is described in detail below.

[0694] System Overview

[0695] This system consists of the following main components:

[0696] 1. Data Collection Unit: This unit accesses the databases of administrative agencies, local agencies and government agencies to collect the latest disaster information and assistance needs information.

[0697] 2. Database unit: This unit stores the collected data and maintains the temporary database required for analysis.

[0698] 3. User interface unit: This unit provides an interface through which users can input their questions or requests for assistance.

[0699] 4. Generative AI model unit: This unit contains an AI model for analyzing user input and generating appropriate answers.

[0700] 5. Matching Unit: This unit analyzes information about relief supplies uploaded by volunteers and matches it with information about the needs of specific regions and municipalities.

[0701] 6. Answer providing unit: This unit provides answers to users based on the analysis results.

[0702] About program processing

[0703] Data Collection Phase

[0704] The server periodically calls the APIs of administrative agencies and government organizations to obtain the latest disaster information and assistance needs information, and the obtained data is stored in an internal database.

[0705] User Interface Phase

[0706] Users access the chatbot from their device and enter questions about disaster information and requests for assistance.

[0707] The terminal transmits the input data to the server.

[0708] The server passes the received data to the generative AI model and analyzes the content of the user's question.

[0709] The generative AI model analyzes the input question and generates the optimal answer, drawing on the necessary information from the server's database.

[0710] Answer provision phase

[0711] The server sends the answer generated by the generative AI model to the device to provide to the user.

[0712] The terminal displays the generated answers on a user interface.

[0713] Analysis and matching phase of supply support

[0714] The user uploads images or inventory lists of relief supplies from the terminal.

[0715] The terminal transmits the uploaded data to the server.

[0716] The server passes the uploaded material information to the generative AI model and begins analysis.

[0717] The generative AI model uses image recognition technology to identify the type and quantity of supplies.

[0718] The server compares the analysis results with the assistance needs database of administrative and government agencies to identify the appropriate destination.

[0719] Based on the result of the comparison, the server sends specific delivery address information to the terminal to provide to the volunteer.

[0720] The terminal displays the delivery destination information on the user interface.

[0721] Specific examples

[0722] Specific examples for disaster victims

[0723] 1. The user types into the chatbot on their device, "Where is the nearest evacuation shelter?"

[0724] 2. The device sends the query data to the server.

[0725] 3. The server retrieves the latest evacuation shelter information from the database and uses the generative AI model to generate an answer such as, "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA-shi."

[0726] 4. The server sends the generated answer to the device, where the user can view it on the interface.

[0727] Specific examples for volunteers

[0728] 1. The user types into the chatbot on their device, "I'd like to send 50 boxes of diapers. Where do I need them?"

[0729] 2. The device sends the query data to the server.

[0730] 3. The chatbot prompts the user to "upload an image of diapers or an inventory list."

[0731] 4. User uploads images and inventory list.

[0732] 5. The device sends the upload data to the server.

[0733] 6. The generative AI model analyzes the uploaded images and listings.

[0734] 7. The server compares the analysis results with the support needs database and identifies the necessary destination.

[0735] 8. The server generates a response such as "AA City Hall currently needs diapers. The delivery address is AA, AA-cho, AA, AA City, AAA-AAAA, AA City Hall Disaster Response Headquarters," and sends it to the terminal.

[0736] 9. Users can view the information on the interface and take specific action.

[0737] The above is the "Mode for carrying out the invention" of the chatbot system specialized for disaster relief in this invention. This system can provide quick and accurate information to disaster victims and those seeking support, and can significantly improve the efficiency and effectiveness of support activities.

[0738] The processing flow will be explained below.

[0739] Data Collection Phase

[0740] Step 1:

[0741] The server uses APIs to access public databases from government agencies, local authorities, and government agencies, and periodically (for example, every hour) sends requests to designated endpoints to retrieve the latest disaster and relief needs information.

[0742] Step 2:

[0743] The server parses and reads the collected data and extracts the necessary information (shelter information, assistance needs, disaster situation, etc.), which includes parsing the data in JSON and XML formats.

[0744] Step 3:

[0745] The server stores the extracted information in its internal database, overwriting any existing information with the latest information and deleting the old data.

[0746] User Interface Phase

[0747] Step 4:

[0748] Users access chatbots from their devices (smartphones or PCs), specifically by connecting to the chatbot's interface through a web page or dedicated app.

[0749] Step 5:

[0750] The user enters their question or request for assistance into the chatbot's input field.

[0751] Step 6:

[0752] The device sends the user's input data to the server, using the HTTPS communication protocol.

[0753] Step 7:

[0754] The server passes the received input data to the generative AI model and begins analysis. The generative AI model is then passed the user's question and desired assistance.

[0755] Step 8:

[0756] The generative AI model analyzes the input data and generates the best answer, specifically using natural language processing (NLP) techniques to understand the question and generate a corresponding answer.

[0757] Step 9:

[0758] The server sends the answer generated by the generative AI model to the device for return to the user.

[0759] Step 10:

[0760] The device will display the generated answer on the user interface, allowing the user to obtain the information they need through the chatbot.

[0761] Analysis and matching phase of supply support

[0762] Step 11:

[0763] Users upload images or inventory lists of relief supplies from their devices.

[0764] Step 12:

[0765] The device sends the uploaded data to the server.

[0766] Step 13:

[0767] The server passes the uploaded material information (images and text data) to the generative AI model and begins analysis.

[0768] Step 14:

[0769] The generative AI model uses image recognition and text analysis to identify the type and quantity of supplies. Specifically, it analyzes images of supplies and identifies their classification and quantity.

[0770] Step 15:

[0771] The server then compares the analysis results with the support needs databases of administrative and government agencies, comparing the information on needed supplies with current needs and identifying which regions and municipalities need those supplies.

[0772] Step 16:

[0773] The server then uses the results of the match to generate appropriate delivery information for the user, including specific addresses and contact information.

[0774] Step 17:

[0775] The server sends the generated delivery address information to the terminal.

[0776] Step 18:

[0777] The terminal displays the delivery destination information on the user interface, and users can send supplies based on this information.

[0778] This is the specific flow of the program processing for the disaster relief chatbot system. This processing step enables the prompt and accurate provision of information to disaster victims and those seeking support.

[0779] Example 1

[0780] 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."

[0781] In the event of a large-scale disaster, rapid and accurate information provision is required, but in conventional systems, information collection and analysis are often done manually, which takes time and effort, and can result in delays in providing appropriate information. Another issue is the inability to respond appropriately in real time to the information and needs of victims and supporters. Furthermore, there is a lack of mechanisms for volunteers to efficiently provide relief supplies. In these situations, a system is needed that can effectively support the actions of victims and those seeking support.

[0782] 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.

[0783] In this invention, the server includes: means for collecting disaster information and support needs information from databases of administrative agencies, local agencies, and government agencies; means for saving the collected data in an internal database; interface means for users to input questions and support requests; means for analyzing the user's input and generating appropriate answers using a generative AI model; means for providing the generated answers to the user; means for volunteers to upload the characteristics and quantities of relief supplies; means for analyzing the uploaded supply information and comparing it with local information; and means for presenting appropriate supply destinations based on the comparison results. This enables disaster victims and those seeking support to receive information quickly and accurately, significantly improving the efficiency and effectiveness of support activities.

[0784] "Administrative agencies" are organizations that provide public services, such as national and local governments.

[0785] "Local organizations" are organizations that carry out disaster response and support activities within local governments and communities.

[0786] "Government agencies" are public organizations such as central government ministries and agencies responsible for national administration.

[0787] A "database" is a collection of information that is structured to make it easy to manage and search.

[0788] "Disaster information" is detailed information about natural and man-made disasters.

[0789] "Support needs information" refers to information about the relief supplies and services needed by disaster-stricken areas and victims in the event of a disaster.

[0790] A "user interface" is the means by which a user interacts with a system.

[0791] A "generative AI model" is a computer program that uses artificial intelligence to analyze user input and generate appropriate answers.

[0792] "Volunteers" are individuals or groups who provide support activities free of charge.

[0793] "Relief supplies" are items such as food, medicine, and clothing provided to victims in the event of a disaster.

[0794] "Regional information" refers to information about the disaster situation and assistance needs in a specific region.

[0795] A "prompt" is text that contains questions or instructions to be input into a generative AI model.

[0796] The present invention provides a system for quickly and accurately providing necessary information during a large-scale disaster and supporting the actions of disaster victims and those seeking assistance. This system executes a series of processes to collect, store, and analyze disaster information and assistance needs information from databases of administrative agencies, local agencies, and government agencies, and provide the information to users. Specific embodiments for implementing the present invention are described in detail below.

[0797] System Overview

[0798] This system consists of the following main components:

[0799] 1. Data Collection Unit: This unit accesses the databases of administrative agencies, local agencies and government agencies to collect the latest disaster information and assistance needs information.

[0800] 2. Database unit: This unit stores the collected data and maintains the temporary database required for analysis. Specifically, a MySQL database is used.

[0801] 3. User interface unit: This unit provides an interface where users can enter questions or requests for assistance. It runs on a web browser.

[0802] 4. Generative AI model unit: This unit contains an AI model for analyzing user input and generating appropriate answers. Generative AI models such as GPT-3 are used.

[0803] 5. Matching Unit: This unit analyzes information about relief supplies uploaded by volunteers and matches it with information about the needs of specific regions and municipalities.

[0804] 6. Answer providing unit: This unit provides answers to users based on the analysis results.

[0805] About program processing

[0806] Data Collection Phase

[0807] The server periodically calls the APIs of government agencies and organizations to obtain the latest disaster and relief needs information. It connects to the API using Python's requests library and retrieves data in JSON format. The retrieved data is then stored in a MySQL database using Python's MySQL Connector.

[0808] User Interface Phase

[0809] A user accesses the chatbot from their device via a web browser and inputs a question or request for assistance. For example, they might input, "Where is the nearest evacuation shelter?" The device sends the input data to the server using WebSocket or an HTTP request. The server processes the received request using a web framework such as Flask and passes the prompt text to the generative AI model.

[0810] For example: "Where is the nearest shelter?"

[0811] Analysis of generative AI models

[0812] A generative AI model (e.g., GPT-3) analyzes the prompt sentence and generates an appropriate answer. In the analysis process, the necessary information is retrieved from the database using a SELECT statement, and an answer such as "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA, AA City" is generated.

[0813] Answer provision phase

[0814] The server sends the answers generated by the generative AI model to the device, which then displays the received answers on a web browser, allowing the user to view the information in real time.

[0815] Analysis and matching phase of supply support

[0816] The user uploads images of relief supplies and an inventory list. For example, they might type, "I'd like to send 50 boxes of diapers. Where do they need them?" and upload images of the supplies. The device then sends the uploaded file to the server via HTTP POST. The server saves the file in a temporary storage area and analyzes the image using Python's Pillow library or similar. The generative AI model uses TensorFlow or PyTorch to identify the supply data from the image, compares it with a MySQL database, and then generates specific delivery address information, such as, "AA City Hall is currently in need of diapers. The delivery address is AAA-AAAA, AA Town, AA City, AA City Hall Disaster Response Headquarters."

[0817] Specific examples

[0818] Specific examples for victims:

[0819] 1. User types, "Where is the nearest shelter?"

[0820] 2. The device sends the information to the server.

[0821] 3. The server retrieves the appropriate evacuation shelter information from the database and generates the information "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA-shi." through the generative AI model.

[0822] 4. The server sends the generated answer to the device, and the user views the information in the browser.

[0823] Examples for volunteers:

[0824] 1. A user types into the chatbot, "I'd like to send 50 boxes of diapers. Where do they need to go?"

[0825] 2. The device sends the information to the server.

[0826] 3. The chatbot will prompt you to "Upload an image of your diapers or an inventory list."

[0827] 4. The user uploads the image.

[0828] 5. The device sends the data to the server.

[0829] 6. The generative AI model analyzes the image to identify the type and quantity of supplies.

[0830] 7. The server identifies the appropriate delivery address based on the matching results and generates the information, "AA City Hall currently needs diapers. The delivery address is AAA-AAAA, AA-cho, AA City, AA City Disaster Response Headquarters."

[0831] 8. Users can view the information in their browser and take specific action.

[0832] The above is the specific processing and operation of the embodiment of the present invention. This system enables quick and accurate provision of information and support to disaster victims and those seeking support, significantly improving the efficiency and effectiveness of support activities.

[0833] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0834] Program processing steps

[0835] Step 1:

[0836] The server periodically calls the API of the administrative agency or government institution.

[0837] Input: API endpoint

[0838] Data processing: Use the Python requests library to connect to the API and retrieve data in JSON format.

[0839] Output: Retrieved JSON data

[0840] Specific behavior:

[0841] The server accesses the API endpoint using the requests.get() method and extracts the JSON data from the response object.

[0842] Step 2:

[0843] The server stores the acquired data in an internal database.

[0844] Input: JSON data

[0845] Data processing: Analyze the data to extract important information and store it in a MySQL database using INSERT statements.

[0846] Output: Disaster information and assistance needs information stored in a database

[0847] Specific behavior:

[0848] The server converts the JSON data into a dictionary using the json.loads() method, connects to the database using the MySQL Connector, and issues an INSERT statement using the cursor.execute() method.

[0849] Step 3:

[0850] The user accesses the chatbot from their device and enters their question or the assistance they would like.

[0851] Input: Question or request for assistance (e.g., "Where is the nearest evacuation center?")

[0852] Data processing: User input is obtained using HTML forms or JavaScript.

[0853] Output: Question data

[0854] Specific behavior:

[0855] The user accesses the chatbot's UI on a web browser, enters a question in the text box, and clicks the send button.

[0856] Step 4:

[0857] The terminal transmits the input data to the server.

[0858] Input: Question data

[0859] Data processing: Send the question data to the server as a WebSocket or HTTP POST request.

[0860] Output: The query data passed to the server

[0861] Specific behavior:

[0862] The device sends data to the server using the JavaScript fetch() method or the WebSocket.send() method.

[0863] Step 5:

[0864] The server passes the received data to the generative AI model for analysis.

[0865] Input: Question data

[0866] Data processing: The question data is passed to a generative AI model (e.g., GPT-3) as a prompt.

[0867] Output: The answer parsed by the generative AI model

[0868] Specific behavior:

[0869] The server uses Flask to process incoming requests and send them to the API of the generative AI model.

[0870] Step 6:

[0871] The generative AI model analyzes the input question and generates an appropriate answer.

[0872] Input: prompt statement

[0873] Data processing: Analyzes the prompt statement, retrieves the necessary information from the database using a SELECT statement, and generates an answer.

[0874] Output: The generated answer

[0875] Specific behavior:

[0876] The generative AI model receives the API request and generates an answer using its internal algorithm. The server receives the result and processes it again.

[0877] Step 7:

[0878] The server sends the answer generated by the generative AI model to the user's device.

[0879] Input: Generated answer

[0880] Data processing: The generated answer is sent to the device as an HTTP or WebSocket response.

[0881] Output: Answer data sent to the device

[0882] Specific behavior:

[0883] The server uses Flask's response object to generate the answer and send it back to the device.

[0884] Step 8:

[0885] The terminal displays the generated answer on a user interface.

[0886] Input: Generated response data

[0887] Data processing: The received data is formatted for display using HTML and JavaScript.

[0888] Output: The answer displayed in the user interface

[0889] Specific behavior:

[0890] The terminal uses JavaScript DOM manipulation methods to dynamically display the received response data on a web page.

[0891] Step 9:

[0892] Users upload images of relief supplies and inventory lists from their devices.

[0893] Input: Images and inventory list of relief supplies

[0894] Data processing: Taking user input from forms and uploading files.

[0895] Output: Uploaded file data

[0896] Specific behavior:

[0897] The user selects an image or list using a file input form on a web browser and clicks the upload button.

[0898] Step 10:

[0899] The device sends the uploaded data to the server.

[0900] Input: File data

[0901] Data processing: Send the file data to the server as an HTTP POST request.

[0902] Output: File data passed to the server

[0903] Specific behavior:

[0904] The device uses the JavaScript fetch() method to send the file data to the server.

[0905] Step 11:

[0906] The server passes the uploaded material information to the generative AI model and begins analysis.

[0907] Input: File data

[0908] Data processing: Save the file to a temporary storage area and read the data using the image analysis library.

[0909] Output: Image data or list data for analysis

[0910] Specific behavior:

[0911] The server uses an image analysis library such as Pillow or performs direct text analysis.

[0912] Step 12:

[0913] The generative AI model uses image recognition technology to identify the type and quantity of supplies.

[0914] Input: Image data or list data

[0915] Data processing: Image analysis algorithms are used to identify material information and count quantities.

[0916] Output: Identified material data

[0917] Specific behavior:

[0918] The generative AI model uses TensorFlow or PyTorch to analyze images and identify the type and quantity of supplies.

[0919] Step 13:

[0920] The server compares the analysis results with a database of assistance needs and identifies the appropriate destination.

[0921] Input: Identified material data

[0922] Data processing: Database matching is performed to find the optimal delivery destination.

[0923] Output: Proper shipping information

[0924] Specific behavior:

[0925] The server runs a SELECT statement against the MySQL database to match the needs data with the supplies data.

[0926] Step 14:

[0927] Based on the matching results, the server provides the terminal with the appropriate delivery address for the supplies.

[0928] Enter the appropriate shipping information

[0929] Data processing: The destination information is formatted in a user-friendly format and sent as an HTTP response.

[0930] Output: Shipping information sent to the terminal

[0931] Specific behavior:

[0932] The server uses Flask's response object to send the destination information to the terminal.

[0933] Step 15:

[0934] The terminal displays the delivery information on the user interface.

[0935] Input: Shipping information

[0936] Data processing: The received information is formatted for display using HTML and JavaScript.

[0937] Output: Shipping information displayed on the user interface

[0938] Specific behavior:

[0939] The terminal uses JavaScript DOM manipulation methods to dynamically display the delivery information on a web page.

[0940] (Application example 1)

[0941] 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."

[0942] When a large-scale disaster occurs, it is difficult for victims and those seeking aid to quickly and accurately obtain the information they need. Furthermore, insufficient management of relief supplies and matching of appropriate delivery destinations reduces the efficiency and effectiveness of relief activities. Conventional systems have limited user interfaces and make it difficult to respond in real time, making it difficult to provide disaster information immediately.

[0943] 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.

[0944] In this invention, the server includes: means for collecting the latest disaster information and assistance needs information from databases of administrative agencies, local agencies, and national agencies; means for storing the collected data in an internal database; interface means for users to input questions and assistance requests; means for analyzing user input and generating appropriate answers using a generative AI model; means for providing the generated answers to users; means for volunteers to upload images of relief supplies and inventory lists; means for analyzing the uploaded supply information and comparing it with current needs information for specific regions and municipalities; means for presenting appropriate supply destinations based on the comparison results; means for providing responses in real time based on user input information and questions; and means for providing evacuation center information and emergency contact information via a smartphone application. This allows disaster victims and assistance seekers to quickly and accurately obtain information, improving the efficiency and effectiveness of assistance activities.

[0945] "Administrative agencies" refer to public institutions such as national and local governments and similar organizations.

[0946] A "local agency" is an agency or organization that provides public services or functions in a particular geographic area.

[0947] "Government agencies" refer to various agencies of the central government responsible for the administration of the country.

[0948] A "database" is a mechanism or system for systematically storing and managing digital information.

[0949] "Disaster information" refers to information such as forecasts, occurrence status, damage status, and response measures regarding emergencies such as natural disasters and accidents.

[0950] "Support needs information" refers to information on specific needs, such as relief supplies, services, and information, required by disaster-stricken areas and disaster victims.

[0951] An "interface" refers to the operation screen, input means, and output means that users use to use a system.

[0952] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and automatically generate answers to user questions.

[0953] An "answer" is information or instructions provided in response to a user's question.

[0954] "Volunteers" are individuals or groups who voluntarily engage in activities such as disaster relief and social contribution.

[0955] "Supply information" refers to specific information such as the type and quantity of relief supplies provided.

[0956] "Verification" is the process of comparing information to see if it matches.

[0957] "Destination" refers to the place where supplies, information, etc. should be delivered or the recipient.

[0958] "Real-time" refers to information processing and system response occurring immediately and without delay.

[0959] A "smartphone application" is a software program that runs on a smartphone.

[0960] "Evacuation shelter information" refers to information about facilities and locations for evacuation in the event of a disaster.

[0961] "Emergency contact information" refers to contact information for use in the event of a disaster or emergency.

[0962] This invention relates to a system that provides necessary information quickly and accurately in the event of a large-scale disaster, and supports the actions of victims and those seeking assistance. This system is composed of the following main components:

[0963] Data Acquisition Unit

[0964] The server periodically accesses the databases of administrative agencies, local agencies, and government agencies to collect the latest disaster information and assistance needs information, which is then stored in an internal database.

[0965] Database Unit

[0966] The server's internal database stores collected disaster and assistance needs information, and is updated in real time to enable prompt responses to user questions and requests.

[0967] User Interface Unit

[0968] Users access the system using a smartphone application, which provides an interface for inputting questions about disaster information and requests for assistance.

[0969] Generative AI Model Unit

[0970] The server analyzes the user's input data using a generative AI model, such as OpenAI's GPT-3, to generate an appropriate answer. The generated answer is then provided to the user by the server.

[0971] Answer Providing Unit

[0972] The server provides the answers generated by the generative AI model to the user through a smartphone application, allowing the user to obtain the information they need in real time.

[0973] Logistics Support Analysis and Matching Unit

[0974] When users upload images of relief supplies and inventory lists, the server analyzes this data and compares it with information on relief needs. TensorFlow is used for image recognition technology. Based on the results of the comparison, the server identifies the appropriate delivery address for the supplies and presents it to the user.

[0975] Examples:

[0976] Specific examples for victims:

[0977] 1. The user types "Where is the nearest evacuation shelter?" into the smartphone application.

[0978] 2. The application sends the query data to the server.

[0979] 3. The server retrieves the latest evacuation shelter information from the database and uses the generative AI model to generate an answer such as, "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA-shi."

[0980] 4. The server sends the generated answer to the application, where the user can view it on the interface.

[0981] Examples for volunteers:

[0982] 1. A user types in a smartphone application, "I'd like to send 50 boxes of diapers. Where do I need them?"

[0983] 2. The application sends the query data to the server.

[0984] 3. The chatbot instructs the user to "upload an image of diapers or an inventory list."

[0985] 4. User uploads images and inventory list.

[0986] 5. The application sends the upload data to the server.

[0987] 6. The generative AI model analyzes the uploaded images and listings.

[0988] 7. The server compares the analysis results with the support needs database and identifies the necessary destination.

[0989] 8. The server generates a response such as "AA City Hall currently needs diapers. The delivery address is AA, AA-cho, AA, AA City, AAA-AAAA, AA City Hall Disaster Response Headquarters." and sends it to the application.

[0990] 9. Users can view the information on the interface and take specific action.

[0991] Hardware and software used:

[0992] Server: Cloud server (e.g. Google Cloud, AWS EC2)

[0993] Software: Python, Firebase Admin SDK, React Native, Django, OpenAI API, TensorFlow

[0994] Device: Smartphone

[0995] Example prompt sentence:

[0996] "Where is the nearest shelter?"

[0997] "I'd like to send 50 boxes of diapers. Where do you need them?"

[0998] Please tell me the current disaster situation.

[0999] "I would like to know the list of relief supplies in demand."

[1000] The above is an embodiment of the present invention. This system makes it possible to provide quick and accurate information to disaster victims and those seeking support, significantly improving the efficiency and effectiveness of support activities.

[1001] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1002] Step 1:

[1003] The server periodically calls the APIs of administrative agencies, local agencies, and government agencies to obtain the latest disaster information and assistance needs information. The API requests are input, and the disaster information and assistance needs information obtained as output is saved in an internal database. This ensures that the server always has the latest information.

[1004] Step 2:

[1005] Users use a smartphone application to input questions about disaster information and requests for assistance. Input includes text input and image uploads, and output is sent to the server via the device. This input data includes the user's needs and questions.

[1006] Step 3:

[1007] The device sends the received user input data to the server. The input is the user's text data or image data, and the output is sent in a format that can be analyzed by the server. This prepares the server for the next step of processing.

[1008] Step 4:

[1009] The server passes the user's input data to the generative AI model and generates an appropriate answer. The input is the user's question, and the output is the answer to the question generated by the generative AI model. The AI ​​model, for example, uses OpenAI's GPT-3, which analyzes the user's question using natural language processing.

[1010] Step 5:

[1011] The server sends the generated answer back to the smartphone application, which takes the generated answer as input and sends it to the device in a format that the user can use as output, allowing the user to receive the answer quickly.

[1012] Step 6:

[1013] The user checks the answer displayed on the device through the smartphone application. The answer from the server is input, and the information provided to the user is output. This allows the user to decide what to do based on the necessary information.

[1014] Step 7:

[1015] When a user uploads images of relief supplies or an inventory list, the device sends that information to the server. The input is the user's image data and list data, and the output is sent in a format that can be analyzed by the server. This data includes information about the relief supplies.

[1016] Step 8:

[1017] The server uses a generative AI model to analyze the uploaded images and lists of relief supplies and identify the type and quantity of supplies. Image data and list data are input, and the analysis results are obtained as output. Image recognition technology such as TensorFlow is used for the analysis.

[1018] Step 9:

[1019] The server compares the analysis results with the support needs information stored in its internal database and identifies appropriate delivery destinations that meet those needs. The inputs are the analysis results and support needs information, and the output is appropriate delivery destination information. As a result of the comparison, areas and facilities in need of relief supplies are identified.

[1020] Step 10:

[1021] The server provides the user with appropriate delivery information through a smartphone application. The delivery information is input and sent to the device in a format that the user can use as output, allowing the user to take specific supportive actions.

[1022] 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.

[1023] The present invention is a system that responds quickly and accurately to victims and those seeking assistance in the event of a large-scale disaster. This system collects disaster information and assistance needs information from databases of administrative agencies, local organizations, and government agencies, and combines a generative AI model and an emotion engine to provide users with appropriate information and assistance. An embodiment of the present invention is described in detail below.

[1024] System Overview

[1025] This system consists of the following main components:

[1026] 1. Data Collection Unit: This unit accesses the databases of administrative agencies, local agencies and government agencies to collect the latest disaster information and assistance needs information.

[1027] 2. Database unit: This unit stores the collected data and maintains the temporary database required for analysis.

[1028] 3. User interface unit: This unit provides an interface through which users can input their questions or requests for assistance.

[1029] 4. Generative AI model unit: This unit contains an AI model for analyzing user input and generating appropriate answers.

[1030] 5. Emotion Engine Unit: This unit analyzes emotions from user input and adjusts the tone and expression of the generated answers based on the results.

[1031] 6. Matching Unit: This unit analyzes information about relief supplies uploaded by volunteers and matches it with information about the needs of specific regions and municipalities.

[1032] 7. Answer providing unit: This unit provides answers to users based on the analysis results.

[1033] About program processing

[1034] Data Collection Phase

[1035] The server retrieves the latest disaster and assistance needs information through APIs from administrative, local, and government agencies. This data is parsed into an appropriate format and then stored in an internal database.

[1036] User Interface Phase

[1037] Users access the chatbot from their device (smartphone or PC) and ask questions about disaster information or enter the details of the assistance they would like to receive.

[1038] The device sends user input to the server, which passes the data to the generative AI model and emotion engine unit.

[1039] The server uses the emotion engine unit to analyze the user's emotional state. Depending on the emotional state, additional information is provided for the generative AI model unit to generate an optimal answer. For example, if the user is in great distress, a more careful and reassuring answer will be generated.

[1040] Answer provision phase

[1041] The server then sends the generated answer to the user's device, adjusting the tone and expression of the answer based on the information analyzed by the emotion engine.

[1042] The device displays the generated answer on the user interface, allowing users to not only get the information they need through the chatbot, but also receive emotionally sensitive responses.

[1043] Analysis and matching phase of supply support

[1044] The user uploads images or inventory lists of relief supplies from the terminal.

[1045] The device sends the uploaded information about the supplies to the server, which then passes it to the generative AI model and emotion engine unit to begin analysis.

[1046] The generative AI model uses image recognition and text analysis to identify the type and quantity of supplies. The server then compares this information with a database of government and administrative agencies' needs. An emotion engine then provides additional information to determine the urgency of the need.

[1047] Based on the matching results, the server generates appropriate delivery information for the user, providing specific contact details and addresses for the delivery destination.

[1048] The server sends the generated delivery destination information to the terminal, which displays this information on the user interface, allowing the user to quickly deliver the relief supplies.

[1049] Specific examples

[1050] Specific examples for disaster victims

[1051] 1. The user types "Where is the nearest evacuation shelter?" into the device.

[1052] 2. The device sends the question data to the server.

[1053] 3. The server retrieves the latest evacuation shelter information from the database and uses the generative AI model and emotion engine to respond, "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA-shi."

[1054] 4. The server generates a response and sends it to the terminal, where the user can view the response on the interface.

[1055] Specific examples for volunteers

[1056] 1. The user types into the chatbot on their device, "I'd like to send 50 boxes of diapers. Where do I need them?"

[1057] 2. The device sends the question data to the server.

[1058] 3. The chatbot prompts the user to "upload an image of diapers or an inventory list."

[1059] 4. User uploads images and inventory list.

[1060] 5. The device sends the upload data to the server.

[1061] 6. Generative AI models and emotion engines analyze images and lists.

[1062] 7. The server compares the analysis results with the assistance needs database and identifies the necessary destination.

[1063] 8. The server generates a response saying, "AA City Hall currently needs diapers. The delivery address is AAA-AAAA, AA-cho, AA City, AA City Hall Disaster Response Headquarters." and sends it to the terminal.

[1064] 9. Users can view the information on the interface and take specific action.

[1065] The above is the "Mode for carrying out the invention" of the chatbot system specialized for disaster relief in this invention. This system makes it possible to provide quick and accurate information to disaster victims and those seeking support while taking into consideration their feelings.

[1066] The processing flow will be explained below.

[1067] Data Collection Phase

[1068] Step 1:

[1069] The server uses APIs to access public databases from administrative, local, and government agencies. It periodically (for example, every hour) sends requests to designated endpoints to retrieve the latest disaster and relief needs information.

[1070] Step 2:

[1071] The server parses the data it receives and extracts the necessary information (e.g., evacuation shelter information, assistance needs, disaster status, etc.). This includes parsing data in JSON and XML format.

[1072] Step 3:

[1073] The server stores the extracted information in its internal database, overwriting any existing information with the latest information and deleting the old data.

[1074] User Interface Phase

[1075] Step 4:

[1076] Users access chatbots from their devices (smartphones or PCs), specifically by connecting to the chatbot's interface through a web page or dedicated app.

[1077] Step 5:

[1078] Users enter their question or request for assistance into the chatbot's input field, for example, "Where is the nearest evacuation center?"

[1079] Step 6:

[1080] The device sends the user's input data to the server, using the HTTPS communication protocol.

[1081] Step 7:

[1082] The server passes the received input data to the generative AI model and emotion engine to begin analysis. The user's question is analyzed.

[1083] Step 8:

[1084] The emotional engine analyzes the user's emotional state, for example, by determining the emotional state from the content of the text, the speed of typing, and the structure of the text.

[1085] Step 9:

[1086] The generative AI model refers to the analysis results of the emotion engine and generates an appropriate response. If the emotion engine detects "anxiety," it will generate a response that provides a sense of security.

[1087] Step 10:

[1088] The server then sends the generated answer to the device for delivery to the user, with the tone and expression influenced by the emotion engine.

[1089] Step 11:

[1090] The device displays the generated answers in a user interface, allowing the user to view and act on the answers.

[1091] Analysis and matching phase of supply support

[1092] Step 12:

[1093] Users upload images or inventory lists of relief supplies from their devices. For example, they can upload images or lists of diapers.

[1094] Step 13:

[1095] The device sends the uploaded data to the server using HTTPS as the communication protocol.

[1096] Step 14:

[1097] The server passes the uploaded information on supplies to the generative AI model and emotion engine, and begins analysis. The type and quantity of supplies are identified.

[1098] Step 15:

[1099] The generative AI model uses image recognition technology and text analysis to identify the type and quantity of supplies.

[1100] Step 16:

[1101] The server then compares the identified supply information with the support needs databases of administrative and government agencies, comparing the required supplies with current needs and identifying which regions and municipalities need the supplies.

[1102] Step 17:

[1103] The emotion engine determines the urgency of the support. For example, if there is a high urgent need for a particular item, that information will be reflected in the matching results.

[1104] Step 18:

[1105] Based on the results of the matching, the server generates appropriate delivery information for the user, providing specific addresses and contact information.

[1106] Step 19:

[1107] The server sends the generated destination information to the terminal, using HTTPS as the communication protocol.

[1108] Step 20:

[1109] The terminal displays delivery destination information on the user interface, and users can send supplies based on this information.

[1110] Specific examples

[1111] Specific examples for disaster victims

[1112] Step 1:

[1113] A user types into a device, "Where is the nearest shelter?"

[1114] Step 2:

[1115] The terminal transmits the question data to the server.

[1116] Step 3:

[1117] The server retrieves the latest evacuation shelter information from the database.

[1118] Step 4:

[1119] The emotion engine analyzes the user's emotional state and detects "anxiety."

[1120] Step 5:

[1121] The generative AI model references the results of the emotion engine and generates a reassuring response: "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA-shi. Please stay safe."

[1122] Step 6:

[1123] The server generates a response and sends it to the device.

[1124] Step 7:

[1125] The device displays the answer on the user interface, where the user can confirm the answer.

[1126] Specific examples for volunteers

[1127] Step 1:

[1128] The user types into the chatbot on their device, "I'd like to send 50 boxes of diapers. Where do they need to be?"

[1129] Step 2:

[1130] The terminal transmits the question data to the server.

[1131] Step 3:

[1132] The chatbot instructs the user to "upload an image of diapers or an inventory list."

[1133] Step 4:

[1134] Users upload images and inventory lists.

[1135] Step 5:

[1136] The device sends the upload data to the server.

[1137] Step 6:

[1138] A generative AI model and an emotion engine analyze images and lists. The generative AI model identifies supply information, and the emotion engine determines the urgency of assistance.

[1139] Step 7:

[1140] The server compares the analysis results with the support needs database to identify the necessary recipients and evaluates the urgency of the identified recipients.

[1141] Step 8:

[1142] The server generates a response saying, "AA City Hall is currently in need of diapers. The delivery address is AAA-AAAA, AA-cho, AA city, AA City Hall Disaster Response Headquarters," and sends it to the terminal.

[1143] Step 9:

[1144] Users can view the information on the interface and take specific action.

[1145] The above is the "Mode for carrying out the invention" of the chatbot system specialized for disaster relief in this invention. This system realizes the provision of fast and accurate information to disaster victims and those seeking support, and enables responses that take into consideration emotions.

[1146] Example 2

[1147] 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."

[1148] In modern disaster response, it is difficult to provide victims and those seeking assistance with prompt and appropriate information and match them with relief supplies. Disaster sites, in particular, require appropriate responses amidst emotional turmoil. Conventional systems often lack consideration for emotions, resulting in low user satisfaction. Furthermore, efficient matching of relief supplies by volunteers is also lacking.

[1149] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting the latest disaster information and support needs information from databases of administrative agencies, local agencies, and government agencies; means for saving the collected data in an internal database; interface means for users to input questions and support requests; means for analyzing the user's input and generating an appropriate answer using a generative AI model; means for analyzing the user's emotional state and adjusting the tone and expression of the generated answer using an emotion engine; means for providing the generated answer to the user; means for volunteers to upload images and inventory lists of relief supplies; means for analyzing the uploaded supply information and comparing it with current needs information for specific regions and municipalities; and means for presenting appropriate supply destinations based on the comparison results. This allows users to receive fast and accurate information that takes emotions into consideration, and also enables volunteers to efficiently match relief supplies.

[1150] "Administrative, local and governmental agencies" refers to central administrative agencies, local governments and local community organizations that manage and provide disaster information and assistance needs information.

[1151] "Database" refers to a collection of digital data for systematically collecting, storing, and managing disaster information and assistance needs information.

[1152] "Internal Database" means a dedicated database managed for temporary or long-term storage of collected data and for use in analysis and query.

[1153] "Interface means" refers to the interactive user interface through which a user inputs information and receives information from the system.

[1154] "Generative AI model" refers to an artificial intelligence model used to analyze user input and generate appropriate responses.

[1155] An "emotion engine" is an engine that has the ability to analyze the emotional state of a user's input and adjust the tone and expression of the answers it generates based on the results.

[1156] "Relief supplies" refers to goods and resources provided as support to disaster-stricken areas.

[1157] "Analysis" refers to the process of breaking down collected data or uploaded information and converting it into an understandable format.

[1158] "Current needs information" refers to information regarding the support needs and shortages of supplies that specific regions and local governments are currently facing.

[1159] "Delivery information" refers to the specific address and contact information for sending relief supplies.

[1160] "System" refers to a collection of hardware and software for integrally managing and executing a series of functions provided by the present invention.

[1161] The present invention is a system that responds quickly and accurately to victims and those seeking assistance in the event of a large-scale disaster. This system collects disaster information and assistance needs information from databases of administrative agencies, local organizations, and government agencies, and combines a generative AI model and an emotion engine to provide users with appropriate information and assistance. An embodiment of the present invention is described in detail below.

[1162] System Overview

[1163] This system consists of the following main components:

[1164] 1. Data Collection Unit: This unit accesses the databases of administrative agencies, local agencies and government agencies to collect the latest disaster information and assistance needs information.

[1165] 2. Database unit: This unit stores the collected data and maintains the temporary database required for analysis.

[1166] 3. User interface unit: This unit provides an interface through which users can input their questions or requests for assistance.

[1167] 4. Generative AI model unit: This unit contains an AI model for analyzing user input and generating appropriate answers.

[1168] 5. Emotion Engine Unit: This unit analyzes emotions from user input and adjusts the tone and expression of the generated answers based on the results.

[1169] 6. Matching Unit: This unit analyzes information about relief supplies uploaded by volunteers and matches it with information about the needs of specific regions and municipalities.

[1170] 7. Answer providing unit: This unit provides answers to users based on the analysis results.

[1171] About program processing

[1172] Data Collection Phase

[1173] The server obtains the latest disaster and assistance needs information through APIs from administrative, local, and government agencies. This data is parsed into an appropriate format and stored in an internal database. For example, it sends an HTTP request to the API endpoint of the Cabinet Office disaster response site and parses the returned JSON data.

[1174] User Interface Phase

[1175] Users access the chatbot from their devices (smartphones or PCs) and ask questions about disaster information or input their desired assistance. For example, a user might input, "Where is the nearest evacuation shelter?"

[1176] The device sends the user's input to the server. The sent data is passed to the generative AI model and emotion engine unit. Specifically, the device sends data to the server via an Ajax request by pressing the submit button on the form.

[1177] The server uses the emotion engine unit to analyze the user's emotional state, and based on the analyzed emotion data, provides additional information for the generative AI model unit to generate the optimal answer.

[1178] Answer provision phase

[1179] The server then sends the generated answer to the user's device. The tone and expression of the answer are adjusted based on the information analyzed by the emotion engine. For example, the answer text might be something like, "The nearest evacuation shelter is AA Elementary School. Don't worry."

[1180] The device displays the generated answer on the user interface, allowing users to not only get the information they need through the chatbot, but also receive emotionally sensitive responses.

[1181] Specific examples

[1182] Specific examples for disaster victims

[1183] 1. The user types "Where is the nearest evacuation shelter?" into the device.

[1184] 2. The device sends the question data to the server.

[1185] 3. The server retrieves the latest evacuation shelter information from the database and uses the generative AI model and emotion engine to respond, "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA-shi."

[1186] 4. The server generates a response and sends it to the terminal, where the user can view the response on the interface.

[1187] Specific examples for volunteers

[1188] 1. The user types into the chatbot on their device, "I'd like to send 50 boxes of diapers. Where do I need them?"

[1189] 2. The device sends the question data to the server.

[1190] 3. The chatbot prompts the user to "upload an image of diapers or an inventory list."

[1191] 4. User uploads images and inventory list.

[1192] 5. The device sends the upload data to the server.

[1193] 6. Generative AI models and emotion engines analyze images and lists.

[1194] 7. The server compares the analysis results with the assistance needs database and identifies the necessary destination.

[1195] 8. The server generates a response saying, "AA City Hall currently needs diapers. The delivery address is AAA-AAAA, AA-cho, AA City, AA City Hall Disaster Response Headquarters." and sends it to the terminal.

[1196] 9. Users can view the information on the interface and take specific action.

[1197] The above is the "Mode for carrying out the invention" of the chatbot system specialized for disaster relief in this invention. This system makes it possible to provide quick and accurate information to disaster victims and those seeking support while taking into consideration their feelings.

[1198] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1199] Step 1: Collect data

[1200] The server calls the API of a government agency, local agency, or government organization. For example, it sends an HTTP request to the API endpoint of the Cabinet Office disaster response site.

[1201] Parse the raw data returned by the server. Analyze the JSON format data and extract the necessary items (e.g., shelter address and emergency contact information).

[1202] The server stores the parsed data in an internal database, and then inserts the data into a table using a database management system (e.g., PostgreSQL).

[1203] Input: JSON data returned from government API

[1204] Output: Parsed data stored in an internal database

[1205] Step 2: Accept user access

[1206] Users access the chatbot from their smartphone or PC by accessing a dedicated URL or launching a dedicated app.

[1207] Input: User's access request

[1208] Output: Chatbot launch and interface display

[1209] Step 3: Accepting user questions

[1210] The user inputs a question or request for assistance through the device interface, for example, "Where is the nearest evacuation center?"

[1211] The terminal sends the user's input data to the server. By pressing the submit button on the form, the data is sent to the server via an Ajax request.

[1212] Input: User's question or request for assistance

[1213] Output: The input data sent to the server

[1214] Step 4: Sentiment Analysis

[1215] The server passes the received data to the emotion engine, which uses NLP models to analyze the text data and identify the user's emotional state.

[1216] The emotion engine analyzes the emotional tone of the user's input text and determines, for example, "high stress."

[1217] Input: User-entered text

[1218] Output: Analyzed emotion data (e.g., high stress)

[1219] Step 5: Generate an answer

[1220] The generative AI model generates the optimal answer based on the analyzed emotional data. For example, if the user is in great distress, it will generate a more thoughtful and reassuring answer. The answer text might be something like, "The nearest evacuation shelter is AA Elementary School. Please rest assured."

[1221] Input: Analyzed emotion data and user questions

[1222] Output: Generated answer text

[1223] Step 6: Provide your answers

[1224] The server sends the generated answer to the device for delivery to the user, and sends the answer text to the device in an HTTP response.

[1225] The device displays the generated answer on the user interface, and the answer text is automatically displayed in the display area for the user to see.

[1226] Input: Generated answer text

[1227] Output: The answer displayed on the interface

[1228] Step 7: Upload your supplies

[1229] The user uploads an image or inventory list of relief supplies from their device and sends it using the "Upload" button.

[1230] The device sends the uploaded data to the server as an HTTP POST request.

[1231] Input: Images or inventory list of relief supplies

[1232] Output: Upload data sent to the server

[1233] Step 8: Analyze material data

[1234] The server passes the uploaded material data to the generative AI model, which then transfers it to the analysis endpoint and begins analysis.

[1235] A generative AI model uses image recognition technology and text analysis to identify the type and quantity of supplies.

[1236] Input: Uploaded material data

[1237] Output: Analyzed material information (type and quantity)

[1238] Step 9: Matching with needs information

[1239] The server compares the analysis results with the support needs database, and matches the required supply data with the support needs by executing a search query.

[1240] Input: Parsed material information

[1241] Output: Matching results with the needs database

[1242] Step 10: Generate and provide shipping information

[1243] The server generates appropriate delivery address information for the goods, for example, "AA City Hall, 〒AAA-AAAA."

[1244] The server sends the destination information to the terminal, which then sends the destination data to the terminal as an HTTP response.

[1245] The terminal displays the information in the user interface. The delivery information is automatically displayed in the display area.

[1246] Input: Matching result

[1247] Output: Shipping information displayed on the terminal

[1248] These are the specific processing steps of this system's program. This allows users to receive prompt and accurate information that takes their emotions into consideration, and also enables efficient matching of relief supplies by volunteers.

[1249] (Application example 2)

[1250] 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."

[1251] The lack of a support system that can respond quickly and accurately to victims and those seeking support during large-scale disasters is an issue. Specifically, there is a lack of appropriate information provision and matching of relief supplies to quickly deliver the food and relief supplies needed by victims. Furthermore, there is a lack of consideration for users' emotions, and psychological support for victims is insufficient.

[1252] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting the latest disaster information and support needs information from databases of administrative agencies, local agencies, and government agencies, means for saving the collected data in an internal database, interface means for users to input questions and support requests, means for analyzing user input and generating appropriate answers using a generative AI model, means for providing the generated answers to users, means for volunteers to upload images and inventory lists of relief supplies, means for analyzing the uploaded supply information and comparing it with current needs information for specific regions or municipalities, means for presenting appropriate supply destinations based on the comparison results, means for analyzing emotions from user input and adjusting the tone and expression of the generated answers based on the results, and means for quickly and accurately delivering food and other items to disaster victims in the event of a disaster. This enables the provision of information and matching of supplies to disaster victims and those seeking support quickly and accurately, and also enables responses that take emotions into consideration.

[1253] "Administrative, local and government agency databases" refers to information systems provided by public agencies that manage and store disaster information and assistance needs information.

[1254] "Data collection instruments" means mechanisms for obtaining required information from administrative, regional and government agency databases.

[1255] "Internal database" refers to data storage for storing collected disaster information and assistance needs information.

[1256] The "interface means" is a user interface through which a user inputs questions or requests for assistance.

[1257] A "generative AI model" is an artificial intelligence algorithm that analyzes user input and generates appropriate answers.

[1258] The "answer providing means" is a system component for providing the generated answer to the user.

[1259] "Supply upload method" refers to the mechanism by which volunteers submit images and inventory lists of supplies to the system.

[1260] The "supply information analysis means" is a mechanism for analyzing information on uploaded relief supplies and comparing it with information on current needs in specific regions or municipalities.

[1261] The "supply delivery destination presentation means" is a system component that notifies volunteers of the appropriate delivery destination for supplies based on the matching results.

[1262] A "sentiment analysis means" is a mechanism for analyzing emotions from user input and adjusting the tone and expression of the generated response based on the results.

[1263] "Delivery support means" is a system component that provides prompt and accurate delivery support for food and other items to disaster victims in the event of a disaster.

[1264] This invention is a system that responds quickly and accurately to victims and those seeking assistance in the event of a large-scale disaster. This system collects disaster information and assistance needs information, and provides appropriate information and assistance by combining a generative AI model and an emotion engine.

[1265] System Overview

[1266] This system consists of the following main components:

[1267] 1. Data collection unit:

[1268] - Access databases of administrative, local and government agencies to collect the latest disaster and assistance needs information.

[1269] 2. Database Unit:

[1270] - Store the collected data and maintain a temporary database for analysis.

[1271] 3. User Interface Unit:

[1272] - Provide an interface for users to enter questions or requests for assistance.

[1273] 4. Generative AI model unit:

[1274] - Includes AI models to analyze user input and generate appropriate answers.

[1275] 5. Emotion Engine Unit:

[1276] - Analyze the sentiment of user input and adjust the tone and wording of the generated answers accordingly.

[1277] 6. Matching Unit:

[1278] - Analyze information about relief supplies uploaded by volunteers and match it with information about the needs of specific regions and municipalities.

[1279] 7. Answer Providing Unit:

[1280] - Providing answers to users based on the analysis results.

[1281] Generating a Program

[1282] A natural language description of the process

[1283] Data collection phase:

[1284] The server retrieves the latest disaster and assistance needs information through APIs from administrative, local, and government agencies. This is achieved by using the Python requests library to retrieve data from the APIs and store it in MongoDB.

[1285] User Interface Phase:

[1286] Users access the app from their devices (smartphones or PCs) and ask questions about disaster information or enter requests for assistance. This data is sent to the server via a RESTful API. The front end is built using JavaScript (React, Vue.js, etc.).

[1287] Linking generative AI models with emotion engines:

[1288] The server uses an emotion engine (such as Azure Cognitive Services' Text Analytics API) to analyze the user's emotional state. The results are fed into a generative AI model (such as OpenAI's GPT-3) to generate an appropriate response. The emotion engine analyzes the user's input and adjusts the tone and expression of the response based on the user's emotional state.

[1289] Answer provision phase:

[1290] The server then provides the generated answer to the user, adjusting the tone and expression of the answer based on the information analyzed by the emotion engine. This data is then sent to the front-end application and displayed on the user interface.

[1291] Specific examples

[1292] 1. Example for disaster victims:

[1293] A user types into a device, "Where is the nearest shelter?"

[1294] The terminal sends the query data to the server, and the server retrieves the latest evacuation shelter information from the database.

[1295] Using a generative AI model and emotion engine, the answer is generated: "The nearest evacuation shelter is AA Elementary School. The address is AA, AA Town, AA City."

[1296] The server generates a response and sends it to the terminal, where the user can view the response on the interface.

[1297] 2. Example for volunteers:

[1298] The user types into the chatbot on their device, "I'd like to send 50 boxes of diapers. Where do I need them?"

[1299] The device sends the question data to the server, and the chatbot prompts the user to upload an image or inventory list.

[1300] Users upload images and inventory lists, and the device sends the data to a server.

[1301] A generative AI model and emotion engine analyze images and lists, and the server compares them with a database of assistance needs to identify the destination.

[1302] The server generates a response saying, "AA City Hall is currently in need of diapers. The delivery address is AAA-AAAA, AA-cho, AA city, AA City Hall Disaster Response Headquarters," and sends it to the terminal.

[1303] Users can view the information on the interface and take specific action.

[1304] Prompt Sentence Examples

[1305] Example for disaster victims: "Where is the nearest evacuation center?"

[1306] Example for volunteers: "I'd like to send 50 boxes of diapers. Where do you need them?"

[1307] This will enable quick and accurate provision of information and matching of supplies to disaster victims and those seeking assistance, and will also enable responses that take into consideration emotions.

[1308] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1309] Step 1:

[1310] The server accesses APIs provided by administrative agencies, local organizations, and government agencies to obtain the latest disaster information and assistance needs information. The data obtained from the API is in JSON format, which is parsed and stored in MongoDB. This allows the latest disaster information and assistance needs information to be accumulated in an internal database.

[1311] Step 2:

[1312] Users access the app from their devices (smartphones or PCs) and input their questions or requests for assistance through the interface. This user-entered data is sent to the server using a RESTful API. The input information is passed to the server in text format.

[1313] Step 3:

[1314] The server performs sentiment analysis on the received user input data using the Text Analytics API of Azure Cognitive Services, identifying the user's emotional state (e.g., joy, anxiety, anger, etc.) and receiving the results in JSON format.

[1315] Step 4:

[1316] Based on the results of the sentiment analysis, the server generates a prompt for a generative AI model (such as OpenAI's GPT-3) and asks for an appropriate answer. The generative AI model generates text that is adapted to the input prompt, and that text is returned to the server as the answer.

[1317] Step 5:

[1318] The server further adjusts the answer received from the generative AI model. Based on the results of the emotion engine, it adjusts the tone and expression of the answer to be more dignified and emotionally relevant. Using this adjusted answer text, it prepares to provide appropriate information to the user.

[1319] Step 6:

[1320] The server returns the adjusted answer to the device via a RESTful API. The device receives this data and displays it on its user interface, where the user can view the generated answer.

[1321] Step 7:

[1322] Volunteers upload images of relief supplies and inventory lists from their devices. The devices then send the uploaded data to the server. The data format is JPEG or PNG for images, and CSV or JSON for lists.

[1323] Step 8:

[1324] The server uses a generative AI model to perform image recognition and text analysis of the uploaded relief supplies, identifying the type and quantity of supplies and matching this with relief needs information in an internal database. As a result of the matching, the required supply information is identified.

[1325] Step 9:

[1326] Based on the matching results, the server generates appropriate delivery information for the goods, including specific contact details and addresses, and sends it to the terminal and displays it on the user interface.

[1327] Step 10:

[1328] The user can check the delivery destination information provided from the terminal and quickly deliver the relief supplies to the specified location.

[1329] 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.

[1330] 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.

[1331] 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.

[1332] [Third embodiment]

[1333] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1334] 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.

[1335] 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).

[1336] 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.

[1337] 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.

[1338] 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).

[1339] 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.

[1340] 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.

[1341] 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.

[1342] 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.

[1343] 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.

[1344] 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."

[1345] The present invention is a system for quickly and accurately providing necessary information in the event of a large-scale disaster and supporting the actions of victims and those seeking assistance. This system executes a series of processes to collect, store, analyze, and provide disaster information and assistance needs information to users from databases of administrative agencies, local agencies, and government agencies. An embodiment of the present invention is described in detail below.

[1346] System Overview

[1347] This system consists of the following main components:

[1348] 1. Data Collection Unit: This unit accesses the databases of administrative agencies, local agencies and government agencies to collect the latest disaster information and assistance needs information.

[1349] 2. Database unit: This unit stores the collected data and maintains the temporary database required for analysis.

[1350] 3. User interface unit: This unit provides an interface through which users can input their questions or requests for assistance.

[1351] 4. Generative AI model unit: This unit contains an AI model for analyzing user input and generating appropriate answers.

[1352] 5. Matching Unit: This unit analyzes information about relief supplies uploaded by volunteers and matches it with information about the needs of specific regions and municipalities.

[1353] 6. Answer providing unit: This unit provides answers to users based on the analysis results.

[1354] About program processing

[1355] Data Collection Phase

[1356] The server periodically calls the APIs of administrative agencies and government organizations to obtain the latest disaster information and assistance needs information, and the obtained data is stored in an internal database.

[1357] User Interface Phase

[1358] Users access the chatbot from their device and enter questions about disaster information and requests for assistance.

[1359] The terminal transmits the input data to the server.

[1360] The server passes the received data to the generative AI model and analyzes the content of the user's question.

[1361] The generative AI model analyzes the input question and generates the optimal answer, drawing on the necessary information from the server's database.

[1362] Answer provision phase

[1363] The server sends the answer generated by the generative AI model to the device to provide to the user.

[1364] The terminal displays the generated answers on a user interface.

[1365] Analysis and matching phase of supply support

[1366] The user uploads images or inventory lists of relief supplies from the terminal.

[1367] The terminal transmits the uploaded data to the server.

[1368] The server passes the uploaded material information to the generative AI model and begins analysis.

[1369] The generative AI model uses image recognition technology to identify the type and quantity of supplies.

[1370] The server compares the analysis results with the assistance needs database of administrative and government agencies to identify the appropriate destination.

[1371] Based on the result of the comparison, the server sends specific delivery address information to the terminal to provide to the volunteer.

[1372] The terminal displays the delivery destination information on the user interface.

[1373] Specific examples

[1374] Specific examples for disaster victims

[1375] 1. The user types into the chatbot on their device, "Where is the nearest evacuation shelter?"

[1376] 2. The device sends the query data to the server.

[1377] 3. The server retrieves the latest evacuation shelter information from the database and uses the generative AI model to generate an answer such as, "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA-shi."

[1378] 4. The server sends the generated answer to the device, where the user can view it on the interface.

[1379] Specific examples for volunteers

[1380] 1. The user types into the chatbot on their device, "I'd like to send 50 boxes of diapers. Where do I need them?"

[1381] 2. The device sends the query data to the server.

[1382] 3. The chatbot prompts the user to "upload an image of diapers or an inventory list."

[1383] 4. User uploads images and inventory list.

[1384] 5. The device sends the upload data to the server.

[1385] 6. The generative AI model analyzes the uploaded images and listings.

[1386] 7. The server compares the analysis results with the support needs database and identifies the necessary destination.

[1387] 8. The server generates a response such as "AA City Hall currently needs diapers. The delivery address is AA, AA-cho, AA, AA City, AAA-AAAA, AA City Hall Disaster Response Headquarters," and sends it to the terminal.

[1388] 9. Users can view the information on the interface and take specific action.

[1389] The above is the "Mode for carrying out the invention" of the chatbot system specialized for disaster relief in this invention. This system can provide quick and accurate information to disaster victims and those seeking support, and can significantly improve the efficiency and effectiveness of support activities.

[1390] The processing flow will be explained below.

[1391] Data Collection Phase

[1392] Step 1:

[1393] The server uses APIs to access public databases from government agencies, local authorities, and government agencies, and periodically (for example, every hour) sends requests to designated endpoints to retrieve the latest disaster and relief needs information.

[1394] Step 2:

[1395] The server parses and reads the collected data and extracts the necessary information (shelter information, assistance needs, disaster situation, etc.), which includes parsing the data in JSON and XML formats.

[1396] Step 3:

[1397] The server stores the extracted information in its internal database, overwriting any existing information with the latest information and deleting the old data.

[1398] User Interface Phase

[1399] Step 4:

[1400] Users access chatbots from their devices (smartphones or PCs), specifically by connecting to the chatbot's interface through a web page or dedicated app.

[1401] Step 5:

[1402] The user enters their question or request for assistance into the chatbot's input field.

[1403] Step 6:

[1404] The device sends the user's input data to the server, using the HTTPS communication protocol.

[1405] Step 7:

[1406] The server passes the received input data to the generative AI model and begins analysis. The generative AI model is then passed the user's question and desired assistance.

[1407] Step 8:

[1408] The generative AI model analyzes the input data and generates the best answer, specifically using natural language processing (NLP) techniques to understand the question and generate a corresponding answer.

[1409] Step 9:

[1410] The server sends the answer generated by the generative AI model to the device for return to the user.

[1411] Step 10:

[1412] The device will display the generated answer on the user interface, allowing the user to obtain the information they need through the chatbot.

[1413] Analysis and matching phase of supply support

[1414] Step 11:

[1415] Users upload images or inventory lists of relief supplies from their devices.

[1416] Step 12:

[1417] The device sends the uploaded data to the server.

[1418] Step 13:

[1419] The server passes the uploaded material information (images and text data) to the generative AI model and begins analysis.

[1420] Step 14:

[1421] The generative AI model uses image recognition and text analysis to identify the type and quantity of supplies. Specifically, it analyzes images of supplies and identifies their classification and quantity.

[1422] Step 15:

[1423] The server then compares the analysis results with the support needs databases of administrative and government agencies, comparing the information on needed supplies with current needs and identifying which regions and municipalities need those supplies.

[1424] Step 16:

[1425] The server then uses the results of the match to generate appropriate delivery information for the user, including specific addresses and contact information.

[1426] Step 17:

[1427] The server sends the generated delivery address information to the terminal.

[1428] Step 18:

[1429] The terminal displays the delivery destination information on the user interface, and users can send supplies based on this information.

[1430] This is the specific flow of the program processing for the disaster relief chatbot system. This processing step enables the prompt and accurate provision of information to disaster victims and those seeking support.

[1431] Example 1

[1432] 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."

[1433] In the event of a large-scale disaster, rapid and accurate information provision is required, but in conventional systems, information collection and analysis are often done manually, which takes time and effort, and can result in delays in providing appropriate information. Another issue is the inability to respond appropriately in real time to the information and needs of victims and supporters. Furthermore, there is a lack of mechanisms for volunteers to efficiently provide relief supplies. In these situations, a system is needed that can effectively support the actions of victims and those seeking support.

[1434] 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.

[1435] In this invention, the server includes: means for collecting disaster information and support needs information from databases of administrative agencies, local agencies, and government agencies; means for saving the collected data in an internal database; interface means for users to input questions and support requests; means for analyzing the user's input and generating appropriate answers using a generative AI model; means for providing the generated answers to the user; means for volunteers to upload the characteristics and quantities of relief supplies; means for analyzing the uploaded supply information and comparing it with local information; and means for presenting appropriate supply destinations based on the comparison results. This enables disaster victims and those seeking support to receive information quickly and accurately, significantly improving the efficiency and effectiveness of support activities.

[1436] "Administrative agencies" are organizations that provide public services, such as national and local governments.

[1437] "Local organizations" are organizations that carry out disaster response and support activities within local governments and communities.

[1438] "Government agencies" are public organizations such as central government ministries and agencies responsible for national administration.

[1439] A "database" is a collection of information that is structured to make it easy to manage and search.

[1440] "Disaster information" is detailed information about natural and man-made disasters.

[1441] "Support needs information" refers to information about the relief supplies and services needed by disaster-stricken areas and victims in the event of a disaster.

[1442] A "user interface" is the means by which a user interacts with a system.

[1443] A "generative AI model" is a computer program that uses artificial intelligence to analyze user input and generate appropriate answers.

[1444] "Volunteers" are individuals or groups who provide support activities free of charge.

[1445] "Relief supplies" are items such as food, medicine, and clothing provided to victims in the event of a disaster.

[1446] "Regional information" refers to information about the disaster situation and assistance needs in a specific region.

[1447] A "prompt" is text that contains questions or instructions to be input into a generative AI model.

[1448] The present invention provides a system for quickly and accurately providing necessary information during a large-scale disaster and supporting the actions of disaster victims and those seeking assistance. This system executes a series of processes to collect, store, and analyze disaster information and assistance needs information from databases of administrative agencies, local agencies, and government agencies, and provide the information to users. Specific embodiments for implementing the present invention are described in detail below.

[1449] System Overview

[1450] This system consists of the following main components:

[1451] 1. Data Collection Unit: This unit accesses the databases of administrative agencies, local agencies and government agencies to collect the latest disaster information and assistance needs information.

[1452] 2. Database unit: This unit stores the collected data and maintains the temporary database required for analysis. Specifically, a MySQL database is used.

[1453] 3. User interface unit: This unit provides an interface where users can enter questions or requests for assistance. It runs on a web browser.

[1454] 4. Generative AI model unit: This unit contains an AI model for analyzing user input and generating appropriate answers. Generative AI models such as GPT-3 are used.

[1455] 5. Matching Unit: This unit analyzes information about relief supplies uploaded by volunteers and matches it with information about the needs of specific regions and municipalities.

[1456] 6. Answer providing unit: This unit provides answers to users based on the analysis results.

[1457] About program processing

[1458] Data Collection Phase

[1459] The server periodically calls the APIs of government agencies and organizations to obtain the latest disaster and relief needs information. It connects to the API using Python's requests library and retrieves data in JSON format. The retrieved data is then stored in a MySQL database using Python's MySQL Connector.

[1460] User Interface Phase

[1461] A user accesses the chatbot from their device via a web browser and inputs a question or request for assistance. For example, they might input, "Where is the nearest evacuation shelter?" The device sends the input data to the server using WebSocket or an HTTP request. The server processes the received request using a web framework such as Flask and passes the prompt text to the generative AI model.

[1462] For example: "Where is the nearest shelter?"

[1463] Analysis of generative AI models

[1464] A generative AI model (e.g., GPT-3) analyzes the prompt sentence and generates an appropriate answer. In the analysis process, the necessary information is retrieved from the database using a SELECT statement, and an answer such as "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA, AA City" is generated.

[1465] Answer provision phase

[1466] The server sends the answers generated by the generative AI model to the device, which then displays the received answers on a web browser, allowing the user to view the information in real time.

[1467] Analysis and matching phase of supply support

[1468] The user uploads images of relief supplies and an inventory list. For example, they might type, "I'd like to send 50 boxes of diapers. Where do they need them?" and upload images of the supplies. The device then sends the uploaded file to the server via HTTP POST. The server saves the file in a temporary storage area and analyzes the image using Python's Pillow library or similar. The generative AI model uses TensorFlow or PyTorch to identify the supply data from the image, compares it with a MySQL database, and then generates specific delivery address information, such as, "AA City Hall is currently in need of diapers. The delivery address is AAA-AAAA, AA Town, AA City, AA City Hall Disaster Response Headquarters."

[1469] Specific examples

[1470] Specific examples for victims:

[1471] 1. User types, "Where is the nearest shelter?"

[1472] 2. The device sends the information to the server.

[1473] 3. The server retrieves the appropriate evacuation shelter information from the database and generates the information "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA-shi." through the generative AI model.

[1474] 4. The server sends the generated answer to the device, and the user views the information in the browser.

[1475] Examples for volunteers:

[1476] 1. A user types into the chatbot, "I'd like to send 50 boxes of diapers. Where do they need to go?"

[1477] 2. The device sends the information to the server.

[1478] 3. The chatbot will prompt you to "Upload an image of your diapers or an inventory list."

[1479] 4. The user uploads the image.

[1480] 5. The device sends the data to the server.

[1481] 6. The generative AI model analyzes the image to identify the type and quantity of supplies.

[1482] 7. The server identifies the appropriate delivery address based on the matching results and generates the information, "AA City Hall currently needs diapers. The delivery address is AAA-AAAA, AA-cho, AA City, AA City Disaster Response Headquarters."

[1483] 8. Users can view the information in their browser and take specific action.

[1484] The above is the specific processing and operation of the embodiment of the present invention. This system enables quick and accurate provision of information and support to disaster victims and those seeking support, significantly improving the efficiency and effectiveness of support activities.

[1485] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1486] Program processing steps

[1487] Step 1:

[1488] The server periodically calls the API of the administrative agency or government institution.

[1489] Input: API endpoint

[1490] Data processing: Use the Python requests library to connect to the API and retrieve data in JSON format.

[1491] Output: Retrieved JSON data

[1492] Specific behavior:

[1493] The server accesses the API endpoint using the requests.get() method and extracts the JSON data from the response object.

[1494] Step 2:

[1495] The server stores the acquired data in an internal database.

[1496] Input: JSON data

[1497] Data processing: Analyze the data to extract important information and store it in a MySQL database using INSERT statements.

[1498] Output: Disaster information and assistance needs information stored in a database

[1499] Specific behavior:

[1500] The server converts the JSON data into a dictionary using the json.loads() method, connects to the database using the MySQL Connector, and issues an INSERT statement using the cursor.execute() method.

[1501] Step 3:

[1502] The user accesses the chatbot from their device and enters their question or the assistance they would like.

[1503] Input: Question or request for assistance (e.g., "Where is the nearest evacuation center?")

[1504] Data processing: User input is obtained using HTML forms or JavaScript.

[1505] Output: Question data

[1506] Specific behavior:

[1507] The user accesses the chatbot's UI on a web browser, enters a question in the text box, and clicks the send button.

[1508] Step 4:

[1509] The terminal transmits the input data to the server.

[1510] Input: Question data

[1511] Data processing: Send the question data to the server as a WebSocket or HTTP POST request.

[1512] Output: The query data passed to the server

[1513] Specific behavior:

[1514] The device sends data to the server using the JavaScript fetch() method or the WebSocket.send() method.

[1515] Step 5:

[1516] The server passes the received data to the generative AI model for analysis.

[1517] Input: Question data

[1518] Data processing: The question data is passed to a generative AI model (e.g., GPT-3) as a prompt.

[1519] Output: The answer parsed by the generative AI model

[1520] Specific behavior:

[1521] The server uses Flask to process incoming requests and send them to the API of the generative AI model.

[1522] Step 6:

[1523] The generative AI model analyzes the input question and generates an appropriate answer.

[1524] Input: prompt statement

[1525] Data processing: Analyzes the prompt statement, retrieves the necessary information from the database using a SELECT statement, and generates an answer.

[1526] Output: The generated answer

[1527] Specific behavior:

[1528] The generative AI model receives the API request and generates an answer using its internal algorithm. The server receives the result and processes it again.

[1529] Step 7:

[1530] The server sends the answer generated by the generative AI model to the user's device.

[1531] Input: Generated answer

[1532] Data processing: The generated answer is sent to the device as an HTTP or WebSocket response.

[1533] Output: Answer data sent to the device

[1534] Specific behavior:

[1535] The server uses Flask's response object to generate the answer and send it back to the device.

[1536] Step 8:

[1537] The terminal displays the generated answer on a user interface.

[1538] Input: Generated response data

[1539] Data processing: The received data is formatted for display using HTML and JavaScript.

[1540] Output: The answer displayed in the user interface

[1541] Specific behavior:

[1542] The terminal uses JavaScript DOM manipulation methods to dynamically display the received response data on a web page.

[1543] Step 9:

[1544] Users upload images of relief supplies and inventory lists from their devices.

[1545] Input: Images and inventory list of relief supplies

[1546] Data processing: Taking user input from forms and uploading files.

[1547] Output: Uploaded file data

[1548] Specific behavior:

[1549] The user selects an image or list using a file input form on a web browser and clicks the upload button.

[1550] Step 10:

[1551] The device sends the uploaded data to the server.

[1552] Input: File data

[1553] Data processing: Send the file data to the server as an HTTP POST request.

[1554] Output: File data passed to the server

[1555] Specific behavior:

[1556] The device uses the JavaScript fetch() method to send the file data to the server.

[1557] Step 11:

[1558] The server passes the uploaded material information to the generative AI model and begins analysis.

[1559] Input: File data

[1560] Data processing: Save the file to a temporary storage area and read the data using the image analysis library.

[1561] Output: Image data or list data for analysis

[1562] Specific behavior:

[1563] The server uses an image analysis library such as Pillow or performs direct text analysis.

[1564] Step 12:

[1565] The generative AI model uses image recognition technology to identify the type and quantity of supplies.

[1566] Input: Image data or list data

[1567] Data processing: Image analysis algorithms are used to identify material information and count quantities.

[1568] Output: Identified material data

[1569] Specific behavior:

[1570] The generative AI model uses TensorFlow or PyTorch to analyze images and identify the type and quantity of supplies.

[1571] Step 13:

[1572] The server compares the analysis results with a database of assistance needs and identifies the appropriate destination.

[1573] Input: Identified material data

[1574] Data processing: Database matching is performed to find the optimal delivery destination.

[1575] Output: Proper shipping information

[1576] Specific behavior:

[1577] The server runs a SELECT statement against the MySQL database to match the needs data with the supplies data.

[1578] Step 14:

[1579] Based on the matching results, the server provides the terminal with the appropriate delivery address for the supplies.

[1580] Enter the appropriate shipping information

[1581] Data processing: The destination information is formatted in a user-friendly format and sent as an HTTP response.

[1582] Output: Shipping information sent to the terminal

[1583] Specific behavior:

[1584] The server uses Flask's response object to send the destination information to the terminal.

[1585] Step 15:

[1586] The terminal displays the delivery information on the user interface.

[1587] Input: Shipping information

[1588] Data processing: The received information is formatted for display using HTML and JavaScript.

[1589] Output: Shipping information displayed on the user interface

[1590] Specific behavior:

[1591] The terminal uses JavaScript DOM manipulation methods to dynamically display the delivery information on a web page.

[1592] (Application example 1)

[1593] 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."

[1594] When a large-scale disaster occurs, it is difficult for victims and those seeking aid to quickly and accurately obtain the information they need. Furthermore, insufficient management of relief supplies and matching of appropriate delivery destinations reduces the efficiency and effectiveness of relief activities. Conventional systems have limited user interfaces and make it difficult to respond in real time, making it difficult to provide disaster information immediately.

[1595] 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.

[1596] In this invention, the server includes: means for collecting the latest disaster information and assistance needs information from databases of administrative agencies, local agencies, and national agencies; means for storing the collected data in an internal database; interface means for users to input questions and assistance requests; means for analyzing user input and generating appropriate answers using a generative AI model; means for providing the generated answers to users; means for volunteers to upload images of relief supplies and inventory lists; means for analyzing the uploaded supply information and comparing it with current needs information for specific regions and municipalities; means for presenting appropriate supply destinations based on the comparison results; means for providing responses in real time based on user input information and questions; and means for providing evacuation center information and emergency contact information via a smartphone application. This allows disaster victims and assistance seekers to quickly and accurately obtain information, improving the efficiency and effectiveness of assistance activities.

[1597] "Administrative agencies" refer to public institutions such as national and local governments and similar organizations.

[1598] A "local agency" is an agency or organization that provides public services or functions in a particular geographic area.

[1599] "Government agencies" refer to various agencies of the central government responsible for the administration of the country.

[1600] A "database" is a mechanism or system for systematically storing and managing digital information.

[1601] "Disaster information" refers to information such as forecasts, occurrence status, damage status, and response measures regarding emergencies such as natural disasters and accidents.

[1602] "Support needs information" refers to information on specific needs, such as relief supplies, services, and information, required by disaster-stricken areas and disaster victims.

[1603] An "interface" refers to the operation screen, input means, and output means that users use to use a system.

[1604] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and automatically generate answers to user questions.

[1605] An "answer" is information or instructions provided in response to a user's question.

[1606] "Volunteers" are individuals or groups who voluntarily engage in activities such as disaster relief and social contribution.

[1607] "Supply information" refers to specific information such as the type and quantity of relief supplies provided.

[1608] "Verification" is the process of comparing information to see if it matches.

[1609] "Destination" refers to the place where supplies, information, etc. should be delivered or the recipient.

[1610] "Real-time" refers to information processing and system response occurring immediately and without delay.

[1611] A "smartphone application" is a software program that runs on a smartphone.

[1612] "Evacuation shelter information" refers to information about facilities and locations for evacuation in the event of a disaster.

[1613] "Emergency contact information" refers to contact information for use in the event of a disaster or emergency.

[1614] This invention relates to a system that provides necessary information quickly and accurately in the event of a large-scale disaster, and supports the actions of victims and those seeking assistance. This system is composed of the following main components:

[1615] Data Acquisition Unit

[1616] The server periodically accesses the databases of administrative agencies, local agencies, and government agencies to collect the latest disaster information and assistance needs information, which is then stored in an internal database.

[1617] Database Unit

[1618] The server's internal database stores collected disaster and assistance needs information, and is updated in real time to enable prompt responses to user questions and requests.

[1619] User Interface Unit

[1620] Users access the system using a smartphone application, which provides an interface for inputting questions about disaster information and requests for assistance.

[1621] Generative AI Model Unit

[1622] The server analyzes the user's input data using a generative AI model, such as OpenAI's GPT-3, to generate an appropriate answer. The generated answer is then provided to the user by the server.

[1623] Answer Providing Unit

[1624] The server provides the answers generated by the generative AI model to the user through a smartphone application, allowing the user to obtain the information they need in real time.

[1625] Logistics Support Analysis and Matching Unit

[1626] When users upload images of relief supplies and inventory lists, the server analyzes this data and compares it with information on relief needs. TensorFlow is used for image recognition technology. Based on the results of the comparison, the server identifies the appropriate delivery address for the supplies and presents it to the user.

[1627] Examples:

[1628] Specific examples for victims:

[1629] 1. The user types "Where is the nearest evacuation shelter?" into the smartphone application.

[1630] 2. The application sends the query data to the server.

[1631] 3. The server retrieves the latest evacuation shelter information from the database and uses the generative AI model to generate an answer such as, "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA-shi."

[1632] 4. The server sends the generated answer to the application, where the user can view it on the interface.

[1633] Examples for volunteers:

[1634] 1. A user types in a smartphone application, "I'd like to send 50 boxes of diapers. Where do I need them?"

[1635] 2. The application sends the query data to the server.

[1636] 3. The chatbot instructs the user to "upload an image of diapers or an inventory list."

[1637] 4. User uploads images and inventory list.

[1638] 5. The application sends the upload data to the server.

[1639] 6. The generative AI model analyzes the uploaded images and listings.

[1640] 7. The server compares the analysis results with the support needs database and identifies the necessary destination.

[1641] 8. The server generates a response such as "AA City Hall currently needs diapers. The delivery address is AA, AA-cho, AA, AA City, AAA-AAAA, AA City Hall Disaster Response Headquarters." and sends it to the application.

[1642] 9. Users can view the information on the interface and take specific action.

[1643] Hardware and software used:

[1644] Server: Cloud server (e.g. Google Cloud, AWS EC2)

[1645] Software: Python, Firebase Admin SDK, React Native, Django, OpenAI API, TensorFlow

[1646] Device: Smartphone

[1647] Example prompt sentence:

[1648] "Where is the nearest shelter?"

[1649] "I'd like to send 50 boxes of diapers. Where do you need them?"

[1650] Please tell me the current disaster situation.

[1651] "I would like to know the list of relief supplies in demand."

[1652] The above is an embodiment of the present invention. This system makes it possible to provide quick and accurate information to disaster victims and those seeking support, significantly improving the efficiency and effectiveness of support activities.

[1653] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1654] Step 1:

[1655] The server periodically calls the APIs of administrative agencies, local agencies, and government agencies to obtain the latest disaster information and assistance needs information. The API requests are input, and the disaster information and assistance needs information obtained as output is saved in an internal database. This ensures that the server always has the latest information.

[1656] Step 2:

[1657] Users use a smartphone application to input questions about disaster information and requests for assistance. Input includes text input and image uploads, and output is sent to the server via the device. This input data includes the user's needs and questions.

[1658] Step 3:

[1659] The device sends the received user input data to the server. The input is the user's text data or image data, and the output is sent in a format that can be analyzed by the server. This prepares the server for the next step of processing.

[1660] Step 4:

[1661] The server passes the user's input data to the generative AI model and generates an appropriate answer. The input is the user's question, and the output is the answer to the question generated by the generative AI model. The AI ​​model, for example, uses OpenAI's GPT-3, which analyzes the user's question using natural language processing.

[1662] Step 5:

[1663] The server sends the generated answer back to the smartphone application, which takes the generated answer as input and sends it to the device in a format that the user can use as output, allowing the user to receive the answer quickly.

[1664] Step 6:

[1665] The user checks the answer displayed on the device through the smartphone application. The answer from the server is input, and the information provided to the user is output. This allows the user to decide what to do based on the necessary information.

[1666] Step 7:

[1667] When a user uploads images of relief supplies or an inventory list, the device sends that information to the server. The input is the user's image data and list data, and the output is sent in a format that can be analyzed by the server. This data includes information about the relief supplies.

[1668] Step 8:

[1669] The server uses a generative AI model to analyze the uploaded images and lists of relief supplies and identify the type and quantity of supplies. Image data and list data are input, and the analysis results are obtained as output. Image recognition technology such as TensorFlow is used for the analysis.

[1670] Step 9:

[1671] The server compares the analysis results with the support needs information stored in its internal database and identifies appropriate delivery destinations that meet those needs. The inputs are the analysis results and support needs information, and the output is appropriate delivery destination information. As a result of the comparison, areas and facilities in need of relief supplies are identified.

[1672] Step 10:

[1673] The server provides the user with appropriate delivery information through a smartphone application. The delivery information is input and sent to the device in a format that the user can use as output, allowing the user to take specific supportive actions.

[1674] 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.

[1675] The present invention is a system that responds quickly and accurately to victims and those seeking assistance in the event of a large-scale disaster. This system collects disaster information and assistance needs information from databases of administrative agencies, local organizations, and government agencies, and combines a generative AI model and an emotion engine to provide users with appropriate information and assistance. An embodiment of the present invention is described in detail below.

[1676] System Overview

[1677] This system consists of the following main components:

[1678] 1. Data Collection Unit: This unit accesses the databases of administrative agencies, local agencies and government agencies to collect the latest disaster information and assistance needs information.

[1679] 2. Database unit: This unit stores the collected data and maintains the temporary database required for analysis.

[1680] 3. User interface unit: This unit provides an interface through which users can input their questions or requests for assistance.

[1681] 4. Generative AI model unit: This unit contains an AI model for analyzing user input and generating appropriate answers.

[1682] 5. Emotion Engine Unit: This unit analyzes emotions from user input and adjusts the tone and expression of the generated answers based on the results.

[1683] 6. Matching Unit: This unit analyzes information about relief supplies uploaded by volunteers and matches it with information about the needs of specific regions and municipalities.

[1684] 7. Answer providing unit: This unit provides answers to users based on the analysis results.

[1685] About program processing

[1686] Data Collection Phase

[1687] The server retrieves the latest disaster and assistance needs information through APIs from administrative, local, and government agencies. This data is parsed into an appropriate format and then stored in an internal database.

[1688] User Interface Phase

[1689] Users access the chatbot from their device (smartphone or PC) and ask questions about disaster information or enter the details of the assistance they would like to receive.

[1690] The device sends user input to the server, which passes the data to the generative AI model and emotion engine unit.

[1691] The server uses the emotion engine unit to analyze the user's emotional state. Depending on the emotional state, additional information is provided for the generative AI model unit to generate an optimal answer. For example, if the user is in great distress, a more careful and reassuring answer will be generated.

[1692] Answer provision phase

[1693] The server then sends the generated answer to the user's device, adjusting the tone and expression of the answer based on the information analyzed by the emotion engine.

[1694] The device displays the generated answer on the user interface, allowing users to not only get the information they need through the chatbot, but also receive emotionally sensitive responses.

[1695] Analysis and matching phase of supply support

[1696] The user uploads images or inventory lists of relief supplies from the terminal.

[1697] The device sends the uploaded information about the supplies to the server, which then passes it to the generative AI model and emotion engine unit to begin analysis.

[1698] The generative AI model uses image recognition and text analysis to identify the type and quantity of supplies. The server then compares this information with a database of government and administrative agencies' needs. An emotion engine then provides additional information to determine the urgency of the need.

[1699] Based on the matching results, the server generates appropriate delivery information for the user, providing specific contact details and addresses for the delivery destination.

[1700] The server sends the generated delivery destination information to the terminal, which displays this information on the user interface, allowing the user to quickly deliver the relief supplies.

[1701] Specific examples

[1702] Specific examples for disaster victims

[1703] 1. The user types "Where is the nearest evacuation shelter?" into the device.

[1704] 2. The device sends the question data to the server.

[1705] 3. The server retrieves the latest evacuation shelter information from the database and uses the generative AI model and emotion engine to respond, "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA-shi."

[1706] 4. The server generates a response and sends it to the terminal, where the user can view the response on the interface.

[1707] Specific examples for volunteers

[1708] 1. The user types into the chatbot on their device, "I'd like to send 50 boxes of diapers. Where do I need them?"

[1709] 2. The device sends the question data to the server.

[1710] 3. The chatbot prompts the user to "upload an image of diapers or an inventory list."

[1711] 4. User uploads images and inventory list.

[1712] 5. The device sends the upload data to the server.

[1713] 6. Generative AI models and emotion engines analyze images and lists.

[1714] 7. The server compares the analysis results with the assistance needs database and identifies the necessary destination.

[1715] 8. The server generates a response saying, "AA City Hall currently needs diapers. The delivery address is AAA-AAAA, AA-cho, AA City, AA City Hall Disaster Response Headquarters." and sends it to the terminal.

[1716] 9. Users can view the information on the interface and take specific action.

[1717] The above is the "Mode for carrying out the invention" of the chatbot system specialized for disaster relief in this invention. This system makes it possible to provide quick and accurate information to disaster victims and those seeking support while taking into consideration their feelings.

[1718] The processing flow will be explained below.

[1719] Data Collection Phase

[1720] Step 1:

[1721] The server uses APIs to access public databases from administrative, local, and government agencies. It periodically (for example, every hour) sends requests to designated endpoints to retrieve the latest disaster and relief needs information.

[1722] Step 2:

[1723] The server parses the data it receives and extracts the necessary information (e.g., evacuation shelter information, assistance needs, disaster status, etc.). This includes parsing data in JSON and XML format.

[1724] Step 3:

[1725] The server stores the extracted information in its internal database, overwriting any existing information with the latest information and deleting the old data.

[1726] User Interface Phase

[1727] Step 4:

[1728] Users access chatbots from their devices (smartphones or PCs), specifically by connecting to the chatbot's interface through a web page or dedicated app.

[1729] Step 5:

[1730] Users enter their question or request for assistance into the chatbot's input field, for example, "Where is the nearest evacuation center?"

[1731] Step 6:

[1732] The device sends the user's input data to the server, using the HTTPS communication protocol.

[1733] Step 7:

[1734] The server passes the received input data to the generative AI model and emotion engine to begin analysis. The user's question is analyzed.

[1735] Step 8:

[1736] The emotional engine analyzes the user's emotional state, for example, by determining the emotional state from the content of the text, the speed of typing, and the structure of the text.

[1737] Step 9:

[1738] The generative AI model refers to the analysis results of the emotion engine and generates an appropriate response. If the emotion engine detects "anxiety," it will generate a response that provides a sense of security.

[1739] Step 10:

[1740] The server then sends the generated answer to the device for delivery to the user, with the tone and expression influenced by the emotion engine.

[1741] Step 11:

[1742] The device displays the generated answers in a user interface, allowing the user to view and act on the answers.

[1743] Analysis and matching phase of supply support

[1744] Step 12:

[1745] Users upload images or inventory lists of relief supplies from their devices. For example, they can upload images or lists of diapers.

[1746] Step 13:

[1747] The device sends the uploaded data to the server using HTTPS as the communication protocol.

[1748] Step 14:

[1749] The server passes the uploaded information on supplies to the generative AI model and emotion engine, and begins analysis. The type and quantity of supplies are identified.

[1750] Step 15:

[1751] The generative AI model uses image recognition technology and text analysis to identify the type and quantity of supplies.

[1752] Step 16:

[1753] The server then compares the identified supply information with the support needs databases of administrative and government agencies, comparing the required supplies with current needs and identifying which regions and municipalities need the supplies.

[1754] Step 17:

[1755] The emotion engine determines the urgency of the support. For example, if there is a high urgent need for a particular item, that information will be reflected in the matching results.

[1756] Step 18:

[1757] Based on the results of the matching, the server generates appropriate delivery information for the user, providing specific addresses and contact information.

[1758] Step 19:

[1759] The server sends the generated destination information to the terminal, using HTTPS as the communication protocol.

[1760] Step 20:

[1761] The terminal displays delivery destination information on the user interface, and users can send supplies based on this information.

[1762] Specific examples

[1763] Specific examples for disaster victims

[1764] Step 1:

[1765] A user types into a device, "Where is the nearest shelter?"

[1766] Step 2:

[1767] The terminal transmits the question data to the server.

[1768] Step 3:

[1769] The server retrieves the latest evacuation shelter information from the database.

[1770] Step 4:

[1771] The emotion engine analyzes the user's emotional state and detects "anxiety."

[1772] Step 5:

[1773] The generative AI model references the results of the emotion engine and generates a reassuring response: "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA-shi. Please stay safe."

[1774] Step 6:

[1775] The server generates a response and sends it to the device.

[1776] Step 7:

[1777] The device displays the answer on the user interface, where the user can confirm the answer.

[1778] Specific examples for volunteers

[1779] Step 1:

[1780] The user types into the chatbot on their device, "I'd like to send 50 boxes of diapers. Where do they need to be?"

[1781] Step 2:

[1782] The terminal transmits the question data to the server.

[1783] Step 3:

[1784] The chatbot instructs the user to "upload an image of diapers or an inventory list."

[1785] Step 4:

[1786] Users upload images and inventory lists.

[1787] Step 5:

[1788] The device sends the upload data to the server.

[1789] Step 6:

[1790] A generative AI model and an emotion engine analyze images and lists. The generative AI model identifies supply information, and the emotion engine determines the urgency of assistance.

[1791] Step 7:

[1792] The server compares the analysis results with the support needs database to identify the necessary recipients and evaluates the urgency of the identified recipients.

[1793] Step 8:

[1794] The server generates a response saying, "AA City Hall is currently in need of diapers. The delivery address is AAA-AAAA, AA-cho, AA city, AA City Hall Disaster Response Headquarters," and sends it to the terminal.

[1795] Step 9:

[1796] Users can view the information on the interface and take specific action.

[1797] The above is the "Mode for carrying out the invention" of the chatbot system specialized for disaster relief in this invention. This system realizes the provision of fast and accurate information to disaster victims and those seeking support, and enables responses that take into consideration emotions.

[1798] Example 2

[1799] 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."

[1800] In modern disaster response, it is difficult to provide victims and those seeking assistance with prompt and appropriate information and match them with relief supplies. Disaster sites, in particular, require appropriate responses amidst emotional turmoil. Conventional systems often lack consideration for emotions, resulting in low user satisfaction. Furthermore, efficient matching of relief supplies by volunteers is also lacking.

[1801] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting the latest disaster information and support needs information from databases of administrative agencies, local agencies, and government agencies; means for saving the collected data in an internal database; interface means for users to input questions and support requests; means for analyzing the user's input and generating an appropriate answer using a generative AI model; means for analyzing the user's emotional state and adjusting the tone and expression of the generated answer using an emotion engine; means for providing the generated answer to the user; means for volunteers to upload images and inventory lists of relief supplies; means for analyzing the uploaded supply information and comparing it with current needs information for specific regions and municipalities; and means for presenting appropriate supply destinations based on the comparison results. This allows users to receive fast and accurate information that takes emotions into consideration, and also enables volunteers to efficiently match relief supplies.

[1802] "Administrative, local and governmental agencies" refers to central administrative agencies, local governments and local community organizations that manage and provide disaster information and assistance needs information.

[1803] "Database" refers to a collection of digital data for systematically collecting, storing, and managing disaster information and assistance needs information.

[1804] "Internal Database" means a dedicated database managed for temporary or long-term storage of collected data and for use in analysis and query.

[1805] "Interface means" refers to the interactive user interface through which a user inputs information and receives information from the system.

[1806] "Generative AI model" refers to an artificial intelligence model used to analyze user input and generate appropriate responses.

[1807] An "emotion engine" is an engine that has the ability to analyze the emotional state of a user's input and adjust the tone and expression of the answers it generates based on the results.

[1808] "Relief supplies" refers to goods and resources provided as support to disaster-stricken areas.

[1809] "Analysis" refers to the process of breaking down collected data or uploaded information and converting it into an understandable format.

[1810] "Current needs information" refers to information regarding the support needs and shortages of supplies that specific regions and local governments are currently facing.

[1811] "Delivery information" refers to the specific address and contact information for sending relief supplies.

[1812] "System" refers to a collection of hardware and software for integrally managing and executing a series of functions provided by the present invention.

[1813] The present invention is a system that responds quickly and accurately to victims and those seeking assistance in the event of a large-scale disaster. This system collects disaster information and assistance needs information from databases of administrative agencies, local organizations, and government agencies, and combines a generative AI model and an emotion engine to provide users with appropriate information and assistance. An embodiment of the present invention is described in detail below.

[1814] System Overview

[1815] This system consists of the following main components:

[1816] 1. Data Collection Unit: This unit accesses the databases of administrative agencies, local agencies and government agencies to collect the latest disaster information and assistance needs information.

[1817] 2. Database unit: This unit stores the collected data and maintains the temporary database required for analysis.

[1818] 3. User interface unit: This unit provides an interface through which users can input their questions or requests for assistance.

[1819] 4. Generative AI model unit: This unit contains an AI model for analyzing user input and generating appropriate answers.

[1820] 5. Emotion Engine Unit: This unit analyzes emotions from user input and adjusts the tone and expression of the generated answers based on the results.

[1821] 6. Matching Unit: This unit analyzes information about relief supplies uploaded by volunteers and matches it with information about the needs of specific regions and municipalities.

[1822] 7. Answer providing unit: This unit provides answers to users based on the analysis results.

[1823] About program processing

[1824] Data Collection Phase

[1825] The server obtains the latest disaster and assistance needs information through APIs from administrative, local, and government agencies. This data is parsed into an appropriate format and stored in an internal database. For example, it sends an HTTP request to the API endpoint of the Cabinet Office disaster response site and parses the returned JSON data.

[1826] User Interface Phase

[1827] Users access the chatbot from their devices (smartphones or PCs) and ask questions about disaster information or input their desired assistance. For example, a user might input, "Where is the nearest evacuation shelter?"

[1828] The device sends the user's input to the server. The sent data is passed to the generative AI model and emotion engine unit. Specifically, the device sends data to the server via an Ajax request by pressing the submit button on the form.

[1829] The server uses the emotion engine unit to analyze the user's emotional state, and based on the analyzed emotion data, provides additional information for the generative AI model unit to generate the optimal answer.

[1830] Answer provision phase

[1831] The server then sends the generated answer to the user's device. The tone and expression of the answer are adjusted based on the information analyzed by the emotion engine. For example, the answer text might be something like, "The nearest evacuation shelter is AA Elementary School. Don't worry."

[1832] The device displays the generated answer on the user interface, allowing users to not only get the information they need through the chatbot, but also receive emotionally sensitive responses.

[1833] Specific examples

[1834] Specific examples for disaster victims

[1835] 1. The user types "Where is the nearest evacuation shelter?" into the device.

[1836] 2. The device sends the question data to the server.

[1837] 3. The server retrieves the latest evacuation shelter information from the database and uses the generative AI model and emotion engine to respond, "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA-shi."

[1838] 4. The server generates a response and sends it to the terminal, where the user can view the response on the interface.

[1839] Specific examples for volunteers

[1840] 1. The user types into the chatbot on their device, "I'd like to send 50 boxes of diapers. Where do I need them?"

[1841] 2. The device sends the question data to the server.

[1842] 3. The chatbot prompts the user to "upload an image of diapers or an inventory list."

[1843] 4. User uploads images and inventory list.

[1844] 5. The device sends the upload data to the server.

[1845] 6. Generative AI models and emotion engines analyze images and lists.

[1846] 7. The server compares the analysis results with the assistance needs database and identifies the necessary destination.

[1847] 8. The server generates a response saying, "AA City Hall currently needs diapers. The delivery address is AAA-AAAA, AA-cho, AA City, AA City Hall Disaster Response Headquarters." and sends it to the terminal.

[1848] 9. Users can view the information on the interface and take specific action.

[1849] The above is the "Mode for carrying out the invention" of the chatbot system specialized for disaster relief in this invention. This system makes it possible to provide quick and accurate information to disaster victims and those seeking support while taking into consideration their feelings.

[1850] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1851] Step 1: Collect data

[1852] The server calls the API of a government agency, local agency, or government organization. For example, it sends an HTTP request to the API endpoint of the Cabinet Office disaster response site.

[1853] Parse the raw data returned by the server. Analyze the JSON format data and extract the necessary items (e.g., shelter address and emergency contact information).

[1854] The server stores the parsed data in an internal database, and then inserts the data into a table using a database management system (e.g., PostgreSQL).

[1855] Input: JSON data returned from government API

[1856] Output: Parsed data stored in an internal database

[1857] Step 2: Accept user access

[1858] Users access the chatbot from their smartphone or PC by accessing a dedicated URL or launching a dedicated app.

[1859] Input: User's access request

[1860] Output: Chatbot launch and interface display

[1861] Step 3: Accepting user questions

[1862] The user inputs a question or request for assistance through the device interface, for example, "Where is the nearest evacuation center?"

[1863] The terminal sends the user's input data to the server. By pressing the submit button on the form, the data is sent to the server via an Ajax request.

[1864] Input: User's question or request for assistance

[1865] Output: The input data sent to the server

[1866] Step 4: Sentiment Analysis

[1867] The server passes the received data to the emotion engine, which uses NLP models to analyze the text data and identify the user's emotional state.

[1868] The emotion engine analyzes the emotional tone of the user's input text and determines, for example, "high stress."

[1869] Input: User-entered text

[1870] Output: Analyzed emotion data (e.g., high stress)

[1871] Step 5: Generate an answer

[1872] The generative AI model generates the optimal answer based on the analyzed emotional data. For example, if the user is in great distress, it will generate a more thoughtful and reassuring answer. The answer text might be something like, "The nearest evacuation shelter is AA Elementary School. Please rest assured."

[1873] Input: Analyzed emotion data and user questions

[1874] Output: Generated answer text

[1875] Step 6: Provide your answers

[1876] The server sends the generated answer to the device for delivery to the user, and sends the answer text to the device in an HTTP response.

[1877] The device displays the generated answer on the user interface, and the answer text is automatically displayed in the display area for the user to see.

[1878] Input: Generated answer text

[1879] Output: The answer displayed on the interface

[1880] Step 7: Upload your supplies

[1881] The user uploads an image or inventory list of relief supplies from their device and sends it using the "Upload" button.

[1882] The device sends the uploaded data to the server as an HTTP POST request.

[1883] Input: Images or inventory list of relief supplies

[1884] Output: Upload data sent to the server

[1885] Step 8: Analyze material data

[1886] The server passes the uploaded material data to the generative AI model, which then transfers it to the analysis endpoint and begins analysis.

[1887] A generative AI model uses image recognition technology and text analysis to identify the type and quantity of supplies.

[1888] Input: Uploaded material data

[1889] Output: Analyzed material information (type and quantity)

[1890] Step 9: Matching with needs information

[1891] The server compares the analysis results with the support needs database, and matches the required supply data with the support needs by executing a search query.

[1892] Input: Parsed material information

[1893] Output: Matching results with the needs database

[1894] Step 10: Generate and provide shipping information

[1895] The server generates appropriate delivery address information for the goods, for example, "AA City Hall, 〒AAA-AAAA."

[1896] The server sends the destination information to the terminal, which then sends the destination data to the terminal as an HTTP response.

[1897] The terminal displays the information in the user interface. The delivery information is automatically displayed in the display area.

[1898] Input: Matching result

[1899] Output: Shipping information displayed on the terminal

[1900] These are the specific processing steps of this system's program. This allows users to receive prompt and accurate information that takes their emotions into consideration, and also enables efficient matching of relief supplies by volunteers.

[1901] (Application example 2)

[1902] 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."

[1903] The lack of a support system that can respond quickly and accurately to victims and those seeking support during large-scale disasters is an issue. Specifically, there is a lack of appropriate information provision and matching of relief supplies to quickly deliver the food and relief supplies needed by victims. Furthermore, there is a lack of consideration for users' emotions, and psychological support for victims is insufficient.

[1904] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting the latest disaster information and support needs information from databases of administrative agencies, local agencies, and government agencies, means for saving the collected data in an internal database, interface means for users to input questions and support requests, means for analyzing user input and generating appropriate answers using a generative AI model, means for providing the generated answers to users, means for volunteers to upload images and inventory lists of relief supplies, means for analyzing the uploaded supply information and comparing it with current needs information for specific regions or municipalities, means for presenting appropriate supply destinations based on the comparison results, means for analyzing emotions from user input and adjusting the tone and expression of the generated answers based on the results, and means for quickly and accurately delivering food and other items to disaster victims in the event of a disaster. This enables the provision of information and matching of supplies to disaster victims and those seeking support quickly and accurately, and also enables responses that take emotions into consideration.

[1905] "Administrative, local and government agency databases" refers to information systems provided by public agencies that manage and store disaster information and assistance needs information.

[1906] "Data collection instruments" means mechanisms for obtaining required information from administrative, regional and government agency databases.

[1907] "Internal database" refers to data storage for storing collected disaster information and assistance needs information.

[1908] The "interface means" is a user interface through which a user inputs questions or requests for assistance.

[1909] A "generative AI model" is an artificial intelligence algorithm that analyzes user input and generates appropriate answers.

[1910] The "answer providing means" is a system component for providing the generated answer to the user.

[1911] "Supply upload method" refers to the mechanism by which volunteers submit images and inventory lists of supplies to the system.

[1912] The "supply information analysis means" is a mechanism for analyzing information on uploaded relief supplies and comparing it with information on current needs in specific regions or municipalities.

[1913] The "supply delivery destination presentation means" is a system component that notifies volunteers of the appropriate delivery destination for supplies based on the matching results.

[1914] A "sentiment analysis means" is a mechanism for analyzing emotions from user input and adjusting the tone and expression of the generated response based on the results.

[1915] "Delivery support means" is a system component that provides prompt and accurate delivery support for food and other items to disaster victims in the event of a disaster.

[1916] This invention is a system that responds quickly and accurately to victims and those seeking assistance in the event of a large-scale disaster. This system collects disaster information and assistance needs information, and provides appropriate information and assistance by combining a generative AI model and an emotion engine.

[1917] System Overview

[1918] This system consists of the following main components:

[1919] 1. Data collection unit:

[1920] - Access databases of administrative, local and government agencies to collect the latest disaster and assistance needs information.

[1921] 2. Database Unit:

[1922] - Store the collected data and maintain a temporary database for analysis.

[1923] 3. User Interface Unit:

[1924] - Provide an interface for users to enter questions or requests for assistance.

[1925] 4. Generative AI model unit:

[1926] - Includes AI models to analyze user input and generate appropriate answers.

[1927] 5. Emotion Engine Unit:

[1928] - Analyze the sentiment of user input and adjust the tone and wording of the generated answers accordingly.

[1929] 6. Matching Unit:

[1930] - Analyze information about relief supplies uploaded by volunteers and match it with information about the needs of specific regions and municipalities.

[1931] 7. Answer Providing Unit:

[1932] - Providing answers to users based on the analysis results.

[1933] Generating a Program

[1934] A natural language description of the process

[1935] Data collection phase:

[1936] The server retrieves the latest disaster and assistance needs information through APIs from administrative, local, and government agencies. This is achieved by using the Python requests library to retrieve data from the APIs and store it in MongoDB.

[1937] User Interface Phase:

[1938] Users access the app from their devices (smartphones or PCs) and ask questions about disaster information or enter requests for assistance. This data is sent to the server via a RESTful API. The front end is built using JavaScript (React, Vue.js, etc.).

[1939] Linking generative AI models with emotion engines:

[1940] The server uses an emotion engine (such as Azure Cognitive Services' Text Analytics API) to analyze the user's emotional state. The results are fed into a generative AI model (such as OpenAI's GPT-3) to generate an appropriate response. The emotion engine analyzes the user's input and adjusts the tone and expression of the response based on the user's emotional state.

[1941] Answer provision phase:

[1942] The server then provides the generated answer to the user, adjusting the tone and expression of the answer based on the information analyzed by the emotion engine. This data is then sent to the front-end application and displayed on the user interface.

[1943] Specific examples

[1944] 1. Example for disaster victims:

[1945] A user types into a device, "Where is the nearest shelter?"

[1946] The terminal sends the query data to the server, and the server retrieves the latest evacuation shelter information from the database.

[1947] Using a generative AI model and emotion engine, the answer is generated: "The nearest evacuation shelter is AA Elementary School. The address is AA, AA Town, AA City."

[1948] The server generates a response and sends it to the terminal, where the user can view the response on the interface.

[1949] 2. Example for volunteers:

[1950] The user types into the chatbot on their device, "I'd like to send 50 boxes of diapers. Where do I need them?"

[1951] The device sends the question data to the server, and the chatbot prompts the user to upload an image or inventory list.

[1952] Users upload images and inventory lists, and the device sends the data to a server.

[1953] A generative AI model and emotion engine analyze images and lists, and the server compares them with a database of assistance needs to identify the destination.

[1954] The server generates a response saying, "AA City Hall is currently in need of diapers. The delivery address is AAA-AAAA, AA-cho, AA city, AA City Hall Disaster Response Headquarters," and sends it to the terminal.

[1955] Users can view the information on the interface and take specific action.

[1956] Prompt Sentence Examples

[1957] Example for disaster victims: "Where is the nearest evacuation center?"

[1958] Example for volunteers: "I'd like to send 50 boxes of diapers. Where do you need them?"

[1959] This will enable quick and accurate provision of information and matching of supplies to disaster victims and those seeking assistance, and will also enable responses that take into consideration emotions.

[1960] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1961] Step 1:

[1962] The server accesses APIs provided by administrative agencies, local organizations, and government agencies to obtain the latest disaster information and assistance needs information. The data obtained from the API is in JSON format, which is parsed and stored in MongoDB. This allows the latest disaster information and assistance needs information to be accumulated in an internal database.

[1963] Step 2:

[1964] Users access the app from their devices (smartphones or PCs) and input their questions or requests for assistance through the interface. This user-entered data is sent to the server using a RESTful API. The input information is passed to the server in text format.

[1965] Step 3:

[1966] The server performs sentiment analysis on the received user input data using the Text Analytics API of Azure Cognitive Services, identifying the user's emotional state (e.g., joy, anxiety, anger, etc.) and receiving the results in JSON format.

[1967] Step 4:

[1968] Based on the results of the sentiment analysis, the server generates a prompt for a generative AI model (such as OpenAI's GPT-3) and asks for an appropriate answer. The generative AI model generates text that is adapted to the input prompt, and that text is returned to the server as the answer.

[1969] Step 5:

[1970] The server further adjusts the answer received from the generative AI model. Based on the results of the emotion engine, it adjusts the tone and expression of the answer to be more dignified and emotionally relevant. Using this adjusted answer text, it prepares to provide appropriate information to the user.

[1971] Step 6:

[1972] The server returns the adjusted answer to the device via a RESTful API. The device receives this data and displays it on its user interface, where the user can view the generated answer.

[1973] Step 7:

[1974] Volunteers upload images of relief supplies and inventory lists from their devices. The devices then send the uploaded data to the server. The data format is JPEG or PNG for images, and CSV or JSON for lists.

[1975] Step 8:

[1976] The server uses a generative AI model to perform image recognition and text analysis of the uploaded relief supplies, identifying the type and quantity of supplies and matching this with relief needs information in an internal database. As a result of the matching, the required supply information is identified.

[1977] Step 9:

[1978] Based on the matching results, the server generates appropriate delivery information for the goods, including specific contact details and addresses, and sends it to the terminal and displays it on the user interface.

[1979] Step 10:

[1980] The user can check the delivery destination information provided from the terminal and quickly deliver the relief supplies to the specified location.

[1981] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1982] 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.

[1983] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1984] [Fourth embodiment]

[1985] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1986] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1987] 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).

[1988] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1989] 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.

[1990] 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).

[1991] 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.

[1992] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1993] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1994] 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.

[1995] 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.

[1996] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1997] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1998] The present invention is a system for quickly and accurately providing necessary information in the event of a large-scale disaster and supporting the actions of victims and those seeking assistance. This system executes a series of processes to collect, store, analyze, and provide disaster information and assistance needs information to users from databases of administrative agencies, local agencies, and government agencies. An embodiment of the present invention is described in detail below.

[1999] System Overview

[2000] This system consists of the following main components:

[2001] 1. Data Collection Unit: This unit accesses the databases of administrative agencies, local agencies and government agencies to collect the latest disaster information and assistance needs information.

[2002] 2. Database unit: This unit stores the collected data and maintains the temporary database required for analysis.

[2003] 3. User interface unit: This unit provides an interface through which users can input their questions or requests for assistance.

[2004] 4. Generative AI model unit: This unit contains an AI model for analyzing user input and generating appropriate answers.

[2005] 5. Matching Unit: This unit analyzes information about relief supplies uploaded by volunteers and matches it with information about the needs of specific regions and municipalities.

[2006] 6. Answer providing unit: This unit provides answers to users based on the analysis results.

[2007] About program processing

[2008] Data Collection Phase

[2009] The server periodically calls the APIs of administrative agencies and government organizations to obtain the latest disaster information and assistance needs information, and the obtained data is stored in an internal database.

[2010] User Interface Phase

[2011] Users access the chatbot from their device and enter questions about disaster information and requests for assistance.

[2012] The terminal transmits the input data to the server.

[2013] The server passes the received data to the generative AI model and analyzes the content of the user's question.

[2014] The generative AI model analyzes the input question and generates the optimal answer, drawing on the necessary information from the server's database.

[2015] Answer provision phase

[2016] The server sends the answer generated by the generative AI model to the device to provide to the user.

[2017] The terminal displays the generated answers on a user interface.

[2018] Analysis and matching phase of supply support

[2019] The user uploads images or inventory lists of relief supplies from the terminal.

[2020] The terminal transmits the uploaded data to the server.

[2021] The server passes the uploaded material information to the generative AI model and begins analysis.

[2022] The generative AI model uses image recognition technology to identify the type and quantity of supplies.

[2023] The server compares the analysis results with the assistance needs database of administrative and government agencies to identify the appropriate destination.

[2024] Based on the result of the comparison, the server sends specific delivery address information to the terminal to provide to the volunteer.

[2025] The terminal displays the delivery destination information on the user interface.

[2026] Specific examples

[2027] Specific examples for disaster victims

[2028] 1. The user types into the chatbot on their device, "Where is the nearest evacuation shelter?"

[2029] 2. The device sends the query data to the server.

[2030] 3. The server retrieves the latest evacuation shelter information from the database and uses the generative AI model to generate an answer such as, "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA-shi."

[2031] 4. The server sends the generated answer to the device, where the user can view it on the interface.

[2032] Specific examples for volunteers

[2033] 1. The user types into the chatbot on their device, "I'd like to send 50 boxes of diapers. Where do I need them?"

[2034] 2. The device sends the query data to the server.

[2035] 3. The chatbot prompts the user to "upload an image of diapers or an inventory list."

[2036] 4. User uploads images and inventory list.

[2037] 5. The device sends the upload data to the server.

[2038] 6. The generative AI model analyzes the uploaded images and listings.

[2039] 7. The server compares the analysis results with the support needs database and identifies the necessary destination.

[2040] 8. The server generates a response such as "AA City Hall currently needs diapers. The delivery address is AA, AA-cho, AA, AA City, AAA-AAAA, AA City Hall Disaster Response Headquarters," and sends it to the terminal.

[2041] 9. Users can view the information on the interface and take specific action.

[2042] The above is the "Mode for carrying out the invention" of the chatbot system specialized for disaster relief in this invention. This system can provide quick and accurate information to disaster victims and those seeking support, and can significantly improve the efficiency and effectiveness of support activities.

[2043] The processing flow will be explained below.

[2044] Data Collection Phase

[2045] Step 1:

[2046] The server uses APIs to access public databases from government agencies, local authorities, and government agencies, and periodically (for example, every hour) sends requests to designated endpoints to retrieve the latest disaster and relief needs information.

[2047] Step 2:

[2048] The server parses and reads the collected data and extracts the necessary information (shelter information, assistance needs, disaster situation, etc.), which includes parsing the data in JSON and XML formats.

[2049] Step 3:

[2050] The server stores the extracted information in its internal database, overwriting any existing information with the latest information and deleting the old data.

[2051] User Interface Phase

[2052] Step 4:

[2053] Users access chatbots from their devices (smartphones or PCs), specifically by connecting to the chatbot's interface through a web page or dedicated app.

[2054] Step 5:

[2055] The user enters their question or request for assistance into the chatbot's input field.

[2056] Step 6:

[2057] The device sends the user's input data to the server, using the HTTPS communication protocol.

[2058] Step 7:

[2059] The server passes the received input data to the generative AI model and begins analysis. The generative AI model is then passed the user's question and desired assistance.

[2060] Step 8:

[2061] The generative AI model analyzes the input data and generates the best answer, specifically using natural language processing (NLP) techniques to understand the question and generate a corresponding answer.

[2062] Step 9:

[2063] The server sends the answer generated by the generative AI model to the device for return to the user.

[2064] Step 10:

[2065] The device will display the generated answer on the user interface, allowing the user to obtain the information they need through the chatbot.

[2066] Analysis and matching phase of supply support

[2067] Step 11:

[2068] Users upload images or inventory lists of relief supplies from their devices.

[2069] Step 12:

[2070] The device sends the uploaded data to the server.

[2071] Step 13:

[2072] The server passes the uploaded material information (images and text data) to the generative AI model and begins analysis.

[2073] Step 14:

[2074] The generative AI model uses image recognition and text analysis to identify the type and quantity of supplies. Specifically, it analyzes images of supplies and identifies their classification and quantity.

[2075] Step 15:

[2076] The server then compares the analysis results with the support needs databases of administrative and government agencies, comparing the information on needed supplies with current needs and identifying which regions and municipalities need those supplies.

[2077] Step 16:

[2078] The server then uses the results of the match to generate appropriate delivery information for the user, including specific addresses and contact information.

[2079] Step 17:

[2080] The server sends the generated delivery address information to the terminal.

[2081] Step 18:

[2082] The terminal displays the delivery destination information on the user interface, and users can send supplies based on this information.

[2083] This is the specific flow of the program processing for the disaster relief chatbot system. This processing step enables the prompt and accurate provision of information to disaster victims and those seeking support.

[2084] Example 1

[2085] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2086] In the event of a large-scale disaster, rapid and accurate information provision is required, but in conventional systems, information collection and analysis are often done manually, which takes time and effort, and can result in delays in providing appropriate information. Another issue is the inability to respond appropriately in real time to the information and needs of victims and supporters. Furthermore, there is a lack of mechanisms for volunteers to efficiently provide relief supplies. In these situations, a system is needed that can effectively support the actions of victims and those seeking support.

[2087] 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.

[2088] In this invention, the server includes: means for collecting disaster information and support needs information from databases of administrative agencies, local agencies, and government agencies; means for saving the collected data in an internal database; interface means for users to input questions and support requests; means for analyzing the user's input and generating appropriate answers using a generative AI model; means for providing the generated answers to the user; means for volunteers to upload the characteristics and quantities of relief supplies; means for analyzing the uploaded supply information and comparing it with local information; and means for presenting appropriate supply destinations based on the comparison results. This enables disaster victims and those seeking support to receive information quickly and accurately, significantly improving the efficiency and effectiveness of support activities.

[2089] "Administrative agencies" are organizations that provide public services, such as national and local governments.

[2090] "Local organizations" are organizations that carry out disaster response and support activities within local governments and communities.

[2091] "Government agencies" are public organizations such as central government ministries and agencies responsible for national administration.

[2092] A "database" is a collection of information that is structured to make it easy to manage and search.

[2093] "Disaster information" is detailed information about natural and man-made disasters.

[2094] "Support needs information" refers to information about the relief supplies and services needed by disaster-stricken areas and victims in the event of a disaster.

[2095] A "user interface" is the means by which a user interacts with a system.

[2096] A "generative AI model" is a computer program that uses artificial intelligence to analyze user input and generate appropriate answers.

[2097] "Volunteers" are individuals or groups who provide support activities free of charge.

[2098] "Relief supplies" are items such as food, medicine, and clothing provided to victims in the event of a disaster.

[2099] "Regional information" refers to information about the disaster situation and assistance needs in a specific region.

[2100] A "prompt" is text that contains questions or instructions to be input into a generative AI model.

[2101] The present invention provides a system for quickly and accurately providing necessary information during a large-scale disaster and supporting the actions of disaster victims and those seeking assistance. This system executes a series of processes to collect, store, and analyze disaster information and assistance needs information from databases of administrative agencies, local agencies, and government agencies, and provide the information to users. Specific embodiments for implementing the present invention are described in detail below.

[2102] System Overview

[2103] This system consists of the following main components:

[2104] 1. Data Collection Unit: This unit accesses the databases of administrative agencies, local agencies and government agencies to collect the latest disaster information and assistance needs information.

[2105] 2. Database unit: This unit stores the collected data and maintains the temporary database required for analysis. Specifically, a MySQL database is used.

[2106] 3. User interface unit: This unit provides an interface where users can enter questions or requests for assistance. It runs on a web browser.

[2107] 4. Generative AI model unit: This unit contains an AI model for analyzing user input and generating appropriate answers. Generative AI models such as GPT-3 are used.

[2108] 5. Matching Unit: This unit analyzes information about relief supplies uploaded by volunteers and matches it with information about the needs of specific regions and municipalities.

[2109] 6. Answer providing unit: This unit provides answers to users based on the analysis results.

[2110] About program processing

[2111] Data Collection Phase

[2112] The server periodically calls the APIs of government agencies and organizations to obtain the latest disaster and relief needs information. It connects to the API using Python's requests library and retrieves data in JSON format. The retrieved data is then stored in a MySQL database using Python's MySQL Connector.

[2113] User Interface Phase

[2114] A user accesses the chatbot from their device via a web browser and inputs a question or request for assistance. For example, they might input, "Where is the nearest evacuation shelter?" The device sends the input data to the server using WebSocket or an HTTP request. The server processes the received request using a web framework such as Flask and passes the prompt text to the generative AI model.

[2115] For example: "Where is the nearest shelter?"

[2116] Analysis of generative AI models

[2117] A generative AI model (e.g., GPT-3) analyzes the prompt sentence and generates an appropriate answer. In the analysis process, the necessary information is retrieved from the database using a SELECT statement, and an answer such as "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA, AA City" is generated.

[2118] Answer provision phase

[2119] The server sends the answers generated by the generative AI model to the device, which then displays the received answers on a web browser, allowing the user to view the information in real time.

[2120] Analysis and matching phase of supply support

[2121] The user uploads images of relief supplies and an inventory list. For example, they might type, "I'd like to send 50 boxes of diapers. Where do they need them?" and upload images of the supplies. The device then sends the uploaded file to the server via HTTP POST. The server saves the file in a temporary storage area and analyzes the image using Python's Pillow library or similar. The generative AI model uses TensorFlow or PyTorch to identify the supply data from the image, compares it with a MySQL database, and then generates specific delivery address information, such as, "AA City Hall is currently in need of diapers. The delivery address is AAA-AAAA, AA Town, AA City, AA City Hall Disaster Response Headquarters."

[2122] Specific examples

[2123] Specific examples for victims:

[2124] 1. User types, "Where is the nearest shelter?"

[2125] 2. The device sends the information to the server.

[2126] 3. The server retrieves the appropriate evacuation shelter information from the database and generates the information "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA-shi." through the generative AI model.

[2127] 4. The server sends the generated answer to the device, and the user views the information in the browser.

[2128] Examples for volunteers:

[2129] 1. A user types into the chatbot, "I'd like to send 50 boxes of diapers. Where do they need to go?"

[2130] 2. The device sends the information to the server.

[2131] 3. The chatbot will prompt you to "Upload an image of your diapers or an inventory list."

[2132] 4. The user uploads the image.

[2133] 5. The device sends the data to the server.

[2134] 6. The generative AI model analyzes the image to identify the type and quantity of supplies.

[2135] 7. The server identifies the appropriate delivery address based on the matching results and generates the information, "AA City Hall currently needs diapers. The delivery address is AAA-AAAA, AA-cho, AA City, AA City Disaster Response Headquarters."

[2136] 8. Users can view the information in their browser and take specific action.

[2137] The above is the specific processing and operation of the embodiment of the present invention. This system enables quick and accurate provision of information and support to disaster victims and those seeking support, significantly improving the efficiency and effectiveness of support activities.

[2138] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2139] Program processing steps

[2140] Step 1:

[2141] The server periodically calls the API of the administrative agency or government institution.

[2142] Input: API endpoint

[2143] Data processing: Use the Python requests library to connect to the API and retrieve data in JSON format.

[2144] Output: Retrieved JSON data

[2145] Specific behavior:

[2146] The server accesses the API endpoint using the requests.get() method and extracts the JSON data from the response object.

[2147] Step 2:

[2148] The server stores the acquired data in an internal database.

[2149] Input: JSON data

[2150] Data processing: Analyze the data to extract important information and store it in a MySQL database using INSERT statements.

[2151] Output: Disaster information and assistance needs information stored in a database

[2152] Specific behavior:

[2153] The server converts the JSON data into a dictionary using the json.loads() method, connects to the database using the MySQL Connector, and issues an INSERT statement using the cursor.execute() method.

[2154] Step 3:

[2155] The user accesses the chatbot from their device and enters their question or the assistance they would like.

[2156] Input: Question or request for assistance (e.g., "Where is the nearest evacuation center?")

[2157] Data processing: User input is obtained using HTML forms or JavaScript.

[2158] Output: Question data

[2159] Specific behavior:

[2160] The user accesses the chatbot's UI on a web browser, enters a question in the text box, and clicks the send button.

[2161] Step 4:

[2162] The terminal transmits the input data to the server.

[2163] Input: Question data

[2164] Data processing: Send the question data to the server as a WebSocket or HTTP POST request.

[2165] Output: The query data passed to the server

[2166] Specific behavior:

[2167] The device sends data to the server using the JavaScript fetch() method or the WebSocket.send() method.

[2168] Step 5:

[2169] The server passes the received data to the generative AI model for analysis.

[2170] Input: Question data

[2171] Data processing: The question data is passed to a generative AI model (e.g., GPT-3) as a prompt.

[2172] Output: The answer parsed by the generative AI model

[2173] Specific behavior:

[2174] The server uses Flask to process incoming requests and send them to the API of the generative AI model.

[2175] Step 6:

[2176] The generative AI model analyzes the input question and generates an appropriate answer.

[2177] Input: prompt statement

[2178] Data processing: Analyzes the prompt statement, retrieves the necessary information from the database using a SELECT statement, and generates an answer.

[2179] Output: The generated answer

[2180] Specific behavior:

[2181] The generative AI model receives the API request and generates an answer using its internal algorithm. The server receives the result and processes it again.

[2182] Step 7:

[2183] The server sends the answer generated by the generative AI model to the user's device.

[2184] Input: Generated answer

[2185] Data processing: The generated answer is sent to the device as an HTTP or WebSocket response.

[2186] Output: Answer data sent to the device

[2187] Specific behavior:

[2188] The server uses Flask's response object to generate the answer and send it back to the device.

[2189] Step 8:

[2190] The terminal displays the generated answer on a user interface.

[2191] Input: Generated response data

[2192] Data processing: The received data is formatted for display using HTML and JavaScript.

[2193] Output: The answer displayed in the user interface

[2194] Specific behavior:

[2195] The terminal uses JavaScript DOM manipulation methods to dynamically display the received response data on a web page.

[2196] Step 9:

[2197] Users upload images of relief supplies and inventory lists from their devices.

[2198] Input: Images and inventory list of relief supplies

[2199] Data processing: Taking user input from forms and uploading files.

[2200] Output: Uploaded file data

[2201] Specific behavior:

[2202] The user selects an image or list using a file input form on a web browser and clicks the upload button.

[2203] Step 10:

[2204] The device sends the uploaded data to the server.

[2205] Input: File data

[2206] Data processing: Send the file data to the server as an HTTP POST request.

[2207] Output: File data passed to the server

[2208] Specific behavior:

[2209] The device uses the JavaScript fetch() method to send the file data to the server.

[2210] Step 11:

[2211] The server passes the uploaded material information to the generative AI model and begins analysis.

[2212] Input: File data

[2213] Data processing: Save the file to a temporary storage area and read the data using the image analysis library.

[2214] Output: Image data or list data for analysis

[2215] Specific behavior:

[2216] The server uses an image analysis library such as Pillow or performs direct text analysis.

[2217] Step 12:

[2218] The generative AI model uses image recognition technology to identify the type and quantity of supplies.

[2219] Input: Image data or list data

[2220] Data processing: Image analysis algorithms are used to identify material information and count quantities.

[2221] Output: Identified material data

[2222] Specific behavior:

[2223] The generative AI model uses TensorFlow or PyTorch to analyze images and identify the type and quantity of supplies.

[2224] Step 13:

[2225] The server compares the analysis results with a database of assistance needs and identifies the appropriate destination.

[2226] Input: Identified material data

[2227] Data processing: Database matching is performed to find the optimal delivery destination.

[2228] Output: Proper shipping information

[2229] Specific behavior:

[2230] The server runs a SELECT statement against the MySQL database to match the needs data with the supplies data.

[2231] Step 14:

[2232] Based on the matching results, the server provides the terminal with the appropriate delivery address for the supplies.

[2233] Enter the appropriate shipping information

[2234] Data processing: The destination information is formatted in a user-friendly format and sent as an HTTP response.

[2235] Output: Shipping information sent to the terminal

[2236] Specific behavior:

[2237] The server uses Flask's response object to send the destination information to the terminal.

[2238] Step 15:

[2239] The terminal displays the delivery information on the user interface.

[2240] Input: Shipping information

[2241] Data processing: The received information is formatted for display using HTML and JavaScript.

[2242] Output: Shipping information displayed on the user interface

[2243] Specific behavior:

[2244] The terminal uses JavaScript DOM manipulation methods to dynamically display the delivery information on a web page.

[2245] (Application example 1)

[2246] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2247] When a large-scale disaster occurs, it is difficult for victims and those seeking aid to quickly and accurately obtain the information they need. Furthermore, insufficient management of relief supplies and matching of appropriate delivery destinations reduces the efficiency and effectiveness of relief activities. Conventional systems have limited user interfaces and make it difficult to respond in real time, making it difficult to provide disaster information immediately.

[2248] 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.

[2249] In this invention, the server includes: means for collecting the latest disaster information and assistance needs information from databases of administrative agencies, local agencies, and national agencies; means for storing the collected data in an internal database; interface means for users to input questions and assistance requests; means for analyzing user input and generating appropriate answers using a generative AI model; means for providing the generated answers to users; means for volunteers to upload images of relief supplies and inventory lists; means for analyzing the uploaded supply information and comparing it with current needs information for specific regions and municipalities; means for presenting appropriate supply destinations based on the comparison results; means for providing responses in real time based on user input information and questions; and means for providing evacuation center information and emergency contact information via a smartphone application. This allows disaster victims and assistance seekers to quickly and accurately obtain information, improving the efficiency and effectiveness of assistance activities.

[2250] "Administrative agencies" refer to public institutions such as national and local governments and similar organizations.

[2251] A "local agency" is an agency or organization that provides public services or functions in a particular geographic area.

[2252] "Government agencies" refer to various agencies of the central government responsible for the administration of the country.

[2253] A "database" is a mechanism or system for systematically storing and managing digital information.

[2254] "Disaster information" refers to information such as forecasts, occurrence status, damage status, and response measures regarding emergencies such as natural disasters and accidents.

[2255] "Support needs information" refers to information on specific needs, such as relief supplies, services, and information, required by disaster-stricken areas and disaster victims.

[2256] An "interface" refers to the operation screen, input means, and output means that users use to use a system.

[2257] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and automatically generate answers to user questions.

[2258] An "answer" is information or instructions provided in response to a user's question.

[2259] "Volunteers" are individuals or groups who voluntarily engage in activities such as disaster relief and social contribution.

[2260] "Supply information" refers to specific information such as the type and quantity of relief supplies provided.

[2261] "Verification" is the process of comparing information to see if it matches.

[2262] "Destination" refers to the place where supplies, information, etc. should be delivered or the recipient.

[2263] "Real-time" refers to information processing and system response occurring immediately and without delay.

[2264] A "smartphone application" is a software program that runs on a smartphone.

[2265] "Evacuation shelter information" refers to information about facilities and locations for evacuation in the event of a disaster.

[2266] "Emergency contact information" refers to contact information for use in the event of a disaster or emergency.

[2267] This invention relates to a system that provides necessary information quickly and accurately in the event of a large-scale disaster, and supports the actions of victims and those seeking assistance. This system is composed of the following main components:

[2268] Data Acquisition Unit

[2269] The server periodically accesses the databases of administrative agencies, local agencies, and government agencies to collect the latest disaster information and assistance needs information, which is then stored in an internal database.

[2270] Database Unit

[2271] The server's internal database stores collected disaster and assistance needs information, and is updated in real time to enable prompt responses to user questions and requests.

[2272] User Interface Unit

[2273] Users access the system using a smartphone application, which provides an interface for inputting questions about disaster information and requests for assistance.

[2274] Generative AI Model Unit

[2275] The server analyzes the user's input data using a generative AI model, such as OpenAI's GPT-3, to generate an appropriate answer. The generated answer is then provided to the user by the server.

[2276] Answer Providing Unit

[2277] The server provides the answers generated by the generative AI model to the user through a smartphone application, allowing the user to obtain the information they need in real time.

[2278] Logistics Support Analysis and Matching Unit

[2279] When users upload images of relief supplies and inventory lists, the server analyzes this data and compares it with information on relief needs. TensorFlow is used for image recognition technology. Based on the results of the comparison, the server identifies the appropriate delivery address for the supplies and presents it to the user.

[2280] Examples:

[2281] Specific examples for victims:

[2282] 1. The user types "Where is the nearest evacuation shelter?" into the smartphone application.

[2283] 2. The application sends the query data to the server.

[2284] 3. The server retrieves the latest evacuation shelter information from the database and uses the generative AI model to generate an answer such as, "The nearest evacuation shelter is AA Elementary School. The address is AA, AA-cho, AA-shi."

[2285] 4. The server sends the generated answer to the application, where the user can view it on the interface.

[2286] Examples for volunteers:

[2287] 1. A user types in a smartphone application, "I'd like to send 50 boxes of diapers. Where do I need them?"

[2288] 2. The application sends the query data to the server.

[2289] 3. The chatbot instructs the user to "upload an image of diapers or an inventory list."

[2290] 4. User uploads images and inventory list.

[2291] 5. The application sends the upload data to the server.

[2292] 6. The generative AI model analyzes the uploaded images and listings.

[2293] 7. The server compares the analysis results with the support needs database and identifies the necessary destination.

[2294] 8. The server generates a response such as "AA City Hall currently needs diapers. The delivery address is AA, AA-cho, AA, AA City, AAA-AAAA, AA City Hall Disaster Response Headquarters." and sends it to the application.

[2295] 9. Users can view the information on the interface and take specific action.

[2296] Hardware and software used:

[2297] Server: Cloud server (e.g. Google Cloud, AWS EC2)

[2298] Software: Python, Firebase Admin SDK, React Native, Django, OpenAI API, TensorFlow

[2299] Device: Smartphone

[2300] Example prompt sentence:

[2301] "Where is the nearest shelter?"

[2302] "I'd like to send 50 boxes of diapers. Where do you need them?"

[2303] Please tell me the current disaster situation.

[2304] "I would like to know the list of relief supplies in demand."

[2305] The above is an embodiment of the present invention. This system makes it possible to provide quick and accurate information to disaster victims and those seeking support, significantly improving the efficiency and effectiveness of support activities.

[2306] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2307] Step 1:

[2308] The server periodically calls the APIs of administrative agencies, local agencies, and government agencies to obtain the latest disaster information ...

Claims

1. A means of collecting up-to-date disaster and assistance needs information from administrative, local and government databases; a means for storing the collected data in an internal database; an interface means for a user to input a question or request for assistance; A means of analyzing user input and generating appropriate answers using a generative AI model; a means for providing the generated answer to the user; A way for volunteers to upload images and inventory lists of relief supplies, A means to analyze the uploaded supply information and compare it with the current needs information of specific regions and municipalities, A means for suggesting an appropriate delivery destination for the goods based on the matching result; A system including:

2. The system of claim 1, wherein the generative AI model identifies the type and quantity of relief supplies using image recognition technology.

3. 10. The system of claim 1, wherein the user interface answers questions from the user in real time.

Images